CN112070510A - A method and equipment for detecting substandard goods based on blockchain - Google Patents

Abstract

Translated fromChinese

本申请的目的是提供一种基于区块链的检测不合格商品的方法，该方法包括：向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息；获得知识图谱对应的连接关系特征信息；根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。

The purpose of this application is to provide a blockchain-based method for detecting unqualified commodities, the method comprising: sending a model acquisition request to the blockchain, and receiving the commodity detection returned by the blockchain according to the model acquisition request The model and the model data information corresponding to the commodity detection model and the first commodity calibration information; obtain the connection relationship feature information corresponding to the knowledge graph; determine the second commodity calibration according to the model data increment information and the first commodity calibration information information, update the commodity detection model according to the model data information, the model data increment information, the connection relationship feature information and the second commodity calibration information, and determine the need to upload according to the model data increment information to the model data update information of the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain.

Description

Translated fromChinese

一种基于区块链的检测不合格商品的方法与设备A method and equipment for detecting substandard goods based on blockchain

技术领域technical field

本申请涉及通信领域，尤其涉及一种用于基于区块链的检测不合格商品的技术。The present application relates to the field of communications, and in particular, to a technology for detecting unqualified commodities based on blockchain.

背景技术Background technique

随着科技的进步和社会的发展，网络与我们的生活越来越密切，网络购物方式已被大多数人所接受，但是，网络购物中存在很多假冒伪劣商品和违禁商品，人们很难去做判断。现有技术中，通常只能人工标注假冒伪劣商品和违禁商品，然而若商品描述变化频繁，则很难检测到，且该方式需要花费极大的人力成本和时间成本，针对上述问题，现有技术中每个公司可能会建立自己的知识图谱模型，来检查假冒伪劣商品和违禁商品，然而，各个公司所建立的知识图谱是互相独立的，且由于每个公司的训练数据非常有限，使得所建立的知识图谱模型的检测准确性较低。With the advancement of technology and the development of society, the Internet has become more and more closely related to our lives, and online shopping has been accepted by most people. However, there are many counterfeit and shoddy goods and prohibited goods in online shopping, and it is difficult for people to do it. judge. In the prior art, it is usually only possible to manually mark fake and shoddy goods and prohibited goods. However, if the description of the goods changes frequently, it is difficult to detect, and this method requires great labor and time costs. In view of the above problems, the existing Each company in the technology may establish its own knowledge graph model to check counterfeit and shoddy goods and prohibited goods. However, the knowledge graphs established by each company are independent of each other, and each company has very limited training data. The detection accuracy of the established knowledge graph model is low.

发明内容SUMMARY OF THE INVENTION

本申请的一个目的是提供一种基于区块链的检测不合格商品的方法与设备。An object of this application is to provide a method and device for detecting unqualified commodities based on blockchain.

根据本申请的一个方面，提供了一种基于区块链的检测不合格商品的方法，该方法包括：According to one aspect of the present application, there is provided a blockchain-based method for detecting unqualified commodities, the method comprising:

向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；Send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, as well as model data information and first commodity calibration information corresponding to the commodity detection model, wherein the model The data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information, and the first commodity calibration information is used to demarcate whether each commodity in the plurality of commodities is Substandard goods;

获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；Obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, the knowledge graph includes a plurality of nodes, and each of the knowledge graphs The node corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent each node in the knowledge graph connection between;

根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；The second commodity calibration information is determined according to the model data increment information and the first commodity calibration information, and the second commodity calibration information is determined according to the model data information, the model data increment information, the connection relationship feature information and the second commodity Calibration information, update the commodity detection model;

根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。According to the model data increment information, determine the model data update information that needs to be uploaded to the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain.

根据本申请的一个方面，提供了一种基于区块链的检测不合格商品的网络设备，该设备包括：According to an aspect of the present application, a blockchain-based network device for detecting unqualified commodities is provided, the device comprising:

一一模块，用于向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；A module is used to send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, as well as model data information and first commodity calibration information corresponding to the commodity detection model. , wherein the model data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information, and the first commodity calibration information is used to calibrate the plurality of commodities Whether each of the products is a non-conforming product;

一二模块，用于获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；The first and second modules are used to obtain the feature information of the connection relationship corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, the knowledge graph includes a plurality of nodes, and the Each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent the The connection relationship between each node in the knowledge graph;

一三模块，用于根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；One and three modules are used to determine the second commodity calibration information according to the model data increment information and the first commodity calibration information, and according to the model data information, the model data increment information, and the connection relationship feature information and the second commodity calibration information to update the commodity detection model;

一四模块，用于根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。The first four modules are used to determine the model data update information that needs to be uploaded to the blockchain according to the model data increment information, and upload the updated commodity detection model and the model data update information to the district blockchain.

根据本申请的一个方面，提供了一种基于区块链的检测不合格商品的设备，其中，该设备包括：According to one aspect of the present application, a blockchain-based device for detecting unqualified commodities is provided, wherein the device includes:

处理器；以及processor; and

被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器执行如下操作：memory arranged to store computer-executable instructions which, when executed, cause the processor to:

向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；Send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, as well as model data information and first commodity calibration information corresponding to the commodity detection model, wherein the model The data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information, and the first commodity calibration information is used to demarcate whether each commodity in the plurality of commodities is Substandard goods;

获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；Obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, the knowledge graph includes a plurality of nodes, and each of the knowledge graphs The node corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent each node in the knowledge graph connection between;

根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；The second commodity calibration information is determined according to the model data increment information and the first commodity calibration information, and the second commodity calibration information is determined according to the model data information, the model data increment information, the connection relationship feature information and the second commodity Calibration information, update the commodity detection model;

根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。According to the model data increment information, determine the model data update information that needs to be uploaded to the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain.

根据本申请的一个方面，提供了一种存储指令的计算机可读介质，所述指令在被执行时使得系统进行如下操作：According to one aspect of the present application, there is provided a computer-readable medium storing instructions that, when executed, cause a system to:

向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；Send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, as well as model data information and first commodity calibration information corresponding to the commodity detection model, wherein the model The data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information, and the first commodity calibration information is used to demarcate whether each commodity in the plurality of commodities is Substandard goods;

获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；Obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, the knowledge graph includes a plurality of nodes, and each of the knowledge graphs The node corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent each node in the knowledge graph connection between;

根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；The second commodity calibration information is determined according to the model data increment information and the first commodity calibration information, and the second commodity calibration information is determined according to the model data information, the model data increment information, the connection relationship feature information and the second commodity Calibration information, update the commodity detection model;

根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。According to the model data increment information, determine the model data update information that needs to be uploaded to the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain.

与现有技术相比，本申请能够通过向区块链请求商品检测模型及模型数据信息等相关信息，并根据模型数据增量信息来建立知识图谱，进而通过训练更新商品检测模型，并将更新后的商品检测模型上传至区块链，从而能够实现不同公司来共同维护并更新商品检测模型，可以提高商品检测模型检测违禁假冒商品的准确性，能够大大减少每个公司在单独训练生成商品检测模型过程中的训练成本。Compared with the prior art, the present application can request relevant information such as the commodity detection model and model data information from the blockchain, and establish a knowledge map according to the incremental information of the model data, and then update the commodity detection model through training, and update the product detection model. The resulting commodity detection model is uploaded to the blockchain, so that different companies can jointly maintain and update the commodity detection model, which can improve the accuracy of the commodity detection model to detect prohibited and counterfeit commodities, and can greatly reduce the need for each company to generate commodity detection through separate training. The training cost of the model process.

附图说明Description of drawings

通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

图1示出根据本申请一个实施例的一种基于区块链的检测不合格商品的方法流程图；FIG. 1 shows a flowchart of a method for detecting unqualified commodities based on blockchain according to an embodiment of the present application;

图2示出根据本申请一个实施例的一种基于区块链的构建知识图谱的方法流程图；FIG. 2 shows a flowchart of a method for building a knowledge graph based on blockchain according to an embodiment of the present application;

图3示出根据本申请一个实施例的一种基于区块链的更新商品检测模型的方法流程图；3 shows a flowchart of a method for updating a commodity detection model based on a blockchain according to an embodiment of the present application;

图4示出根据本申请一个实施例的一种基于区块链的检测不合格商品的网络设备结构图；Fig. 4 shows a block chain-based network device structure diagram for detecting unqualified commodities according to an embodiment of the present application;

图5示出可被用于实施本申请中所述的各个实施例的示例性系统。FIG. 5 illustrates an exemplary system that may be used to implement various embodiments described in this application.

附图中相同或相似的附图标记代表相同或相似的部件。The same or similar reference numbers in the drawings represent the same or similar parts.

具体实施方式Detailed ways

下面结合附图对本申请作进一步详细描述。The present application will be described in further detail below with reference to the accompanying drawings.

在本申请一个典型的配置中，终端、服务网络的设备和可信方均包括一个或多个处理器(例如，中央处理器(Central Processing Unit，CPU))、输入/输出接口、网络接口和内存。In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party all include one or more processors (for example, a central processing unit (CPU)), an input/output interface, a network interface, and Memory.

内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RandomAccess Memory，RAM)和/或非易失性内存等形式，如只读存储器(Read Only Memory，ROM)或闪存(Flash Memory)。内存是计算机可读介质的示例。The memory may include non-persistent memory in computer readable media, random access memory (Random Access Memory, RAM) and/or non-volatile memory, such as read only memory (Read Only Memory, ROM) or flash memory (Flash). Memory). Memory is an example of a computer-readable medium.

计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(Phase-Change Memory，PCM)、可编程随机存取存储器(Programmable Random Access Memory，PRAM)、静态随机存取存储器(Static Random-Access Memory，SRAM)、动态随机存取存储器(Dynamic Random AccessMemory，DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(Electrically-Erasable Programmable Read-Only Memory，EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、数字多功能光盘(Digital Versatile Disc,DVD)或其他光学存储、磁盒式磁带，磁带磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (Phase-Change Memory, PCM), programmable random access memory (Programmable Random Access Memory, PRAM), static random access memory (Static Random-Access Memory, SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (Electrically-Erasable Programmable Read- Only Memory (EEPROM), flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

本申请所指设备包括但不限于用户设备、网络设备、或用户设备与网络设备通过网络相集成所构成的设备。所述用户设备包括但不限于任何一种可与用户进行人机交互(例如通过触摸板进行人机交互)的移动电子产品，例如智能手机、平板电脑等，所述移动电子产品可以采用任意操作系统，如Android操作系统、iOS操作系统等。其中，所述网络设备包括一种能够按照事先设定或存储的指令，自动进行数值计算和信息处理的电子设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific IntegratedCircuit，ASIC)、可编程逻辑器件(Programmable Logic Device，PLD)、现场可编程门阵列(Field Programmable Gate Array，FPGA)、数字信号处理器(Digital Signal Processor，DSP)、嵌入式设备等。所述网络设备包括但不限于计算机、网络主机、单个网络服务器、多个网络服务器集或多个服务器构成的云；在此，云由基于云计算(Cloud Computing)的大量计算机或网络服务器构成，其中，云计算是分布式计算的一种，由一群松散耦合的计算机集组成的一个虚拟超级计算机。所述网络包括但不限于互联网、广域网、城域网、局域网、VPN网络、无线自组织网络(Ad Hoc网络)等。优选地，所述设备还可以是运行于所述用户设备、网络设备、或用户设备与网络设备、网络设备、触摸终端或网络设备与触摸终端通过网络相集成所构成的设备上的程序。The equipment referred to in this application includes, but is not limited to, user equipment, network equipment, or equipment formed by integrating user equipment and network equipment through a network. The user equipment includes, but is not limited to, any mobile electronic product that can perform human-computer interaction with the user (for example, human-computer interaction through a touchpad), such as a smart phone, a tablet computer, etc., and the mobile electronic product can use any operation. system, such as Android operating system, iOS operating system, etc. The network device includes an electronic device that can automatically perform numerical calculation and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC) , Programmable Logic Device (PLD), Field Programmable Gate Array (Field Programmable Gate Array, FPGA), Digital Signal Processor (Digital Signal Processor, DSP), embedded devices, etc. The network device includes, but is not limited to, a computer, a network host, a single network server, multiple network server sets, or a cloud composed of multiple servers; here, a cloud is composed of a large number of computers or network servers based on cloud computing, Among them, cloud computing is a kind of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless ad hoc network (Ad Hoc network), and the like. Preferably, the device may also be a program running on the user equipment, network equipment, or a device formed by user equipment and network equipment, network equipment, touch terminal or network equipment and touch terminal integrated through a network.

当然，本领域技术人员应能理解上述设备仅为举例，其他现有的或今后可能出现的设备如可适用于本申请，也应包含在本申请保护范围以内，并在此以引用方式包含于此。Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or possible devices that may appear in the future, if applicable to this application, should also be included within the protection scope of this application, and are included in this application by reference. this.

在本申请的描述中，“多个”的含义是两个或者更多，除非另有明确具体的限定。In the description of this application, "plurality" means two or more, unless expressly and specifically defined otherwise.

图1示出了根据本申请一个实施例的一种基于区块链的检测不合格商品的方法流程图，该方法包括步骤S11、步骤S12、步骤S13和步骤S14。在步骤S11中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；在步骤S12中，网络设备获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；在步骤S13中，网络设备根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；在步骤S14中，网络设备根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链Fig. 1 shows a flowchart of a method for detecting unqualified commodities based on blockchain according to an embodiment of the present application, the method includes step S11, step S12, step S13 and step S14. In step S11, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each commodity in is a substandard commodity; in step S12, the network device obtains the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information. , the knowledge graph includes a plurality of nodes, each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, and the target object is a commodity or an associated object , the connection relationship feature information is used to represent the connection relationship between each node in the knowledge graph; in step S13, the network device determines the second product according to the model data increment information and the first product calibration information Commodity calibration information, update the commodity detection model according to the model data information, the model data increment information, the connection relationship feature information and the second commodity calibration information; in step S14, the network device The model data incremental information, determine the model data update information that needs to be uploaded to the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain

在步骤S11中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品。In step S11, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each item in is a non-conforming item.

在一些实施例中，响应于网络设备发送的模型获取请求，区块链会对网络设备进行身份验证，在身份验证通过后才会将商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息返回给网络设备。在一些实施例中，商品检测模型的输入为某个商品对应的商品特征信息且输出用于指示该商品是否是不合格商品的商品检测信息。在一些实施例中，商品检测信息包括用于指示所述目标商品是否是不合格商品的指示信息，如“1”指示商品为合格商品，“0”指示商品为不合格商品。在一些实施例中，商品检测信息包括该目标商品是不合格商品的概率信息，如商品检测信息指示该目标商品有70％的概率为不合格商品，如商品检测信息指示该目标商品有30％的概率为合格商品。In some embodiments, in response to a model acquisition request sent by a network device, the blockchain will perform identity verification on the network device, and only after the identity verification is passed will the commodity detection model and the model data information corresponding to the commodity detection model and The first commodity calibration information is returned to the network device. In some embodiments, the input of the commodity detection model is commodity feature information corresponding to a commodity, and the output is commodity detection information used to indicate whether the commodity is a substandard commodity. In some embodiments, the commodity detection information includes indication information for indicating whether the target commodity is a substandard commodity, for example, "1" indicates that the commodity is a qualified commodity, and "0" indicates that the commodity is a substandard commodity. In some embodiments, the commodity detection information includes probability information that the target commodity is a substandard commodity. For example, the commodity detection information indicates that the target commodity has a 70% probability of being a substandard commodity. For example, the commodity detection information indicates that the target commodity has a 30% probability. The probability of being a qualified product.

在一些实施例中，商品检测模型是基于模型数据信息、第一商品标定信息等样本数据通过训练获得的，可以是基于这些样本数据通过训练生成的商品检测模型，也可是基于这些样本数据通过训练对当前商品检测模型进行更新，将更新后的当前商品检测模型作为所述商品检测模型。在一些实施例中，模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，商品特征信息包括任何与商品的特征相关的信息，可选地，商品特征信息包括但不限于商品标题描述、商品分类标签、商品价格、商品对应的商户信息、商品评论信息、商品发货地、商品销量、商品评价信息、商品描述信息等。In some embodiments, the commodity detection model is obtained through training based on sample data such as model data information and first commodity calibration information. The current commodity detection model is updated, and the updated current commodity detection model is used as the commodity detection model. In some embodiments, the model data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information. The commodity feature information includes any information related to the features of the commodities. Optionally The commodity feature information includes, but is not limited to, commodity title description, commodity classification label, commodity price, merchant information corresponding to the commodity, commodity review information, commodity shipping location, commodity sales volume, commodity evaluation information, commodity description information, etc.

在一些实施例中，商品特征信息可有一个或多个关联对象。在一些实施例中，商品特征信息所关联的关联对象可以是该商品特征信息中包括的任意对象，例如，商品A的商品特征信息包括商品A对应的商户信息“商户B”，则该商品特征信息所关联的关联对象可以是商户B；又例如，商品A的商品特征信息包括商品A对应的商品描述信息“狗喜欢使用该商品”，则该商品特征信息所关联的关联对象可以是狗。在一些实施例中，还可以根据该商品特征信息的语义内容，将与该语义内容相关联的对象确定为该商品特征信息所关联的关联对象，例如，商品A的商品特征信息的语义内容包括“高端宠物食品品牌”，则可将与该语义内容相关联的对象“猫”、“狗”确定为该商品特征信息所关联的关联对象。在一些实施例中，关联对象可以是任何形式的任何对象，优选地，包括但不限于商户对象、用户对象、商品对象等。在一些实施例中，关联对象对应的对象特征信息包括任何与关联对象的特征相关的信息，当一个关联对象是某个商品时，该关联对象对应的对象特征信息即为该商品的商品特征信息；当一个关联对象是某个用户时，该关联对象对应的对象特征信息包括但不限于该用户上传、编辑、浏览、购买商品的历史行为信息、用户的兴趣标签信息等；当一个关联对象是某个商户时，该关联对象对应的对象特征信息包括但不限于该商户所出售的其他商品、商户的评价信息等。在一些实施例中，不合格商品包括但不限于假冒伪劣商品、违法违禁商品等。In some embodiments, item feature information may have one or more associated objects. In some embodiments, the associated object associated with the product feature information may be any object included in the product feature information. For example, if the product feature information of product A includes the merchant information "merchant B" corresponding to product A, then the product feature The associated object associated with the information may be merchant B; for another example, if the commodity feature information of commodity A includes commodity description information corresponding to commodity A "dogs like to use this commodity", the associated object associated with the commodity feature information may be dogs. In some embodiments, the object associated with the semantic content may also be determined as the associated object associated with the product feature information according to the semantic content of the product feature information. For example, the semantic content of the product feature information of product A includes: "High-end pet food brand", the objects "cat" and "dog" associated with the semantic content can be determined as the associated objects associated with the product feature information. In some embodiments, the associated object may be any object in any form, preferably, including but not limited to a merchant object, a user object, a commodity object, and the like. In some embodiments, the object feature information corresponding to the associated object includes any information related to the feature of the associated object. When an associated object is a certain commodity, the object feature information corresponding to the associated object is the commodity feature information of the commodity ; When an associated object is a user, the object feature information corresponding to the associated object includes but is not limited to the user's uploading, editing, browsing, and purchasing historical behavior information, user's interest tag information, etc.; when an associated object is For a certain merchant, the object feature information corresponding to the associated object includes, but is not limited to, other commodities sold by the merchant, evaluation information of the merchant, and the like. In some embodiments, unqualified commodities include, but are not limited to, counterfeit and shoddy commodities, illegal and prohibited commodities, and the like.

在步骤S12中，网络设备获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系。In step S12, the network device obtains the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, and the knowledge graph includes a plurality of nodes. Each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent all Describe the connection relationship between each node in the knowledge graph.

在一些实施例中，模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息，商品特征增量信息可以是新增的至少一个商品对应的商品特征信息，或者，还可以是从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息。在一些实施例中，根据从区块链获得的模型数据信息以及模型数据增量信息，构建知识图谱，知识图谱中包括多个节点，每个节点可以是从区块链获得的模型数据信息中的一个商品或该商品所关联的关联对象，也可以是模型数据增量信息中的一个新增商品及该新增商品所关联的关联对象，商品特征信息或对象特征信息是对应的商品节点或关联对象节点的属性。In some embodiments, the model data incremental information includes commodity feature incremental information and second object feature information corresponding to a second associated object associated with the commodity feature incremental information, and the commodity feature incremental information may be newly added Product feature information corresponding to at least one product, or, may also be newly added product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain. In some embodiments, a knowledge graph is constructed according to the model data information obtained from the blockchain and the incremental information of the model data. The knowledge graph includes a plurality of nodes, and each node may be from the model data information obtained from the blockchain. A commodity or an associated object associated with the commodity, it can also be a new commodity in the incremental information of the model data and the associated object associated with the new commodity, and the commodity feature information or object feature information is the corresponding commodity node or Properties of the associated object node.

在一些实施例中，知识图谱能够反映各个节点之间的关系，在知识图谱中，通过两个节点各自的属性(即商品节点对应的商品特征信息或关联对象节点对应的对象特征信息)，可以建立起两个节点之间的连接(即商品与商品之间的关联、商品与关联对象之间的关联、关联对象与关联对象之间的关联)，两个节点之间可以直接连接，也可以通过一个或多个其他节点间接连接，例如，商品A对应的节点与关联对象B的节点直接连接，并通过关联对象B对应的节点与商品C对应的节点间接连接；又例如，商品A的商品特征信息包括“曾经被用户U购买”，用户B的对象特征信息包括“曾经浏览过商品B”，由此通过知识图谱能够建立商品A与用户U之间的直接关联，商品B与用户U之间的直接关联，商品A与商品B之间的间接关联(也即商品A对应的节点与用户U对应的节点直接连接，商品B对应的节点与用户U对应的节点直接连接，商品A对应的节点与商品B对应的节点通过用户U对应的节点间接连接)。In some embodiments, the knowledge graph can reflect the relationship between each node. In the knowledge graph, through the respective attributes of the two nodes (that is, the product feature information corresponding to the product node or the object feature information corresponding to the associated object node), the Establish a connection between two nodes (ie, the association between commodities and commodities, the association between commodities and associated objects, the association between associated objects and associated objects), and the two nodes can be directly connected, or they can be Indirectly connected through one or more other nodes, for example, the node corresponding to commodity A is directly connected to the node of associated object B, and indirectly connected to the node corresponding to commodity C through the node corresponding to associated object B; for another example, the commodity of commodity A The feature information includes "was purchased by user U", and the object feature information of user B includes "browsed product B", so the direct association between product A and user U can be established through the knowledge graph, and the relationship between product B and user U can be established. The direct association between product A and product B (that is, the node corresponding to product A is directly connected to the node corresponding to user U, the node corresponding to product B is directly connected to the node corresponding to user U, the node corresponding to product A is directly connected to the node corresponding to user U, and the node corresponding to product A is directly connected to the node corresponding to user U. The node and the node corresponding to the commodity B are indirectly connected through the node corresponding to the user U).

再例如，商品C的商品特征信息包括“曾经多次在电影E中出现”，电影E的对象特征信息包括“曾经多次出现商品D”，由此通过知识图谱能够建立商品C与电影E之间的直接关联，商品D与电影E之间的直接关联，商品C与商品D之间的间接关联(也即商品C对应的节点与电影E对应的节点直接连接，商品D对应的节点与电影E对应的节点直接连接，商品C对应的节点与商品D对应的节点通过电影E对应的节点间接连接)。For another example, the product feature information of product C includes "has appeared in movie E many times", and the object feature information of movie E includes "has appeared product D many times", so the relationship between product C and movie E can be established through the knowledge graph. The direct association between commodity D and movie E, the indirect association between commodity C and commodity D (that is, the node corresponding to commodity C is directly connected to the node corresponding to movie E, the node corresponding to commodity D is directly connected to the movie The node corresponding to E is directly connected, and the node corresponding to product C and the node corresponding to product D are indirectly connected through the node corresponding to movie E).

又例如，商品A的商品特征信息包括“商品描述中多次出现了‘狗’”，商品B的商品特征信息包括“商品描述中多次出现了‘猫’”，关联对象“狗”的对象特征信息中包括“与猫都是常见宠物”，关联对象“猫”的对象特征信息中包括“与狗都是常见宠物”，由此通过知识图谱能够建立商品A与关联对象“狗”之间的直接关联，商品B与关联对象“猫”之间的直接关联，关联对象“狗”与关联对象“猫”之间的直接关联，商品A与商品B之间的间接关联(也即商品A对应的节点与关联对象“狗”的节点直接连接，商品B对应的节点与关联对象“猫”对应的节点直接连接，商品A对应的节点与商品B对应的节点通过关联对象“狗”对应的节点与关联对象“猫”对应的节点间接连接)。For another example, the product feature information of product A includes "the 'dog' appears many times in the product description", and the product feature information of the product B includes "the 'cat' appears many times in the product description", and the object associated with the object "dog" The feature information includes "common pets with cats", and the object feature information of the associated object "cat" includes "common pets with dogs", so that the relationship between commodity A and the associated object "dog" can be established through the knowledge graph. The direct association between commodity B and the associated object "cat", the direct association between the associated object "dog" and the associated object "cat", the indirect association between commodity A and commodity B (that is, commodity A The corresponding node is directly connected to the node of the associated object "dog", the node corresponding to the commodity B is directly connected to the node corresponding to the associated object "cat", the node corresponding to the commodity A and the node corresponding to the commodity B are connected through the associated object "dog". The node is indirectly connected with the node corresponding to the associated object "cat").

在一些实施例中，连接关系可以是两个节点之间的直接连接关系，例如，节点A与节点B直接连接，或者，连接关系还可以是两个节点之间的间接连接关系，此时连接关系中包括两个节点之间的连接所对应的跳数，例如，节点A与节点B直接连接，则节点A到节点B的跳数为1，又例如，节点A通过节点B与节点C间接相连，则节点A到节点C的跳数为2。在一些实施例中，每个节点可以只与一个节点之间存在连接关系，也可以同时与多个节点之间存在连接关系。在一些实施例中，两个节点之间可以只存在一个连接关系，也可以同时存在多个连接关系。In some embodiments, the connection relationship may be a direct connection relationship between two nodes, for example, node A is directly connected to node B, or the connection relationship may also be an indirect connection relationship between two nodes, in which case the connection The relationship includes the number of hops corresponding to the connection between two nodes. For example, if node A is directly connected to node B, the number of hops from node A to node B is 1. For example, node A is indirectly connected to node C through node B. If connected, the number of hops from node A to node C is 2. In some embodiments, each node may only have a connection relationship with one node, or may have a connection relationship with multiple nodes at the same time. In some embodiments, only one connection relationship may exist between two nodes, or multiple connection relationships may exist simultaneously.

在一些实施例中，连接关系特征信息可以是知识图谱中各个节点之间的多个连接关系的集合。例如，商品A的商品特征信息包括“曾经被用户U1购买”，用户U1的对象特征信息包括“曾经购买过商品B”，则知识图谱中包括分别与商品A、用户U1、商品B对应的三个节点，且基于该知识图谱可获得该三个节点对应的连接关系特征信息，该连接关系特征信息用于指示商品A和用户U1具有直接连接关系“被购买”，用户U1和商品B具有直接连接关系“购买”，商品A和商品B具有间接连接关系(间接连接关系是指两个节点并未直接相连，而是通过一个或多个其他节点相连接，如本实例中，商品A和商品B通过用户U1相连接)。In some embodiments, the connection relationship feature information may be a collection of multiple connection relationships between nodes in the knowledge graph. For example, if the product feature information of product A includes "have been purchased by user U1", and the object feature information of user U1 includes "have purchased product B", then the knowledge graph includes three items corresponding to product A, user U1, and product B respectively. and based on the knowledge graph, the connection relationship feature information corresponding to the three nodes can be obtained. The connection relationship feature information is used to indicate that product A and user U1 have a direct connection relationship "purchased", and user U1 and product B have direct connection relationship "purchased". The connection relationship is "purchase", and commodity A and commodity B have an indirect connection relationship (indirect connection relationship means that the two nodes are not directly connected, but are connected through one or more other nodes, such as in this example, commodity A and commodity B is connected via user U1).

在一些实施例中，两个节点之间的连接关系是有方向的，如上例中商品A到用户U1的连接关系“被购买”是从商品A对应的节点指向用户U1对应的节点，用户U1到商品B的连接关系“购买”是从用户U1对应的节点指向商品B对应的节点。In some embodiments, the connection relationship between the two nodes is directional. For example, in the above example, the connection relationship between product A and user U1 is “purchased” from the node corresponding to product A to the node corresponding to user U1. User U1 The connection relationship "purchase" to commodity B is from the node corresponding to user U1 to the node corresponding to commodity B.

在步骤S13中，网络设备根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型。在一些实施例中，在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品及该至少一个商品对应的商品特征信息，则需要获取该新增的至少一个商品对应的商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，则需要确定该至少一个商品中是否存在需要重新标定的商品，若是，重新获取这部分需要重新标定的商品对应的商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。In step S13, the network device determines second commodity calibration information according to the model data increment information and the first commodity calibration information, and determines the second commodity calibration information according to the model data information, the model data increment information, and the connection relationship feature. information and the second commodity calibration information to update the commodity detection model. In some embodiments, in some embodiments, if the model data incremental information includes at least one newly added product and the product feature information corresponding to the at least one product in addition to the model data information obtained from the blockchain, it is necessary to obtain the model data information. Commodity calibration information corresponding to the newly added at least one commodity, and second commodity calibration information corresponding to all commodities in the knowledge map is determined according to the first commodity calibration information corresponding to the model data information. In some embodiments, if the model data incremental information includes new product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain, it is necessary to determine whether the at least one product exists The product that needs to be re-calibrated, if so, re-acquire the product calibration information corresponding to the product that needs to be re-calibrated, and determine the second product calibration information corresponding to all products in the knowledge map according to the first product calibration information corresponding to the model data information. .

在一些实施例中，可以接收用户输入的该至少一个商品对应的商品标定信息。在一些实施例中，还从知识图谱中获得与该至少一个商品存在连接关系的至少一个已标定商品，根据该至少一个商品对应的商品特征信息与所述至少一个已标定商品对应的商品特征信息之间的相似度信息，对该至少一个商品进行标定并获得对应的商品标定信息。在一些实施例中，由模型训练人员人工对该至少一个商品标注商品标定信息。在一些实施例中，若知识图谱中与该至少一个商品存在连接关系的至少一个已标定商品与该商品之间具有相似的价格、相似的购买量、相似的浏览量等相似的商品特征信息，则可以根据该已标定商品是否为不合格商品，来标定该至少一个商品是否为不合格商品，例如，若该已标定商品为不合格商品，则可以标定该至少一个商品同样也为不合格商品，又例如，若该已标定商品为合格商品，则可以标定该至少一个商品同样也为合格商品。在一些实施例中，基于所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，通过训练对从区块链获得的商品检测模型进行更新。In some embodiments, commodity calibration information corresponding to the at least one commodity input by the user may be received. In some embodiments, at least one calibrated commodity that has a connection relationship with the at least one commodity is also obtained from the knowledge graph, and according to the commodity characteristic information corresponding to the at least one commodity and the commodity characteristic information corresponding to the at least one calibrated commodity The similarity information between the at least one commodity is calibrated and the corresponding commodity calibration information is obtained. In some embodiments, the at least one commodity is manually marked with commodity calibration information by a model trainer. In some embodiments, if the at least one calibrated commodity in the knowledge graph that has a connection relationship with the at least one commodity has similar commodity feature information, such as similar price, similar purchase amount, similar pageview amount, and the like, Whether the at least one commodity is a non-conforming commodity can be calibrated according to whether the calibrated commodity is a non-conforming commodity. For example, if the calibrated commodity is a non-conforming commodity, the at least one commodity can also be demarcated as a non-conforming commodity. , for another example, if the marked commodity is a qualified commodity, the at least one commodity can also be marked as a qualified commodity. In some embodiments, the product detection model obtained from the blockchain is updated through training based on the model data information, the model data increment information, the connection relationship feature information, and the second product calibration information .

在步骤S14中，网络设备根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品及该至少一个商品对应的商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的商品特征信息对该商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品对应的商品标定信息，也可以包括知识图谱中的所有商品对应的商品特征信息以及所有商品特征信息所关联的所有关联对象对应的所有对象特征信息以及所有商品对应的所有商品标定信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的新增商品特征信息及该新增商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品中需要重新标定的这部分商品对应的商品标定信息，也可以包括知识图谱中的所有商品对应的商品特征信息以及所有商品特征信息所关联的所有关联对象对应的所有对象特征信息以及所有商品对应的商品标定信息。In step S14, the network device determines the model data update information that needs to be uploaded to the blockchain according to the model data increment information, and uploads the updated commodity detection model and the model data update information to the blockchain. In some embodiments, if the model data incremental information includes at least one newly added product and the product feature information corresponding to the at least one product in addition to the model data information obtained from the blockchain, it may be determined that the data that needs to be uploaded to the blockchain The model data update information may only include the product feature information corresponding to the at least one product, the object feature information corresponding to the associated object associated with the product feature information, and the product calibration information corresponding to the at least one product, or may include all the knowledge graphs. Product feature information corresponding to the product, all object feature information corresponding to all associated objects associated with all product feature information, and all product calibration information corresponding to all products. In some embodiments, if the model data incremental information includes the newly added product feature information corresponding to at least one product among the multiple products in the model data information obtained from the blockchain, it may be determined that the information that needs to be uploaded to the blockchain The model data update information may only include the new product feature information corresponding to the at least one product, the object feature information corresponding to the associated object associated with the newly added product feature information, and the at least one product corresponding to the part of the product that needs to be re-calibrated. The product calibration information may also include product feature information corresponding to all products in the knowledge graph, all object feature information corresponding to all associated objects associated with all product feature information, and product calibration information corresponding to all products.

本申请能够通过向区块链请求商品检测模型及模型数据信息等相关信息，并根据模型数据增量信息来建立知识图谱，进而通过训练更新商品检测模型，并将更新后的商品检测模型上传至区块链，从而能够实现不同公司来共同维护并更新商品检测模型，可以提高商品检测模型检测违禁假冒商品的准确性，能够大大减少每个公司在单独训练生成商品检测模型过程中的训练成本。In this application, the product detection model and model data information and other related information can be requested from the blockchain, and a knowledge graph can be established according to the incremental information of the model data, and then the product detection model can be updated through training, and the updated product detection model can be uploaded to The blockchain enables different companies to jointly maintain and update the commodity detection model, which can improve the accuracy of the commodity detection model in detecting prohibited and counterfeit commodities, and can greatly reduce the training cost of each company in the process of separately training and generating commodity detection models.

在一些实施例中，所述步骤S12之前还包括：网络设备根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱。在一些实施例中，模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息，商品特征增量信息可以是新增的至少一个商品对应的商品特征信息，或者，还可以是从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息。在一些实施例中，根据从区块链获得的模型数据信息以及模型数据增量信息，构建知识图谱，知识图谱中包括多个节点，每个节点可以是从区块链获得的模型数据信息中的一个商品或该商品所关联的关联对象，也可以是模型数据增量信息中的一个新增商品及该新增商品所关联的关联对象，商品特征信息或对象特征信息是对应的商品节点或关联对象节点的属性。在一些实施例中，知识图谱能够反映各个节点之间的关系，在知识图谱中，通过两个节点各自的属性(即商品节点对应的商品特征信息或关联对象节点对应的对象特征信息)，可以建立起两个节点之间的连接(即商品与商品之间的关联、商品与关联对象之间的关联、关联对象与关联对象之间的关联)，两个节点之间可以直接连接，也可以通过一个或多个其他节点间接连接。In some embodiments, before the step S12, the method further includes: the network device constructs the knowledge graph according to the model data information and the model data increment information. In some embodiments, the model data incremental information includes commodity feature incremental information and second object feature information corresponding to a second associated object associated with the commodity feature incremental information, and the commodity feature incremental information may be newly added Product feature information corresponding to at least one product, or, may also be newly added product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain. In some embodiments, a knowledge graph is constructed according to the model data information obtained from the blockchain and the incremental information of the model data. The knowledge graph includes a plurality of nodes, and each node may be from the model data information obtained from the blockchain. A commodity or an associated object associated with the commodity, it can also be a new commodity in the incremental information of the model data and the associated object associated with the new commodity, and the commodity feature information or object feature information is the corresponding commodity node or Properties of the associated object node. In some embodiments, the knowledge graph can reflect the relationship between each node. In the knowledge graph, through the respective attributes of the two nodes (that is, the product feature information corresponding to the product node or the object feature information corresponding to the associated object node), the Establish a connection between two nodes (ie, the association between commodities and commodities, the association between commodities and associated objects, the association between associated objects and associated objects), and the two nodes can be directly connected, or they can be Indirectly connected through one or more other nodes.

在一些实施例中，所述模型数据信息还包括所述商品检测模型对应的原始连接关系特征信息，所述原始连接关系特征信息是根据所述商品特征信息及所述对象特征信息构建的原始知识图谱获得的；其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱，包括：根据所述模型数据信息、所述模型数据增量信息以及所述原始连接关系特征信息，构建所述知识图谱。在一些实施例中，从区块链获得的模型数据信息中还包括商品检测模型对应的原始连接关系特征信息，原始连接关系特征信息是从根据模型数据信息中的多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息构建的原始知识图谱中获得的。在一些实施例中，根据模型数据信息、模型数据增量信息以及原始连接关系特征信息，构建所述知识图谱，可以加速知识图谱的构建过程，提高知识图谱的构建效率。In some embodiments, the model data information further includes original connection relationship feature information corresponding to the product detection model, where the original connection relationship feature information is original knowledge constructed according to the product feature information and the object feature information Obtained from a graph; wherein, constructing the knowledge graph according to the model data information and the model data increment information includes: according to the model data information, the model data increment information and the original connection The relational feature information is used to construct the knowledge graph. In some embodiments, the model data information obtained from the blockchain further includes original connection relationship feature information corresponding to the product detection model, and the original connection relationship feature information is obtained from product feature information corresponding to multiple products in the model data information. and obtained from the original knowledge graph constructed by the object feature information corresponding to the associated object associated with the commodity feature information. In some embodiments, the knowledge graph is constructed according to the model data information, the model data increment information and the original connection relationship feature information, which can speed up the construction process of the knowledge graph and improve the construction efficiency of the knowledge graph.

在一些实施例中，所述模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息；其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建知识图谱，包括：根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱。在一些实施例中，商品特征增量信息可以是在从区块链获得的模型数据信息以外新增的至少一个商品对应的商品特征信息，或者，还可以是从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息。In some embodiments, the model data incremental information includes commodity feature incremental information and second object feature information corresponding to a second associated object associated with the commodity feature incremental information; wherein the model data is based on the model. Using the data information and the model data increment information to construct a knowledge graph includes: constructing the knowledge graph according to the model data information, the commodity feature increment information and the second object feature information. In some embodiments, the product feature increment information may be product feature information corresponding to at least one newly added product in addition to the model data information obtained from the blockchain, or may also be model data information obtained from the blockchain New product feature information corresponding to at least one of the multiple products in the .

在一些实施例中，所述方法还包括：网络设备根据所述商品特征增量信息，确定所述商品特征增量信息所关联的第二关联对象，并获取所述第二关联对象对应的第二对象特征信息。在一些实施例中，从商品特征增量信息中提取一个或多个对象，并将该一个或多个对象中的全部或部分对象确定为该商品特征增量信息所关联的第二关联对象，可选地，从该一个或多个对象中选择与该商品特征增量信息对应的一个或多个商品具有一定联系的至少一个对象，其中，与一个或多个商品具有一定联系的对象可能为语义上具有包含或被包含关系的对象(如“宠物”和“狗”)、能够与一个或多个商品成套使用的对象(如“充电器”和“充电线”)等。在一些实施例中，根据该商品特征增量信息的语义内容，将与该语义内容相关联的对象确定为该商品特征增量信息所关联的第二关联对象，例如，新增商品A对应的商品特征增量信息的语义内容包括“高端宠物食品品牌”，则可将与该语义内容相关联的对象“猫”、“狗”确定为该商品特征增量信息所关联的第二关联对象，也即，所确定的第二关联对象并非是直接包含在商品特征增量信息中的对象，由此能够实现更全面的关联。在一些实施例中，对于第二关联对象，在本地或网络上收集该第二关联对象对应的对象相关信息后，对象相关信息是与该第二关联对象相关的任何信息，然后可以直接根据该对象相关信息确定该第二关联对象对应的第二对象特征信息，或者，可以对该对象相关信息进行特征提取后再确定该第二关联对象对应的第二对象特征信息。在一些实施例中，若第二关联对象为一个商品，可以直接将该商品对应的商品特征信息作为其对应的第二对象特征信息。In some embodiments, the method further includes: the network device determines, according to the commodity feature increment information, a second associated object associated with the commodity feature increment information, and obtains a first associated object corresponding to the second associated object. Two object feature information. In some embodiments, one or more objects are extracted from the commodity feature incremental information, and all or part of the one or more objects are determined as the second associated objects associated with the commodity feature incremental information, Optionally, at least one object that has a certain relationship with one or more products corresponding to the product feature incremental information is selected from the one or more objects, wherein the object that has a certain relationship with the one or more products may be Objects that semantically have contained or contained relationships (such as "pets" and "dogs"), objects that can be used in sets with one or more commodities (such as "chargers" and "charging cables"), and so on. In some embodiments, according to the semantic content of the product feature incremental information, the object associated with the semantic content is determined as the second associated object associated with the product feature incremental information, for example, the newly added product A corresponds to If the semantic content of the product feature incremental information includes "high-end pet food brand", the objects "cat" and "dog" associated with the semantic content can be determined as the second associated objects associated with the product feature incremental information, That is, the determined second associated object is not an object directly included in the commodity feature incremental information, so that a more comprehensive association can be achieved. In some embodiments, for the second associated object, after the object-related information corresponding to the second associated object is collected locally or on the network, the object-related information is any information related to the second associated object, and then the object-related information can be directly The object-related information determines the second object feature information corresponding to the second associated object, or the second object feature information corresponding to the second associated object can be determined after feature extraction is performed on the object-related information. In some embodiments, if the second associated object is a commodity, the commodity characteristic information corresponding to the commodity may be directly used as the corresponding second object characteristic information.

在一些实施例中，所述商品特征增量信息中包括一个或多个对象；其中，所述确定所述商品特征增量信息所关联的第二关联对象，包括：将所述一个或多个对象中的至少一个对象作为所述商品特征增量信息所关联的第二关联对象。在一些实施例中，可将所述一个或多个对象直接作为该商品特征增量信息所关联的第二关联对象。在一些实施例中，若商品特征增量信息中包括多个对象，可从该多个对象中确定至少一个对象来作为该商品特征增量信息所关联的第二关联对象。In some embodiments, the commodity feature increment information includes one or more objects; wherein the determining a second associated object associated with the commodity feature increment information includes: adding the one or more objects At least one of the objects is used as a second associated object associated with the commodity feature increment information. In some embodiments, the one or more objects may be directly used as the second associated object associated with the commodity feature incremental information. In some embodiments, if the product feature incremental information includes multiple objects, at least one object may be determined from the multiple objects as the second associated object associated with the product feature incremental information.

在一些实施例中，所述将所述一个或多个对象中的至少一个对象作为该商品特征增量信息所关联的第二关联对象，包括：从所述一个或多个对象中确定至少一个对象，并将所述至少一个对象作为所述商品特征增量信息所关联的第二关联对象。在一些实施例中，从所述一个或多个对象中选择与该商品特征增量信息对应的一个或多个商品之间的关联程度大于预定关联度的至少一个对象作为该商品特征增量信息所关联的第二关联对象。在一些实施例中，从所述一个或多个对象中确定访问率或点击率最高的对象作为该商品特征增量信息所关联的第二关联对象。在一些实施例中，根据所述一个或多个对象中每个对象在该商品特征增量信息中的比重，从所述一个或多个对象中确定至少一个对象，其中，所述至少一个对象中的每个对象在该商品特征增量信息中的比重满足预定的比重阈值。In some embodiments, using at least one of the one or more objects as the second associated object associated with the commodity feature incremental information includes: determining at least one object from the one or more objects object, and use the at least one object as a second associated object associated with the commodity feature incremental information. In some embodiments, at least one object whose degree of association between one or more commodities corresponding to the commodity feature increment information is greater than a predetermined degree of association is selected from the one or more objects as the commodity characteristic increment information The associated second association object. In some embodiments, an object with the highest visit rate or click rate is determined from the one or more objects as the second associated object associated with the product feature incremental information. In some embodiments, at least one object is determined from the one or more objects according to the proportion of each of the one or more objects in the commodity feature incremental information, wherein the at least one object is The proportion of each object in the commodity feature incremental information meets a predetermined proportion threshold.

在一些实施例中，所述从所述一个或多个对象中确定至少一个对象，包括：根据所述一个或多个对象中每个对象在所述商品特征增量信息中的比重，从所述一个或多个对象中确定至少一个对象，其中，所述至少一个对象中的每个对象在所述商品特征增量信息中的比重满足预定的比重阈值。在一些实施例中，一个对象在该商品特征增量信息中的比重用于表征该对象在该商品特征增量信息中的重要程度，该重要程度能够在一定程度上反映该对象对商品特征增量信息对应的一个或多个商品的使用或销售的影响程度。在一些实施例中，根据每个对象在该商品特征增量信息中的比重，从所述一个或多个对象中确定出所对应的比重大于或等于预定的比重阈值的至少一个对象。在一些实施例中，所述方法还包括：网络设备根据每个对象在所述商品特征增量信息中的出现次数，确定该对象在所述商品特征增量信息中的比重。在一些实施例中，一个对象在该商品特征增量信息中的出现次数越高，该对象在该商品特征增量信息中的比重越高，反之则越低。在一些实施例中，进一步结合对象在该商品特征增量信息中的出现位置，来调整该对象在该商品特征增量信息中的比重，例如，若一个对象在该商品特征增量信息中出现多次，且大多数出现在该商品特征增量信息对应的一个或多个商品的商品描述信息中，则提高该对象在该商品特征增量信息中的比重，可选地，可针对不同的出现位置设定不同的加权系数，由此来调整对象在该商品特征增量信息中的比重。In some embodiments, the determining at least one object from the one or more objects includes: according to the proportion of each object in the one or more objects in the commodity feature incremental information, from the At least one object is determined from the one or more objects, wherein the proportion of each object in the at least one object in the commodity feature increment information satisfies a predetermined proportion threshold. In some embodiments, the proportion of an object in the commodity feature incremental information is used to represent the importance of the object in the commodity feature incremental information, and the importance can reflect the object's contribution to the commodity feature incremental information to a certain extent. The degree of influence of the usage or sales of one or more commodities corresponding to the quantity information. In some embodiments, at least one object whose corresponding weight is greater than or equal to a predetermined weight threshold is determined from the one or more objects according to the weight of each object in the commodity feature increment information. In some embodiments, the method further includes: the network device determining the proportion of each object in the commodity characteristic increment information according to the number of occurrences of the object in the commodity characteristic increment information. In some embodiments, the higher the number of occurrences of an object in the product feature incremental information, the higher the proportion of the object in the product feature incremental information, and vice versa. In some embodiments, the proportion of the object in the product feature incremental information is adjusted by further combining the appearance position of the object in the product feature incremental information. For example, if an object appears in the product feature incremental information multiple times, and most of them appear in the commodity description information of one or more commodities corresponding to the commodity feature incremental information, then the proportion of the object in the commodity feature incremental information is increased. Different weighting coefficients are set for the appearing position, thereby adjusting the proportion of the object in the incremental information of the product feature.

在一些实施例中，所述方法还包括：网络设备根据每个对象在所述商品特征增量信息中的语义重要程度，确定该对象在所述商品特征增量信息中的比重。在一些实施例中，所述语义重要程度能够在一定程度上反映该对象与该商品特征增量信息对应的一个或多个商品之间的关联性，语义重要程度越高，该对象与该商品特征增量信息对应的一个或多个商品之间关联程度越高。在一些实施例中，一个对象在该商品特征增量信息中的语义重要程度越高，该对象在该商品特征增量信息中的比重越高，反之则越低。In some embodiments, the method further includes: the network device determining the proportion of each object in the commodity feature incremental information according to the semantic importance of each object in the commodity feature incremental information. In some embodiments, the semantic importance level can reflect the correlation between the object and one or more commodities corresponding to the commodity feature incremental information to a certain extent. The higher the degree of correlation between one or more commodities corresponding to the feature incremental information. In some embodiments, the higher the semantic importance of an object in the product feature incremental information, the higher the proportion of the object in the product feature incremental information, and vice versa.

在一些实施例中，所述商品特征增量信息包括新增的至少一个商品对应的第一商品特征信息；其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：根据所述模型数据信息、所述第一商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述新增的至少一个商品对应的节点以及与所述第二关联对象对应的节点。在一些实施例中，商品特征增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品对应的第一商品特征信息，模型数据增量信息包括该新增的至少一个商品对应的第一商品特征信息以及该第一商品特征信息所关联的第二关联对象对应的第二对象特征信息。在一些实施例中，构建的知识图谱中除了包括模型数据信息中的多个商品对应的节点及该多个商品对应的商品特征信息所关联的多个关联对象对应的节点以外，还包括新增的至少一个商品对应的节点及该新增的至少一个商品对应的商品特征信息所关联的多个关联对象对应的节点。In some embodiments, the product feature increment information includes first product feature information corresponding to at least one newly added product; wherein the information based on the model data, the product feature increment information and the first product feature information Two object feature information, and constructing the knowledge graph includes: constructing the knowledge graph according to the model data information, the first commodity feature information and the second object feature information, wherein the knowledge graph also includes It includes a node corresponding to the newly added at least one commodity and a node corresponding to the second associated object. In some embodiments, the product feature incremental information includes first product feature information corresponding to at least one newly added product in addition to the model data information obtained from the blockchain, and the model data incremental information includes the newly added at least one product corresponding to and the second object feature information corresponding to the second associated object associated with the first product feature information. In some embodiments, in addition to including nodes corresponding to multiple commodities in the model data information and nodes corresponding to multiple associated objects associated with the commodity feature information corresponding to the multiple commodities, the constructed knowledge graph also includes newly added nodes. The node corresponding to the at least one commodity of , and the nodes corresponding to multiple associated objects associated with the commodity feature information corresponding to the newly added at least one commodity.

在一些实施例中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：获得所述新增的至少一个商品对应的新增商品标定信息，并根据所述新增商品标定信息以及所述第一商品标定信息确定第二商品标定信息。在一些实施例中，因为新增的至少一个商品之前不存在于区块链上，新增的至少一个商品也从未被标定，因此需要获取新增的至少一个商品对应的商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。在一些实施例中，所述商品特征增量信息包括所述多个商品中的至少一个商品对应的新增商品特征信息；其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：根据所述模型数据信息、所述新增商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述第二关联对象对应的节点。在一些实施例中，商品特征增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，模型数据增量信息包括该新增商品特征信息所关联的第二关联对象对应的第二对象特征信息。在一些实施例中，构建的知识图谱中除了包括模型数据信息中的多个商品对应的节点及该多个商品对应的商品特征信息所关联的多个关联对象对应的节点以外，还包括该多个商品中的至少一个商品对应的新增商品特征信息所关联的至少一个关联对象对应的节点。In some embodiments, the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information includes: obtaining newly added commodity calibration information corresponding to the newly added at least one commodity, and determining second commodity calibration information according to the newly added commodity calibration information and the first commodity calibration information. In some embodiments, because the at least one newly added product does not exist on the blockchain before, and the at least one newly added product has never been calibrated, it is necessary to obtain product calibration information corresponding to the newly added at least one product, and According to the first commodity calibration information corresponding to the model data information, the second commodity calibration information corresponding to all commodities in the knowledge graph is determined. In some embodiments, the commodity feature increment information includes newly added commodity feature information corresponding to at least one commodity in the plurality of commodities; wherein the information according to the model data, the commodity feature increment information and the second object feature information, and constructing the knowledge graph includes: constructing the knowledge graph according to the model data information, the newly added product feature information, and the second object feature information, wherein the The knowledge graph also includes nodes corresponding to the second associated objects. In some embodiments, the product feature incremental information includes newly added product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain, and the model data incremental information includes the newly added product feature Second object feature information corresponding to the second associated object associated with the information. In some embodiments, the constructed knowledge graph includes, in addition to nodes corresponding to multiple commodities in the model data information and nodes corresponding to multiple associated objects associated with the commodity feature information corresponding to the multiple commodities, the A node corresponding to at least one associated object associated with the newly added product feature information corresponding to at least one of the products.

在一些实施例中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：确定所述多个商品中的至少一个商品中是否存在需要重新标定的商品；若是，获得所述需要重新标定的商品对应的最新商品标定信息，并根据所述最新商品标定信息以及所述第一商品标定信息确定第二商品标定信息；否则，直接将所述第一商品标定信息作为第二商品标定信息。在一些实施例中，因为该多个商品中的至少一个商品之前已经存在于区块链上，该至少一个商品也已经被标定过，因此需要先确定该至少一个商品中是否存在需要重新标定的商品，若是，需要对这部分需要重新标定的商品进行重新标定，以获得这部分需要重新标定的商品对应的最新商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。In some embodiments, the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information includes: determining whether at least one commodity in the plurality of commodities needs to be re-calibrated If it is, obtain the latest commodity calibration information corresponding to the commodity that needs to be re-calibrated, and determine the second commodity calibration information according to the latest commodity calibration information and the first commodity calibration information; otherwise, directly A commodity calibration information is used as the second commodity calibration information. In some embodiments, because at least one commodity in the plurality of commodities has existed on the blockchain before, and the at least one commodity has also been calibrated, it is necessary to first determine whether there is any commodity that needs to be re-calibrated in the at least one commodity. If it is a commodity, it is necessary to re-calibrate this part of the commodity that needs to be re-calibrated to obtain the latest commodity calibration information corresponding to this part of the commodity that needs to be re-calibrated, and according to the first commodity calibration information corresponding to the model data information, determine the knowledge map. The calibration information of the second product corresponding to all products of .

在一些实施例中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：根据所述第一商品标定信息及所述第二商品标定信息，确定商品标定增量信息；将所述模型数据增量信息以及所述商品标定增量信息确定为需要上传至区块链的模型数据更新信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品及该至少一个商品对应的商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的商品特征信息对该商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品对应的商品标定信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的新增商品特征信息及该新增商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品中需要重新标定的这部分商品对应的商品标定信息。In some embodiments, determining the model data update information that needs to be uploaded to the blockchain according to the model data increment information includes: determining according to the first commodity calibration information and the second commodity calibration information Commodity calibration increment information; determine the model data increment information and the commodity calibration increment information as model data update information that needs to be uploaded to the blockchain. In some embodiments, if the model data incremental information includes at least one newly added product and the product feature information corresponding to the at least one product in addition to the model data information obtained from the blockchain, it may be determined that the data that needs to be uploaded to the blockchain The model data update information may only include the object feature information corresponding to the associated object associated with the product feature information corresponding to the at least one product, and the product calibration information corresponding to the at least one product. In some embodiments, if the model data incremental information includes the newly added product feature information corresponding to at least one product among the multiple products in the model data information obtained from the blockchain, it may be determined that the information that needs to be uploaded to the blockchain The model data update information may only include the new product feature information corresponding to the at least one product, the object feature information corresponding to the associated object associated with the newly added product feature information, and the at least one product corresponding to the part of the product that needs to be re-calibrated. Product calibration information.

在一些实施例中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：根据所述模型数据信息及所述模型数据增量信息，确定最新模型数据信息；将所述最新模型数据信息以及所述第二商品标定信息确定为需要上传至区块链的模型数据更新信息。在一些实施例中，根据模型数据信息及模型数据增量信息，确定最新模型数据信息，最新模型数据中除了包括模型数据信息以外，还包括模型数据信息以外新增的至少一个商品对应的商品特征信息以及该商品特征信息所关联的关联对象对应的对象特征信息，还包括模型数据信息中的至少一个存在新增商品特征信息的已有商品对应的新增商品特征信息以及该新增商品特征信息关联的关联对象对应的对象特征信息。在一些实施例中，可以将最新模型数据信息以及第二商品标定信息确定为需要上传至区块链的模型数据更新信息，其中，第二商品标定信息是构建的知识图谱中的所有商品对应的商品标定信息。In some embodiments, determining the model data update information that needs to be uploaded to the blockchain according to the model data increment information includes: determining the latest model according to the model data information and the model data increment information Data information; determine the latest model data information and the second commodity calibration information as model data update information that needs to be uploaded to the blockchain. In some embodiments, the latest model data information is determined according to the model data information and the model data increment information, and the latest model data includes, in addition to the model data information, a product feature corresponding to at least one newly added product in addition to the model data information information and the object feature information corresponding to the associated object associated with the product feature information, and also includes the newly added product feature information corresponding to at least one existing product with the newly added product feature information in the model data information and the newly added product feature information Object feature information corresponding to the associated associated object. In some embodiments, the latest model data information and the second commodity calibration information may be determined as model data update information that needs to be uploaded to the blockchain, where the second commodity calibration information corresponds to all commodities in the constructed knowledge graph Product calibration information.

在一些实施例中，所述模型数据更新信息还包括所述连接关系特征信息。在一些实施例中，还可以将从构建的知识图谱中获得的连接关系特征信息也上传至区块链，以便于其他网络设备可以从区块链中获得该连接关系特征信息，并根据该连接关系特征信息、模型数据增量信息以及同样从区块链中获得的模型数据信息，构建知识图谱，可以加速知识图谱的构建过程，提高知识图谱的构建效率。In some embodiments, the model data update information further includes the connection relationship feature information. In some embodiments, the connection relationship feature information obtained from the constructed knowledge graph can also be uploaded to the blockchain, so that other network devices can obtain the connection relationship feature information from the blockchain and use the connection Relational feature information, model data incremental information, and model data information also obtained from the blockchain, to build a knowledge graph, can speed up the construction process of the knowledge graph and improve the construction efficiency of the knowledge graph.

在一些实施例中，所述方法还包括：网络设备将目标检测商品对应的目标商品特征信息输入所述更新后的商品检测模型，得到所述更新后的商品检测模型输出的与所述目标检测商品对应的商品检测信息，其中，所述商品检测信息用于指示所述目标检测商品是否是不合格商品。在一些实施例中，所述商品检测信息包括用于指示所述目标商品是否是不合格商品的指示信息，如“1”指示商品为合格商品，“0”指示商品为不合格商品。在一些实施例中，所述商品检测信息包括该目标商品是不合格商品的概率信息，如商品检测信息指示该目标商品有70％的概率为不合格商品，如商品检测信息指示该目标商品有30％的概率为合格商品。In some embodiments, the method further includes: the network device inputs the target commodity feature information corresponding to the target detection commodity into the updated commodity detection model, and obtains the output of the updated commodity detection model and the target detection model. Commodity detection information corresponding to the commodity, wherein the commodity detection information is used to indicate whether the target detection commodity is a substandard commodity. In some embodiments, the commodity detection information includes indication information for indicating whether the target commodity is a substandard commodity, for example, "1" indicates that the commodity is a qualified commodity, and "0" indicates that the commodity is a substandard commodity. In some embodiments, the commodity detection information includes probability information that the target commodity is a substandard commodity. For example, the commodity detection information indicates that the target commodity has a 70% probability of being a substandard commodity. For example, the commodity detection information indicates that the target commodity has 30% probability of qualifying items.

在一些实施例中，所述方法还包括：若所述商品检测信息指示所述目标检测商品是不合格商品，网络设备输出与所述目标检测商品存在连接关系的至少一个已标定不合格商品。在一些实施例中，所述至少一个已标定不合格商品是从更新后的知识图谱中获得的，已标定不合格商品可能与目标商品存在直接连接，也可能与目标商品存在间接连接。例如，若将商品A输入更新后的商品检测模型之后输出的商品检测信息指示商品A是不合格商品，则输出与商品A存在直接连接的已标定不合格商品B和C。可选地，还可输出与目标商品存在连接关系的至少一个已标定合格商品，以用于后续作进一步的比对或处理。In some embodiments, the method further includes: if the commodity detection information indicates that the target detection commodity is a substandard commodity, the network device outputs at least one calibrated substandard commodity that has a connection relationship with the target detection commodity. In some embodiments, the at least one calibrated unqualified commodity is obtained from the updated knowledge graph, and the calibrated unqualified commodity may have a direct connection with the target commodity or an indirect connection with the target commodity. For example, if the commodity detection information output after commodity A is input into the updated commodity detection model indicates that commodity A is a substandard commodity, the calibrated substandard commodities B and C that are directly connected to commodity A are output. Optionally, at least one calibrated qualified commodity that has a connection relationship with the target commodity can also be output for subsequent further comparison or processing.

在一些实施例中，若存在多个与所述目标检测商品存在连接关系的已标定不合格商品；其中，所述方法还包括：从所述多个已标定不合格商品确定至少一个已标定不合格商品，其中，所述至少一个已标定不合格商品中的每个已标定不合格商品与所述目标检测商品之间的连接关系对应的连接跳数小于或等于预定的跳数阈值。在一些实施例中，从更新后的知识图谱中获得与所述目标商品存在连接关系的多个已标定不合格商品，并获得所述目标商品与每个已标定不合格商品之间的它连接关系对应的连接跳数，之后从多个已标定不合格商品选择所对应的连接跳数小于或等于预定的跳数阈值的至少一个已标定不合格商品。在一些实施例中，可基于经验来设定跳数阈值，可选地，可基于针对商品检测信息的反馈信息来调整跳数阈值。In some embodiments, if there are multiple calibrated unqualified commodities that are connected to the target detection product; wherein the method further includes: determining at least one calibrated unqualified commodity from the multiple calibrated unqualified commodities A qualified commodity, wherein the connection hop count corresponding to the connection relationship between each of the at least one calibrated unqualified commodity and the target detection commodity is less than or equal to a predetermined hop count threshold. In some embodiments, a plurality of calibrated unqualified products that have a connection relationship with the target product are obtained from the updated knowledge graph, and other connections between the target product and each of the calibrated unqualified products are obtained The number of connection hops corresponding to the relationship is selected, and then at least one calibrated unqualified commodity whose corresponding connection hop number is less than or equal to the predetermined hop number threshold is selected from a plurality of calibrated unqualified commodities. In some embodiments, the hop count threshold may be set based on experience, and optionally, the hop count threshold may be adjusted based on feedback information for commodity detection information.

图2示出了根据本申请一个实施例的一种基于区块链的构建知识图谱的方法流程图，该方法包括步骤S21和步骤S22。在步骤S21中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；在步骤S22中，网络设备根据所述模型数据信息以及所述模型数据增量信息，构建知识图谱，其中，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象。Fig. 2 shows a flowchart of a method for building a knowledge graph based on a blockchain according to an embodiment of the present application, and the method includes steps S21 and S22. In step S21, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each commodity in is an unqualified commodity; in step S22, the network device constructs a knowledge graph according to the model data information and the model data increment information, wherein the knowledge graph includes a plurality of nodes, the Each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, and the target object is a commodity or an associated object.

在步骤S21中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品。其中，本实施例中的相关操作已在前述实施例中予以详述，在此不再赘述。In step S21, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each item in is a non-conforming item. The relevant operations in this embodiment have been described in detail in the foregoing embodiments, and are not repeated here.

在步骤S22中，网络设备根据所述模型数据信息以及所述模型数据增量信息，构建知识图谱，其中，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象。其中，本实施例中的相关操作已在前述实施例中予以详述，在此不再赘述。In step S22, the network device constructs a knowledge graph according to the model data information and the model data increment information, wherein the knowledge graph includes a plurality of nodes, and each node in the knowledge graph corresponds to the model A target object in the data information or the model data increment information, where the target object is a commodity or an associated object. The relevant operations in this embodiment have been described in detail in the foregoing embodiments, and are not repeated here.

图3示出了根据本申请一个实施例的一种更新商品检测模型的方法流程图，该方法包括步骤S31、步骤S32和步骤S33。在步骤S31中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；在步骤S32中，网络设备获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；在步骤S33中，网络设备根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型。Fig. 3 shows a flowchart of a method for updating a commodity detection model according to an embodiment of the present application, and the method includes step S31, step S32 and step S33. In step S31, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each commodity in is an unqualified commodity; in step S32, the network device obtains the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information. , the knowledge graph includes a plurality of nodes, each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, and the target object is a commodity or an associated object , the connection relationship feature information is used to represent the connection relationship between each node in the knowledge graph; in step S33, the network device determines the second product according to the model data increment information and the first product calibration information For commodity calibration information, the commodity detection model is updated according to the model data information, the model data increment information, the connection relationship feature information and the second commodity calibration information.

在步骤S31中，网络设备向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品。其中，本实施例中的相关操作已在前述实施例中予以详述，在此不再赘述。In step S31, the network device sends a model acquisition request to the blockchain, and receives the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each item in is a non-conforming item. The relevant operations in this embodiment have been described in detail in the foregoing embodiments, and are not repeated here.

在步骤S32中，网络设备获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系。其中，本实施例中的相关操作已在前述实施例中予以详述，在此不再赘述。In step S32, the network device obtains the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, and the knowledge graph includes a plurality of nodes. Each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent all Describe the connection relationship between each node in the knowledge graph. The relevant operations in this embodiment have been described in detail in the foregoing embodiments, and are not repeated here.

在步骤S33中，网络设备根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型。其中，本实施例中的相关操作已在前述实施例中予以详述，在此不再赘述。In step S33, the network device determines second commodity calibration information according to the model data increment information and the first commodity calibration information, and determines the second commodity calibration information according to the model data information, the model data increment information, and the connection relationship feature. information and the second commodity calibration information to update the commodity detection model. The relevant operations in this embodiment have been described in detail in the foregoing embodiments, and are not repeated here.

图4示出了根据本申请一个实施例的一种基于区块链的检测不合格商品的网络设备结构图，该设备包括一一模块11、一二模块12、一三模块13和一四模块14。一一模块11，用于向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；一二模块12，用于获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；一三模块13，用于根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；一四模块14，用于根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。Fig. 4 shows a block chain-based network device structure diagram for detecting unqualified commodities according to an embodiment of the present application, the device includes a one-one module 11, a one-two module 12, a three-module 13 and a four-module 14. A module 11 is configured to send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each commodity in is a substandard commodity; the first and second modules 12 are used to obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information. , the knowledge graph includes a plurality of nodes, each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, and the target object is a commodity or an associated object , the connection relationship feature information is used to represent the connection relationship between each node in the knowledge graph; a third module 13 is used to determine the second product according to the model data increment information and the first product calibration information Commodity calibration information, update the commodity detection model according to the model data information, the model data increment information, the connection relationship feature information and the second commodity calibration information; a fourth module 14 is used to update the commodity detection model according to the The model data incremental information is determined, the model data update information that needs to be uploaded to the blockchain is determined, and the updated commodity detection model and the model data update information are uploaded to the blockchain.

一一模块11，用于向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品。A module 11 is configured to send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, the model data information corresponding to the commodity detection model, and the first commodity calibration information, wherein the model data information includes commodity feature information corresponding to multiple commodities and object feature information corresponding to associated objects associated with the commodity feature information, and the first commodity calibration information is used to calibrate the multiple commodities Whether each item in is a non-conforming item.

在一些实施例中，响应于网络设备发送的模型获取请求，区块链会对网络设备进行身份验证，在身份验证通过后才会将商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息返回给网络设备。在一些实施例中，商品检测模型的输入为某个商品对应的商品特征信息且输出用于指示该商品是否是不合格商品的商品检测信息。在一些实施例中，商品检测信息包括用于指示所述目标商品是否是不合格商品的指示信息，如“1”指示商品为合格商品，“0”指示商品为不合格商品。在一些实施例中，商品检测信息包括该目标商品是不合格商品的概率信息，如商品检测信息指示该目标商品有70％的概率为不合格商品，如商品检测信息指示该目标商品有30％的概率为合格商品。In some embodiments, in response to a model acquisition request sent by a network device, the blockchain will perform identity verification on the network device, and only after the identity verification is passed will the commodity detection model and the model data information corresponding to the commodity detection model and The first commodity calibration information is returned to the network device. In some embodiments, the input of the commodity detection model is commodity feature information corresponding to a commodity, and the output is commodity detection information used to indicate whether the commodity is a substandard commodity. In some embodiments, the commodity detection information includes indication information for indicating whether the target commodity is a substandard commodity, for example, "1" indicates that the commodity is a qualified commodity, and "0" indicates that the commodity is a substandard commodity. In some embodiments, the commodity detection information includes probability information that the target commodity is a substandard commodity. For example, the commodity detection information indicates that the target commodity has a 70% probability of being a substandard commodity. For example, the commodity detection information indicates that the target commodity has a 30% probability. The probability of being a qualified product.

在一些实施例中，商品检测模型是基于模型数据信息、第一商品标定信息等样本数据通过训练获得的，可以是基于这些样本数据通过训练生成的商品检测模型，也可是基于这些样本数据通过训练对当前商品检测模型进行更新，将更新后的当前商品检测模型作为所述商品检测模型。在一些实施例中，模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，商品特征信息包括任何与商品的特征相关的信息，可选地，商品特征信息包括但不限于商品标题描述、商品分类标签、商品价格、商品对应的商户信息、商品评论信息、商品发货地、商品销量、商品评价信息、商品描述信息等。In some embodiments, the commodity detection model is obtained through training based on sample data such as model data information and first commodity calibration information. The current commodity detection model is updated, and the updated current commodity detection model is used as the commodity detection model. In some embodiments, the model data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information. The commodity feature information includes any information related to the features of the commodities. Optionally The commodity feature information includes, but is not limited to, commodity title description, commodity classification label, commodity price, merchant information corresponding to the commodity, commodity review information, commodity shipping location, commodity sales volume, commodity evaluation information, commodity description information, etc.

在一些实施例中，商品特征信息可有一个或多个关联对象。在一些实施例中，商品特征信息所关联的关联对象可以是该商品特征信息中包括的任意对象，例如，商品A的商品特征信息包括商品A对应的商户信息“商户B”，则该商品特征信息所关联的关联对象可以是商户B；又例如，商品A的商品特征信息包括商品A对应的商品描述信息“狗喜欢使用该商品”，则该商品特征信息所关联的关联对象可以是狗。在一些实施例中，还可以根据该商品特征信息的语义内容，将与该语义内容相关联的对象确定为该商品特征信息所关联的关联对象，例如，商品A的商品特征信息的语义内容包括“高端宠物食品品牌”，则可将与该语义内容相关联的对象“猫”、“狗”确定为该商品特征信息所关联的关联对象。在一些实施例中，关联对象可以是任何形式的任何对象，优选地，包括但不限于商户对象、用户对象、商品对象等。在一些实施例中，关联对象对应的对象特征信息包括任何与关联对象的特征相关的信息，当一个关联对象是某个商品时，该关联对象对应的对象特征信息即为该商品的商品特征信息；当一个关联对象是某个用户时，该关联对象对应的对象特征信息包括但不限于该用户上传、编辑、浏览、购买商品的历史行为信息、用户的兴趣标签信息等；当一个关联对象是某个商户时，该关联对象对应的对象特征信息包括但不限于该商户所出售的其他商品、商户的评价信息等。在一些实施例中，不合格商品包括但不限于假冒伪劣商品、违法违禁商品等。In some embodiments, item feature information may have one or more associated objects. In some embodiments, the associated object associated with the product feature information may be any object included in the product feature information. For example, if the product feature information of product A includes the merchant information "merchant B" corresponding to product A, then the product feature The associated object associated with the information may be merchant B; for another example, if the commodity feature information of commodity A includes commodity description information corresponding to commodity A "dogs like to use this commodity", the associated object associated with the commodity feature information may be dogs. In some embodiments, the object associated with the semantic content may also be determined as the associated object associated with the product feature information according to the semantic content of the product feature information. For example, the semantic content of the product feature information of product A includes: "High-end pet food brand", the objects "cat" and "dog" associated with the semantic content can be determined as the associated objects associated with the product feature information. In some embodiments, the associated object may be any object in any form, preferably, including but not limited to a merchant object, a user object, a commodity object, and the like. In some embodiments, the object feature information corresponding to the associated object includes any information related to the feature of the associated object. When an associated object is a certain commodity, the object feature information corresponding to the associated object is the commodity feature information of the commodity ; When an associated object is a user, the object feature information corresponding to the associated object includes but is not limited to the user's uploading, editing, browsing, and purchasing historical behavior information, user's interest tag information, etc.; when an associated object is For a certain merchant, the object feature information corresponding to the associated object includes, but is not limited to, other commodities sold by the merchant, evaluation information of the merchant, and the like. In some embodiments, unqualified commodities include, but are not limited to, counterfeit and shoddy commodities, illegal and prohibited commodities, and the like.

一二模块12，用于获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系。The first and second modules 12 are used to obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, and the knowledge graph includes a plurality of nodes. Each node in the knowledge graph corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent all Describe the connection relationship between each node in the knowledge graph.

在一些实施例中，模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息，商品特征增量信息可以是新增的至少一个商品对应的商品特征信息，或者，还可以是从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息。在一些实施例中，根据从区块链获得的模型数据信息以及模型数据增量信息，构建知识图谱，知识图谱中包括多个节点，每个节点可以是从区块链获得的模型数据信息中的一个商品或该商品所关联的关联对象，也可以是模型数据增量信息中的一个新增商品及该新增商品所关联的关联对象，商品特征信息或对象特征信息是对应的商品节点或关联对象节点的属性。在一些实施例中，知识图谱能够反映各个节点之间的关系，在知识图谱中，通过两个节点各自的属性(即商品节点对应的商品特征信息或关联对象节点对应的对象特征信息)，可以建立起两个节点之间的连接(即商品与商品之间的关联、商品与关联对象之间的关联、关联对象与关联对象之间的关联)，两个节点之间可以直接连接，也可以通过一个或多个其他节点间接连接，例如，商品A对应的节点与关联对象B的节点直接连接，并通过关联对象B对应的节点与商品C对应的节点间接连接；又例如，商品A的商品特征信息包括“曾经被用户U购买”，用户B的对象特征信息包括“曾经浏览过商品B”，由此通过知识图谱能够建立商品A与用户U之间的直接关联，商品B与用户U之间的直接关联，商品A与商品B之间的间接关联(也即商品A对应的节点与用户U对应的节点直接连接，商品B对应的节点与用户U对应的节点直接连接，商品A对应的节点与商品B对应的节点通过用户U对应的节点间接连接)。In some embodiments, the model data incremental information includes commodity feature incremental information and second object feature information corresponding to a second associated object associated with the commodity feature incremental information, and the commodity feature incremental information may be newly added Product feature information corresponding to at least one product, or, may also be newly added product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain. In some embodiments, a knowledge graph is constructed according to the model data information obtained from the blockchain and the incremental information of the model data. The knowledge graph includes a plurality of nodes, and each node may be from the model data information obtained from the blockchain. A commodity or an associated object associated with the commodity, it can also be a new commodity in the incremental information of the model data and the associated object associated with the new commodity, and the commodity feature information or object feature information is the corresponding commodity node or Properties of the associated object node. In some embodiments, the knowledge graph can reflect the relationship between each node. In the knowledge graph, through the respective attributes of the two nodes (that is, the product feature information corresponding to the product node or the object feature information corresponding to the associated object node), the Establish a connection between two nodes (ie, the association between commodities and commodities, the association between commodities and associated objects, the association between associated objects and associated objects), and the two nodes can be directly connected, or they can be Indirectly connected through one or more other nodes, for example, the node corresponding to commodity A is directly connected to the node of associated object B, and indirectly connected to the node corresponding to commodity C through the node corresponding to associated object B; for another example, the commodity of commodity A The feature information includes "was purchased by user U", and the object feature information of user B includes "browsed product B", so the direct association between product A and user U can be established through the knowledge graph, and the relationship between product B and user U can be established. The direct association between commodity A and commodity B (that is, the node corresponding to commodity A is directly connected to the node corresponding to user U, the node corresponding to commodity B is directly connected to the node corresponding to user U, and the node corresponding to commodity A is directly connected to the node corresponding to user U. The node and the node corresponding to the commodity B are indirectly connected through the node corresponding to the user U).

再例如，商品C的商品特征信息包括“曾经多次在电影E中出现”，电影E的对象特征信息包括“曾经多次出现商品D”，由此通过知识图谱能够建立商品C与电影E之间的直接关联，商品D与电影E之间的直接关联，商品C与商品D之间的间接关联(也即商品C对应的节点与电影E对应的节点直接连接，商品D对应的节点与电影E对应的节点直接连接，商品C对应的节点与商品D对应的节点通过电影E对应的节点间接连接)。For another example, the product feature information of product C includes "has appeared in movie E many times", and the object feature information of movie E includes "has appeared product D many times", so the relationship between product C and movie E can be established through the knowledge graph. The direct association between commodity D and movie E, the indirect association between commodity C and commodity D (that is, the node corresponding to commodity C is directly connected to the node corresponding to movie E, the node corresponding to commodity D is directly connected to the movie The node corresponding to E is directly connected, and the node corresponding to product C and the node corresponding to product D are indirectly connected through the node corresponding to movie E).

又例如，商品A的商品特征信息包括“商品描述中多次出现了‘狗’”，商品B的商品特征信息包括“商品描述中多次出现了‘猫’”，关联对象“狗”的对象特征信息中包括“与猫都是常见宠物”，关联对象“猫”的对象特征信息中包括“与狗都是常见宠物”，由此通过知识图谱能够建立商品A与关联对象“狗”之间的直接关联，商品B与关联对象“猫”之间的直接关联，关联对象“狗”与关联对象“猫”之间的直接关联，商品A与商品B之间的间接关联(也即商品A对应的节点与关联对象“狗”的节点直接连接，商品B对应的节点与关联对象“猫”对应的节点直接连接，商品A对应的节点与商品B对应的节点通过关联对象“狗”对应的节点与关联对象“猫”对应的节点间接连接)。For another example, the product feature information of product A includes "the 'dog' appears many times in the product description", and the product feature information of the product B includes "the 'cat' appears many times in the product description", and the object associated with the object "dog" The feature information includes "common pets with cats", and the object feature information of the associated object "cat" includes "common pets with dogs", so that the relationship between commodity A and the associated object "dog" can be established through the knowledge graph. The direct association between commodity B and the associated object "cat", the direct association between the associated object "dog" and the associated object "cat", the indirect association between commodity A and commodity B (that is, commodity A The corresponding node is directly connected to the node of the associated object "dog", the node corresponding to the commodity B is directly connected to the node corresponding to the associated object "cat", the node corresponding to the commodity A and the node corresponding to the commodity B are connected through the associated object "dog". The node is indirectly connected with the node corresponding to the associated object "cat").

在一些实施例中，连接关系可以是两个节点之间的直接连接关系，例如，节点A与节点B直接连接，或者，连接关系还可以是两个节点之间的间接连接关系，此时连接关系中包括两个节点之间的连接所对应的跳数，例如，节点A与节点B直接连接，则节点A到节点B的跳数为1，又例如，节点A通过节点B与节点C间接相连，则节点A到节点C的跳数为2。在一些实施例中，每个节点可以只与一个节点之间存在连接关系，也可以同时与多个节点之间存在连接关系。在一些实施例中，两个节点之间可以只存在一个连接关系，也可以同时存在多个连接关系。In some embodiments, the connection relationship may be a direct connection relationship between two nodes, for example, node A is directly connected to node B, or the connection relationship may also be an indirect connection relationship between two nodes, in which case the connection The relationship includes the number of hops corresponding to the connection between two nodes. For example, if node A is directly connected to node B, the number of hops from node A to node B is 1. For example, node A is indirectly connected to node C through node B. If connected, the number of hops from node A to node C is 2. In some embodiments, each node may only have a connection relationship with one node, or may have a connection relationship with multiple nodes at the same time. In some embodiments, only one connection relationship may exist between two nodes, or multiple connection relationships may exist simultaneously.

在一些实施例中，连接关系特征信息可以是知识图谱中各个节点之间的多个连接关系的集合。例如，商品A的商品特征信息包括“曾经被用户U1购买”，用户U1的对象特征信息包括“曾经购买过商品B”，则知识图谱中包括分别与商品A、用户U1、商品B对应的三个节点，且基于该知识图谱可获得该三个节点对应的连接关系特征信息，该连接关系特征信息用于指示商品A和用户U1具有直接连接关系“被购买”，用户U1和商品B具有直接连接关系“购买”，商品A和商品B具有间接连接关系(间接连接关系是指两个节点并未直接相连，而是通过一个或多个其他节点相连接，如本实例中，商品A和商品B通过用户U1相连接)。In some embodiments, the connection relationship feature information may be a collection of multiple connection relationships between nodes in the knowledge graph. For example, if the product feature information of product A includes "have been purchased by user U1", and the object feature information of user U1 includes "have purchased product B", then the knowledge graph includes three items corresponding to product A, user U1, and product B respectively. and based on the knowledge graph, the connection relationship feature information corresponding to the three nodes can be obtained. The connection relationship feature information is used to indicate that product A and user U1 have a direct connection relationship "purchased", and user U1 and product B have direct connection relationship "purchased". The connection relationship is "purchase", and commodity A and commodity B have an indirect connection relationship (indirect connection relationship means that the two nodes are not directly connected, but are connected through one or more other nodes, such as in this example, commodity A and commodity B is connected via user U1).

在一些实施例中，两个节点之间的连接关系是有方向的，如上例中商品A到用户U1的连接关系“被购买”是从商品A对应的节点指向用户U1对应的节点，用户U1到商品B的连接关系“购买”是从用户U1对应的节点指向商品B对应的节点。In some embodiments, the connection relationship between the two nodes is directional. For example, in the above example, the connection relationship between product A and user U1 is “purchased” from the node corresponding to product A to the node corresponding to user U1. User U1 The connection relationship "purchase" to commodity B is from the node corresponding to user U1 to the node corresponding to commodity B.

一三模块13，用于根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品及该至少一个商品对应的商品特征信息，则需要获取该新增的至少一个商品对应的商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，则需要确定该至少一个商品中是否存在需要重新标定的商品，若是，重新获取这部分需要重新标定的商品对应的商品标定信息，并根据模型数据信息对应的第一商品标定信息，确定知识图谱中的所有商品对应的第二商品标定信息。A third module 13 is configured to determine second commodity calibration information according to the model data increment information and the first commodity calibration information, and according to the model data information, the model data increment information, and the connection relationship feature information and the second commodity calibration information to update the commodity detection model. In some embodiments, if the model data incremental information includes at least one newly added product and the product feature information corresponding to the at least one product in addition to the model data information obtained from the blockchain, it is necessary to obtain the newly added at least one product Corresponding commodity calibration information, and according to the first commodity calibration information corresponding to the model data information, determine the second commodity calibration information corresponding to all commodities in the knowledge map. In some embodiments, if the model data incremental information includes new product feature information corresponding to at least one product among multiple products in the model data information obtained from the blockchain, it is necessary to determine whether the at least one product exists The product that needs to be re-calibrated, if so, re-acquire the product calibration information corresponding to the product that needs to be re-calibrated, and determine the second product calibration information corresponding to all products in the knowledge map according to the first product calibration information corresponding to the model data information. .

在一些实施例中，可以接收用户输入的该至少一个商品对应的商品标定信息。在一些实施例中，还从知识图谱中获得与该至少一个商品存在连接关系的至少一个已标定商品，根据该至少一个商品对应的商品特征信息与所述至少一个已标定商品对应的商品特征信息之间的相似度信息，对该至少一个商品进行标定并获得对应的商品标定信息。在一些实施例中，由模型训练人员人工对该至少一个商品标注商品标定信息。在一些实施例中，若知识图谱中与该至少一个商品存在连接关系的至少一个已标定商品与该商品之间具有相似的价格、相似的购买量、相似的浏览量等相似的商品特征信息，则可以根据该已标定商品是否为不合格商品，来标定该至少一个商品是否为不合格商品，例如，若该已标定商品为不合格商品，则可以标定该至少一个商品同样也为不合格商品，又例如，若该已标定商品为合格商品，则可以标定该至少一个商品同样也为合格商品。在一些实施例中，基于所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，通过训练对从区块链获得的商品检测模型进行更新。In some embodiments, commodity calibration information corresponding to the at least one commodity input by the user may be received. In some embodiments, at least one calibrated commodity that has a connection relationship with the at least one commodity is also obtained from the knowledge graph, and according to the commodity characteristic information corresponding to the at least one commodity and the commodity characteristic information corresponding to the at least one calibrated commodity The similarity information between the at least one commodity is calibrated and the corresponding commodity calibration information is obtained. In some embodiments, the at least one commodity is manually marked with commodity calibration information by a model trainer. In some embodiments, if the at least one calibrated commodity in the knowledge graph that has a connection relationship with the at least one commodity has similar commodity feature information, such as similar price, similar purchase amount, similar pageview amount, and the like, Whether the at least one commodity is a non-conforming commodity can be calibrated according to whether the calibrated commodity is a non-conforming commodity. For example, if the calibrated commodity is a non-conforming commodity, the at least one commodity can also be demarcated as a non-conforming commodity. , for another example, if the marked commodity is a qualified commodity, the at least one commodity can also be marked as a qualified commodity. In some embodiments, the product detection model obtained from the blockchain is updated through training based on the model data information, the model data increment information, the connection relationship feature information, and the second product calibration information .

一四模块14，用于根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息以外新增的至少一个商品及该至少一个商品对应的商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的商品特征信息对该商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品对应的商品标定信息，也可以包括知识图谱中的所有商品对应的商品特征信息以及所有商品特征信息所关联的所有关联对象对应的所有对象特征信息以及所有商品对应的所有商品标定信息。在一些实施例中，若模型数据增量信息包括从区块链获得的模型数据信息中的多个商品中的至少一个商品对应的新增商品特征信息，则可以确定需要上传至区块链的模型数据更新信息可以仅包括该至少一个商品对应的新增商品特征信息及该新增商品特征信息所关联的关联对象对应的对象特征信息以及该至少一个商品中需要重新标定的这部分商品对应的商品标定信息，也可以包括知识图谱中的所有商品对应的商品特征信息以及所有商品特征信息所关联的所有关联对象对应的所有对象特征信息以及所有商品对应的商品标定信息。A fourth module 14 is used to determine the model data update information that needs to be uploaded to the blockchain according to the model data increment information, and upload the updated commodity detection model and the model data update information to the blockchain. In some embodiments, if the model data incremental information includes at least one newly added product and the product feature information corresponding to the at least one product in addition to the model data information obtained from the blockchain, it may be determined that the data that needs to be uploaded to the blockchain The model data update information may only include the product feature information corresponding to the at least one product, the object feature information corresponding to the associated object associated with the product feature information, and the product calibration information corresponding to the at least one product, or may include all the knowledge graphs. Product feature information corresponding to the product, all object feature information corresponding to all associated objects associated with all product feature information, and all product calibration information corresponding to all products. In some embodiments, if the model data incremental information includes the newly added product feature information corresponding to at least one product among the multiple products in the model data information obtained from the blockchain, it may be determined that the information that needs to be uploaded to the blockchain The model data update information may only include the new product feature information corresponding to the at least one product, the object feature information corresponding to the associated object associated with the newly added product feature information, and the at least one product corresponding to the part of the product that needs to be re-calibrated. The product calibration information may also include product feature information corresponding to all products in the knowledge graph, all object feature information corresponding to all associated objects associated with all product feature information, and product calibration information corresponding to all products.

在一些实施例中，所述设备还用于：根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device is further configured to: construct the knowledge graph according to the model data information and the model data increment information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述模型数据信息还包括所述商品检测模型对应的原始连接关系特征信息，所述原始连接关系特征信息是根据所述商品特征信息及所述对象特征信息构建的原始知识图谱获得的；其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱，包括：根据所述模型数据信息、所述模型数据增量信息以及所述原始连接关系特征信息，构建所述知识图谱。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the model data information further includes original connection relationship feature information corresponding to the product detection model, where the original connection relationship feature information is original knowledge constructed according to the product feature information and the object feature information Obtained from a graph; wherein, constructing the knowledge graph according to the model data information and the model data increment information includes: according to the model data information, the model data increment information and the original connection The relational feature information is used to construct the knowledge graph. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息；其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建知识图谱，包括：根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the model data incremental information includes commodity feature incremental information and second object feature information corresponding to a second associated object associated with the commodity feature incremental information; wherein the model data is based on the model. Using the data information and the model data increment information to construct a knowledge graph includes: constructing the knowledge graph according to the model data information, the commodity feature increment information and the second object feature information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述设备还用于：根据所述商品特征增量信息，确定所述商品特征增量信息所关联的第二关联对象，并获取所述第二关联对象对应的第二对象特征信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device is further configured to: determine, according to the commodity feature incremental information, a second associated object associated with the commodity feature incremental information, and obtain a second associated object corresponding to the second associated object Object feature information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述商品特征增量信息中包括一个或多个对象；其中，所述确定所述商品特征增量信息所关联的第二关联对象，包括：将所述一个或多个对象中的至少一个对象作为所述商品特征增量信息所关联的第二关联对象。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the commodity feature increment information includes one or more objects; wherein the determining a second associated object associated with the commodity feature increment information includes: adding the one or more objects At least one of the objects is used as a second associated object associated with the commodity feature increment information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述将所述一个或多个对象中的至少一个对象作为该商品特征增量信息所关联的第二关联对象，包括：从所述一个或多个对象中确定至少一个对象，并将所述至少一个对象作为所述商品特征增量信息所关联的第二关联对象。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, using at least one of the one or more objects as the second associated object associated with the commodity feature incremental information includes: determining at least one object from the one or more objects object, and use the at least one object as a second associated object associated with the commodity feature incremental information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述从所述一个或多个对象中确定至少一个对象，包括：根据所述一个或多个对象中每个对象在所述商品特征增量信息中的比重，从所述一个或多个对象中确定至少一个对象，其中，所述至少一个对象中的每个对象在所述商品特征增量信息中的比重满足预定的比重阈值。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the determining at least one object from the one or more objects includes: according to the proportion of each object in the one or more objects in the commodity feature incremental information, from the At least one object is determined from the one or more objects, wherein the proportion of each object in the at least one object in the commodity feature increment information satisfies a predetermined proportion threshold. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述设备还用于：根据每个对象在所述商品特征增量信息中的出现次数，确定该对象在所述商品特征增量信息中的比重。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device is further configured to: determine the proportion of each object in the product feature incremental information according to the number of occurrences of each object in the product feature incremental information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述设备还英语：根据每个对象在所述商品特征增量信息中的语义重要程度，确定该对象在所述商品特征增量信息中的比重。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device also: according to the semantic importance of each object in the commodity feature incremental information, determine the proportion of the object in the commodity feature incremental information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述商品特征增量信息包括新增的至少一个商品对应的第一商品特征信息；其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：根据所述模型数据信息、所述第一商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述新增的至少一个商品对应的节点以及与所述第二关联对象对应的节点。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the product feature increment information includes first product feature information corresponding to at least one newly added product; wherein the information based on the model data, the product feature increment information and the first product feature information Two object feature information, and constructing the knowledge graph includes: constructing the knowledge graph according to the model data information, the first commodity feature information and the second object feature information, wherein the knowledge graph also includes It includes a node corresponding to the newly added at least one commodity and a node corresponding to the second associated object. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：获得所述新增的至少一个商品对应的新增商品标定信息，并根据所述新增商品标定信息以及所述第一商品标定信息确定第二商品标定信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information includes: obtaining newly added commodity calibration information corresponding to the newly added at least one commodity, and determining second commodity calibration information according to the newly added commodity calibration information and the first commodity calibration information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述商品特征增量信息包括所述多个商品中的至少一个商品对应的新增商品特征信息；其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：根据所述模型数据信息、所述新增商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述第二关联对象对应的节点。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the commodity feature increment information includes newly added commodity feature information corresponding to at least one commodity in the plurality of commodities; wherein the information according to the model data, the commodity feature increment information and the second object feature information, and constructing the knowledge graph includes: constructing the knowledge graph according to the model data information, the newly added product feature information, and the second object feature information, wherein the The knowledge graph also includes nodes corresponding to the second associated objects. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：确定所述多个商品中的至少一个商品中是否存在需要重新标定的商品；若是，获得所述需要重新标定的商品对应的最新商品标定信息，并根据所述最新商品标定信息以及所述第一商品标定信息确定第二商品标定信息；否则，直接将所述第一商品标定信息作为第二商品标定信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information includes: determining whether at least one commodity in the plurality of commodities needs to be re-calibrated If it is, obtain the latest commodity calibration information corresponding to the commodity that needs to be re-calibrated, and determine the second commodity calibration information according to the latest commodity calibration information and the first commodity calibration information; otherwise, directly A commodity calibration information is used as the second commodity calibration information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：根据所述第一商品标定信息及所述第二商品标定信息，确定商品标定增量信息；将所述模型数据增量信息以及所述商品标定增量信息确定为需要上传至区块链的模型数据更新信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the determining, according to the model data increment information, the model data update information that needs to be uploaded to the blockchain includes: determining, according to the first commodity calibration information and the second commodity calibration information, Commodity calibration increment information; determine the model data increment information and the commodity calibration increment information as model data update information that needs to be uploaded to the blockchain. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：根据所述模型数据信息及所述模型数据增量信息，确定最新模型数据信息；将所述最新模型数据信息以及所述第二商品标定信息确定为需要上传至区块链的模型数据更新信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, determining the model data update information that needs to be uploaded to the blockchain according to the model data increment information includes: determining the latest model according to the model data information and the model data increment information Data information; determine the latest model data information and the second commodity calibration information as model data update information that needs to be uploaded to the blockchain. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述模型数据更新信息还包括所述连接关系特征信息。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the model data update information further includes the connection relationship feature information. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述设备还用于：将目标检测商品对应的目标商品特征信息输入所述更新后的商品检测模型，得到所述更新后的商品检测模型输出的与所述目标检测商品对应的商品检测信息，其中，所述商品检测信息用于指示所述目标检测商品是否是不合格商品。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device is further configured to: input the target commodity feature information corresponding to the target detection commodity into the updated commodity detection model, and obtain the target detection commodity outputted by the updated commodity detection model and the target detection commodity Corresponding commodity detection information, wherein the commodity detection information is used to indicate whether the target detection commodity is a substandard commodity. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，所述设备还用于：若所述商品检测信息指示所述目标检测商品是不合格商品，网络设备输出与所述目标检测商品存在连接关系的至少一个已标定不合格商品。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, the device is further configured to: if the commodity detection information indicates that the target detection commodity is a substandard commodity, the network device outputs at least one calibrated substandard commodity that has a connection relationship with the target detection commodity . Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

在一些实施例中，若存在多个与所述目标检测商品存在连接关系的已标定不合格商品；其中，所述设备还用于：从所述多个已标定不合格商品确定至少一个已标定不合格商品，其中，所述至少一个已标定不合格商品中的每个已标定不合格商品与所述目标检测商品之间的连接关系对应的连接跳数小于或等于预定的跳数阈值。在此，相关操作与图1所示实施例相同或相近，故不再赘述，在此以引用方式包含于此。In some embodiments, if there are a plurality of calibrated unqualified commodities that have a connection relationship with the target detection commodity; wherein, the device is further configured to: determine at least one calibrated unqualified commodity from the plurality of calibrated unqualified commodities Unqualified commodities, wherein the connection hop count corresponding to the connection relationship between each of the at least one calibrated unqualified commodity and the target detection commodity is less than or equal to a predetermined hop count threshold. Here, the related operations are the same as or similar to the embodiment shown in FIG. 1 , so they are not repeated here, but are incorporated herein by reference.

图5示出了可被用于实施本申请中所述的各个实施例的示例性系统。FIG. 5 illustrates an exemplary system that may be used to implement various embodiments described in this application.

如图5所示在一些实施例中，系统300能够作为各所述实施例中的任意一个设备。在一些实施例中，系统300可包括具有指令的一个或多个计算机可读介质(例如，系统存储器或NVM/存储设备320)以及与该一个或多个计算机可读介质耦合并被配置为执行指令以实现模块从而执行本申请中所述的动作的一个或多个处理器(例如，(一个或多个)处理器305)。As shown in FIG. 5, in some embodiments, thesystem 300 can function as any of the devices in each of the described embodiments. In some embodiments,system 300 may include one or more computer-readable media (eg, system memory or NVM/storage device 320 ) having instructions and be coupled to the one or more computer-readable media and configured to execute Instructions to implement a module to perform one or more processors (eg, processor(s) 305 ) to perform the actions described herein.

对于一个实施例，系统控制模块310可包括任意适当的接口控制器，以向(一个或多个)处理器305中的至少一个和/或与系统控制模块310通信的任意适当的设备或组件提供任意适当的接口。For one embodiment, thesystem control module 310 may include any suitable interface controller to provide at least one of the processor(s) 305 and/or any suitable device or component in communication with thesystem control module 310 any appropriate interface.

系统控制模块310可包括存储器控制器模块330，以向系统存储器315提供接口。存储器控制器模块330可以是硬件模块、软件模块和/或固件模块。Thesystem control module 310 may include a memory controller module 330 to provide an interface to thesystem memory 315 . The memory controller module 330 may be a hardware module, a software module, and/or a firmware module.

系统存储器315可被用于例如为系统300加载和存储数据和/或指令。对于一个实施例，系统存储器315可包括任意适当的易失性存储器，例如，适当的DRAM。在一些实施例中，系统存储器315可包括双倍数据速率类型四同步动态随机存取存储器(DDR4SDRAM)。System memory 315 may be used, for example, to load and store data and/or instructions forsystem 300 . For one embodiment,system memory 315 may include any suitable volatile memory, eg, suitable DRAM. In some embodiments,system memory 315 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

对于一个实施例，系统控制模块310可包括一个或多个输入/输出(I/O)控制器，以向NVM/存储设备320及(一个或多个)通信接口325提供接口。For one embodiment,system control module 310 may include one or more input/output (I/O) controllers to provide interfaces to NVM/storage device 320 and communication interface(s) 325 .

例如，NVM/存储设备320可被用于存储数据和/或指令。NVM/存储设备320可包括任意适当的非易失性存储器(例如，闪存)和/或可包括任意适当的(一个或多个)非易失性存储设备(例如，一个或多个硬盘驱动器(HDD)、一个或多个光盘(CD)驱动器和/或一个或多个数字通用光盘(DVD)驱动器)。For example, NVM/storage device 320 may be used to store data and/or instructions. NVM/storage device 320 may include any suitable non-volatile memory (eg, flash memory) and/or may include any suitable non-volatile storage device(s) (eg, one or more hard drives ( HDD), one or more compact disc (CD) drives and/or one or more digital versatile disc (DVD) drives).

NVM/存储设备320可包括在物理上作为系统300被安装在其上的设备的一部分的存储资源，或者其可被该设备访问而不必作为该设备的一部分。例如，NVM/存储设备320可通过网络经由(一个或多个)通信接口325进行访问。NVM/storage device 320 may include storage resources that are physically part of the device on whichsystem 300 is installed, or it may be accessed by the device without necessarily being part of the device. For example, the NVM/storage device 320 is accessible via the communication interface(s) 325 over a network.

(一个或多个)通信接口325可为系统300提供接口以通过一个或多个网络和/或与任意其他适当的设备通信。系统300可根据一个或多个无线网络标准和/或协议中的任意标准和/或协议来与无线网络的一个或多个组件进行无线通信。Communication interface(s) 325 may provide an interface forsystem 300 to communicate over one or more networks and/or with any other suitable device.System 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and/or protocols.

对于一个实施例，(一个或多个)处理器305中的至少一个可与系统控制模块310的一个或多个控制器(例你如，存储器控制器模块330)的逻辑封装在一起。对于一个实施例，(一个或多个)处理器305中的至少一个可与系统控制模块310的一个或多个控制器的逻辑封装在一起以形成系统级封装(SiP)。对于一个实施例，(一个或多个)处理器305中的至少一个可与系统控制模块310的一个或多个控制器的逻辑集成在同一模具上。对于一个实施例，(一个或多个)处理器305中的至少一个可与系统控制模块310的一个或多个控制器的逻辑集成在同一模具上以形成片上系统(SoC)。For one embodiment, at least one of the processor(s) 305 may be packaged with the logic of one or more controllers of the system control module 310 (eg, memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged with logic of one or more controllers of thesystem control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of thesystem control module 310 . For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic of one or more controllers of thesystem control module 310 to form a system on a chip (SoC).

在各个实施例中，系统300可以但不限于是：服务器、工作站、台式计算设备或移动计算设备(例如，膝上型计算设备、持有计算设备、平板电脑、上网本等)。在各个实施例中，系统300可具有更多或更少的组件和/或不同的架构。例如，在一些实施例中，系统300包括一个或多个摄像机、键盘、液晶显示器(LCD)屏幕(包括触屏显示器)、非易失性存储器端口、多个天线、图形芯片、专用集成电路(ASIC)和扬声器。In various embodiments,system 300 may be, but is not limited to, a server, workstation, desktop computing device, or mobile computing device (eg, laptop computing device, handheld computing device, tablet computer, netbook, etc.). In various embodiments,system 300 may have more or fewer components and/or different architectures. For example, in some embodiments,system 300 includes one or more cameras, keyboards, liquid crystal display (LCD) screens (including touchscreen displays), non-volatile memory ports, multiple antennas, graphics chips, application specific integrated circuits ( ASIC) and speakers.

本申请还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机代码，当所述计算机代码被执行时，如前任一项所述的方法被执行。The present application also provides a computer-readable storage medium, where the computer-readable storage medium stores computer code, and when the computer code is executed, the method described in any preceding item is executed.

本申请还提供了一种计算机程序产品，当所述计算机程序产品被计算机设备执行时，如前任一项所述的方法被执行。The present application also provides a computer program product, when the computer program product is executed by a computer device, the method according to any one of the preceding items is executed.

本申请还提供了一种计算机设备，所述计算机设备包括：The present application also provides a computer device, the computer device comprising:

一个或多个处理器；one or more processors;

存储器，用于存储一个或多个计算机程序；memory for storing one or more computer programs;

当所述一个或多个计算机程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如前任一项所述的方法。The one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of any preceding item.

需要注意的是，本申请可在软件和/或软件与硬件的组合体中被实施，例如，可采用专用集成电路(ASIC)、通用目的计算机或任何其他类似硬件设备来实现。在一个实施例中，本申请的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地，本申请的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中，例如，RAM存储器，磁或光驱动器或软磁盘及类似设备。另外，本申请的一些步骤或功能可采用硬件来实现，例如，作为与处理器配合从而执行各个步骤或功能的电路。It should be noted that the present application may be implemented in software and/or a combination of software and hardware, eg, an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs of the present application (including associated data structures) may be stored on a computer-readable recording medium, such as RAM memory, magnetic or optical drives or floppy disks, and the like. In addition, some steps or functions of the present application may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

另外，本申请的一部分可被应用为计算机程序产品，例如计算机程序指令，当其被计算机执行时，通过该计算机的操作，可以调用或提供根据本申请的方法和/或技术方案。本领域技术人员应能理解，计算机程序指令在计算机可读介质中的存在形式包括但不限于源文件、可执行文件、安装包文件等，相应地，计算机程序指令被计算机执行的方式包括但不限于：该计算机直接执行该指令，或者该计算机编译该指令后再执行对应的编译后程序，或者该计算机读取并执行该指令，或者该计算机读取并安装该指令后再执行对应的安装后程序。在此，计算机可读介质可以是可供计算机访问的任意可用的计算机可读存储介质或通信介质。In addition, a part of the present application can be applied as a computer program product, such as computer program instructions, which when executed by a computer, through the operation of the computer, can invoke or provide methods and/or technical solutions according to the present application. Those skilled in the art should understand that the existing forms of computer program instructions in computer-readable media include but are not limited to source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include but are not limited to Limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding post-installation program. program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium that can be accessed by a computer.

通信介质包括藉此包含例如计算机可读指令、数据结构、程序模块或其他数据的通信信号被从一个系统传送到另一系统的介质。通信介质可包括有导的传输介质(诸如电缆和线(例如，光纤、同轴等))和能传播能量波的无线(未有导的传输)介质，诸如声音、电磁、RF、微波和红外。计算机可读指令、数据结构、程序模块或其他数据可被体现为例如无线介质(诸如载波或诸如被体现为扩展频谱技术的一部分的类似机制)中的已调制数据信号。术语“已调制数据信号”指的是其一个或多个特征以在信号中编码信息的方式被更改或设定的信号。调制可以是模拟的、数字的或混合调制技术。Communication media includes media by which communication signals containing, for example, computer readable instructions, data structures, program modules or other data are transmitted from one system to another. Communication media may include conducted transmission media such as cables and wires (eg, fiber optic, coaxial, etc.) and wireless (unconducted transmission) media capable of propagating energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared . Computer readable instructions, data structures, program modules or other data may be embodied, for example, as a modulated data signal in a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are altered or set in a manner that encodes information in the signal. Modulation can be analog, digital or hybrid modulation techniques.

作为示例而非限制，计算机可读存储介质可包括以用于存储诸如计算机可读指令、数据结构、程序模块或其它数据的信息的任何方法或技术实现的易失性和非易失性、可移动和不可移动的介质。例如，计算机可读存储介质包括，但不限于，易失性存储器，诸如随机存储器(RAM,DRAM,SRAM)；以及非易失性存储器，诸如闪存、各种只读存储器(ROM,PROM,EPROM,EEPROM)、磁性和铁磁/铁电存储器(MRAM,FeRAM)；以及磁性和光学存储设备(硬盘、磁带、CD、DVD)；或其它现在已知的介质或今后开发的能够存储供计算机系统使用的计算机可读信息/数据。By way of example and not limitation, computer-readable storage media may include volatile and non-volatile, readable storage media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Removable and non-removable media. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM) , EEPROM), magnetic and ferromagnetic/ferroelectric memory (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, tapes, CDs, DVDs); or other media now known or later developed capable of storing data for computer systems Computer readable information/data used.

在此，根据本申请的一个实施例包括一个装置，该装置包括用于存储计算机程序指令的存储器和用于执行程序指令的处理器，其中，当该计算机程序指令被该处理器执行时，触发该装置运行基于前述根据本申请的多个实施例的方法和/或技术方案。Here, an embodiment according to the present application includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, a trigger is The apparatus operates based on the aforementioned methods and/or technical solutions according to various embodiments of the present application.

对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。装置权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一，第二等词语用来表示名称，而并不表示任何特定的顺序。It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but that the present application may be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Accordingly, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the application is to be defined by the appended claims rather than the foregoing description, which is therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in this application. Any reference signs in the claims shall not be construed as limiting the involved claim. Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Several units or means recited in the device claims can also be realized by one unit or means by means of software or hardware. The terms first, second, etc. are used to denote names and do not denote any particular order.

Claims (20)

Translated fromChinese

1.一种基于区块链的检测不合格商品的方法，其中，所述方法包括：1. A method for detecting substandard goods based on blockchain, wherein the method comprises:向区块链发送模型获取请求，接收所述区块链根据所述模型获取请求所返回的商品检测模型以及所述商品检测模型对应的模型数据信息和第一商品标定信息，其中，所述模型数据信息包括多个商品对应的商品特征信息以及所述商品特征信息所关联的关联对象对应的对象特征信息，所述第一商品标定信息用于标定所述多个商品中的每个商品是否是不合格商品；Send a model acquisition request to the blockchain, and receive the commodity detection model returned by the blockchain according to the model acquisition request, as well as model data information and first commodity calibration information corresponding to the commodity detection model, wherein the model The data information includes commodity feature information corresponding to a plurality of commodities and object feature information corresponding to an associated object associated with the commodity feature information, and the first commodity calibration information is used to demarcate whether each commodity in the plurality of commodities is Substandard goods;获得知识图谱对应的连接关系特征信息，其中，所述知识图谱是根据所述模型数据信息以及模型数据增量信息构建得到的，所述知识图谱包括多个节点，所述知识图谱中的每个节点对应所述模型数据信息或所述模型数据增量信息中的一个目标对象，所述目标对象为一个商品或一个关联对象，所述连接关系特征信息用于表征所述知识图谱中的各个节点之间的连接关系；Obtain the connection relationship feature information corresponding to the knowledge graph, wherein the knowledge graph is constructed according to the model data information and the model data increment information, the knowledge graph includes a plurality of nodes, and each of the knowledge graphs The node corresponds to a target object in the model data information or the model data incremental information, the target object is a commodity or an associated object, and the connection relationship feature information is used to represent each node in the knowledge graph connection between;根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，根据所述模型数据信息、所述模型数据增量信息、所述连接关系特征信息以及所述第二商品标定信息，更新所述商品检测模型；The second commodity calibration information is determined according to the model data increment information and the first commodity calibration information, and the second commodity calibration information is determined according to the model data information, the model data increment information, the connection relationship feature information and the second commodity Calibration information, update the commodity detection model;根据所述模型数据增量信息，确定需要上传至所述区块链的模型数据更新信息，并将更新后的商品检测模型以及所述模型数据更新信息上传至所述区块链。According to the model data increment information, determine the model data update information that needs to be uploaded to the blockchain, and upload the updated commodity detection model and the model data update information to the blockchain.2.根据权利要求1所述的方法，其中，所述获得知识图谱对应的连接关系特征信息，之前还包括：2. The method according to claim 1, wherein, before obtaining the connection relationship feature information corresponding to the knowledge graph, the method further comprises:根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱。The knowledge graph is constructed according to the model data information and the model data increment information.3.根据权利要求2所述的方法，其中，所述模型数据信息还包括所述商品检测模型对应的原始连接关系特征信息，所述原始连接关系特征信息是根据所述商品特征信息及所述对象特征信息构建的原始知识图谱获得的；3. The method according to claim 2, wherein the model data information further comprises original connection relationship feature information corresponding to the product detection model, the original connection relationship feature information is based on the product feature information and the Obtained from the original knowledge graph constructed by object feature information;其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建所述知识图谱，包括：Wherein, constructing the knowledge graph according to the model data information and the model data increment information includes:根据所述模型数据信息、所述模型数据增量信息以及所述原始连接关系特征信息，构建所述知识图谱。The knowledge graph is constructed according to the model data information, the model data increment information and the original connection relationship feature information.4.根据权利要求2所述的方法，其中，所述模型数据增量信息包括商品特征增量信息及所述商品特征增量信息所关联的第二关联对象对应的第二对象特征信息；4. The method according to claim 2, wherein the model data increment information comprises commodity feature increment information and second object characteristic information corresponding to a second associated object associated with the commodity characteristic increment information;其中，所述根据所述模型数据信息以及所述模型数据增量信息，构建知识图谱，包括：Wherein, constructing a knowledge graph according to the model data information and the model data increment information includes:根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱。The knowledge graph is constructed according to the model data information, the commodity feature increment information and the second object feature information.5.根据权利要求4所述的方法，其中，所述方法还包括：5. The method of claim 4, wherein the method further comprises:根据所述商品特征增量信息，确定所述商品特征增量信息所关联的第二关联对象，并获取所述第二关联对象对应的第二对象特征信息。According to the commodity feature increment information, a second associated object associated with the commodity feature increment information is determined, and second object feature information corresponding to the second associated object is acquired.6.根据权利要求5所述的方法，其中，所述商品特征增量信息中包括一个或多个对象；6. The method according to claim 5, wherein the commodity feature incremental information includes one or more objects;其中，所述确定所述商品特征增量信息所关联的第二关联对象，包括：Wherein, the determining the second associated object associated with the commodity feature incremental information includes:将所述一个或多个对象中的至少一个对象作为所述商品特征增量信息所关联的第二关联对象。Taking at least one object among the one or more objects as the second associated object associated with the commodity feature increment information.7.根据权利要求6所述的方法，其中，所述将所述一个或多个对象中的至少一个对象作为该商品特征增量信息所关联的第二关联对象，包括：7. The method according to claim 6, wherein the using at least one of the one or more objects as the second associated object associated with the commodity feature incremental information comprises:从所述一个或多个对象中确定至少一个对象，并将所述至少一个对象作为所述商品特征增量信息所关联的第二关联对象。At least one object is determined from the one or more objects, and the at least one object is used as a second associated object associated with the commodity feature increment information.8.根据权利要求7所述的方法，其中，所述从所述一个或多个对象中确定至少一个对象，包括：8. The method of claim 7, wherein the determining at least one object from the one or more objects comprises:根据所述一个或多个对象中每个对象在所述商品特征增量信息中的比重，从所述一个或多个对象中确定至少一个对象，其中，所述至少一个对象中的每个对象在所述商品特征增量信息中的比重满足预定的比重阈值。Determine at least one object from the one or more objects according to the proportion of each of the one or more objects in the commodity feature incremental information, wherein each object of the at least one object The proportion in the commodity feature increment information satisfies a predetermined proportion threshold.9.根据权利要求8所述的方法，其中，所述方法还包括：9. The method of claim 8, wherein the method further comprises:根据每个对象在所述商品特征增量信息中的出现次数，确定该对象在所述商品特征增量信息中的比重。According to the appearance times of each object in the commodity feature incremental information, the proportion of the object in the commodity feature incremental information is determined.10.根据权利要求8所述的方法，其中，所述方法还包括：10. The method of claim 8, wherein the method further comprises:根据每个对象在所述商品特征增量信息中的语义重要程度，确定该对象在所述商品特征增量信息中的比重。According to the semantic importance of each object in the commodity feature incremental information, the proportion of the object in the commodity feature incremental information is determined.11.根据权利要求4所述的方法，其中，所述商品特征增量信息包括新增的至少一个商品对应的第一商品特征信息；11. The method according to claim 4, wherein the commodity feature increment information comprises first commodity feature information corresponding to at least one newly added commodity;其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：Wherein, constructing the knowledge graph according to the model data information, the commodity feature increment information and the second object feature information includes:根据所述模型数据信息、所述第一商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述新增的至少一个商品对应的节点以及与所述第二关联对象对应的节点。The knowledge graph is constructed according to the model data information, the feature information of the first product and the feature information of the second object, wherein the knowledge graph further includes a node corresponding to the newly added at least one product and A node corresponding to the second associated object.12.根据权利要求11所述的方法，其中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：12. The method according to claim 11, wherein the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information comprises:获得所述新增的至少一个商品对应的新增商品标定信息，并根据所述新增商品标定信息以及所述第一商品标定信息确定第二商品标定信息。The newly added commodity calibration information corresponding to the newly added at least one commodity is obtained, and the second commodity calibration information is determined according to the newly added commodity calibration information and the first commodity calibration information.13.根据权利要求4所述的方法，其中，所述商品特征增量信息包括所述多个商品中的至少一个商品对应的新增商品特征信息；13. The method according to claim 4, wherein the commodity feature increment information comprises newly added commodity feature information corresponding to at least one commodity in the plurality of commodities;其中，所述根据所述模型数据信息、所述商品特征增量信息及所述第二对象特征信息，构建所述知识图谱，包括：Wherein, constructing the knowledge graph according to the model data information, the commodity feature increment information and the second object feature information includes:根据所述模型数据信息、所述新增商品特征信息及所述第二对象特征信息，构建所述知识图谱，其中，所述知识图谱中还包括所述第二关联对象对应的节点。The knowledge graph is constructed according to the model data information, the feature information of the newly added product, and the feature information of the second object, wherein the knowledge graph further includes a node corresponding to the second associated object.14.根据权利要求13所述的方法，其中，所述根据所述模型数据增量信息以及所述第一商品标定信息确定第二商品标定信息，包括：14. The method according to claim 13, wherein the determining the second commodity calibration information according to the model data increment information and the first commodity calibration information comprises:确定所述多个商品中的至少一个商品中是否存在需要重新标定的商品；若是，获得所述需要重新标定的商品对应的最新商品标定信息，并根据所述最新商品标定信息以及所述第一商品标定信息确定第二商品标定信息；否则，直接将所述第一商品标定信息作为第二商品标定信息。Determine whether there is a commodity that needs to be re-calibrated in at least one of the plurality of commodities; if so, obtain the latest commodity calibration information corresponding to the commodity that needs to be re-calibrated, and obtain the latest commodity calibration information according to the latest commodity calibration information and the first The commodity calibration information determines the second commodity calibration information; otherwise, the first commodity calibration information is directly used as the second commodity calibration information.15.根据权利要求1所述的方法，其中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：15. The method according to claim 1, wherein, according to the model data increment information, determining the model data update information that needs to be uploaded to the blockchain comprises:将所述模型数据增量信息以及商品标定增量信息确定为需要上传至区块链的模型数据更新信息。The model data incremental information and the commodity calibration incremental information are determined as model data update information that needs to be uploaded to the blockchain.16.根据权利要求1所述的方法，其中，所述根据所述模型数据增量信息，确定需要上传至区块链的模型数据更新信息，包括：16. The method according to claim 1, wherein, according to the model data increment information, determining the model data update information that needs to be uploaded to the blockchain comprises:根据所述模型数据信息及所述模型数据增量信息，确定最新模型数据信息；determining the latest model data information according to the model data information and the model data increment information;将所述最新模型数据信息以及所述第二商品标定信息确定为需要上传至区块链的模型数据更新信息。The latest model data information and the second commodity calibration information are determined as model data update information that needs to be uploaded to the blockchain.17.根据权利要求15或16所述的方法，其中，所述模型数据更新信息还包括所述连接关系特征信息。17. The method according to claim 15 or 16, wherein the model data update information further comprises the connection relationship feature information.18.根据权利要求1至17中任一项所述的方法，其中，所述方法还包括：18. The method of any one of claims 1 to 17, wherein the method further comprises:将目标检测商品对应的目标商品特征信息输入所述更新后的商品检测模型，得到所述更新后的商品检测模型输出的与所述目标检测商品对应的商品检测信息，其中，所述商品检测信息用于指示所述目标检测商品是否是不合格商品。Inputting the target commodity feature information corresponding to the target detection commodity into the updated commodity detection model to obtain commodity detection information corresponding to the target detection commodity output by the updated commodity detection model, wherein the commodity detection information It is used to indicate whether the target detection commodity is an unqualified commodity.19.一种基于区块链的检测不合格商品的设备，其中，所述设备包括：19. A blockchain-based device for detecting substandard commodities, wherein the device comprises:处理器；以及processor; and被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器执行如权利要求1至18中任一项所述的方法。a memory arranged to store computer-executable instructions which, when executed, cause the processor to perform a method as claimed in any one of claims 1 to 18.20.一种存储指令的计算机可读介质，所述指令在被执行时使得系统进行如权利要求1至18中任一项所述方法的操作。20. A computer readable medium storing instructions which, when executed, cause a system to operate the method of any one of claims 1 to 18.

Images