相关申请的交叉引用CROSS-REFERENCE TO RELATED APPLICATIONS
本公开要求于2023年08月28日提交的申请号为202311094066.7、名称为“意图预测方法、装置、存储介质与电子设备”的中国专利申请的优先权，该中国专利申请的全部内容通过引用并入全文。The present disclosure claims priority to Chinese patent application numbered 202311094066.7, filed on August 28, 2023, and entitled “Intent Prediction Method, Device, Storage Medium and Electronic Device”, the entire contents of which are incorporated herein by reference.
本公开涉及大数据技术领域，尤其涉及一种意图预测方法、意图预测装置、计算机可读存储介质与电子设备。The present disclosure relates to the field of big data technology, and in particular to an intention prediction method, an intention prediction device, a computer-readable storage medium, and an electronic device.
随着移动互联网的飞速发展和大数据的时代的来临，数据分析变得越来越重要。尤其在通信行业，通信运营商不仅作为用户通信数据信息的传输管道提供者，更是数据信息的存储者。科学有效地利用数据信息进行数据分析，挖掘用户数据的意图和潜在价值，合理应用到用户营销服务，对运营商进行运营数字化转型具有重要意义。With the rapid development of mobile Internet and the advent of the era of big data, data analysis has become increasingly important. Especially in the communications industry, communications operators are not only the transmission pipeline providers of user communication data information, but also the data storage providers. Scientifically and effectively using data information for data analysis, mining the intention and potential value of user data, and rationally applying it to user marketing services are of great significance to operators' digital transformation of operations.
相关技术中的意图预测方法无法满足当前用户数据量庞大的应用场景，使得用户意图预测过程速度慢，且准确度低下，造成用户的意图预测效率低下。The intention prediction method in the related technology cannot meet the current application scenarios with huge amounts of user data, which makes the user intention prediction process slow and inaccurate, resulting in low efficiency in user intention prediction.
发明内容Summary of the invention
本公开提供了一种意图预测方法、意图预测装置、计算机可读存储介质与电子设备，进而至少在一定程度上改善意图预测效率低下的问题。The present disclosure provides an intention prediction method, an intention prediction device, a computer-readable storage medium and an electronic device, thereby improving the problem of low efficiency of intention prediction at least to a certain extent.
本公开的其他特性和优点将通过下面的详细描述变得显然，或部分地通过本公开的实践而习得。Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.
根据本公开的第一方面，提供一种意图预测方法，包括：获取用户的唯一标识信息、网络行为数据与网络性能数据；将所述网络行为数据与网络性能数据划分为多个维度，并对不同所述维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据；对所述初始特征数据进行特征融合，以得到中间特征数据；利用预设深度模型对所述中间特征数据进行处理，得到用户等级信息与目标特征数据；利用意图预测模型对所述用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。According to a first aspect of the present disclosure, there is provided an intention prediction method, comprising: obtaining a user's unique identification information, network behavior data, and network performance data; dividing the network behavior data and network performance data into multiple dimensions, and merging the network behavior data and network performance data of different dimensions to obtain initial feature data; performing feature fusion on the initial feature data to obtain intermediate feature data; processing the intermediate feature data using a preset deep model to obtain user level information and target feature data; and processing the user's unique identification information, user level information, and target feature data using an intention prediction model to obtain an intention prediction result.
可选的，所述将所述网络行为数据与网络性能数据划分为多个维度，并对不同所述维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据，包括：在所述网络行为数据与网络性能数据中确定M个数据样本，并将每个所述数据样本划分为N个维度，在同一所述数据样本中，将所述N个维度的网络行为数据与网络性能数据进行合并，以得到M个中间维度数据，M与N是正整数；根据所述M个中间维度数据确定特征值和特征向量，将所述特征值对应的特征向量进行累加，以得到所述初始特征数据。Optionally, dividing the network behavior data and network performance data into multiple dimensions, and merging the network behavior data and network performance data of different dimensions to obtain initial feature data, includes: determining M data samples in the network behavior data and network performance data, and dividing each of the data samples into N dimensions, and in the same data sample, merging the network behavior data and network performance data of the N dimensions to obtain M intermediate dimensional data, where M and N are positive integers; determining eigenvalues and eigenvectors based on the M intermediate dimensional data, and accumulating the eigenvectors corresponding to the eigenvalues to obtain the initial feature data.
可选的，所述对所述初始特征数据进行特征融合，以得到中间特征数据，包括：对所述初始特征数据进行特征组合，以得到组合特征数据；根据所述组合特征数据之间的相似度对所述组合特征数据进行分类，以得到特征分类数据；对所述特征分类数据进行特征融合，以得到所述中间特征数据。Optionally, the feature fusing the initial feature data to obtain intermediate feature data includes: feature combining the initial feature data to obtain combined feature data; classifying the combined feature data according to the similarity between the combined feature data to obtain feature classification data; and feature fusing the feature classification data to obtain the intermediate feature data.
可选的，所述对所述特征分类数据进行特征融合，以得到所述中间特征数据，包括：将所述特征分类数据划分为T份，在所述T份特征分类数据中，选取任一份所述特征分类数据作为测试集，并将剩余的T-1份所述特征分类数据作为训练集，以对预设特征融合模型进行训练，T是正整数；根据所述预设特征融合模型的T次输出结果，确定所述中间特征数据。Optionally, the feature fusion of the feature classification data to obtain the intermediate feature data includes: dividing the feature classification data into T parts, selecting any one of the T parts of the feature classification data as a test set, and using the remaining T-1 parts of the feature classification data as a training set to train a preset feature fusion model, where T is a positive integer; and determining the intermediate feature data based on T output results of the preset feature fusion model.
可选的，所述利用预设深度模型对所述中间特征数据进行处理，得到用户等级信息与目标特征数据，包括：在所述中间特征数据中提取所述目标特征数据；利用所述预设深度模型对所述目标特征数据进行处理，以确定所述目标特征数据对应的用户等级信息。Optionally, the intermediate feature data is processed using a preset depth model to obtain user level information and target feature data, including: extracting the target feature data from the intermediate feature data; and processing the target feature data using the preset depth model to determine the user level information corresponding to the target feature data.
可选的，所述利用意图预测模型对所述用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果，包括：将同一所述用户的唯一标识信息、所述用户等级信息，以及所述目标特征数据进行一一对应，以得到意图识别数据；将所述意图识别数据输入所述意图预测模型，以得到所述用户的意图预测结果。Optionally, the intention prediction model is used to process the user's unique identification information, user level information and target feature data to obtain an intention prediction result, including: making one-to-one correspondence between the unique identification information, the user level information, and the target feature data of the same user to obtain intention recognition data; and inputting the intention recognition data into the intention prediction model to obtain the user's intention prediction result.
可选的，在所述获取用户的唯一标识信息、网络行为数据与网络性能数据后，所述方法还包括：对所述网络行为数据与网络性能数据进行数据预处理。Optionally, after obtaining the user's unique identification information, network behavior data and network performance data, the method further includes: performing data preprocessing on the network behavior data and network performance data.
根据本公开的第二方面，提供一种意图预测装置，包括：数据获取模块，被配置为获取用户的唯一标识信息、网络行为数据与网络性能数据；降维处理模块，被配置为将所述网络行为数据与网络性能数据划分为多个维度，并对不同所述维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据；特征融合模块，被配置为对所述初始特征数据进行特征融合，以得到中间特征数据；用户等级信息获取模块，被配置为利用预设深度模型对所述中间特征数据进行处理，得到用户等级信息与目标特征数据；意图预测结果获取模块，被配置为利用意图预测模型对所述用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。According to a second aspect of the present disclosure, there is provided an intention prediction device, comprising: a data acquisition module, configured to acquire a user's unique identification information, network behavior data, and network performance data; a dimension reduction processing module, configured to divide the network behavior data and network performance data into multiple dimensions, and merge the network behavior data and network performance data of different dimensions to obtain an initial feature. feature data; a feature fusion module, configured to perform feature fusion on the initial feature data to obtain intermediate feature data; a user level information acquisition module, configured to process the intermediate feature data using a preset deep model to obtain user level information and target feature data; an intention prediction result acquisition module, configured to process the user's unique identification information, user level information and target feature data using an intention prediction model to obtain an intention prediction result.
根据本公开的第三方面，提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述第一方面的意图预测方法及其可能的实现方式。According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the intention prediction method of the first aspect and its possible implementation methods are implemented.
根据本公开的第四方面，提供一种电子设备，包括：处理器；存储器，用于存储所述处理器的可执行指令。其中，所述处理器配置为经由执行所述可执行指令，来执行上述第一方面的意图预测方法及其可能的实现方式。According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the intention prediction method of the first aspect and possible implementation thereof by executing the executable instructions.
本公开的技术方案具有以下有益效果：The technical solution disclosed in this disclosure has the following beneficial effects:
一方面，通过对用户数据进行降维处理以及特征融合，在一定程度上避免了相关技术中的意图预测方法在处理海量用户数据时，出现的模型训练过程复杂，且数据过拟合等问题，加速了模型训练过程，以及意图预测过程，同时基于特征处理后的中间特征数据获取用户等级信息，根据用户等级信息与对应的目标特征数据共同预测用户意图，在降低了冗余数据特征对意图预测结果的影响的同时，提高了用户意图预测准确率，从而大大提高了意图预测效率。另一方面，通过获取用户的唯一标识信息、网络行为数据与网络性能数据等多个维度的用户数据，提升了用户数据的丰富度，进一步确保了意图预测结果的准确率。On the one hand, by reducing the dimension of user data and fusing features, the problem of complex model training process and data overfitting in the intention prediction method in related technologies when processing massive user data is avoided to a certain extent, and the model training process and intention prediction process are accelerated. At the same time, user level information is obtained based on the intermediate feature data after feature processing, and user intention is predicted based on the user level information and the corresponding target feature data. While reducing the impact of redundant data features on the intention prediction results, the accuracy of user intention prediction is improved, thereby greatly improving the efficiency of intention prediction. On the other hand, by obtaining user data in multiple dimensions such as user unique identification information, network behavior data and network performance data, the richness of user data is improved, and the accuracy of intention prediction results is further ensured.
图1示出本示例性实施方式的一种系统运行架构；FIG1 shows a system operation architecture of this exemplary embodiment;
图2示出本示例性实施方式中一种意图预测方法的流程图；FIG2 shows a flow chart of an intention prediction method in this exemplary embodiment;
图3示出本示例性实施方式中一种获取初始特征数据的流程图；FIG3 shows a flow chart of obtaining initial feature data in this exemplary embodiment;
图4示出本示例性实施方式中一种获取中间特征数据的流程图；FIG4 shows a flow chart of obtaining intermediate feature data in this exemplary embodiment;
图5示出本示例性实施方式中一种特征融合的过程的流程图；FIG5 is a flow chart showing a process of feature fusion in this exemplary embodiment;
图6示出本示例性实施方式中一种获取用户等级信息的流程图；FIG6 shows a flow chart of obtaining user level information in this exemplary embodiment;
图7示出本示例性实施方式中一种获取意图预测结果的流程图；FIG7 shows a flow chart of obtaining intention prediction results in this exemplary embodiment;
图8示出本示例性实施方式中一种意图预测单元的架构图；FIG8 shows an architecture diagram of an intention prediction unit in this exemplary embodiment;
图9示出本示例性实施方式中另一种意图预测方法的流程图；FIG9 shows a flow chart of another intention prediction method in this exemplary embodiment;
图10示出本示例性实施方式中一种意图预测装置的结构示意图；FIG10 is a schematic diagram showing the structure of an intention prediction device in this exemplary embodiment;
图11示出本示例性实施方式中一种电子设备的结构示意图。FIG. 11 is a schematic structural diagram of an electronic device in this exemplary embodiment.
现在将参考附图更全面地描述示例实施方式。然而，示例实施方式能够以多种形式实施，且不应被理解为限于在此阐述的范例；相反，提供这些实施方式使得本公开将更加全面和完整，并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。在下面的描述中，提供许多具体细节从而给出对本公开的实施方式的充分理解。然而，本领域技术人员将意识到，可以实践本公开的技术方案而省略特定细节中的一个或更多，或者可以采用其它的方法、组元、装置、步骤等。在其它情况下，不详细示出或描述公知技术方案以避免喧宾夺主而使得本公开的各方面变得模糊。Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.
此外，附图仅为本公开的示意性图解，并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分，因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体，不一定必须与物理或逻辑上独立的实体相对应。可以采用软件形式来实现这些功能实体，或在一个或多个硬件模块或集成电路中实现这些功能实体，或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices.
相关技术中，通过获取用户历史通话记录，提取特征，对智能对话模型进行训练，使智能对话模型能够适应不同应用场景下的用户意图识别；或者通过采集分析用户行为数据；根据行业知识图谱对用户行为数据进行知识解读，获取用户行业知识清单；应用多种用户特征识别模型识别并输出用户的个性化特征与需求，使得意图识别场景与特征处理方法较为单一、且未考虑海量特征数据的处理方式，造成意图预测方法无法满足当前用户数据量庞大的应用场景，且用户意图预测过程速度慢，准确度低下，导致用户的意图预测效率低下。In the related technology, by obtaining the user's historical call records, extracting features, and training the intelligent dialogue model, the intelligent dialogue model can adapt to user intention recognition in different application scenarios; or by collecting and analyzing user behavior data; interpreting user behavior data according to the industry knowledge graph to obtain the user's industry knowledge list; applying a variety of user feature recognition models to identify and output the user's personalized features and needs, the intention recognition scenario and feature processing method are relatively single, and the processing method of massive feature data is not considered, resulting in the intention prediction method being unable to meet the current application scenarios with huge amounts of user data, and the user intention prediction process is slow and inaccurate, resulting in low efficiency in user intention prediction.
鉴于上述一个或多个问题，本公开示例性实施方式首先提供一种意图预测方法。下面结合图1对本示例性实施方式运行环境的系统架构进行说明。In view of one or more of the above problems, the exemplary embodiment of the present disclosure first provides an intention prediction method. The system architecture of the operating environment of the exemplary embodiment is described below in conjunction with FIG. 1 .
参考图1所示，系统架构100可以包括终端设备110和服务器120。终端设备110可以是平板电脑、笔记本电脑、台式电脑等电子设备，终端设备110可以用于用户的唯一标识信息、网络行为数据与网络性能数据。服务器120泛指提供本示例性实施方式中意图预测相关服务的后台系统，如可以是实现意图预测方法的服务器。服务器120可以是一台服务器或多台服务器形成的集群，本公开对此不做限定。终端设备110与服务器120之间可以通过有线或无线的通信链路形成连接，以进行数据交互。As shown in reference figure 1, the system architecture 100 may include a terminal device 110 and a server 120. The terminal device 110 may be an electronic device such as a tablet computer, a laptop computer, a desktop computer, etc. The terminal device 110 may be used for the user's unique identification information, network behavior data, and network performance data. The server 120 generally refers to a background system that provides intention prediction related services in this exemplary embodiment, such as a server that implements the intention prediction method. The server 120 may be a cluster formed by one server or multiple servers, which is not limited in this disclosure. The terminal device 110 and the server 120 may be connected via a wired or wireless communication link to exchange data.
可以由终端设备110执行本示例性实施方式中的意图预测方法。例如，在通信服务场景中，终端设备110可以是用户使用的电子设备，终端设备110通过执行意图预测方法，可以收集用户的唯一标识信息、网络行为数据与网络性能数据，确定用户等级信息，从而对用户意图进行预测，获知用户的通信业务需求，对用户进行针对性推荐，以改善用户体验。The intention prediction method in this exemplary embodiment may be executed by the terminal device 110. For example, in a communication service scenario, the terminal device 110 may be an electronic device used by a user, and the terminal device 110 may collect the user's unique identification information, network behavior data, and network performance data by executing the intention prediction method, and determine the user's level information, thereby predicting the user's intention, understanding the user's communication service needs, and making targeted recommendations to the user to improve the user experience.
在一种实施方式中，可以由终端设备110获取用户的唯一标识信息、网络行为数据与网络性能数据，并将用户的唯一标识信息、网络行为数据与网络性能数据发送至服务器120，服务器120在接收到用户的唯一标识信息、网络行为数据与网络性能数据后，将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据，再对初始特征数据进行特征融合，以得到中间特征数据，并利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据，最后利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。In one embodiment, the terminal device 110 can obtain the user's unique identification information, network behavior data, and network performance data, and send the user's unique identification information, network behavior data, and network performance data to the server 120. After receiving the user's unique identification information, network behavior data, and network performance data, the server 120 divides the network behavior data and network performance data into multiple dimensions, and merges the network behavior data and network performance data of different dimensions to obtain initial feature data, and then performs feature fusion on the initial feature data to obtain intermediate feature data, and uses a preset deep model to process the intermediate feature data to obtain user level information and target feature data, and finally uses the intention prediction model to process the user's unique identification information, user level information, and target feature data to obtain an intention prediction result.
由上可知，本示例性实施方式中的意图预测方法可以由上述终端设备110或服务器120执行。It can be seen from the above that the intention prediction method in this exemplary embodiment can be executed by the above-mentioned terminal device 110 or server 120.
下面结合图2对意图预测方法进行说明。图2示出了意图预测方法的示例性流程，包括以下步骤S210至S250：The intention prediction method is described below in conjunction with FIG2 . FIG2 shows an exemplary process of the intention prediction method, including the following steps S210 to S250:
步骤S210，获取用户的唯一标识信息、网络行为数据与网络性能数据；Step S210, obtaining the user's unique identification information, network behavior data and network performance data;
步骤S220，将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据；Step S220, dividing the network behavior data and the network performance data into multiple dimensions, and merging the network behavior data and the network performance data of different dimensions to obtain initial feature data;
步骤S230，对初始特征数据进行特征融合，以得到中间特征数据；Step S230, performing feature fusion on the initial feature data to obtain intermediate feature data;
步骤S240，利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据；Step S240, using a preset depth model to process the intermediate feature data to obtain user level information and target feature data;
步骤S250，利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。Step S250, using the intention prediction model to process the user's unique identification information, user level information and target feature data to obtain an intention prediction result.
基于上述方法，一方面，通过对用户数据进行降维处理以及特征融合，在一定程度上避免了相关技术中的意图预测方法在处理海量用户数据时，出现的模型训练过程复杂，且数据过拟合等问题，加速了模型训练过程，以及意图预测过程，同时基于特征处理后的中间特征数据获取用户等级信息，根据用户等级信息与对应的目标特征数据共同预测用户意图，在降低了冗余数据特征对意图预测结果的影响的同时，提高了用户意图预测准确率，从而大大提高了意图预测效率。另一方面，通过获取用户的唯一标识信息、网络行为数据与网络性能数据等多个维度的用户数据，提升了用户数据的丰富度，进一步确保了意图预测结果的准确率。Based on the above method, on the one hand, by reducing the dimension of user data and fusing features, the problems of complex model training process and data overfitting in the intention prediction method in related technologies when processing massive user data are avoided to a certain extent, and the model training process and intention prediction process are accelerated. At the same time, user level information is obtained based on the intermediate feature data after feature processing, and user intention is predicted based on the user level information and the corresponding target feature data. While reducing the impact of redundant data features on the intention prediction results, the accuracy of user intention prediction is improved, thereby greatly improving the efficiency of intention prediction. On the other hand, by obtaining user data in multiple dimensions such as user unique identification information, network behavior data and network performance data, the richness of user data is improved, and the accuracy of intention prediction results is further ensured.
下面对图2中的每个步骤进行具体说明。Each step in FIG. 2 is described in detail below.
参考图2，在步骤S210中，获取用户的唯一标识信息、网络行为数据与网络性能数据。Referring to FIG. 2 , in step S210 , the user's unique identification information, network behavior data, and network performance data are obtained.
其中，唯一标识信息用于表征用户的身份信息，本公开对唯一标识信息的具体内容不作特殊限定，例如，唯一标识信息可以包括用户的账号，或者用户使用的终端设备的IP(Internet Protocol，网际互连协议)地址等。网络行为数据可以包括用户的网络操作数据，本公开对网络行为数据的具体内容不作特殊限定，示例性的，网络行为数据可以包括用户的搜索数据，通信业务消费数据等。网络性能数据可以表征用户所使用的无线网络或移动网络的网络状态信息，例如，网络性能数据可以包括用户当前所使用的网络的带宽、时延、带宽时延积等数据。Among them, the unique identification information is used to represent the identity information of the user. The present disclosure does not specifically limit the specific content of the unique identification information. For example, the unique identification information may include the user's account, or the IP (Internet Protocol) address of the terminal device used by the user. Network behavior data may include the user's network operation data. The present disclosure does not specifically limit the specific content of the network behavior data. For example, the network behavior data may include the user's search data, communication service consumption data, etc. Network performance data may represent the network status information of the wireless network or mobile network used by the user. For example, the network performance data may include the bandwidth, delay, bandwidth-delay product and other data of the network currently used by the user.
举例而言，可以设定数据采集周期，以按照数据采集周期定期采集用户的唯一标识信息、网络行为数据与网络性能数据，以得到表1所示的用户特征数据库信息表。For example, a data collection cycle may be set to regularly collect the user's unique identification information, network behavior data, and network performance data according to the data collection cycle to obtain the user feature database information table shown in Table 1.
表1用户特征数据库信息表
Table 1 User feature database information table
为了使获取的网络行为数据与网络性能数据更易于在深度模型中进行训练，在一种实施方式中，在获取用户的唯一标识信息、网络行为数据与网络性能数据后，上述方法还可以包括：In order to make the acquired network behavior data and network performance data easier to train in the deep model, in one embodiment, after acquiring the user's unique identification information, network behavior data and network performance data, the above method may further include:
对网络行为数据与网络性能数据进行数据预处理。Perform data preprocessing on network behavior data and network performance data.
举例而言，对网络行为数据与网络性能数据进行数据预处理主要可以包括数据清洗、数据转换、数据筛选等。在对用户的通信业务意图预测场景中，由于运营商的用户群体范围广，相应的网络行为数据与网络性能数据的数据量也十分庞大，因此为了更有效地提取用户数据的业务特征，预测用户的意图，需要根据下述步骤对获取的网络行为数据与网络性能数据进行数据预处理：For example, data preprocessing of network behavior data and network performance data can mainly include data cleaning, data conversion, data screening, etc. In the scenario of predicting the user's communication service intention, due to the wide range of operators' user groups, the corresponding network behavior data and network performance data are also very large. Therefore, in order to more effectively extract the service characteristics of user data and predict user intentions, it is necessary to preprocess the acquired network behavior data and network performance data according to the following steps:
(1)数据导入：可以通过Oracle数据库提供的数据迁移工具SQL Developer直接将获取的用户的唯一标识信息、网络行为数据与网络性能数据导入到数据库，并导出数据存储文件中的用户日志数据进行数据分析；(1) Data import: You can use the data migration tool SQL Developer provided by Oracle Database to directly import the acquired user's unique identification information, network behavior data, and network performance data into the database, and export the user log data in the data storage file for data analysis;
(2)数据清洗：由于获取的用户的唯一标识信息、网络行为数据与网络性能数据因数据特点不一致，会存在数据缺失、冗余、格式不正确数据或者脏数据等问题，因此需要针对缺失数据、错误数据、逻辑错误、冗余数据、重复数据进行数据清洗，提升数据质量，也便于在后续用户业务数据特征提取步骤中提升模型精准度，对于没有价值或并不需要的数据进行删除。(2) Data cleaning: Since the unique identification information, network behavior data, and network performance data of users are inconsistent due to data characteristics, there may be problems such as missing data, redundancy, incorrectly formatted data, or dirty data. Therefore, it is necessary to clean the missing data, erroneous data, logical errors, redundant data, and duplicate data to improve data quality. This will also facilitate improving the accuracy of the model in the subsequent user business data feature extraction step and delete data that is of no value or is not needed.
(3)数据转换：可以使用极差标准化法，对数据进行标准化处理，消除变量量纲和变异范围对数据的影响。示例性的，可以取网络行为数据与网络性能数据的最大值(Xmax)和最小值(Xmin)，并计算极差R＝Xmin-Xmax，并根据公式(1)计算网络行为数据或网络性能数据标准化后的值：
(3) Data conversion: The range normalization method can be used to normalize the data to eliminate the influence of the variable dimension and variation range on the data. For example, the maximum value (Xmax ) and the minimum value (Xmin ) of the network behavior data and the network performance data can be taken, and the range R = Xmin -Xmax can be calculated, and the standardized value of the network behavior data or the network performance data can be calculated according to formula (1):
X是网络行为数据或网络性能数据的样本值，X’是网络行为数据或网络性能数据标准化后的值。X is a sample value of network behavior data or network performance data, and X' is a standardized value of network behavior data or network performance data.
(4)数据过滤：根据公式(2)可以通过方差选择法，进行数据特征筛选：
(4) Data filtering: According to formula (2), data features can be screened by using the variance selection method:
其中，σ表示数据的总体方差，X为是网络行为数据或网络性能数据的样本值，α是数据的总体均值，N为是网络行为数据或网络性能数据的样本个数。Among them, σ represents the overall variance of the data, X is the sample value of the network behavior data or network performance data, α is the overall mean of the data, and N is the number of samples of the network behavior data or network performance data.
通过对网络行为数据与网络性能数据进行数据预处理，降低了处理后的网络行为数据与网络性能数据的数据冗余度，进一步加快模型收敛速率，加速意图预测过程。By preprocessing the network behavior data and network performance data, the data redundancy of the processed network behavior data and network performance data is reduced, further accelerating the model convergence rate and the intention prediction process.
继续参考图2，在步骤S220中，将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据。Continuing to refer to FIG. 2 , in step S220 , the network behavior data and the network performance data are divided into multiple dimensions, and the network behavior data and the network performance data of different dimensions are merged to obtain initial feature data.
其中，初始特征数据包括网络行为数据与网络性能数据对应的低维数据，例如，网络行为数据可以包括用户搜索的问题，如“家中路由器总是断网是怎么回事？”，而该网络行为数据对应的初始特征数据可以是一组二进制数字，如“00110101”，该二进制数字“00110101”可以被设备识别为“家中路由器总是断网是怎么回事？”，从而实现了获取网络行为数据与网络性能数据对应的低维数据。Among them, the initial feature data includes low-dimensional data corresponding to the network behavior data and the network performance data. For example, the network behavior data may include questions searched by users, such as "Why is the router at home always disconnected from the Internet?", and the initial feature data corresponding to the network behavior data may be a set of binary numbers, such as "00110101". The binary number "00110101" can be recognized by the device as "Why is the router at home always disconnected from the Internet?", thereby achieving the acquisition of low-dimensional data corresponding to the network behavior data and the network performance data.
在一种实施方式中，上述将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据，参考图3所示，可以包括步骤S310～S320：In one embodiment, the above-mentioned network behavior data and network performance data are divided into multiple dimensions, and the network behavior data and network performance data of different dimensions are merged to obtain initial feature data. Referring to FIG. 3, steps S310 to S320 may be included:
步骤S310，在网络行为数据与网络性能数据中确定M个数据样本，并将每个数据样本划分为N个维度，在同一数据样本中，将N个维度的网络行为数据与网络性能数据进行合并，以得到M个中间维度数据，M与N是正整数；Step S310, determining M data samples in the network behavior data and the network performance data, and dividing each data sample into N dimensions, and merging the network behavior data and the network performance data of the N dimensions in the same data sample to obtain M intermediate dimensional data, where M and N are positive integers;
步骤S320，根据M个中间维度数据确定特征值和特征向量，将特征值对应的特征向量进行累加，以得到初始特征数据。Step S320, determining eigenvalues and eigenvectors according to the M intermediate dimensional data, and accumulating the eigenvectors corresponding to the eigenvalues to obtain initial eigendata.
其中，数据样本可以代表数据的组，M个数据样本可以包括将网络行为数据与网络性能数据分为M组数据，中间维度数据可以是每个数据样本中N个维度数据的合并结果。The data sample may represent a group of data, the M data samples may include dividing the network behavior data and the network performance data into M groups of data, and the intermediate dimensional data may be a merged result of the N dimensional data in each data sample.
举例而言，可以使用主成分分析(Principal Component Analysis，PCA)方法对网络行为数据与网络性能数据进行降维处理，以得到初始特征数据，例如，X为网络行为数据或网络性能数据，X中包含M个数据样本，每个数据样本包括N个维度的数据，如下述公式(3)所示，对X中每个数据样本中不同维度的数据进行合并，以得到公式(4)。
For example, the principal component analysis (PCA) method can be used to reduce the dimension of the network behavior data and the network performance data to obtain the initial feature data. For example, X is the network behavior data or the network performance data, X contains M data samples, and each data sample includes data of N dimensions, as shown in the following formula (3). The data of different dimensions in each data sample in X are merged to obtain formula (4).
其中，XNM可以表示第M个数据样本中的第N维度的网络行为数据或网络性能数据。
X＝[X1,X2,...XM] (4)Here, XNM may represent the network behavior data or network performance data of the Nth dimension in the Mth data sample.
X＝[X1 ,X2 ,...XM ] (4)
其中，XM可以表示第M个中间维度数据。Among them, XM can represent the Mth intermediate dimension data.
再根据中间维度数据计算对应的特征值和特征向量，将特征值按照由大到小进行排序，并根据下述公式(5)累计贡献率来确定降维数：
Then, the corresponding eigenvalues and eigenvectors are calculated based on the intermediate dimensional data, the eigenvalues are sorted from large to small, and the dimensionality reduction number is determined based on the cumulative contribution rate according to the following formula (5):
其中，Pk是累计贡献率，λk表示第k个特征值对应的贡献率。Among them,Pk is the cumulative contribution rate, andλk represents the contribution rate corresponding to the kth eigenvalue.
在Pk满足预设贡献率阈值的情况下，可以停止累加，以表示降维结束，并根据当前维度的数据得到初始特征数据，其中，预设贡献率阈值可以是0.85。When Pk meets the preset contribution rate threshold, accumulation can be stopped to indicate the end of dimensionality reduction, and initial feature data can be obtained based on the data of the current dimension, where the preset contribution rate threshold can be 0.85.
通过对网络行为数据与网络性能数据进行数据划分和数据合并，以得到低维的初始特征数据，可以有效缓解维度灾难问题，降低数据结构复杂度，有利于提升意图预测效率。By partitioning and merging network behavior data and network performance data to obtain low-dimensional initial feature data, the dimensionality curse problem can be effectively alleviated, the complexity of the data structure can be reduced, and the efficiency of intent prediction can be improved.
继续参考图2，在步骤S230中，对初始特征数据进行特征融合，以得到中间特征数据。Continuing to refer to FIG. 2 , in step S230 , feature fusion is performed on the initial feature data to obtain intermediate feature data.
其中，中间特征数据是初始特征数据的特征融合结果。在一种实施方式中，上述对初始特征数据进行特征融合，以得到中间特征数据，参考图4所示，可以包括步骤S410～S430：The intermediate feature data is the feature fusion result of the initial feature data. In one embodiment, the feature fusion of the initial feature data to obtain the intermediate feature data may include steps S410 to S430 as shown in FIG4 :
步骤S410，对初始特征数据进行特征组合，以得到组合特征数据；Step S410, combining the initial feature data to obtain combined feature data;
其中，组合特征数据可以包括基于初始特征数据的进行特征提取、特征交叉形成的新的特征群。示例性的，如，初始特征数据包括网络操作数据A，搜索行为数据B以及网络性能数据C，可以通过对初始特征数据进行特征提取与特征组合，以得到中间特征数据D，该中间特征数据D＝A+C，从而将具有联系的初始特征数据通过特征组合的方式进行关联，形成新的特征数据。The combined feature data may include a new feature group formed by feature extraction and feature cross-extraction based on the initial feature data. For example, if the initial feature data includes network operation data A, search behavior data B, and network performance data C, the initial feature data may be extracted and combined to obtain intermediate feature data D, where D=A+C, so that the related initial feature data are associated by feature combination to form new feature data.
步骤S420，根据组合特征数据之间的相似度对组合特征数据进行分类，以得到特征分类数据。Step S420: classify the combined feature data according to the similarity between the combined feature data to obtain feature classification data.
其中，相似性距离可以表示特征数据之间的相似度，本公开对相似性距离的具体内容不作特殊限定，例如，相似性距离可以包括汉明距离、欧氏距离等。特征分类数据可以是对组合特征数据的重新分类的结果，特征分类数据中每个类别中的数据之间相似度较高。The similarity distance may represent the similarity between feature data, and the present disclosure does not specifically limit the specific content of the similarity distance. For example, the similarity distance may include Hamming distance, Euclidean distance, etc. The feature classification data may be the result of reclassifying the combined feature data, and the similarity between the data in each category in the feature classification data is relatively high.
举例而言，可以将用户的唯一标识信息user_id作为主键，通过K最邻近(K-Nearest Neighbor，KNN)算法或K均值聚类算法(K-means clustering algorithm)，按照组合特征数据之间的相似度对组合特征数据进行分类，以得到特征分类数据：For example, the user's unique identification information user_id can be used as the primary key, and the combined feature data can be classified according to the similarity between the combined feature data through the K-Nearest Neighbor (KNN) algorithm or the K-means clustering algorithm to obtain feature classification data:
(1)KNN算法(1) KNN algorithm
根据下述公式(6)计算xk与yk之间的欧氏距离d(x,y)，以获取样本点xk的最接近的k个临近点yk：
The Euclidean distance d(x,y) between xk and yk is calculated according to the following formula (6) to obtain the k nearest neighboring points yk of the sample point xk :
其中，n是样本点的总个数。Among them, n is the total number of sample points.
在确定xk的最接近的k个临近点yk后，可以将yk中出现频率最高的类别确定为样本点xk的类别。After determining the k nearest neighboring points yk of xk , the category with the highest frequency in yk can be determined as the category of the sample point xk .
(2)K-means算法(2) K-means algorithm
若样本集L，其中L＝{X1,X2，...Xn}，包括n个样本数据Xi(0＜i≤n)，选择n个聚类中心点K1，K2，K3，...Kn，根据公式(7)计算各个聚类中心点与样本数据Xi之间的欧式距离：
If the sample set L, where L = {X1 , X2 , ... Xn }, includes n sample dataXi (0 < i ≤ n), select n cluster centers K1 , K2 , K3 , ... Kn , and calculate the Euclidean distance between each cluster center and the sample dataXi according to formula (7):
将每个样本点Xi划分到距离它最近的聚类中心点Ki所代表的簇中，用各个簇中所有样本点的中心点Kit(0＜t≤n)代表簇的中心点；重复以上步骤，直到簇的中心点不变或达到设定的迭代次数或达到预设容错范围。Divide each sample pointXi into the cluster represented by the cluster center pointKi that is closest to it, and use the center pointKit (0＜t≤n) of all sample points in each cluster to represent the center point of the cluster; repeat the above steps until the center point of the cluster remains unchanged or reaches the set number of iterations or the preset fault tolerance range.
基于组合特征数据之间的相似度对组合特征数据进行分类，可以挖掘组合特征数据之间的内在联系，使得获取的每个类别中的特征分类数据具有强关联性。By classifying the combined feature data based on the similarity between the combined feature data, the intrinsic connection between the combined feature data can be mined, so that the feature classification data in each category obtained has a strong correlation.
步骤S430，对特征分类数据进行特征融合，以得到中间特征数据。Step S430, performing feature fusion on the feature classification data to obtain intermediate feature data.
在一种实施方式中，上述对特征分类数据进行特征融合，以得到中间特征数据，参考图5所示，可以包括步骤S510～S520：In one embodiment, the feature fusion of the feature classification data to obtain the intermediate feature data may include steps S510 to S520 as shown in FIG5 :
步骤S510，将特征分类数据划分为T份，在T份特征分类数据中，选取任一份特征分类数据作为测试集，并将剩余的T-1份特征分类数据作为训练集，以对预设特征融合模型进行训练，T是正整数；Step S510, dividing the feature classification data into T parts, selecting any one of the T parts of the feature classification data as a test set, and using the remaining T-1 parts of the feature classification data as a training set to train a preset feature fusion model, where T is a positive integer;
步骤S520，根据预设特征融合模型的T次输出结果，确定中间特征数据。Step S520, determining intermediate feature data according to T output results of the preset feature fusion model.
其中，训练集可以是用于训练预设特征融合模型的数据，测试集可以是验证预设特征融合模型处理结果的数据。预设特征融合模型可以是用于对特征分类数据进行特征融合的深度模型，本公开对预设特征融合模型的具体内容不作特殊限定，示例性的，预设特征融合模型可以包括基于Stacking算法的深度模型。The training set may be data used to train a preset feature fusion model, and the test set may be data for verifying the processing result of the preset feature fusion model. The preset feature fusion model may be a deep model used to perform feature fusion on feature classification data. The present disclosure does not specifically limit the specific content of the preset feature fusion model. Exemplarily, the preset feature fusion model may include a deep model based on the Stacking algorithm.
举例而言，预设特征融合模型可以是基于改进的Stacking算法的深度模型，可以将特征分类数据划分为5等份，以得到Train1、Train2、Train3、Train4、Train5共五组特征分类数据，依次选择其中一组特征分类数据作为测试集，其余四组作为训练集，对预设特征融合模型进行训练，以得到五组预测结果Pre1、Pre2、Pre3、Pre4、Pre5(即预设特征融合模型的第一层网络输出结果)；再计算五组预测结果Pre1、Pre2、Pre3、Pre4、Pre5的加权平均值，将该加权平均值输入预设特征融合模型的第二层网络，根据第二层网络的输出结果获取中间特征数据。For example, the preset feature fusion model can be a deep model based on the improved Stacking algorithm, and the feature classification data can be divided into five equal parts to obtain five groups of feature classification data, namely Train1, Train2, Train3, Train4, and Train5. One group of feature classification data is selected as a test set, and the remaining four groups are selected as training sets to train the preset feature fusion model to obtain five groups of prediction results Pre1, Pre2, Pre3, Pre4, and Pre5 (i.e., the first layer network output results of the preset feature fusion model); then the five groups of predictions are calculated. The weighted average of the measurement results Pre1, Pre2, Pre3, Pre4, and Pre5 is input into the second layer network of the preset feature fusion model, and the intermediate feature data is obtained according to the output result of the second layer network.
基于图5所示的方法，对特征分类数据进行特征融合，以得到中间特征数据，可以进一步提升模型分类的准确率与鲁棒性，从而有利于提升意图预测准确度。Based on the method shown in FIG5 , feature fusion is performed on the feature classification data to obtain intermediate feature data, which can further improve the accuracy and robustness of the model classification, thereby helping to improve the accuracy of intent prediction.
基于图4的方法，通过多种模型对初始特征数据进行处理，以得到中间特征数据，相比于使用单一模型进行特征构造的方法，有效提升了中间特征数据的分类准确率，进一步降低了中间特征数据的冗余数据量，有利于提升意图预测整体效率。Based on the method of Figure 4, the initial feature data is processed through multiple models to obtain intermediate feature data. Compared with the method of using a single model for feature construction, the classification accuracy of the intermediate feature data is effectively improved, and the amount of redundant data of the intermediate feature data is further reduced, which is conducive to improving the overall efficiency of intent prediction.
继续参考图2，在步骤S240中，利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据。Continuing to refer to FIG. 2 , in step S240 , the intermediate feature data is processed using a preset depth model to obtain user level information and target feature data.
其中，预设深度模型是基于注意力机制的神经网络模型，例如，预设深度模型可以包括Transformer模型。用户等级信息可以用于表示用户的等级，例如，用户的等级可以包括优质用户、高级用户和普通用户3个等级。目标特征数据可以是用于确定用户等级信息的数据，本公开对目标特征数据不作特殊限定，示例性的，目标特征数据可以是在中间特征数据中提取到的用户访问量、用户访问时长、用户访问频次、用户上网流量、用户通话总时长等数据。Among them, the preset deep model is a neural network model based on the attention mechanism. For example, the preset deep model may include a Transformer model. User level information may be used to indicate the level of the user. For example, the user level may include three levels: premium users, advanced users, and ordinary users. Target feature data may be data used to determine user level information. The present disclosure does not specifically limit the target feature data. Exemplarily, the target feature data may be data such as user visits, user visit duration, user visit frequency, user Internet traffic, and total user call duration extracted from the intermediate feature data.
在一种实施方式中，上述利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据，参考图6所示，可以包括步骤S610～S620：In one embodiment, the above-mentioned processing of the intermediate feature data using the preset depth model to obtain the user level information and the target feature data may include steps S610 to S620 as shown in FIG6 :
步骤S610，在中间特征数据中提取目标特征数据；Step S610, extracting target feature data from the intermediate feature data;
步骤S620，利用预设深度模型对目标特征数据进行处理，以确定目标特征数据对应的用户等级信息。Step S620: Process the target feature data using a preset depth model to determine user level information corresponding to the target feature data.
举例而言，预设深度模型可以包括改进的Transformer模型，可以首先在中间特征数据中提取用户访问量、用户访问时长、用户访问频次、用户上网流量、用户通话总时长等数据，以获取目标特征数据，目标特征数据的内容说明可以如表2所示。将目标特征数据中的80％作为训练集，以训练预设深度模型，将目标特征数据剩余的20％作为测试集，以验证预设深度模型的预测准确率，可以通过公式(8)计算模型的查全率和查准率，以对模型的预测效果进行评估，如：根据模型的查全率和查准率计算得到的模型预测准确率为74.37％：
F1＝(2*precision*recall)/(precision+recall) (8)For example, the preset deep model may include an improved Transformer model, and the user access volume, user access duration, user access frequency, user Internet traffic, user total call duration and other data may be first extracted from the intermediate feature data to obtain the target feature data, and the content description of the target feature data may be shown in Table 2. 80% of the target feature data is used as a training set to train the preset deep model, and the remaining 20% of the target feature data is used as a test set to verify the prediction accuracy of the preset deep model. The recall rate and precision rate of the model may be calculated by formula (8) to evaluate the prediction effect of the model, such as: the prediction accuracy of the model calculated based on the recall rate and precision rate of the model is 74.37%:
F1＝(2*precision*recall)/(precision+recall) (8)
其中，F1是模型的预测准确率，precision是查准率，recall是查全率。Among them, F1 is the prediction accuracy of the model, precision is the precision rate, and recall is the recall rate.
在预设深度模型训练完成后，可以在目标特征数据中提取词向量，将该词向量作为初始化值输入到预设深度模型中学习全局信息，最后基于预设深度模型的全连接层和逻辑回归方法确定每个用户的user_id对应的用户等级信息。After the preset deep model training is completed, the word vector can be extracted from the target feature data, and the word vector can be input into the preset deep model as the initialization value to learn the global information. Finally, the user level information corresponding to each user's user_id is determined based on the fully connected layer and logistic regression method of the preset deep model.
表2目标特征数据内容说明表
Table 2 Target feature data content description
基于图6的方法，可以获取目标特征数据对应的用户等级信息，实现了对用户等级的分类，提高了获取的用户等级信息的准确率，进一步提升了意图预测的准确率。Based on the method of FIG6 , user level information corresponding to the target feature data can be obtained, user level classification is achieved, the accuracy of the obtained user level information is improved, and the accuracy of intent prediction is further improved.
继续参考图2，在步骤S250中，利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。Continuing to refer to FIG. 2 , in step S250 , the user's unique identification information, user level information, and target feature data are processed using the intention prediction model to obtain an intention prediction result.
其中，意图预测模型是用于对用户意图进行识别的深度模型，本公开对意图预测模型的具体种类不作特殊限定，示例性的，意图预测模型可以包括Text-CNN(Text Convolutional Neural Networks，文本卷积神经网络)模型。Among them, the intent prediction model is a deep model used to identify user intent. The present disclosure does not specifically limit the specific type of the intent prediction model. Exemplarily, the intent prediction model may include a Text-CNN (Text Convolutional Neural Networks) model.
在一种实施方式中，上述利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果，参考图7所示，可以步骤S710～S720：In one embodiment, the above-mentioned intention prediction model is used to process the user's unique identification information, user level information and target feature data to obtain an intention prediction result. Referring to FIG. 7 , steps S710 to S720 may be performed:
步骤S710，将同一用户的唯一标识信息、用户等级信息，以及目标特征数据进行一一对应，以得到意图识别数据；Step S710, matching the unique identification information, user level information, and target feature data of the same user one by one to obtain intent recognition data;
步骤S720，将意图识别数据输入意图预测模型，以得到用户的意图预测结果。Step S720, input the intention recognition data into the intention prediction model to obtain the user's intention prediction result.
其中，意图识别数据可以用于对用户意图进行识别。意图预测结果可以包括意图预测模型的输出结果，本公开对意图预测结果的具体内容不作特殊限定，示例性的，意图预测结果可以包括用户的通信业务需求以及用户的基本信息。The intent recognition data can be used to identify the user's intent. The intent prediction result can include the output of the intent prediction model. As a result, the present disclosure does not specifically limit the specific content of the intention prediction result. For example, the intention prediction result may include the user's communication service needs and the user's basic information.
举例而言，利用Text-CNN模型对目标特征数据进行编码，并与特征词向量进行拼接，形成带有上下文特征信息的词向量，再根据该词向量获取意图类别标签的概率分布结果，最后根据概率分布结果确定用户的意图预测结果。For example, the Text-CNN model is used to encode the target feature data and concatenate it with the feature word vector to form a word vector with contextual feature information. The probability distribution result of the intent category label is then obtained based on the word vector, and finally the user's intent prediction result is determined based on the probability distribution result.
在一种实施方式中，可以将本示例性实施方式的意图预测方法进行集成，以得到意图预测单元，并将该意图预测单元嵌入到通信系统中，对用户的通信业务需求进行预测。In one implementation, the intention prediction method of this exemplary implementation may be integrated to obtain an intention prediction unit, and the intention prediction unit may be embedded in a communication system to predict the user's communication service needs.
举例而言，意图预测单元的架构可以如图8所示，意图预测单元可以包括数据管理子单元，数据采集子单元，特征工程子单元，模型训练子单元以及意图预测子单元。在数据存储子单元中可以存储所有用户的网络数据，在数据采集子单元中，可以在网络数据中筛选包括用户的唯一标识信息的用户基础数据，网络操作数据，搜索数据以及网络性能数据，在获取这些数据后，可以在特征工程子单元中，对这些数据进行数据清洗、数据预处理、特征选择(数据降维、数据分类)以及特征组合，以得到初始特征数据，将初始特征数据输入模型训练子单元，以对构建的预设特征融合模型以及预设深度模型进行模型训练，基于训练好的预设特征融合模型对初始特征数据进行特征融合，以得到中间特征数据，将中间特征数据输入训练好的预设深度模型中，以得到用户等级信息；在意图预测子单元中将用户等级信息，用户的唯一标识信息以及目标特征数据输入意图预测模型，以得到用户的意图预测结果，基于用户的意图预测结果确定用户的业务需求信息，根据业务需求信息进行服务策略制定，将制定好的服务策略下发至业务处理子单元，以使得业务处理子单元根据服务策略进行营销服务、运营调度、用户管理以及故障告警，并更新用户的网络数据，同时将更新后的数据重新存储在数据管理子单元中。For example, the architecture of the intent prediction unit can be shown in Figure 8. The intent prediction unit can include a data management subunit, a data collection subunit, a feature engineering subunit, a model training subunit and an intent prediction subunit. The network data of all users can be stored in the data storage subunit. In the data collection subunit, user basic data including the user's unique identification information, network operation data, search data and network performance data can be screened in the network data. After obtaining these data, they can be cleaned, preprocessed, feature selected (data dimension reduction, data classification) and feature combined in the feature engineering subunit to obtain initial feature data. The initial feature data is input into the model training subunit to perform model training on the preset feature fusion model and the preset deep model constructed. The initial feature data is feature fused based on the trained preset feature fusion model to obtain. To intermediate feature data, the intermediate feature data is input into a trained preset deep model to obtain user level information; in the intention prediction subunit, the user level information, the user's unique identification information and the target feature data are input into the intention prediction model to obtain the user's intention prediction result, the user's business demand information is determined based on the user's intention prediction result, a service strategy is formulated according to the business demand information, and the formulated service strategy is sent to the business processing subunit, so that the business processing subunit performs marketing services, operation scheduling, user management and fault alarm according to the service strategy, and updates the user's network data, and stores the updated data again in the data management subunit.
通过将意图预测方法的集成在意图预测单元中，并将意图预测单元嵌入通信服务系统，可以使得通信服务系统基于用户的网络数据预测用户意图，从而为通信服务系统进行业务智能处理提供可能性。By integrating the intention prediction method into the intention prediction unit and embedding the intention prediction unit into the communication service system, the communication service system can predict the user's intention based on the user's network data, thereby providing the possibility for the communication service system to perform business intelligent processing.
在一种实施方式中，参考图9所示，本示例性实施方式的意图预测方法的一种示例性流程可以包括步骤S901～S909：In one embodiment, referring to FIG. 9 , an exemplary process of the intention prediction method of this exemplary embodiment may include steps S901 to S909:
步骤S901，获取用户的网络数据；Step S901, obtaining user's network data;
步骤S902，根据用户的网络数据获取用户的唯一标识信息、网络行为数据以及网络性能数据；Step S902, obtaining the user's unique identification information, network behavior data, and network performance data according to the user's network data;
步骤S903，对网络行为数据以及网络性能数据进行预处理；Step S903, preprocessing the network behavior data and the network performance data;
步骤S904，基于PCA方法对预处理后的网络行为数据以及网络性能数据进行数据降维，以得到初始特征数据；Step S904, performing data dimension reduction on the preprocessed network behavior data and network performance data based on the PCA method to obtain initial feature data;
步骤S905，对初始特征数据进行特征组合，以得到组合特征数据；Step S905, combining the initial feature data to obtain combined feature data;
步骤S906，利用KNN算法和K-means算法对组合特征数据进行分类，以得到特征分类数据；Step S906, classifying the combined feature data using the KNN algorithm and the K-means algorithm to obtain feature classification data;
步骤S907，基于Stacking算法模型对特征分类数据进行特征融合，以得到中间特征数据；Step S907, performing feature fusion on the feature classification data based on the Stacking algorithm model to obtain intermediate feature data;
步骤S908，基于Transformer模型对中间特征数据进行处理，以得到用户等级信息以及目标特征数据；Step S908, processing the intermediate feature data based on the Transformer model to obtain user level information and target feature data;
步骤S909，利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。Step S909, using the intention prediction model to process the user's unique identification information, user level information and target feature data to obtain an intention prediction result.
基于图9的方法，有效提升了意图预测准确率，进一步提升了意图预测效率。Based on the method in Figure 9, the accuracy of intent prediction is effectively improved, and the efficiency of intent prediction is further improved.
基于上述方法，在一定程度上避免了相关技术中的意图预测方法在处理海量用户数据时，出现的模型训练过程复杂，且数据过拟合等问题，加速了模型训练过程，以及意图预测过程，提高了用户意图预测准确率，从而大大提高了意图预测效率。Based on the above method, the problems of complex model training process and data overfitting that arise in the intention prediction method in the related technology when processing massive user data are avoided to a certain extent, the model training process and the intention prediction process are accelerated, and the accuracy of user intention prediction is improved, thereby greatly improving the efficiency of intention prediction.
本公开的示例性实施方式还提供一种意图预测装置。如图10所示，该意图预测装置1000可以包括：The exemplary embodiment of the present disclosure also provides an intention prediction device. As shown in FIG10 , the intention prediction device 1000 may include:
数据获取模块1010，被配置为获取用户的唯一标识信息、网络行为数据与网络性能数据；The data acquisition module 1010 is configured to acquire the user's unique identification information, network behavior data and network performance data;
降维处理模块1020，被配置为将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据；A dimensionality reduction processing module 1020 is configured to divide the network behavior data and the network performance data into multiple dimensions, and merge the network behavior data and the network performance data of different dimensions to obtain initial feature data;
特征融合模块1030，被配置为对初始特征数据进行特征融合，以得到中间特征数据；The feature fusion module 1030 is configured to perform feature fusion on the initial feature data to obtain intermediate feature data;
用户等级信息获取模块1040，被配置为利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据；The user level information acquisition module 1040 is configured to process the intermediate feature data using a preset deep model to obtain user level information and target feature data;
意图预测结果获取模块1050，被配置为利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。The intention prediction result acquisition module 1050 is configured to use the intention prediction model to process the user's unique identification information, user level information and target feature data to obtain the intention prediction result.
在一种实施方式中，上述将网络行为数据与网络性能数据划分为多个维度，并对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据，可以包括：In one implementation, the above-mentioned dividing the network behavior data and the network performance data into multiple dimensions and merging the network behavior data and the network performance data of different dimensions to obtain the initial feature data may include:
在网络行为数据与网络性能数据中确定M个数据样本，并将每个数据样本划分为N个维度，在同一数据样本中，将N个维度的网络行为数据与网络性能数据进行合并，以得到M个中间维度数据，M与N是正整数；Determine M data samples in the network behavior data and the network performance data, and divide each data sample into N dimensions. In the same data sample, merge the network behavior data and the network performance data of N dimensions to obtain M intermediate dimension data, where M and N are positive integers.
根据M个中间维度数据确定特征值和特征向量，将特征值对应的特征向量进行累加，以得到初始特征数据。The eigenvalues and eigenvectors are determined according to the M intermediate dimensional data, and the eigenvectors corresponding to the eigenvalues are accumulated to obtain the initial eigendata.
在一种实施方式中，上述对初始特征数据进行特征融合，以得到中间特征数据，可以包括：In one implementation, the above-mentioned feature fusion of the initial feature data to obtain the intermediate feature data may include:
对初始特征数据进行特征组合，以得到组合特征数据；Performing feature combination on the initial feature data to obtain combined feature data;
根据组合特征数据之间的相似度对组合特征数据进行分类，以得到特征分类数据；Classifying the combined feature data according to the similarity between the combined feature data to obtain feature classification data;
对特征分类数据进行特征融合，以得到中间特征数据。Feature fusion is performed on the feature classification data to obtain intermediate feature data.
在一种实施方式中，上述对特征分类数据进行特征融合，以得到中间特征数据，可以包括：In one implementation, the above-mentioned feature fusion of the feature classification data to obtain the intermediate feature data may include:
将特征分类数据划分为T份，在T份特征分类数据中，选取任一份特征分类数据作为测试集，并将剩余的T-1份特征分类数据作为训练集，以对预设特征融合模型进行训练，T是正整数；The feature classification data is divided into T parts, and any one of the T parts of feature classification data is selected as a test set, and the remaining T-1 parts of feature classification data are used as training sets to train the preset feature fusion model, where T is a positive integer;
根据预设特征融合模型的T次输出结果，确定中间特征数据。Determine the intermediate feature data based on the T output results of the preset feature fusion model.
在一种实施方式中，上述利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据，可以包括：In one implementation, the above-mentioned processing of the intermediate feature data using the preset deep model to obtain the user level information and the target feature data may include:
在中间特征数据中提取目标特征数据；Extracting target feature data from the intermediate feature data;
利用预设深度模型对目标特征数据进行处理，以确定目标特征数据对应的用户等级信息。The target feature data is processed using a preset deep model to determine the user level information corresponding to the target feature data.
在一种实施方式中，上述利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果，可以包括：In one embodiment, the above-mentioned processing of the user's unique identification information, user level information and target feature data using the intention prediction model to obtain the intention prediction result may include:
将同一用户的唯一标识信息、用户等级信息，以及目标特征数据进行一一对应，以得到意图识别数据；Match the unique identification information, user level information, and target feature data of the same user one by one to obtain intent recognition data;
将意图识别数据输入意图预测模型，以得到用户的意图预测结果。The intent recognition data is input into the intent prediction model to obtain the user's intent prediction result.
在一种实施方式中，在获取用户的唯一标识信息、网络行为数据与网络性能数据后，上述装置还可以包括：In one embodiment, after obtaining the user's unique identification information, network behavior data, and network performance data, the above-mentioned device may further include:
对网络行为数据与网络性能数据进行数据预处理。Perform data preprocessing on network behavior data and network performance data.
上述装置中各部分的具体细节在方法部分实施方式中已经详细说明，因而不再赘述。The specific details of each part of the above device have been described in detail in the method part implementation method, so they will not be repeated here.
基于上述装置，一方面，通过对用户数据进行降维处理以及特征融合，在一定程度上避免了相关技术中的意图预测方法在处理海量用户数据时，出现的模型训练过程复杂，且数据过拟合等问题，加速了模型训练过程，以及意图预测过程，同时基于特征处理后的中间特征数据获取用户等级信息，根据用户等级信息与对应的目标特征数据共同预测用户意图，在降低了冗余数据特征对意图预测结果的影响的同时，提高了用户意图预测准确率，从而大大提高了意图预测效率。另一方面，通过获取用户的唯一标识信息、网络行为数据与网络性能数据等多个维度的用户数据，提升了用户数据的丰富度，进一步确保了意图预测结果的准确率。Based on the above device, on the one hand, by performing dimensionality reduction processing and feature fusion on user data, the problems of complex model training process and data overfitting that occur in the intention prediction method in the related technology when processing massive user data are avoided to a certain extent, and the model training process and the intention prediction process are accelerated. At the same time, user level information is obtained based on the intermediate feature data after feature processing, and user intention is predicted based on the user level information and the corresponding target feature data. While reducing the impact of redundant data features on the intention prediction results, the accuracy of user intention prediction is improved, thereby greatly improving the efficiency of intention prediction. On the other hand, by obtaining user data in multiple dimensions such as user unique identification information, network behavior data and network performance data, the richness of user data is improved, and the accuracy of intention prediction results is further ensured.
本公开的示例性实施方式还提供了一种计算机可读存储介质，可以实现为一种程序产品的形式，其包括程序代码，当程序产品在电子设备上运行时，程序代码用于使电子设备执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。在一种可选的实施方式中，该程序产品可以实现为便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在电子设备，例如个人电脑上运行。然而，本公开的程序产品不限于此，在本文件中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。The exemplary embodiments of the present disclosure also provide a computer-readable storage medium, which can be implemented in the form of a program product, which includes a program code, and when the program product is run on an electronic device, the program code is used to cause the electronic device to perform the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. In an optional embodiment, the program product can be implemented as a portable compact disk read-only memory (CD-ROM) and includes program code, and can be run on an electronic device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or device.
程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
可以以一种或多种程序设计语言的任意组合来编写用于执行本公开操作的程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages. Languages include object-oriented programming languages such as Java, C++, etc., as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, as a separate software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).
本公开的示例性实施方式还提供一种电子设备。该电子设备可以包括处理器与存储器。存储器存储有处理器的可执行指令，如可以是程序代码。处理器通过执行该可执行指令来执行本示例性实施方式中的方法。The exemplary embodiment of the present disclosure also provides an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as program codes. The processor executes the method in the exemplary embodiment by executing the executable instructions.
下面参考图11，以通用计算设备的形式对电子设备进行示例性说明。应当理解，图11显示的电子设备1100仅仅是一个示例，不应对本公开实施方式的功能和使用范围带来限制。Referring to Fig. 11, an electronic device is exemplarily described in the form of a general computing device. It should be understood that the electronic device 1100 shown in Fig. 11 is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.
如图11所示，电子设备1100可以包括：处理器1110、存储器1120、总线1130、I/O(输入/输出)接口1140、网络适配器1150。As shown in FIG. 11 , the electronic device 1100 may include a processor 1110 , a memory 1120 , a bus 1130 , an I/O (input/output) interface 1140 , and a network adapter 1150 .
处理器1110可以包括一个或多个处理单元，例如：处理器1110可以包括中央处理器(Central Processing Unit，CPU)、AP(Application Processor，应用处理器)、调制解调处理器、显示处理器(Display Process Unit，DPU)、GPU(Graphics Processing Unit，图形处理器)、ISP(Image Signal Processor，图像信号处理器)、控制器、编码器、解码器、DSP(Digital Signal Processor，数字信号处理器)、基带处理器、人工智能处理器等。在一种实施方式中，可以由GPU获取用户的唯一标识信息、网络行为数据与网络性能数据；并将网络行为数据与网络性能数据划分为多个维度，对不同维度的网络行为数据与网络性能数据进行合并，以得到初始特征数据；再对初始特征数据进行特征融合，以得到中间特征数据；利用预设深度模型对中间特征数据进行处理，得到用户等级信息与目标特征数据；最后利用意图预测模型对用户的唯一标识信息、用户等级信息与目标特征数据进行处理，以得到意图预测结果。The processor 1110 may include one or more processing units, for example: the processor 1110 may include a central processing unit (CPU), an AP (Application Processor), a modem processor, a display processor (DPU), a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, an artificial intelligence processor, etc. In one embodiment, the GPU may obtain the user's unique identification information, network behavior data, and network performance data; and divide the network behavior data and network performance data into multiple dimensions, and merge the network behavior data and network performance data of different dimensions to obtain initial feature data; then perform feature fusion on the initial feature data to obtain intermediate feature data; use a preset deep model to process the intermediate feature data to obtain user level information and target feature data; finally, use the intention prediction model to process the user's unique identification information, user level information, and target feature data to obtain an intention prediction result.
存储器1120可以包括易失性存储器，例如RAM 1121、缓存单元1122，还可以包括非易失性存储器，例如ROM 1123。存储器1120还可以包括一个或多个程序模块1124，这样的程序模块1124包括但不限于：操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。例如，程序模块1124可以包括上述装置1000中的各模块。The memory 1120 may include a volatile memory, such as a RAM 1121, a cache unit 1122, and may also include a non-volatile memory, such as a ROM 1123. The memory 1120 may also include one or more program modules 1124, such program modules 1124 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. For example, the program module 1124 may include each module in the above-mentioned device 1000.
总线1130用于实现电子设备1100的不同组件之间的连接，可以包括数据总线、地址总线和控制总线。The bus 1130 is used to realize the connection between different components of the electronic device 1100, and may include a data bus, an address bus, and a control bus.
电子设备1100可以通过I/O接口1140与一个或多个外部设备1200(例如键盘、鼠标、外置控制器等)进行通信。The electronic device 1100 can communicate with one or more external devices 1200 (eg, a keyboard, a mouse, an external controller, etc.) through the I/O interface 1140 .
电子设备1100可以通过网络适配器1150与一个或者多个网络通信，例如网络适配器1150可以提供如3G/4G/5G等移动通信解决方案，或者提供如无线局域网、蓝牙、近场通信等无线通信解决方案。网络适配器1150可以通过总线1130与电子设备1100的其它模块通信。The electronic device 1100 can communicate with one or more networks through the network adapter 1150. For example, the network adapter 1150 can provide mobile communication solutions such as 3G/4G/5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 1150 can communicate with other modules of the electronic device 1100 through the bus 1130.
尽管图11中未示出，还可以在电子设备1100中设置其它硬件和/或软件模块，包括但不限于：显示器、微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。Although not shown in FIG. 11 , other hardware and/or software modules may be provided in the electronic device 1100 , including but not limited to: a display, a microcode, a device driver, a redundant processor, an external disk drive array, a RAID system, a tape drive, and a data backup storage system, etc.
应当注意，尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元，但是这种划分并非强制性的。实际上，根据本公开的示例性实施方式，上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之，上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.
所属技术领域的技术人员能够理解，本公开的各个方面可以实现为系统、方法或程序产品。因此，本公开的各个方面可以具体实现为以下形式，即：完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等)，或硬件和软件方面结合的实施方式，这里可以统称为“电路”、“模块”或“系统”。本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其他实施方式。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施方式仅被视为示例性的，本公开的真正范围和精神由权利要求指出。It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or implementations combining hardware and software aspects, which may be collectively referred to herein as "circuit", "module" or "system". Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and implementation are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限定。It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094066.7ACN117217365A (en) | 2023-08-28 | 2023-08-28 | Intent prediction method and device, storage medium and electronic equipment |
| CN202311094066.7 | 2023-08-28 |
| Publication Number | Publication Date |
|---|---|
| WO2025044371A1true WO2025044371A1 (en) | 2025-03-06 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/097223PendingWO2025044371A1 (en) | 2023-08-28 | 2024-06-04 | Intention prediction method and apparatus, storage medium, and electronic device |
| Country | Link |
|---|---|
| CN (1) | CN117217365A (en) |
| WO (1) | WO2025044371A1 (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117217365A (en)* | 2023-08-28 | 2023-12-12 | 中国电信股份有限公司技术创新中心 | Intent prediction method and device, storage medium and electronic equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210191506A1 (en)* | 2018-01-26 | 2021-06-24 | Institute Of Software Chinese Academy Of Sciences | Affective interaction systems, devices, and methods based on affective computing user interface |
| CN113298321A (en)* | 2021-06-22 | 2021-08-24 | 深圳市查策网络信息技术有限公司 | User intention prediction method based on multi-data fusion |
| CN115238816A (en)* | 2022-08-10 | 2022-10-25 | 平安科技（深圳）有限公司 | User classification method based on multi-metadata fusion and related equipment |
| CN116310382A (en)* | 2023-02-27 | 2023-06-23 | 中国工商银行股份有限公司 | Public opinion prediction method, device, electronic equipment and storage medium |
| CN117217365A (en)* | 2023-08-28 | 2023-12-12 | 中国电信股份有限公司技术创新中心 | Intent prediction method and device, storage medium and electronic equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210191506A1 (en)* | 2018-01-26 | 2021-06-24 | Institute Of Software Chinese Academy Of Sciences | Affective interaction systems, devices, and methods based on affective computing user interface |
| CN113298321A (en)* | 2021-06-22 | 2021-08-24 | 深圳市查策网络信息技术有限公司 | User intention prediction method based on multi-data fusion |
| CN115238816A (en)* | 2022-08-10 | 2022-10-25 | 平安科技（深圳）有限公司 | User classification method based on multi-metadata fusion and related equipment |
| CN116310382A (en)* | 2023-02-27 | 2023-06-23 | 中国工商银行股份有限公司 | Public opinion prediction method, device, electronic equipment and storage medium |
| CN117217365A (en)* | 2023-08-28 | 2023-12-12 | 中国电信股份有限公司技术创新中心 | Intent prediction method and device, storage medium and electronic equipment |
| Publication number | Publication date |
|---|---|
| CN117217365A (en) | 2023-12-12 |
| Publication | Publication Date | Title |
|---|---|---|
| CN112084383B (en) | Knowledge graph-based information recommendation method, device, equipment and storage medium | |
| CN111612038B (en) | Abnormal user detection method and device, storage medium and electronic equipment | |
| JP2020123331A (en) | Intent identification method, device, and computer-readable storage medium | |
| CN111612041A (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| CN116049412B (en) | Text classification method, model training method, device and electronic equipment | |
| CN113934851B (en) | Data enhancement method, device and electronic device for text classification | |
| WO2020140624A1 (en) | Method for extracting data from log, and related device | |
| CN112883990A (en) | Data classification method and device, computer storage medium and electronic equipment | |
| CN119938335A (en) | Service proxy method and system based on Doris front-end node | |
| CN119323209B (en) | Automatic ICD coding method and system based on multi-label information fusion | |
| WO2025044371A1 (en) | Intention prediction method and apparatus, storage medium, and electronic device | |
| CN114781611A (en) | Natural language processing method, language model training method and related equipment | |
| CN113315851A (en) | Domain name detection method, device and storage medium | |
| CN118261677A (en) | Client information analysis management system and method based on data mining | |
| CN119620957A (en) | Erasure code compatible reading and writing method and system based on bidirectional data access agent | |
| CN115687732B (en) | User analysis method and system based on AI and streaming computing | |
| CN120151781A (en) | Intelligent scheduling method for SMS sending channels based on multi-source data fusion | |
| CN119048147B (en) | User portrait generation method and system based on behavior data | |
| CN119513818A (en) | A multimodal data fusion method, device, equipment and medium | |
| Mondal et al. | A survey of multimodal event detection based on data fusion | |
| CN119646188A (en) | Training method, device and equipment for generative recall large model based on advertisement | |
| CN119562294A (en) | Root cause analysis method, device, storage medium and electronic device for perceived poor quality | |
| CN115904920A (en) | A test case recommendation method, device, terminal and storage medium | |
| CN113627563A (en) | Label labeling method, device and medium | |
| CN113792163A (en) | Multimedia recommendation method and device, electronic equipment and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application | Ref document number:24857916 Country of ref document:EP Kind code of ref document:A1 |