CN111783445A - Data generation method, device, medium and electronic device - Google Patents
Data generation method, device, medium and electronic deviceDownload PDFInfo
- Publication number
- CN111783445A CN111783445ACN201910558488.2ACN201910558488ACN111783445ACN 111783445 ACN111783445 ACN 111783445ACN 201910558488 ACN201910558488 ACN 201910558488ACN 111783445 ACN111783445 ACN 111783445A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- data
- evaluated
- evaluation data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Electronic shopping [e-shopping] by investigating goods or services
- G06Q30/0625—Electronic shopping [e-shopping] by investigating goods or services by formulating product or service queries, e.g. using keywords or predefined options
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及数据处理技术领域，尤其涉及一种数据生成方法、装置、介质及电子设备。The present invention relates to the technical field of data processing, and in particular, to a data generation method, device, medium and electronic device.
背景技术Background technique
随着电子商务的兴起，网购已经成为了一种颇受欢迎的购物方式，其具有两大优势：便利性和商品多样性。With the rise of e-commerce, online shopping has become a popular shopping method with two major advantages: convenience and variety.
其中，在网购过程中，由于网购过程存在着关于商品的信任危机，即用户通过浏览应用程序(Application，简称APP)或者网站上商品图片或者文字介绍而获取到的有限的商品认知与接收到的实际商品的差异。因此，用户通常在对于商品的特性(外形样式、材料质地、价格)比较满意时，还会通过浏览已购买用户对于商品的评论的方式以便进一步进行决策。Among them, in the process of online shopping, there is a crisis of trust in the online shopping process, that is, the limited recognition and reception of products obtained by users by browsing the application (Application, APP for short) or the product pictures or text introductions on the website differences in the actual product. Therefore, when the user is generally satisfied with the characteristics of the product (shape, material texture, price), he or she will make further decisions by browsing the comments of the purchased user on the product.
但是，由于商品评论信息通常数量较多，并且内容混乱，从而导致了查看商品评论的用户并不能高效地获取到该商品核心的评价数据。However, because the product review information is usually large in quantity and the content is chaotic, users who view the product reviews cannot efficiently obtain the core evaluation data of the product.
发明内容SUMMARY OF THE INVENTION
本发明实施例提供一种数据生成方法、装置、介质及电子设备，以为用户提供高价值的商品数据，为用户的购物决策提供可靠的参考。Embodiments of the present invention provide a data generation method, device, medium and electronic device, so as to provide users with high-value commodity data and provide a reliable reference for users' shopping decisions.
第一方面，本发明实施例提供一种数据生成方法，包括：In a first aspect, an embodiment of the present invention provides a data generation method, including:
获取待评价对象的历史评价数据，并提取所述历史评价数据的评价关键词，所述评价关键词用于表征所述待评价对象的物理特性；Obtain historical evaluation data of the object to be evaluated, and extract evaluation keywords of the historical evaluation data, where the evaluation keywords are used to characterize the physical properties of the object to be evaluated;
根据所述评价关键词以及预设神经网络模型生成所述评价关键词对应的评价数据；generating evaluation data corresponding to the evaluation keywords according to the evaluation keywords and a preset neural network model;
在所述待评价对象的评价区域中的第一预设位置展示所述评价数据。The evaluation data is displayed at a first preset position in the evaluation area of the object to be evaluated.
在一种可能的设计中，在在所述待评价对象的评价区域中的预设位置展示所述评价数据之后，还包括：In a possible design, after displaying the evaluation data at a preset position in the evaluation area of the object to be evaluated, the method further includes:
获取针对第一评价数据输入的第一评价指令，所述评价数据包括所述第一评价数据；obtaining a first evaluation instruction input for first evaluation data, the evaluation data including the first evaluation data;
在所述待评价对象的评价区域中的第二预设位置展示所述第一评价指令所对应的第一子评价，所述第一子评价用于评价所述第一评价数据，所述第二预设位置与所述第一预设位置在所述评价区域中相邻设置。A first sub-evaluation corresponding to the first evaluation instruction is displayed at a second preset position in the evaluation area of the object to be evaluated, where the first sub-evaluation is used to evaluate the first evaluation data, and the first sub-evaluation is used to evaluate the first evaluation data. Two preset positions are arranged adjacent to the first preset position in the evaluation area.
在一种可能的设计中，所述提取所述历史评价数据的评价关键词，包括：In a possible design, the extracting evaluation keywords of the historical evaluation data include:
根据预设词库对所述历史评价数据进行分词处理，以获取分词集合；Perform word segmentation processing on the historical evaluation data according to a preset thesaurus to obtain a word segmentation set;
根据预设关键词权重算法计算所述分词集合中每个分词的权重值；Calculate the weight value of each word segment in the word segment set according to a preset keyword weight algorithm;
选取所述权重值大于预设权重值的分词作为所述历史评价数据的第一评价关键词，所述评价关键词包括所述第一评价关键词。The word segmentation with the weight value greater than the preset weight value is selected as the first evaluation keyword of the historical evaluation data, and the evaluation keyword includes the first evaluation keyword.
在一种可能的设计中，所述获取待评价对象的历史评价数据，包括：In a possible design, the obtaining historical evaluation data of the object to be evaluated includes:
当所述待评价对象对应的评价的条目数量大于预设条目数量阈值时，获取当前的所述评价作为所述待评价对象对应的所述历史评价数据。When the number of evaluation items corresponding to the to-be-evaluated object is greater than a preset number of entries threshold, the current evaluation is acquired as the historical evaluation data corresponding to the to-be-evaluated object.
在一种可能的设计中，在所述根据预设词库对所述历史评价数据进行分词处理之前，还包括：In a possible design, before the word segmentation processing is performed on the historical evaluation data according to the preset vocabulary, the method further includes:
对所述历史评价数据进行预处理，所述预处理包括：去除所述历史评价数据中的停用词以及标点符号。The historical evaluation data is preprocessed, and the preprocessing includes: removing stop words and punctuation marks in the historical evaluation data.
在一种可能的设计中，所述获取待评价对象的历史评价数据，并提取所述历史评价数据的评价关键词，包括：In a possible design, obtaining historical evaluation data of the object to be evaluated, and extracting evaluation keywords of the historical evaluation data, including:
当所述待评价对象对应的评价条目小于或者等于所述预设条目阈值时，获取所述待评价对象对应的三级类目对应的评价关键词作为第二评价关键词，所述评价关键词包括所述第二评价关键词。When the evaluation item corresponding to the object to be evaluated is less than or equal to the preset item threshold, the evaluation keyword corresponding to the third-level category corresponding to the object to be evaluated is obtained as a second evaluation keyword, and the evaluation keyword The second evaluation keyword is included.
在一种可能的设计中，所述根据所述评价关键词以及预设神经网络模型生成所述评价关键词对应的评价数据，包括：In a possible design, generating the evaluation data corresponding to the evaluation keywords according to the evaluation keywords and a preset neural network model includes:
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第一评价数据；generating first evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第二评价数据；generating second evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
其中，所述评价数据包括所述第一评价数据以及所述第二评价数据。The evaluation data includes the first evaluation data and the second evaluation data.
在一种可能的设计中，在所述根据所述评价关键词以及预设神经网络模型生成所述评价关键词对应的评价数据之前，还包括：In a possible design, before generating the evaluation data corresponding to the evaluation keywords according to the evaluation keywords and a preset neural network model, the method further includes:
根据所述评价关键词以及所述历史评价数据对所述预设神经网络模型进行训练，所述预设神经网络模型为长短期记忆网络模型。The preset neural network model is trained according to the evaluation keywords and the historical evaluation data, and the preset neural network model is a long short-term memory network model.
在一种可能的设计中，所述根据所述评价关键词对所述预设神经网络模型进行训练，包括：In a possible design, the training of the preset neural network model according to the evaluation keywords includes:
对所述评价关键词以及所述分词集合中的各个分词进行向量化，并将向量化后的数据矩阵作为训练数据输入对所述长短期记忆网络模型进行训练。The evaluation keyword and each word segment in the word segment set are vectorized, and the vectorized data matrix is input as training data to train the long short-term memory network model.
第二方面，本发明实施例还提供一种数据生成装置，包括：In a second aspect, an embodiment of the present invention further provides a data generation device, including:
获取模块，用于获取待评价对象的历史评价数据；The acquisition module is used to acquire the historical evaluation data of the object to be evaluated;
提取模块，用于提取所述历史评价数据的评价关键词，所述评价关键词用于表征所述待评价对象的物理特性；an extraction module for extracting evaluation keywords of the historical evaluation data, where the evaluation keywords are used to characterize the physical properties of the object to be evaluated;
处理模块，用于根据所述评价关键词以及预设神经网络模型生成所述评价关键词对应的评价数据；a processing module, configured to generate evaluation data corresponding to the evaluation keywords according to the evaluation keywords and a preset neural network model;
显示模块，用于在所述待评价对象的评价区域中的第一预设位置展示所述评价数据。A display module, configured to display the evaluation data at a first preset position in the evaluation area of the object to be evaluated.
在一种可能的设计中，所述获取模块，还用于获取针对第一评价数据输入的第一评价指令，所述评价数据包括所述第一评价数据；In a possible design, the obtaining module is further configured to obtain a first evaluation instruction input for first evaluation data, where the evaluation data includes the first evaluation data;
所述显示模块，还用于在所述待评价对象的评价区域中的第二预设位置展示所述第一评价指令所对应的第一子评价，所述第一子评价用于评价所述第一评价数据，所述第二预设位置与所述第一预设位置在所述评价区域中相邻设置。The display module is further configured to display a first sub-evaluation corresponding to the first evaluation instruction at a second preset position in the evaluation area of the object to be evaluated, and the first sub-evaluation is used to evaluate the For the first evaluation data, the second preset position and the first preset position are arranged adjacent to each other in the evaluation area.
在一种可能的设计中，所述提取模块，具体用于：In a possible design, the extraction module is specifically used for:
根据预设词库对所述历史评价数据进行分词处理，以获取分词集合；Perform word segmentation processing on the historical evaluation data according to a preset thesaurus to obtain a word segmentation set;
根据预设关键词权重算法计算所述分词集合中每个分词的权重值；Calculate the weight value of each word segment in the word segment set according to the preset keyword weight algorithm;
选取所述权重值大于预设权重值的分词作为所述历史评价数据的第一评价关键词，所述评价关键词包括所述第一评价关键词。The word segmentation with the weight value greater than the preset weight value is selected as the first evaluation keyword of the historical evaluation data, and the evaluation keyword includes the first evaluation keyword.
在一种可能的设计中，所述获取模块，具体用于：In a possible design, the acquisition module is specifically used for:
当所述待评价对象对应的评价的条目数量大于预设条目数量阈值时，获取当前的所述评价作为所述待评价对象对应的所述历史评价数据。When the number of evaluation items corresponding to the to-be-evaluated object is greater than a preset number of entries threshold, the current evaluation is acquired as the historical evaluation data corresponding to the to-be-evaluated object.
在一种可能的设计中，所述处理模块，还用于对所述历史评价数据进行预处理，所述预处理包括：去除所述历史评价数据中的停用词以及标点符号。In a possible design, the processing module is further configured to preprocess the historical evaluation data, and the preprocessing includes: removing stop words and punctuation marks in the historical evaluation data.
在一种可能的设计中，所述提取模块，具体用于：In a possible design, the extraction module is specifically used for:
当所述待评价对象对应的评价条目小于或者等于所述预设条目阈值时，获取所述待评价对象对应的三级类目对应的评价关键词作为第二评价关键词，所述评价关键词包括所述第二评价关键词。When the evaluation item corresponding to the object to be evaluated is less than or equal to the preset item threshold, the evaluation keyword corresponding to the third-level category corresponding to the object to be evaluated is obtained as a second evaluation keyword, and the evaluation keyword The second evaluation keyword is included.
在一种可能的设计中，所述处理模块，具体用于：In a possible design, the processing module is specifically used for:
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第一评价数据；generating first evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第二评价数据；generating second evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
其中，所述评价数据包括所述第一评价数据以及所述第二评价数据。The evaluation data includes the first evaluation data and the second evaluation data.
在一种可能的设计中，所述数据生成装置，还包括：In a possible design, the data generating device further includes:
训练模块，用于根据所述评价关键词以及所述历史评价数据对所述预设神经网络模型进行训练，所述预设神经网络模型为长短期记忆网络模型。A training module, configured to train the preset neural network model according to the evaluation keywords and the historical evaluation data, where the preset neural network model is a long short-term memory network model.
在一种可能的设计中，所述训练模块，具体用于：In a possible design, the training module is specifically used to:
对所述评价关键词以及所述分词集合中的各个分词进行向量化，并将向量化后的数据矩阵作为训练数据输入对所述长短期记忆网络模型进行训练。The evaluation keyword and each word segment in the word segment set are vectorized, and the vectorized data matrix is input as training data to train the long short-term memory network model.
第三方面，本发明实施例还提供一种电子设备，包括：In a third aspect, an embodiment of the present invention further provides an electronic device, including:
处理器；以及，processor; and,
存储器，用于存储所述处理器的可执行指令；a memory for storing executable instructions for the processor;
其中，所述处理器配置为经由执行所述可执行指令来执行第一方面中任意一种可能的数据生成方法。Wherein, the processor is configured to execute any one of the possible data generation methods in the first aspect by executing the executable instructions.
第四方面，本发明实施例还提供一种存储介质，其上存储有计算机程序，该程序被处理器执行时实现第一方面中任意一种可能的数据生成方法。In a fourth aspect, an embodiment of the present invention further provides a storage medium on which a computer program is stored, and when the program is executed by a processor, implements any one of the possible data generation methods in the first aspect.
本发明实施例提供的一种数据生成方法、装置、介质及电子设备，通过获取待评价对象的历史评价数据，并从历史评价数据中提取能够用于表征所述待评价对象的物理特性评价关键词，然后通过将评价关键词输入至预设神经网络模型获取到评价数据，其中，该评价数据可以作为待评价对象的核心评价数据，在待评价对象的评价区域中的第一预设位置进行展示，从而为用户输出用于表征待评价对象相关特征的高价值评价数据。A data generation method, device, medium and electronic device provided by the embodiments of the present invention obtain historical evaluation data of an object to be evaluated, and extract from the historical evaluation data a physical property evaluation key that can be used to characterize the object to be evaluated Then, the evaluation data is obtained by inputting the evaluation keywords into the preset neural network model, wherein the evaluation data can be used as the core evaluation data of the object to be evaluated, and the evaluation data is performed at the first preset position in the evaluation area of the object to be evaluated. display, so as to output high-value evaluation data for the user to characterize the relevant characteristics of the object to be evaluated.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.
图1是本发明根据一示例实施例示出的数据生成方法应用场景架构示意图；1 is a schematic diagram of an application scenario architecture of a data generation method according to an exemplary embodiment of the present invention;
图2是本发明根据一示例实施例示出的数据生成方法的流程示意图；2 is a schematic flowchart of a data generation method according to an exemplary embodiment of the present invention;
图3是图2所示实施例中的一种可能的商品信息浏览界面示意图；3 is a schematic diagram of a possible commodity information browsing interface in the embodiment shown in FIG. 2;
图4是本发明根据另一示例实施例示出的数据生成方法的流程示意图；4 is a schematic flowchart of a data generation method according to another exemplary embodiment of the present invention;
图5是图4所示实施例中的一种可能的商品评价界面示意图；FIG. 5 is a schematic diagram of a possible product evaluation interface in the embodiment shown in FIG. 4;
图6是本发明根据一示例实施例示出的预设神经网络模型训练过程示意图；6 is a schematic diagram of a training process of a preset neural network model according to an exemplary embodiment of the present invention;
图7是本发明根据一示例实施例示出的数据生成装置的结构示意图；7 is a schematic structural diagram of a data generating apparatus according to an exemplary embodiment of the present invention;
图8是本发明根据另一示例实施例示出的数据生成装置的结构示意图；8 is a schematic structural diagram of a data generating apparatus according to another exemplary embodiment of the present invention;
图9是本发明根据一示例实施例示出的电子设备的结构示意图。FIG. 9 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third", "fourth", etc. (if present) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to Describe a particular order or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.
一般来说，用户网购一件商品的流程大致可以简化为如下流程：(1)无意识的浏览商品或者有目标地搜索某件商品；(2)查看商品详情；(3)查看商品评论；(4)下单支付购买。在上述步骤(2)中，假设用户对于商品的特性(外形样式、材料质地、价格)比较满意，此时用户并不会像在实体店购物时一样直接进入购买环节，因为用户明白，此时看到的物品可能与真实物品存在差异，因而用户一般会仔细的浏览已购买用户对于商品的评论，并且会重点关注自己在意的一些特性，比如颜色、样式等，在此过程中，商品评论信息在很大程度上决定了用户的下单购买行为。Generally speaking, the process of a user purchasing a product online can be roughly simplified as follows: (1) Unconsciously browsing the product or searching for a certain product purposefully; (2) Viewing product details; (3) Viewing product reviews; (4) ) to place an order to pay for the purchase. In the above step (2), it is assumed that the user is satisfied with the characteristics of the product (appearance style, material texture, price). At this time, the user will not directly enter the purchase link as when shopping in a physical store, because the user understands that at this time The items seen may be different from the real items, so users will generally carefully browse the reviews of the purchased users' products, and will focus on some features that they care about, such as color, style, etc. During this process, the product review information To a large extent, it determines the user's order and purchase behavior.
而当前，网购商品的商品评论信息都是由用户在完成交易后自愿性填写。通过对用户的评论行为的简单分析，可以以京东商城APP上的商品评价作为参考，为了鼓励用户提供评论信息，京东商城使用了评价订单送京豆的激励策略。At present, the product review information of online shopping products is filled in voluntarily by the user after completing the transaction. Through a simple analysis of the user's comment behavior, the product evaluation on the Jingdong Mall APP can be used as a reference. In order to encourage users to provide comment information, Jingdong Mall uses the incentive strategy of sending Jingdou for evaluation orders.
具体的，在此情景下，用户可以大致分为三类：第一类是不参与评论者，第二类是真实评论者，第三类是为拿京豆奖励者。Specifically, in this scenario, users can be roughly divided into three categories: the first category is those who do not participate in commenting, the second category is real commenters, and the third category is those who receive Jingdou rewards.
可以理解的，第一类人中，有部分是没有评价意识的人，还有部分人是有评价意识，但是觉得写评论是一件费时费力的事情；而第二类人主要来源于无奖励也会评价的人，这部分用户自主评价意识比较强，一般是对购买的商品有明确的喜好与厌恶感并且想要分享给后来的购买者，因而这类人提交的评论信息价值会比较高，还有部分是受奖励策略刺激而认真评价的人；第三类人则基本是为了奖励而随意评论的人，他们的评论一般毫无意义。It is understandable that some of the first type of people are people who have no sense of evaluation, and some people have a sense of evaluation, but feel that writing comments is a time-consuming and laborious thing; while the second type of people mainly comes from the lack of rewards People who will also evaluate. These users have a strong sense of self-evaluation. Generally, they have clear preferences and dislikes for the purchased products and want to share them with subsequent buyers. Therefore, the value of the comments submitted by such people will be relatively high. , and some are people who are motivated by the reward strategy and make serious comments; the third type of people are basically people who comment randomly for the sake of reward, and their comments are generally meaningless.
并且，对用户填写的商品评论信息的内容也是因人而异，有的评论简洁、重点突出，有的则文不对题。因此，过多的商品评论信息反而会给用户在进行购买决策时造成困扰，而无法快速获取到有效的评价数据。In addition, the content of the product review information filled in by the user also varies from person to person, some comments are concise and focused, while others are incorrect. Therefore, too much product review information will cause trouble for users when making purchase decisions, and it is impossible to quickly obtain effective evaluation data.
针对上述存在的各个问题，本发明实施例提供一种数据生成方法，通过获取待评价对象的历史评价数据，并从历史评价数据中提取能够用于表征所述待评价对象的物理特性评价关键词，然后通过将评价关键词输入至预设神经网络模型获取到商品评价数据，其中，该商品评价数据可以作为待评价对象的核心评价数据，在待评价对象的评价区域中的第一预设位置进行展示，从而为用户提供高价值的商品评价数据，以对用户的购物决策提供可靠的参考。可选的，上述的待评价对象可以理解为待评价商品，而上述的历史评价数据可以理解为商品的历史评价信息。In view of the above-mentioned problems, an embodiment of the present invention provides a data generation method, by acquiring historical evaluation data of an object to be evaluated, and extracting from the historical evaluation data physical property evaluation keywords that can be used to characterize the object to be evaluated , and then obtain the product evaluation data by inputting the evaluation keywords into the preset neural network model, wherein the product evaluation data can be used as the core evaluation data of the object to be evaluated, and the first preset position in the evaluation area of the object to be evaluated Display, so as to provide users with high-value product evaluation data to provide a reliable reference for users' shopping decisions. Optionally, the above-mentioned object to be evaluated can be understood as the commodity to be evaluated, and the above-mentioned historical evaluation data can be understood as the historical evaluation information of the commodity.
其中，对于该方案中的数据生成方法所实现的装置可以为任意可以进行游戏的各类电子设备中，包括平板电脑，智能手机，个人计算机等。下面通过几个具体实现方式对该数据生成方法进行详细说明。Wherein, the device implemented by the data generation method in this solution may be any of various electronic devices that can play games, including tablet computers, smart phones, personal computers, and the like. The data generation method will be described in detail below through several specific implementation manners.
图1是本发明根据一示例实施例示出的数据生成方法应用场景架构示意图。如图1所示，在需要为待评价对象提供评价数据时，例如需要为待评价商品提供商品评价数据时，可以是通过网关发送请求，然后通过商品评价获取服务从核心评价数据库中获取相应的核心评价，并将这些核心评价作为待评价商品的商品评价数据，并响应输出为在待评价商品的评价区域中进行展示。FIG. 1 is a schematic diagram of an application scenario architecture of a data generation method according to an exemplary embodiment of the present invention. As shown in Figure 1, when it is necessary to provide evaluation data for the object to be evaluated, for example, when it is necessary to provide product evaluation data for the product to be evaluated, a request can be sent through the gateway, and then the corresponding product evaluation data is obtained from the core evaluation database through the product evaluation acquisition service. core evaluations, and use these core evaluations as product evaluation data of the product to be evaluated, and the response output is displayed in the evaluation area of the product to be evaluated.
其中，商品评价获取服务可以是通过商品评价获取接口从核心评论数据库中获取，也可以是从历史评论获取接口中根据当前的待评价商品已经具备的历史评论信息中获得。The product evaluation obtaining service may be obtained from the core review database through the product evaluation obtaining interface, or may be obtained from the historical review obtaining interface according to the historical review information already possessed by the current product to be evaluated.
值得理解的，对于从历史评论获取接口中根据当前的待评价商品已经具备的历史评论信息中获得，可以是当待评价商品已经具备一定数量的历史评价数据，例如，可以设置一个评价数阈值，当商品的评价数超过该阈值时，可以对该待评价商品进行评价关键词提取，即将所有的评价数据汇总为多个评价集合，比如每个评价集合中有100条评价，然后输入至训练完成的长短期记忆网络模型(Long Short-Term Memory，简称LSTM)，以生成评价数据，并还可以将该评价数据与待评价商品的编码建立映射关系，以便后续查询。It is worth understanding that for the historical review information obtained from the historical review acquisition interface based on the current review information that the product to be evaluated already has, it can be when the product to be evaluated already has a certain amount of historical evaluation data. For example, a threshold for the number of reviews can be set. When the number of evaluations of a product exceeds the threshold, evaluation keywords can be extracted for the product to be evaluated, that is, all evaluation data are aggregated into multiple evaluation sets, for example, there are 100 evaluations in each evaluation set, and then input to the training completion. The long short-term memory network model (Long Short-Term Memory, referred to as LSTM) to generate evaluation data, and can also establish a mapping relationship between the evaluation data and the code of the product to be evaluated for subsequent query.
还值得理解的，而考虑有些商品刚上架，没有历史评论信息或评论信息太少，此时利用三级类目的评论关键词作为该待评价商品的评论关键词。而对于这种情况，核心评论数据库可以通过商品评价生成服务生成，而商品评价生成服务可以是在线的，也可以是离线的，其具体是通过先获取商品信息以及该待评价对应商品三级目类的历史评价数据，然后通过关键词权重算法，例如词频-逆文本频率指数算法(Term Frequency–InverseDocument Frequency，简称TF-IDF)获取历史评价数据中评价关键词，以生成评价关键词数据库，然后将评价关键词输入至LSTM中，以生成评价数据，并还可以将该商品评价数据与三级类目建立映射关系，以便后续查询。It is also worth understanding. Considering that some products have just been put on the shelves, there is no historical comment information or there is too little comment information. At this time, the comment keywords of the third-level category are used as the comment keywords of the product to be evaluated. In this case, the core review database can be generated through the product evaluation generation service, and the product evaluation generation service can be online or offline. Class of historical evaluation data, and then obtain the evaluation keywords in the historical evaluation data through the keyword weight algorithm, such as the term frequency-inverse text frequency index algorithm (Term Frequency-Inverse Document Frequency, referred to as TF-IDF), to generate an evaluation keyword database, and then The evaluation keywords are input into the LSTM to generate evaluation data, and a mapping relationship between the product evaluation data and the three-level category can also be established for subsequent query.
此外，还可以是将上述两种方式获取到的评价关键词均输入至LSTM中，从而生成对应评价关键词的商品评价数据。并且，将商品评价数据以(待评价对象编码：核心评价1，核心评价2……)和(三级类目：核心评价1，核心评价2……)的映射关系保存到数据库中，以供线上查询使用。In addition, the evaluation keywords obtained in the above two ways may also be input into the LSTM, thereby generating product evaluation data corresponding to the evaluation keywords. In addition, the product evaluation data is stored in the database with the mapping relationship of (code of object to be evaluated: core evaluation 1, core evaluation 2...) and (three-level category: core evaluation 1, core evaluation 2...) for use in the database. Use online inquiries.
图2是本发明根据一示例实施例示出的数据生成方法的流程示意图。如图2所示，本实施例提供的数据生成方法，包括：FIG. 2 is a schematic flowchart of a data generation method according to an exemplary embodiment of the present invention. As shown in Figure 2, the data generation method provided by this embodiment includes:
步骤101、获取待评价对象的历史评价数据。Step 101: Obtain historical evaluation data of the object to be evaluated.
具体的，可以是当待评价对象对应的评价的条目数量大于预设条目数量阈值时，获取当前的商品评价作为待评价对象对应的历史评价数据。例如，当待评价对象对应的评价数据的条目数量大于100条时，就可以将这这些商品评价数据作为历史评价数据，用来进行评价关键词的提取。其中，还可以通过将所有的历史评价数据汇总成多个评价数据集合的方式进行提取，例如每个评价数据集合可以包括100条评论。Specifically, when the number of evaluation items corresponding to the object to be evaluated is greater than a preset number of entries threshold, the current product evaluation can be obtained as historical evaluation data corresponding to the object to be evaluated. For example, when the number of items of evaluation data corresponding to the object to be evaluated is greater than 100, these commodity evaluation data can be used as historical evaluation data to extract evaluation keywords. The extraction may also be performed by aggregating all historical evaluation data into multiple evaluation data sets, for example, each evaluation data set may include 100 comments.
步骤102、提取历史评价数据的评价关键词。
对于当待评价商品对应的评价的条目数量大于预设条目数量阈值时，在获取待评价对象的历史评价数据之后，则可以继续提取历史评价数据的评价关键词，其中，评价关键词用于表征待评价商品的物理特性。For when the number of evaluation items corresponding to the product to be evaluated is greater than the preset number of entries threshold, after obtaining the historical evaluation data of the object to be evaluated, the evaluation keywords of the historical evaluation data can continue to be extracted, wherein the evaluation keywords are used to represent The physical properties of the commodity to be evaluated.
具体的，可以是根据预设词库对历史评价数据进行分词处理，以获取分词集合，然后，再根据预设关键词权重算法计算分词集合中每个分词的权重值，并选取权重值大于预设权重值的分词作为历史评价数据的第一评价关键词，评价关键词包括第一评价关键词。可选的，为了分词能够更加准确，在根据预设词库对历史评价数据进行分词处理之前，还可以对历史评价数据进行预处理，其中，预处理可以包括：去除历史评价数据中的停用词以及标点符号。Specifically, the historical evaluation data may be subjected to word segmentation processing according to a preset thesaurus to obtain a word segmentation set, and then, the weight value of each word segmentation in the word segmentation set may be calculated according to a preset keyword weight algorithm, and the weight value greater than the predetermined weight value may be selected. The word segmentation of the weight value is set as the first evaluation keyword of the historical evaluation data, and the evaluation keyword includes the first evaluation keyword. Optionally, in order to make word segmentation more accurate, before performing word segmentation processing on the historical evaluation data according to the preset vocabulary, the historical evaluation data may also be preprocessed, wherein the preprocessing may include: removing the deactivation in the historical evaluation data. words and punctuation.
值得说明的，在本实施例中，预设词库可以为结巴分词库或者其他分词库，还可以是现有分词库的基础上添加自定义词典的扩展分词库。并且，对于关键词权重算法则可以为TF-IDF算法。其中，对于TF-IDF算法的原理：实际是先计算TF与IDF的乘积，然后，用乘积的结果来衡量一个词库中的词对每一篇文档的重要程度，用以评估关键词对于一个文件集或一个语料库中的其中一份文件的重要程度。其中，对于TF-IDF算法的具体实现原理，为现有算法，在本实施例中不做具体限定。It is worth noting that, in this embodiment, the preset thesaurus may be a stuttering thesaurus or other word segmentation databases, and may also be an extended word segmentation database in which a custom dictionary is added on the basis of the existing word segmentation database. And, for the keyword weight algorithm, the TF-IDF algorithm can be used. Among them, the principle of the TF-IDF algorithm: the actual is to first calculate the product of TF and IDF, and then use the result of the product to measure the importance of the words in a thesaurus to each document to evaluate the importance of keywords to a document. The importance of one of the documents in a document set or a corpus. The specific implementation principle of the TF-IDF algorithm is an existing algorithm, which is not specifically limited in this embodiment.
此外，在另一种可能的情况中，当有些商品刚上架，没有历史评价数据或评价数据太少时，即当待评价商品对应的评价条目小于或者等于预设条目阈值时，则可以获取待评价商品对应的三级类目对应的评价关键词作为第二评价关键词，评价关键词包括第二评价关键词。In addition, in another possible situation, when some products have just been put on the shelves, there is no historical evaluation data or there is too little evaluation data, that is, when the evaluation items corresponding to the products to be evaluated are less than or equal to the preset entry threshold, the to-be-evaluated product can be obtained. The evaluation keyword corresponding to the tertiary category corresponding to the product is used as the second evaluation keyword, and the evaluation keyword includes the second evaluation keyword.
步骤103、根据评价关键词以及预设神经网络模型生成评价关键词对应的评价数据。Step 103: Generate evaluation data corresponding to the evaluation keywords according to the evaluation keywords and the preset neural network model.
而在获取到评价关键词之后，可以将评价关键词输入到训练完成的LSTM模型中，以生成评价关键词对应的评价数据。其中，对于预设神经网络模型，如LSTM模型的训练在后续实施例中进行详细说明。其中，可以通过深度学习的方式对模型进行训练，深度学习是一类机器学习算法，可以将深度学习理解为一种数据特征学习方法。其使用多层非线性处理单元级联进行特征提取和转换，每个连续的层使用前一层的输出作为输入，通过对特征逐层抽象，便可以学习到更高级的数据特征。而LSTM是一种特殊的循环神经网络，LSTM通过添加输入门限、遗忘门限和输出门限解决了传统循环神经网络难以处理长距离依赖的问题。After the evaluation keywords are obtained, the evaluation keywords can be input into the trained LSTM model to generate evaluation data corresponding to the evaluation keywords. The training of the preset neural network model, such as the LSTM model, will be described in detail in subsequent embodiments. Among them, the model can be trained by means of deep learning, which is a type of machine learning algorithm, and deep learning can be understood as a data feature learning method. It uses a cascade of multi-layer nonlinear processing units for feature extraction and transformation. Each successive layer uses the output of the previous layer as input. By abstracting features layer by layer, more advanced data features can be learned. LSTM is a special recurrent neural network. LSTM solves the problem that traditional recurrent neural networks are difficult to deal with long-distance dependencies by adding input thresholds, forgetting thresholds and output thresholds.
步骤104、在待评价对象的评价区域中的第一预设位置展示商品评价数据。Step 104: Display the product evaluation data at a first preset position in the evaluation area of the object to be evaluated.
在根据评价关键词以及预设神经网络模型生成评价关键词对应的评价数据之后，还可以在待评价商品的评价区域中的第一预设位置展示商品评价数据，以对待评价商品进行评价。After the evaluation data corresponding to the evaluation keywords is generated according to the evaluation keywords and the preset neural network model, the product evaluation data may also be displayed at the first preset position in the evaluation area of the product to be evaluated to evaluate the product to be evaluated.
在一种可能的情况中，图3是图2所示实施例中的一种可能的商品信息浏览界面示意图。可以选取手机作为待评价商品进行举例说明，如图3所示，评价区域中的第一预设位置可以为图3所示的核心评论区，而通过本实施例方法生成的商品评价数据，例如可以为：功能齐全、使用舒适以及完美运行等。而核心评论区的商品评价数据可以是根据全部评论区域中的历史评价数据确定的核心评价数据，也可以是根据商品三级类目(手机)对应的核心评价数据。In a possible situation, FIG. 3 is a schematic diagram of a possible commodity information browsing interface in the embodiment shown in FIG. 2 . A mobile phone can be selected as the product to be evaluated for illustration. As shown in FIG. 3, the first preset position in the evaluation area can be the core comment area shown in FIG. 3, and the product evaluation data generated by the method of this embodiment, such as It can be: fully functional, comfortable to use and perfectly functioning. The product evaluation data in the core comment area may be the core evaluation data determined according to the historical evaluation data in all the comment areas, or may be the core evaluation data corresponding to the third-level category (mobile phone) of the product.
在本实施例中，通过获取待评价商品的历史评价数据，并从历史评价数据中提取能够用于表征所述待评价商品的物理特性评价关键词，然后通过将评价关键词输入至预设神经网络模型获取到商品评价数据，其中，该商品评价数据可以作为待评价商品的核心评价数据，在待评价商品的评价区域中的第一预设位置进行展示，从而为用户输出用于表征待评价对象相关特征的高价值评价数据。In this embodiment, the historical evaluation data of the commodity to be evaluated is obtained, and the evaluation keywords that can be used to characterize the physical properties of the commodity to be evaluated are extracted from the historical evaluation data, and then the evaluation keywords are input into the preset neural network. The network model obtains the product evaluation data, wherein the product evaluation data can be used as the core evaluation data of the product to be evaluated, and displayed in the first preset position in the evaluation area of the product to be evaluated, so as to be output for the user to represent the product to be evaluated High-value evaluation data for object-related features.
图4是本发明根据另一示例实施例示出的数据生成方法的流程示意图。如图4所示，本实施例提供的数据生成方法，包括：FIG. 4 is a schematic flowchart of a data generation method according to another exemplary embodiment of the present invention. As shown in Figure 4, the data generation method provided by this embodiment includes:
步骤201、获取待评价对象的历史评价数据。Step 201: Obtain historical evaluation data of the object to be evaluated.
步骤202、提取历史评价数据的评价关键词。
步骤203、根据评价关键词以及预设神经网络模型生成评价关键词对应的评价数据。Step 203: Generate evaluation data corresponding to the evaluation keywords according to the evaluation keywords and the preset neural network model.
步骤204、在待评价对象的评价页面中的第一预设位置展示商品评价数据。Step 204: Display the product evaluation data at a first preset position in the evaluation page of the object to be evaluated.
值得说明的，本实施例中的步骤201-204的具体实现方式参照图2所示实施例中步骤101-104的描述，这里不再赘述。It should be noted that for the specific implementation of steps 201-204 in this embodiment, reference is made to the description of steps 101-104 in the embodiment shown in FIG. 2, and details are not repeated here.
步骤205、获取针对第一评价数据输入的第一评价指令。Step 205: Obtain a first evaluation instruction input for the first evaluation data.
在待评价商品的评价页面中的第一预设位置展示商品评价数据之后，为了更加方便用户进行商品评价，尤其是为了提高上述第一类用户的进行评价价的频率，以及提高第三类用户的评价数据的可信度。除了在传统的文字、图片或者视频的评价的基础上，还可以获取针对第一商品评价数据输入的第一评价指令。继续参照图3，则可以是通过“赞”或者“踩”的方式对待评价商品进行简单快速的评价，则不仅能简化用户个人的评价流程，还可以对商品整体的品质作出有效的评价。值得理解的，在本实施例中，第一评价指令即可以为用户“赞”或者“踩”的评价输入。After the product evaluation data is displayed in the first preset position on the evaluation page of the product to be evaluated, in order to make it more convenient for users to evaluate the product, especially to increase the frequency of evaluating the first type of users, and to increase the frequency of the third type of users. the reliability of the evaluation data. In addition to the evaluation based on the traditional text, picture or video, the first evaluation instruction input for the evaluation data of the first product can also be obtained. Continuing to refer to FIG. 3 , it is possible to simply and quickly evaluate the product to be evaluated by “like” or “dislike”, which not only simplifies the user's personal evaluation process, but also effectively evaluates the overall quality of the product. It should be understood that, in this embodiment, the first evaluation instruction may be an evaluation input of "like" or "dislike" by the user.
步骤206、在待评价对象的评价区域中的第二预设位置展示第一评价指令所对应的第一子评价。Step 206: Display the first sub-evaluation corresponding to the first evaluation instruction at a second preset position in the evaluation area of the object to be evaluated.
图5是图4所示实施例中的一种可能的商品评价界面示意图。如图5所示，通过本实施例提供的数据生成方法在对待评价商品进行评价时，即可以对核心评价进行简单的“赞”或者“踩”的操作，还可以输入具体的评价，对待评价对象进行更多维度以及详细的评价，有利于建立商品评价的可信度以及价值。FIG. 5 is a schematic diagram of a possible product evaluation interface in the embodiment shown in FIG. 4 . As shown in FIG. 5 , when evaluating the product to be evaluated by the data generation method provided in this embodiment, a simple “like” or “dislike” operation can be performed on the core evaluation, and a specific evaluation can also be input to evaluate the product to be evaluated. More dimensions and detailed evaluation of the object is conducive to establishing the credibility and value of the product evaluation.
并且，还可以在待评价商品的评价区域中的第二预设位置展示第一评价指令所对应的第一子评价，第一子评价用于评价第一商品评价数据，第二预设位置与第一预设位置在评价区域中相邻设置。In addition, the first sub-evaluation corresponding to the first evaluation instruction can also be displayed at the second preset position in the evaluation area of the product to be evaluated, the first sub-evaluation is used to evaluate the evaluation data of the first product, and the second preset position is the same as the The first preset positions are arranged adjacently in the evaluation area.
图6是本发明根据一示例实施例示出的预设神经网络模型训练过程示意图。如图6所示，上述任意实施例中，对于预设神经网络模型训练的过程，包括：FIG. 6 is a schematic diagram of a training process of a preset neural network model according to an exemplary embodiment of the present invention. As shown in FIG. 6 , in any of the above-mentioned embodiments, the training process of the preset neural network model includes:
步骤301、获取待评价对象的历史评价数据。Step 301: Obtain historical evaluation data of the object to be evaluated.
可以通过信息获取接口获取待评价商品的历史评价数据，其中，还可以对历史评价数据汇总为多个评价数据集合。The historical evaluation data of the commodity to be evaluated can be acquired through the information acquisition interface, and the historical evaluation data can also be aggregated into multiple evaluation data sets.
步骤302、对历史评价数据进行预处理。
在获取待评价商品的历史评价数据之后，还可以对历史评价数据进行预处理，例如去除历史评价数据中的停用词以及标点符号。After acquiring the historical evaluation data of the commodity to be evaluated, the historical evaluation data may also be preprocessed, for example, to remove stop words and punctuation marks in the historical evaluation data.
步骤303、根据预设词库对历史评价数据进行分词处理。Step 303: Perform word segmentation processing on the historical evaluation data according to a preset word library.
然后，可以根据预设词库对历史评价数据进行分词处理，其中，预设词库可以为结巴分词库或者其他分词库，还可以是现有分词库的基础上添加自定义词典的扩展分词库。Then, word segmentation processing can be performed on the historical evaluation data according to a preset thesaurus, wherein the preset thesaurus can be a stuttering word segmentation database or other word segmentation databases, or it can be a custom dictionary added on the basis of the existing word segmentation database. Expand the lexicon.
步骤304、提取历史评价数据的评价关键词。Step 304: Extract the evaluation keywords of the historical evaluation data.
步骤305、对评价关键词进行向量化。
可以根据预设关键词权重算法，例如TF-IDF算法计算分词集合中每个分词的权重值，并选取权重值大于预设权重值的分词作为历史评价数据的评价关键词。并在确定评价关键词之后，对其进行向量化处理。其中，向量化的方式可以为借助Word2vec，具体的，Word2vec，是一群用来产生词向量的相关模型。这些模型为浅而双层的神经网络，用来训练以重新建构语言学之词文本。网络以词表现，并且需猜测相邻位置的输入词，在word2vec中词袋模型假设下，词的顺序是不重要的。训练完成之后，word2vec模型可用来映射每个词到一个向量，可用来表示词对词之间的关系，该向量为神经网络之隐藏层。The weight value of each word segment in the word segment set can be calculated according to a preset keyword weight algorithm, such as the TF-IDF algorithm, and a word segment with a weight value greater than the preset weight value is selected as the evaluation keyword of the historical evaluation data. And after the evaluation keywords are determined, they are vectorized. Among them, the way of vectorization can be with the help of Word2vec, specifically, Word2vec is a group of related models used to generate word vectors. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic word texts. The network is represented by words and needs to guess the input words in adjacent positions. Under the assumption of the bag-of-words model in word2vec, the order of words is not important. After the training is completed, the word2vec model can be used to map each word to a vector, which can be used to represent the relationship between words and words, which is the hidden layer of the neural network.
步骤306、对分词集合中的各个分词进行向量化。Step 306: Vectorize each word segment in the word segment set.
此外，还可以对分词集合中的各个分词进行向量化，具体向量化方式同样可以是借助Word2vec。In addition, each word segment in the word segment set can also be vectorized, and the specific vectorization method can also use Word2vec.
步骤307、得到向量化后的数据矩阵。Step 307: Obtain a vectorized data matrix.
在对评价关键词进行向量化以及对分词集合中的各个分词进行向量化之后，将向量化后的数据构建为数据矩阵。After vectorizing the evaluation keywords and vectorizing each segment in the segment set, the vectorized data is constructed as a data matrix.
步骤308、输入至长短期记忆网络模型进行训练。
将构建出的数据矩阵输入至长短期记忆网络模型进行训练。Input the constructed data matrix into the long short-term memory network model for training.
图7是本发明根据一示例实施例示出的数据生成装置的结构示意图。如图7所示，本实施例提供的数据生成装置，包括：FIG. 7 is a schematic structural diagram of a data generating apparatus according to an exemplary embodiment of the present invention. As shown in Figure 7, the data generation device provided by this embodiment includes:
获取模块401，用于获取待评价对象的历史评价数据；an
提取模块402，用于提取所述历史评价数据的评价关键词，所述评价关键词用于表征所述待评价对象的物理特性；An
处理模块403，用于根据所述评价关键词以及预设神经网络模型生成所述评价关键词对应的评价数据；A
显示模块404，用于在所述待评价对象的评价区域中的第一预设位置展示所述评价数据，以对所述待评价对象进行评价。The
在一种可能的设计中，所述获取模块401，还用于获取针对第一评价数据输入的第一评价指令，所述评价数据包括所述第一评价数据；In a possible design, the obtaining
所述显示模块404，还用于在所述待评价对象的评价区域中的第二预设位置展示所述第一评价指令所对应的第一子评价，所述第一子评价用于评价所述第一评价数据，所述第二预设位置与所述第一预设位置在所述评价区域中相邻设置。The
在一种可能的设计中，所述提取模块402，具体用于：In a possible design, the
根据预设词库对所述历史评价数据进行分词处理，以获取分词集合；Perform word segmentation processing on the historical evaluation data according to a preset thesaurus to obtain a word segmentation set;
根据预设关键词权重算法计算所述分词集合中每个分词的权重值；Calculate the weight value of each word segment in the word segment set according to the preset keyword weight algorithm;
选取所述权重值大于预设权重值的分词作为所述历史评价数据的第一评价关键词，所述评价关键词包括所述第一评价关键词。The word segmentation with the weight value greater than the preset weight value is selected as the first evaluation keyword of the historical evaluation data, and the evaluation keyword includes the first evaluation keyword.
在一种可能的设计中，所述获取模块401，具体用于：In a possible design, the obtaining
当所述待评价对象对应的评价的条目数量大于预设条目数量阈值时，获取当前的所述商品评价作为所述待评价对象对应的所述历史评价数据。When the number of evaluation items corresponding to the to-be-evaluated object is greater than a preset number of entries threshold, the current product evaluation is acquired as the historical evaluation data corresponding to the to-be-evaluated object.
在一种可能的设计中，所述处理模块403，还用于对所述历史评价数据进行预处理，所述预处理包括：去除所述历史评价数据中的停用词以及标点符号。In a possible design, the
在一种可能的设计中，所述提取模块402，具体用于：In a possible design, the
当所述待评价对象对应的评价条目小于或者等于所述预设条目阈值时，获取所述待评价对象对应的三级类目对应的评价关键词作为第二评价关键词，所述评价关键词包括所述第二评价关键词。When the evaluation item corresponding to the object to be evaluated is less than or equal to the preset item threshold, the evaluation keyword corresponding to the third-level category corresponding to the object to be evaluated is obtained as a second evaluation keyword, and the evaluation keyword The second evaluation keyword is included.
在一种可能的设计中，所述处理模块403，具体用于：In a possible design, the
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第一评价数据；generating first evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
根据所述第一评价关键词以及预设神经网络模型生成所述待评价对象对应的第二评价数据；generating second evaluation data corresponding to the object to be evaluated according to the first evaluation keyword and a preset neural network model;
其中，所述评价数据包括所述第一评价数据以及所述第二评价数据。The evaluation data includes the first evaluation data and the second evaluation data.
在图7所示实施例的基础上，图8是本发明根据另一示例实施例示出的数据生成装置的结构示意图。如图8所示，本实施例提供的数据生成装置，还包括：On the basis of the embodiment shown in FIG. 7 , FIG. 8 is a schematic structural diagram of a data generating apparatus according to another exemplary embodiment of the present invention. As shown in FIG. 8 , the data generating apparatus provided by this embodiment further includes:
训练模块405，用于根据所述评价关键词以及所述历史评价数据对所述预设神经网络模型进行训练，所述预设神经网络模型为长短期记忆网络模型。The
在一种可能的设计中，所述训练模块405，具体用于：In a possible design, the
对所述评价关键词以及所述分词集合中的各个分词进行向量化，并将向量化后的数据矩阵作为训练数据输入对所述长短期记忆网络模型进行训练。The evaluation keyword and each word segment in the word segment set are vectorized, and the vectorized data matrix is input as training data to train the long short-term memory network model.
以上处理模块403可以被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(Application Specific Integrated Circuit，简称ASIC)，或，一个或多个微处理器(digital singnal processor，简称DSP)，或，一个或者多个现场可编程门阵列(Field Programmable Gate Array，简称FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(CentralProcessing Unit，简称CPU)或其它可以调用程序代码的处理器。再如，这些模块可以集成在一起，以片上系统(system-on-a-chip，简称SOC)的形式实现。The
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。值得说明地，图7-图8所示实施例提供的数据生成装置，可用于执行上述任一方法实施例提供的数据生成方法，具体实现方式和技术效果类似，这里不再赘述。In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software functional units. It is worth noting that the data generating apparatus provided by the embodiments shown in FIG. 7 to FIG. 8 can be used to execute the data generating method provided by any of the above method embodiments, and the specific implementation manner and technical effect are similar, and are not repeated here.
图9是本发明根据一示例实施例示出的电子设备的结构示意图。如图9所示，本实施例提供的一种电子设备500，包括：FIG. 9 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention. As shown in FIG. 9 , an electronic device 500 provided in this embodiment includes:
处理器501；以及，
存储器502，用于存储所述处理器的可执行指令，该存储器还可以是flash(闪存)；a
其中，所述处理器501配置为经由执行所述可执行指令来执行上述方法中的各个步骤。具体可以参见前面方法实施例中的相关描述。Wherein, the
可选地，存储器502既可以是独立的，也可以跟处理器501集成在一起。Optionally, the
当所述存储器502是独立于处理器501之外的器件时，所述电子设备还可以包括：When the
总线503，用于连接所述处理器501以及所述存储器502。The
本实施例还提供一种可读存储介质，可读存储介质中存储有计算机程序，当电子设备的至少一个处理器执行该计算机程序时，电子设备执行上述的各种实施方式提供的方法。This embodiment also provides a readable storage medium in which a computer program is stored. When at least one processor of the electronic device executes the computer program, the electronic device executes the methods provided by the above-mentioned various embodiments.
本实施例还提供一种程序产品，该程序产品包括计算机程序，该计算机程序存储在可读存储介质中。电子设备的至少一个处理器可以从可读存储介质读取该计算机程序，至少一个处理器执行该计算机程序使得电子设备实施上述的各种实施方式提供的方法。This embodiment also provides a program product, where the program product includes a computer program, and the computer program is stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to implement the methods provided by the various embodiments described above.
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或对其中部分或全部技术特征进行等同替换；而这些修改或替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. scope.
Claims (12)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910558488.2ACN111783445B (en) | 2019-06-26 | 2019-06-26 | Data generation method, device, medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910558488.2ACN111783445B (en) | 2019-06-26 | 2019-06-26 | Data generation method, device, medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111783445Atrue CN111783445A (en) | 2020-10-16 |
| CN111783445B CN111783445B (en) | 2025-05-23 |
Family
ID=72754896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910558488.2AActiveCN111783445B (en) | 2019-06-26 | 2019-06-26 | Data generation method, device, medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783445B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099899A (en)* | 2022-06-28 | 2022-09-23 | 平安银行股份有限公司 | Data processing method, device, electronic device and storage medium |
| WO2024245068A1 (en)* | 2023-05-31 | 2024-12-05 | 杭州阿里巴巴海外互联网产业有限公司 | Commodity review content processing method, and electronic device |
| CN119336812A (en)* | 2024-09-11 | 2025-01-21 | 中科链安(北京)科技有限公司 | A method and system for mining Ethereum address entity information |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870973A (en)* | 2012-12-13 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Information push and search method and apparatus based on electronic information keyword extraction |
| CN103996130A (en)* | 2014-04-29 | 2014-08-20 | 北京京东尚科信息技术有限公司 | Goods evaluation information filtering method and goods evaluation information filtering system |
| CN104731873A (en)* | 2015-03-05 | 2015-06-24 | 北京汇行科技有限公司 | Evaluation information generation method and device |
| CN104766224A (en)* | 2015-04-09 | 2015-07-08 | 网易传媒科技（北京）有限公司 | Shopping evaluation display method and system |
| CN104966204A (en)* | 2015-07-06 | 2015-10-07 | 无锡天脉聚源传媒科技有限公司 | Network shop generation method and apparatus |
| CN106919619A (en)* | 2015-12-28 | 2017-07-04 | 阿里巴巴集团控股有限公司 | A kind of commercial articles clustering method, device and electronic equipment |
| CN107807942A (en)* | 2016-09-09 | 2018-03-16 | 腾讯科技（深圳）有限公司 | Comment information presentation method and device |
| CN108256968A (en)* | 2018-01-12 | 2018-07-06 | 湖南大学 | A kind of electric business platform commodity comment of experts generation method |
| CN108932335A (en)* | 2018-07-10 | 2018-12-04 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus generating official documents and correspondence |
| CN109101553A (en)* | 2018-07-11 | 2018-12-28 | 政采云有限公司 | The buying user's evaluation method and system of industry for the non-benefited party of purchaser |
| CN109271520A (en)* | 2018-10-25 | 2019-01-25 | 北京小度信息科技有限公司 | Data extraction method, data extraction device, storage medium and electronic equipment |
- 2019
- 2019-06-26CNCN201910558488.2Apatent/CN111783445B/enactiveActive
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870973A (en)* | 2012-12-13 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Information push and search method and apparatus based on electronic information keyword extraction |
| CN103996130A (en)* | 2014-04-29 | 2014-08-20 | 北京京东尚科信息技术有限公司 | Goods evaluation information filtering method and goods evaluation information filtering system |
| CN104731873A (en)* | 2015-03-05 | 2015-06-24 | 北京汇行科技有限公司 | Evaluation information generation method and device |
| CN104766224A (en)* | 2015-04-09 | 2015-07-08 | 网易传媒科技（北京）有限公司 | Shopping evaluation display method and system |
| CN104966204A (en)* | 2015-07-06 | 2015-10-07 | 无锡天脉聚源传媒科技有限公司 | Network shop generation method and apparatus |
| CN106919619A (en)* | 2015-12-28 | 2017-07-04 | 阿里巴巴集团控股有限公司 | A kind of commercial articles clustering method, device and electronic equipment |
| CN107807942A (en)* | 2016-09-09 | 2018-03-16 | 腾讯科技（深圳）有限公司 | Comment information presentation method and device |
| CN108256968A (en)* | 2018-01-12 | 2018-07-06 | 湖南大学 | A kind of electric business platform commodity comment of experts generation method |
| CN108932335A (en)* | 2018-07-10 | 2018-12-04 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus generating official documents and correspondence |
| CN109101553A (en)* | 2018-07-11 | 2018-12-28 | 政采云有限公司 | The buying user's evaluation method and system of industry for the non-benefited party of purchaser |
| CN109271520A (en)* | 2018-10-25 | 2019-01-25 | 北京小度信息科技有限公司 | Data extraction method, data extraction device, storage medium and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099899A (en)* | 2022-06-28 | 2022-09-23 | 平安银行股份有限公司 | Data processing method, device, electronic device and storage medium |
| WO2024245068A1 (en)* | 2023-05-31 | 2024-12-05 | 杭州阿里巴巴海外互联网产业有限公司 | Commodity review content processing method, and electronic device |
| CN119336812A (en)* | 2024-09-11 | 2025-01-21 | 中科链安(北京)科技有限公司 | A method and system for mining Ethereum address entity information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111783445B (en) | 2025-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784455B (en) | Article recommendation method and recommendation equipment | |
| CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
| CN110427560B (en) | Model training method applied to recommendation system and related device | |
| CN107357793B (en) | Information recommendation method and device | |
| CN108536852A (en) | Question and answer exchange method and device, computer equipment and computer readable storage medium | |
| CN113268656A (en) | User recommendation method and device, electronic equipment and computer storage medium | |
| CN114819967B (en) | Data processing method, device, electronic device and computer readable storage medium | |
| CN108845986A (en) | A kind of sentiment analysis method, equipment and system, computer readable storage medium | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| JP2019164706A (en) | Information processing device, information processing method, and program | |
| Lin et al. | A consumer review-driven recommender service for web e-commerce | |
| CN111783445A (en) | Data generation method, device, medium and electronic device | |
| CN118350894A (en) | Commodity recommendation method and device and electronic equipment | |
| CN112507241A (en) | Vehicle type recommendation method, system, medium and electronic device for obtaining vehicle type recommendation list | |
| CN112184250B (en) | Method and device for generating retrieval page, storage medium and computer equipment | |
| US20210056149A1 (en) | Search system, search method, and program | |
| CN105931055A (en) | Service provider feature modeling method for crowdsourcing platform | |
| CN112288510A (en) | Item recommendation method, device, equipment and storage medium | |
| JP6865706B2 (en) | Information processing equipment, information processing methods, and information processing programs | |
| Jayasinghe et al. | Detecting deception: Employing deep neural networks for fraudulent review detection on amazon | |
| CN112328918B (en) | Commodity sorting method, computing device and computer-readable storage medium | |
| CN113722487A (en) | User emotion analysis method, device and equipment and storage medium | |
| CN116860969A (en) | A customer review analysis method, system, equipment and medium | |
| US20140067595A1 (en) | Determining giftability of a product | |
| CN115511582A (en) | Artificial intelligence based Commodity recommendation system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |