CN115063237A - Credit card recommendation method, device, electronic device and storage medium - Google Patents
Credit card recommendation method, device, electronic device and storage mediumDownload PDFInfo
- Publication number
- CN115063237A CN115063237ACN202210852354.3ACN202210852354ACN115063237ACN 115063237 ACN115063237 ACN 115063237ACN 202210852354 ACN202210852354 ACN 202210852354ACN 115063237 ACN115063237 ACN 115063237A
- Authority
- CN
- China
- Prior art keywords
- information
- credit card
- target
- user
- comment
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本申请涉及信用卡推荐技术领域，具体涉及一种信用卡推荐方法、装置、电子设备及存储介质。The present application relates to the technical field of credit card recommendation, and in particular, to a method, device, electronic device and storage medium for credit card recommendation.
背景技术Background technique
信用卡是由信用卡公司对信用合格的消费者发行的信用证明，可以用于透支等形式的提前消费。为了匹配不同消费者的需求，信用卡公司设计了多种类型的信用卡，消费者可以根据自己的需要选择不同类型的信用卡进行开卡。然而，随着信用卡公司设计的信用卡类型增加，权益相似的信用卡越来越多，除了信用卡权益之外，消费者还需要详细了解每一种信用卡类型的评价，才能够从中选择理想的信用卡。A credit card is a credit certificate issued by a credit card company to a credit-qualified consumer, which can be used for early consumption in the form of overdraft. In order to match the needs of different consumers, credit card companies have designed various types of credit cards, and consumers can choose different types of credit cards to open cards according to their needs. However, as the types of credit cards designed by credit card companies increase, and there are more and more credit cards with similar benefits, consumers need to understand the evaluation of each credit card type in detail in addition to the credit card benefits before they can choose the ideal credit card.
目前的信用卡推荐方法需要用户基于自己的需求在搜索栏中进行搜索，以得到理想的信用卡类型，然而这种方式通常按照热度排序进行推荐，推荐信用卡的准确率不高。The current credit card recommendation method requires users to search in the search bar based on their own needs to obtain the ideal credit card type. However, this method is usually recommended by popularity, and the accuracy of recommending credit cards is not high.
发明内容SUMMARY OF THE INVENTION
本申请提供一种信用卡推荐方法、装置、电子设备及存储介质，旨在解决目前的信用卡推荐方法通常按照热度排序进行推荐，推荐信用卡的准确率不高的问题。The present application provides a credit card recommendation method, device, electronic device and storage medium, which aims to solve the problem that the current credit card recommendation method is usually recommended according to the ranking of popularity, and the accuracy of recommending credit cards is not high.
第一方面，本申请提供一种信用卡推荐方法，包括：In a first aspect, the present application provides a credit card recommendation method, including:
接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；Receive a credit card application instruction, and determine the target user corresponding to the credit card application instruction;
从预设的评论数据库中，查询得到所述目标用户的历史评论；From a preset comment database, query to obtain the historical comments of the target user;
通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；By using a preset emotion prediction model, the historical comments are predicted and processed to obtain emotional information corresponding to the historical comments, wherein the emotional information includes one of positive information, neutral information and negative information;
根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；According to the emotional information corresponding to the historical review, the historical review is screened to obtain a target review, wherein the emotional information corresponding to the target review is one of neutral information and negative information;
提取所述目标评论中的用户诉求信息；extracting user appeal information in the target comment;
将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；Matching the user appeal information with the rights and interests information corresponding to the preset candidate credit cards to obtain a first similarity between the user appeal information and the rights and interests information;
根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。According to the first similarity between the user appeal information and the rights and interests information, determine the target rights and interests information and the target credit card corresponding to the target rights and interests information, and recommend the target credit card to the source terminal of the credit card application instruction .
在本申请的一种可能的实现方式中，所述根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述目标用户的目标终端，包括：In a possible implementation manner of the present application, the target benefit information and the target credit card corresponding to the target benefit information are determined according to the first similarity between the user appeal information and the benefit information, and the The target credit card is recommended to the target terminal of the target user, including:
获取所述目标用户的用户属性信息，其中，所述用户属性信息包括年龄、性别和收入中的至少一者；obtaining user attribute information of the target user, wherein the user attribute information includes at least one of age, gender and income;
根据所述用户属性信息对应的修正值，对初始的相似度阈值进行修正，得到预设的第一相似度阈值；modifying the initial similarity threshold according to the correction value corresponding to the user attribute information to obtain a preset first similarity threshold;
将所述用户诉求信息与所述权益信息之间的第一相似度与所述第一相似度阈值进行对比，得到相似度大于所述第一相似度阈值的目标权益信息；Comparing the first similarity between the user appeal information and the equity information with the first similarity threshold to obtain target equity information with a similarity greater than the first similarity threshold;
将所述目标权益信息对应的候选信用卡作为目标信用卡，将所述目标信用卡推荐至目标用户的目标终端。The candidate credit card corresponding to the target rights and interests information is used as the target credit card, and the target credit card is recommended to the target terminal of the target user.
在本申请的一种可能的实现方式中，所述将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度之前，所述方法还包括：In a possible implementation manner of the present application, the user's appeal information is matched with the rights and interests information corresponding to the preset candidate credit cards to obtain the first similarity between the user's appeal information and the rights and interests information. Before the degree, the method further includes:
获取初始信用卡，以及所述初始信用卡对应的权益信息；Obtain an initial credit card and the rights and interests information corresponding to the initial credit card;
根据所述权益信息中的权益种类，对所述初始信用卡进行分类，得到多个信用卡集合；Classifying the initial credit card according to the rights and interests types in the rights and interests information to obtain a plurality of credit card sets;
获取每一个信用卡集合中信用卡评分最高的信用卡，将得到的信用卡作为候选信用卡。Obtain the credit card with the highest credit card score in each credit card collection, and use the obtained credit card as the candidate credit card.
在本申请的一种可能的实现方式中，所述提取所述目标评论中的用户诉求信息，包括：In a possible implementation manner of the present application, the extracting user appeal information in the target comment includes:
对所述目标评论进行分词处理，得到所述目标评论对应的候选词语；Perform word segmentation processing on the target comment to obtain candidate words corresponding to the target comment;
统计所述目标评论中所述候选词语的出现次数，得到出现次数大于预设的次数阈值的目标词语；Count the number of occurrences of the candidate words in the target comment, and obtain the target words whose number of occurrences is greater than a preset number of thresholds;
将所述目标词语的信息设定为所述目标评论中的用户诉求信息。The information of the target word is set as the user appeal information in the target comment.
在本申请的一种可能的实现方式中，所述从预设的评论数据库中，查询得到所述目标用户的历史评论，包括：In a possible implementation manner of the present application, the historical comments of the target user are obtained by querying from a preset comment database, including:
获取预设的评论数据库中所述目标用户的用户评论；Obtain the user comments of the target user in the preset comment database;
将所述用户评论与预设的默认评论进行对比，得到所述用户评论与所述默认评论之间的第二相似度；Comparing the user comment with a preset default comment to obtain a second similarity between the user comment and the default comment;
将第二相似度小于预设的第二相似度阈值的用户评论设定为所述目标用户的历史评论。User comments whose second similarity is less than a preset second similarity threshold are set as the historical comments of the target user.
在本申请的一种可能的实现方式中，所述从预设的评论数据库中，查询得到所述目标用户的历史评论之前，所述方法还包括：In a possible implementation manner of the present application, before the historical comments of the target user are obtained by querying from a preset comment database, the method further includes:
获取所述目标用户对应的历史推荐次数，以及所述目标用户对应的历史推荐信用卡；Obtaining the historical recommendation times corresponding to the target user, and the historically recommended credit card corresponding to the target user;
若所述历史推荐次数小于预设的次数阈值，或者所述目标用户持有的信用卡中包含所述历史推荐信用卡，则执行所述从预设的评论数据库中，查询得到所述目标用户的历史评论的步骤。If the number of historical recommendations is less than a preset number of times threshold, or the credit cards held by the target user include the historically recommended credit cards, execute the query to obtain the history of the target user from the preset comment database Steps to comment.
在本申请的一种可能的实现方式中，所述通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息之前，所述方法还包括：In a possible implementation manner of the present application, before performing prediction processing on the historical comments by using a preset emotion prediction model to obtain emotional information corresponding to the historical comments, the method further includes:
获取样本数据集，其中，所述样本数据集包括样本评论和所述样本评论对应的标签信息；obtaining a sample data set, wherein the sample data set includes sample comments and label information corresponding to the sample comments;
通过初始的情感预测模型，对所述样本评论进行预测处理，得到所述样本评论对应的情感信息；Performing prediction processing on the sample comments through an initial emotion prediction model to obtain emotional information corresponding to the sample comments;
根据所述标签信息和所述情感信息，对所述初始的情感预测模型中的参数进行调整，得到预设的情感预测模型。According to the label information and the emotion information, the parameters in the initial emotion prediction model are adjusted to obtain a preset emotion prediction model.
第二方面，本申请提供一种信用卡推荐装置，包括：In a second aspect, the present application provides a credit card recommendation device, including:
接收单元，用于接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；a receiving unit, configured to receive a credit card application instruction, and determine a target user corresponding to the credit card application instruction;
查询单元，用于从预设的评论数据库中，查询得到所述目标用户的历史评论；a query unit, configured to query and obtain the historical comments of the target user from a preset comment database;
预测单元，用于通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；A prediction unit, configured to perform prediction processing on the historical comments through a preset emotional prediction model, and obtain emotional information corresponding to the historical comments, wherein the emotional information includes one of positive information, neutral information and negative information ;
筛选单元，用于根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；a screening unit, configured to screen the historical comments according to the emotional information corresponding to the historical comments to obtain a target comment, wherein the emotional information corresponding to the target comment is one of neutral information and negative information;
提取单元，用于提取所述目标评论中的用户诉求信息；an extraction unit, used for extracting user appeal information in the target comment;
匹配单元，用于将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；a matching unit, configured to match the user appeal information with the rights and interests information corresponding to preset candidate credit cards to obtain a first similarity between the user appeal information and the rights and interests information;
确定单元，用于根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。a determining unit, configured to determine target rights and interests information and a target credit card corresponding to the target rights and interests information according to the first similarity between the user appeal information and the rights and interests information, and recommend the target credit card to the credit card The source terminal of the application command.
在本申请的一种可能的实现方式中，确定单元还用于：In a possible implementation manner of the present application, the determining unit is further used for:
获取所述目标用户的用户属性信息，其中，所述用户属性信息包括年龄、性别和收入中的至少一者；obtaining user attribute information of the target user, wherein the user attribute information includes at least one of age, gender and income;
根据所述用户属性信息对应的修正值，对初始的相似度阈值进行修正，得到预设的第一相似度阈值；modifying the initial similarity threshold according to the correction value corresponding to the user attribute information to obtain a preset first similarity threshold;
将所述用户诉求信息与所述权益信息之间的第一相似度与所述第一相似度阈值进行对比，得到相似度大于所述第一相似度阈值的目标权益信息；Comparing the first similarity between the user appeal information and the equity information with the first similarity threshold to obtain target equity information with a similarity greater than the first similarity threshold;
将所述目标权益信息对应的候选信用卡作为目标信用卡，将所述目标信用卡推荐至目标用户的目标终端。The candidate credit card corresponding to the target rights and interests information is used as the target credit card, and the target credit card is recommended to the target terminal of the target user.
在本申请的一种可能的实现方式中，匹配单元还用于：In a possible implementation manner of the present application, the matching unit is also used for:
获取初始信用卡，以及所述初始信用卡对应的权益信息；Obtain an initial credit card and the rights and interests information corresponding to the initial credit card;
根据所述权益信息中的权益种类，对所述初始信用卡进行分类，得到多个信用卡集合；Classifying the initial credit card according to the rights and interests types in the rights and interests information to obtain a plurality of credit card sets;
获取每一个信用卡集合中信用卡评分最高的信用卡，将得到的信用卡作为候选信用卡。Obtain the credit card with the highest credit card score in each credit card collection, and use the obtained credit card as the candidate credit card.
在本申请的一种可能的实现方式中，提取单元还用于：In a possible implementation manner of the present application, the extraction unit is also used for:
对所述目标评论进行分词处理，得到所述目标评论对应的候选词语；Perform word segmentation processing on the target comment to obtain candidate words corresponding to the target comment;
统计所述目标评论中所述候选词语的出现次数，得到出现次数大于预设的次数阈值的目标词语；Count the number of occurrences of the candidate words in the target comment, and obtain the target words whose number of occurrences is greater than a preset number of thresholds;
将所述目标词语的信息设定为所述目标评论中的用户诉求信息。The information of the target word is set as the user appeal information in the target comment.
在本申请的一种可能的实现方式中，查询单元还用于：In a possible implementation manner of the present application, the query unit is also used for:
获取预设的评论数据库中所述目标用户的用户评论；Obtain the user comments of the target user in the preset comment database;
将所述用户评论与预设的默认评论进行对比，得到所述用户评论与所述默认评论之间的第二相似度；Comparing the user comment with a preset default comment to obtain a second similarity between the user comment and the default comment;
将第二相似度小于预设的第二相似度阈值的用户评论设定为所述目标用户的历史评论。User comments whose second similarity is less than a preset second similarity threshold are set as the historical comments of the target user.
在本申请的一种可能的实现方式中，查询单元还用于：In a possible implementation manner of the present application, the query unit is also used for:
获取所述目标用户对应的历史推荐次数，以及所述目标用户对应的历史推荐信用卡；Obtaining the historical recommendation times corresponding to the target user, and the historically recommended credit card corresponding to the target user;
若所述历史推荐次数小于预设的次数阈值，或者所述目标用户持有的信用卡中包含所述历史推荐信用卡，则执行所述从预设的评论数据库中，查询得到所述目标用户的历史评论的步骤。If the number of historical recommendations is less than a preset number of times threshold, or the credit cards held by the target user include the historically recommended credit cards, execute the query to obtain the history of the target user from the preset comment database Steps to comment.
在本申请的一种可能的实现方式中，预测单元还用于：In a possible implementation manner of the present application, the prediction unit is also used for:
获取样本数据集，其中，所述样本数据集包括样本评论和所述样本评论对应的标签信息；obtaining a sample data set, wherein the sample data set includes sample comments and label information corresponding to the sample comments;
通过初始的情感预测模型，对所述样本评论进行预测处理，得到所述样本评论对应的情感信息；Performing prediction processing on the sample comments through an initial emotion prediction model to obtain emotional information corresponding to the sample comments;
根据所述标签信息和所述情感信息，对所述初始的情感预测模型中的参数进行调整，得到预设的情感预测模型。According to the label information and the emotion information, the parameters in the initial emotion prediction model are adjusted to obtain a preset emotion prediction model.
第三方面，本申请还提供一种电子设备，电子设备包括处理器、存储器以及存储于存储器中并可在处理器上运行的计算机程序，处理器调用存储器中的计算机程序时执行本申请提供的任一种信用卡推荐方法中的步骤。In a third aspect, the present application also provides an electronic device, the electronic device includes a processor, a memory, and a computer program stored in the memory and running on the processor, and the processor executes the computer program provided by the present application when the processor calls the computer program in the memory Steps in any of the credit card recommendation methods.
第四方面，本申请还提供一种存储介质，存储介质上存储有计算机程序，计算机程序被处理器执行时实现本申请提供的任一种信用卡推荐方法中的步骤。In a fourth aspect, the present application further provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps in any of the credit card recommendation methods provided by the present application are implemented.
综上所述，本申请实施例提供的信用卡推荐方法，包括：接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；从预设的评论数据库中，查询得到所述目标用户的历史评论；通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；提取所述目标评论中的用户诉求信息；将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。To sum up, the credit card recommendation method provided by the embodiment of the present application includes: receiving a credit card application instruction, determining a target user corresponding to the credit card application instruction; querying and obtaining historical comments of the target user from a preset comment database ; Carry out prediction processing on the historical comments through a preset emotional prediction model to obtain emotional information corresponding to the historical comments, wherein the emotional information includes one of positive information, neutral information and negative information; according to the The emotional information corresponding to the historical comments is screened to obtain the target comments, wherein the emotional information corresponding to the target comments is one of neutral information and negative information; extract the user demands in the target comments information; match the user's appeal information with the rights and interests information corresponding to the preset candidate credit cards to obtain the first similarity between the user's appeal information and the rights and interests information; according to the user's appeal information and the rights and interests The first similarity between the information is used to determine the target rights information and the target credit card corresponding to the target rights information, and recommend the target credit card to the source terminal of the credit card application instruction.
一方面，本申请实施例提供的信用卡推荐方法可以根据目标用户的评论确定目标用户的诉求，然后根据目标用户的诉求，确定待推荐的目标信用卡，因此在推荐信用卡时更加具有针对性，匹配了用户痛点，提高了信用卡推荐的准确性，并且，还可以自动化地对信用卡进行推荐，提高了信用卡的推荐效率。另一方面，在确定目标用户的诉求时，根据评论对应的情感信息进行了筛选，将其中情感积极的评论筛除，既减少了评论数量，进而减少了信用卡推荐时所需要的计算量和计算时间，又保留了其中包含用户诉求信息的目标评论，提高了信用卡推荐的准确性。On the one hand, the credit card recommendation method provided by the embodiment of the present application can determine the appeal of the target user according to the comments of the target user, and then determine the target credit card to be recommended according to the appeal of the target user. User pain points, improve the accuracy of credit card recommendation, and can also automatically recommend credit cards, improving the efficiency of credit card recommendation. On the other hand, when determining the appeal of the target user, it is screened according to the emotional information corresponding to the comments, and the comments with positive emotions are screened out, which not only reduces the number of comments, but also reduces the amount of calculation and calculation required for credit card recommendation. Time, but also retains the target comments containing the user's appeal information, which improves the accuracy of credit card recommendation.
附图说明Description of drawings
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.
图1是本申请实施例提供的信用卡推荐方法的应用场景示意图；1 is a schematic diagram of an application scenario of a credit card recommendation method provided by an embodiment of the present application;
图2是本申请实施例中提供的信用卡推荐方法的一种流程示意图；2 is a schematic flowchart of a credit card recommendation method provided in an embodiment of the present application;
图3是本申请实施例中提供的获取候选信用卡的一种流程示意图；FIG. 3 is a schematic flowchart of obtaining a candidate credit card provided in an embodiment of the present application;
图4是本申请实施例中提供的信用卡推荐方法的又一种流程示意图；FIG. 4 is another schematic flowchart of the credit card recommendation method provided in the embodiment of the present application;
图5是本申请实施例中提供的信用卡推荐装置的一个实施例结构示意图；FIG. 5 is a schematic structural diagram of an embodiment of a credit card recommendation device provided in an embodiment of the present application;
图6是本申请实施例中提供的电子设备的一个实施例结构示意图。FIG. 6 is a schematic structural diagram of an embodiment of the electronic device provided in the embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域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，都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.
在本申请实施例的描述中，需要理解的是，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个所述特征。在本申请实施例的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are only used for description purposes, and should not be interpreted as indicating or implying relative importance or implicitly indicating the indicated technical features quantity. Thus, features defined as "first", "second" may expressly or implicitly include one or more of said features. In the description of the embodiments of the present application, "plurality" means two or more, unless otherwise expressly and specifically defined.
为了使本领域任何技术人员能够实现和使用本申请，给出了以下描述。在以下描述中，为了解释的目的而列出了细节。应当明白的是，本领域普通技术人员可以认识到，在不使用这些特定细节的情况下也可以实现本申请。在其它实例中，不会对公知的过程进行详细阐述，以避免不必要的细节使本申请实施例的描述变得晦涩。因此，本申请并非旨在限于所示的实施例，而是与符合本申请实施例所公开的原理和特征的最广范围相一致。The following description is presented to enable any person skilled in the art to make and use the present application. In the following description, details are set forth for the purpose of explanation. It is to be understood that one of ordinary skill in the art can realize that the present application may be practiced without the use of these specific details. In other instances, well-known procedures have not been described in detail in order to avoid obscuring the description of the embodiments of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and features disclosed in the embodiments of this application.
本申请实施例提供一种信用卡推荐方法、装置、电子设备和存储介质。其中，该信用卡推荐装置可以集成在电子设备中，该电子设备可以是服务器，也可以是终端等设备。Embodiments of the present application provide a credit card recommendation method, device, electronic device, and storage medium. Wherein, the credit card recommending device may be integrated in an electronic device, and the electronic device may be a server or a terminal or other device.
本申请实施例信用卡推荐方法的执行主体可以为本申请实施例提供的信用卡推荐装置，或者集成了该信用卡推荐装置的服务器设备、物理主机或者对象设备(UserEquipment，UE)等不同类型的电子设备，其中，信用卡推荐装置可以采用硬件或者软件的方式实现，UE具体可以为智能手机、平板电脑、笔记本电脑、掌上电脑、台式电脑或者个人数字助理(Personal Digital Assistant，PDA)等终端设备。The execution body of the credit card recommendation method in the embodiment of the present application may be the credit card recommendation device provided in the embodiment of the present application, or different types of electronic devices such as a server device, a physical host, or an object device (UserEquipment, UE) integrated with the credit card recommendation device, The credit card recommendation device may be implemented in hardware or software, and the UE may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a handheld computer, a desktop computer, or a Personal Digital Assistant (PDA).
该电子设备可以采用单独运行的工作方式，或者也可以采用设备集群的工作方式。The electronic device may work in a single operation mode, or may also work in a cluster of devices.
参见图1，图1是本申请实施例所提供的信用卡推荐系统的场景示意图。其中，该信用卡推荐系统可以包括电子设备101，电子设备101中集成有信用卡推荐装置。Referring to FIG. 1 , FIG. 1 is a schematic diagram of a scenario of a credit card recommendation system provided by an embodiment of the present application. Wherein, the credit card recommendation system may include an
另外，如图1所示，该信用卡推荐系统还可以包括存储器102，用于存储数据，如存储文本数据。In addition, as shown in FIG. 1 , the credit card recommendation system may further include a
需要说明的是，图1所示的信用卡推荐系统的场景示意图仅仅是一个示例，本申请实施例描述的信用卡推荐系统以及场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着信用卡推荐系统的演变和新业务场景的出现，本发明实施例提供的技术方案对于类似的技术问题，同样适用。It should be noted that the schematic diagram of the scene of the credit card recommendation system shown in FIG. 1 is only an example, and the credit card recommendation system and the scene described in the embodiments of the present application are for the purpose of illustrating the technical solutions of the embodiments of the present application more clearly, and do not constitute a For the limitations of the technical solutions provided in the embodiments of the present application, those of ordinary skill in the art know that with the evolution of the credit card recommendation system and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present invention are also applicable to similar technical problems.
下面，开始介绍本申请实施例提供的信用卡推荐方法，本申请实施例中以电子设备作为执行主体，为了简化与便于描述，后续方法实施例中将省略该执行主体，该信用卡推荐方法包括：接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；从预设的评论数据库中，查询得到所述目标用户的历史评论；通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；提取所述目标评论中的用户诉求信息；将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。Next, the credit card recommendation method provided by the embodiment of the present application will be introduced. In the embodiment of the present application, an electronic device is used as the execution body. For simplicity and convenience of description, the execution body will be omitted in the subsequent method embodiments. The credit card recommendation method includes: receiving The credit card application instruction is used to determine the target user corresponding to the credit card application instruction; the historical comments of the target user are obtained by querying from a preset comment database; the historical comments are predicted and processed through a preset emotion prediction model, Obtain emotional information corresponding to the historical comments, wherein the emotional information includes one of positive information, neutral information and negative information; screen the historical comments according to the emotional information corresponding to the historical comments to obtain a target comment , wherein the emotional information corresponding to the target comment is one of neutral information and negative information; extract the user appeal information in the target comment; compare the user appeal information with the rights and interests information corresponding to the preset candidate credit cards Carry out matching to obtain the first similarity between the user appeal information and the rights and interests information; according to the first similarity between the user appeal information and the rights and interests information, determine the target rights and interests information, and the target rights and interests information The target credit card corresponding to the entitlement information recommends the target credit card to the source terminal of the credit card application instruction.
参照图2，图2是本申请实施例提供的信用卡推荐方法的一种流程示意图。需要说明的是，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。该信用卡推荐方法具体可以包括以下步骤201-步骤205，其中：Referring to FIG. 2 , FIG. 2 is a schematic flowchart of a credit card recommendation method provided by an embodiment of the present application. It should be noted that although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be performed in an order different from that herein. The credit card recommendation method may specifically include the following steps 201-205, wherein:
201、接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户。201. Receive a credit card application instruction, and determine a target user corresponding to the credit card application instruction.
本申请实施例提供的信用卡推荐方法可以应用于金融领域。其中，信用卡申请指令可以是指用户申请新的信用卡时，通过银行软件发出的指令。例如，用户在通过智能手机、个人电脑等终端操作银行软件，点击“申请开卡”等用于申请新信用卡的虚拟按键时，相当于发出了信用卡申请指令。The credit card recommendation method provided by the embodiment of the present application can be applied to the financial field. The credit card application instruction may refer to an instruction sent by the bank software when the user applies for a new credit card. For example, when a user operates a banking software through a terminal such as a smartphone or a personal computer, and clicks a virtual button for applying for a new credit card, such as "apply for card issuance", it is equivalent to issuing a credit card application instruction.
通过信用卡申请指令携带的用户标识，电子设备可以得到对应的目标用户。例如，用户标识可以是指用户此时操作的终端的终端设备号，或者可以是用户采用的账户名等等。Through the user ID carried in the credit card application instruction, the electronic device can obtain the corresponding target user. For example, the user identification may refer to the terminal device number of the terminal operated by the user at this time, or may be the account name adopted by the user, or the like.
202、从预设的评论数据库中，查询得到所述目标用户的历史评论。202. Query to obtain historical comments of the target user from a preset comment database.
预设的评论数据库可以是指用于存储评论的数据库，在本申请实施例中，评论可以是指用户对于信用卡发布的评论。例如，可以将银行软件后台用于存储评论的数据库作为预设的评论数据库。The preset comment database may refer to a database for storing comments, and in this embodiment of the present application, the comments may refer to comments posted by users on credit cards. For example, the database used for storing comments in the backend of the banking software can be used as a preset comment database.
在执行步骤202时，电子设备可以根据目标用户对应的用户标识，从评论数据库中查询得到目标用户发布的历史评论。When
在一些实施例中，还可以通过一定的方法，将目标用户开卡后未及时进行评论，而由软件自行发送的默认评论删除，以减少历史评论的数量，并保留有使用价值的真实评论。此时，步骤“从预设的评论数据库中，查询得到所述目标用户的历史评论”，包括：In some embodiments, a certain method can also be used to delete the default comments sent by the software without commenting in time after the target user opens the card, so as to reduce the number of historical comments and retain valuable real comments. At this time, the step of "inquiring to obtain the historical comments of the target user from the preset comment database" includes:
(1.1)获取预设的评论数据库中所述目标用户的用户评论。(1.1) Obtain user comments of the target user in a preset comment database.
预设的评论数据库的说明可以参考上文，具体不进行赘述。For the description of the preset comment database, reference may be made to the above description, which will not be described in detail.
目标用户的用户评论可以是指预设的评论数据库中，目标用户发布的所有评论。The user comments of the target user may refer to all comments published by the target user in a preset comment database.
(1.2)将所述用户评论与预设的默认评论进行对比，得到所述用户评论与所述默认评论之间的第二相似度。(1.2) Comparing the user comment with a preset default comment to obtain a second similarity between the user comment and the default comment.
预设的默认评论是指用户开卡后未及时进行评论，而由软件自行发送的评论。The preset default comment refers to the comment sent by the software without timely comment after the user opens the card.
在进行对比时，电子设备可以将用户评论和预设的默认评论均通过word2vec等开源的语言处理模型，转换为词向量，然后对比两个词向量之间的相似度，得到第二相似度。When comparing, the electronic device can convert both user comments and preset default comments into word vectors through an open source language processing model such as word2vec, and then compare the similarity between the two word vectors to obtain the second similarity.
可以理解的，第二相似度越大，则说明用户评论与默认评论之间越相似，该用户评论是用户开卡后未及时进行评论，而由软件自行发送的评论的概率越大。It can be understood that the greater the second similarity, the more similar the user comment is to the default comment. The user comment is not commented in time after the user opens the card, and the probability of the comment sent by the software is greater.
(1.3)将第二相似度小于预设的第二相似度阈值的用户评论设定为所述目标用户的历史评论。(1.3) Set user comments whose second similarity is less than a preset second similarity threshold as the historical comments of the target user.
通过步骤(1.1)-步骤(1.3)的方法，可以有效去除默认评论，保留存在使用价值的评论，以减少后续的计算量。Through the method of step (1.1)-step (1.3), the default comment can be effectively removed, and the comment with use value can be retained, so as to reduce the amount of subsequent calculation.
203、通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者。203. Perform prediction processing on the historical comment by using a preset emotion prediction model to obtain emotional information corresponding to the historical comment, where the emotional information includes one of positive information, neutral information and negative information.
其中，预设的情感预测模型可以用于对文本中的情感信息进行预测。例如，可以将ABSA(Aspect Based Sentiment Analysis)等开源的模型作为初始的情感预测模型，对初始的情感预测模型进行训练后，得到预设的情感预测模型，通过预设的情感预测模型对历史评论中的情感信息进行预测，得到目标用户对于不同信用卡的态度。在本申请实施例中，情感信息包括积极信息、中性信息和消极信息中的一者，若输出的情感信息为积极信息，则说明目标用户对于该历史评论对应的信用卡持积极态度，该信用卡符合目标用户的使用需求。若输出的情感信息为中性信息或消极信息，则说明目标用户对于该历史评论对应的信用卡持中性态度或者消极态度，该信用卡不完全符合目标用户的使用需求。例如当情感信息为喜欢、赞扬等积极信息时，说明目标用户对于该历史评论对应的信用卡持积极态度，该信用卡符合目标用户的使用需求。当情感信息为冷淡、批评等中性信息或消极信息时，说明目标用户对于该历史评论对应的信用卡持中性态度或者消极态度，该信用卡不完全符合目标用户的使用需求。The preset emotion prediction model can be used to predict emotion information in the text. For example, an open source model such as ABSA (Aspect Based Sentiment Analysis) can be used as the initial sentiment prediction model. After training the initial sentiment prediction model, a preset sentiment prediction model can be obtained, and historical comments can be analyzed through the preset sentiment prediction model. Predict the emotional information in the target user's attitude towards different credit cards. In the embodiment of the present application, the emotional information includes one of positive information, neutral information and negative information. If the output emotional information is positive information, it means that the target user has a positive attitude towards the credit card corresponding to the historical comment. Meet the needs of target users. If the output emotional information is neutral or negative, it means that the target user has a neutral or negative attitude towards the credit card corresponding to the historical comment, and the credit card does not fully meet the target user's usage needs. For example, when the emotional information is positive information such as likes and praises, it means that the target user has a positive attitude towards the credit card corresponding to the historical comment, and the credit card meets the usage needs of the target user. When the emotional information is neutral information or negative information such as indifference and criticism, it means that the target user has a neutral or negative attitude towards the credit card corresponding to the historical comment, and the credit card does not fully meet the use needs of the target user.
其中，初始的情感预测模型可以通过以下方法进行训练：Among them, the initial sentiment prediction model can be trained by the following methods:
(2.1)获取样本数据集，其中，所述样本数据集包括样本评论和所述样本评论对应的标签信息。(2.1) Obtain a sample data set, wherein the sample data set includes sample reviews and label information corresponding to the sample reviews.
其中，样本评论同样可以从预设的评论数据库中抽取得到。样本评论对应的标签信息可以由人工标注后得到，可以理解的，标签信息同样为积极信息、中性信息和消极信息中的一者。The sample comments can also be extracted from a preset comment database. The label information corresponding to the sample comments can be obtained by manual labeling. It is understandable that the label information is also one of positive information, neutral information and negative information.
(2.2)通过初始的情感预测模型，对所述样本评论进行预测处理，得到所述样本评论对应的情感信息。(2.2) Perform prediction processing on the sample comments through an initial emotion prediction model to obtain emotional information corresponding to the sample comments.
(2.3)根据所述标签信息和所述情感信息，对所述初始的情感预测模型中的参数进行调整，得到预设的情感预测模型。(2.3) According to the label information and the emotion information, the parameters in the initial emotion prediction model are adjusted to obtain a preset emotion prediction model.
204、根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者。204. Screen the historical comments according to the emotional information corresponding to the historical comments to obtain a target comment, where the emotional information corresponding to the target comment is one of neutral information and negative information.
在一些实施例中，可以将历史评论中，对应的情感信息为积极信息的评论排除，将剩余的历史评论作为目标评论。In some embodiments, comments whose corresponding sentiment information is positive information in the historical comments may be excluded, and the remaining historical comments may be used as target comments.
筛选的目的是得到用户不完全满意时，发布的评论，进而可以从这些评论中，得出用户对信用卡不满意的原因，并根据这些原因推荐合适的信用卡。The purpose of screening is to get the comments released by users when they are not completely satisfied, and then from these comments, the reasons for users' dissatisfaction with credit cards can be obtained, and suitable credit cards can be recommended according to these reasons.
205、提取所述目标评论中的用户诉求信息。205. Extract the user appeal information in the target comment.
在一些实施例中，电子设备可以通过预设的语义识别模型，得到目标评论中的用户诉求信息。其中，可以采用开源的文本分类网络，作为初始的语义识别模型，然后通过样本数据对初始的语义识别模型进行训练后，得到预设的语义识别模型。可以理解的，此时，对于一条历史评论，提取得到的用户诉求信息为预设诉求信息中的一者。In some embodiments, the electronic device may obtain the user appeal information in the target comment through a preset semantic recognition model. Among them, an open source text classification network can be used as an initial semantic recognition model, and then a preset semantic recognition model is obtained after training the initial semantic recognition model through sample data. Understandably, at this time, for a historical comment, the user appeal information obtained by extraction is one of the preset appeal information.
在另一些实施例中，可以根据用户诉求信息中词语的出现次数，提取得到目标评论中的用户诉求信息。此时，步骤“提取所述目标评论中的用户诉求信息”，包括：In other embodiments, the user appeal information in the target comment may be extracted and obtained according to the number of occurrences of words in the user appeal information. At this time, the step "extract the user's appeal information in the target comment" includes:
(3.1)对所述目标评论进行分词处理，得到所述目标评论对应的候选词语。(3.1) Perform word segmentation on the target comment to obtain candidate words corresponding to the target comment.
示例性地，电子设备可以通过word2vec等开源的语言处理模型，对目标评论进行分词处理，得到目标评论对应的候选词语。例如，当目标评论为“这张信用卡的还款利息特别高，利息竟然要XX％”时，分词后得到的候选词语包括“这张”、“信用卡”、“还款”、“利息”、“特别”、“竟然”、“XX％”。Exemplarily, the electronic device may perform word segmentation processing on the target comment by using an open source language processing model such as word2vec to obtain candidate words corresponding to the target comment. For example, when the target comment is "The repayment interest of this credit card is very high, and the interest is XX%", the candidate words obtained after the segmentation include "this", "credit card", "repayment", "interest", "Special", "Unexpectedly", "XX%".
在一些实施例中，电子设备还可以对分词后得到的词语进行筛选，保留其中的名词，并将保留的名词作为候选词语。例如，可以将上述分词后的词语进行筛选，保留其中的名词“信用卡”、“利息”，并将“信用卡”、“利息”作为候选词语。In some embodiments, the electronic device may further screen the words obtained after the word segmentation, retain the nouns therein, and use the reserved nouns as candidate words. For example, the words after the above segmentation can be screened, the nouns "credit card" and "interest" can be retained, and "credit card" and "interest" can be used as candidate words.
(3.2)统计所述目标评论中所述候选词语的出现次数，得到出现次数大于预设的次数阈值的目标词语。(3.2) Count the number of occurrences of the candidate words in the target comment, and obtain the target words whose number of occurrences is greater than a preset number of times threshold.
其中，预设的次数阈值用于评估候选词语出现次数的大小，具体数值可以根据实际场景进行设置，例如，预设的次数阈值可以设置为1，即候选次数出现过至少2次，则将其作为目标词语。Among them, the preset number of times threshold is used to evaluate the size of the number of occurrences of the candidate words, and the specific value can be set according to the actual scene. For example, the preset number of times threshold can be set to 1, that is, the number of candidates has appeared at least 2 times, then it is set to as the target word.
例如，在步骤(3.1)的例子中，候选词语“利息”出现过2次，而候选词语“信用卡”出现过1次，因此将候选词语“利息”作为目标词语。For example, in the example of step (3.1), the candidate word "interest" appears twice, and the candidate word "credit card" appears once, so the candidate word "interest" is used as the target word.
获取目标词语的目的是为了获取目标用户发布评论的原因，候选词语的出现次数越多，说明该词语与发布评论原因相关的概率越高，因此将出现次数较多的候选词语作为目标词语。The purpose of obtaining the target word is to obtain the reason for the target user to post comments. The more occurrences of the candidate word, the higher the probability that the word is related to the reason for posting the comment. Therefore, the candidate word with more occurrences is used as the target word.
(3.3)将所述目标词语的信息设定为所述目标评论中的用户诉求信息。(3.3) The information of the target word is set as the user appeal information in the target comment.
得到目标词语后，可以将目标词语的信息作为用户诉求信息，即将目标词语作为用户的诉求。例如在上述例子中，可以将利息作为用户的诉求，即用户可以需求低利息的信用卡。After the target word is obtained, the information of the target word can be used as the user's appeal information, that is, the target word can be regarded as the user's appeal. For example, in the above example, interest can be taken as the user's demand, that is, the user can demand a credit card with low interest.
206、将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度。206. Match the user appeal information with the rights and interests information corresponding to preset candidate credit cards to obtain a first similarity between the user appeal information and the rights and interests information.
为了得到满足用户诉求的信用卡，可以将用户诉求信息与候选信用卡对应的权益信息进行匹配。In order to obtain a credit card that satisfies the user's appeal, the user's appeal information may be matched with the rights and interests information corresponding to the candidate credit card.
其中，预设的候选信用卡可以包括银行所发行的所有信用卡。The preset candidate credit cards may include all credit cards issued by banks.
其中，权益信息可以是指银行为信用卡设置的用户权益。例如，可以包括：N期免利息、专属客服、可N次逾期等等。在银行设计信用卡时，可以在后台数据库中将其对应的权益信息与信用卡关联。The rights and interests information may refer to the user rights and interests set by the bank for the credit card. For example, it can include: N periods of interest-free, exclusive customer service, N times overdue, etc. When a bank designs a credit card, its corresponding rights information can be associated with the credit card in the background database.
在执行步骤206时，电子设备可以通过word2vec等开源的语言处理模型，将用户诉求信息和候选信用卡对应的权益信息转换为词向量，然后将2个词向量进行对比，得到用户诉求信息与权益信息之间的第一相似度。When performing
207、根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。207. According to the first similarity between the user's appeal information and the rights and interests information, determine the target rights and interests information and the target credit card corresponding to the target rights and interests information, and recommend the target credit card to the credit card application instruction. source terminal.
在一些实施例中，可以将第一相似度与预设的第一相似度阈值进行对比，得到第一相似度大于第一相似度阈值的目标信用卡，并将目标信用卡推送至信用卡申请指令的来源终端。例如，目标用户通过智能手机、个人电脑等终端操作银行软件，点击“申请开卡”等用于申请新信用卡的虚拟按键后，电子设备通过步骤201-步骤207的方法得到目标信用卡，然后在银行软件的界面中显示目标信用卡。In some embodiments, the first similarity may be compared with a preset first similarity threshold to obtain a target credit card whose first similarity is greater than the first similarity threshold, and the target credit card may be pushed to the source of the credit card application instruction terminal. For example, after the target user operates the banking software through a terminal such as a smartphone or a personal computer, and clicks a virtual button for applying for a new credit card, such as "apply for card opening", the electronic device obtains the target credit card through the methods of
需要说明的是，如果第一相似度大于第一相似度阈值的候选信用卡有多张，则可以将其中第一相似度最大的作为目标信用卡，并将目标信用卡推送至来源终端。It should be noted that if there are multiple candidate credit cards with the first similarity greater than the first similarity threshold, the one with the largest first similarity may be used as the target credit card, and the target credit card may be pushed to the source terminal.
可见，通过步骤201-步骤207的方法，得到的目标信用卡所对应的权益信息与用户的诉求相匹配，因此更符合用户的需求。It can be seen that, through the methods of
在一些实施例中，第一相似度阈值还可以根据目标用户的用户属性进行自适应调整。此时，步骤“根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述目标用户的目标终端”，包括：In some embodiments, the first similarity threshold may also be adaptively adjusted according to user attributes of the target user. At this time, the step "determines the target rights information and the target credit card corresponding to the target rights information according to the first similarity between the user's appeal information and the rights and interests information, and recommends the target credit card to the target User's target terminal", including:
(4.1)获取所述目标用户的用户属性信息，其中，所述用户属性信息包括年龄、性别和收入中的至少一者。(4.1) Obtain user attribute information of the target user, wherein the user attribute information includes at least one of age, gender and income.
在执行步骤(4.1)时，电子设备可以根据目标用户的用户标识，从预设的用户属性数据库中读取得到目标用户的用户属性信息。When performing step (4.1), the electronic device may read the user attribute information of the target user from a preset user attribute database according to the user identification of the target user.
其中，预设的用户属性数据库可以是指银行软件后台用于存储用户属性信息的数据库。Wherein, the preset user attribute database may refer to a database used by the bank software backend to store user attribute information.
(4.2)根据所述用户属性信息对应的修正值，对初始的相似度阈值进行修正，得到预设的第一相似度阈值。(4.2) Correcting the initial similarity threshold according to the correction value corresponding to the user attribute information to obtain a preset first similarity threshold.
其中，初始的相似度阈值是预先设置好的基准阈值，具体数值可以根据实际场景需求进行设置。The initial similarity threshold is a preset reference threshold, and the specific value can be set according to actual scene requirements.
修正值是用于对初始的相似度阈值进行调整的值，当用户属性信息不同时，可以采用不同的修正值对初始的相似度阈值进行调整。例如，对于年龄较大的用户，其希望享有的权益可能较为固定，即使信用卡对应的权益与其希望现有的权益差异较小，该用户可能也不会申请该信用卡。例如，对于年龄较大的用户，其希望享有的权益若是“低利息”或者“免利息”相关的内容，则对于权益为“利息可分期”的信用卡，该用户可能也不会想申请该信用卡。而对于年龄较小的用户，只要信用卡对应的权益与其希望现有的权益相关联，该用户就有可能会申请该信用卡。The correction value is a value used to adjust the initial similarity threshold. When the user attribute information is different, different correction values can be used to adjust the initial similarity threshold. For example, for an older user, the rights he wishes to enjoy may be relatively fixed, and even if the rights corresponding to the credit card are less different from the rights he wishes to have, the user may not apply for the credit card. For example, for older users, if the benefits they want to enjoy are related to "low interest" or "interest-free", then for credit cards with "interest installable" benefits, the user may not want to apply for the credit card. . For younger users, as long as the rights corresponding to the credit card are associated with their desired existing rights, the user may apply for the credit card.
在执行步骤(4.2)时，电子设备可以查询预设的对应关系表，得到用户属性信息对应的修正值。然后计算初始的相似度阈值，与修正值之间的差，以得到预设的第一相似度阈值。When performing step (4.2), the electronic device may query the preset correspondence table to obtain the correction value corresponding to the user attribute information. Then, the difference between the initial similarity threshold and the corrected value is calculated to obtain a preset first similarity threshold.
其中，预设的对应关系表可以存储在银行软件的后台数据库中。The preset correspondence table may be stored in the background database of the banking software.
(4.3)将所述用户诉求信息与所述权益信息之间的第一相似度与所述第一相似度阈值进行对比，得到相似度大于所述第一相似度阈值的目标权益信息。(4.3) Comparing the first similarity between the user appeal information and the equity information with the first similarity threshold to obtain target equity information with a similarity greater than the first similarity threshold.
(4.4)将所述目标权益信息对应的候选信用卡作为目标信用卡，将所述目标信用卡推荐至目标用户的目标终端。(4.4) The candidate credit card corresponding to the target rights and interests information is used as the target credit card, and the target credit card is recommended to the target terminal of the target user.
综上所述，本申请实施例提供的信用卡推荐方法，包括：接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；从预设的评论数据库中，查询得到所述目标用户的历史评论；通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；提取所述目标评论中的用户诉求信息；将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。To sum up, the credit card recommendation method provided by the embodiment of the present application includes: receiving a credit card application instruction, determining a target user corresponding to the credit card application instruction; querying and obtaining historical comments of the target user from a preset comment database ; Carry out prediction processing on the historical comments through a preset emotional prediction model to obtain emotional information corresponding to the historical comments, wherein the emotional information includes one of positive information, neutral information and negative information; according to the The emotional information corresponding to the historical comments is screened to obtain the target comments, wherein the emotional information corresponding to the target comments is one of neutral information and negative information; extract the user demands in the target comments information; match the user's appeal information with the rights and interests information corresponding to the preset candidate credit cards to obtain the first similarity between the user's appeal information and the rights and interests information; according to the user's appeal information and the rights and interests The first similarity between the information is used to determine the target rights information and the target credit card corresponding to the target rights information, and recommend the target credit card to the source terminal of the credit card application instruction.
一方面，本申请实施例提供的信用卡推荐方法可以根据目标用户的评论确定目标用户的诉求，然后根据目标用户的诉求，确定待推荐的目标信用卡，因此在推荐信用卡时更加具有针对性，匹配了用户痛点，提高了信用卡推荐的准确性，并且，还可以自动化地对信用卡进行推荐，提高了信用卡的推荐效率。另一方面，在确定目标用户的诉求时，根据评论对应的情感信息进行了筛选，将其中情感积极的评论筛除，既减少了评论数量，进而减少了信用卡推荐时所需要的计算量和计算时间，又保留了其中包含用户诉求信息的目标评论，提高了信用卡推荐的准确性。On the one hand, the credit card recommendation method provided by the embodiment of the present application can determine the appeal of the target user according to the comments of the target user, and then determine the target credit card to be recommended according to the appeal of the target user. User pain points, improve the accuracy of credit card recommendation, and can also automatically recommend credit cards, improving the efficiency of credit card recommendation. On the other hand, when determining the appeal of the target user, it is screened according to the emotional information corresponding to the comments, and the comments with positive emotions are screened out, which not only reduces the number of comments, but also reduces the amount of calculation and calculation required for credit card recommendation. Time, but also retains the target comments containing the user's appeal information, which improves the accuracy of credit card recommendation.
在一些实施例中，可以在选择候选信用卡时，首先对信用卡进行分类，然后将其中评分较高的信用卡作为候选信用卡，以减少信用卡的数量，进而可以减少获取第一相似度时的计算量和计算时间。参考图3，此时，步骤“将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度”之前，所述方法还包括：In some embodiments, when selecting candidate credit cards, the credit cards may be classified first, and then the credit cards with higher scores may be used as candidate credit cards, so as to reduce the number of credit cards, thereby reducing the amount of calculation and calculation when obtaining the first similarity. calculating time. Referring to FIG. 3, at this time, before the step of "matching the user's appeal information with the rights and interests information corresponding to the preset candidate credit cards to obtain the first similarity between the user's appeal information and the rights and interests information", the The method also includes:
301、获取初始信用卡，以及所述初始信用卡对应的权益信息。301. Acquire an initial credit card and rights information corresponding to the initial credit card.
在本申请实施例中，初始信用卡可以包括银行所发行的所有信用卡。In this embodiment of the present application, the initial credit card may include all credit cards issued by the bank.
302、根据所述权益信息中的权益种类，对所述初始信用卡进行分类，得到多个信用卡集合。302. Classify the initial credit card according to the rights and interests types in the rights and interests information to obtain multiple credit card sets.
其中，权益种类可以包括“利息”、“售后”、“商品”、“理财”等等。例如对于“N期免利息”、“利息可分期”等等与利息相关的权益，其对应的权益种类可以是“利息”。Among them, the types of rights and interests may include "interest", "after-sales", "commodities", "financial management" and so on. For example, for interest-related rights such as "N-period interest-free", "interest can be divided into installments", etc., the corresponding rights and interests can be "interest".
执行步骤302时，电子设备可以将权益种类相同的初始信用卡分为一类，得到一个信用卡集合，对所有初始信用卡均分类完成后，即可得到所有信用卡集合。When performing
303、获取每一个信用卡集合中信用卡评分最高的信用卡，将得到的信用卡作为候选信用卡。303. Obtain the credit card with the highest credit card score in each credit card set, and use the obtained credit card as a candidate credit card.
信用卡评分可以是指用户在银行软件上对初始信用卡进行打分后，存储在银行软件后台数据库中的分数。在执行步骤303时，对于每一个信用卡集合，电子设备可以从银行软件后台数据库中，获取其中信用卡对应的信用卡评分，并将各信用卡对应的信用卡评分进行排序，取其中信用卡评分最高的信用卡，然后将每一个信用卡集合中取出的信用卡作为候选信用卡，可以理解的，若共存在10个信用卡集合，则候选信用卡的个数为10。The credit card score may refer to the score stored in the background database of the bank software after the user scores the initial credit card on the bank software. When performing
执行步骤301-步骤303的目的是对于每一个权益种类，都仅设置一个候选信用卡，因此可以减少候选信用卡的数量，进而可以减少获取第一相似度时的计算量和计算时间，并且，由于每一个权益种类都存在对应的候选信用卡，因此也不会出现无法确定与用户诉求信息匹配的目标信用卡的问题。The purpose of executing
在一些实施例中，电子设备可以首先判断目标用户是否对推荐的信用卡感兴趣，若目标用户对推荐的信用卡感兴趣，再执行步骤202-步骤207，以避免浪费计算资源，并且引起目标用户反感。参考图4，此时，步骤“从预设的评论数据库中，查询得到所述目标用户的历史评论”之前，所述方法还包括：In some embodiments, the electronic device may first determine whether the target user is interested in the recommended credit card, and if the target user is interested in the recommended credit card, then perform
401、获取所述目标用户对应的历史推荐次数，以及所述目标用户对应的历史推荐信用卡。401. Obtain the historical recommendation times corresponding to the target user and the historically recommended credit cards corresponding to the target user.
在本申请实施例中，历史推荐次数是指信用卡的历史推荐次数。因此，目标用户对应的历史推荐次数是指对目标用户进行信用卡推荐的次数。In this embodiment of the present application, the historical recommendation times refers to the historical recommendation times of a credit card. Therefore, the number of historical recommendations corresponding to the target user refers to the number of times of recommending credit cards to the target user.
历史推荐信用卡是指曾对用户推荐过的信用卡。因此，目标用户对应的历史推荐信用卡是指曾对目标用户推荐过的信用卡。Historically recommended credit cards refer to credit cards that have been recommended to users in the past. Therefore, the historically recommended credit card corresponding to the target user refers to the credit card that has been recommended to the target user.
目标用户对应的历史推荐次数和目标用户对应的历史推荐信用卡均可以存储在银行软件的后台数据库中，在执行步骤401时，电子设备从中读取得到历史推荐次数和历史推荐信用卡。The historical recommendation times corresponding to the target user and the historically recommended credit cards corresponding to the target user can be stored in the background database of the banking software, and when
402、若所述历史推荐次数小于预设的次数阈值，或者所述目标用户持有的信用卡中包含所述历史推荐信用卡，则执行所述从预设的评论数据库中，查询得到所述目标用户的历史评论的步骤。402. If the number of historical recommendations is less than a preset number of times threshold, or the credit cards held by the target user include the historically recommended credit cards, execute the query to obtain the target user from a preset comment database. steps for a historical review.
若历史推荐次数小于预设的次数阈值，则说明对目标用户推荐信用卡的次数较少，即使目标用户尚未开通推荐的信用卡，也不能说明目标用户对推荐的信用卡不感兴趣，因此电子设备可以执行步骤202-步骤207。If the number of historical recommendations is less than the preset number of times threshold, it means that the number of credit cards recommended to the target user is relatively small. Even if the target user has not opened the recommended credit card, it does not mean that the target user is not interested in the recommended credit card, so the electronic device can perform the steps 202-
若目标用户持有的信用卡中包含历史推荐信用卡，则说明目标用户开通了曾推荐的信用卡，因此可以说明目标用户对推荐的信用卡感兴趣，电子设备可以执行步骤202-步骤207。If the credit card held by the target user includes historically recommended credit cards, it means that the target user has opened the recommended credit card, so it can be shown that the target user is interested in the recommended credit card, and the electronic device can execute steps 202-207.
为了更好实施本申请实施例中的信用卡推荐方法，在信用卡推荐方法基础之上，本申请实施例中还提供一种信用卡推荐装置，如图5所示，为本申请实施例中信用卡推荐装置的一个实施例结构示意图，该信用卡推荐装置500包括：In order to better implement the credit card recommendation method in the embodiment of the present application, on the basis of the credit card recommendation method, the embodiment of the present application further provides a credit card recommending device, as shown in FIG. 5 , which is the credit card recommending device in the embodiment of the present application. A schematic structural diagram of an embodiment, the credit
接收单元501，用于接收信用卡申请指令，确定所述信用卡申请指令对应的目标用户；A receiving
查询单元502，用于从预设的评论数据库中，查询得到所述目标用户的历史评论；A
预测单元503，用于通过预设的情感预测模型，对所述历史评论进行预测处理，得到所述历史评论对应的情感信息，其中，情感信息包括积极信息、中性信息和消极信息中的一者；The
筛选单元504，用于根据所述历史评论对应的情感信息，对所述历史评论进行筛选，得到目标评论，其中，所述目标评论对应的情感信息为中性信息和消极信息中的一者；A
提取单元505，用于提取所述目标评论中的用户诉求信息；an
匹配单元506，用于将所述用户诉求信息与预设的候选信用卡对应的权益信息进行匹配，得到所述用户诉求信息与所述权益信息之间的第一相似度；A
确定单元507，用于根据所述用户诉求信息与所述权益信息之间的第一相似度，确定目标权益信息，以及所述目标权益信息对应的目标信用卡，将所述目标信用卡推荐至所述信用卡申请指令的来源终端。The determining
在本申请的一种可能的实现方式中，确定单元507还用于：In a possible implementation manner of the present application, the determining
获取所述目标用户的用户属性信息，其中，所述用户属性信息包括年龄、性别和收入中的至少一者；obtaining user attribute information of the target user, wherein the user attribute information includes at least one of age, gender and income;
根据所述用户属性信息对应的修正值，对初始的相似度阈值进行修正，得到预设的第一相似度阈值；modifying the initial similarity threshold according to the correction value corresponding to the user attribute information to obtain a preset first similarity threshold;
将所述用户诉求信息与所述权益信息之间的第一相似度与所述第一相似度阈值进行对比，得到相似度大于所述第一相似度阈值的目标权益信息；Comparing the first similarity between the user appeal information and the equity information with the first similarity threshold to obtain target equity information with a similarity greater than the first similarity threshold;
将所述目标权益信息对应的候选信用卡作为目标信用卡，将所述目标信用卡推荐至目标用户的目标终端。The candidate credit card corresponding to the target rights and interests information is used as the target credit card, and the target credit card is recommended to the target terminal of the target user.
在本申请的一种可能的实现方式中，匹配单元506还用于：In a possible implementation manner of the present application, the
获取初始信用卡，以及所述初始信用卡对应的权益信息；Obtain an initial credit card and the rights and interests information corresponding to the initial credit card;
根据所述权益信息中的权益种类，对所述初始信用卡进行分类，得到多个信用卡集合；Classifying the initial credit card according to the rights and interests types in the rights and interests information to obtain a plurality of credit card sets;
获取每一个信用卡集合中信用卡评分最高的信用卡，将得到的信用卡作为候选信用卡。Obtain the credit card with the highest credit card score in each credit card collection, and use the obtained credit card as the candidate credit card.
在本申请的一种可能的实现方式中，提取单元505还用于：In a possible implementation manner of the present application, the
对所述目标评论进行分词处理，得到所述目标评论对应的候选词语；Perform word segmentation processing on the target comment to obtain candidate words corresponding to the target comment;
统计所述目标评论中所述候选词语的出现次数，得到出现次数大于预设的次数阈值的目标词语；Count the number of occurrences of the candidate words in the target comment, and obtain the target words whose number of occurrences is greater than a preset number of thresholds;
将所述目标词语的信息设定为所述目标评论中的用户诉求信息。The information of the target word is set as the user appeal information in the target comment.
在本申请的一种可能的实现方式中，查询单元502还用于：In a possible implementation manner of the present application, the
获取预设的评论数据库中所述目标用户的用户评论；Obtain the user comments of the target user in the preset comment database;
将所述用户评论与预设的默认评论进行对比，得到所述用户评论与所述默认评论之间的第二相似度；Comparing the user comment with a preset default comment to obtain a second similarity between the user comment and the default comment;
将第二相似度小于预设的第二相似度阈值的用户评论设定为所述目标用户的历史评论。User comments whose second similarity is less than a preset second similarity threshold are set as the historical comments of the target user.
在本申请的一种可能的实现方式中，查询单元502还用于：In a possible implementation manner of the present application, the
获取所述目标用户对应的历史推荐次数，以及所述目标用户对应的历史推荐信用卡；Obtaining the historical recommendation times corresponding to the target user, and the historically recommended credit card corresponding to the target user;
若所述历史推荐次数小于预设的次数阈值，或者所述目标用户持有的信用卡中包含所述历史推荐信用卡，则执行所述从预设的评论数据库中，查询得到所述目标用户的历史评论的步骤。If the number of historical recommendations is less than a preset number of times threshold, or the credit cards held by the target user include the historically recommended credit cards, execute the query to obtain the history of the target user from the preset comment database Steps to comment.
在本申请的一种可能的实现方式中，预测单元503还用于：In a possible implementation manner of the present application, the
获取样本数据集，其中，所述样本数据集包括样本评论和所述样本评论对应的标签信息；obtaining a sample data set, wherein the sample data set includes sample comments and label information corresponding to the sample comments;
通过初始的情感预测模型，对所述样本评论进行预测处理，得到所述样本评论对应的情感信息；Performing prediction processing on the sample comments through an initial emotion prediction model to obtain emotional information corresponding to the sample comments;
根据所述标签信息和所述情感信息，对所述初始的情感预测模型中的参数进行调整，得到预设的情感预测模型。According to the label information and the emotion information, the parameters in the initial emotion prediction model are adjusted to obtain a preset emotion prediction model.
具体实施时，以上各个单元可以作为独立的实体来实现，也可以进行任意组合，作为同一或若干个实体来实现，以上各个单元的具体实施可参见前面的方法实施例，在此不再赘述。During specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.
由于该信用卡推荐装置可以执行任意实施例中信用卡推荐方法中的步骤，因此，可以实现本申请任意实施例中信用卡推荐方法所能实现的有益效果，详见前面的说明，在此不再赘述。Since the credit card recommending device can execute the steps in the credit card recommending method in any embodiment, the beneficial effects that can be achieved by the credit card recommending method in any embodiment of the present application can be achieved.
此外，为了更好实施本申请实施例中信用卡推荐方法，在信用卡推荐方法基础之上，本申请实施例还提供一种电子设备，参阅图6，图6示出了本申请实施例电子设备的一种结构示意图，具体的，本申请实施例提供的电子设备包括处理器601，处理器601用于执行存储器602中存储的计算机程序时实现任意实施例中信用卡推荐方法的各步骤；或者，处理器601用于执行存储器602中存储的计算机程序时实现如图5对应实施例中各模块的功能。In addition, in order to better implement the credit card recommendation method in the embodiment of the present application, on the basis of the credit card recommendation method, the embodiment of the present application further provides an electronic device. Referring to FIG. 6, FIG. 6 shows the electronic device of the embodiment of the present application. A schematic structural diagram. Specifically, the electronic device provided in the embodiment of the present application includes a
示例性的，计算机程序可以被分割成一个或多个模块/单元，一个或者多个模块/单元被存储在存储器602中，并由处理器601执行，以完成本申请实施例。一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述计算机程序在计算机装置中的执行过程。Exemplarily, the computer program may be divided into one or more modules/units, and one or more modules/units are stored in the
电子设备可包括，但不仅限于处理器601、存储器602。本领域技术人员可以理解，示意仅仅是电子设备的示例，并不构成对电子设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件。The electronic device may include, but is not limited to, the
处理器601可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，处理器是电子设备的控制中心，利用各种接口和线路连接整个电子设备的各个部分。The
存储器602可用于存储计算机程序和/或模块，处理器601通过运行或执行存储在存储器602内的计算机程序和/或模块，以及调用存储在存储器602内的数据，实现计算机装置的各种功能。存储器602可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据电子设备的使用所创建的数据(比如音频数据、视频数据等)等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。The
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的信用卡推荐装置、电子设备及其相应单元的具体工作过程，可以参考任意实施例中信用卡推荐方法的说明，具体在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of the description, for the specific working process of the credit card recommendation device, electronic equipment and corresponding units described above, reference may be made to the description of the credit card recommendation method in any embodiment. This will not be repeated here.
本领域普通技术人员可以理解，上述实施例的各种方法中的全部或部分步骤可以通过指令来完成，或通过指令控制相关的硬件来完成，该指令可以存储于一存储介质中，并由处理器进行加载和执行。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructions, or by instructions that control relevant hardware, and the instructions can be stored in a storage medium and processed by to load and execute.
为此，本申请实施例提供一种存储介质，存储介质上存储有计算机程序，该计算机程序被处理器执行时执行本申请任意实施例中信用卡推荐方法中的步骤，具体操作可参考任意实施例中信用卡推荐方法的说明，在此不再赘述。To this end, an embodiment of the present application provides a storage medium, where a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps in the credit card recommendation method in any embodiment of the present application are performed. For specific operations, reference may be made to any embodiment. The description of the recommended method for credit cards in China will not be repeated here.
其中，该存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁盘或光盘等。Wherein, the storage medium may include: a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and the like.
由于该存储介质中所存储的指令，可以执行本申请任意实施例中信用卡推荐方法中的步骤，因此，可以实现本申请任意实施例中信用卡推荐方法所能实现的有益效果，详见前面的说明，在此不再赘述。Since the instructions stored in the storage medium can execute the steps in the credit card recommending method in any embodiment of the present application, the beneficial effects that can be achieved by the credit card recommending method in any embodiment of the present application can be achieved. Please refer to the foregoing description for details. , and will not be repeated here.
以上对本申请实施例所提供的一种信用卡推荐方法、装置、存储介质及电子设备进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。A method, device, storage medium and electronic device for recommending a credit card provided by the embodiments of the present application have been described above in detail. The principles and implementations of the present application are described with specific examples. The descriptions of the above embodiments are only It is used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. In summary, this specification The content should not be construed as a limitation on this application.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210852354.3ACN115063237A (en) | 2022-07-19 | 2022-07-19 | Credit card recommendation method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210852354.3ACN115063237A (en) | 2022-07-19 | 2022-07-19 | Credit card recommendation method, device, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115063237Atrue CN115063237A (en) | 2022-09-16 |
Family
ID=83206132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210852354.3APendingCN115063237A (en) | 2022-07-19 | 2022-07-19 | Credit card recommendation method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063237A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879974A (en)* | 2022-11-17 | 2023-03-31 | 平安健康保险股份有限公司 | User screening method based on machine learning and related equipment |
| CN116756419A (en)* | 2023-06-02 | 2023-09-15 | 平安银行股份有限公司 | Credit card rights recommending method, device, equipment and medium based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8515828B1 (en)* | 2012-05-29 | 2013-08-20 | Google Inc. | Providing product recommendations through keyword extraction from negative reviews |
| CN111459989A (en)* | 2020-03-30 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Credit card recommendation method, device, equipment and medium |
| CN112949322A (en)* | 2021-04-27 | 2021-06-11 | 李蕊男 | E-commerce opinion mining recommendation system driven by online text comments |
| CN114090880A (en)* | 2021-11-10 | 2022-02-25 | 北京明略软件系统有限公司 | Method and device for product recommendation, electronic device, storage medium |
- 2022
- 2022-07-19CNCN202210852354.3Apatent/CN115063237A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8515828B1 (en)* | 2012-05-29 | 2013-08-20 | Google Inc. | Providing product recommendations through keyword extraction from negative reviews |
| CN111459989A (en)* | 2020-03-30 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Credit card recommendation method, device, equipment and medium |
| CN112949322A (en)* | 2021-04-27 | 2021-06-11 | 李蕊男 | E-commerce opinion mining recommendation system driven by online text comments |
| CN114090880A (en)* | 2021-11-10 | 2022-02-25 | 北京明略软件系统有限公司 | Method and device for product recommendation, electronic device, storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879974A (en)* | 2022-11-17 | 2023-03-31 | 平安健康保险股份有限公司 | User screening method based on machine learning and related equipment |
| CN116756419A (en)* | 2023-06-02 | 2023-09-15 | 平安银行股份有限公司 | Credit card rights recommending method, device, equipment and medium based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106897428B (en) | Text classification feature extraction method and text classification method and device | |
| CN107463605B (en) | Method and device for identifying low-quality news resource, computer equipment and readable medium | |
| WO2020244073A1 (en) | Speech-based user classification method and device, computer apparatus, and storage medium | |
| CN112733042B (en) | Recommendation information generation method, related device and computer program product | |
| WO2020108608A1 (en) | Search result processing method, device, terminal, electronic device, and storage medium | |
| US20200134398A1 (en) | Determining intent from multimodal content embedded in a common geometric space | |
| CN111191445A (en) | Advertisement text classification method and device | |
| WO2020257991A1 (en) | User identification method and related product | |
| CN112102049A (en) | Model training method, business processing method, device and equipment | |
| CN107832338A (en) | A kind of method and system for identifying core product word | |
| CN115063237A (en) | Credit card recommendation method, device, electronic device and storage medium | |
| CN111552802A (en) | Text classification model training method and device | |
| CN114067343A (en) | Data set construction method, model training method and corresponding device | |
| CN116933130A (en) | Enterprise industry classification method, system, equipment and medium based on big data | |
| WO2022237215A1 (en) | Model training method and system, and device and computer-readable storage medium | |
| WO2025113288A1 (en) | Content recommendation method and apparatus, and device | |
| CN112712394B (en) | Customer lead sharing method, system, computer and readable storage medium | |
| WO2024245081A1 (en) | Model training method, text processing method and related device | |
| CN111695357B (en) | Text labeling method and related product | |
| CN111507114B (en) | Reverse translation-based spoken language text enhancement method and system | |
| CN111625619B (en) | Query omission method, device, computer readable medium and electronic equipment | |
| CN115129864A (en) | Text classification method and device, computer equipment and storage medium | |
| CN111898378B (en) | Industry classification method and device for government enterprise clients, electronic equipment and storage medium | |
| CN111475647A (en) | Document processing method and device and server | |
| CN111597368B (en) | A data processing method and device |
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 |