Customer mining method and device, storage medium and program product

Abstract

The invention discloses a client mining method and device, a storage medium and a program product, and relates to the technical field of data analysis, the client mining method comprises the steps of generating a client screening condition according to a pre-constructed client knowledge graph, the client knowledge graph being constructed based on a preset graph construction template; and when customer screening condition configuration set by the user based on the customer screening conditions is received, performing customer mining according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list. According to the method, client mining is carried out through the configured and templated knowledge graph, so that the technical problem of low service response efficiency caused by the fact that client mining by utilizing the knowledge graph depends on the support of information technicians in related technologies is solved, the technical use threshold of the knowledge graph and the technical dependence on the information technicians are reduced, and the user experience is improved. And the service response efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a customer mining method, device, storage medium and program product. Background Art

[0002] In order for product sales personnel to make targeted product recommendations to target customers, information technology personnel are required to extract target customer lists based on business needs. Traditional direct data extraction and artificial intelligence models each have their own advantages, but they also face problems such as understanding bias, insufficient effect and lack of explainability.

[0003] Although the use of knowledge graphs for customer mining in related technologies provides new ideas for solving these problems, the complexity of its construction, updating and use and its dependence on information technology personnel still lead to inefficient business response.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a customer mining method, device, storage medium and program product, aiming to solve the technical problem in related technologies that customer mining using knowledge graphs relies on the support of information technology personnel, resulting in low business response efficiency.

[0006] To achieve the above objectives, the present application proposes a customer mining method, which comprises:

[0007] Generate customer screening conditions according to a pre-built customer knowledge graph, wherein the customer knowledge graph is built based on a preset graph building template;

[0008] When receiving the customer screening condition configuration set by the user based on the customer screening condition, customer mining is performed according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list.

[0009] In one embodiment, before the step of generating customer screening conditions based on the pre-built customer knowledge graph, the step further includes:

[0010] Get entity relationship configuration and data date configuration;

[0011] Based on the graph construction template, a knowledge graph is constructed according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph.

[0012] In one embodiment, the step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph includes:

[0013] Building a template based on the graph, generating a first data job according to the entity relationship configuration and the data date configuration;

[0014] The first data job reads the tabular data of the data date corresponding to the data date configuration in the preset data source, and performs structured processing on the tabular data to generate a customer knowledge graph.

[0015] In one embodiment, after the step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph, the step further includes:

[0016] Get the update data date configuration;

[0017] Based on the preset data update template, according to the update data date configuration, generate a second data job;

[0018] The table data of the data date corresponding to the updated data date configuration in the preset data source is read through the second data job, and the customer knowledge graph is updated according to the table data.

[0019] In one embodiment, the customer knowledge graph includes at least graph data and graph metadata, the graph data includes at least customer entities, customer relationships and data dates, and the graph metadata includes at least one or more of attribute field names, attribute field descriptions, attribute graph type names, attribute types and attribute value ranges.

[0020] In one embodiment, the customer screening condition configuration includes at least one or more of a target customer screening condition, a relationship screening condition, a relationship statistics screening condition, and an associated customer statistics screening condition.

[0021] The step of performing customer mining according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list includes:

[0022] Generate a list of candidate target customers based on customer entities in the customer knowledge graph that meet the target customer screening conditions;

[0023] Generate a candidate associated customer list based on the candidate target customer list and the customer relationships that meet the relationship screening conditions in the customer knowledge graph;

[0024] Calculating the relationship attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the relationship statistics screening condition and the relationship attribute statistics of each candidate target customer to obtain a relationship statistics screened customer list; and / or

[0025] Calculating the associated customer attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the associated customer statistical screening conditions and the associated customer attribute statistics of each candidate target customer to obtain an associated customer statistical screening customer list;

[0026] The customer list is filtered according to the relationship statistics and / or the associated customer statistics to obtain a target customer list.

[0027] In one embodiment, the method further comprises:

[0028] Receiving a product screening configuration template selected by a user, wherein the product screening configuration template is created based on preset product information and screening condition configuration;

[0029] According to the product screening configuration template, product customer screening conditions are obtained, and customer mining is performed according to the product customer screening conditions and the customer knowledge graph to obtain a product customer list.

[0030] In addition, to achieve the above purpose, the present application also proposes a customer mining device, the customer mining device comprising:

[0031] A condition generation module, used to generate customer screening conditions based on a pre-built customer knowledge graph, wherein the customer knowledge graph is constructed based on a preset graph construction template;

[0032] The customer mining module is used to perform customer mining according to the customer screening condition configuration and the customer knowledge graph when receiving the customer screening condition configuration set by the user based on the customer screening condition, so as to obtain a list of target customers.

[0033] In addition, to achieve the above objectives, the present application also proposes a customer mining device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the customer mining method described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the customer mining method described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the customer mining method described above are implemented.

[0036] The present application provides a customer mining method, which generates customer screening conditions by using a customer knowledge graph constructed using a graph construction template, so that users can set appropriate customer screening condition configurations for mining related customers; when receiving the customer screening condition configurations set by the user, customer mining is performed based on the customer screening condition configurations and the customer knowledge graph, and a target customer list is obtained, so as to mine a customer list that meets the user's business needs in real time. By performing customer mining through a configured and templated knowledge graph, the technical problem that the use of knowledge graphs for customer mining in related technologies relies on the support of information technology personnel, resulting in low business response efficiency, is solved, the technical dependence of knowledge graphs on information technology personnel is reduced, and business response efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 A flowchart of the first embodiment of the customer mining method of the present application is provided;

[0040] Figure 2 A flow chart of a graph construction module provided for the second embodiment of the customer mining method of the present application;

[0041] Figure 3 A flow chart of an available screening condition generation module provided in the second embodiment of the customer mining method of the present application;

[0042] Figure 4 A schematic diagram of a page prototype of the first condition type provided for the second embodiment of the customer mining method of the present application;

[0043] Figure 5 A schematic diagram of a page prototype of a second condition type provided for the second embodiment of the customer mining method of the present application;

[0044] Figure 6 A schematic diagram of the flow of the graph query module provided for the second embodiment of the customer mining method of this application;

[0045] Figure 7 A schematic diagram of the flow of real-time graph query provided in the second embodiment of the customer mining method of this application;

[0046] Figure 8 This is a schematic diagram of the module structure of the customer mining device according to an embodiment of the present application;

[0047] Fig. 9 A schematic diagram of the device structure of the hardware operating environment involved in the customer mining method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solution of the embodiment of the present application is: generating customer screening conditions based on a pre-constructed customer knowledge graph, wherein the customer knowledge graph is constructed based on a preset graph construction template; when receiving a customer screening condition configuration set by a user based on the customer screening condition, performing customer mining based on the customer screening condition configuration and the customer knowledge graph to obtain a list of target customers.

[0052] According to existing technology, in order for front-line product sales staff of commercial banks to recommend financial products to their target customers in a targeted manner, IT personnel are required to extract target customer lists based on business needs. The current method is generally that IT personnel directly extract data based on their own business understanding or use artificial intelligence models to calculate the list. The former is prone to the problem of misunderstanding between IT and business, and the problem of poor list effect; the latter may have a better list effect, but the model calculation results often lack intuitive business explanations.

[0053] In recent years, knowledge graphs have been increasingly widely used in the financial industry and can also be used to solve such problems. However, the construction, use, and update steps of knowledge graphs are complicated. Generally, IT personnel pre-build relatively large knowledge graphs containing various business data, and then carry out customized development, query or calculation based on the needs of a specific business scenario of business personnel. The update of relevant knowledge graphs is also highly dependent on IT personnel, resulting in slow response to business needs and low efficiency.

[0054] Technical terms involved in this application:

[0055] Knowledge graph: a structured semantic knowledge base that stores information related to entities (such as people, places, objects, concepts, etc.) in the form of graphs. Knowledge graphs usually contain two elements: entities and relationships.

[0056] Entity: A node in a knowledge graph that represents a specific object or concept in the real world.

[0057] Relationship: An edge between entities, which represents a certain connection or attribute between entities, such as "belongs to", "is located in", "created by", etc.

[0058] Data operations: usually refers to a series of tasks that need to be completed in the process of data processing, analysis and management, such as data cleaning, data analysis, data visualization, database management, etc.

[0059] This application uses configurable and templated knowledge graphs to perform customer mining, solving the technical problem in related technologies that the use of knowledge graphs for customer mining relies on the support of information technology personnel, resulting in low business response efficiency. It lowers the technical usage threshold of knowledge graphs and the technical dependence on information technology personnel, and improves business response efficiency.

[0060] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a customer mining device, etc. The following takes the customer mining device as an example to illustrate this embodiment and the following embodiments.

[0061] Based on this, the present application embodiment provides a customer mining method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the customer mining method of the present application.

[0062] In this embodiment, the customer mining method includes steps S10 to S20:

[0063] Step S10, generating customer screening conditions according to a pre-constructed customer knowledge graph, wherein the customer knowledge graph is constructed based on a preset graph construction template;

[0064] It should be noted that the graph construction template refers to the template for building a customer knowledge graph, which defines the structure of the graph and the type of information that needs to be included, so that the characteristics and behavior patterns of customers and the relationships between different customers can be identified by building a knowledge graph. The customer knowledge graph is a structured database that can contain customer information and relationships between customers, as well as various information about customers, such as their purchase history, preferences, behavior patterns, etc., to support customer mining and analysis.

[0065] In addition, it should be noted that the customer screening conditions are various conditions defined based on the customer knowledge graph for screening out specific customer groups, which contain the same customer attribute information as the customer knowledge graph. By setting the customer screening condition configuration, you can screen out customers with the same customer attributes, and you can also screen out other related customers with specific customer relationships.

[0066] It can be understood that in order to distinguish the characteristics between different customers and identify the correlation between different customers, the customer knowledge graph constructed using the graph construction template generates customer screening conditions, so that target customers can be quickly located and identified according to business needs.

[0067] Step S20, when receiving the customer screening condition configuration set by the user based on the customer screening condition, customer mining is performed according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list.

[0068] It should be noted that customer screening condition configuration refers to the specific screening conditions set by users according to business needs to guide customer mining. It is customized by users according to business needs and may include specific customer attributes, behavioral characteristics, etc. The target customer list is a list of customers that meets the user-configured screening conditions and business needs after screening, and is used for marketing activities, product recommendations, personalized services, etc.

[0069] It can be understood that when the system receives the customer filtering condition configuration set by the user based on the customer filtering condition, it uses the customer knowledge graph and the customer filtering condition configuration set by the user to perform the customer mining process, mines out customers who meet the customer filtering condition configuration from a large amount of customer data, and obtains a list of customers that can meet specific business needs. The configurable and templated knowledge graph allows business personnel to quickly adjust customer mining strategies according to actual business needs, thereby improving the flexibility and customizability of the system.

[0070] In a feasible implementation manner, before the step of generating customer screening conditions based on the pre-built customer knowledge graph, the step further includes:

[0071] Step S101, obtaining entity relationship configuration and data date configuration;

[0072] It should be noted that the entity relationship configuration defines the entity types that can be included in the knowledge graph and the relationships between entities. Entities can include information such as customers, products, services, events, etc., while relationships describe how these entities are related to each other. For example, a customer may have a purchase relationship with multiple products, or an event may have a participation relationship with multiple customers.

[0073] In addition, it should be noted that the data date configuration is the time range of the data used to build the knowledge graph. Data at different time points may have a significant impact on the analysis results. For example, the latest data may be needed to capture the latest behavior patterns of customers, or historical data may be needed to analyze long-term trends.

[0074] It is understandable that in order to ensure that the knowledge graph can accurately reflect the business needs and the latest status of customer data, before building the knowledge graph, it is necessary to determine which entities (such as customers, products) and the relationships between them (such as purchase, use) will be included in the graph, and which time range of data will be used.

[0075] Step S102, based on the graph construction template, construct a knowledge graph according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph.

[0076] It can be understood that by using the pre-set graph building template, according to the entity relationship configuration and data date configuration, a customized customer knowledge graph containing the required entities and relationships is created to provide a data foundation for subsequent customer mining.

[0077] In this implementation, by obtaining entity relationship configuration and data date configuration, it is ensured that the construction of the knowledge graph can accurately reflect business needs and the latest customer data; then the graph construction template is used to build a customized knowledge graph, which can quickly identify customers who meet specific conditions from a large amount of customer data, thereby providing support for marketing, sales or services.

[0078] In a feasible implementation, the step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph includes:

[0079] Step S1021, constructing a template based on the graph, and generating a first data job according to the entity relationship configuration and the data date configuration;

[0080] It should be noted that a data job is a set of instructions for processing and transforming data, which defines how to extract and organize information from raw data to build a knowledge graph.

[0081] It can be understood that based on the graph construction template, the first data job is generated according to the entity relationship configuration and data date configuration, ensuring that the data job can process the data according to the predetermined rules and structure, and providing the necessary data preparation for generating the customer knowledge graph.

[0082] Step S1022: read the table data of the data date corresponding to the data date configuration in the preset data source through the first data operation, and perform structured processing on the table data to generate a customer knowledge graph.

[0083] It should be noted that a data lake refers to a system that stores a large amount of raw data, usually in an unstructured or semi-structured form. Tabular data refers to data organized in rows and columns for easy reading and analysis.

[0084] It can be understood that the first data job generated is executed to read the tabular data with the data date corresponding to the data date configuration from a preset data source (such as a data lake), thereby obtaining the actual data required to build the knowledge graph, and structuring these data according to customer entities and customer relationships according to the entity relationship configuration to construct a complete customer knowledge graph.

[0085] In this implementation, by generating the first data job, it is ensured that the data processing process can be carried out according to the predetermined rules and structure, providing the necessary data preparation for generating the customer knowledge graph. Then, by reading the table data in the data source, the actual data required for building the knowledge graph is obtained, and finally the customer knowledge graph is generated. This not only improves the efficiency of knowledge graph construction, but also ensures that the graph is always based on the latest data, thereby improving the accuracy and relevance of the graph. By automating and optimizing the data processing process, the overall construction performance of the knowledge graph is improved.

[0086] In a feasible implementation manner, after the step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph, the step further includes:

[0087] Step S103, obtaining update data date configuration;

[0088] It is understandable that the date configuration for obtaining updated data is used to determine the time range within which the knowledge graph data needs to be updated, ensuring that the knowledge graph can reflect the latest customer data and improve the timeliness and accuracy of analysis and decision-making.

[0089] Step S104, generating a second data job based on a preset data update template and according to the update data date configuration;

[0090] It should be noted that the data update template refers to a predefined template used to guide the data update process of the knowledge graph, including data extraction, processing and update rules.

[0091] It can be understood that according to the preset data update template and the new data date configuration, a second data job is generated to process and update the data in the knowledge graph, provide necessary instructions and rules for the data update of the knowledge graph, and ensure the automation and standardization of the update process.

[0092] Step S105, reading the table data of the data date corresponding to the updated data date configuration in the preset data source through the second data operation, and updating the customer knowledge graph according to the table data.

[0093] It can be understood that the second data job generated is executed to read the tabular data with the data date corresponding to the updated data date configuration from a pre-set data source (such as a data lake), and use this data to update the customer knowledge graph. By regularly updating the data in the knowledge graph, the timeliness and accuracy of the graph are maintained, providing the latest customer insights for business decisions.

[0094] In this implementation, by obtaining the update data date configuration, the data range of the knowledge graph that needs to be updated is determined; then by generating the second data job, the necessary instructions and rules are provided for the data update of the knowledge graph; finally, by executing the second data job and updating the customer knowledge graph, it is ensured that the graph can reflect the latest customer data, improving the timeliness and accuracy of analysis and decision-making. Not only does it improve the update efficiency of the knowledge graph, it also ensures that the graph is always based on the latest data, thereby improving the accuracy and relevance of the graph. In addition, by automating and real-time monitoring of the data update process, manual entry errors caused by differences in understanding of business needs are avoided, and the overall update performance of the knowledge graph is improved.

[0095] In a feasible implementation, the customer knowledge graph includes at least graph data and graph metadata, the graph data includes at least customer entities, customer relationships and data dates, and the graph metadata includes at least one or more of attribute field names, attribute field descriptions, attribute graph type names, attribute types and attribute value ranges.

[0096] It should be noted that the customer entity is the basic unit in the customer knowledge graph, representing a specific customer or a customer-related entity, such as an individual, company, or other organization. The customer relationship describes the relationship between customer entities, such as a purchase relationship, a recommendation relationship, or a social network relationship. The data date identifies the timestamp of the data record, which is used to track the timeliness and historical changes of the data.

[0097] In addition, it should be noted that the attribute field name is the corresponding field name in the data lake specified by the user, which is convenient for reference and retrieval in the graph. The attribute field description refers to the field description of the corresponding data in the data lake, which helps users understand the purpose and meaning of the field. The attribute graph type is used to distinguish the type of the attribute, such as customer entity attributes or customer relationship attributes, which helps to organize and classify different entities and attributes in the graph. The attribute type is the attribute data type configured by the user, such as string, number, date, etc., to ensure data consistency and correct processing. The attribute value range specifies the possible value range or allowed value set of the attribute, which is used for data validation and constraints.

[0098] In a feasible implementation manner, the customer screening condition configuration includes at least one or more of a target customer screening condition, a relationship screening condition, a relationship statistics screening condition, and an associated customer statistics screening condition.

[0099] The step of performing customer mining according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list includes:

[0100] Step S201, generating a list of candidate target customers according to the customer entities in the customer knowledge graph that meet the target customer screening conditions;

[0101] It should be noted that the target customer screening conditions define basic customer characteristics or attributes and are used to preliminarily screen potential target customers.

[0102] It can be understood that a preliminary list of candidate target customers is generated based on customer entities that meet the target customer screening conditions in the customer knowledge graph, providing an initial customer group based on specific business needs for subsequent screening and analysis.

[0103] Step S202, generating a candidate associated customer list according to the candidate target customer list and the customer relationships that meet the relationship screening conditions in the customer knowledge graph;

[0104] It should be noted that the relationship screening condition defines the screening condition of the relationship characteristics between customers, which is used to identify other customers related to the target customer.

[0105] It can be understood that, based on the candidate target customer list and the customer relationships that meet the relationship screening conditions, a candidate associated customer list is generated to identify other customers who have a direct relationship with the target customer, providing a wider customer network for further analysis.

[0106] Step S203, calculating the relationship attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the relationship statistics screening condition and the relationship attribute statistics of each candidate target customer to obtain a relationship statistics screened customer list;

[0107] It should be noted that the relationship statistics screening condition defines the statistical characteristics based on customer relationships, which is used to further screen target customers.

[0108] It can be understood that when the customer screening condition configuration includes relationship statistical screening conditions, the relationship attribute statistics of each candidate target customer in the candidate target customer list are calculated, and the candidate associated customer list is screened in combination with the relationship statistical screening conditions. The target customer group is further refined through statistical analysis to identify those customers who meet specific conditions in terms of relationship attributes.

[0109] and / or step S204, calculating the associated customer attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the associated customer statistical screening condition and the associated customer attribute statistics of each candidate target customer to obtain an associated customer statistical screening customer list;

[0110] It should be noted that the associated customer statistical screening condition defines the statistical characteristics of the associated customers based on the target customer, which is used to further screen the target customers.

[0111] It can be understood that when the customer screening condition configuration includes the associated customer statistical screening condition, the associated customer attribute statistical value of each candidate target customer in the candidate associated customer list is calculated, and the candidate associated customer list is screened in combination with the associated customer statistical screening condition, and the target customer group is further refined through statistical analysis to identify those customers who meet specific conditions in terms of associated customer attributes.

[0112] Step S205, filtering the customer list according to the relationship statistics and / or filtering the customer list according to the associated customer statistics to obtain a target customer list.

[0113] It should be noted that when the customer screening condition configuration includes both the relationship statistics screening condition and the associated customer statistics screening condition, the relationship statistics screening customer list and the associated customer statistics screening customer list can be obtained, and the two customer lists are processed as intersection or union to obtain the target customer list.

[0114] It is understandable that by filtering the customer list based on relationship statistics and / or filtering the customer list based on associated customer statistics, a target customer list is finally obtained, which provides a target customer group that has undergone multiple rounds of screening and analysis, and provides accurate target customer data for business scenarios such as marketing, sales or services.

[0115] In this embodiment, by statistically analyzing relationships and associated customers, the target customer list can be further refined and optimized, which can more accurately locate potential high-value customers and improve the pertinence and success rate of marketing activities. In addition, by flexibly configuring screening conditions, customer mining strategies can be quickly adjusted according to different business scenarios and needs, improving business response speed and market adaptability.

[0116] In a feasible implementation manner, the method further includes:

[0117] Step S30, receiving a product screening configuration template selected by a user, wherein the product screening configuration template is created based on preset product information and screening condition configuration;

[0118] It should be noted that the product screening configuration template is a template created by the user based on the product information and the screening condition configuration selected for the product characteristics for specific business needs. The product screening configuration templates for different products can be displayed in a visual interface for user selection. Product information can include product-related attribute information, such as product name, product category, etc.

[0119] In addition, it should be noted that the visual interface can simultaneously display product filtering configuration templates and customer filtering conditions available for user selection, so that the user can simultaneously obtain product filtering configuration templates selected for different products and customer filtering condition configurations based on the customer filtering conditions to perform customer mining, so as to meet more precise customer mining needs for specific products.

[0120] It is understandable that in order to facilitate users to quickly mine product-related customer lists, users can provide one or more preset product screening configuration templates for users to choose from in the visual interface, so that after the system receives the product screening configuration template selected by the user, further customer mining can be carried out, allowing users to quickly select or customize screening conditions according to the needs of specific products or services, thereby improving the targetedness and efficiency of customer mining.

[0121] Step S40, obtaining product customer screening conditions according to the product screening configuration template, and performing customer mining according to the product customer screening conditions and the customer knowledge graph to obtain a product customer list.

[0122] It can be understood that based on the product screening configuration template selected by the user, customer screening conditions for specific products are automatically obtained or generated, and the customer mining process is performed using the obtained product customer screening conditions and customer knowledge graph to identify customers who meet these conditions, so as to screen out potential customer groups interested in specific products or services from a large amount of customer data, and provide accurate target customer data for marketing, sales or services.

[0123] In this implementation, by providing a product screening configuration template, users are allowed to quickly select or customize screening conditions according to the needs of specific products or services, and potential customer groups interested in specific products or services are screened out from a large amount of customer data through automated screening condition generation. This not only improves the efficiency and accuracy of customer mining, but also ensures the pertinence and relevance of mining results, thereby providing strong support for marketing, sales or services, helping enterprises better understand customer needs, improve customer satisfaction, enhance market competitiveness, and achieve more efficient resource allocation and business decisions.

[0124] This embodiment provides a customer mining method, which generates customer screening conditions using a customer knowledge graph constructed using a graph construction template, so that users can set appropriate customer screening condition configurations for mining related customers; when receiving the customer screening condition configurations set by the user, customer mining is performed based on the customer screening condition configurations and the customer knowledge graph to obtain a list of target customers, so as to mine a list of customers that meet the user's business needs in real time. By performing customer mining through a configured and templated knowledge graph, the technical problem that the use of knowledge graphs for customer mining in related technologies relies on the support of information technology personnel, resulting in low business response efficiency, is solved, the technical dependence of knowledge graphs on information technology personnel is reduced, and business response efficiency is improved.

[0125] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those of the above-mentioned first embodiment can be referred to the above introduction and will not be repeated later.

[0126] Exemplarily, in order to help understand the implementation process of the customer mining method obtained by combining this embodiment with the above-mentioned first embodiment, the method can be divided into three modules according to function: a graph construction module, an available screening condition generation module and a graph query module. Specifically:

[0127] 1. Graph construction module: The input of the graph construction module is entity relationship configuration, data lake table and data date configuration, and the output is graph data and graph metadata.

[0128] like Figure 2 As shown, Figure 2 A flow chart of the graph construction module provided for the second embodiment of the customer mining method of this application. The user configures the entity relationship and data date by building a template. The graph construction module reads the table data of the corresponding data date from the data lake, generates the corresponding data job, automatically builds the graph data of the corresponding data date and stores it in the graph database. At the same time, the graph metadata is calculated based on the table data and stored in the relational database.

[0129] Specifically, the graph construction requires the following information, which the user configures according to the customer knowledge graph construction template and provides to the system. The customer knowledge graph construction template contains the following content:

[0130] 1) Customer entity configuration: the data lake library name and table name of the customer ID and customer attribute source.

[0131] 2) Customer relationship configuration: The data lake library name and table name of the customer relationship ID and relationship attribute source.

[0132] 3)Data date.

[0133] Specifically, the format of the customer entity configuration is as follows:

[0134]

[0135] The format of the customer relationship configuration is as follows:

[0136]

[0137] The graph construction module generates a data job (identified by a globally unique data job ID) based on this information. The job reads the corresponding data from the data lake, generates point (entity) insertion statements and edge (relationship) insertion statements for the graph database, and writes the corresponding graph data to the graph database.

[0138] In addition, business personnel can configure the data date of data jobs on the data job scheduling platform to implement regular updates of graph data. The format of the data update template is as follows:

[0139] Data job ID Data date

[0140] At the same time, the module generates graph metadata based on this information and stores it in a relational database. The format of the graph metadata is as follows:

[0141] Attribute field name Attribute Field Description Property Graph Type Name Property Type Attribute value range

[0142] in:

[0143] 1) Attribute field name: the English name of the corresponding field in the data lake specified by the user.

[0144] 2) Attribute field description: The corresponding field description in the data lake, such as comment information, is usually in Chinese.

[0145] 3) Attribute map type: A value of 0 indicates that the attribute is a customer entity attribute, and a value of 1 indicates that the attribute is a relationship attribute.

[0146] 4) Attribute type: that is, the attribute type configured by the user. String is a character type, numerical is a numeric type, date is a date type, and bool is a Boolean type.

[0147] 5) Attribute value range: When the attribute type is string, a list of possible values ​​for the attribute is obtained by counting the data in the data lake.

[0148] A convenient customer knowledge graph construction template is provided, so that business personnel can build a knowledge graph for mining the target customer list of the financial product in accordance with the specific characteristics of the financial product. The construction template has strong business explainability. Business personnel configure the customer entity attributes and customer relationship attributes related to the financial product through the construction template. The system can automatically read the relevant data from the data lake through data jobs and complete the construction of the knowledge graph for the financial product without relying on IT personnel. In addition, a data update template for the knowledge graph is also provided. Business personnel only need to configure the specific date of the data based on the data update template. The system can automatically read the data of the corresponding date from the data lake through data jobs and complete the update of the graph data. After the data update is completed, business personnel can select the corresponding date when using the graph, so as to use the updated graph data for real-time query without relying on IT personnel.

[0149] 2. Available filtering condition generation module: The available filtering condition generation module takes graph metadata as input and outputs available filtering conditions.

[0150] like Figure 3 As shown, Figure 3 A flow chart of an available screening condition generation module provided for the second embodiment of the customer mining method of the present application. The available screening condition generation module reads the graph metadata from the relational database and generates corresponding available screening conditions.

[0151] Among them, the available filtering conditions can include two types:

[0152] 1) Available filter conditions for filtering customer (target customer or associated customer) attributes and relationship attributes. This filter condition directly matches and filters based on the attribute value. Applicable to all attribute types.

[0153] 2) Available filtering conditions for filtering the statistical values ​​of associated customer attributes and the statistical values ​​of relationship attributes. This filtering condition calculates the statistical value by counting the attribute values ​​of multiple associated customers or the attribute values ​​of multiple relationship edges associated with each candidate target customer, and then performs matching and filtering based on the statistical value. It is only applicable to numerical and bool types.

[0154] Specifically, it includes:

[0155] For type 1): For each attribute in the graph metadata, different logics are used to generate corresponding available filtering conditions according to the attribute type of the graph metadata:

[0156] 1. string type: Display according to the attribute value range. For example, for attribute a, the possible values ​​in its data are x, y, and z, and the interface displays x, y, and z. This allows users to check x and y when performing query configuration, indicating that attribute a must be configured to have a value of x or y.

[0157] 2. Numerical type: Displays numerical ranges. This allows users to configure the numerical range of the attribute when performing query configuration. For example, if the configuration attribute b needs to satisfy the value range (2,3], the user selects the lower bound condition as >, the lower bound value is 2, and the upper bound condition as <=, the upper bound value is 3. This means that the attribute value must be greater than 2 and not greater than 3.

[0158] 3. Date type: Date range display. This allows users to configure the date value range of the attribute when performing query configuration. For example, if the configuration attribute c needs to satisfy the value range of 2020-01-01 to 2020-12-31, the user selects 2020-01-01 in the start date and 2020-12-31 in the end date.

[0159] 4. Bool type: drop-down box display, including "yes" and "no" two options. For example, if the configuration attribute d needs to satisfy "yes", the user selects the drop-down option "yes".

[0160] The page prototype of the above example is as follows Figure 4 As shown, Figure 4 A schematic diagram of a page prototype of the first conditional type provided for the second embodiment of the customer mining method of the present application.

[0161] For type 2): For each numerical attribute in the graph metadata, four filtering conditions are generated, which represent the filtering conditions that the statistical values ​​calculated by the four statistical methods need to meet. The four statistical methods are minimum, maximum, sum, and average. For each bool attribute in the graph metadata, two filtering conditions are generated, which represent the filtering conditions that the statistical values ​​calculated by the two statistical methods need to meet. The two statistical methods are quantity (i.e., the number of attribute values ​​with "yes") and proportion (i.e., the number of attribute values ​​with "yes" divided by the total number).

[0162] The page prototype of the above example is as follows Figure 5 As shown, Figure 5 A schematic diagram of a page prototype of the second condition type provided for the second embodiment of the customer mining method of the present application.

[0163] 3. Graph query module: The input of the graph query module is the user's filtering condition configuration and data date configuration, as well as graph data, and the output is the target customer list.

[0164] like Figure 6 As shown, Figure 6 A flow chart of the graph query module provided for the second embodiment of the customer mining method of this application. The user configures the filtering conditions through the available filtering conditions and filtering templates (optional), and the user also configures the data date. The graph query module queries the target customer list from the graph data based on the filtering conditions and data date.

[0165] 1) Query configuration: The query template contains the following five parts. Users can configure all parts or select only individual parts for configuration:

[0166] 1. Target customer screening conditions: Configure the attributes that target customers need to meet. The system screens customers who meet the conditions from all data as candidate target customers.

[0167] 2. Relationship screening conditions: configure the attributes that the relationship needs to meet, as well as the relationship level. The system screens the relationships that meet the conditions from the candidate target customers' relationships based on the relationship attributes, thereby mining candidate associated customers of the candidate target customers.

[0168] 3. Related customer screening conditions: Configure the attributes that related customers need to meet. The system screens related customers that meet the conditions from the candidate related customers of the candidate target customers based on the attributes of the related customers.

[0169] 4. Relationship statistics screening conditions: configure the conditions that the statistical values ​​of relationship attributes must meet. For each candidate target customer, the system calculates the statistical values ​​of its relationship attributes and screens the target customers that meet the conditions as the result list.

[0170] 5. Related customer statistics screening conditions: configure the conditions that the statistical values ​​of related customer attributes must meet. For each candidate target customer, the system calculates the attribute statistics of the related customer and screens the target customers that meet the conditions as the result list.

[0171] Among them, if the user configures "four" and "five" at the same time, the final output result list will be the intersection of the two.

[0172] A screening configuration template is provided for each financial product, so that business personnel can directly use the screening configuration template to complete the mining of the target customer list for the financial product. Users can select some of the screening conditions from all available screening conditions for configuration. For example, the customer entity contains three attributes a, b, and c. When the user configures the customer entity attributes, only attribute b can be selected for configuration. In addition, the system also provides commonly used screening configuration templates for user convenience. The so-called screening configuration template is a collection of attributes. For example, when the user is mining the target customers of a financial product x, the relevant customer entity attributes are b and c. Then when the user selects template x (corresponding to financial product x), the system only displays attributes b and c for the user to configure.

[0173] 2) Data date configuration: The system obtains available data dates based on the existing data in the graph, and displays the data date list to the user in a list format. The user completes the configuration by checking the corresponding data date.

[0174] 3) Real-time graph query: Figure 7 As shown, Figure 7 A flow chart of real-time graph query provided in the second embodiment of the customer mining method of this application. Specifically, the following steps are included:

[0175] Step 1: Based on the target customer screening conditions, select some candidate target customers through the point query function of the graph database as the starting point of the graph query. The obtained data format is as follows (one row of data for each candidate target customer):

[0176] Target customer ID

[0177] Step 2: Take the output of step 1 as input, filter out the related customers of the candidate target customers by the relationship filtering conditions, through the edge query function of the graph database, and specify the filtering conditions that the related customers need to meet. The obtained data format is as follows (each candidate target customer may be associated with multiple related customers through multiple relationship paths, so each candidate target customer ID may correspond to multiple data):

[0178]

[0179] Step 3.1: Take the output of step 2 as input, and calculate the specified statistical value of the specified attribute of the relationship for each candidate target customer according to the relationship statistical screening conditions (at this time, the associated customer attributes are not considered, and only the target customer ID, relationship attribute 1, relationship attribute 2, and relationship attribute n fields are used for calculation), and filter out the target customers that do not meet the statistical value range. The data format is as follows (one row of data for each candidate target customer):

[0180] Target customer ID

[0181] Step 3.2: Take the output of step 2 as input, and according to the related customer statistical screening conditions, for each candidate target customer, calculate the specified statistical value of the specified attribute of the related customer (at this time, the relationship attribute is not considered, and only the target customer ID, related customer attribute 1, related customer attribute 2, and related customer attribute n fields are used for calculation), and filter out the target customers that do not meet the statistical value range. The data format obtained is as follows (one row of data for each candidate target customer):

[0182] Target customer ID

[0183] Step 4: The final target customer list is the intersection of the output of step 3.1 and the output of step 3.2.

[0184] It provides a convenient customer knowledge graph query template, so that business personnel can configure the query template according to the specific characteristics of financial products and complete the mining of the target customer list. The query template contains the following five sections: 1. Attribute screening configuration of target customers; 2. Attribute screening configuration of relationships; 3. Attribute screening configuration of related customers; 4. Attribute statistical value screening configuration of multiple relationships of the same target customer; 5. Attribute statistical value screening configuration of multiple related customers of the same target customer. The query template has strong business interpretability. When business personnel configure the above sections, the system can automatically generate complex graph database query statements to complete the query of the customer knowledge graph, thereby obtaining a list of target customers that meet each screening condition without relying on IT personnel.

[0185] In this embodiment, through convenient and explainable template configuration, business personnel can configure according to the relevant customer attributes and relationship attributes of the product, and the system automatically generates data operations, which automatically build graph data and generate corresponding graph query configuration interfaces. After the data operation is completed, business personnel can perform convenient query configuration in the graph query configuration interface, perform graph queries in real time, and obtain target customer lists. A target customer list mining method based on an explainable configuration template is implemented, avoiding the problem of complex knowledge graph construction, use, and update steps. Business personnel can use knowledge graphs to conduct targeted target customer list mining through convenient configuration.

[0186] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the customer mining method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0187] This application also provides a customer mining device, please refer to Figure 8 , the customer mining device comprises:

[0188] A condition generation module 10, used to generate customer screening conditions according to a pre-constructed customer knowledge graph, wherein the customer knowledge graph is constructed based on a preset graph construction template;

[0189] The customer mining module 20 is used to perform customer mining according to the customer screening condition configuration and the customer knowledge graph when receiving the customer screening condition configuration set by the user based on the customer screening condition, so as to obtain a list of target customers.

[0190] Optionally, the condition generation module 10 is further used for:

[0191] Get entity relationship configuration and data date configuration;

[0192] Based on the graph construction template, a knowledge graph is constructed according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph.

[0193] Optionally, the condition generation module 10 is further used for:

[0194] Building a template based on the graph, generating a first data job according to the entity relationship configuration and the data date configuration;

[0195] The first data job reads the tabular data of the data date corresponding to the data date configuration in the preset data source, and performs structured processing on the tabular data to generate a customer knowledge graph.

[0196] Optionally, the condition generation module 10 is further used for:

[0197] Get the update data date configuration;

[0198] Based on the preset data update template, according to the update data date configuration, generate a second data job;

[0199] The table data of the data date corresponding to the updated data date configuration in the preset data source is read through the second data job, and the customer knowledge graph is updated according to the table data.

[0200] Optionally, the customer knowledge graph includes at least graph data and graph metadata, the graph data includes at least customer entities, customer relationships and data dates, and the graph metadata includes at least one or more of attribute field names, attribute field descriptions, attribute graph type names, attribute types and attribute value ranges.

[0201] Optionally, the customer screening condition configuration includes at least one or more of a target customer screening condition, a relationship screening condition, a relationship statistics screening condition, and an associated customer statistics screening condition, and the customer mining module 20 is further used to:

[0202] Generate a list of candidate target customers based on customer entities in the customer knowledge graph that meet the target customer screening conditions;

[0203] Generate a candidate associated customer list based on the candidate target customer list and the customer relationships that meet the relationship screening conditions in the customer knowledge graph;

[0204] Calculating the relationship attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the relationship statistics screening condition and the relationship attribute statistics of each candidate target customer to obtain a relationship statistics screened customer list; and / or

[0205] Calculating the associated customer attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the associated customer statistical screening conditions and the associated customer attribute statistics of each candidate target customer to obtain an associated customer statistical screening customer list;

[0206] The customer list is filtered according to the relationship statistics and / or the associated customer statistics to obtain a target customer list.

[0207] Optionally, the customer mining device further includes:

[0208] A configuration template receiving module 30 is used to receive a product screening configuration template selected by a user, wherein the product screening configuration template is created based on preset product information and screening condition configuration;

[0209] The product customer mining module 40 is used to obtain product customer screening conditions according to the product screening configuration template, and perform customer mining according to the product customer screening conditions and the customer knowledge graph to obtain a product customer list.

[0210] The customer mining device provided by the present application adopts the customer mining method in the above embodiment, which can solve the technical problem that the customer mining using knowledge graph in the related technology relies on the support of information technology personnel, resulting in low business response efficiency. Compared with the prior art, the beneficial effects of the customer mining device provided by the present application are the same as the beneficial effects of the customer mining method provided by the above embodiment, and the other technical features in the customer mining device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0211] The present application provides a customer mining device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the customer mining method in the first embodiment described above.

[0212] Reference below Fig. 9 , which shows a schematic diagram of the structure of a customer mining device suitable for implementing the embodiment of the present application. The customer mining device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The customer mining device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0213] like Fig. 9 As shown, the customer mining device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the customer mining device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the customer mining device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a customer mining device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0214] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0215] The customer mining device provided by the present application adopts the customer mining method in the above embodiment, which can solve the technical problem that the use of knowledge graphs for customer mining in related technologies relies on the support of information technology personnel, resulting in low business response efficiency. Compared with the prior art, the beneficial effects of the customer mining device provided by the present application are the same as the beneficial effects of the customer mining method provided by the above embodiment, and the other technical features in the customer mining device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0216] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0217] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0218] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the customer mining method in the above-mentioned embodiment.

[0219] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0220] The computer-readable storage medium may be included in the client mining device; or may exist independently without being assembled into the client mining device.

[0221] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the customer mining device, the customer mining device: generates customer filtering conditions based on a pre-constructed customer knowledge graph, and the customer knowledge graph is constructed based on a preset graph construction template; when receiving a customer filtering condition configuration set by a user based on the customer filtering condition, performs customer mining according to the customer filtering condition configuration and the customer knowledge graph to obtain a list of target customers.

[0222] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0223] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0224] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0225] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned customer mining method, and can solve the technical problem in the related art that customer mining using knowledge graphs relies on the support of information technology personnel, resulting in low business response efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the customer mining method provided by the above-mentioned embodiment, and will not be repeated here.

[0226] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned customer mining method when executed by a processor.

[0227] The computer program product provided by this application can solve the technical problem in the related art that customer mining using knowledge graphs relies on the support of information technology personnel, resulting in low business response efficiency. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the customer mining method provided by the above embodiment, which will not be repeated here.

[0228] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A customer mining method, characterized in that: The method comprises: Generate customer screening conditions according to a pre-built customer knowledge graph, wherein the customer knowledge graph is built based on a preset graph building template; When receiving the customer screening condition configuration set by the user based on the customer screening condition, customer mining is performed according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list.

2. The method according to claim 1, characterized in that: Before the step of generating customer screening conditions according to the pre-built customer knowledge graph, the step further includes: Get entity relationship configuration and data date configuration; Based on the graph construction template, a knowledge graph is constructed according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph.

3. The method according to claim 2, characterized in that: The step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph includes: Building a template based on the graph, generating a first data job according to the entity relationship configuration and the data date configuration; The first data job reads the tabular data of the data date corresponding to the data date configuration in the preset data source, and performs structured processing on the tabular data to generate a customer knowledge graph.

4. The method according to claim 2, characterized in that: After the step of constructing a knowledge graph based on the graph construction template and according to the entity relationship configuration and the data date configuration to obtain a customer knowledge graph, the step further includes: Get the update data date configuration; Based on the preset data update template, according to the update data date configuration, generate a second data job; The table data of the data date corresponding to the updated data date configuration in the preset data source is read through the second data job, and the customer knowledge graph is updated according to the table data.

5. The method according to any one of claims 1 to 4, characterized in that: The customer knowledge graph includes at least graph data and graph metadata, wherein the graph data includes at least customer entities, customer relationships and data dates, and the graph metadata includes at least one or more of attribute field names, attribute field descriptions, attribute graph type names, attribute types and attribute value ranges.

6. The method according to claim 1, characterized in that: The customer screening condition configuration includes at least one or more of target customer screening conditions, relationship screening conditions, relationship statistics screening conditions and associated customer statistics screening conditions. The step of performing customer mining according to the customer screening condition configuration and the customer knowledge graph to obtain a target customer list includes: Generate a list of candidate target customers based on customer entities in the customer knowledge graph that meet the target customer screening conditions; Generate a candidate associated customer list based on the candidate target customer list and the customer relationships that meet the relationship screening conditions in the customer knowledge graph; Calculating the relationship attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the relationship statistics screening condition and the relationship attribute statistics of each candidate target customer to obtain a relationship statistics screened customer list; and / or Calculating the associated customer attribute statistics of each candidate target customer in the candidate associated customer list, and screening the candidate associated customer list according to the associated customer statistical screening conditions and the associated customer attribute statistics of each candidate target customer to obtain an associated customer statistical screening customer list; The customer list is filtered according to the relationship statistics and / or the associated customer statistics to obtain a target customer list.

7. The method according to claim 1, characterized in that: The method further comprises: Receiving a product screening configuration template selected by a user, wherein the product screening configuration template is created based on preset product information and screening condition configuration; According to the product screening configuration template, product customer screening conditions are obtained, and customer mining is performed according to the product customer screening conditions and the customer knowledge graph to obtain a product customer list.

8. A customer mining device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the customer mining method according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the customer mining method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the customer mining method according to any one of claims 1 to 7 are implemented.

Images