A banking financial marketing recommendation method and device

Abstract

The present application provides a bank financial marketing recommendation method and device, which can be applied to the financial field, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, and with a customer-centric approach, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities and various visual marketing views to help account managers understand the characteristics and relationships between customers and products, allowing account managers to better serve customers and improve marketing quality. At the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that the present application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a banking financial marketing recommendation method and device. Background Art

[0002] With the development of mobile Internet, the interconnection of all things has become possible, and the data generated by this interconnection is also growing explosively, and this data can serve as the basis for analyzing relationships. Knowledge graph is the most effective way to represent relationships, and it depicts our real world in the form of a graph. The knowledge graph aims to organically organize fragmented data by establishing association links between data, making it easier for people and machines to understand and process data, and providing convenience for search, mining, analysis, etc., and providing a knowledge base foundation for the realization of artificial intelligence.

[0003] Although banks have accumulated a large amount of information, traditional banks mainly use data to display data according to traditional transaction utilization. Information only exists in isolation, and the internal relationship of the data is not mined. When marketing to customers, account managers cannot intuitively and comprehensively grasp the customer information, product information and their relationship. When they cannot fully grasp the customer and product information and their internal relationship, they cannot provide exclusive services to customers, and the marketing efficiency will be low. Based on the above situation, in order to improve marketing efficiency, account managers often set up their own small ledgers, record some characteristics and important information of customers through some customer transaction data on the device and some information obtained when contacting customers; collect some product information through major websites, and record some information about products they care about. This way of working is relatively inefficient. Account managers only have the energy to provide services to familiar customers, and give up providing services to other customers, which may cause continuous customer loss. Summary of the invention

[0004] In response to the problems in the prior art, the present application provides a banking financial marketing recommendation method and device. In order to break the isolated data and realize the interconnection of data, the bank's data is connected in series, and the implicit relationships are mined through continuous penetration in various related information. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, with a customer-centric approach, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, and providing various visual marketing views to help account managers grasp the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality.

[0005] In order to solve the above technical problems, this application provides the following technical solutions:

[0006] In a first aspect, the present application provides a banking financial marketing recommendation method, comprising:

[0007] Obtain the identity information of the customer to be recommended;

[0008] Generate banking financial product recommendation information based on the identity information and a preset banking financial product knowledge graph;

[0009] Recommend bank financial products to the customer to be recommended according to the bank financial product recommendation information; wherein,

[0010] The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities.

[0011] Furthermore, it also includes:

[0012] Establish the bank's financial product knowledge graph.

[0013] Furthermore, the bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management association relationship between the customer entity and the customer-subscribed financial agreement entity, and the association relationship between the customer entity and the transaction information entity; the bank financial product recommendation information is generated according to the identity information and the preset bank financial product knowledge graph, including:

[0014] Query the bank financial product knowledge graph according to the identity information to obtain the customer entity corresponding to the identity information, as well as the corresponding bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity;

[0015] According to the interpersonal association relationship in the bank financial product knowledge graph, obtain the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to other customer entities in the same family as the customer;

[0016] Based on the inference engine and the custom inference rules, the bank financial product recommendation information is generated by combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer.

[0017] Furthermore, the bank financial product recommendation information is generated based on the inference engine and the custom inference rules, in combination with the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer, including:

[0018] Calling the Java API of the Jena inference engine to construct triples according to the bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer;

[0019] The custom inference rules interact with the inference engine through Jena's Java API, and the inference engine is started through Jena's Java API, so that the Jena engine traverses all triples and performs inference operations according to the custom inference rules to generate the bank financial product recommendation information.

[0020] Furthermore, the custom inference rules may be dynamically changed in response to a set event trigger.

[0021] Furthermore, the bank financial product recommendation information includes: product type, risk level and yield in the last 7 days;

[0022] The recommending a bank financial product to the customer to be recommended according to the bank financial product recommendation information includes:

[0023] Match financial products based on product type, risk level and yield in the last 7 days.

[0024] Furthermore, the method is triggered in response to an event that a financial product of a customer expires, an event that a large amount of funds is deposited into the customer's account, or an event that the customer's birthday occurs.

[0025] In a second aspect, the present application provides a banking financial marketing recommendation device, comprising:

[0026] Acquisition module, to obtain the identity information of the customer to be recommended;

[0027] A recommendation information generation module generates recommendation information of bank financial products according to the identity information and a preset bank financial product knowledge graph;

[0028] The recommendation module recommends bank financial products to the customer to be recommended according to the bank financial product recommendation information; wherein:

[0029] The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities.

[0030] Furthermore, it also includes:

[0031] Establish a module to establish the bank financial product knowledge graph.

[0032] Furthermore, the bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management association relationship between the customer entity and the customer-subscribed financial agreement entity, and the association relationship between the customer entity and the transaction information entity; the generation module includes:

[0033] A query unit, which queries the bank financial product knowledge graph according to the identity information to obtain a customer entity corresponding to the identity information, as well as a corresponding bank account information entity, a customer-subscribed financial agreement entity, and a transaction information entity;

[0034] A family member acquisition unit, which acquires, according to the interpersonal association relationship in the bank financial product knowledge graph, bank account information entities, customer-subscribed financial agreement entities, and transaction information entities corresponding to other customer entities in the same family as the customer;

[0035] The generating unit generates the bank financial product recommendation information based on the inference engine and the custom inference rules, combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer.

[0036] Furthermore, the generating unit comprises:

[0037] A calling unit calls a Java API of a Jena reasoning engine to construct a triple according to a bank account information entity, a customer-subscribed financial agreement entity, and a transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer;

[0038] The interaction unit interacts the custom inference rules with the inference engine through the Java API of Jena, and starts the inference engine through the Java API of Jena, thereby enabling the Jena engine to traverse all triples, and perform inference operations according to the custom inference rules to generate the bank financial product recommendation information.

[0039] Furthermore, the custom inference rules may be dynamically changed in response to a set event trigger.

[0040] Furthermore, the bank financial product recommendation information includes: product type, risk level and yield in the last 7 days;

[0041] The recommendation module is specifically used to match financial products according to the product type, risk level and yield in the last 7 days.

[0042] Furthermore, the device is triggered in response to an event of expiration of a customer's financial product, an event of a large amount of funds being deposited into the customer's account, and a customer's birthday event.

[0043] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the bank financial marketing recommendation method when executing the program.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the bank financial marketing recommendation method when executed by a processor.

[0045] It can be seen from the above technical solution that the bank financial marketing recommendation method and device provided by the present application breaks the isolated data, realizes the interconnection of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing the knowledge graph, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategy and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, providing various visual marketing views, helping account managers to grasp the characteristics and associations between customers and products, allowing account managers to better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that the present application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 It is a flow chart for constructing a banking financial information marketing map in an embodiment of the present application.

[0048] Figure 2 It is a schematic diagram of knowledge acquisition in an embodiment of the present application.

[0049] Figure 3 It is a schematic diagram of the composition of customer information in an embodiment of the present application.

[0050] Figure 4 It is a schematic diagram of the knowledge integration process in the embodiment of the present application.

[0051] Figure 5 It is a schematic diagram of the marketing strategy in the embodiment of this application.

[0052] Figure 6 It is a schematic diagram of the knowledge processing flow in the embodiment of this application.

[0053] Figure 7 It is a schematic diagram of knowledge application in an embodiment of the present application.

[0054] Figure 8 It is one of the partial schematic diagrams of the banking financial product knowledge graph in the embodiment of this application.

[0055] Fig. 9 It is one of the partial schematic diagrams of the banking financial product knowledge graph in the embodiment of this application.

[0056] Fig.10 It is one of the partial schematic diagrams of the banking financial product knowledge graph in the embodiment of this application.

[0057] Fig.11 It is a flowchart of the banking financial marketing recommendation method in the embodiment of the present application.

[0058] Fig.12 In the embodiment of this application Fig.11 Specific flow chart of step 102 in FIG.

[0059] Fig.13 In the embodiment of this application Fig.12 Specific flow chart of step 202 in FIG.

[0060] Fig.14 It is a structural diagram of the banking financial marketing recommendation device in the embodiment of the present application.

[0061] Fig.15 It is a structural diagram of the generation module in the bank financial marketing recommendation device in the embodiment of the present application.

[0062] Fig.16 It is a schematic diagram of the generation unit of the generation module described in the embodiment of the present application.

[0063] Fig.17 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] It should be noted that the bank financial marketing recommendation method and device disclosed in the present application can be used in the financial field, and can also be used in any field other than the financial field. The application field of the bank financial marketing recommendation method and device disclosed in the present application is not limited.

[0066] Considering that banks have accumulated a large amount of information, traditional banks mainly use data to display data according to traditional transactions. Information only exists in isolation, and the internal relationship of the data is not mined. When marketing to customers, account managers cannot intuitively and comprehensively grasp the customer information, product information and their relationship. When they cannot fully grasp the customer and product information and their internal relationship, they cannot provide exclusive services to customers, and the marketing efficiency will be low. Based on the above situation, in order to improve marketing efficiency, account managers often set up their own small ledgers, record some characteristics and important information of customers through some customer transaction data on the device and some information obtained when contacting customers; collect some product information through major websites, and record some information about products they care about. This way of working is relatively inefficient. Account managers only have the energy to provide services to familiar customers, and give up providing services to other customers, which may cause continuous customer loss.

[0067] Based on the above content, the present application also provides a bank financial marketing recommendation device for implementing the bank financial marketing recommendation method provided in one or more embodiments of the present application. The bank financial marketing recommendation device can be communicatively connected with a client device, and the client terminal device can be provided with multiple ones. The client terminal device can access the bank financial marketing recommendation device through a bank app.

[0068] Among them, the bank financial marketing recommendation device can collect and obtain the identity information of the customer to be recommended from the customer terminal device, and generate bank financial product recommendation information based on the identity information and a preset bank financial product knowledge graph; then, bank financial products are recommended to the customer to be recommended based on the bank financial product recommendation information.

[0069] It is understandable that the client device may include a smart phone, a tablet electronic device, a portable computer, a desktop computer, a personal digital assistant (PDA), a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0070] The client device has a communication module (i.e., a communication unit) that can communicate with a remote bank financial marketing recommendation device to achieve data transmission with the bank financial marketing recommendation device. For example, the communication unit can send the identity information of the customer to be recommended to the bank financial marketing recommendation device so that the bank financial marketing recommendation device can store the identity information of the customer to be recommended.

[0071] The bank financial marketing recommendation device and the client device may communicate using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocol may include, for example, TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol) and REST protocol (Representational State Transfer) used on top of the above protocols.

[0072] The bank financial marketing recommendation method, electronic device, computer-readable storage medium and bank financial marketing recommendation device provided in the present application obtain the identity information of the customer to be recommended; then generate bank financial product recommendation information based on the identity information and a preset bank financial product knowledge graph; then recommend bank financial products to the customer to be recommended based on the bank financial product recommendation information; wherein the bank financial product knowledge graph includes customer entities and interpersonal relationships between each customer entity.

[0073] The details are described through the following multiple embodiments and application examples.

[0074] In order to solve the problem that when the account manager conducts marketing to the customer, it is impossible to intuitively and comprehensively grasp the customer information, product information and their relationship, and when it is impossible to comprehensively grasp the customer and product information and their internal relationship, it is impossible to provide exclusive services to the customer, and the marketing efficiency will be low, this application provides an embodiment of a banking financial marketing recommendation method, see Fig.11 The bank financial marketing recommendation method specifically includes the following contents:

[0075] Step 101: Obtain identity information of the customer to be recommended.

[0076] It can be understood that the identity information of the customer to be recommended can be understood as the unique identification information of the customer to be recommended, which can be internal identification information within the bank, such as a multi-digit letter code or a digital code, and further can be a hash value. The identity information can also be the customer's public ID, such as an identity card, social security card, etc., but the present application is not limited to this.

[0077] Step 102: Generate banking financial product recommendation information based on the identity information and a preset banking financial product knowledge graph.

[0078] Step 103: Recommend bank financial products to the customer to be recommended based on the bank financial product recommendation information.

[0079] The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities.

[0080] It can be seen from the above technical solutions that the bank financial marketing recommendation method provided by this application breaks the isolated data, realizes the interconnection of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, and providing various visual marketing views to help account managers grasp the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that this application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

[0081] In some embodiments, the interpersonal relationship may be a relationship between colleagues in the same company, or a relationship between family members. The relationship between family members is used as an example for explanation below, and it is understandable that for other interpersonal relationships, similar concepts can be used for recommendation.

[0082] It can be understood that within the banking system, the customer identity information can be associated with all corresponding reserved information, and the reserved information can be considered as the customer information corresponding to the customer identity information.

[0083] In the specific implementation, we can first build a marketing map of bank financial information, such as Figure 1 As shown, the construction flow chart of the banking financial information marketing map includes "knowledge acquisition S100", "knowledge integration S200", "marketing strategy S300", "knowledge processing S400" and "knowledge application S500".

[0084] like Figure 2 As shown, the “knowledge acquisition S100” includes the extraction of basic data, which mainly includes two parts, one part is “customer information S110”; the other part is “product information S120”.

[0085] like Figure 3 As shown, the "customer information S110" mainly includes "basic information S111", "family information S112" (entities that constitute the interpersonal relationship between family members), "financial products held S113", "financial agreements signed S114", "financial product transaction details S115", and "consumption information S116".

[0086] The "basic information S111" is mainly based on the customer information entered when the customer signs the agreement, and the rest is based on the customer's current financial product holding information, etc. It includes name, customer information number, gender, date of birth, customer risk level, occupation, total assets, current balance, non-performing loan balance, service star, contribution star, and permanent location.

[0087] The "family information S112" is the customer information entered when the customer signs the agreement, or the customer family information learned by the customer manager when serving the customer and entered into the marketing system, including information about the spouse and children.

[0088] The "Financial Products Held S113" obtains a list of products held by the customer based on the financial product information currently held by the customer, including current, fixed deposits, funds, wealth management, bonds, insurance, account foreign exchange, account precious metals, account crude oil, account agricultural products, account precious metals, physical precious metals, accumulated precious metals, physical precious metals, credit cards, debit cards, and personal loan products.

[0089] The "Signing Financial Agreement S114" obtains a list of valid financial agreements based on the customer's existing valid financial agreements, including personal online banking, personal mobile banking, personal telephone banking, messenger, personal SMS banking, payment, U-Shield, password device, password card, and personal settlement package.

[0090] The "Financial Product Transaction Details S115" obtains the transaction history details of each product in the past six months in each product system, including current, fixed, fund, wealth management, bond, insurance, account foreign exchange, account precious metals, account crude oil, account agricultural products, account precious metals, physical precious metals, and accumulated precious metal products.

[0091] The "consumption information S116" is based on the customer's credit card, debit card and other transaction details, by classifying the information of the counterparty, and counting the total consumption amount in the past 6 months by category. The categories include food consumption amount, clothing consumption amount, daily necessities consumption amount, medical consumption amount, education consumption amount, decoration consumption amount, home appliance consumption amount, car consumption amount, book and software consumption amount, jewelry consumption amount, catering consumption amount, travel and business trip consumption amount, beauty and hairdressing consumption amount, entertainment consumption amount, communication consumption amount, and overseas consumption amount.

[0092] Furthermore, the bank system also includes product information. The "product information S120" refers to the financial products sold in the bank, including two parts. One part is investment products, including deposits, wealth management, bonds, insurance, account foreign exchange, account crude oil, account agricultural products, and precious metals; the other part is agreement products, including personal online banking, personal mobile banking, personal telephone banking, messenger, personal SMS banking, payment, U shield, password device, password card, and personal settlement package. Different products obtain different key information of products, such as fund products obtain fund name, fund code, fund type, fund risk level, currency, minimum purchase amount, transaction spread, net value / yield, whether it can be invested regularly, dividend method, fund status, purchase channel, whether it can be pledged, etc. Financial products obtain information such as product name, product code, return type, product risk level, initial purchase starting amount, transaction spread, performance benchmark, product term, fundraising time, interest accrual date, maturity date, maturity payment date, redemption settlement date, most recent subscription date, most recent redemption date, issuing region, currency, purchase channel, whether it can be pledged, sales commission, custody fee, management fee, etc.

[0093] In this embodiment, the bank financial product recommendation information is generated based on the identity information and the preset bank financial product knowledge graph, such as Fig.12 include:

[0094] S201: Query the bank financial product knowledge graph according to the identity information to obtain the customer entity corresponding to the identity information, as well as the corresponding bank account information entity, customer-subscribed financial agreement entity and transaction information entity.

[0095] It can be understood that various information entities within the bank and their respective associations can be queried based on the above identity information.

[0096] S202: According to the interpersonal association relationship in the bank financial product knowledge graph, obtain the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to other customer entities that are members of the same family as the customer.

[0097] Through the above embodiments, using technologies such as knowledge reasoning, a huge marketing knowledge graph is established, and the ability of multi-dimensional perspective analysis is provided, providing various visual marketing views, helping account managers to understand the characteristics and relationships between customers and products, allowing account managers to better serve customers and improve marketing quality. This allows account managers to give full play to their inherent value, further enhance the image of the company, and allow the company to further enhance its competitiveness among peers.

[0098] The other steps of the present invention are described below. During the specific implementation, the acquired knowledge can be organized and converted into a triple structure.

[0099] like Figure 4 As shown, the "knowledge integration S200" is to organize the knowledge acquired in the above process and convert it into a triple structure, which mainly includes "constructing ontology S210", "constructing attributes S220" and "extracting relations S230".

[0100] In the "constructing ontology S210", the object ontology is determined. The ontology involved in the data object of the present invention includes customers and products. Each independent customer and each independent product is an ontology. The partial ontology is extracted as follows:

[0101] Ontology Description Huang Xiaoming Customer ontology Yang Shuya Customer ontology E Fund Science and Technology Mixed Fund Product Body Wells Fargo Innovation Technology Product Body Behavioral habits Behavioral Habits

[0102] The "constructing attributes S220" is to obtain the associated attributes from the elements obtained in the "knowledge acquisition S100". Some of the extracted attributes are as follows:

[0103] property Attribute Description husband Identify the husband attribute between customer entities wife Identify the wife attribute between the client ontology and the client ontology hold Identify the attributes of the product ontology held by the customer ontology Overseas consumption Identify the attributes of customer ontology and behavior habit ontology

[0104] The “extracting relationship S230” means that after determining the ontology and the attribute, the ontology and the attribute are established in a relationship to form triples. The list of extracted partial triples is as follows:

[0105]

[0106]

[0107] Of course, the triple structure may also be other similar structures, and the present application is not limited to this triple structure.

[0108] S203: Generate the bank financial product recommendation information based on the inference engine and the custom inference rules, combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer.

[0109] In this application, knowledge graph and knowledge reasoning are combined. Reasoning is to obtain new knowledge or conclusions through various methods. These knowledge and conclusions meet the semantics. Its specific tasks can be divided into satisfiability, classification, and materialization.

[0110] It can be understood that the satisfiability in reasoning can be reflected in ontology or concept. Ontology, ontology satisfiability is to check whether an ontology is satisfiable, that is, to check whether the ontology has a model. If the ontology is not satisfied, it means that there is an inconsistency. Concept satisfiability is to check the satisfiability of a concept, that is, to check whether there is a model so that the explanation for the concept is not an empty set.

[0111] It can be understood that the reasoning engine in the present application can control the execution of the system, including pattern matching (matching the facts in the fact set with the conditional part of the rule, the rules whose entire LHS are satisfied are triggered and added to the agenda), conflict resolution (selecting one from the multiple triggered rules according to a certain strategy), and action execution (executing the RHS of the selected rule, thereby performing certain operations on the WM).

[0112] Specifically, the inference engine may use at least one of the following tools:

[0113] Drools:

[0114] Drools is a commercial rule management system that provides a rule inference engine. Its core algorithm is an improvement on the RETE algorithm. It provides a rule definition language and supports embedding Java code.

[0115] Jena:

[0116] Jena is a Java framework for building semantic web applications. It provides interfaces for processing RDF, RDFs, and OWL data, as well as a rule engine. It provides memory storage and query of triples.

[0117] RDF4J:

[0118] RDF4J is an open source framework for processing RDF data, supporting the parsing, storage, reasoning, and querying of semantic data. It can be associated with almost all RDF storage systems and can be used to access remote RDF storage.

[0119] In the above-mentioned embodiments of the present invention, it can be known that the above-mentioned triples adopt the jena tool. However, those skilled in the art understand that the core concept of the present invention is not to adopt what kind of reasoning engine, but to adopt the technology of the reasoning engine to solve the technical problem of the present invention. Therefore, the present invention can be appropriately adjusted for the use of other tools, which will not be elaborated here.

[0120] Specifically, in the jena tool, the inference engine and the custom inference rules are combined with the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer to generate the bank financial product recommendation information, such as Fig.13 ,include:

[0121] S221: calling the Java API of the Jena reasoning engine to construct a triple according to the bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer;

[0122] S222: The custom inference rules interact with the inference engine through the Java API of Jena, and the inference engine is started through the Java API of Jena, so that the Jena engine traverses all triples and performs inference operations according to the custom inference rules to generate the bank financial product recommendation information.

[0123] In this application, when reasoning, the triples created above are used to perform ontology reasoning using the Jena reasoning engine, and the reasoning results are saved in the graph database for use by the marketing penetration system. This includes the steps of "custom reasoning rules S410", "knowledge reasoning S420", "reasoning results S430", "JanusGraph graph database S440", and "marketing penetration system S450".

[0124] like Figure 6 As shown, the "knowledge processing S400" uses the triples created above to perform ontology reasoning using the Jena reasoning engine, and saves the reasoning results in the graph database for use by the marketing penetration system. It includes the steps of "custom reasoning rules S410", "knowledge reasoning S420", "reasoning results S430", "JanusGraph graph database S440", and "marketing penetration system S450".

[0125] The "custom reasoning rules S410" is a key link in using the Jena reasoning engine. It mainly converts the logic to be inferred according to the reasoning rule description language supported by Jena based on the analysis and summary of business experts. The following is an example of a custom rule:

[0126] Rule 1: [ruleGblCreCard:(?a:wife?b)(?a:overseas spending:behavioral habits)->(?b:recommendation:visa / master credit card)]

[0127] Rule 1 means that if a wife has a habit of spending overseas, she should recommend visa / master credit cards to her husband.

[0128] The "knowledge reasoning S420" calls the Java API of the Jena reasoning engine to build triples, and interacts the custom reasoning rules with the reasoning engine through the Jena Java API, and starts the reasoning engine through the Jena Java API. The Jena engine then traverses all triples and performs reasoning operations according to the reasoning rules.

[0129] The "reasoning result S430" is a complete reasoning result obtained by the Jena reasoning engine through all triple reasoning operations, and the reasoning result is also output in the format of triples, such as (:Huang Xiaoming:Recommendation:visa / master credit card).

[0130] The "JanusGraph graph database S440" is used to persistently store the original triple information of the knowledge graph and the triple information obtained by reasoning. Since the graph involved in the present invention is very large, a distributed database is selected for storage, and the relationship between the information of the knowledge graph is complex, so a graph database should be preferred. Therefore, the present invention uses a JanusGraph graph database to store knowledge graph information.

[0131] The "marketing penetration system S450" refers to a marketing system that can directly obtain the data of the above-mentioned knowledge graph through the JanusGraph graph database, so that customer managers can grasp various complex knowledge graph information.

[0132] Furthermore, the establishment of the bank financial product knowledge graph of the present application can be performed online or offline, that is, the bank financial recommendation method further includes: establishing the bank financial product knowledge graph.

[0133] More preferably, the bank financial product knowledge graph can be constructed in a distributed server cluster.

[0134] In some embodiments, the recommendation of bank financial products can be that business personnel specify customers with specific characteristics based on experience or tasks assigned by the upper level, and then market products with specified characteristics or a specific product. For example, marketing Tianlibao net value financial products to customers whose current balance is greater than 10% of total assets and whose current balance is greater than 500,000.

[0135] Bank financial product recommendations can also be based on acquired data. According to combined indicators, sample data of currently held products are used to obtain feature variables using decision trees, and the model is verified based on retained samples. After the final feature variables are selected, decision trees are used based on the latest feature variables to perform calculations for customers who do not hold the product, and marketing strategies are defined for customers with high scores to recommend the product.

[0136] Specifically, Figure 5As shown, the "marketing strategy S300" defines the marketing strategy based on the information obtained in the "knowledge acquisition S100". The marketing strategy mainly includes "expert strategy S310" and "intelligent strategy S320". The "expert strategy S310" is that the business personnel specify customers with specific characteristics based on experience or tasks specified by the upper level, and then market products with specified characteristics or specify a certain product. For example, the Tianlibao net value financial product is marketed to customers whose current balance is greater than 10% of the total assets and whose current balance is greater than 500,000. The "intelligent strategy S320" is based on the data obtained in the "knowledge acquisition S100", according to the combination index, using the sampling data of the currently held products, using the decision tree to obtain the characteristic variables, and verifying the model based on the retained samples. After selecting the final characteristic variables, the decision tree is used to calculate the customers who do not hold the product based on the latest characteristic variables, and obtain the high-scoring customers to define the marketing strategy to recommend the product. The successful marketing rate of the recommended customers is regularly counted, and the characteristic variables are readjusted or the model with a low success rate is exited. The marketing plan defined in “Marketing Strategy S300”, i.e. the relationship between customer recommended products, is converted into a triple structure.

[0137] In this embodiment, it is necessary to regularly count the successful marketing rate for the recommended customers, and readjust the feature variables or exit the model with a low success rate.

[0138] In this application, the knowledge graph of banking financial products is a huge relationship network formed by combining customer information, product information, relationship information, model information, and reasoning information through the above process, providing the ability to analyze problems from multiple dimensions and deeply explore the value behind the data.

[0139] like Figure 7 As shown, the "knowledge application S500" combines customer information, product information, relationship information, model information, and reasoning information through the above process to form a huge relationship network, providing the ability to analyze problems from multiple dimensions and deeply digging into the value behind the data. The present invention mainly provides three dimensions to intuitively display the knowledge graph to the account manager. They are "customer information penetration query S510", "product marketing penetration query S520", "product interconnection penetration query S530", and "event triggering task query S540".

[0140] like Figure 8As shown, the "customer information penetration query S510" is based on the marketing information penetration knowledge graph, and the account manager can view the information of the knowledge graph according to the customer dimension. The account manager searches for customers through information such as customer number, name, ID number, etc. Clicking on a customer will display the customer's knowledge graph information, which will display some basic information of the customer, information on products held, information on signed agreements, consumption analysis information, family member information, recommended products, etc. By penetrating layer by layer, the account manager can grasp all the real characteristic relationships that match the customer, laying a very important knowledge foundation for the account manager to find marketing opportunities.

[0141] like Fig. 9 As shown, the "product marketing penetration query S520" is the information of the knowledge graph viewed by the account manager based on the product dimension. The account manager searches for the product of interest through information such as product number, product name or product attributes, and clicks on the product to display the knowledge graph information related to the product, and displays the relevant basic information of the product, such as product name, product number, product type, risk level, and yield rate in the last 7 days. In addition, product recommendation information is obtained from the knowledge graph based on the marketing information penetration, and the knowledge of the customers who are compatible with the product and the relationship between the customers is displayed. This transaction is mainly to meet the scenarios such as the account manager's marketing of the main product. For example, if the marketing of a fund is very popular and there is only a short opening period of a few days, the account manager will promote the fund product during the subscription period of the newly issued fund, and through this transaction, the fund will be marketed to customers who are compatible with the product.

[0142] Those skilled in the art will appreciate that the above embodiments can be summarized as follows: the bank financial product recommendation information includes: product type, risk level, and yield rate in the last 7 days;

[0143] The recommending a bank financial product to the customer to be recommended according to the bank financial product recommendation information includes:

[0144] Match financial products based on product type, risk level and yield in the last 7 days.

[0145] like Fig.10 As shown, the "product interconnection penetration query S530" allows the account manager to grasp the product information and similar features of the product more quickly, so as to quickly find similar products or better products for customers, respond to customers quickly, better improve customers' perception of account managers, reflect the professional level of account managers, and provide customers with better and more professional service levels.

[0146] In some embodiments, the custom inference rules may be dynamically changed in response to a set event trigger.

[0147] Specifically, the above-mentioned set events refer to the customer's product expiration event, the customer's large amount of funds deposited into the account event, the customer's birthday event, etc. Through events, combined with the above-mentioned various knowledge graphs, the account manager can grasp the real-time dynamics of the customer, create the best marketing opportunities, and let the customer have an exclusive service experience of caring service, thereby improving the service level.

[0148] Therefore, in summary, it can be seen from the above technical solutions that the bank financial marketing recommendation method provided by this application breaks the isolated data, realizes the interconnection of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, and providing various visual marketing views to help account managers grasp the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that this application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

[0149] Furthermore, in order to break the isolated data and realize the interconnection and interoperability of data, the bank's data is connected in series, and the implicit relationships are explored through continuous penetration in various related information. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, customer information, product information, marketing strategies and other data are associated with knowledge through customer-centricity to form a marketing knowledge graph, provide multi-perspective analysis capabilities, and provide various visual marketing views to help account managers understand the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality. The present application provides an embodiment of a bank financial marketing recommendation device, see Fig.14 The bank financial marketing recommendation device specifically includes the following contents:

[0150] The acquisition module 10 acquires the identity information of the customer to be recommended.

[0151] It can be understood that the identity information of the customer to be recommended can be understood as the unique identification information of the customer to be recommended, which can be internal identification information within the bank, such as a multi-digit letter code or a digital code, and further can be a hash value. The identity information can also be the customer's public ID, such as an identity card, social security card, etc., but the present application is not limited to this.

[0152] The recommendation information generation module 20 generates bank financial product recommendation information according to the identity information and a preset bank financial product knowledge graph.

[0153] The recommendation module 30 recommends bank financial products to the customer to be recommended according to the bank financial product recommendation information; wherein:

[0154] The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities.

[0155] In some embodiments, the interpersonal relationship may be a relationship between colleagues in the same company, or a relationship between family members. The relationship between family members is used as an example for explanation below, and it is understandable that for other interpersonal relationships, similar concepts can be used for recommendation.

[0156] It can be understood that within the banking system, the customer identity information can be associated with all corresponding reserved information, and the reserved information can be considered as the customer information corresponding to the customer identity information. For example, Figure 3 As shown, the "customer information S110" mainly includes "basic information S111", "family information S112" (entities that constitute the interpersonal relationship between family members), "financial products held S113", "financial agreements signed S114", "financial product transaction details S115", and "consumption information S116", which will not be elaborated here.

[0157] In this embodiment, the bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management association relationship between the customer entity and the customer-subscribed financial agreement entity, and the association relationship between the customer entity and the transaction information entity; the generation module, such as Fig.15 ,include:

[0158] A query unit 21 queries the bank financial product knowledge graph according to the identity information to obtain a customer entity corresponding to the identity information, as well as a corresponding bank account information entity, a customer-subscribed financial agreement entity, and a transaction information entity;

[0159] A family member acquisition unit 22 acquires, according to the interpersonal association relationship in the bank financial product knowledge graph, bank account information entities, customer-subscribed financial agreement entities, and transaction information entities corresponding to other customer entities in the same family as the customer;

[0160] The generation unit 23 generates the bank financial product recommendation information based on the inference engine and the custom inference rules, combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer.

[0161] Through the above embodiments, using technologies such as knowledge reasoning, a huge marketing knowledge graph is established, and the ability of multi-dimensional perspective analysis is provided, providing various visual marketing views, helping account managers to understand the characteristics and relationships between customers and products, allowing account managers to better serve customers and improve marketing quality. This allows account managers to give full play to their inherent value, further enhance the image of the company, and allow the company to further enhance its competitiveness among peers.

[0162] In this application, knowledge graph and knowledge reasoning are combined. Reasoning is to obtain new knowledge or conclusions through various methods. These knowledge and conclusions meet the semantics. Its specific tasks can be divided into satisfiability, classification, and materialization.

[0163] It can be understood that the satisfiability in reasoning can be reflected in ontology or concept. Ontology, ontology satisfiability is to check whether an ontology is satisfiable, that is, to check whether the ontology has a model. If the ontology is not satisfied, it means that there is an inconsistency. Concept satisfiability is to check the satisfiability of a concept, that is, to check whether there is a model so that the explanation for the concept is not an empty set.

[0164] It can be understood that the reasoning engine in the present application can control the execution of the system, including pattern matching (matching the facts in the fact set with the conditional part of the rule, the rules whose entire LHS are satisfied are triggered and added to the agenda), conflict resolution (selecting one from the multiple triggered rules according to a certain strategy), and action execution (executing the RHS of the selected rule, thereby performing certain operations on the WM).

[0165] Specifically, the inference engine may use at least one of the following tools:

[0166] Drools:

[0167] Drools is a commercial rule management system that provides a rule inference engine. Its core algorithm is an improvement on the RETE algorithm. It provides a rule definition language and supports embedding Java code.

[0168] Jena:

[0169] Jena is a Java framework for building semantic web applications. It provides interfaces for processing RDF, RDFs, and OWL data, as well as a rule engine. It provides memory storage and query of triples.

[0170] RDF4J:

[0171] RDF4J is an open source framework for processing RDF data, supporting the parsing, storage, reasoning, and querying of semantic data. It can be associated with almost all RDF storage systems and can be used to access remote RDF storage.

[0172] In the above-mentioned embodiments of the present invention, it can be known that the above-mentioned triples adopt the jena tool. However, those skilled in the art understand that the core concept of the present invention is not to adopt what kind of reasoning engine, but to adopt the technology of the reasoning engine to solve the technical problem of the present invention. Therefore, the present invention can be appropriately adjusted for the use of other tools, which will not be elaborated here.

[0173] The generating unit, such as Fig.16 include:

[0174] The calling unit 221 calls the Java API of the Jena reasoning engine to construct a triple according to the bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer;

[0175] The interaction unit 222 interacts the custom inference rules with the inference engine through the Java API of Jena, and starts the inference engine through the Java API of Jena, thereby enabling the Jena engine to traverse all triples and perform inference operations according to the custom inference rules to generate the bank financial product recommendation information.

[0176] Through the above embodiments, using technologies such as knowledge reasoning, a huge marketing knowledge graph is established, and the ability of multi-dimensional perspective analysis is provided, providing various visual marketing views, helping account managers to understand the characteristics and relationships between customers and products, allowing account managers to better serve customers and improve marketing quality. This allows account managers to give full play to their inherent value, further enhance the image of the company, and allow the company to further enhance its competitiveness among peers.

[0177] It can be understood that in specific implementation, the acquired knowledge can be organized and converted into a triple structure, which will not be elaborated here.

[0178] Of course, the triple structure may also be other similar structures, and the present application is not limited to this triple structure.

[0179] In some embodiments, the bank financial product recommendation device of the present invention further includes: an establishment module to establish the bank financial product knowledge graph.

[0180] More preferably, the bank financial product knowledge graph can be constructed in a distributed server cluster.

[0181] In some embodiments, the recommendation of bank financial products can be that business personnel specify customers with specific characteristics based on experience or tasks assigned by the upper level, and then market products with specified characteristics or a specific product. For example, marketing Tianlibao net value financial products to customers whose current balance is greater than 10% of total assets and whose current balance is greater than 500,000.

[0182] Bank financial product recommendations can also be based on acquired data. According to combined indicators, sample data of currently held products are used to obtain feature variables using decision trees, and the model is verified based on retained samples. After the final feature variables are selected, decision trees are used based on the latest feature variables to perform calculations for customers who do not hold the product, and marketing strategies are defined for customers with high scores to recommend the product.

[0183] In some embodiments, the custom inference rules may be dynamically changed in response to a set event trigger.

[0184] Specifically, the above-mentioned set events refer to the customer's product expiration event, the customer's large amount of funds deposited into the account event, the customer's birthday event, etc. Through events, combined with the above-mentioned various knowledge graphs, the account manager can grasp the real-time dynamics of the customer, create the best marketing opportunities, and let the customer have an exclusive service experience of caring service, thereby improving the service level.

[0185] The bank's financial product recommendation information, including: product type, risk level, and yield rate in the last 7 days;

[0186] The recommendation module is specifically used to match financial products according to the product type, risk level and yield in the last 7 days.

[0187] The device is triggered in response to an event that a financial product of a customer expires, an event that a large amount of funds is deposited into the customer's account, and an event that the customer's birthday occurs.

[0188] It can be seen from the above technical solution that the bank financial marketing recommendation device provided by this application breaks the isolated data, realizes the interconnection of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing the knowledge graph, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategy and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, providing various visual marketing views, helping account managers to grasp the characteristics and associations between customers and products, allowing account managers to better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that this application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

[0189] From the hardware level, in order to break the isolated data and realize the interconnection of data, the bank's data is connected in series, and various related information is continuously penetrated to explore implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, customer information, product information, marketing strategies and other data are associated with knowledge through customer-centricity to form a marketing knowledge graph, provide multi-perspective analysis capabilities, and provide various visual marketing views to help account managers understand the characteristics and associations between customers and products, so that account managers can better serve customers and improve marketing quality. This application provides an embodiment of an electronic device for implementing all or part of the content of the bank financial marketing recommendation method, and the electronic device specifically includes the following content:

[0190] Fig.17 Schematic block diagram of the device structure of the electronic device 9600 according to an embodiment of the present application. Fig.17 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.17 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0191] In one embodiment, the banking and financial marketing recommendation function may be integrated into the central processing unit. The central processing unit may be configured to perform the following control:

[0192] Step 101: Obtain identity information of the customer to be recommended.

[0193] It can be understood that the identity information of the customer to be recommended can be understood as the unique identification information of the customer to be recommended, which can be internal identification information within the bank, such as a multi-digit letter code or a digital code, and further can be a hash value. The identity information can also be the customer's public ID, such as an identity card, social security card, etc., but the present application is not limited to this.

[0194] Step 102: Generate banking financial product recommendation information based on the identity information and a preset banking financial product knowledge graph.

[0195] The bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management relationship between the customer entity and the financial agreement entity that the customer has subscribed to, and the association relationship between the customer entity and the transaction information entity.

[0196] Step 103: Recommend bank financial products to the customer to be recommended based on the bank financial product recommendation information.

[0197] It can be seen from the above technical solutions that the electronic device provided by this application breaks the isolated data, realizes the interconnection and interoperability of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, and providing various visual marketing views to help account managers grasp the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that this application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

[0198] In another embodiment, the bank financial marketing recommendation device may be configured separately from the central processor 9100. For example, the bank financial marketing recommendation device may be a chip connected to the central processor 9100, and the bank financial marketing recommendation function may be implemented through the control of the central processor.

[0199] like Fig.17 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.17 In addition, the electronic device 9600 may also include Fig.17 For components not shown, reference may be made to the prior art.

[0200] like Fig.17 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of various components of the electronic device 9600.

[0201] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0202] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0203] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0204] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0205] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0206] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0207] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the bank financial marketing recommendation method in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps of the bank financial marketing recommendation method in the above embodiments are implemented by the execution subject being a bank financial marketing recommendation device or a client. For example, when the processor executes the computer program, the following steps are implemented:

[0208] Step 101: Obtain identity information of the customer to be recommended.

[0209] It can be understood that the identity information of the customer to be recommended can be understood as the unique identification information of the customer to be recommended, which can be internal identification information within the bank, such as a multi-digit letter code or a digital code, and further can be a hash value. The identity information can also be the customer's public ID, such as an identity card, social security card, etc., but the present application is not limited to this.

[0210] Step 102: Generate banking financial product recommendation information based on the identity information and a preset banking financial product knowledge graph.

[0211] The bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management relationship between the customer entity and the financial agreement entity that the customer has subscribed to, and the association relationship between the customer entity and the transaction information entity.

[0212] Step 103: Recommend bank financial products to the customer to be recommended based on the bank financial product recommendation information.

[0213] It can be seen from the above technical solution that the computer storage medium provided by this application breaks the isolated data, realizes the interconnection and interoperability of data, connects the bank's data in series, continuously penetrates various related information, and mines implicit relationships. By utilizing knowledge graphs, with the help of knowledge analysis, graph construction, knowledge reasoning, graph storage, graph calculation and other knowledge graph technologies, through customer-centricity, customer information, product information, marketing strategies and other data are associated with knowledge to form a marketing knowledge graph, providing multi-perspective analysis capabilities, and providing various visual marketing views to help account managers grasp the characteristics and relationships between customers and products, so that account managers can better serve customers and improve marketing quality; at the same time, the knowledge graph includes customer entities and interpersonal relationships between each customer entity, so that this application can provide product recommendations based on family members and personal connections based on interpersonal relationships, greatly improving the success rate of financial product processing.

[0214] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0215] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0216] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0217] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0218] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A banking financial marketing recommendation method, characterized in that: include: Obtain the identity information of the customer to be recommended; Generate banking financial product recommendation information based on the identity information and a preset banking financial product knowledge graph; Recommend bank financial products to the customer to be recommended according to the bank financial product recommendation information; wherein, The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities; The bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management association relationship between the customer entity and the customer's subscribed financial agreement entity, and the association relationship between the customer entity and the transaction information entity; The generating of bank financial product recommendation information according to the identity information and the preset bank financial product knowledge graph includes: Query the bank financial product knowledge graph according to the identity information to obtain the customer entity corresponding to the identity information, as well as the corresponding bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity; According to the interpersonal association relationship in the bank financial product knowledge graph, obtain the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to other customer entities in the same family as the customer; Generate the bank financial product recommendation information based on the inference engine and the custom inference rules, combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer; Establishing the bank financial product knowledge graph includes: knowledge acquisition, knowledge integration, marketing strategy, knowledge processing and knowledge application; wherein, the knowledge acquisition includes the extraction of basic data, specifically including customer information and product information; the knowledge integration includes organizing the acquired knowledge and converting it into a triple structure; the marketing strategy includes defining a marketing strategy based on the information acquired in the knowledge acquisition; the knowledge processing is to use the triple structure, use the inference engine to perform ontology reasoning, and save the reasoning results in the graph database; the knowledge application is to combine customer information, product information, association relationship information, and reasoning results to form the bank financial product knowledge graph; The bank financial product recommendation information is generated based on the inference engine and the custom inference rules, combining the bank account information entity, the customer-subscribed financial agreement entity and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer, including: Calling the Java API of the Jena inference engine to construct triples according to the bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer; The custom inference rules interact with the inference engine through Jena's Java API, and the inference engine is started through Jena's Java API, so that the Jena engine traverses all triples and performs inference operations according to the custom inference rules to generate the bank financial product recommendation information.

2. The banking financial marketing recommendation method according to claim 1, characterized in that: The custom inference rules may be dynamically changed in response to set event triggers.

3. The banking financial marketing recommendation method according to claim 1, characterized in that: The bank's financial product recommendation information, including: product type, risk level, and yield rate in the last 7 days; The recommending a bank financial product to the customer to be recommended according to the bank financial product recommendation information includes: Match financial products based on product type, risk level and yield in the last 7 days.

4. The banking financial marketing recommendation method according to claim 3, characterized in that: The method is triggered in response to an event that a financial product of a customer expires, an event that a large amount of funds is deposited into the customer's account, and an event that the customer's birthday occurs.

5. A banking financial marketing recommendation device, characterized in that: include: Acquisition module, to obtain the identity information of the customer to be recommended; A recommendation information generation module generates recommendation information of bank financial products according to the identity information and a preset bank financial product knowledge graph; The recommendation module recommends bank financial products to the customer to be recommended according to the bank financial product recommendation information; wherein: The bank financial product knowledge graph includes customer entities and interpersonal relationships between customer entities; The bank financial product knowledge graph also includes: the association relationship between the customer entity and the bank account information entity, the management association relationship between the customer entity and the customer-subscribed financial agreement entity, and the association relationship between the customer entity and the transaction information entity; the generation module includes: A query unit, which queries the bank financial product knowledge graph according to the identity information to obtain a customer entity corresponding to the identity information, as well as a corresponding bank account information entity, a customer-subscribed financial agreement entity, and a transaction information entity; A family member acquisition unit, which acquires, according to the interpersonal association relationship in the bank financial product knowledge graph, bank account information entities, customer-subscribed financial agreement entities, and transaction information entities corresponding to other customer entities in the same family as the customer; A generating unit, based on an inference engine and a custom inference rule, generates the bank financial product recommendation information by combining the bank account information entity, the customer-subscribed financial agreement entity, and the transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer; Also includes: Establish a module to establish the bank financial product knowledge graph; The establishment module is specifically used for knowledge acquisition, knowledge integration, marketing strategy, knowledge processing and knowledge application; wherein, the knowledge acquisition includes the extraction of basic data, specifically including customer information and product information; the knowledge integration includes organizing the acquired knowledge and converting it into a triple structure; the marketing strategy includes defining a marketing strategy based on the information acquired in the knowledge acquisition; the knowledge processing is to use the triple structure, use the inference engine to perform ontology reasoning, and save the reasoning results in the graph database; the knowledge application is to combine customer information, product information, association relationship information, and reasoning results to form the bank financial product knowledge graph; The generating unit comprises: A calling unit calls a Java API of a Jena reasoning engine to construct a triple according to a bank account information entity, a customer-subscribed financial agreement entity, and a transaction information entity corresponding to the customer entity and other customer entities in the same family as the customer; The interaction unit interacts the custom inference rules with the inference engine through the Java API of Jena, and starts the inference engine through the Java API of Jena, thereby enabling the Jena engine to traverse all triples, and perform inference operations according to the custom inference rules to generate the bank financial product recommendation information.

6. The banking and financial marketing recommendation device according to claim 5, characterized in that: The custom inference rules may be dynamically changed in response to set event triggers.

7. The banking and financial marketing recommendation device according to claim 5, characterized in that: The bank's financial product recommendation information, including: product type, risk level, and yield rate in the last 7 days; The recommendation module is specifically used to match financial products according to the product type, risk level and yield in the last 7 days.

8. The banking and financial marketing recommendation device according to claim 7, characterized in that: The device is triggered in response to an event that a financial product of a customer expires, an event that a large amount of funds is deposited into the customer's account, and an event that the customer's birthday occurs.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the bank financial marketing recommendation method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the bank financial marketing recommendation method described in any one of claims 1 to 4 is implemented.

Images