Financial product pushing method and device, electronic equipment and storage medium

Abstract

The invention discloses a financial product pushing method and device, electronic equipment and a storage medium, and relates to the field of financial science and technology or other related fields, and the method comprises the steps: analyzing a pushing demand of a target financial product, and obtaining a target enterprise of the pushing; related enterprises of the target enterprise are inquired in a target knowledge graph, a related enterprise list is obtained, and the target knowledge graph records all enterprise customers of the financial institution and enterprise association relationships; analyzing the associated enterprise list based on the target knowledge graph to obtain M product pushing paths, M being a positive integer; and pushing the target financial product based on the M product pushing paths. Through the method and the device, the technical problem of low financial product pushing accuracy in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology or other related fields, and in particular to a method for pushing financial products and a device, electronic device, and storage medium thereof. Background Art

[0002] Financial products are financial tools or services provided by financial institutions to their customers. They are the main source of profits for financial institutions. The precise push of financial products is the basis for the precise push of financial institutions. Through precise push, the precise push of financial products can be achieved, the income of financial institutions can be increased, and the push cost of financial institutions can be reduced. At present, financial institutions usually have their own product information databases. Financial institutions analyze the product information database to determine the push demand of target financial products, and then accurately push the target financial products according to the push demand. However, this method requires financial institutions to analyze a large amount of data in the product information database, which is complicated to operate, and the push efficiency is low and the push accuracy is not high.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The main purpose of this application is to provide a method for pushing financial products and its device, electronic device, and storage medium, so as to at least solve the technical problem of low accuracy in pushing financial products in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for pushing financial products is provided, the method comprising: analyzing the push demand of the target financial product to obtain the target enterprise for this push; querying the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate relationships; analyzing the list of associated enterprises based on the target knowledge graph to obtain M product push paths, wherein M is a positive integer; and pushing the target financial product based on the M product push paths.

[0006] Furthermore, the step of analyzing the push demand of the target financial product and obtaining the target enterprise for this push includes: analyzing the push demand to obtain product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; querying the customer resource library of the financial institution based on the product attribute information to obtain query results, wherein the query results are used to record enterprise attribute information that matches the product attribute information; determining the target enterprise for this push based on the enterprise attribute information indicated by the query result.

[0007] Furthermore, the step of querying the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises includes: determining the target node corresponding to the target enterprise in the target knowledge graph, and determining R associated nodes of the target node, wherein R is a positive integer; determining the enterprise customer represented by each of the associated nodes to obtain all associated enterprises of the target enterprise; and generating a list of associated enterprises based on all the associated enterprises, wherein the list of associated enterprises at least includes the enterprise name of each of the associated enterprises.

[0008] Furthermore, the step of analyzing the associated enterprise list based on the target knowledge graph to obtain M product push paths includes: for each of the associated enterprises in the associated enterprise list, locating the connection line between the associated node corresponding to the associated enterprise and the target node in the target knowledge graph; analyzing the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; and generating M product push paths based on the association information and the connection line.

[0009] Furthermore, the step of analyzing the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information includes: analyzing the connection line in the target knowledge graph to obtain the association type of the enterprise association relationship represented by the connection line, wherein the association type includes: equity association, supply association and transaction association; and obtaining the association information between the associated enterprise and the target enterprise based on the association type.

[0010] Furthermore, the step of obtaining the association information between the associated enterprise and the target enterprise based on the association type includes: when the association type is equity association, obtaining the equity association information between the associated enterprise and the target enterprise, wherein the equity association information includes: shareholding role and shareholding ratio; when the association type is supply association, obtaining the supply association information between the associated enterprise and the target enterprise, wherein the supply association information includes: supply role and supply cycle; when the association type is transaction association, obtaining the transaction association information between the associated enterprise and the target enterprise, wherein the transaction association information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

[0011] Furthermore, the step of generating M product push paths based on the association information and the connecting lines includes: obtaining an association analysis rule, wherein the association analysis rule is used to record N preset association information and a score value corresponding to each preset association information, and N is a positive integer; based on the association analysis rule and the association information, calculating the association score of each association node to obtain R association scores; based on the R association scores, determining M push nodes among the R association nodes; for each push node, generating the product push path based on the connecting line corresponding to the push node.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a financial product push device is also provided, which includes: a first analysis unit, used to analyze the push demand of the target financial product and obtain the target enterprise for this push; a query unit, used to query the associated enterprises of the target enterprise in the target knowledge graph and obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of financial institutions and corporate associations; a second analysis unit, used to analyze the list of associated enterprises based on the target knowledge graph and obtain M product push paths, wherein M is a positive integer; a push unit, used to push the target financial product based on the M product push paths.

[0013] Furthermore, the first analysis unit includes: a first analysis module, used to analyze the push demand and obtain product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; a query module, used to query the customer resource library of the financial institution based on the product attribute information and obtain query results, wherein the query results are used to record enterprise attribute information that matches the product attribute information; a first determination module, used to determine the target enterprise for this push based on the enterprise attribute information indicated by the query result.

[0014] Furthermore, the query unit includes: a second determination module, used to determine the target node corresponding to the target enterprise in the target knowledge graph, and determine R associated nodes of the target node, wherein R is a positive integer; a third determination module, used to determine the enterprise customer represented by each of the associated nodes, and obtain all associated enterprises of the target enterprise; a first generation module, used to generate an associated enterprise list based on all the associated enterprises, wherein the associated enterprise list contains at least the enterprise name of each of the associated enterprises.

[0015] Furthermore, the second analysis unit includes: a positioning module, used to locate, in the target knowledge graph, for each of the associated enterprises in the associated enterprise list, a connection line between the associated node corresponding to the associated enterprise and the target node; a second analysis module, used to analyze the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; and a second generation module, used to generate M product push paths based on the association information and the connection line.

[0016] Furthermore, the second analysis module includes: an analysis submodule, used to analyze the connection lines in the target knowledge graph to obtain the association type of the enterprise relationship represented by the connection lines, wherein the association type includes: equity association, supply association and transaction association; a first acquisition submodule, used to obtain the association information between the associated enterprise and the target enterprise based on the association type.

[0017] Furthermore, the second analysis module also includes: a second acquisition submodule, which is used to obtain the equity relationship information between the associated enterprise and the target enterprise when the association type is equity relationship, wherein the equity relationship information includes: shareholding role and shareholding ratio; a third acquisition submodule, which is used to obtain the supply relationship information between the associated enterprise and the target enterprise when the association type is supply relationship, wherein the supply relationship information includes: supply role and supply cycle; a fourth acquisition submodule, which is used to obtain the transaction relationship information between the associated enterprise and the target enterprise when the association type is transaction relationship, wherein the transaction relationship information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

[0018] Furthermore, the second generation module includes: a fifth acquisition submodule, used to acquire association analysis rules, wherein the association analysis rules are used to record N preset association information and a score value corresponding to each preset association information, and N is a positive integer; a calculation submodule, used to calculate the association score of each of the association nodes based on the association analysis rules and the association information, and obtain R association scores; a determination submodule, used to determine M push nodes among the R association nodes based on the R association scores; and a generation submodule, used to generate the product push path for each of the push nodes based on the connection line corresponding to the push node.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for pushing financial products.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is also provided, including one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the financial product push method described in any one of the above-mentioned items.

[0021] The present invention proposes a method for pushing financial products. First, the push demand of the target financial product is analyzed to obtain the target enterprise for this push. Then, the associated enterprises of the target enterprise are queried in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations. Then, the list of associated enterprises is analyzed based on the target knowledge graph to obtain M product push paths, wherein M is a positive integer. Finally, the target financial product is pushed based on the M product push paths.

[0022] In the present invention, the method of knowledge graph analysis is adopted, and the purpose of accurately locating the target enterprise and its related network is achieved by means of deep related enterprise relationship mining, thereby realizing the technical effect of personalized and intelligent push of financial products. Specifically, the present invention first analyzes the characteristics of the target financial product and customer needs to determine the target enterprise; then uses the constructed financial institution corporate customer knowledge graph to query the related enterprises of the target enterprise to form a relationship network; then based on the graph analysis algorithm, the list of related enterprises is analyzed to generate multiple product push paths with high correlation; finally, the push of financial products is implemented according to these paths, which improves the pertinence and success rate of the push, thereby solving the technical problem of low accuracy of financial product push in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for pushing financial products is shown;

[0025] Figure 2 is a flow chart of an optional method for pushing financial products according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of an optional device for pushing financial products according to an embodiment of the present invention;

[0027] Figure 4The present invention is a structural block diagram of an electronic device for executing a method for pushing financial products according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the method and device for pushing financial products in this application can be used in the field of financial technology to accurately push products to corporate customers of financial institutions, and can also be used in any field other than the field of financial technology to accurately push products to corporate customers of financial institutions. The application does not limit the application field of the method and device for pushing financial products in this application.

[0031] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, processing, transmission, provision, disclosure, use and processing of the relevant data comply with the laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0032] The information collection (for example, user voice, video, and text collection) and analysis operations involved in this application have provided users with corresponding operation entrances when they are executed, allowing users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0033] The following embodiments of the present invention can be applied to various systems / applications / devices that require accurate push of financial products and customer relationship management, and can realize intelligent and customized push of financial products. The present invention uses knowledge graphs to construct and analyze enterprise relationship networks, and then determines the optimal product push path based on this network, which can better understand and meet the financial needs of target enterprises, improve push efficiency and customer satisfaction.

[0034] The present invention is described in detail below in conjunction with various embodiments.

[0035] Embodiment 1

[0036] According to an embodiment of the present invention, an embodiment of a method for pushing financial products is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] The method for pushing financial products provided in the first embodiment of the present invention may be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for pushing financial products is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0038] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0039] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method for pushing financial products in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for pushing financial products described above is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0040] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0042] Under the above operating environment, the present invention provides Figure 2The push method of financial products shown in the figure is implemented by an intimate push recommendation system, which combines knowledge graph technology and is used in the scenario of precise push of financial products, especially for the problems of product homogeneity and single push path. By analyzing the enterprise association relationship and intelligently generating push paths, the accuracy and success rate of financial product push can be improved to meet the purpose of personalized service needs of enterprises.

[0043] The embodiment of the present invention is described in detail below in conjunction with various specific steps.

[0044] Figure 2 is a flow chart of an optional method for pushing financial products according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0045] Step S201, analyzing the push demand of the target financial product, and obtaining the target enterprise for this push.

[0046] Specifically, target financial products refer to specific financial products that financial institutions want to promote or sell, such as corporate loans, financial management services, letter of credit services, etc., which have specific market positioning and target customer groups.

[0047] Push demand refers to the specific requirements for the marketing of financial products under a specific push strategy, including but not limited to: the purpose of product promotion (such as increasing market share, improving customer satisfaction), identification criteria for target customer groups (such as industry type, enterprise size), promotion time window (such as the end of the quarter, before holidays) and expected push effect (such as conversion rate, customer feedback).

[0048] Optionally, step S201 includes: analyzing the push demand to obtain product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; querying the customer resource library of the financial institution based on the product attribute information to obtain query results, wherein the query results are used to record enterprise attribute information that matches the product attribute information; determining the target enterprise for this push based on the enterprise attribute information indicated by the query results.

[0049] It should be noted that product attribute information includes product type, service scope, and customer qualification requirements, etc. Among them, product type defines the category to which the financial product belongs, such as deposit, loan, insurance, or investment and financial management; service scope refers to the service area or industry that the financial product can provide, for example, the product can only serve enterprises in a specific geographical area or a certain industry; customer qualification requirements refer to the conditions that the target customer needs to meet in order to apply for or use the product, such as the company's credit rating, financial status, industry attributes, etc.

[0050] In the step of querying the customer resource library of the financial institution, the customer resource library is a database maintained by the financial institution containing all corporate customer information, including information data such as corporate name, corporate type, industry, geographical region, financial status, credit rating, and business records with the bank. By matching the attributes of the target financial product with the corporate attribute information in the customer resource library, a list of potential target companies that meet the product application conditions can be screened out.

[0051] After attribute matching, the enterprise attribute information will indicate which enterprises meet the specific needs of the target financial product. For example, if the product is positioned to serve technology-based SMEs, then the enterprise attribute information will include enterprises with characteristics such as technology industry classification, small and medium enterprise scale, and good credit. Based on the above information, financial institutions can further analyze and select companies that are most likely to be interested in financial products as target enterprises, thereby improving the pertinence and success rate of push activities.

[0052] In an optional embodiment, it is assumed that the target financial product is a supply chain financing service designed for manufacturing enterprises, with a product type of loan, a service scope covering the whole country, and customer qualification requirements including that the enterprise must have actual production activities in the manufacturing industry, a credit rating of B or above, and an annual turnover of more than 5 million. When conducting push demand analysis, the financial institution first extracts these attribute information, and then searches the customer resource library for information on all manufacturing enterprises for preliminary screening. Next, through further credit evaluation and turnover verification, a group of qualified manufacturing enterprises are finally identified as target enterprises, and push strategies for supply chain financing services are customized for these enterprises to improve the attractiveness of financing services and the actual signing rate.

[0053] Through the above-mentioned precise matching method, financial institutions can effectively improve service quality and market competitiveness, while reducing push costs and improving overall efficiency.

[0054] Step S202, query the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations.

[0055] Specifically, the target knowledge graph is a complex network graph constructed by financial institutions based on all their corporate customers and the various relationships between them. It not only contains basic information about corporate customers, such as company name, industry, size, etc., but more importantly, it records multi-dimensional related data such as equity relationships, supply relationships, and transaction relationships between companies. Through such a graph, financial institutions can intuitively understand and analyze the connections between corporate customers and how these connections affect corporate behavior.

[0056] An affiliated enterprise refers to an enterprise that is connected to the target enterprise through some form of relationship, including equity holding, supply chain cooperation, transaction transactions, joint investment, etc. The existence of affiliated enterprises can help financial institutions understand the ecological network and business environment of the target enterprise more comprehensively, and provide a basis for the formulation of financial product recommendations and push strategies.

[0057] Enterprise relationships are the connections or ties between enterprises. These relationships are represented by lines between nodes in the target knowledge graph. Specifically:

[0058] 1. Equity relations, which reflect the ownership or control structure between enterprises, such as holding companies, controlled companies, sister companies in the same group, sister companies with the same holding, subsidiaries, etc.

[0059] 2. Supply relationship, which describes the supplier and customer relationship between enterprises, including transactions between an enterprise as a supplier or customer and its affiliated enterprises.

[0060] 3. Transaction relationship, recording direct transaction activities between enterprises, including transaction amount, frequency, cycle, etc.

[0061] Optionally, step S202 includes: determining a target node corresponding to a target enterprise in a target knowledge graph, and determining R associated nodes of the target node, where R is a positive integer; determining the enterprise customer represented by each associated node, and obtaining all associated enterprises of the target enterprise; and generating an associated enterprise list based on all associated enterprises, wherein the associated enterprise list contains at least the enterprise name of each associated enterprise.

[0062] It should be noted that determining the target node corresponding to the target enterprise in the target knowledge graph means finding a unique node representing the target enterprise in the node set of the graph, which contains all relevant information about the target enterprise and its association with other nodes; the step of determining the associated nodes of the target node involves analyzing the relationship type and strength between the target node and other nodes, and selecting R most relevant nodes, where the value of R can be determined based on different analysis needs and graph scales; determining the corporate customer represented by each associated node means extracting the corresponding entity information from the associated node, that is, corporate customers that have a direct or indirect relationship with the target enterprise; generating a list of associated enterprises means organizing the extracted corporate customer information into a list form, including the name of each associated enterprise, and other key attributes such as industry, scale, and equity holding ratio.

[0063] In an optional implementation, taking a large financial institution as an example, assuming that the target enterprise is enterprise C, the bank first locates the node of enterprise C in the target knowledge graph, and then uses the graph analysis algorithm to find other enterprise nodes that are directly or indirectly related to enterprise C. For example, enterprise C is connected with enterprises A and B through equity relations, is related to enterprises D and E through supply relations, and has dealings with enterprises F and G through transaction relations. After determining these related nodes, the bank further analyzes the specific information of each related node and identifies that A and B, who have equity relations with enterprise C, are its important shareholders; enterprises D and E are its stable suppliers and customers, and enterprises F and G are its frequent trading partners. This information is organized into a list of related enterprises, which includes not only the names of the enterprises, but also more detailed descriptions of the related relationships and related scores (such as equity holding ratios, transaction amounts, etc.).

[0064] Financial institutions can then further analyze the business environment and potential needs of Company C based on this list of related companies. For example, if Company C's shareholders, Companies A and B, have previously used supply chain financing services, then financial institutions can infer that Company C may also have similar needs, and thus recommend supply chain financing as one of the key financial products.

[0065] In addition, through the analysis of the supply chain cooperation between enterprises D and E, financial institutions can recognize that enterprise C plays an important role in the supply chain of a specific industry, which may prompt financial institutions to provide financial products tailored to the characteristics of the industry, such as industry loans or specific supply chain financial services. Similarly, through the transactions between enterprises F and G, financial institutions can understand the business scope and business model of enterprise C, and thus more specifically recommend financial products suitable for its business needs, such as trade financing, accounts receivable financing, etc.

[0066] Through the above steps, financial institutions can not only improve the accuracy of financial product push, but also enhance business cooperation with Enterprise C and improve customer experience and satisfaction.

[0067] Step S203: Analyze the list of related enterprises based on the target knowledge graph to obtain M product push paths, where M is a positive integer.

[0068] Specifically, the product push path refers to a series of strategies or channels that can be used to promote financial products from related enterprises to target enterprises, determined by analyzing the association relationships between enterprises. In the present invention, M product push paths are generated through the enterprise association information in the target knowledge graph, aiming to find the path that is most likely to prompt the target enterprise to accept the financial product recommendation, thereby improving the conversion rate and success rate of the push activity.

[0069] Optionally, step S203 includes: for each associated enterprise in the associated enterprise list, locating the connection line between the associated node corresponding to the associated enterprise and the target node in the target knowledge graph; analyzing the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; and generating M product push paths based on the association information and the connection line.

[0070] It should be noted that in the target knowledge graph, financial institutions first need to find the nodes corresponding to each enterprise in the list of related enterprises, and determine the connecting lines between these nodes and the target nodes. These connecting lines represent the types of relationships between enterprises, such as equity relationships, supply relationships, transaction relationships, etc.

[0071] For example, consider enterprise C as the target enterprise, and its list of associated enterprises includes A, B, D, E, F, G, etc. The bank finds the node of enterprise C in the knowledge graph, and then uses the graph algorithm to find the connection lines between A, B, D, E, F, G and C, that is, the specific relationship between them and C.

[0072] Furthermore, the step of analyzing the corporate affiliations between the associated companies and the target company to obtain the affiliation information involves an in-depth analysis of the affiliations represented by the connecting lines to extract key information of the associated companies, such as equity holding ratio, supply frequency, transaction amount, etc., which evaluate the strength of the affiliation and infer potential financial needs.

[0073] For example, if Company A holds 0.9 of the equity of Company C, it can get 2 points according to the equity relationship scoring rules. Company D is a supplier of Company C and has had supply transactions in the past two years. According to the supply relationship scoring rules, it can get 8 points. Company G is a trading counterparty of Company C and ranks in the top 5 in terms of transaction frequency in the past year. According to the transaction relationship scoring rules, it can get 3 points.

[0074] Furthermore, in the step of generating M product push paths based on associated information and connecting lines, combined with the associated information and relationship types of associated enterprises, the financial institution can generate multiple product push paths, where M represents the number of recommended paths, which is used to guide push activities and recommend financial products to target enterprises through the most relevant associated enterprises, in order to obtain higher acceptance and conversion rates.

[0075] For example, assuming that enterprise C has a strong equity relationship with A, a stable supply relationship with D, and frequent transactions with G, the financial institution can generate the following three product push paths.

[0076] Path 1: Recommend equity financing services to Company C through Company A, take advantage of the equity relationship between them, emphasize the benefits of equity financing for financial structure optimization and capital operation, and A’s previous success stories.

[0077] Path 2: Recommend supply chain finance products to enterprise C through enterprise D. Based on D's role as a supplier and C's supply chain needs, provide services including accounts receivable financing and procurement financing, emphasizing the positive impact of supply chain financial services on cash flow and supply chain management.

[0078] Path 3: Recommend trade financing or letter of credit services to enterprise C through enterprise G. Given that G is C's counterparty, the value of trade financing in promoting trade activities and reducing transaction risks can be emphasized, as well as G's satisfactory feedback when using similar services.

[0079] Through the above steps, financial institutions can generate and optimize M product push paths for target enterprise C based on the target knowledge graph. Each path makes full use of the information of the most relevant associated enterprises to C to achieve accurate push of financial products and improve customer satisfaction. In addition, the generation of M paths also takes into account the weighted scores of different relationship types, thereby ensuring that the recommended path is not only based on the existence of the associated relationship, but also on the strength of the relationship and the degree of potential financial demand matching. The above strategic product push path generation method can help financial institutions use their customer resources more effectively and improve the pertinence and conversion rate of push activities.

[0080] Optionally, the step of obtaining association information by analyzing the enterprise association relationship between the associated enterprises and the target enterprise based on the connection lines includes: analyzing the connection lines in the target knowledge graph to obtain the association type of the enterprise association relationship represented by the connection lines, wherein the association type includes: equity association, supply association and transaction association; and obtaining the association information between the associated enterprises and the target enterprise based on the association type.

[0081] It should be noted that in the target knowledge graph, the connection lines not only connect the enterprise nodes, but also carry various association information between enterprises. By analyzing these connection lines, financial institutions can gain in-depth understanding of the type and strength of the relationship between the associated enterprises and the target enterprises, which is crucial for formulating effective financial product promotion strategies.

[0082] Equity relationship refers to the connection between enterprises through holding each other's equity. Specifically, equity relationship can be manifested as a direct controlling or controlled relationship, or a brother company relationship between enterprises (that is, they are controlled by the same company).

[0083] Through equity relationship analysis, financial institutions can identify important shareholders or investees of target companies and assess their influence and control over target companies. For example, if an important shareholder of target company C, company A, has previously obtained loan services from the financial institution and has given positive feedback, then the financial institution can recommend loan products to company C based on this equity relationship, emphasizing the success stories and positive reviews of company A.

[0084] Supply relationships describe the cooperative relationship between suppliers and customers. In the financial industry, this relationship is not only reflected in the daily supply of goods or services, but may also extend to the delivery of financial service needs.

[0085] Through supply linkage analysis, financial institutions can determine which companies are the main suppliers or customers of the target company, which usually have a direct or indirect impact on the target company's procurement decisions and business operations. For example, if company D is a long-term supplier of company C, and company D has a good transaction record with the financial institution, then the financial institution can consider promoting supply chain financial services to company C through company D to meet the financial needs of payment, accounts receivable management, etc. between companies C and D.

[0086] Transaction relationships record direct transaction activities between enterprises, including details such as transaction amount, transaction frequency, and transaction cycle.

[0087] Through transaction association analysis, financial institutions can identify which companies the target company has frequent transactions with and the characteristics and patterns of these transactions. For example, if company G has large and frequent transaction records with company C, then company G may be an effective channel for recommending trade financing or credit products to company C to optimize its cash flow management and transaction security.

[0088] In a specific embodiment, assume that there is enterprise C as the target enterprise in the knowledge graph, as well as its associated enterprises A (equity association), D (supply association), and G (transaction association). The financial institution first analyzes the connection lines in the knowledge graph to determine the association types of enterprises A, D, and G associated with enterprise C, which are equity association, supply association, and transaction association, respectively. Next, the financial institution obtains detailed association information based on these association types: enterprise A holds 0.9 of the equity of enterprise C, enterprise D is a long-term supplier of enterprise C, and enterprise G has more than 10 transaction records with enterprise C in the past year, and the transaction amount is large.

[0089] Based on the above-mentioned related information, the financial institution generates the following three product push paths.

[0090] Equity-related path: Recommend equity financing services to Company C through Company A, emphasize the benefits of equity financing for financial structure optimization and capital operation, as well as the success stories and satisfactory feedback of Company A as an important shareholder of Company C.

[0091] Supply-linked path: Recommend supply chain finance products to company C through company D. Based on company D’s role as a supplier of company C, it provides services including accounts receivable financing and procurement financing, emphasizing the positive impact of supply chain financial services on cash flow management.

[0092] Transaction association path: Recommend trade financing or letter of credit services to enterprise C through enterprise G. Given the frequent transaction records between enterprises G and C, the value of trade financing in promoting trade activities and reducing transaction risks can be emphasized, as well as enterprise G’s positive experience in using similar services.

[0093] Through the above steps, financial institutions can not only generate accurate product push paths based on the specific relationship type between target enterprise C and its affiliated enterprises, but also adjust push strategies based on detailed information of the relationship (such as equity ratio, supply frequency, transaction amount, etc.) to improve the success rate of financial product recommendations and customer satisfaction. This strategic product push path generation method effectively utilizes the knowledge graph resources within financial institutions and enhances the intelligence and customization level of push activities.

[0094] Optionally, the step of obtaining association information between the associated enterprise and the target enterprise based on the association type includes: when the association type is equity association, obtaining the equity association information between the associated enterprise and the target enterprise, wherein the equity association information includes: shareholding role and shareholding ratio; when the association type is supply association, obtaining the supply association information between the associated enterprise and the target enterprise, wherein the supply association information includes: supply role and supply cycle; when the association type is transaction association, obtaining the transaction association information between the associated enterprise and the target enterprise, wherein the transaction association information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

[0095] In the target knowledge graph, financial institutions can obtain detailed information on different types of relationships by analyzing the connection lines, i.e., the relationships, between the target enterprise and its affiliated enterprises. This is crucial for building an effective financial product delivery path.

[0096] In the case of equity relationship, the shareholding role refers to the specific role in the equity relationship between the affiliated enterprise and the target enterprise, which can be "shareholder" (i.e. the affiliated enterprise holds the equity of the target enterprise) or "shareholder" (i.e. the target enterprise is held by the affiliated enterprise). The shareholding ratio refers to the amount of equity held by the shareholding role in the target enterprise, expressed as a percentage. The above information is very critical for evaluating the influence of the affiliated enterprise on the target enterprise and the potential equity financing needs.

[0097] For example, if Company X, as a shareholder, holds 0.9 of the equity of Company Y, this means that Company X has strong control over Y and may be one of the important decision makers of Company Y. When recommending financial products, this strong equity connection may indicate that Company Y has a high financing demand, especially equity financing or corporate merger and acquisition loans, because Company X may be interested in helping Company Y optimize its capital structure or expand its business.

[0098] In the case of a supply relationship, the supply role refers to the role played by the associated enterprise in the supply chain relationship with the target enterprise, which can be a "supplier" (i.e. providing goods or services to the target enterprise) or a "customer" (i.e. purchasing goods or services from the target enterprise). The supply cycle reflects the frequency and regularity of transactions between the supply role and the target enterprise, which is crucial for evaluating the demand and applicability of supply chain financial products.

[0099] For example, as a long-term supplier, Enterprise M regularly supplies raw materials to Enterprise N. If the supply cycle is stable, it indicates that the supply chain relationship between Enterprise M and N is solid, and Enterprise M may have a deep understanding of N's procurement model and payment habits. In this case, financial institutions can consider recommending supply chain financial products to N through Enterprise M, such as open account financing or advance payment financing, to meet the liquidity and supply chain management needs of Enterprise N.

[0100] When the association type is transaction association, the transaction amount, transaction frequency, transaction time point and transaction cycle jointly describe the transaction activity characteristics between the target enterprise and the associated enterprise. Among them, the transaction amount reflects the scale of a single transaction; the transaction frequency records the number of transactions that occurred within a certain time window; the transaction time point and transaction cycle respectively indicate the specific time point of the transaction and the cyclical law of the transaction activity, which are of great value for analyzing the stability of the transaction relationship and predicting future transaction needs.

[0101] For example, Enterprise P has conducted transactions with Enterprise Q many times in the past year, and the transaction amount is stable at the million level, and the transaction time points are mainly concentrated at the end of each quarter. This shows that there are frequent and regular transaction activities between P and Q. Based on this information, financial institutions can recommend trade financing or accounts receivable financing related products to Enterprise Q to help it better manage cash flow pressure at the end of the quarter, and provide competitive interest rates or services to attract Enterprise Q to adopt.

[0102] An optional implementation example selects a specific scenario, assuming that enterprise Z is the target enterprise, and it has equity associations, supply associations, and transaction associations with enterprises W, X, and Y in the knowledge graph. Through the query, the financial institution learned that: enterprise W holds 40% of the equity of enterprise Z, indicating that enterprise W has greater control and financial influence on enterprise Z; enterprise X is a long-term supplier of enterprise Z, with a supply cycle of once a month and a stable supply amount, which reflects a stable supply chain relationship; enterprise Y and enterprise Z have more than 20 transaction records in the past year, with an average transaction amount of about 5 million, and the transaction time points are scattered, but the transaction cycle is once every two months on average, showing a regular transaction pattern.

[0103] Based on the above-mentioned related information, financial institutions can develop the following three product push paths for Company Z.

[0104] Equity-related path: Recommend equity financing or corporate M&A loans to company Z through company W, take advantage of the close equity relationship between W and Z, and emphasize how these financial products can help company Z optimize its capital structure or promote business growth.

[0105] Supply association path: Recommend supply chain financial products, such as accounts receivable financing, to company Z through company X. Based on the stable supply cycle between X and Z, a financing plan that meets their supply chain management needs is designed to improve the capital turnover efficiency of company Z.

[0106] Transaction association path: Recommend trade financing services such as letters of credit or bill financing to company Z through company Y. Considering the large and regular transaction cycles between Y and Z, flexible financing options are provided to alleviate cash flow pressure at the end of the quarter or at a specific time point.

[0107] Through the above steps, financial institutions can build accurate product push paths based on the specific association information between target enterprise Z and related enterprises W, X, and Y, thereby improving the pertinence and success rate of financial product recommendations, while also enhancing business relationships and trust with corporate customers. This strategic product push path generation method fully utilizes the deep association analysis capabilities of the target knowledge graph and provides financial institutions with a more intelligent and customized push method.

[0108] Optionally, the step of generating M product push paths based on association information and connection lines includes: obtaining an association analysis rule, wherein the association analysis rule is used to record N preset association information and a score value corresponding to each preset association information, and N is a positive integer; based on the association analysis rule and the association information, calculating the association score of each association node to obtain R association scores; based on the R association scores, determining M push nodes among the R association nodes; for each push node, generating a product push path based on the connection line corresponding to the push node.

[0109] The association analysis rule is a set of scoring systems preset by financial institutions to evaluate the strength and value of corporate associations. It includes multiple preset association information and their corresponding score values, which represent the number of corporate association types considered in the rule. The preset association information refers to the key indicators defined in the association analysis rule for analyzing corporate relationships. The score value is a pre-set value based on the importance of this information, which is used for weighting when calculating the association.

[0110] For example, equity-related information: shareholding ratio; supply-related information: annual supply times; transaction-related information: transaction amount, transaction frequency, and dispersion coefficient of transaction cycle.

[0111] For equity relationships, if the equity ratio of the associated enterprise to the target enterprise is between 0.8 and 1.1, it may be given a maximum score of 2 points; and if the transaction amount is above a certain threshold, it may also be given a higher score. These rules not only take into account the existence of the relationship, but also quantify the strength of the relationship, providing a basis for determining the best push path.

[0112] The relevance score is a numerical value calculated based on the association information by applying the relevance analysis rules to quantify the strength and value of the relationship between the associated enterprise and the target enterprise. R relevance scores correspond to R associated nodes (i.e., associated enterprises), where R is a positive integer, indicating that the target enterprise has R associated enterprises.

[0113] As an exemplary example, if enterprise A holds a 0.9 equity ratio in target enterprise C (according to the association analysis rules, the equity ratio is between 0.8 and 1.1, and 2 points are obtained), and enterprise A has frequent transactions with enterprise C (transaction frequency ranks in the top 5, and 3 points are obtained), the association score of enterprise A can be calculated by weighting the score values ​​of these preset association information. For example, the final association score may be 5 points.

[0114] The push node is the M nodes that are most suitable as financial product recommendation channels among the R associated nodes, selected according to the association score. M is a positive integer, representing the number of associated enterprises that the financial institution will go through to push financial products to the target enterprise. The purpose of selecting the push node is to determine the associated enterprises that are most likely to have a positive impact on the target enterprise, so as to improve the success rate of financial product recommendations.

[0115] In an optional embodiment, it is assumed that the target enterprise is enterprise Z, which has R associated nodes in the target knowledge graph, namely associated enterprises W, X, Y, etc. Through analysis, the financial institution obtains the following associated information: enterprise W holds 0.9 of the equity of enterprise Z, which is a strong equity association; enterprise X is a long-term supplier of enterprise Z. In the past two years, enterprise X has supplied goods to Z more than 20 times a year, which is a strong supply association; the transaction amount between enterprise Y and enterprise Z is large and the transaction frequency is high. The transaction frequency ranks in the top 5 in the past year, which is a strong transaction association.

[0116] Next, the financial institution applies the association analysis rules to calculate the association score of each association node: the equity association score of enterprise W is 2 points; the supply association score of enterprise X is 8 points (assuming that there has been supply in the past two years and the amount is ≥ 1 million); the transaction association score of enterprise Y is 5 points (assuming that the transaction frequency ranks in the top 5 in the past year and the transaction time point is within 0-31 days); based on R association scores (i.e., the scores of W, X, and Y), the financial institution determines M push nodes.

[0117] Assume that M is set to 2, which means that the financial institution will select the two related enterprises with the highest association scores as push nodes. In this example, enterprise X and enterprise Y will be selected as push nodes because they have the highest association scores.

[0118] For each push node, a product push path is generated based on the connection line. Specifically, on the path from enterprise X (strong supply association) to enterprise Z, financial institutions can recommend supply chain financing services, such as accounts receivable financing, to meet the funding needs between enterprise Z and supplier X. On the path from enterprise Y (strong transaction association) to enterprise Z, financial institutions recommend trade financing products, such as letters of credit or bill financing, to support the trade activities between enterprise Z and its trading partner Y.

[0119] Through the above steps, financial institutions can intelligently select the most effective push nodes based on the correlation scores between target enterprises and related enterprises, generate M product push paths, thereby improving the accuracy and effectiveness of financial product recommendations, while also strengthening the cooperative relationship with corporate customers and improving customer satisfaction and loyalty. This push strategy based on knowledge graph and correlation analysis provides strong support for the precise push of enterprise-level financial products, helping financial institutions stand out in the fiercely competitive market.

[0120] Step S204: Push the target financial product based on the M product push paths.

[0121] Through the above steps S201 to S204, the push demand of the target financial product can be analyzed first to obtain the target enterprise for this push, and then the associated enterprises of the target enterprise can be queried in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate relationships, and then the list of associated enterprises is analyzed based on the target knowledge graph to obtain M product push paths, wherein M is a positive integer, and finally the target financial product is pushed based on the M product push paths.

[0122] In the embodiment of the present invention, the knowledge graph analysis method is adopted to achieve the purpose of accurately locating the target enterprise and its associated network by means of deep related enterprise relationship mining, thereby realizing the technical effect of personalized and intelligent push of financial products. Specifically, the present invention first analyzes the characteristics of the target financial product and customer needs to determine the target enterprise; then uses the constructed financial institution corporate customer knowledge graph to query the related enterprises of the target enterprise to form a relationship network; then based on the graph analysis algorithm, the list of related enterprises is analyzed to generate multiple product push paths with high correlation; finally, the push of financial products is implemented according to these paths, which improves the pertinence and success rate of the push, thereby solving the technical problem of low accuracy of financial product push in related technologies.

[0123] The present invention is described below in conjunction with another optional embodiment.

[0124] Embodiment 2

[0125] An embodiment of the present invention further provides a push device for financial products. It should be noted that the push device for financial products in the embodiment of the present invention includes multiple implementation units, which can be used to execute the push method for financial products provided in the above-mentioned embodiment one, and each implementation unit corresponds to each implementation step in the above-mentioned embodiment one.

[0126] Figure 3 is a schematic diagram of an optional financial product push device according to an embodiment of the present invention, such as Figure 3 As shown, the device may include: a first analyzing unit 31 , a querying unit 32 , a second analyzing unit 33 , and a pushing unit 34 .

[0127] The first analysis unit 31 is used to analyze the push demand of the target financial product and obtain the target enterprise for this push;

[0128] A query unit 32 is used to query the target enterprise's associated enterprises in the target knowledge graph to obtain an associated enterprise list, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations;

[0129] The second analysis unit 33 is used to analyze the list of related enterprises based on the target knowledge graph to obtain M product push paths, where M is a positive integer;

[0130] The push unit 34 is used to push the target financial product based on the M product push paths.

[0131] The above-mentioned financial product push device can first analyze the push demand of the target financial product through the first analysis unit 31 to obtain the target enterprise for this push, and then query the associated enterprises of the target enterprise in the target knowledge graph through the query unit 32 to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate relationships, and then analyze the list of associated enterprises based on the target knowledge graph through the second analysis unit 33 to obtain M product push paths, wherein M is a positive integer, and finally push the target financial product based on the M product push paths through the push unit 34.

[0132] In the embodiment of the present invention, the knowledge graph analysis method is adopted to achieve the purpose of accurately locating the target enterprise and its associated network by means of deep related enterprise relationship mining, thereby realizing the technical effect of personalized and intelligent push of financial products. Specifically, the present invention first analyzes the characteristics of the target financial product and customer needs to determine the target enterprise; then uses the constructed financial institution corporate customer knowledge graph to query the related enterprises of the target enterprise to form a relationship network; then based on the graph analysis algorithm, the list of related enterprises is analyzed to generate multiple product push paths with high correlation; finally, the push of financial products is implemented according to these paths, which improves the pertinence and success rate of the push, thereby solving the technical problem of low accuracy of financial product push in related technologies.

[0133] Optionally, the first analysis unit includes: a first analysis module, used to analyze the push demand and obtain product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; a query module, used to query the customer resource library of the financial institution based on the product attribute information to obtain the query results, wherein the query results are used to record the enterprise attribute information that matches the product attribute information; a first determination module, used to determine the target enterprise for this push based on the enterprise attribute information indicated by the query result.

[0134] Optionally, the query unit includes: a second determination module, used to determine the target node corresponding to the target enterprise in the target knowledge graph, and determine R associated nodes of the target node, where R is a positive integer; a third determination module, used to determine the corporate customer represented by each associated node, and obtain all associated enterprises of the target enterprise; a first generation module, used to generate an associated enterprise list based on all associated enterprises, wherein the associated enterprise list contains at least the enterprise name of each associated enterprise.

[0135] Optionally, the second analysis unit includes: a positioning module, used to locate the connection line between the associated node corresponding to the associated enterprise and the target node in the target knowledge graph for each associated enterprise in the associated enterprise list; a second analysis module, used to analyze the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; a second generation module, used to generate M product push paths based on the association information and the connection line.

[0136] Optionally, the second analysis module includes: an analysis submodule, used to analyze the connection lines in the target knowledge graph to obtain the association types of the enterprise association relationships represented by the connection lines, wherein the association types include: equity association, supply association and transaction association; a first acquisition submodule, used to obtain the association information between the associated enterprises and the target enterprise based on the association type.

[0137] Optionally, the second analysis module also includes: a second acquisition sub-module, which is used to obtain equity association information between the associated enterprise and the target enterprise when the association type is equity association, wherein the equity association information includes: shareholding role and shareholding ratio; a third acquisition sub-module, which is used to obtain supply association information between the associated enterprise and the target enterprise when the association type is supply association, wherein the supply association information includes: supply role and supply cycle; a fourth acquisition sub-module, which is used to obtain transaction association information between the associated enterprise and the target enterprise when the association type is transaction association, wherein the transaction association information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

[0138] Optionally, the second generation module includes: a fifth acquisition submodule, used to acquire association analysis rules, wherein the association analysis rules are used to record N preset association information and the score value corresponding to each preset association information, and N is a positive integer; a calculation submodule, used to calculate the association score of each association node based on the association analysis rules and the association information, and obtain R association scores; a determination submodule, used to determine M push nodes among the R association nodes based on the R association scores; and a generation submodule, used to generate a product push path for each push node based on the connecting line corresponding to the push node.

[0139] It should be noted that the first analysis unit 31, the query unit 32, the second analysis unit 33, and the push unit 34 correspond to steps S201 to S204 in the first embodiment, and the examples and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the contents disclosed in the first embodiment. It should be noted that the above modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above modules or units can also be part of the device and can be run in the computer terminal 10 provided in the first embodiment.

[0140] The present invention is described below in conjunction with another optional embodiment.

[0141] Embodiment 3

[0142] An embodiment of the present invention may also provide an electronic device, Figure 4 is a structural block diagram of an electronic device for executing a method for pushing financial products according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0143] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the push method and device of financial products in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the push method of the above-mentioned financial products. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0144] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: analyze the push demand of the target financial product to obtain the target enterprise for this push; query the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate relationships; analyze the list of associated enterprises based on the target knowledge graph to obtain M product push paths, wherein M is a positive integer; and push the target financial product based on the M product push paths.

[0145] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: analyze the push demand and obtain the product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; query the customer resource library of the financial institution based on the product attribute information to obtain the query results, wherein the query results are used to record the enterprise attribute information that matches the product attribute information; determine the target enterprise for this push based on the enterprise attribute information indicated by the query result.

[0146] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the target node corresponding to the target enterprise in the target knowledge graph, and determine R associated nodes of the target node, where R is a positive integer; determine the enterprise customers represented by each associated node, and obtain all associated enterprises of the target enterprise; generate an associated enterprise list based on all associated enterprises, wherein the associated enterprise list at least includes the enterprise name of each associated enterprise.

[0147] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each associated enterprise in the associated enterprise list, locate the connection line between the associated node corresponding to the associated enterprise and the target node in the target knowledge graph; analyze the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; generate M product push paths based on the association information and the connection line.

[0148] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: analyze the connection lines in the target knowledge graph to obtain the association types of the enterprise association relationships represented by the connection lines, where the association types include: equity association, supply association and transaction association; obtain the association information between the associated enterprises and the target enterprise based on the association type.

[0149] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: when the association type is equity association, obtain the equity association information between the associated enterprise and the target enterprise, wherein the equity association information includes: shareholding role and shareholding ratio; when the association type is supply association, obtain the supply association information between the associated enterprise and the target enterprise, wherein the supply association information includes: supply role and supply cycle; when the association type is transaction association, obtain the transaction association information between the associated enterprise and the target enterprise, wherein the transaction association information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

[0150] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain the association analysis rules, wherein the association analysis rules are used to record N preset association information and the score value corresponding to each preset association information, N is a positive integer; based on the association analysis rules and the association information, calculate the association score of each association node to obtain R association scores; based on the R association scores, determine M push nodes among the R association nodes; for each push node, generate a product push path based on the connecting line corresponding to the push node.

[0151] By adopting the embodiment of the present invention, a scheme for pushing financial products is provided. Through the method of knowledge graph analysis and the means of deep related enterprise relationship mining, the purpose of accurately locating the target enterprise and its related network is achieved, thereby realizing the technical effect of personalized and intelligent push of financial products. Specifically, the present invention first analyzes the characteristics of the target financial product and customer needs to determine the target enterprise; then uses the constructed financial institution enterprise customer knowledge graph to query the related enterprises of the target enterprise to form a relationship network; then based on the graph analysis algorithm, the list of related enterprises is analyzed to generate multiple product push paths with high correlation; finally, the push of financial products is implemented according to these paths, which improves the pertinence and success rate of the push, thereby solving the technical problem of low accuracy of financial product push in related technologies.

[0152] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), a PAD or other terminal device. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0153] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0154] The present invention is described below in conjunction with another optional embodiment.

[0155] Embodiment 4

[0156] The embodiment of the present invention further provides a computer-readable storage medium. Optionally, in the embodiment of the present invention, the computer-readable storage medium can be used to store the program code executed by the method for pushing financial products provided in the first embodiment.

[0157] Optionally, in an embodiment of the present invention, the above-mentioned storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0158] An embodiment of the present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of a method for pushing financial products: analyzing the push requirements of a target financial product to obtain a target enterprise for this push; querying the associated enterprises of the target enterprise in a target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations; analyzing the list of associated enterprises based on the target knowledge graph to obtain M product push paths, wherein M is a positive integer; and pushing the target financial product based on the M product push paths.

[0159] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0160] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0164] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0165] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for pushing financial products, characterized in that: include: Analyze the push demand of the target financial products and obtain the target enterprises for this push; Query the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations; Analyze the list of related enterprises based on the target knowledge graph to obtain M product push paths, where M is a positive integer; The target financial product is pushed based on the M product push paths.

2. The push method according to claim 1, characterized in that: Analyze the push demand of the target financial products and obtain the steps of the target enterprises for this push, including: Analyze the push demand to obtain product attribute information of the target financial product, wherein the product attribute information includes: product type, service scope and customer qualification requirements; Based on the product attribute information, query the customer resource library of the financial institution to obtain a query result, wherein the query result is used to record the enterprise attribute information matching the product attribute information; The target enterprise for this push is determined based on the enterprise attribute information indicated by the query result.

3. The push method according to claim 1, characterized in that: The step of searching the target enterprise's associated enterprises in the target knowledge graph to obtain an associated enterprise list includes: Determine a target node corresponding to the target enterprise in the target knowledge graph, and determine R associated nodes of the target node, where R is a positive integer; Determine the enterprise customer represented by each of the associated nodes, and obtain all associated enterprises of the target enterprise; A list of associated enterprises is generated based on all the associated enterprises, wherein the list of associated enterprises at least includes the enterprise name of each of the associated enterprises.

4. The push method according to claim 3, characterized in that: The step of analyzing the associated enterprise list based on the target knowledge graph to obtain M product push paths includes: For each of the associated enterprises in the associated enterprise list, locating a connection line between the associated node corresponding to the associated enterprise and the target node in the target knowledge graph; Analyze the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information; M product push paths are generated based on the association information and the connection lines.

5. The push method according to claim 4, characterized in that: The step of analyzing the enterprise association relationship between the associated enterprise and the target enterprise based on the connection line to obtain association information includes: Analyzing the connection line in the target knowledge graph to obtain the association type of the enterprise association relationship represented by the connection line, wherein the association type includes: equity association, supply association and transaction association; The association information between the associated enterprise and the target enterprise is acquired based on the association type.

6. The push method according to claim 5, characterized in that: The step of acquiring the association information between the associated enterprise and the target enterprise based on the association type includes: In the case where the association type is equity association, acquiring equity association information between the associated enterprise and the target enterprise, wherein the equity association information includes: shareholding role and shareholding ratio; In the case where the association type is supply association, obtaining supply association information between the associated enterprise and the target enterprise, wherein the supply association information includes: supply role and supply cycle; In the case where the association type is a transaction association, the transaction association information between the associated enterprise and the target enterprise is obtained, wherein the transaction association information includes: transaction amount, transaction frequency, transaction time point and transaction cycle.

7. The push method according to claim 6, characterized in that: The step of generating M product push paths based on the association information and the connection lines includes: Obtaining a correlation analysis rule, wherein the correlation analysis rule is used to record N preset correlation information and a score value corresponding to each preset correlation information, where N is a positive integer; Based on the association analysis rule and the association information, calculating the association score of each of the association nodes to obtain R association scores; Based on the R association scores, determining M push nodes from the R associated nodes; For each of the push nodes, the product push path is generated based on the connection line corresponding to the push node.

8. A device for pushing financial products, characterized in that: include: The first analysis unit is used to analyze the push demand of the target financial product and obtain the target enterprise for this push; A query unit, used to query the associated enterprises of the target enterprise in the target knowledge graph to obtain a list of associated enterprises, wherein the target knowledge graph records all corporate customers of the financial institution and corporate associations; A second analysis unit is used to analyze the associated enterprise list based on the target knowledge graph to obtain M product push paths, where M is a positive integer; A push unit is used to push the target financial product based on the M product push paths.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for pushing financial products according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for pushing financial products as described in any one of claims 1 to 7.

Images