Information recommendation method and device based on graph network, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an information recommendation method and device based on a graph network, electronic equipment and a storage medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring a user identifier set of a plurality of users and historical insurance policy data of the plurality of users; constructing a network atlas according to the user identifier set and the historical insurance policy data to select a first node and a second node, and determining a first common node set; when the first common node set is a non-empty set, performing similarity calculation on the first node and the second node to obtain a first similarity value; when the first similarity value is greater than or equal to a preset similarity threshold value, determining a first insurance product set and a second insurance product set; and recommending the insurance products in the second insurance product set to the user corresponding to the first node, and recommending the insurance products in the first insurance product set to the user corresponding to the second node. According to the embodiment of the invention, the similarity between the users can be measured, and the accuracy of product recommendation is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to an information recommendation method, device, electronic device and storage medium based on a graph network. Background Art

[0002] In the insurance industry, providing customers with personalized insurance product recommendations is a critical task. With the rapid increase in the number of insurance products, policyholders often find it difficult to choose from a multitude of options, and traditional recommendation methods often cannot effectively handle this information overload problem.

[0003] Traditional recommendation methods mainly rely on customers’ historical purchase records and basic information. Although this method can reflect customers’ purchasing habits to a certain extent, it ignores the potential connections and social influence between customers, resulting in a lack of diversity and innovation in recommendation results, thus missing the opportunity to provide more accurate recommendations. In addition, this method often faces the cold start problem when dealing with new customers or new products due to the lack of sufficient historical data, making it difficult to provide accurate recommendations. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an information recommendation method, device, electronic device and storage medium based on a graph network, which provides accurate insurance product recommendation results by measuring the similarities between users and improves the accuracy of product recommendations.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes an information recommendation method based on a graph network, the method comprising: Acquire a user identification set of multiple users and historical insurance policy data of the multiple users, wherein the historical insurance policy data includes at least one insurance product; Constructing a network graph according to the user identification set and the historical policy data, wherein different nodes in the network graph correspond to different users; Selecting a first node and a second node in the network graph, and determining a first common node set connected to the first node and the second node, wherein the common nodes in the first common node set are connected to the first node and the second node at the same time; When the first common node set is a non-empty set, similarity calculation is performed on the first node and the second node based on the first common node set and the network graph to obtain a first similarity value; When the first similarity value is greater than or equal to a preset similarity threshold, determining a first insurance product set corresponding to the first node, and determining a second insurance product set corresponding to the second node; Recommending insurance products in the second insurance product set to a user corresponding to the first node, and recommending insurance products in the first insurance product set to a user corresponding to the second node.

[0006] In some embodiments, the insurance product is provided with an insurance identifier, and the user identifier set includes a plurality of user identifiers; and constructing a network graph according to the user identifier set and the historical insurance policy data includes: Performing a deduplication operation on the historical policy data based on the insurance identifier to obtain target policy data; Constructing binary data according to the target policy data and the user identifier; A network graph is constructed based on the binary data.

[0007] In some embodiments, performing a deduplication operation on the historical policy data based on the insurance identifier to obtain target policy data includes: Classifying the historical policy data based on the insurance identifier to obtain a plurality of policy groups; Detecting the number of insurance products in each of the policy groups, and determining the policy group in which the number of insurance products is greater than a preset number as a first policy group, and determining the policy group in which the number of insurance products is less than the preset number as a second policy group; Obtain the policy time of each policy product in the first policy group to obtain a policy time set; Compare all the policy times in the policy time set, filter out the target policy time closest to the current moment, and determine the target insurance product corresponding to the target policy time; Updating the first policy group according to the target insurance product; The target policy data is obtained according to the updated first policy group and the second policy group.

[0008] In some embodiments, constructing a network graph based on the binary data includes: Obtaining the user identifier in the two-tuple data and the product identifier of the target insurance policy data; Performing correlation analysis on the user identifier and the product identifier to obtain a correlation relationship; The user corresponding to the user identification is used as a node, and a plurality of the nodes are connected according to the association relationship to construct a network graph.

[0009] In some embodiments, the calculating the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value includes: For each common node in the first common node set, determining the number of connection lines of the common node according to the network graph; Performing a logarithmic operation on the common nodes according to the number of the connection lines to obtain an operation result; The operation results of all the common nodes are accumulated to obtain a first similarity value.

[0010] In some embodiments, after calculating the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value, the method further includes: When the first similarity value is less than a preset similarity threshold, selecting a third node in the network graph, and determining a second common node set connected to the first node and the third node, wherein the common nodes in the second common node set are connected to the first node and the third node at the same time; When the second common node set is a non-empty set, similarity calculation is performed on the first node and the third node based on the second common node set and the network graph to obtain a second similarity value; When the second similarity value is greater than or equal to the preset similarity threshold, determining a first insurance product set corresponding to the first node, and determining a third insurance product set corresponding to the third node; An insurance product in the third insurance product set is recommended to a user corresponding to the first node, and an insurance product in the first insurance product set is recommended to a user corresponding to the third node.

[0011] In some embodiments, determining a first insurance product set corresponding to the first node and determining a second insurance product set corresponding to the second node includes: Determining a first connection line connected to the first node in the network graph, and determining a first product identifier of the first connection line; Determining a first insurance product corresponding to the first product identifier to generate a first insurance product set; Determining a second connection line connected to the second node in the network graph, and determining a second product identifier of the second connection line; A second insurance product corresponding to the second product identifier is determined to generate a second insurance product set.

[0012] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes an information recommendation device based on a graph network, the device comprising: A data acquisition module, used to acquire a user identification set of multiple users and historical insurance policy data of multiple users, wherein the historical insurance policy data includes at least one insurance product; A graph construction module, used to construct a network graph according to the user identification set and the historical policy data, wherein different nodes in the network graph correspond to different users; a node determination module, configured to select a first node and a second node in the network graph, and determine a first common node set connected to the first node and the second node, wherein the common nodes in the first common node set are simultaneously connected to the first node and the second node; a similarity calculation module, configured to, when the first common node set is a non-empty set, calculate the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value; a set determination module, configured to determine a first insurance product set corresponding to the first node and a second insurance product set corresponding to the second node when the first similarity value is greater than or equal to a preset similarity threshold; A product recommendation module is used to recommend insurance products in the second insurance product set to users corresponding to the first node, and to recommend insurance products in the first insurance product set to users corresponding to the second node.

[0013] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the information recommendation method based on the graph network as described in the first aspect when executing the computer program.

[0014] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the information recommendation method based on the graph network as described in the first aspect.

[0015] The information recommendation method, device, electronic device and storage medium based on graph network proposed in the present application first obtain a user identification set of multiple users and historical policy data of multiple users, that is, historical insurance products that users have purchased, and then construct a network graph based on the user identification set and the historical policy data. The relationship between users can be intuitively displayed through the network graph. After that, a first node and a second node are arbitrarily selected in the network graph, and a first common node set connected to the first node and the second node is determined, so that the nodes connected to the first node and the second node can be determined, and further, the common insurance products owned by the user corresponding to the first node and the user corresponding to the second node can be determined. When the first common node set is a non-empty set, it means that the user corresponding to the first node and the user corresponding to the second node have common insurance products. At this time, the first node and the second node can be recommended based on the first common node set and the network graph. The similarity calculation is performed at each point to determine the similarity between the first node and the second node, and a first similarity value is obtained to measure the similarity between different users. The potential association between users can be further analyzed. When the first similarity value is greater than or equal to the preset similarity threshold, it indicates that there is a potential association between the user corresponding to the first node and the user corresponding to the second node, and the insurance products held by the users corresponding to the two nodes are relatively similar. At this time, the first insurance product set corresponding to the first node is determined, and the second insurance product set corresponding to the second node is determined, so that the insurance products purchased or currently held by different users can be determined respectively. Finally, the insurance products in the second insurance product set are recommended to the user corresponding to the first node, and the insurance products in the first insurance product set are recommended to the user corresponding to the second node. By using the similarity and association between users, more accurate and comprehensive personalized recommendations are provided to increase user satisfaction. The embodiment of the present application analyzes the potential association between users by calculating the similarity between users, so that the needs and preferences of users can be captured more accurately and comprehensively, and more personalized insurance product recommendations can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of a graph network-based information recommendation method provided in an embodiment of the present application; Figure 2 yes Figure 1 Flow chart of step S102 in FIG. Figure 3 yes Figure 2 Flow chart of step S201 in FIG. Figure 4 yes Figure 2 Flow chart of step S203 in FIG. Figure 5A flow chart of a method for calculating the similarity between a first node and a second node based on a first common node set and a network graph provided in an embodiment of the present application; Figure 6 is a flowchart of a graph network-based information recommendation method provided by another embodiment of the present application; Figure 7 A flow chart of a method for determining a first insurance product set and a second insurance product set provided in an embodiment of the present application; Figure 8 is a schematic diagram of the structure of an information recommendation device based on a graph network provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0020] First, some nouns involved in this application are analyzed: Natural Language Processing (NLP): NLP uses computers to process, understand, and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0021] The graph network-based information recommendation method and device, electronic device, and storage medium provided in the embodiments of the present application provide accurate insurance product recommendation results by measuring the similarities between users, thereby improving the accuracy of product recommendations.

[0022] The following examples are used to illustrate the method. First, the information recommendation method based on a graph network in the example of the present application is described.

[0023] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0024] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robotics technology, biometrics technology, module management technology of online meeting systems, natural language processing technology, and machine learning / deep learning.

[0025] The information recommendation method based on a graph network provided in the embodiment of the present application relates to the field of financial technology technology. The information recommendation method based on a graph network provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the information recommendation method based on a graph network, etc., but is not limited to the above forms.

[0026] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0027] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0028] In the insurance industry, providing customers with personalized insurance product recommendations is a critical task. With the rapid increase in the number of insurance products, policyholders often find it difficult to choose from a multitude of options, and traditional recommendation methods often cannot effectively handle this information overload problem.

[0029] Traditional recommendation methods mainly rely on customers’ historical purchase records and basic information. Although this method can reflect customers’ purchasing habits to a certain extent, it ignores the potential connections and social influence between customers, resulting in a lack of diversity and innovation in recommendation results, thus missing the opportunity to provide more accurate recommendations. In addition, this method often faces the cold start problem when dealing with new customers or new products due to the lack of sufficient historical data, making it difficult to provide accurate recommendations.

[0030] In order to solve the above problems, the present embodiment provides an information recommendation method, device, electronic device and storage medium based on a graph network. First, a user identification set of multiple users and historical policy data of multiple users, that is, historical insurance products that the users have purchased, are obtained, and then a network graph is constructed based on the user identification set and the historical policy data. The relationship between users can be intuitively displayed through the network graph. After that, a first node and a second node are arbitrarily selected in the network graph, and a first common node set connected to the first node and the second node is determined, so that the nodes connected to the first node and the second node can be determined, and further, the common insurance products owned by the user corresponding to the first node and the user corresponding to the second node can be determined. When the first common node set is a non-empty set, it means that the user corresponding to the first node and the user corresponding to the second node have a common insurance product. At this time, the first node can be recommended based on the first common node set and the network graph. The first node and the second node perform similarity calculation to determine the similarity between the first node and the second node, obtain a first similarity value, measure the similarity between different users, and further analyze the potential association between users. When the first similarity value is greater than or equal to the preset similarity threshold, it indicates that there is a potential association between the user corresponding to the first node and the user corresponding to the second node, and the insurance products held by the users corresponding to the two nodes are relatively similar. At this time, the first insurance product set corresponding to the first node is determined, and the second insurance product set corresponding to the second node is determined, so that the insurance products purchased or currently held by different users can be determined respectively. Finally, the insurance products in the second insurance product set are recommended to the user corresponding to the first node, and the insurance products in the first insurance product set are recommended to the user corresponding to the second node. By using the similarity and association between users, more accurate and comprehensive personalized recommendations are provided to increase user satisfaction. The embodiment of the present application analyzes the potential association between users by calculating the similarity between users, so that the needs and preferences of users can be captured more accurately and comprehensively, and more personalized insurance product recommendations can be provided.

[0031] The following is a detailed description with reference to the accompanying drawings.

[0032] Figure 1 is an optional flowchart of the information recommendation method based on the graph network provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0033] Step S101, obtaining a user identification set of multiple users and historical insurance policy data of the multiple users, wherein the historical insurance policy data includes at least one insurance product.

[0034] In step S101 of some embodiments, a user identification set of multiple users is obtained, wherein the user identification set stores user identifications of different users, for example, ID numbers, mobile phone numbers, etc., and historical insurance policy data of multiple users is obtained, i.e., insurance products that different users are currently holding or have held, as well as purchase records of the insurance products, etc., to facilitate subsequent analysis of the insurance preferences of different users.

[0035] Step S102, constructing a network graph based on the user identification set and historical policy data.

[0036] In step S102 of some embodiments, a network graph is constructed based on a set of user identifiers and historical policy data. The graph can intuitively display relationships between users, such as social networks, similarities in purchasing behaviors, etc., which helps to discover potential connections in user groups.

[0037] Step S103, selecting a first node and a second node in the network graph, and determining a first common node set connected to the first node and the second node.

[0038] It should be noted that the common nodes in the first common node set are connected to the first node and the second node at the same time.

[0039] In step S103 of some embodiments, a first node and a second node are selected in a network graph, wherein the first node and the second node in the embodiments of the present application may be randomly selected or selected in order, etc., and the embodiments of the present application do not impose specific limitations, and common nodes connected to the first node and the second node at the same time are determined in the network graph, and the common nodes are sorted into a first common node set to realize the collection of products jointly held by users corresponding to the first node and users corresponding to the second node.

[0040] Step S104: when the first common node set is a non-empty set, similarity calculation is performed on the first node and the second node based on the first common node set and the network graph to obtain a first similarity value.

[0041] In step S104 of some embodiments, when the first common node set is a non-empty set, it indicates that there are common nodes between the first node and the second node, that is, the users corresponding to the two nodes hold common products. At this time, the similarity between the first node and the second node is calculated based on the first common node set and the network graph to obtain a first similarity value, thereby determining the similarity between the user corresponding to the first node and the user corresponding to the second node, so as to facilitate subsequent correlation analysis of the user corresponding to the first node and the user corresponding to the second node based on the similarity, and further determine the similarity between the two users.

[0042] Step S105: When the first similarity value is greater than or equal to a preset similarity threshold, a first insurance product set corresponding to the first node is determined, and a second insurance product set corresponding to the second node is determined.

[0043] In step S105 of some embodiments, when the first similarity value is greater than or equal to a preset similarity threshold, it indicates that the products held by the user corresponding to the first node and the user corresponding to the second node are relatively similar. The first insurance product set corresponding to the first node can be directly determined, and the second insurance product set corresponding to the second node can be determined, thereby achieving accurate recommendation of the first insurance product and the second insurance product, and being able to comprehensively and accurately recommend related products of interest to users, thereby improving user experience.

[0044] It should be noted that the preset similarity threshold can be set according to the needs of the user, and the embodiment of the present application does not impose any specific limitation.

[0045] Step S106: recommending insurance products in the second insurance product set to the user corresponding to the first node, and recommending insurance products in the first insurance product set to the user corresponding to the second node.

[0046] In step S106 of some embodiments, insurance products in the second insurance product set are recommended to users corresponding to the first node, and insurance products in the first insurance product set are recommended to users corresponding to the second node, utilizing the similarities and correlations between users to provide more accurate and comprehensive personalized recommendations and increase user satisfaction.

[0047] See also Figure 2 In some embodiments, step S102 may also include but is not limited to steps S201 to S203.

[0048] It should be noted that the insurance product is provided with an insurance identifier, and the user identifier set includes multiple user identifiers.

[0049] Step S201, deduplicate historical policy data based on the insurance identifier to obtain target policy data.

[0050] Step S202, constructing binary data according to the target policy data and the user identifier.

[0051] Step S203, constructing a network graph based on the bigram data.

[0052] In steps S201 to S203 of some embodiments, in the process of constructing a network graph based on a set of user identifiers and historical policy data, since different types of insurance products are provided with different insurance identifiers, that is, insurance products correspond one-to-one to insurance identifiers, the embodiments of the present application can perform deduplication operations on historical policy data based on insurance identifiers, thereby avoiding interference from multiple duplicate policy data of the same insurance product, reducing the amount of data to be processed, and improving the efficiency of processing data to obtain target policy data. Deduplication ensures the consistency and accuracy of the data and avoids analysis and decision-making errors caused by duplicate data. Afterwards, binary data is constructed based on the target policy data and the user identifier to obtain a data set corresponding to the user identifier and the target policy data. Finally, a network graph is constructed based on the binary data. The graph can intuitively display the relationship between users, such as social networks, similarities in purchasing behaviors, etc., which is helpful to discover potential connections among user groups.

[0053] See also Figure 3 In some embodiments, step S201 may also include but is not limited to steps S301 to S306.

[0054] Step S301, classify the historical policy data based on the insurance identification to obtain multiple policy groups.

[0055] Step S302, detect the number of insurance products in each policy group, and determine the policy group with a number of insurance products greater than a preset number as the first policy group, and determine the policy group with a number of insurance products less than or equal to the preset number as the second policy group.

[0056] Step S303, obtaining the policy time of each policy product in the first policy group to obtain a policy time set.

[0057] Step S304, compare all the policy times in the policy time set, filter out the target policy time closest to the current moment, and determine the target insurance product corresponding to the target policy time.

[0058] Step S305, updating the first policy group according to the target insurance product.

[0059] Step S306, obtaining target policy data according to the updated first policy group and second policy group.

[0060] In steps S301 to S306 of some embodiments, the embodiments of the present application first classify the historical policy data based on the insurance identification, and classify the historical policy data into multiple policy groups of different categories, such as pension insurance, automobile insurance, childcare insurance, etc. Since the same policy may be renewed, multiple duplicate order numbers will appear at this time, resulting in data redundancy. In order to avoid the existence of multiple renewal policies for the same insurance product, the embodiments of the present application need to detect the number of insurance products in each policy group, and determine the policy group with a number of insurance products greater than a preset number as the first policy group, that is, the insurance products in the first policy group are renewed, and the policy group with a number of insurance products less than or equal to the preset number is determined as the second policy group, so as to realize the screening of the renewed insurance products, and then obtain the policy time of each policy product in the first policy group, that is, the user's insurance participation time, A policy time set is obtained to realize the statistics of all insurance time, and then all policy times in the policy time set are compared to screen out the target policy time closest to the current moment, that is, the last insurance or renewal date, and determine the target insurance product corresponding to the target policy time, so as to screen out the target insurance product required by the user. Finally, the first policy group is updated according to the insurance product, that is, all policy products in the first policy group are replaced by the target insurance product, so as to ensure that there is only one policy product in the first policy group, ensuring the consistency and accuracy of the same policy product, so that the renewed insurance products that are still in effect are only taken once to avoid data duplication interference, and then the target policy data is obtained according to the updated first policy group and the second policy group, so as to avoid analysis and decision-making errors caused by duplicate data, reduce the complexity and cost of data processing, and improve operational efficiency.

[0061] It should be noted that the preset number in the embodiment of the present application can be set according to the needs of the user. For example, the preset number can be set to 1, 2 or 3, etc. The embodiment of the present application takes the preset number of 1 as an example, that is, the policy group with the number of insurance products greater than 1 is determined as the first policy group, and the policy group with the number of insurance products less than or equal to 1 is determined as the second policy group.

[0062] See also Figure 4 In some embodiments, step S203 may also include but is not limited to steps S401 to S403.

[0063] Step S401, obtaining the user identifier in the binary data and the product identifier of the target insurance policy data.

[0064] Step S402: Perform correlation analysis on the user identifier and the product identifier to obtain a correlation relationship.

[0065] Step S403: Use the user corresponding to the user identifier as a node, and connect multiple nodes according to the association relationship to construct a network graph.

[0066] In steps S401 to S403 of some embodiments, in the process of constructing a network graph based on binary data, the embodiments of the present application first obtain the user identifier in the binary data and the product identifier of the target policy data, and then perform correlation analysis on the user identifier and the product identifier to analyze the correspondence between the user and the insurance product, so as to determine the insurance product that the user is holding or has purchased, and obtain the association relationship between the user and the insurance product. Finally, the user corresponding to the user identifier is taken as a node, and multiple nodes are connected according to the association relationship, and the edge between the two nodes is taken as the same insurance product held by the two users, that is, each edge connection represents that two users hold the same insurance product, so that the correspondence between the user and the insurance product can be clearly described. The relationship between users can be intuitively displayed through the graph, such as social networks, similarities in purchasing behaviors, etc., which is helpful to discover potential connections in user groups.

[0067] It can be understood that when there are three edges between two nodes, it means that the users corresponding to the two nodes jointly hold three identical insurance products; when there are two edges between two nodes, it means that the users corresponding to the two nodes jointly hold two identical insurance products, and so on. The embodiments of the present application do not make specific limitations.

[0068] See also Figure 5 , Figure 5 A flow chart of a method for calculating the similarity between a first node and a second node based on a first common node set and a network graph provided in an embodiment of the present application, wherein the method includes but is not limited to steps S501 to S503.

[0069] Step S501: for each common node in the first common node set, determine the number of connection lines of the common node according to the network graph.

[0070] Step S502, performing logarithmic operation on the common nodes according to the number of connection lines to obtain operation results.

[0071] Step S503: Accumulate the operation results of all common nodes to obtain a first similarity value.

[0072] In steps S501 to S503 of some embodiments, in the process of calculating the similarity between the first node and the second node based on the first common node set and the network graph, since the common nodes in the first common node set are connected to the first node and the second node at the same time, the embodiment of the present application first determines the number of connection lines for each common node in the first common node set, so as to determine the number of common insurance products held by the user corresponding to the first node and the user corresponding to the second node, and then performs logarithmic operation on the common nodes according to the number of connection lines. Specifically, take the common nodes C and D of the first node A and the second node B as an example for explanation, the common node C has three connection lines, and the common node There are four connecting lines at point D. At this time, 1 / log|N(C)|=1 / log3=2.0959, and 1 / log|N(B)|=1log4=1.6610, and two calculation results of 2.0959 and 1.6610 are obtained. Then, the calculation results of all common nodes are accumulated, that is, AA(D,E)=1.6610+2.0959=3.7569, and the first similarity value is obtained, so that the similarity between the user corresponding to the first node and the user corresponding to the second node can be obtained, which is convenient for the subsequent correlation analysis of the user corresponding to the first node and the user corresponding to the second node based on the similarity, and further judgement of the similarity between the two users.

[0073] See also Figure 6 , Figure 6 It is a flowchart of a graph network-based information recommendation method provided by another embodiment of the present application, and the method includes but is not limited to steps S601 to S604.

[0074] It should be noted that after the similarity between the first node and the second node is calculated based on the first common node set and the network graph to obtain the first similarity value.

[0075] Step S601, when the first similarity value is less than a preset similarity threshold, a third node is selected in the network graph, and a second common node set connected to the first node and the third node is determined.

[0076] It should be noted that the common nodes in the second common node set are connected to the first node and the third node at the same time.

[0077] Step S602: When the second common node set is a non-empty set, similarity calculation is performed on the first node and the third node based on the second common node set and the network graph to obtain a second similarity value.

[0078] Step S603: When the second similarity value is greater than or equal to a preset similarity threshold, a first insurance product set corresponding to the first node is determined, and a third insurance product set corresponding to the third node is determined.

[0079] Step S604: recommend an insurance product in the third insurance product set to a user corresponding to the first node, and recommend an insurance product in the first insurance product set to a user corresponding to the third node.

[0080] In steps S601 to S604 of some embodiments, after the similarity between the first node and the second node is calculated based on the first common node set and the network graph to obtain the first similarity value, the first similarity value is compared with the preset similarity threshold. When the first similarity value is less than the preset similarity threshold, it means that the correlation between the user corresponding to the first node and the user corresponding to the second node is low, and the two users basically do not hold similar insurance products. If insurance products are subsequently recommended to each other based on the users corresponding to the first node or the second node, the recommendation accuracy will be reduced, affecting the user experience. In order to avoid this situation, the embodiment of the present application will select a third node in the network graph when the first similarity value is less than the preset similarity threshold, and determine the second common node set connected to the first node and the third node, thereby determining the common nodes connected to the first node and the third node at the same time. When the second common node set is a non-empty set, the first node can be directly recommended based on the second common node set and the network graph. A similarity calculation is performed between a first node and a third node, so that a second similarity value between the first node and the third node can be calculated, and the degree of similarity between the first node and the third node can be further judged based on the second similarity value, so as to measure the similarity between the user corresponding to the first node and the user corresponding to the third node. When the second similarity value is greater than or equal to a preset similarity threshold, it indicates that there is a potential association between the user corresponding to the first node and the user corresponding to the third node, and the insurance products held by the users corresponding to the two nodes are relatively similar. The first insurance product set corresponding to the first node can be directly determined, and the third insurance product set corresponding to the third node can be determined. Thus, the insurance products purchased or currently held by different users can be determined respectively, and the insurance products in the third insurance product set can be recommended to the user corresponding to the first node, and the insurance products in the first insurance product set can be recommended to the user corresponding to the third node. By utilizing the similarity and association between users, more accurate and comprehensive personalized recommendations can be provided to increase user satisfaction.

[0081] It should be noted that when the second similarity value is less than the preset similarity threshold, other nodes are continuously selected in the network graph for similarity calculation, that is, steps S601 to S604 are repeated, and the embodiments of the present application will not be described in detail here.

[0082] See also Figure 7 , Figure 7 A flow chart of a method for determining a first insurance product set and a second insurance product set provided in an embodiment of the present application, Figure 7The method may include but is not limited to steps S701 to S704.

[0083] Step S701, determining a first connection line connected to a first node in a network graph, and determining a first product identifier of the first connection line.

[0084] Step S702: determine a first insurance product corresponding to the first product identifier to generate a first insurance product set.

[0085] Step S703, determining a second connection line connected to the second node in the network graph, and determining a second product identifier of the second connection line.

[0086] Step S704: determine a second insurance product corresponding to the second product identifier to generate a second insurance product set.

[0087] In steps S701 to S704 of some embodiments, in the process of determining the first insurance product set and the second insurance product set, the embodiments of the present application will determine one or more first connection lines connected to the first node in the network map, determine the first product identifier of the first connection line, and then determine one or more first insurance products corresponding to the first product identifier, thereby generating a first insurance product set. Similarly, a second connection line connected to the second node is determined in the network map, and the second product identifier corresponding to the second connection line is determined, and then one or more second insurance products corresponding to the second product identifier are determined, thereby generating a second insurance product set, achieving accurate recommendations for the first insurance product and the second insurance product, and being able to comprehensively and accurately recommend related products of interest to users, thereby improving user experience.

[0088] See also Figure 8 The embodiment of the present application also provides an information recommendation device based on a graph network, the device comprising: The data acquisition module 801 is used to acquire a user identification set of multiple users and historical insurance policy data of multiple users, wherein the historical insurance policy data includes at least one insurance product; A graph construction module 802, for constructing a network graph based on a user identification set and historical policy data; The node determination module 803 is used to select a first node and a second node in the network graph, and determine a first common node set connected to the first node and the second node, wherein the common nodes in the first common node set are connected to the first node and the second node at the same time; A similarity calculation module 804 is used to calculate the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value when the first common node set is a non-empty set; A set determination module 805, configured to determine a first insurance product set corresponding to the first node and a second insurance product set corresponding to the second node when the first similarity value is greater than or equal to a preset similarity threshold; The product recommendation module 806 is used to recommend insurance products in the second insurance product set to the user corresponding to the first node, and to recommend insurance products in the first insurance product set to the user corresponding to the second node.

[0089] The specific implementation of the graph network-based information recommendation device is basically the same as the specific implementation of the graph network-based information recommendation method described above, and will not be repeated here.

[0090] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned information recommendation method based on the graph network. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0091] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes: The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the information recommendation method based on the graph network in the embodiment of this application; Input / output interface 903, used to implement information input and output; Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.); A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904); The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0092] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned information recommendation method based on the graph network.

[0093] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.

[0094] The information recommendation method, device, electronic device and storage medium based on graph network provided in the embodiments of the present application first obtain a user identification set of multiple users and historical policy data of multiple users, that is, historical insurance products that the users have purchased, and then construct a network graph based on the user identification set and the historical policy data. The relationship between users can be intuitively displayed through the network graph. After that, a first node and a second node are arbitrarily selected in the network graph, and a first common node set connected to the first node and the second node is determined, so that the nodes connected to the first node and the second node can be determined, and further, the common insurance products owned by the user corresponding to the first node and the user corresponding to the second node can be determined. When the first common node set is a non-empty set, it means that the user corresponding to the first node and the user corresponding to the second node have a common insurance product. At this time, the first node and the first common node can be selected based on the first common node set and the network graph. The two nodes perform similarity calculation to determine the similarity between the first node and the second node, obtain a first similarity value, and measure the similarity between different users. The potential association between users can be further analyzed. When the first similarity value is greater than or equal to the preset similarity threshold, it indicates that there is a potential association between the user corresponding to the first node and the user corresponding to the second node, and the insurance products held by the users corresponding to the two nodes are relatively similar. At this time, the first insurance product set corresponding to the first node is determined, and the second insurance product set corresponding to the second node is determined, so that the insurance products purchased or currently held by different users can be determined respectively. Finally, the insurance products in the second insurance product set are recommended to the user corresponding to the first node, and the insurance products in the first insurance product set are recommended to the user corresponding to the second node. By using the similarity and association between users, more accurate and comprehensive personalized recommendations are provided to increase user satisfaction. The embodiment of the present application analyzes the potential association between users by calculating the similarity between users, so that the needs and preferences of users can be captured more accurately and comprehensively, and more personalized insurance product recommendations can be provided.

[0095] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0096] It can be understood by those skilled in the art that Figure 1-9 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0097] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0099] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0100] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0102] The units described above 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.

[0103] 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.

[0104] 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, 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 multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0105] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for information recommendation based on a graph network, characterized in that: The method comprises: Acquire a user identification set of multiple users and historical insurance policy data of the multiple users, wherein the historical insurance policy data includes at least one insurance product; Constructing a network graph according to the user identification set and the historical policy data, wherein different nodes in the network graph correspond to different users; Selecting a first node and a second node in the network graph, and determining a first common node set connected to the first node and the second node, wherein the common nodes in the first common node set are connected to the first node and the second node at the same time; When the first common node set is a non-empty set, similarity calculation is performed on the first node and the second node based on the first common node set and the network graph to obtain a first similarity value; When the first similarity value is greater than or equal to a preset similarity threshold, determining a first insurance product set corresponding to the first node, and determining a second insurance product set corresponding to the second node; Recommending insurance products in the second insurance product set to a user corresponding to the first node, and recommending insurance products in the first insurance product set to a user corresponding to the second node.

2. The information recommendation method based on graph network according to claim 1, characterized in that: The insurance product is provided with an insurance identifier, and the user identifier set includes a plurality of user identifiers; and constructing a network graph according to the user identifier set and the historical insurance policy data includes: Performing a deduplication operation on the historical policy data based on the insurance identifier to obtain target policy data; Constructing binary data according to the target policy data and the user identifier; A network graph is constructed based on the binary data.

3. The information recommendation method based on graph network according to claim 2, characterized in that: The deduplication operation is performed on the historical policy data based on the insurance identifier to obtain target policy data, including: Classifying the historical policy data based on the insurance identifier to obtain a plurality of policy groups; Detecting the number of insurance products in each of the policy groups, and determining the policy group in which the number of insurance products is greater than a preset number as a first policy group, and determining the policy group in which the number of insurance products is less than the preset number as a second policy group; Obtain the policy time of each policy product in the first policy group to obtain a policy time set; Compare all the policy times in the policy time set, filter out the target policy time closest to the current moment, and determine the target insurance product corresponding to the target policy time; updating the first policy group according to the target insurance product; The target policy data is obtained according to the updated first policy group and the second policy group.

4. The information recommendation method based on graph network according to claim 2, characterized in that: The step of constructing a network graph according to the binary data includes: Obtaining the user identifier in the two-tuple data and the product identifier of the target insurance policy data; Performing correlation analysis on the user identifier and the product identifier to obtain a correlation relationship; The user corresponding to the user identification is used as a node, and a plurality of the nodes are connected according to the association relationship to construct a network graph.

5. The information recommendation method based on graph network according to claim 1, characterized in that: The performing similarity calculation on the first node and the second node based on the first common node set and the network graph to obtain a first similarity value includes: For each common node in the first common node set, determining the number of connection lines of the common node according to the network graph; Performing a logarithmic operation on the common nodes according to the number of the connection lines to obtain an operation result; The operation results of all the common nodes are accumulated to obtain a first similarity value.

6. The information recommendation method based on graph network according to claim 1, characterized in that: After calculating the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value, the method further includes: When the first similarity value is less than a preset similarity threshold, selecting a third node in the network graph, and determining a second common node set connected to the first node and the third node, wherein the common nodes in the second common node set are connected to the first node and the third node at the same time; When the second common node set is a non-empty set, similarity calculation is performed on the first node and the third node based on the second common node set and the network graph to obtain a second similarity value; When the second similarity value is greater than or equal to the preset similarity threshold, determining a first insurance product set corresponding to the first node, and determining a third insurance product set corresponding to the third node; An insurance product in the third insurance product set is recommended to a user corresponding to the first node, and an insurance product in the first insurance product set is recommended to a user corresponding to the third node.

7. The information recommendation method based on graph network according to claim 1, characterized in that: The determining a first insurance product set corresponding to the first node, and determining a second insurance product set corresponding to the second node, includes: Determining a first connection line connected to the first node in the network graph, and determining a first product identifier of the first connection line; Determining a first insurance product corresponding to the first product identifier to generate a first insurance product set; Determining a second connection line connected to the second node in the network graph, and determining a second product identifier of the second connection line; A second insurance product corresponding to the second product identifier is determined to generate a second insurance product set.

8. An information recommendation device based on a graph network, characterized in that: The device comprises: A data acquisition module, used to acquire a user identification set of multiple users and historical insurance policy data of multiple users, wherein the historical insurance policy data includes at least one insurance product; A graph construction module, used to construct a network graph according to the user identification set and the historical policy data, wherein different nodes in the network graph correspond to different users; a node determination module, configured to select a first node and a second node in the network graph, and determine a first common node set connected to the first node and the second node, wherein the common nodes in the first common node set are simultaneously connected to the first node and the second node; a similarity calculation module, configured to, when the first common node set is a non-empty set, calculate the similarity between the first node and the second node based on the first common node set and the network graph to obtain a first similarity value; a set determination module, configured to determine a first insurance product set corresponding to the first node and a second insurance product set corresponding to the second node when the first similarity value is greater than or equal to a preset similarity threshold; A product recommendation module is used to recommend insurance products in the second insurance product set to users corresponding to the first node, and to recommend insurance products in the first insurance product set to users corresponding to the second node.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the information recommendation method based on a graph network as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the information recommendation method based on a graph network described in any one of claims 1 to 7 is implemented.

Images