Insurance product recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an insurance product recommendation method and device, electronic equipment and a storage medium, belongs to the technical field of intelligent recommendation, and is suitable for the field of financial science and technology. The method comprises the following steps: acquiring user insurance policy information of an insurance reference user, and acquiring basic user information of a target user; performing information extraction on the user insurance policy information to obtain user insurance information and user credit information; based on the basic user information, performing information query on the user insurance information to obtain user associated insurance information; performing information query on the user credit information based on the basic user information to obtain user associated credit information; based on the user associated credit information, performing credit assessment on the target user to obtain a user assessment category, the user assessment category including a trusted user category; and based on the trusted user category and the user associated insurance information, performing insurance recommendation on the target user. According to the embodiment of the invention, the accuracy of insurance product recommendation can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent recommendation technology, applicable to the field of financial technology, and in particular to an insurance product recommendation method and device, electronic device and storage medium. Background Art

[0002] Intelligent recommendation refers to providing users with personalized choices by analyzing user data. For example, insurance product recommendations in financial scenarios are used to provide users with insurance plan suggestions based on user needs, risk preferences, etc. For example, when a user has just purchased a vehicle, auto insurance products can be recommended to the user to meet the user's needs.

[0003] At present, common insurance product recommendations are often based on the user's basic user information, predicting the user's needs, and then recommending insurance products to the user. However, since this method only considers the user's basic needs, it is easy to cause errors in the predicted user needs, resulting in inaccurate insurance product recommendations. Therefore, how to improve the accuracy of insurance product recommendations has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an insurance product recommendation method and device, an electronic device and a storage medium, aiming to improve the accuracy of insurance product recommendations.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes an insurance product recommendation method, the method comprising:

[0006] Obtain the user policy information of the insured reference user and the basic user information of the target user;

[0007] Extracting the user's insurance policy information to obtain the user's insurance information and user's credit information;

[0008] Based on the basic user information, query the user insurance information to obtain user-related insurance information, wherein the user-related insurance information represents the user policy information of the insurance-related user, and the insurance-related user is an insurance reference user who has a family relationship with the target user;

[0009] Based on the basic user information, query the user credit information to obtain user-related credit information, wherein the user-related credit information represents the user credit information of the insured associated user;

[0010] Based on the user-associated credit information, a credit assessment is performed on the target user to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user;

[0011] Based on the trusted user category and the user-associated insurance information, insurance recommendations are made to the target user.

[0012] In some embodiments, the performing credit evaluation on the target user based on the user-associated credit information to obtain a user evaluation category includes:

[0013] Extracting features from the user-associated credit information to obtain credit features;

[0014] Performing weight allocation on the credit features to obtain the feature weights;

[0015] Based on the feature weights, data evaluation is performed on the credit features to obtain credit evaluation data;

[0016] Based on the credit evaluation data, the credit characteristics are classified to obtain the user evaluation category.

[0017] In some embodiments, querying the user insurance information based on the basic user information to obtain the user-related insurance information includes:

[0018] Based on the user insurance information, a relationship network is constructed to obtain a user insurance relationship network;

[0019] Based on the basic user information, the user insurance relationship network is queried for associated nodes to obtain the user associated insurance information.

[0020] In some embodiments, the step of constructing a relationship network based on the user insurance information to obtain a user insurance relationship network includes:

[0021] Perform entity identification on the user's insurance information to obtain the insurance party entity;

[0022] Perform relationship identification on the insurance party entity to obtain entity relationship;

[0023] Based on the entity relationships, a network is constructed for the insurance party entities to obtain a user relationship network;

[0024] Based on the user insurance information, the user relationship network is filled with information to obtain the user insurance relationship network.

[0025] In some embodiments, querying the user insurance relationship network for associated nodes based on the basic user information to obtain the user associated insurance information includes:

[0026] Based on the basic user information, query the user insurance relationship network to obtain the target user node;

[0027] Based on the target user node, query the connection nodes of the user insurance relationship network to obtain the associated user node;

[0028] Information is extracted from the associated user node to obtain the user-associated insurance information.

[0029] In some embodiments, the making insurance recommendations to the target user based on the trusted user category and the user-associated insurance information includes:

[0030] Based on the trusted user category and the basic user information, screening the preset insurance products to obtain candidate insurances;

[0031] Extracting the user-related insurance information to obtain the related user insurance information;

[0032] Based on the associated user insurance information, the candidate insurances are screened to obtain target insurance.

[0033] In some embodiments, extracting the user's insurance policy information to obtain the user's insurance information and the user's credit information includes:

[0034] Performing text recognition on the user's insurance policy information to obtain insurance policy fields;

[0035] Performing data recognition on the policy fields to obtain the insurance information field and the credit information field;

[0036] Data is extracted from the insurance information field to obtain the user insurance information, and data is extracted from the credit information field to obtain the user credit information.

[0037] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an insurance product recommendation device, the device comprising:

[0038] An information acquisition module is used to obtain the user policy information of the insured reference user and the basic user information of the target user;

[0039] An information extraction module is used to extract the user's insurance policy information to obtain the user's insurance information and user credit information;

[0040] An associated insurance information query module is used to query the user insurance information based on the basic user information to obtain user associated insurance information, wherein the user associated insurance information represents the user policy information of the insured associated user, and the insured associated user is an insured reference user who has a family relationship with the target user;

[0041] An associated credit information query module, used to query the user credit information based on the basic user information to obtain user associated credit information, wherein the user associated credit information represents the user credit information of the insured associated user;

[0042] A credit assessment module, configured to perform a credit assessment on the target user based on the user-associated credit information to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user;

[0043] The insurance recommendation module is used to recommend insurance to the target user based on the trusted user category and the user-related insurance information.

[0044] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0045] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0046] The insurance product recommendation method and device, electronic device and storage medium proposed in the present application obtain the policy information of the insured reference user and the basic user information of the target user, and then extract the user policy information to obtain the user insurance information and user credit information of the insured reference user. On this basis, the basic user information of the target user is used to further query the user insurance information and user credit information to obtain the user-associated insurance information and user-associated credit information associated with the target user. Subsequently, a comprehensive credit assessment is performed on the target user based on the user-associated credit information to form a user assessment category. When the user assessment category is a trusted user category, an insurance product recommendation is provided to the target user based on the user-associated insurance information. This effectively integrates multi-dimensional user data, including personal basic information, associated insurance and credit information, and actual risk assessment results, thereby improving the accuracy of insurance product recommendations and solving the problem of inaccurate recommendations caused by single information in traditional methods, thereby improving the accuracy of insurance product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of the insurance product recommendation method provided in an embodiment of the present application;

[0048] Figure 2 yes Figure 1Flow chart of step S102 in FIG.

[0049] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.

[0050] Figure 4 yes Figure 3 Flow chart of step S301 in FIG.

[0051] Figure 5 yes Figure 3 Flow chart of step S302 in FIG.

[0052] Figure 6 yes Figure 1 Flow chart of step S105 in FIG.

[0053] Figure 7 yes Figure 1 Flow chart of step S106 in FIG.

[0054] Figure 8 is a schematic diagram of the structure of the insurance product recommendation device provided in an embodiment of the present application;

[0055] 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

[0056] 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.

[0057] 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.

[0058] 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.

[0059] First, some nouns involved in this application are analyzed:

[0060] Natural language processing technology: Natural language processing technology combines computer science, linguistics and artificial intelligence, aiming to enable computers to understand, parse and generate human language. NLP technology is widely used, including speech recognition, machine translation, sentiment analysis, chatbots, etc., which can help machines and humans interact more naturally. Through methods such as machine learning and deep learning, NLP continues to improve the accuracy of semantic understanding, context analysis and language generation, providing strong support for human-computer interaction and data analysis.

[0061] Relational Networks: Relational networks are designed to process and understand the relationships between objects in the data. They are particularly effective for tasks such as visual question answering and reasoning because they can capture the interactions and mutual influences between different entities in the input data. Relational networks take objects and their features as input and use learnable relational functions to model the relationships between these objects, thereby generating more context-aware outputs. This structure enables the model to better understand semantic relationships in complex scenes and improve the expressiveness and accuracy of tasks.

[0062] Intelligent recommendation refers to providing users with personalized choices by analyzing user data. For example, insurance product recommendations in financial scenarios are used to provide users with insurance plan suggestions based on user needs, risk preferences, etc. For example, when a user has just purchased a vehicle, auto insurance products can be recommended to the user to meet the user's needs.

[0063] At present, common insurance product recommendations are often based on the user's basic user information, predicting the user's needs, and then recommending insurance products to the user. However, since this method only considers the user's basic needs, it is easy to cause errors in the predicted user needs, resulting in inaccurate insurance product recommendations. Therefore, how to improve the accuracy of insurance product recommendations has become a technical problem that needs to be solved urgently. Based on this, the embodiments of the present application provide an insurance product recommendation method and device, an electronic device, and a storage medium, which are intended to improve the accuracy of insurance product recommendations.

[0064] The insurance product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the insurance product recommendation method in the embodiments of the present application is described.

[0065] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, 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.

[0066] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0067] The insurance product recommendation method provided in the embodiment of the present application relates to the field of intelligent recommendation technology and is applicable to the field of financial technology. The insurance product recommendation method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can 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 a server cluster or distributed system composed of multiple physical servers, or 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 insurance product recommendation method, etc., but is not limited to the above forms.

[0068] 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.

[0069] Figure 1 is an optional flow chart of the insurance product recommendation method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0070] Step S101, obtaining the user policy information of the insured reference user and obtaining the basic user information of the target user;

[0071] Step S102, extracting the user's insurance policy information to obtain the user's insurance information and user credit information;

[0072] Step S103, based on the basic user information, query the user's insurance information to obtain user-related insurance information, wherein the user-related insurance information represents the user's insurance policy information of the insured-related user, and the insured-related user is the insured reference user who has a family relationship with the target user;

[0073] Step S104, based on the basic user information, query the user credit information to obtain the user-related credit information, wherein the user-related credit information represents the user credit information of the insured related user;

[0074] Step S105, based on the user-associated credit information, a credit assessment is performed on the target user to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user;

[0075] Step S106: recommend insurance to the target user based on the trusted user category and the user-related insurance information.

[0076] Steps S101 to S107 shown in the embodiment of the present application are to obtain the user policy information of the insured reference user, obtain the basic user information of the target user, and then extract the user policy information to obtain the user insurance information and the user credit information. Furthermore, based on the basic user information, the user insurance information is queried to obtain the user-associated insurance information, wherein the user-associated insurance information represents the user policy information of the insured associated user, and the insured associated user is the insured reference user who has a family relationship with the target user. At the same time, based on the basic user information, the user credit information is queried to obtain the user-associated credit information, wherein the user-associated credit information represents the user credit information of the insured associated user. Subsequently, based on the user-associated credit information, the target user is credit evaluated to obtain a user evaluation category, wherein the user evaluation category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user. Finally, based on the trusted user category and the user-associated insurance information, insurance recommendations are made to the target user. Therefore, the present application obtains the insurance policy information of the insured reference user and the basic user information of the target user, and then extracts information from the user insurance policy information to obtain the user insurance information and user credit information of the insured reference user. On this basis, the basic user information of the target user is used to further query the user insurance information and user credit information to obtain the user-associated insurance information and user-associated credit information associated with the target user. Subsequently, a comprehensive credit assessment is conducted on the target user based on the user-associated credit information to form a user assessment category. When the user assessment category is a trusted user category, insurance product recommendations are provided to the target user based on the user-associated insurance information. This effectively integrates multi-dimensional user data, including personal basic information, associated insurance and credit information, and actual risk assessment results, thereby improving the accuracy of insurance product recommendations and solving the problem of inaccurate recommendations caused by single information in traditional methods, thereby improving the accuracy of insurance product recommendations.

[0077] In step S101 of some embodiments, the insured reference user refers to an individual or entity that has purchased an insurance product. User policy information refers to all insurance contract information related to the insured reference user, including the insured reference user's personal information, insurance type, insured amount, premium, insurance period, etc. The target user refers to an individual or entity that the insurance company hopes to recommend an insurance product to. Basic user information refers to the basic information of the target user, such as name, age, gender, occupation, family status, etc.

[0078] This application can query the insurance company's database system, extract the policy records of the insured reference user and the personal information of the target user, and thus obtain the user's policy information and basic user information.

[0079] In step S102 of some embodiments, user insurance information refers to specific information about the user's insurance purchase, and the user insurance information may include insurance type, insured amount, premium, insurance period, coverage, etc. For example, the health insurance contract purchased by Zhang San records in detail that his insured amount is 500,000 yuan, the annual premium is 5,000 yuan, and the insurance period is 30 years, wherein the insured amount, annual premium and insurance period are all Zhang San's user insurance information. User credit information refers to information used to assess the risk level of the insured reference user, and the user credit information may include information such as claim settlement history, credit record, transaction behavior, insurance fraud record, etc.

[0080] The present application can obtain specific policy fields by first performing text recognition on the insurance policy information of the insured reference user, and then performing detailed data recognition on these policy fields to distinguish between the insurance information field and the credit information field, and then, extracting data from the insurance information field and the credit information field respectively to obtain the insurance information and user credit information of the insured reference user.

[0081] For details, see Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S203:

[0082] Step S201, performing text recognition on the user's insurance policy information to obtain the insurance policy fields;

[0083] Step S202, data recognition is performed on the policy fields to obtain the insurance information field and the credit information field;

[0084] Step S203, extracting data from the insurance information field to obtain the user's insurance information, and extracting data from the credit information field to obtain the user's credit information.

[0085] In step S201 of some embodiments, the policy field refers to a specific data item in the user's policy information, such as the name of the insured, the insurance amount, the premium, etc.

[0086] This application can use natural language processing technology to identify the text in the user's insurance policy information, thereby extracting the policy fields.

[0087] In step S202 of some embodiments, the insurance information field refers to data items in the policy field that are directly related to the user's insurance behavior, such as insurance type, insured amount, premium, etc. The credit information field refers to data items in the policy field that are related to the user's credit status, such as credit score, historical repayment record, etc.

[0088] Data identification refers to the process of identifying specific data items in the identified policy fields and distinguishing between insurance information and credit information.

[0089] The present application can identify special phrases in the policy fields through the technology of named entity recognition, thereby realizing the classification of the policy fields and obtaining the insurance information field and the credit information field.

[0090] In step S203 of some embodiments, data extraction refers to the process of extracting specific information from the identified data items to form structured data.

[0091] This application can use data analysis technology to extract the above-mentioned insurance information and credit information, thereby obtaining user insurance information and user credit information.

[0092] In steps S201 to S203 shown in this embodiment, text recognition is performed on the user's insurance policy information to obtain the insurance policy field. Then, data recognition is performed on the insurance policy field to obtain the insurance information field and the credit information field. Subsequently, data extraction is performed on the insurance information field to obtain the user's insurance information, and data extraction is performed on the credit information field to obtain the user's credit information, thereby ensuring the accuracy and structuring of the information and providing a solid data foundation for subsequent credit evaluation and personalized insurance product recommendations.

[0093] In step S103 of some embodiments, the insured associated users refer to other insured users who have a family relationship with the target user, wherein the family relationship may be a relationship such as spouse, child or parent.

[0094] Based on the collected user insurance information, a user insurance relationship network is constructed, which shows the insurance association between the insured reference users. Furthermore, using the basic user information of the target user, an in-depth associated user information query is performed on the constructed user insurance relationship network, thereby collecting the insurance policy information of the insured associated users who have a family relationship with the target user, that is, the user associated insurance information.

[0095] For details, see Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S302:

[0096] Step S301, constructing a relationship network based on the user's insurance information to obtain the user's insurance relationship network;

[0097] Step S302: Based on the basic user information, query the associated nodes of the user insurance relationship network to obtain the user associated insurance information.

[0098] In step S301 of some embodiments, the user insurance relationship network refers to a network constructed based on user insurance information, which is used to display the insurance relationship between users.

[0099] This application extracts the insurance party entities by performing entity recognition on the user's insurance information. Subsequently, the relationship recognition is performed on these insurance party entities to determine the relationship between the entities. Using these entity relationships, the solution further constructs a network to connect the insurance party entities into a user relationship network. Finally, according to the user's insurance information, the user relationship network is filled with information to form a detailed user insurance relationship network, which fully displays the insurance relationship between users.

[0100] For details, see Figure 4 In some embodiments, step S301 may include but is not limited to steps S401 to S404:

[0101] Step S401, performing entity identification on the user's insurance information to obtain the insurance party entity;

[0102] Step S402, identifying the relationship of the insurance party entity to obtain the entity relationship;

[0103] Step S403, based on the entity relationship, a network is constructed for the insurance party entity to obtain a user relationship network;

[0104] Step S404: Fill in the user relationship network based on the user insurance information to obtain the user insurance relationship network.

[0105] In step S401 of some embodiments, the insurance party entity refers to an individual or organization involved in the insurance contract, such as the policyholder, the insured, the beneficiary, etc.

[0106] This application can extract insurance party entities, such as policyholders, insured persons, etc., from user insurance information through named entity recognition technology.

[0107] In step S402 of some embodiments, the entity relationship refers to the connection between insurance party entities, such as family members, co-insured persons, etc.

[0108] This application can obtain the entity relationship by identifying the relationship between the insurance party entities mentioned in the user's insurance information.

[0109] In step S403 of some embodiments, the user relationship network refers to a network built based on entity relationships, showing the connections between users, such as family relationships, social relationships, etc.

[0110] This application can utilize the entity relationships between the above-mentioned insurance party entities to construct a network, with the insurance party entities as network nodes and the entity relationships as network edges, thereby forming a user relationship network.

[0111] In step S404 of some embodiments, the present application forms a detailed user insurance relationship network by filling in specific user insurance information, such as insurance type, insurance amount, etc., based on the user relationship network.

[0112] In steps S401 to S404 shown in this embodiment, entity identification is performed on the user's insurance information to obtain the insurance party entity, and then relationship identification is performed on the insurance party entity to obtain the entity relationship. Further, based on the entity relationship, a network is constructed for the insurance party entity to obtain a user relationship network. Then, based on the user's insurance information, information is filled in the user relationship network to obtain a user insurance relationship network, which enhances the understanding of the user's insurance needs and improves the personalization and accuracy of insurance services, and can provide users with more accurate insurance product recommendations, thereby improving user satisfaction and business efficiency.

[0113] In step S302 of some embodiments, the associated node query refers to the process of searching for other users related to the target user in the user insurance relationship network.

[0114] This application performs node query in the user insurance relationship network based on basic user information to locate the target user node. Then, starting from the target user node, a connection node query is performed in the user insurance relationship network to identify the associated user nodes that are directly or indirectly connected to the target user node. Finally, information is extracted from these associated user nodes to obtain the user-associated insurance information of the target user.

[0115] For details, see Figure 5 In some embodiments, step S302 may include but is not limited to steps S501 to S503:

[0116] Step S501, based on basic user information, query the user insurance relationship network to obtain the target user node;

[0117] Step S502: Based on the target user node, query the connection nodes of the user insurance relationship network to obtain the associated user node;

[0118] Step S503: extract information from the associated user node to obtain user-associated insurance information.

[0119] In step S501 of some embodiments, the target user node refers to a node representing a specific target user in the user insurance relationship network.

[0120] Node query refers to the process of searching for specific nodes in the user's insurance relationship network.

[0121] This application can use basic user information as a query condition to locate and identify the node representing the target user in the user insurance relationship network, thereby obtaining the target user node.

[0122] In step S502 of some embodiments, the associated user nodes refer to other user nodes directly or indirectly connected to the target user node in the user insurance relationship network, representing insured users who have family or other relationships with the target user.

[0123] Connection node query refers to the process of finding other nodes connected to the target user node in the user insurance relationship network.

[0124] The present application can start from the target user node and search for other user nodes directly or indirectly connected to the target user node in the user insurance relationship network. These nodes represent insurance reference users who have family or other relationships with the target user.

[0125] In step S503 of some embodiments, information extraction refers to the process of extracting specific data and information from the user insurance relationship network, for example, extracting insurance policy information associated with the user node.

[0126] This application can obtain the user-related insurance information of the target user by extracting the relevant policy information, such as insurance type, insured amount, premium, etc., from the identified associated user node.

[0127] In steps S501 to S503 shown in this embodiment, a node query is performed on the user insurance relationship network based on basic user information to obtain a target user node, and then a connection node query is performed on the user insurance relationship network based on the target user node to obtain an associated user node. Further, information is extracted from the associated user node to obtain user associated insurance information, which can achieve a comprehensive grasp of the insurance status of the target user and his family members, enhance the personalization and accuracy of insurance services, and in addition, provide a basis for insurance product recommendations.

[0128] In steps S301 to S302 shown in this embodiment, a relationship network is constructed based on the user's insurance information to obtain the user's insurance relationship network, and then based on the basic user information, an associated node query is performed on the user's insurance relationship network to obtain the user's associated insurance information, thereby achieving a comprehensive grasp of the insurance needs and status of the target user and his or her family members, facilitating subsequent insurance analysis of the target user, and improving the accuracy of insurance product recommendations.

[0129] In step S104 of some embodiments, the method of querying the user credit information based on the basic user information to obtain the user-associated credit information is similar to the method of querying the user insurance information based on the basic user information to obtain the user-associated insurance information in step S103, so it is not repeated here.

[0130] In step S105 of some embodiments, credit evaluation refers to the process of systematically analyzing and evaluating the credit status of the target user to determine the credit grade or credit category of the target user.

[0131] The present application can obtain credit features by performing feature extraction on user-associated credit information, and then assign weights to the credit features to determine the importance of each credit feature in credit assessment. Further, using the feature weights, data evaluation is performed on the credit features to generate credit assessment data. Finally, based on the credit assessment data, the credit features are classified to determine the user assessment category of the target user, which reflects the user's credit status and risk level.

[0132] It should be noted that the user assessment category includes a trusted user category and a risky user category, wherein the trusted user category is used to indicate that the target user is a non-risky user, and the risky user category is used to indicate that the target user is a risky user.

[0133] For details, see Figure 6 In some embodiments, step S105 may include but is not limited to steps S601 to S604:

[0134] Step S601, extracting features from user-related credit information to obtain credit features;

[0135] Step S602, weighting the credit features to obtain feature weights;

[0136] Step S603, based on the feature weights, perform data evaluation on the credit features to obtain credit evaluation data;

[0137] Step S604: classify the credit characteristics based on the credit evaluation data to obtain a user evaluation category.

[0138] In step S601 of some embodiments, the credit feature refers to a key attribute or indicator extracted from the user-associated credit information, which can be used to evaluate the user's credit status, where the credit feature can be the number of overdue payments, the average credit balance, etc.

[0139] Feature extraction refers to identifying and extracting key information that is helpful for credit assessment from a large amount of user-related credit information.

[0140] This application can ensure the quality and consistency of the data by thoroughly cleaning and formatting the user's associated credit information, and then use data mining techniques, such as association rule learning, to identify common patterns and correlations in user credit behavior. Then, through machine learning algorithms, such as support vector machines or neural networks, the user's associated credit information is deeply analyzed to extract key features that can represent the user's credit status, such as the user's overdue repayment record, the average balance of the credit account, and the credit utilization rate.

[0141] In step S602 of some embodiments, the feature weight represents the importance or influence of each credit feature in the credit assessment, and a credit feature with a high weight has a greater impact on the final credit assessment result.

[0142] Weight allocation refers to assigning a weight value to each credit feature based on its importance.

[0143] This application can use statistical analysis or machine learning algorithms to determine the degree of influence of each credit feature on the user's credit status, and assign weights to the credit features accordingly to obtain feature weights. For example, a logistic regression model can be used to evaluate the impact of different credit features on the probability of default, and weights can be assigned accordingly.

[0144] In step S603 of some embodiments, the credit assessment data is data calculated based on the credit characteristics and their weights, and is used to reflect the credit status of the user.

[0145] The present application can combine feature weights to calculate the target user's credit score or credit level through a mathematical model. For example, based on the feature weight set credit features, a weighted sum formula can be used to calculate the target user's credit assessment data.

[0146] In step S604 of some embodiments, feature classification refers to classifying the target user into different credit levels according to the credit evaluation data.

[0147] This application can determine the user assessment category of the target user by setting a credit assessment threshold and then comparing the target user's credit assessment data with the credit assessment threshold.

[0148] In steps S601 to S604 shown in this embodiment, the credit features are extracted from the user-related credit information to obtain the credit features, and then the credit features are weighted to obtain the feature weights. Furthermore, the credit features are evaluated based on the feature weights to obtain the credit evaluation data, and then the credit features are classified based on the credit evaluation data to obtain the user evaluation category, thereby improving the accuracy of the credit evaluation and facilitating the provision of more accurate insurance product recommendations to users.

[0149] In step S106 of some embodiments, preset insurance products can be screened according to the trusted user category and basic user information to determine candidate insurance products suitable for the target user. Next, the insurance information of the insured associated user is extracted from the user-associated insurance information. Finally, the insurance information of the insured associated user is used to further screen the candidate insurance products to ultimately determine the target insurance that best suits the needs and risk conditions of the target user.

[0150] For details, see Figure 7 In some embodiments, step S106 may include but is not limited to steps S701 to S703:

[0151] Step S701, based on the trusted user category and basic user information, screen the preset insurance products to obtain candidate insurances;

[0152] Step S702, extracting the user-related insurance information to obtain the related user insurance information;

[0153] Step S703: Screen candidate insurances based on the associated user insurance information to obtain target insurances.

[0154] In step S701 of some embodiments, the candidate insurance refers to a list of insurance products that are preliminarily screened based on basic user information and that may be suitable for the target user.

[0155] This application can determine that the target user is a non-dedicated user based on the trusted user category. Therefore, insurance recommendations can be made to the target user. Furthermore, based on the target user's basic user information, the target user's personal needs can be predicted. Then, the pre-built insurance product list can be screened according to the personal needs to obtain candidate insurance.

[0156] In step S702 of some embodiments, the associated user insurance information refers to the insurance information of the insured associated user.

[0157] The present application can use natural language processing technology to lock the information of each insured associated user in the user-associated insurance information, and further extract the information to obtain the insurance information of the associated user.

[0158] In step S703 of some embodiments, the family needs of the target user can be analyzed based on the insurance information of the associated user of the insured associated user, and the family insurance strategy can be used to analyze the family needs of the target user, and then the personal needs of the target user and the family needs can be combined to obtain the target needs of the target user. Further, the target insurance that meets the target needs can be screened out from the candidate insurances.

[0159] In steps S701 to S703 shown in this embodiment, the preset insurance products are screened according to the trusted user category and basic user information to obtain candidate insurances, and then the user-related insurance information is extracted to obtain the associated user insurance information. Subsequently, based on the associated user insurance information, the candidate insurances are screened to obtain the target insurance, thereby ensuring the accuracy of the insurance recommendations and being able to provide users with the insurance plan that best suits their personal circumstances.

[0160] The present application obtains the insurance policy information of the insured reference user and the basic user information of the target user, and then extracts information from the user insurance policy information to obtain the user insurance information and user credit information of the insured reference user. On this basis, the basic user information of the target user is used to further query the user insurance information and user credit information to obtain the user-associated insurance information and user-associated credit information associated with the target user. Subsequently, a comprehensive credit assessment is performed on the target user based on the user-associated credit information to form a user assessment category. When the user assessment category is a trusted user category, insurance product recommendations are provided to the target user based on the user-associated insurance information. This effectively integrates multi-dimensional user data, including personal basic information, associated insurance and credit information, and actual risk assessment results, thereby improving the accuracy of insurance product recommendations and solving the problem of inaccurate recommendations caused by single information in traditional methods, thereby improving the accuracy of insurance product recommendations.

[0161] See also Figure 8 The embodiment of the present application further provides an insurance product recommendation device, which can implement the above-mentioned insurance product recommendation method, and the device includes:

[0162] Information acquisition module 801, used to acquire user policy information of the insured reference user and basic user information of the target user;

[0163] The information extraction module 802 is used to extract the user's insurance policy information to obtain the user's insurance information and user credit information;

[0164] The associated insurance information query module 803 is used to query the user insurance information based on the basic user information to obtain the user associated insurance information, wherein the user associated insurance information represents the user policy information of the insured associated user, and the insured associated user is the insured reference user who has a family relationship with the target user;

[0165] The associated credit information query module 804 is used to query the user credit information based on the basic user information to obtain the user associated credit information, wherein the user associated credit information represents the user credit information of the insured associated user;

[0166] The credit evaluation module 805 is used to perform credit evaluation on the target user based on the user-associated credit information to obtain a user evaluation category, wherein the user evaluation category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user;

[0167] The insurance recommendation module 806 is used to recommend insurance to the target user based on the trusted user category and the user-related insurance information.

[0168] The specific implementation of the insurance product recommendation device is basically the same as the specific implementation of the above-mentioned insurance product recommendation method, and will not be repeated here.

[0169] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned insurance product recommendation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0170] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0171] 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;

[0172] 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 insurance product recommendation method of the embodiment of this application;

[0173] Input / output interface 903, used to implement information input and output;

[0174] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0175] 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);

[0176] 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 .

[0177] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned insurance product recommendation method is implemented.

[0178] 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.

[0179] The insurance product recommendation method, insurance product recommendation device, electronic device and storage medium provided in the embodiments of the present application obtain user policy information of an insured reference user, obtain basic user information of a target user, and then extract information from the user policy information to obtain user insurance information and user credit information. Furthermore, based on the basic user information, information query is performed on the user insurance information to obtain user-associated insurance information, wherein the user-associated insurance information represents user policy information of an insured associated user, and the insured associated user is an insured reference user who has a family relationship with the target user. At the same time, based on the basic user information, information query is performed on the user credit information to obtain user-associated credit information, wherein the user-associated credit information represents user credit information of the insured associated user. Subsequently, based on the user-associated credit information, a credit assessment is performed on the target user to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user. Finally, insurance recommendations are made to the target user based on the trusted user category and the user-associated insurance information.

[0180] 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.

[0181] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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. 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application 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 application should be within the scope of the rights of the present application.

Claims

1. A method for recommending insurance products, characterized in that: The method comprises: Obtain the user policy information of the insured reference user and the basic user information of the target user; Extracting the user's insurance policy information to obtain the user's insurance information and user's credit information; Based on the basic user information, query the user insurance information to obtain user-related insurance information, wherein the user-related insurance information represents the user policy information of the insurance-related user, and the insurance-related user is an insurance reference user who has a family relationship with the target user; Based on the basic user information, query the user credit information to obtain user-related credit information, wherein the user-related credit information represents the user credit information of the insured associated user; Based on the user-associated credit information, a credit assessment is performed on the target user to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user; Based on the trusted user category and the user-associated insurance information, insurance recommendations are made to the target user.

2. The method according to claim 1, characterized in that The step of performing a credit evaluation on the target user based on the user-associated credit information to obtain a user evaluation category includes: Extracting features from the user-associated credit information to obtain credit features; Performing weight allocation on the credit features to obtain the feature weights; Based on the feature weights, data evaluation is performed on the credit features to obtain credit evaluation data; Based on the credit evaluation data, the credit characteristics are classified to obtain the user evaluation category.

3. The method according to claim 1, characterized in that The querying of the user's insurance information based on the basic user information to obtain the user-related insurance information includes: Based on the user insurance information, a relationship network is constructed to obtain a user insurance relationship network; Based on the basic user information, the user insurance relationship network is queried for associated nodes to obtain the user associated insurance information.

4. The method according to claim 3, characterized in that The step of constructing a relationship network based on the user insurance information to obtain a user insurance relationship network includes: Perform entity identification on the user's insurance information to obtain the insurance party entity; Perform relationship identification on the insurance party entity to obtain entity relationship; Based on the entity relationships, a network is constructed for the insurance party entities to obtain a user relationship network; Based on the user insurance information, the user relationship network is filled with information to obtain the user insurance relationship network.

5. The method according to claim 3, characterized in that: The querying of associated nodes on the user insurance relationship network based on the basic user information to obtain the user associated insurance information includes: Based on the basic user information, query the user insurance relationship network to obtain the target user node; Based on the target user node, query the connection nodes of the user insurance relationship network to obtain the associated user node; Information is extracted from the associated user node to obtain the user-associated insurance information.

6. The method according to any one of claims 1 to 5, characterized in that: The recommending insurance to the target user based on the trusted user category and the user-associated insurance information includes: Based on the trusted user category and the basic user information, screening the preset insurance products to obtain candidate insurances; Extracting the user-related insurance information to obtain the related user insurance information; Based on the associated user insurance information, the candidate insurances are screened to obtain target insurance.

7. The method according to any one of claims 1 to 5, characterized in that: The extracting of the user's insurance policy information to obtain the user's insurance information and the user's credit information includes: Performing text recognition on the user's insurance policy information to obtain insurance policy fields; Performing data recognition on the policy fields to obtain the insurance information field and the credit information field; Data is extracted from the insurance information field to obtain the user insurance information, and data is extracted from the credit information field to obtain the user credit information.

8. An insurance product recommendation device, characterized in that: The device comprises: An information acquisition module is used to obtain the user policy information of the insured reference user and the basic user information of the target user; An information extraction module is used to extract the user's insurance policy information to obtain the user's insurance information and user credit information; An associated insurance information query module is used to query the user insurance information based on the basic user information to obtain user associated insurance information, wherein the user associated insurance information represents the user policy information of the insured associated user, and the insured associated user is an insured reference user who has a family relationship with the target user; An associated credit information query module, used to query the user credit information based on the basic user information to obtain user associated credit information, wherein the user associated credit information represents the user credit information of the insured associated user; A credit assessment module, configured to perform a credit assessment on the target user based on the user-associated credit information to obtain a user assessment category, wherein the user assessment category includes a trusted user category, and the trusted user category is used to indicate that the target user is a non-risk user; The insurance recommendation module is used to recommend insurance to the target user based on the trusted user category and the user-related insurance information.

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 insurance product recommendation method according to 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 insurance product recommendation method according to any one of claims 1 to 7 is implemented.

Images