Insurance product recommendation method and related device

Abstract

The embodiment of the invention provides an insurance product recommendation method and a related device, and belongs to the technical field of artificial intelligence. The method comprises the following steps: determining at least one insurance product matched with customer information according to the customer information; each insurance product is matched with target information to obtain a corresponding evaluation index, the target information represents the policy and regulation information related to the insurance industry, and a corresponding evaluation coefficient is obtained according to the evaluation index of each insurance product; and in response to the evaluation coefficient, indicating that the corresponding insurance product conforms to policies and regulations related to the insurance industry, determining the insurance product as a target insurance product, and recommending the target insurance product to the customer. According to the embodiment of the invention, the insurance products can be matched with the policies and regulations related to the insurance industry, and the target insurance products meeting the policies and regulations are recommended to clients.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an insurance product recommendation method and related devices. Background Art

[0002] In the existing insurance industry and related products, traditional insurance sales and customer service systems find it difficult to effectively process and analyze complex insurance policies and insurance product information. When policies and regulations related to the insurance industry change rapidly, insurance products recommended by intelligence may be difficult to meet current policies and regulations.

[0003] Therefore, there is an urgent need for a method to recommend insurance products that meet current policies and regulations to customers. 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, electronic device, storage medium and computer product, aiming to improve the effectiveness 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] Acquire customer information of the customer, and determine at least one insurance product matching the customer information based on the customer information;

[0007] Matching each of the at least one insurance product with the target information to obtain at least one evaluation indicator corresponding to each of the insurance products, wherein the target information is information representing the policies and regulations related to the insurance industry, and the evaluation indicator is used to indicate whether the corresponding insurance product complies with the target type policies and regulations corresponding to the policies and regulations related to the insurance industry, and the target type policies and regulations corresponding to each of the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry;

[0008] Obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each of the insurance products, the evaluation coefficient being used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry;

[0009] In response to the evaluation coefficient indicating that the corresponding insurance product complies with the policies and regulations related to the insurance industry, determining the insurance product as a target insurance product;

[0010] Recommend the target insurance product to the customer.

[0011] In conjunction with the first aspect, in one implementation, before determining at least one insurance product matching the customer information according to the customer information, the method further includes:

[0012] Obtain at least one existing insurance product to be recommended;

[0013] Acquire information related to each of the at least one insurance product to be recommended, perform information extraction processing on the information related to each of the insurance products to be recommended, and obtain index information of each of the insurance products to be recommended;

[0014] Training a preset model with the index information corresponding to each of the insurance products to be recommended to obtain a trained target model;

[0015] The determining, based on the customer information, at least one insurance product matching the customer information comprises:

[0016] The customer information is input into the target model to obtain at least one insurance product matching the customer information.

[0017] In combination with the first aspect, in one implementation, the information extraction process is performed on the information related to each of the insurance products to be recommended to obtain index information of each of the insurance products to be recommended, including:

[0018] Loading information related to the insurance product to be recommended as a document object;

[0019] Segment the document object corresponding to the insurance product to be recommended into multiple text segments by using a paragraph segmentation method and a preset fixed length;

[0020] The multiple text segments corresponding to the insurance products to be recommended are converted into target vectors, and the target vectors are used as index information representing the insurance products to be recommended.

[0021] In combination with the first aspect, in one embodiment, the above-mentioned target information includes at least one item of first category policy and regulatory information, second category policy and regulatory information, and third category policy and regulatory information; the first category policy and regulatory information is information representing policies and regulations related to normative requirements for insurance terms of insurance products, the second category policy and regulatory information is information representing policies and regulations related to specific policy orientations, and the third category policy and regulatory information is information representing policies and regulations that insurance companies corresponding to insurance products must comply with in the course of their operations.

[0022] In combination with the first aspect, in one implementation, if the at least one evaluation indicator includes at least two evaluation indicators, obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product includes:

[0023] Obtaining a weight set for each evaluation indicator in the at least one evaluation indicator;

[0024] The evaluation indexes and their corresponding weights are weighted and summed to obtain the evaluation coefficient corresponding to the insurance product.

[0025] In combination with the first aspect, in one implementation, if the at least one evaluation indicator includes only one evaluation indicator, obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product includes:

[0026] The evaluation index corresponding to the insurance product is used as the evaluation coefficient corresponding to the insurance product.

[0027] 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:

[0028] A product acquisition module, used to acquire customer information of a customer and determine at least one insurance product matching the customer information according to the customer information;

[0029] An indicator determination module, used for matching each of the at least one insurance product with target information to obtain at least one evaluation indicator corresponding to each of the insurance products, wherein the target information is information representing the policies and regulations related to the insurance industry, and the evaluation indicator is used to indicate whether the corresponding insurance product complies with the target type policies and regulations corresponding to the policies and regulations related to the insurance industry, and the target type policies and regulations corresponding to each of the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry;

[0030] A coefficient determination module, used to obtain a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product, wherein the evaluation coefficient is used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry;

[0031] A product determination module, configured to determine the insurance product as a target insurance product in response to the insurance product corresponding to the evaluation coefficient indicating compliance with the policies and regulations related to the insurance industry;

[0032] The product recommendation module is used to recommend the target insurance product to the customer.

[0033] In some embodiments, the device further includes a model training module, which is used to obtain at least one existing insurance product to be recommended; obtain information related to each of the at least one insurance product to be recommended, perform information extraction processing on the information related to each of the insurance products to be recommended, and obtain index information of each of the insurance products to be recommended; train a preset model with the index information corresponding to each of the insurance products to be recommended, and obtain a trained target model;

[0034] In some embodiments, the product acquisition module is further used to input the customer information into the target model to obtain at least one insurance product matching the customer information.

[0035] In some embodiments, the model training module is also used to load the information related to the insurance product to be recommended as a document object; segment the document object corresponding to the insurance product to be recommended into multiple text segments through a paragraph segmentation method and a preset fixed length; convert the multiple text segments corresponding to the insurance product to be recommended into target vectors, and use the target vectors as index information to characterize the insurance product to be recommended.

[0036] In some embodiments, the coefficient determination module is further used to obtain the weight set for each evaluation indicator in the at least one evaluation indicator; perform weighted summation on each evaluation indicator and the corresponding weight to obtain the evaluation coefficient corresponding to the insurance product.

[0037] In some embodiments, the coefficient determination module is further used to use the evaluation index corresponding to the insurance product as the evaluation coefficient corresponding to the insurance product.

[0038] To achieve the above-mentioned purpose, the 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.

[0039] 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.

[0040] To achieve the above objective, a fifth aspect of an embodiment of the present application proposes a computer product, which includes the electronic device described in the third aspect.

[0041] The insurance product recommendation method and device, electronic device, storage medium and computer product proposed in the present application obtain the customer information of the customer, determine at least one insurance product matching the customer information according to the customer information; match each of the at least one insurance product with the target information to obtain at least one evaluation index corresponding to each of the insurance products, wherein the target information is information representing the policies and regulations related to the insurance industry, the evaluation index is used to indicate whether the corresponding insurance product complies with the target type policies and regulations corresponding to the policies and regulations related to the insurance industry, and the target type policies and regulations corresponding to each of the at least one evaluation index are different types of policies and regulations in the policies and regulations related to the insurance industry; obtain the corresponding evaluation coefficient according to the at least one evaluation index of each of the insurance products, the evaluation coefficient is used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry; in response to the evaluation coefficient indicating that the corresponding insurance product complies with the policies and regulations related to the insurance industry, determine the insurance product as a target insurance product, and recommend the target insurance product to the customer. In this way, by matching the insurance product with the policies and regulations related to the insurance industry, the target insurance product that meets the policies and regulations is recommended to the customer. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the insurance product recommendation method provided in an embodiment of the present application;

[0043] Figure 2 The embodiment of this application provides Figure 1 Flow chart of step S103;

[0044] Figure 3 The embodiment of this application provides Figure 1 Flow chart of the steps before step S101;

[0045] Figure 4 The embodiment of this application provides Figure 3 Flow chart of step S302;

[0046] Figure 5 A schematic diagram of the structure of the insurance product recommendation device provided in an embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0048] 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.

[0049] 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.

[0050] 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.

[0051] First, some nouns involved in this application are analyzed:

[0052] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a 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.

[0053] 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 often 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.

[0054] Information Extraction: A text processing technology that extracts specified types of entity, relationship, event and other factual information from natural language text and forms structured data output. Information extraction is a technology that extracts specific information from text data. Text data is composed of some specific units, such as sentences, paragraphs, and chapters. Text information is composed of some small specific units, such as characters, words, phrases, sentences, paragraphs, or a combination of these specific units. Extracting noun phrases, names, place names, etc. from text data are all text information extraction. Of course, the information extracted by text information extraction technology can be various types of information.

[0055] Based on this, the embodiments of the present application provide an insurance product recommendation method and device, electronic device, storage medium and computer product, aiming to improve the accuracy of insurance product recommendations.

[0056] The insurance product recommendation method and device, electronic device, storage medium and computer product provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the insurance product recommendation method in the embodiments of the present application is described.

[0057] 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.

[0058] 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.

[0059] The insurance product recommendation method provided in the embodiment of the present application relates to the field of artificial intelligence 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.

[0060] 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.

[0061] 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 relevant laws, regulations, and standards. 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.

[0062] 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 S105.

[0063] Step S101, obtaining customer information of a customer, and determining at least one insurance product matching the customer information based on the customer information.

[0064] The above-mentioned customer information may include the customer's basic information, financial information, health information, family information and historical insurance status. Basic information may include age, gender, occupation, education level, etc. Financial information may include income, assets, liabilities, etc. Health information may include health status, medical history, physical examination report, etc. Family information may include marital status, number of children, health status of family members, etc. Historical insurance status may include purchased insurance products, claims history, etc.

[0065] In one embodiment, the customer information data may be preprocessed, such as data cleaning, feature engineering, feature selection, etc. Data cleaning is to remove duplicate records and process missing values, feature engineering is to encode categorical data and standardize or normalize numerical data, and feature selection is to select the most influential features using correlation analysis, feature importance assessment, and other methods.

[0066] The types of insurance products can be divided into insurance products related to financial management (financial management insurance), insurance products related to education funds, or insurance products related to accident insurance (personal accident insurance), etc. By matching with customer information, insurance products that match customer needs can be obtained.

[0067] Specifically, GPT's advanced natural language processing capabilities can be used to understand customer information, overcoming the limitations of traditional systems in understanding complex and diverse customer needs.

[0068] Step S102, matching each insurance product in at least one insurance product with the target information to obtain at least one evaluation indicator corresponding to each insurance product.

[0069] The at least one insurance product may include all insurance products acquired in step S101.

[0070] The above-mentioned target information represents policy and regulatory information related to the insurance industry, wherein the above-mentioned target information may include policy and regulatory information of multiple categories. Different categories of policies and regulations are used to regulate requirements in different aspects, such as insurance-related policy documents issued by local governments or policy documents involving support or regulation of insurance in specific fields.

[0071] In one implementation, an insurance policy database may be defined and created. The insurance policy database is used to store policy and regulatory information related to the insurance industry. In the insurance policy database, policies and regulations may be classified according to different topics, such as insurance product supervision policies, insurance company governance policies, insurance market regulation policies, etc. The policy texts may be analyzed and annotated to extract key information, such as policy application scope, main requirements, etc. A policy and regulation table may be established. The policy and regulation table may include fields such as policy name, issuing agency, issuing time, and main content, and an association table may be set up. The association table may be used to record the relationship between the policy and the insurance product and insurance company.

[0072] At least one evaluation index corresponding to the insurance product may be obtained by matching the insurance product with the policy and regulation table and the association table in the insurance policy database.

[0073] In one implementation, the collected policy and regulatory data is entered and checked for accuracy, policy dynamics are monitored regularly, and the insurance policy database is updated in a timely manner to ensure the timeliness of the data.

[0074] The above-mentioned evaluation indicators are used to indicate whether the corresponding insurance products comply with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry. The target-type policies and regulations corresponding to each evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry.

[0075] For example, if the target information includes first-category policies and regulations, second-category policies and regulations, and second-category policies and regulations, then at least one evaluation indicator includes a first evaluation indicator, a second evaluation indicator, and a third evaluation indicator, wherein the target-category policies and regulations corresponding to the first evaluation indicator, the second evaluation indicator, and the third evaluation indicator are first-category policies and regulations, second-category policies and regulations, and second-category policies and regulations, respectively, then the first evaluation indicator is used to indicate whether the corresponding insurance product complies with the first-category policies and regulations, the second evaluation indicator is used to indicate whether the corresponding insurance product complies with the second-category policies and regulations, and the third evaluation indicator is used to indicate whether the corresponding insurance product complies with the third-category policies and regulations.

[0076] In one embodiment, a first value and a second value may be set, the first value being used to indicate that the corresponding insurance product complies with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry, and the second value being used to indicate that the corresponding insurance product does not comply with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry. The first value is greater than the second value. If the corresponding insurance product complies with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry, the evaluation index assigned to the insurance product is the first value. If the corresponding insurance product does not comply with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry, the evaluation index assigned to the insurance product is the second value.

[0077] For example, the first value is 1, the second value is 0, and the target information includes the first category of policies and regulations, the second category of policies and regulations, and the third category of policies and regulations. For insurance product A, if insurance product A complies with the first category of policies and regulations, the first evaluation index of insurance product A is 1; if insurance product A does not comply with the second category of policies and regulations, the second evaluation index of insurance product A is 0; if insurance product A complies with the third category of policies and regulations, the third evaluation index of insurance product A is 1.

[0078] Step S103, obtaining a corresponding evaluation coefficient according to at least one evaluation indicator of each insurance product.

[0079] The above evaluation coefficients are used to indicate whether the corresponding insurance products comply with policies and regulations related to the insurance industry.

[0080] In one implementation, a comprehensive evaluation is performed using multiple evaluation indicators of the insurance product to obtain an evaluation coefficient of the insurance product.

[0081] Step S104, in response to the evaluation coefficient indicating that the corresponding insurance product complies with policies and regulations related to the insurance industry, the insurance product is determined as a target insurance product.

[0082] The above-mentioned target insurance products are insurance products recommended to customers.

[0083] In one embodiment, an evaluation coefficient threshold may be preset, and the evaluation coefficient threshold may be set based on past experience and the strictness of policy requirements. When the evaluation coefficient of an insurance product is higher than the evaluation coefficient threshold, the insurance product may be considered to comply with policies and regulations. Specifically, the evaluation coefficient is compared with the evaluation coefficient threshold. If the evaluation coefficient is greater than the evaluation coefficient threshold, the evaluation coefficient indicates that the corresponding insurance product complies with policies and regulations related to the insurance industry, and the corresponding insurance product is determined as a target insurance product. If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, the evaluation coefficient indicates that the corresponding insurance product does not comply with policies and regulations related to the insurance industry.

[0084] For example, the at least one insurance product obtained in step S101 includes insurance product A, insurance product B and insurance product C. The evaluation coefficients of insurance product A, insurance product B and insurance product C are 0.4, 0.6 and 0.7 respectively. The evaluation coefficient threshold is 0.6. If 0.7 is greater than 0.6, insurance product C is determined as the target insurance product.

[0085] Step S105, recommending the target insurance product to the customer.

[0086] For example, if the target insurance product is Insurance Product C, then Insurance Product C will be recommended to the customer.

[0087] In this embodiment, by obtaining a corresponding evaluation coefficient based on at least one evaluation indicator of the insurance product to determine the target insurance product, it is possible to comprehensively determine the target insurance product in combination with various policies and regulations, thereby improving the effectiveness of determining the target insurance product.

[0088] In some embodiments, the target information includes at least one of the first category of policy and regulatory information, the second category of policy and regulatory information, and the third category of policy and regulatory information.

[0089] The first category of policy and regulatory information mentioned above refers to information on policies and regulations that represent the normative requirements for the insurance clauses of insurance products, such as whether the clauses are clear and easy to understand and do not contain misleading content.

[0090] The second category of policy and regulatory information mentioned above is information that represents policies and regulations related to specific policy orientations, such as support for environmental protection, scientific and technological innovation and other fields.

[0091] The third category of policy and regulatory information mentioned above is information that represents the policies and regulations that the insurance company corresponding to the insurance product must comply with during its operations, such as compliant operations, risk control, etc.

[0092] See also Figure 2 In some embodiments, the at least one evaluation indicator of each insurance product may be at least two evaluation indicators, and the step S103 may include but is not limited to the following steps S201-S202:

[0093] Step S201: Obtain a weight set for each evaluation indicator in at least one evaluation indicator.

[0094] The weights corresponding to the evaluation indicators can be set according to needs.

[0095] Step S202, performing weighted summation on each evaluation indicator and the corresponding weight to obtain an evaluation coefficient corresponding to the insurance product.

[0096] The calculation formula of the evaluation coefficient can be as follows:

[0097]

[0098] Where R represents the evaluation coefficient, N represents the number of evaluation indicators in at least one evaluation indicator of the insurance product, i represents the evaluation indicator number, and P i represents the i-th evaluation indicator, k i Represents the weight corresponding to the i-th evaluation indicator.

[0099] For example, for insurance product A, the evaluation indicators are the first evaluation indicator, the second evaluation indicator and the third evaluation indicator, wherein the first evaluation indicator, the second evaluation indicator and the third evaluation indicator are 1, 0 and 1 respectively, and the corresponding weights of the first evaluation indicator, the second evaluation indicator and the third evaluation indicator are 0.2, 0.3 and 0.5 respectively, then the evaluation coefficient is 1×0.2+0×0.3+1×0.5=0.7.

[0100] If at least one evaluation indicator is only one evaluation indicator, the evaluation indicator corresponding to the insurance product shall be used as the evaluation coefficient corresponding to the insurance product.

[0101] As policies change and our understanding of policies deepens, we can continuously adjust the evaluation indicators, weights of evaluation indicators and evaluation coefficient thresholds corresponding to insurance products to improve the accuracy and effectiveness of the evaluation.

[0102] In this embodiment, the evaluation coefficient corresponding to the insurance product can be obtained by performing weighted summation on each evaluation indicator and the corresponding weight, thereby improving the effectiveness of obtaining the evaluation coefficient.

[0103] Before step S101 in some embodiments, the insurance product recommendation method further includes pre-training a preset model, which is used to predict insurance products. In one embodiment, the preset model can be a transformer model, an LSTM model, or a GPT-2 model, etc.

[0104] See also Figure 3 , before step S101 includes but is not limited to the following steps S301 to S303:

[0105] Step S301, obtaining at least one existing insurance product to be recommended.

[0106] The above-mentioned insurance products to be recommended may be insurance products that are currently available and can be used to recommend customers.

[0107] Step S302, obtaining information related to each insurance product to be recommended in at least one insurance product to be recommended, performing information extraction processing on the information related to each insurance product to be recommended, and obtaining index information of each insurance product to be recommended.

[0108] Information on various insurance products to be recommended can be collected from the company's insurance product database. The information related to the insurance products to be recommended may include product name, coverage, premium, claims conditions, clause details, applicable population, etc.

[0109] The above index information is used to indicate the corresponding insurance product to be recommended.

[0110] For example, at least one insurance product to be recommended includes insurance product A to be recommended, insurance product B to be recommended, and insurance product C to be recommended. First insurance product information related to insurance product A to be recommended is obtained, second insurance product information related to insurance product B to be recommended is obtained, and third insurance product information related to insurance product C to be recommended is obtained. Information extraction is performed on the first insurance product information to obtain index information of insurance product A to be recommended, information extraction is performed on the second insurance product information to obtain index information of insurance product B to be recommended, and information extraction is performed on the third insurance product information to obtain index information of insurance product C to be recommended.

[0111] Step S303: train a preset model with the index information corresponding to each insurance product to be recommended to obtain a trained target model.

[0112] In one embodiment, customer information of multiple historical customers and corresponding selected historical insurance products can be obtained, and the customer information of historical customers, historical insurance products, and index information corresponding to each insurance product to be recommended are used as a data set, wherein the data set is divided into a training set and a test set, and can be divided in a ratio of 7:3, that is, 70% training set and 30% test set. The customer information of historical customers in the training set and the index information corresponding to each insurance product to be recommended are used as input parameters of the preset model, and the corresponding historical insurance products are used as output parameters of the preset model to implement training of the preset model, and the performance of the trained preset model is tested with the test set, and the model parameters are adjusted as needed to optimize the model performance and obtain the target model.

[0113] Taking the transformer model as an example, the transformer model includes an encoder and a decoder. The training process of the language model includes: obtaining a sample video clip and inputting the sample video clip into the transformer model. The sample video clip is encoded by the encoder of the transformer model to obtain a sample video hidden feature vector, and the sample video hidden feature vector is decoded by the decoder of the transformer model so that the sample video hidden feature vector is matrix-multiplied with the reference word vector to obtain a video description segment, and a sample video description segment is obtained. The similarity between the sample video description segment and the reference video description segment is calculated by the loss function of the transformer model, the loss function of the transformer model is optimized according to the similarity, the model loss of the loss function is back-propagated, and the model parameters are continuously adjusted until the similarity is greater than or equal to the similarity threshold, and the optimization of the transformer model is stopped to obtain a model that meets the requirements.

[0114] The target model obtained above is used to subsequently acquire insurance products. Specifically, the customer information is input into the target model to obtain at least one insurance product that matches the customer information.

[0115] In this embodiment, a target model is trained based on index information corresponding to the insurance product to be recommended, so that insurance products matching the customer information can be quickly acquired based on the target model.

[0116] See also Figure 4 In some embodiments, the above step S302 may include but is not limited to the following steps S401 to S403:

[0117] Step S401, loading information related to the insurance product to be recommended as a document object.

[0118] In one implementation, Langchain's CSVLoader, JSONLoader, or other document loaders may be used to load information related to the insurance product to be recommended as a document object.

[0119] Step S402, segmenting the document object corresponding to the insurance product to be recommended into multiple text segments using a paragraph segmentation method and a preset fixed length.

[0120] In one embodiment, the document is segmented into smaller text segments using Langchain's Text Splitter by segmentation by paragraphs and by fixed length, thereby obtaining multiple text segments for better indexing and retrieval.

[0121] Step S403: convert multiple text segments corresponding to the insurance products to be recommended into target vectors, and use the target vectors as index information representing the insurance products to be recommended.

[0122] In one implementation, Langchain's vector store is used to convert the segmented multiple text segments into vector representations, and vector storage methods such as Faiss and Pinecone are used to store them in a vector database to establish index information.

[0123] In this embodiment, by loading the information related to the insurance product to be recommended as a document object and dividing the document object into multiple text segments to obtain a target vector to represent the index information of the insurance product to be recommended, the information of the insurance product to be recommended can be fragmented for better indexing and retrieval.

[0124] After step S105 in some embodiments, the customer may provide feedback on the recommended target insurance product. After obtaining the customer's feedback, the preset model may be optimized based on the customer's feedback.

[0125] Through the above-mentioned insurance product recommendation method, a more intelligent and efficient insurance product recommendation solution is provided, which solves the shortcomings of existing technologies in understanding customer needs, data processing and market adaptability. In addition, by utilizing GPT's advanced natural language processing capabilities, customer needs can be more accurately grasped and personalized services can be provided, thereby improving customer satisfaction. Langchain's efficient data management mechanism ensures the rapid processing and accurate analysis of complex insurance data, improves overall operational efficiency, and combines customer data and market trends to provide highly customized insurance product recommendations and enhance customer purchase willingness. In addition, it can quickly adapt to market changes and policy updates, reduce compliance risks, maintain the timeliness and relevance of services, and optimize models by learning customer feedback to improve service quality.

[0126] See also Figure 5 The embodiment of the present application further provides an insurance product recommendation device, which can implement the above-mentioned insurance product recommendation method. The device 500 includes:

[0127] Product acquisition module 501: used to acquire customer information of a customer, and determine at least one insurance product matching the customer information according to the customer information.

[0128] The above-mentioned customer information may include the customer's basic information, financial information, health information, family information and historical insurance status. Basic information may include age, gender, occupation, education level, etc. Financial information may include income, assets, liabilities, etc. Health information may include health status, medical history, physical examination report, etc. Family information may include marital status, number of children, health status of family members, etc. Historical insurance status may include purchased insurance products, claims history, etc.

[0129] The indicator determination module 502 is used to match each insurance product in at least one insurance product with the target information to obtain at least one evaluation indicator corresponding to each insurance product, wherein the target information is information representing policies and regulations related to the insurance industry, and the evaluation indicator is used to indicate whether the corresponding insurance product complies with the corresponding target type policies and regulations in the policies and regulations related to the insurance industry, and the target type policies and regulations corresponding to each evaluation indicator in the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry.

[0130] The at least one insurance product mentioned above is all insurance products acquired by the product acquisition module 501 .

[0131] The above-mentioned target information may include various categories of policy and regulatory information. Different categories of policies and regulations are used to regulate requirements in different aspects, such as insurance-related policy documents issued by local governments or policy documents involving support or regulation of insurance in specific fields.

[0132] In one embodiment, the indicator determination module 502 can define and create an insurance policy database, which is used to store policy and regulatory information related to the insurance industry, classify policies and regulations according to different topics, such as insurance product supervision policies, insurance company governance policies, insurance market regulation policies, etc., analyze and annotate policy texts, and extract key information, such as policy application scope, main requirements, etc. A policy and regulation table is established, which includes fields such as policy name, issuing agency, issuing time, main content, etc., and an association table is set up, which is used to record the relationship between policies and insurance products and insurance companies.

[0133] The indicator determination module 502 may obtain at least one evaluation indicator corresponding to the insurance product by matching the insurance product with the policy and regulation table and the association table in the insurance policy database.

[0134] The coefficient determination module 503 is used to obtain a corresponding evaluation coefficient according to at least one evaluation indicator of each insurance product, and the evaluation coefficient is used to indicate whether the corresponding insurance product complies with policies and regulations related to the insurance industry.

[0135] In one implementation, the coefficient determination module 503 performs a comprehensive evaluation through multiple evaluation indicators of the insurance product to obtain the evaluation coefficient of the insurance product.

[0136] In one embodiment, the coefficient determination module 503 can pre-set an evaluation coefficient threshold, and can set the evaluation coefficient threshold based on past experience and the strictness of policy requirements, and compare the evaluation coefficient with the evaluation coefficient threshold. If the evaluation coefficient is greater than the evaluation coefficient threshold, the evaluation coefficient indicates that the corresponding insurance product complies with policies and regulations related to the insurance industry, and the corresponding insurance product is determined as the target insurance product. If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, the evaluation coefficient indicates that the corresponding insurance product does not comply with policies and regulations related to the insurance industry.

[0137] The product determination module 504 is configured to determine the insurance product as a target insurance product in response to the evaluation coefficient indicating that the corresponding insurance product complies with policies and regulations related to the insurance industry.

[0138] In one embodiment, an evaluation coefficient threshold may be preset, and the evaluation coefficient threshold may be set based on past experience and the strictness of policy requirements. When the evaluation coefficient of an insurance product is higher than the evaluation coefficient threshold, the insurance product may be considered to comply with policies and regulations. Specifically, if the evaluation coefficient is greater than the evaluation coefficient threshold, the product determination module 504 determines that the insurance product corresponding to the evaluation coefficient indication complies with policies and regulations related to the insurance industry, and determines the corresponding insurance product as a target insurance product. If the evaluation coefficient is less than or equal to the evaluation coefficient threshold, the product determination module 504 determines that the insurance product corresponding to the evaluation coefficient indication does not comply with policies and regulations related to the insurance industry.

[0139] The product recommendation module 505 is used to recommend target insurance products to customers.

[0140] In some embodiments, the device also includes a model training module 506, which is used to obtain at least one existing insurance product to be recommended; obtain information related to each insurance product to be recommended in the at least one insurance product to be recommended, perform information extraction processing on the information related to each insurance product to be recommended, and obtain index information of each insurance product to be recommended; train a preset model with the index information corresponding to each insurance product to be recommended to obtain a trained target model.

[0141] The preset model is used to predict insurance products. In one embodiment, the preset model can be a transformer model, an LSTM model, a GPT-2 model, etc.

[0142] The above-mentioned insurance products to be recommended may be insurance products that are currently available and can be used to recommend customers.

[0143] The above index information is used to indicate the corresponding insurance product to be recommended.

[0144] The model training module 506 can collect various types of insurance product information from the company's insurance product database. The above information related to the insurance product to be recommended may include product name, coverage, premium, claim conditions, clause details, applicable population, etc.

[0145] In one embodiment, the model training module 506 can obtain the customer information of historical customers and the corresponding selected historical insurance products, and use the customer information of historical customers, historical insurance products and index information corresponding to each insurance product to be recommended as a data set, wherein the data set is divided into a training set and a test set, which can be divided in a ratio of 7:3, that is, 70% training set and 30% test set. The customer information of historical customers in the training set and the index information corresponding to each insurance product to be recommended are used as input parameters of the preset model, and the corresponding historical insurance products are used as output parameters of the preset model to train the preset model, and the performance of the trained preset model is tested with the test set, and the model parameters are adjusted as needed to optimize the model performance and obtain the target model.

[0146] In some embodiments, the model training module 506 is specifically used to: load information related to the insurance product to be recommended as a document object; segment the document object corresponding to the insurance product to be recommended into multiple text segments through a paragraph segmentation method and a preset fixed length; convert the multiple text segments corresponding to the insurance product to be recommended into a target vector, and use the target vector as index information to characterize the insurance product to be recommended.

[0147] In some embodiments, the product acquisition module 501 is specifically used to: input customer information into the target model to obtain at least one insurance product that matches the customer information.

[0148] In some embodiments, the coefficient determination module 503 is specifically used to: obtain the weight set for each evaluation indicator in at least one evaluation indicator; and perform weighted summation on each evaluation indicator and the corresponding weight to obtain the evaluation coefficient corresponding to the insurance product.

[0149] The coefficient determination module 503 can set the weight corresponding to the evaluation index according to the requirements.

[0150] In some embodiments, the coefficient determination module 503 is specifically used to: use the evaluation index corresponding to the insurance product as the evaluation coefficient corresponding to the insurance product.

[0151] The specific implementation of the insurance product recommendation device is basically the same as the specific implementation of the insurance product recommendation method. The insurance product recommendation device determines at least one insurance product that matches the customer information based on the customer information; matches each insurance product with the target information to obtain a corresponding evaluation index, wherein the target information is information representing policies and regulations related to the insurance industry, and obtains a corresponding evaluation coefficient based on the evaluation index of each insurance product. In response to the evaluation coefficient indicating that the corresponding insurance product complies with the policies and regulations related to the insurance industry, the insurance product is determined as a target insurance product, and the target insurance product is recommended to the customer. By matching the insurance product with the policies and regulations related to the insurance industry, it is possible to recommend the target insurance product that meets the policies and regulations to the customer.

[0152] 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.

[0153] See also Figure 6 , Figure 6 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0154] The processor 601 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;

[0155] Storage 602 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). Storage 602 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in storage 602, and the processor 601 calls and executes the insurance product recommendation method of the embodiment of this application;

[0156] Input / output interface 603, used to implement information input and output;

[0157] Communication interface 604, 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.);

[0158] Bus 605 , which transmits information between various components of the device (e.g., processor 601 , storage 602 , input / output interface 603 , and communication interface 604 );

[0159] The processor 601 , the storage 602 , the input / output interface 603 and the communication interface 604 are connected to each other in communication within the device via the bus 605 .

[0160] 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.

[0161] 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.

[0162] The insurance product recommendation method, insurance product recommendation device, electronic device, storage medium and computer product provided in the embodiments of the present application obtain the customer information of the customer, determine at least one insurance product that matches the customer information according to the customer information; match each insurance product in the at least one insurance product with the target information, and obtain at least one evaluation indicator corresponding to each insurance product, wherein the target information is information representing policies and regulations related to the insurance industry, the evaluation indicator is used to indicate whether the corresponding insurance product complies with the corresponding target-type policies and regulations in the policies and regulations related to the insurance industry, and the target-type policies and regulations corresponding to each evaluation indicator in the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry; obtain the corresponding evaluation coefficient according to at least one evaluation indicator of each insurance product, and the evaluation coefficient is used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry; in response to the evaluation coefficient indicating that the corresponding insurance product complies with the policies and regulations related to the insurance industry, determine the insurance product as the target insurance product, and recommend the target insurance product to the customer. In this way, by matching the insurance product with the policies and regulations related to the insurance industry, it is possible to recommend the target insurance product that meets the policies and regulations to the customer.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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 recommending insurance products, characterized in that: The method comprises: Acquire customer information of the customer, and determine at least one insurance product matching the customer information based on the customer information; Matching each of the at least one insurance product with the target information to obtain at least one evaluation indicator corresponding to each of the insurance products, wherein the target information is information representing the policies and regulations related to the insurance industry, and the evaluation indicator is used to indicate whether the corresponding insurance product complies with the target type policies and regulations corresponding to the policies and regulations related to the insurance industry, and the target type policies and regulations corresponding to each of the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry; Obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each of the insurance products, the evaluation coefficient being used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry; In response to the evaluation coefficient indicating that the corresponding insurance product complies with the policies and regulations related to the insurance industry, determining the insurance product as a target insurance product; Recommend the target insurance product to the customer.

2. The method according to claim 1, characterized in that Before determining at least one insurance product matching the customer information according to the customer information, the method includes: Obtain at least one existing insurance product to be recommended; Acquire information related to each of the at least one insurance product to be recommended, perform information extraction processing on the information related to each of the insurance products to be recommended, and obtain index information of each of the insurance products to be recommended; Training a preset model with the index information corresponding to each of the insurance products to be recommended to obtain a trained target model; The determining, based on the customer information, at least one insurance product matching the customer information comprises: The customer information is input into the target model to obtain at least one insurance product matching the customer information.

3. The method according to claim 2, characterized in that The information extraction process is performed on the information related to each of the insurance products to be recommended to obtain index information of each of the insurance products to be recommended, including: Loading information related to the insurance product to be recommended as a document object; Segment the document object corresponding to the insurance product to be recommended into multiple text segments by using a paragraph segmentation method and a preset fixed length; The multiple text segments corresponding to the insurance products to be recommended are converted into target vectors, and the target vectors are used as index information representing the insurance products to be recommended.

4. The method according to claim 1, characterized in that: The target information includes at least one of the first category of policy and regulatory information, the second category of policy and regulatory information, and the third category of policy and regulatory information; the first category of policy and regulatory information is information representing policies and regulations related to the normative requirements for the insurance terms of insurance products, the second category of policy and regulatory information is information representing policies and regulations related to specific policy orientations, and the third category of policy and regulatory information is information representing policies and regulations that the insurance company corresponding to the insurance product must comply with in the course of its operations.

5. The method according to claim 1, characterized in that If the at least one evaluation indicator includes at least two evaluation indicators, then obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product includes: Obtaining a weight set for each evaluation indicator in the at least one evaluation indicator; The evaluation indexes and their corresponding weights are weighted and summed to obtain the evaluation coefficient corresponding to the insurance product.

6. The method according to claim 1, characterized in that If the at least one evaluation indicator includes only one evaluation indicator, obtaining a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product includes: The evaluation index corresponding to the insurance product is used as the evaluation coefficient corresponding to the insurance product.

7. An insurance product recommendation device, characterized in that: The device comprises: A product acquisition module, used to acquire customer information of a customer and determine at least one insurance product matching the customer information according to the customer information; An indicator determination module, used for matching each of the at least one insurance product with target information to obtain at least one evaluation indicator corresponding to each of the insurance products, wherein the target information is information representing policies and regulations related to the insurance industry, and the evaluation indicator is used to indicate whether the corresponding insurance product complies with target-type policies and regulations corresponding to the policies and regulations related to the insurance industry, and the target-type policies and regulations corresponding to each of the at least one evaluation indicator are different types of policies and regulations in the policies and regulations related to the insurance industry; A coefficient determination module, used to obtain a corresponding evaluation coefficient according to the at least one evaluation indicator of each insurance product, wherein the evaluation coefficient is used to indicate whether the corresponding insurance product complies with the policies and regulations related to the insurance industry; A product determination module, configured to determine the insurance product as a target insurance product in response to the insurance product corresponding to the evaluation coefficient indicating compliance with the policies and regulations related to the insurance industry; The product recommendation module is used to recommend the target insurance product to the customer.

8. 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 6 when executing the computer program.

9. 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 6 is implemented.

10. A computer product, characterized in that: Comprising a computer device as claimed in claim 8.

Images