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

Abstract

The embodiment of the invention provides an insurance product combination recommendation method and device, electronic equipment and a storage medium, and belongs to the technical field of product recommendation. The method comprises the following steps: acquiring insurance type intention data, insurance input intention data, insurance guarantee range intention data and identity attribute data; screening out candidate insurance products from an insurance product library based on the insurance type intention data and the insurance input intention data, and combining the candidate insurance products according to the insurance range intention data to obtain a candidate insurance product combination; calculating identity attribute data and screening the candidate insurance product combinations to obtain at least one alternative insurance product combination; screening each alternative insurance product combination according to the identity attribute data to obtain a target insurance product combination; and performing product recommendation on the target object based on the target insurance product combination. According to the embodiment of the invention, the accuracy of insurance product combination recommendation can be improved.

Description

Technical Field

[0001] This application relates to the technical field of product recommendation, and particularly to a method and device for recommending insurance product combinations, an electronic device, and a storage medium. Background Art

[0002] When recommending insurance products to an object, it is usually recommended in a single insurance type or fixed combination manner, without fully considering the personalized insurance needs of the object, resulting in an obvious gap between the recommended insurance products and the actual needs of the object, and reducing the success rate of product recommendation. Therefore, how to improve the accuracy of insurance product combination recommendation has become an urgent technical problem to be solved. Summary of the Invention

[0003] The main purpose of the embodiments of this application is to propose a method and device for recommending insurance product combinations, an electronic device, and a storage medium, aiming to improve the accuracy of insurance product combination recommendation.

[0004] To achieve the above object, the first aspect of the embodiments of this application proposes a method for recommending insurance product combinations, and the method includes:

[0005] Obtain the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object, and obtain the identity attribute data of the target object;

[0006] Based on the insurance type intention data and the insurance investment intention data, screen out candidate insurance products from the insurance product library, and combine the candidate insurance products according to the insurance coverage intention data to obtain at least one candidate insurance product combination;

[0007] Calculate the matching degree between the identity attribute data and each of the candidate insurance product combinations to obtain the matching degree scores corresponding to each of the candidate insurance product combinations, and screen the candidate insurance product combinations based on each matching degree score to obtain at least one alternative insurance product combination;

[0008] Determine the risk bearing level and risk preference level of the target object according to the identity attribute data, and screen each of the alternative insurance product combinations based on the risk bearing level and the risk preference level to obtain the target insurance product combination;

[0009] Recommend products to the target object based on the target insurance product combination.

[0010] In some embodiments, the calculating the matching degree between the identity attribute data and each of the candidate insurance product combinations to obtain the matching degree scores corresponding to each of the candidate insurance product combinations includes:

[0011] Extract insurance coverage rules for each of the candidate insurance product combinations to obtain the coverage rules for each candidate insurance product combination;

[0012] Based on the identity attribute data and each of the coverage rules, determine the first matching degree sub-score for each candidate insurance product combination;

[0013] For each candidate insurance product combination, calculate the product matching degree for each insurance product in the candidate insurance product combination based on the identity attribute data to obtain the second matching degree sub-score;

[0014] For each candidate insurance product combination, determine the matching degree score based on the first matching degree sub-score and the second matching degree sub-score of the candidate insurance product combination.

[0015] In some embodiments, the calculating the product matching degree for each insurance product in the candidate insurance product combination based on the identity attribute data to obtain the second matching degree sub-score includes:

[0016] Perform similarity screening on each candidate clustering region based on the identity attribute data to obtain the target clustering region;

[0017] Calculate the product matching degree for each of the insurance products based on the target clustering region to obtain the second matching degree sub-score.

[0018] In some embodiments, the calculating the product matching degree for each of the insurance products based on the target clustering region to obtain the second matching degree sub-score includes:

[0019] Obtain the reference object of the target clustering region, and use the satisfaction data of the reference object for each of the insurance products as the first score for each of the insurance products;

[0020] Use the number of claim settlement times of each of the insurance products for the reference object as the second score for each of the insurance products;

[0021] Use the claim settlement value of each of the insurance products for the reference object as the third score for each of the insurance products;

[0022] Based on the first score, the second score, and the third score of each of the insurance products, determine the product score for each of the insurance products;

[0023] Perform weighted sum processing on each of the product scores to obtain the second matching degree sub-score.

[0024] In some embodiments, the determining the risk preference level of the target object according to the identity attribute data includes:

[0025] Construct a user portrait based on the identity attribute data to obtain a target object portrait;

[0026] Screen out the insurance policy purchase records, insurance policy renewal records, and insurance policy surrender records from the insurance policy record database based on the target object portrait;

[0027] Through a risk preference analysis model, perform preference analysis based on the insurance policy purchase records, the insurance policy renewal records, and the insurance policy surrender records to obtain the risk preference level.

[0028] In some embodiments, the determining the risk bearing level of the target object according to the identity attribute data includes:

[0029] Screen multiple candidate evaluation indicators according to the identity attribute data to obtain at least one target evaluation indicator;

[0030] Score the identity attribute data according to each of the target evaluation indicators to obtain the evaluation scores of each of the target evaluation indicators;

[0031] Perform weighted sum according to each of the evaluation scores to obtain a target score, and determine the risk bearing level based on the target score.

[0032] In some embodiments, the screening of each of the alternative insurance product combinations based on the risk bearing level and the risk preference level to obtain a target insurance product combination includes:

[0033] Evaluate the risk levels of each of the alternative insurance product combinations to determine the risk levels of each of the alternative insurance product combinations;

[0034] Filter out the alternative insurance product combinations whose risk levels are greater than the risk bearing level to obtain the selected insurance product combinations;

[0035] Sort the selected insurance product combinations based on the risk preference level and the risk level to obtain a selected insurance product combination sequence;

[0036] Screen the selected insurance product combination sequence to obtain the target insurance product combination.

[0037] To achieve the above object, a second aspect of the embodiments of the present application proposes a recommendation device for an insurance product combination, and the device includes:

[0038] An acquisition data module, configured to acquire the insurance type intention data, insurance investment intention data, and insurance coverage intention data of a target object, and acquire the identity attribute data of the target object;

[0039] A product portfolio module, configured to screen candidate insurance products from an insurance product library based on the insurance type intention data and the insurance investment intention data, and combine the candidate insurance products according to the insurance coverage intention data to obtain at least one candidate insurance product portfolio;

[0040] A first screening module, configured to calculate the matching degree between the identity attribute data and each of the candidate insurance product portfolios, obtain the matching degree scores corresponding to each of the candidate insurance product portfolios, and screen the candidate insurance product portfolios based on each matching degree score to obtain at least one alternative insurance product portfolio;

[0041] A second screening module, configured to determine the risk bearing level and the risk preference level of the target object according to the identity attribute data, and screen each of the alternative insurance product portfolios based on the risk bearing level and the risk preference level to obtain a target insurance product portfolio;

[0042] A product recommendation module, configured to recommend products to the target object based on the target insurance product portfolio.

[0043] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, where the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect above is implemented.

[0044] To achieve the above object, a fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where 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 above is implemented.

[0045] A recommendation method and device for an insurance product portfolio, an electronic device, and a storage medium proposed in this application. By obtaining the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object, as well as the identity attribute data of the target object, and then accurately screening candidate insurance products from the existing insurance product library based on the insurance type intention data and insurance investment intention data, and then using the insurance coverage intention data for preliminary combination to obtain at least one candidate insurance product portfolio that meets the basic needs of the target object, ensuring that the candidate insurance product portfolio meets the basic requirements of the target object; further, based on the identity attribute data, further matching degree calculations are performed on the candidate insurance product portfolios to determine the matching degree between each combination and the actual needs of the target object, and the candidate insurance product portfolios are screened based on the matching degree to obtain alternative insurance product portfolios that are more in line with the needs of the target object, further improving the accuracy of product recommendation; further, based on the identity attribute data, the risk-bearing level and risk preference level of the target object are determined. The risk-bearing level can accurately evaluate the risk tolerance of the target object, while the risk preference level can reflect the risk acceptance tendency of the target object in insurance selection, and the alternative insurance product portfolios are screened based on the risk-bearing level and risk preference level to ensure that the final recommended target insurance product portfolio can not only accurately match the needs of the target object, but also match the risk characteristics and risk willingness of the target object, realizing in-depth personalized recommendation starting from the actual needs of the target object, further improving the recommendation accuracy of the insurance product portfolio, ensuring that the final recommended target insurance product portfolio to the target object can not only accurately match the object's needs, but also highly match the object's risk characteristics and risk willingness, and finally improving the recommendation accuracy of the insurance product portfolio. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the recommendation method for the insurance product portfolio provided by the embodiment of the present application;

[0047] Figure 2 is Figure 1 the flowchart of step S103 in

[0048] Figure 3 is Figure 2 the flowchart of step S203 in

[0049] Figure 4 is Figure 3 the flowchart of step S302 in

[0050] Figure 5 is Figure 1 the flowchart of step S104 in

[0051] Figure 6 is Figure 1The flowchart of step S104 in

[0052] Figure 7 is Figure 1 The flowchart of step S101 in

[0053] Figure 8 is the structural schematic diagram of the recommended device for the insurance product portfolio provided by the embodiment of the present application;

[0054] Figure 9 is the hardware structural schematic diagram of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0055] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to 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.

[0056] 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 can be executed in a different module division in the device or a different order in the flowchart. Terms such as "first" and "second" in the description, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0058] When recommending insurance products to an object, it is usually recommended in a single insurance type or a fixed combination manner, without fully considering the personalized insurance needs of the object, resulting in an obvious gap between the recommended insurance products and the actual needs of the object, and reducing the success rate of product recommendation. Therefore, how to improve the accuracy of insurance product portfolio recommendation has become an urgent technical problem to be solved.

[0059] Based on this, the embodiments of the present application provide a method and device for recommending an insurance product portfolio, an electronic device and a storage medium, aiming to improve the accuracy of insurance product portfolio recommendation.

[0060] The method and device for recommending an insurance product portfolio, an electronic device and a storage medium provided by the embodiments of the present application will be specifically described through the following embodiments. First, the method for recommending an insurance product portfolio in the embodiments of the present application will be described.

[0061] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is 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.

[0062] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0063] The recommended method for insurance product portfolios provided by the embodiments of the present application relates to the technical field of product recommendation. The recommended method for insurance product portfolios provided by the embodiments of the present application can be applied to a terminal, can also be applied to a server side, or can also be software running on 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, can also be configured as a server cluster or a distributed system composed of multiple physical servers, or can also be configured as a cloud server providing 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 recommended method for insurance product portfolios, etc., but is not limited to the above forms.

[0064] The present application can be used in many general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet-type devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. 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 a distributed computing environment, where 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.

[0065] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing based on data related to the user's 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. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0066] Figure 1 FIG. is an alternative flowchart of the method for recommending an insurance product portfolio provided by an embodiment of the present application. Figure 1 The method in may include but is not limited to steps S101 to S105.

[0067] Step S101, obtain the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object, and obtain the identity attribute data of the target object;

[0068] Step S102, based on the insurance type intention data and insurance investment intention data, screen out candidate insurance products from the insurance product library, and combine the candidate insurance products according to the insurance coverage intention data to obtain at least one candidate insurance product portfolio;

[0069] Step S103, calculate the matching degree between the identity attribute data and each candidate insurance product portfolio, obtain the matching degree scores corresponding to each candidate insurance product portfolio, and screen the candidate insurance product portfolios based on each matching degree score to obtain at least one alternative insurance product portfolio;

[0070] Step S104, determine the risk bearing level and risk preference level of the target object according to the identity attribute data, and screen each alternative insurance product portfolio based on the risk bearing level and risk preference level to obtain the target insurance product portfolio;

[0071] Step S105, recommend products to the target object based on the target insurance product portfolio.

[0072] Steps S101 to S105 shown in the embodiments of the present application, by obtaining the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object, as well as the identity attribute data of the target object, and then based on the insurance type intention data and insurance investment intention data, accurately screening candidate insurance products from the existing insurance product library, and then using the insurance coverage intention data for preliminary combination to obtain at least one candidate insurance product combination that meets the basic needs of the target object, ensuring that the candidate insurance product combination meets the basic requirements of the target object; further calculating the further matching degree of the candidate insurance product combination based on the identity attribute data, determining the matching degree between each combination and the actual needs of the target object, and screening the candidate insurance product combination according to the matching degree to obtain an alternative insurance product combination that is more in line with the needs of the target object, further improving the accuracy of product recommendation; further, determining the risk-bearing level and risk preference level of the target object based on the identity attribute data, the risk-bearing level can accurately evaluate the risk tolerance of the target object, while the risk preference level can reflect the risk acceptance tendency of the target object in insurance selection, and screening the alternative insurance product combination based on the risk-bearing level and risk preference level, ensuring that the finally recommended target insurance product combination can not only accurately match the needs of the target object, but also match the risk characteristics and risk willingness of the target object, realizing in-depth personalized recommendation starting from the actual needs of the target object, further improving the recommendation accuracy of the insurance product combination, ensuring that the finally recommended target insurance product combination to the target object can not only accurately match the object's needs, but also highly match the object's risk characteristics and risk willingness, and finally improving the recommendation accuracy of the insurance product combination.

[0073] In step S101 of some embodiments, the insurance type intention data refers to the information data of the insurance type that the target object hopes to purchase when selecting an insurance product. For example, if the target object checks "medical insurance" and "pet insurance" in the insurance list and does not select "auto insurance", the insurance type intention data is medical insurance and pet insurance. The insurance type intention data is used to clarify the specific insurance categories that the target object is interested in, avoid recommending insurance types that the object is not interested in at all, and effectively improve the accuracy in the preliminary recommendation stage.

[0074] The insurance investment intention data refers to the expenses that the target object intends to invest in insurance, which is a range of expense intervals. For example, if the target object expects the annual insurance expense range to be 5000 to 10000, the numerical form of the insurance investment intention data can be 5000 - 10000. The insurance investment intention data is used to determine the premium range that the target object can accept and avoid recommending insurance combinations that are out of line with the object's ability.

[0075] Insurance coverage intention data refers to the intention information of the scope of protection, the amount of protection, or specific protection items that the target object hopes to obtain through insurance products. The data representation form of insurance coverage intention data is reflected in the form of specific protection items and the corresponding amount range or conditions for that item. For example, if the target object hopes that the hospitalization medical expense reimbursement amount for medical insurance is more than 100,000 yuan, and the death protection amount for personal accident insurance is not less than 200,000 yuan, then the corresponding insurance coverage intention data is "medical insurance protection amount more than 100,000 yuan, personal accident insurance protection amount more than 500,000 yuan". Insurance coverage intention data is used to determine the target object's needs for the specific protection content and amount of insurance products, so that the subsequent insurance product portfolio is within the clear scope of protection of the target object, ensuring that the product portfolio truly meets the actual needs of the target object.

[0076] Identity attribute data refers to the inherent attribute data of the target object itself. Identity attribute data is represented in the form of key-value pairs. Identity attribute data includes age, gender, occupation, income level, education level, marital status, family structure, and region. For example, if the target object is 35 years old, male, with an occupation as an IT engineer, an annual income of 150,000 yuan, married, and has a minor child, the identity attribute data can be (age: 35, gender: male, occupation: IT engineer, annual income: 150,000 yuan, marital status: married, child status: has a minor child).

[0077] Different identity attribute characteristics can lead to significant differences in the insurance needs of the target object. For example, target objects of different ages often show different preferences for insurance types. For instance, the elderly usually pay more attention to medical protection, while the young are more inclined to purchase personal accident insurance or critical illness insurance. Target objects of different genders may also show obvious differences when choosing insurance. For example, women usually pay more attention to health insurance and related insurance products, while men tend to prefer accidental injury protection or property insurance. There are also differences among target objects with different occupations. For example, target objects engaged in outdoor work usually pay more attention to accident insurance and medical insurance, while those engaged in indoor work may be more inclined to purchase insurance products that protect against diseases. In addition, target objects with a higher income level may be more inclined to choose combined products with a wide coverage range and a high amount, while those with a lower income level may be more concerned about cost-effective insurance combinations. Target objects with different educational backgrounds may also show obvious differences in their preference for insurance combination products. For example, highly educated target objects may be more inclined to choose insurance product combinations with a more refined risk coverage range and more specific protection items. Target objects who are married and have minor children usually tend to choose insurance combination products that cover family members, such as the combination of juvenile education insurance, personal accident insurance, and medical insurance. Unmarried or single target objects are more likely to focus on their own health or accident protection. In terms of family structure, for example, target objects with elderly members often tend to increase medical protection or long-term care insurance for elderly family members. Regional factors also affect insurance choices. For example, target objects living in areas with frequent natural disasters are more likely to choose a combination of property insurance and accident insurance, while those living in first-tier cities may pay more attention to high-amount medical insurance or personal insurance combinations.

[0078] The methods for obtaining the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object can be through web form filling, web selection, etc. The identity attribute data of the target object can be obtained by asking users to fill in identity attribute data during user registration in advance, so that the identity data of the target object can be directly queried from the database when needed later.

[0079] In another embodiment, since the data in the database may have the problem of untimely updates, resulting in a deviation between the data in the database and the actual identity attribute data of the target object, in this case, the policy information, claim records, etc. associated with the target object can also be queried to obtain the latest data.

[0080] In step S102 of some embodiments, the insurance product library refers to a set of information of multiple pre-stored insurance products, which includes specific parameter information of multiple insurance products, such as the type of insurance, the amount of protection, the premium range, the scope of protection, and the protection period of each insurance product. For example, the insurance product library stores multiple insurance products such as Product A (medical insurance, protection amount of 200,000 yuan, premium of 2,000 yuan), Product B (personal accident insurance, protection amount of 500,000 yuan, premium of 1,500 yuan), and Product C (property insurance, protection amount of 1 million yuan, premium of 5,000 yuan).

[0081] Based on the insurance type intention data and the insurance investment intention data, screening candidate insurance products from the insurance product library means screening each insurance product in the insurance product library and selecting insurance products of the same type as the insurance type intention data. Then, based on the above insurance products of the same type, further screening is carried out to select the insurance with a premium within the insurance investment intention data as the candidate insurance product. For example, the target object intends to purchase medical insurance and accident insurance, and the insurance investment intention is that the total annual cost does not exceed 8,000 yuan. Then, Product A (medical insurance, 2,000 yuan) and Product B (accident insurance, 3,000 yuan) can be selected from the above product library as candidate insurance products, while a product with a premium exceeding 8,000 yuan or an insurance type that does not meet the requirements will not be included in the candidate products.

[0082] Combining candidate insurance products according to the insurance protection scope intention data to obtain at least one candidate insurance product combination can be achieved through the following methods: First, divide the insurance protection scope intention data according to the insurance type to obtain the insurance protection scope intention data for different insurance types; then, according to the insurance protection scope intention data corresponding to each insurance type, select insurance products from the candidate insurance products that meet the insurance protection scope intention data of this insurance type to form a target insurance product set corresponding to each insurance type; finally, combine each insurance product in the target insurance product sets of different insurance types to obtain at least one candidate insurance product combination.

[0083] For example, the insurance protection scope intention data of the object is: the protection amount of medical insurance is not less than 200,000 yuan, and the protection amount of personal accident insurance is not less than 500,000 yuan. First, divide this data into two parts: medical insurance (protection amount ≥ 200,000 yuan) and personal accident insurance (protection amount ≥ 500,000 yuan). Then, according to these specific intention data, select the medical insurance and personal accident insurance products that meet the conditions from the candidate insurance products respectively to form the target product sets corresponding to each insurance type. Finally, combine the target product sets of medical insurance and personal accident insurance, and traverse to generate all possible product combinations, that is, at least one candidate insurance product combination that meets the requirements of the object. It should be noted that the insurance protection scope intention data can be an amount, an age, or a disease type, and this application does not make any restrictions.

[0084] Please refer to Figure 2 , in some embodiments, step S103 may include but is not limited to steps S201 to S204:

[0085] Step S201, extract insurance coverage rules for each candidate insurance product portfolio to obtain the coverage rules of each candidate insurance product portfolio;

[0086] Step S202, determine the first matching degree sub-score of each candidate insurance product portfolio according to the identity attribute data and each coverage rule;

[0087] Step S203, for each candidate insurance product portfolio, calculate the product matching degree of each insurance product in the candidate insurance product portfolio based on the identity attribute data to obtain the second matching degree sub-score;

[0088] Step S204, for each candidate insurance product portfolio, determine the matching degree score based on the first matching degree sub-score and the second matching degree sub-score of the candidate insurance product portfolio.

[0089] Steps S201 to S204 illustrated in the embodiments of the present application first extract insurance coverage rules for each candidate insurance product portfolio to clarify the protection scope and applicable terms of the portfolio. Then, according to the identity attribute data of the target object and the extracted coverage rules, determine the first matching degree sub-score of each candidate insurance product portfolio; Next, further calculate the product matching degree of each insurance product at the portfolio level to obtain the second matching degree sub-score; Finally, comprehensively process the first and second matching degree sub-scores to obtain the matching degree score of the candidate insurance product portfolio relative to the target object, and finely measure the adaptation degree between the insurance product portfolio and the target object's needs from two dimensions, which not only avoids the deviation that may be brought by the traditional single or empirical matching method, thus improving the recommendation accuracy of the insurance product portfolio.

[0090] In step S201 of some embodiments, the coverage rule is the specific protection content provided by the insurance product portfolio and its corresponding conditions. For example, in the medical insurance scenario, the coverage rule may include the reimbursement amount, deductible, payment ratio, etc. for outpatient expenses, inpatient expenses, surgical expenses, and specific diseases.

[0091] When extracting the coverage rule, the coverage rule can be obtained by retrieving the preset insurance information library, or the coverage rule can be obtained by parsing the insurance product documents.

[0092] In step S202 of some embodiments, the first matching degree sub-score is a numerical value used to represent the matching degree between the identity attribute data and each coverage rule, which is represented by 0 or 1. For a single coverage rule, when the first matching degree sub-score is 1, it means that the identity attribute data conforms to the coverage rule; when the first matching degree sub-score is 0, it means that the identity attribute data does not conform to the coverage rule. For example, in the medical insurance within an insurance product portfolio, it is stipulated that only those aged between 18 and 60 can enjoy the protection provided by the medical insurance. If the age information in the identity attribute data is 65, then the first matching degree sub-score of this insurance product portfolio is 0. For another example, when the identity attributes conform to all the coverage rules of an insurance product portfolio, the first matching degree sub-score of this insurance product portfolio is 1.

[0093] Please refer to Figure 3 , in some embodiments, step S203 may include but is not limited to steps S301 to S302:

[0094] Step S301: Based on the identity attribute data, perform similarity screening on each candidate clustering region to obtain the target clustering region;

[0095] Step S302: Based on the target clustering region, calculate the product matching degree for each insurance product to obtain the second matching degree sub-score.

[0096] Steps S301 to S302 illustrated in the embodiments of the present application find the population similar to the target object, that is, the target clustering region, through the identity attribute data, and then calculate the product matching degree for each insurance product based on the target clustering region to predict the matching degree between the target object and the candidate insurance product portfolio, thereby improving the recommendation accuracy of the candidate insurance product portfolio.

[0097] In step S301 of some embodiments, the candidate clustering regions are obtained by clustering the identity attribute data of historical users. The target clustering region refers to the clustering region with a high similarity to the identity attribute data. The similarity screening of each candidate clustering region based on the identity attribute data to obtain the target clustering region can be achieved in the following way: First, for each candidate clustering region, obtain each candidate identity attribute data of the candidate clustering region and calculate the average value as the clustering center. For each clustering center, calculate the similarity with the vector formed by the identity attribute data, and based on the candidate clustering region corresponding to the minimum similarity, it is used as the target clustering region. The method for calculating the similarity can be cosine similarity or Mahalanobis distance, and the present application does not make specific limitations.

[0098] Please refer to Figure 4 , in some embodiments, step S302 may include but is not limited to steps S401 to S405:

[0099] Step S401: Obtain the reference objects in the target clustering area, and use the satisfaction data of the reference objects for each insurance product as the first score of each insurance product.

[0100] Step S402: Use the number of claim settlement times of each insurance product for the reference objects as the second score of each insurance product.

[0101] Step S403: Use the claim settlement value of each insurance product for the reference objects as the third score of each insurance product.

[0102] Step S404: Based on the first score, second score, and third score of each insurance product, determine the product score of each insurance product.

[0103] Step S405: Perform weighted sum processing based on each product score to obtain the second matching degree sub-score.

[0104] In the steps S401 to S405 shown in the embodiments of the present application, by obtaining the satisfaction data as the first score, the number of claim settlement times as the second score, and the claim settlement value as the third score. Then, comprehensively consider these three, namely the first score, the second score, and the third score, to determine the product score of each insurance product. Then, perform weighted sum processing based on each product score to obtain the second matching degree sub-score of the insurance product portfolio. By comprehensively considering multiple aspects to determine the product score of each insurance product, and finally using the weighted sum processing based on the product score as the second matching degree sub-score of the insurance product portfolio, the accurate calculation of the matching degree between the insurance product portfolio and the target object is realized.

[0105] In step S401 of some embodiments, the reference object refers to an object belonging to the target clustering area, and the reference object can be one or multiple. The satisfaction data of the reference object refers to the scoring value of the reference object for the insurance product, and the way to obtain this scoring value can be through looking up a table. The first score is a value between 0 and 1, which is used to represent the satisfaction of the reference object with the insurance product. The higher the first score, the higher the satisfaction.

[0106] Using the satisfaction data as the first score of each insurance product can be achieved in the following way: First, for an insurance product, obtain the objects among the reference objects that have scored this insurance product, that is, the valid objects. For example, if there are 5 reference objects and 3 of them have scored this insurance product, then the above 3 objects are the valid objects. Then, obtain the average scoring value of the valid objects for this insurance product as the average evaluation value of this insurance product. Repeat the above process to obtain the average evaluation values of each insurance product. Based on the average evaluation values of all insurance products, perform normalization to obtain the first score of each insurance product.

[0107] In step S402 of some embodiments, the second score is a natural number, which is used to represent the number of claims of a certain insurance product to a reference object. The second score can be determined in the following manner: First, for an insurance product, the sum of the number of claims of the insurance product to the reference user is obtained as the second score. The above process is repeated to obtain the second score of each insurance product.

[0108] In step S403 of some embodiments, the third score is a number greater than or equal to zero, which is used to represent the total amount of claims paid by a certain insurance product to a reference object. The third score can be determined in the following manner: First, for an insurance product, the sum of the claims paid by the insurance product to the reference user is obtained as the third score. The above process is repeated to obtain the third score of each insurance product.

[0109] In step S404 of some embodiments, the product score is a numerical value, which is a number greater than zero. The method of confirming the product score can be implemented in the following manner: for an insurance product, the average claim value is obtained by dividing the third score by the second score. Then, the product between the average claim value and the first score is obtained as the product score.

[0110] The reason why the product score is confirmed based on the three dimensions of satisfaction data, number of claims and claim value is that the average claim value composed of the two indicators of number of claims and claim value can represent the actual protection effect of the insurance product on the reference object. For example, a higher average claim value usually means that the insurance product provides a stronger risk protection capability to the object in the actual claim process, while a lower average claim value means that its actual protection effect is relatively limited. At the same time, the satisfaction data can reflect the subjective recognition of the reference object after the actual use of the insurance product. By comprehensively calculating the average claim value and the satisfaction data, the actual protection effectiveness and object recognition of the insurance product can be objectively and comprehensively reflected, so that the final confirmed product score can accurately represent the degree of fit between the insurance product and the needs of the target object, thereby improving the accuracy of the recommendation of insurance product portfolios.

[0111] In step S405 of some embodiments, the second matching sub-score is a numerical value used to characterize the matching degree between the target object and the candidate insurance product combination, and is a numerical value greater than or equal to 0. The higher the second matching sub-score, the more matching the target object and the candidate insurance product combination.

[0112] In one embodiment, the weighted sum process is performed based on each product score to obtain the second matching degree sub-score, which can be achieved in the following way: obtain the weight values of the target object for various types of insurance products, and then perform a weighted sum based on the weight values and the product scores. The way to obtain the weight values can be to set corresponding levels on the web page. For example, for medical products, set three levels: "very important", "relatively important", and "important", and let the target object check, or the target object can directly fill in the weight values.

[0113] In another embodiment, the weighted sum process is performed based on each product score to obtain the second matching degree sub-score, which can be the average value as the second matching degree sub-score.

[0114] In step S204 of some embodiments, the matching degree score refers to the matching value of the target object for the candidate insurance product portfolio. The higher the matching degree score, the more matching between the target object and the candidate insurance product portfolio. Based on the first matching degree sub-score and the second matching degree sub-score of the candidate insurance product portfolio, the matching degree score can be determined in the following way: obtain the product of the first matching degree sub-score and the second matching degree sub-score as the matching degree score. The reason for using the product of the two as the matching degree score is that the first matching degree sub-score is a value of 0 or 1. If it is 0, it means that the target object cannot be covered by the insurance products in the candidate insurance product portfolio, so it can be directly excluded.

[0115] Please refer to Figure 5 , in some embodiments, step S104 includes but is not limited to steps S501 to S503:

[0116] Step S501, construct a user portrait based on the identity attribute data to obtain the target object portrait;

[0117] Step S502, screen out the policy purchase records, policy renewal records, and policy surrender records from the policy record database based on the target object portrait;

[0118] Step S503, through the risk preference analysis model, perform preference analysis based on the policy purchase records, policy renewal records, and policy surrender records to obtain the risk preference level.

[0119] Steps S501 to S503 shown in the embodiments of the present application construct a user portrait based on the identity attribute data to obtain the target object portrait, then screen out the policy purchase records, policy renewal records, and policy surrender records from the policy record database based on the target object portrait, and finally perform preference analysis based on the policy purchase records, policy renewal records, and policy surrender records through the risk preference analysis model to obtain the risk preference level, realizing the accurate evaluation of the risk preference level.

[0120] In step S501 of some embodiments, the target object portrait is a data set constructed from the identity attribute data of the target object, which can represent the insurance demand characteristics of the target object, usually represented in the form of structured data or tags, and can reflect the specific characteristics of the target object in terms of insurance demand, risk tolerance, product preference, etc. For example, the target object portrait may include a series of characteristic tags such as "aged 30 - 40", "married with children", "annual income of about 200,000 yuan", "prefers medical insurance and accident insurance".

[0121] The method of constructing the target object portrait can be achieved through the following steps: First, cluster or extract features from the historical object data to obtain the typical portraits of different object groups; then, based on the specific identity attribute data of the target object and combined with the existing object group portraits, determine the user group to which the target object belongs through methods such as cluster analysis, similarity calculation, or machine learning; finally, use the belonging group as the user portrait of the target object.

[0122] The reason for constructing the target object portrait is, on the one hand, that the target object may not have insurance purchase or related insurance operations, and on the other hand, because the target object portrait not only represents the target object but also represents groups similar to the target object, and potential characteristics of the target object can be mined based on these groups.

[0123] In step S502 of some embodiments, the sample object refers to an object that has the same user portrait as the target object, that is, the user portrait of the sample object is equivalent to the target object portrait. The policy purchase record refers to the historical record of insurance products that the sample object has purchased in the past, usually including information such as the specific insurance product name, insurance type, premium amount, protection amount, and purchase time that the sample object has purchased; the policy renewal record is the historical record of the sample object continuing to insure the original insurance product after it expires, which can reflect the sample object's recognition of the insurance product; the policy surrender record is the record of the sample object having purchased an insurance product but terminating the contract in advance, usually reflecting the sample object's dissatisfaction with the insurance product or changes in protection needs.

[0124] The method of screening corresponding records from the policy record database based on the target object portrait is as follows: First, use the characteristic data of the target object portrait as the screening conditions, for example, use the age group, occupation type, income level, etc. of the target object as query parameters; then, retrieve from the policy record database the sample object groups that have similar or the same characteristics as the target object portrait according to these parameters, and finally, extract the purchase records, renewal records, and surrender records from the historical policy data of these groups.

[0125] In step S503 of some embodiments, the risk preference analysis model is a neural network model that receives policy purchase records, policy renewal records, and policy surrender records and outputs a risk preference level. The risk preference level represents the degree or tendency of the target object to assume risks when selecting insurance products, usually expressed in the form of levels or categories, such as "conservative", "prudent", "medium", "aggressive", etc.

[0126] The reason for performing preference analysis and determining the risk preference level based on policy purchase records, policy renewal records, and policy surrender records is that the historical policy purchase records of the target object can reflect the past insurance selection tendencies of the target object, the renewal records reflect the actual recognition degree of the target object for the protection effect and service of the insurance product, and the surrender records reflect the dissatisfaction of the target object with a certain type of insurance product or the change in risk protection needs. Considering these three types of records comprehensively can objectively and accurately reflect the actual preference and sensitivity of the target object for insurance risk protection, so as to accurately determine the risk preference level of the target object.

[0127] Please refer to Figure 6 , in some embodiments, step S104 includes but is not limited to steps S601 to S603:

[0128] Step S601, screening multiple candidate evaluation indicators according to the identity attribute data to obtain at least one target evaluation indicator;

[0129] Step S602, scoring the identity attribute data according to each target evaluation indicator to obtain the evaluation scores of each target evaluation indicator;

[0130] Step S603, performing a weighted sum according to each evaluation score to obtain a target score, and determining the risk bearing level based on the target score.

[0131] Steps S601 to S603 illustrated in the embodiments of the present application screen multiple candidate evaluation indicators according to the identity attribute data to obtain at least one target evaluation indicator, then score the identity attribute data according to each target evaluation indicator to obtain the evaluation scores of each target evaluation indicator, and finally perform a weighted sum according to each evaluation score to obtain a target score, and determine the risk bearing level based on the target score, so as to accurately evaluate the risk bearing level of the target object.

[0132] In step S601 of some embodiments, the candidate evaluation indicators refer to a set of initial indicator sets used to evaluate the risk tolerance of the target object. These indicators are usually directly related to the identity attribute data of the target object, such as age, income level, occupation type, education level, family structure, asset status, region, etc. The determination of the target evaluation indicators can be achieved in the following way: obtain each non-empty data in the identity attribute data, and according to the non-empty data above, obtain the evaluation indicators matching it as the target evaluation indicators.

[0133] In step S602 of some embodiments, the evaluation score is a quantitative score of the target evaluation indicators on the specific identity attribute data of the target object, which is used to intuitively reflect the risk tolerance of the target object in different indicator dimensions and usually appears as a numerical value. The evaluation score can be determined by setting clear scoring rules or scoring criteria for each target evaluation indicator. For example, assuming that "income level" is a target evaluation indicator, the scoring rule can be set as follows: the object with an annual income of less than 100,000 yuan is scored 3 points, the income between 100,000 - 200,000 yuan is scored 5 points, and the income exceeding 200,000 yuan is scored 5 points. If the actual annual income of the target object is 180,000 yuan, then the evaluation score on the target evaluation indicator of "income level" is 5 points.

[0134] In step S603 of some embodiments, the risk bearing level refers to the ability of the target object to bear risks when choosing an insurance product. For example, it is usually distinguished by different levels such as "low risk bearing level", "medium risk bearing level" or "high risk bearing level". The method for determining the risk bearing level can be achieved in the following way: First, obtain the evaluation scores of the target object on each evaluation indicator according to multiple target evaluation indicators, then assign corresponding weights according to the importance of different evaluation indicators to the risk bearing ability, and perform weighted summation on the evaluation scores to finally obtain a total target score. Subsequently, according to the pre-set threshold interval, map the target score to the corresponding risk bearing level. The specific corresponding weights can be set in advance or determined by the target object.

[0135] Please refer to Figure 7 , in some embodiments, step S104 may include but is not limited to steps S701 to S704:

[0136] Step S701, evaluate the risk levels of each alternative insurance product portfolio to determine the risk levels of each alternative insurance product portfolio;

[0137] Step S702, filter out the alternative insurance product portfolios with risk levels greater than the risk bearing level to obtain the selected insurance product portfolios;

[0138] Step S703: Sort the selected insurance product portfolios based on the risk preference level and the risk level to obtain a sequence of selected insurance product portfolios;

[0139] Step S704: Screen the sequence of selected insurance product portfolios to obtain the target insurance product portfolio.

[0140] Steps S701 to S704 illustrated in the embodiments of the present application screen the alternative insurance product portfolios through the risk preference level, the risk bearing level of the target object, and the risk level of the insurance product portfolio, ensuring that the target object can bear the risk while also ensuring that the recommended insurance product portfolio to the target object conforms to the risk preference of the target object.

[0141] In step S701 of some embodiments, the risk level refers to the classification and evaluation result of the alternative insurance product portfolio in terms of risk bearing, and is used to measure the degree of risk covered by the insurance product portfolio. Usually, the risk level can be divided into multiple levels, such as "low risk", "medium risk" and "high risk", or more refined numerical levels, which are used to characterize the risk exposure degree of the insurance portfolio to the insured object. The risk levels of each alternative insurance product portfolio can be determined in the following ways: input the alternative insurance product portfolio into a pre-trained product portfolio risk assessment model to obtain the risk level of the alternative insurance product portfolio.

[0142] In another embodiment, it can also be achieved in the following ways:

[0143] For an alternative insurance product portfolio, input each insurance product of the alternative insurance product portfolio and the user attribute information into the attention model to determine the attention score of each insurance product;

[0144] For an alternative insurance product portfolio, input each insurance product of the alternative insurance product portfolio into a pre-trained product risk assessment model to obtain the corresponding risk sub-levels of each insurance product;

[0145] Perform weighted sum processing based on the attention score and the corresponding risk sub-level of the attention score to obtain the risk level.

[0146] In this embodiment, the reason for determining the risk level based on the attention score and the risk sub-level is that the attention score can reflect the importance of different insurance products in the entire insurance portfolio, that is, the degree of protection contribution of a certain insurance product to the target object, while the risk sub-level can quantify the risk level of the insurance product itself. By combining these two factors for weighted calculation, when evaluating the overall risk level of the insurance portfolio, not only the independent risk attributes of each insurance product can be considered, but also the weight influence of each insurance product in the portfolio can be fully reflected, so as to more accurately measure the overall risk level of the alternative insurance product portfolio and improve the rationality and accuracy of risk assessment.

[0147] In step S702 of some embodiments, the selected insurance product portfolio is an insurance product portfolio in the alternative insurance product portfolio whose risk level is less than or equal to the risk-bearing level.

[0148] In step S703 of some embodiments, the selected insurance product portfolio sequence is a sequence formed by an insurance product portfolio, and this sequence is sorted from largest to smallest according to the risk level. The selected insurance product portfolio sequence can be determined in the following way: select the selected insurance product portfolios whose risk level is greater than the risk preference level, and then sort the selected insurance product portfolios that are selected according to the risk level from largest to smallest to obtain the selected insurance product portfolio sequence.

[0149] It should be noted that filtering out the insurance product portfolios whose risk level is greater than the risk-bearing level first, and then selecting the insurance product portfolios whose risk level is greater than the risk preference level ensures that the target object can bear the risk and also ensures that the insurance product portfolio recommended to the target object conforms to the risk preference of the target object.

[0150] In step S704 of some embodiments, in one embodiment, screening the selected insurance product portfolio sequence to obtain the target insurance product portfolio can be achieved in the following way: obtain the top N largest insurance product portfolios in the selected insurance product portfolio sequence as the target insurance product portfolio.

[0151] Please refer to Figure 8 , this application embodiment also provides a recommendation device for an insurance product portfolio, which can implement the above-mentioned recommendation method for an insurance product portfolio. The device includes:

[0152] A data acquisition module 801, configured to acquire the insurance type intention data, insurance investment intention data, and insurance protection scope intention data of the target object, and acquire the identity attribute data of the target object;

[0153] The product portfolio module 802 is used to screen candidate insurance products from the insurance product library based on the insurance type intention data and the insurance investment intention data, and combine the candidate insurance products according to the insurance coverage intention data to obtain at least one candidate insurance product portfolio;

[0154] The first screening module 803 is used to calculate the matching degree between the identity attribute data and each candidate insurance product portfolio, obtain the matching degree scores corresponding to each candidate insurance product portfolio, and screen the candidate insurance product portfolios based on each matching degree score to obtain at least one alternative insurance product portfolio;

[0155] The second screening module 804 is used to determine the risk bearing level and risk preference level of the target object according to the identity attribute data, and screen each alternative insurance product portfolio based on the risk bearing level and risk preference level to obtain the target insurance product portfolio;

[0156] The product recommendation module 805 is used to recommend products to the target object based on the target insurance product portfolio.

[0157] The specific implementation manner of the recommended device for the insurance product portfolio is basically the same as the specific embodiment of the above-mentioned recommended method for the insurance product portfolio, and will not be described in detail here.

[0158] 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 when the processor executes the computer program, it implements the above-mentioned recommended method for the insurance product portfolio. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0159] Please refer to Figure 9 , Figure 9 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes:

[0160] The processor 901 can be implemented in a general-purpose CPU (Central Processing Unit, central processor), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0161] 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), etc. The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902, and are called by the processor 901 to execute the recommended method for the insurance product portfolio in the embodiments of this application;

[0162] The input / output interface 903 is used to implement information input and output;

[0163] The communication interface 904 is used to implement communication and interaction between this device and other devices. It can communicate through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0164] The bus 905 transmits information between various components of the device (such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0165] Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are communicatively connected to each other inside the device through the bus 905.

[0166] The embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned recommended method for the insurance product portfolio is implemented.

[0167] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The recommendation method for insurance product portfolios, the recommendation device for insurance product portfolios, the electronic device, and the storage medium provided by the embodiments of the present application obtain the insurance type intention data, insurance investment intention data, and insurance coverage intention data of the target object, as well as the identity attribute data of the target object. Then, based on the insurance type intention data and insurance investment intention data, candidate insurance products are accurately screened from the existing insurance product library, and then preliminary combinations are made using the insurance coverage intention data to obtain at least one candidate insurance product portfolio that meets the basic needs of the target object, ensuring that the candidate insurance product portfolio meets the basic requirements of the target object. Further, based on the identity attribute data, further matching degree calculations are performed on the candidate insurance product portfolios to determine the matching degree between each portfolio and the actual needs of the target object, and the candidate insurance product portfolios are screened according to the matching degree to obtain alternative insurance product portfolios that are more in line with the needs of the target object, further improving the accuracy of product recommendation. Further, based on the identity attribute data, the risk-bearing level and risk preference level of the target object are determined. The risk-bearing level can accurately evaluate the risk tolerance of the target object, while the risk preference level can reflect the risk acceptance tendency of the target object in insurance selection. And based on the risk-bearing level and risk preference level, the fitness screening of the alternative insurance product portfolios is carried out, ensuring that the finally recommended target insurance product portfolio can not only accurately match the needs of the target object, but also coincide with the risk characteristics and risk willingness of the target object, realizing in-depth personalized recommendation starting from the actual needs of the target object, further improving the recommendation accuracy of the insurance product portfolio, and ensuring that the finally recommended target insurance product portfolio for the target object can not only accurately match the object's needs, but also highly coincide with the object's risk characteristics and risk willingness, ultimately improving the recommendation accuracy of the insurance product portfolio.

[0169] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0170] Those skilled in the art can understand 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 those shown in the figures, or combine some steps, or different steps.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0173] As used in the specification of this application and the above-mentioned drawings, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0174] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or its similar expressions refer to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (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, and c can be single or multiple.

[0175] In the several embodiments provided in this 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 merely illustrative. For example, the above-mentioned unit division is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0176] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, the functional units in various embodiments of the present application may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store programs.

[0179] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings. However, this does not limit the scope of the rights of the embodiments of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall fall within the scope of the rights of the embodiments of the present application.

Claims

1. A method for recommending an insurance product combination, characterized in that: The method comprises: Obtaining the target object's insurance type intention data, insurance investment intention data, and insurance coverage intention data, and obtaining the target object's identity attribute data; Based on the insurance type intention data and the insurance investment intention data, candidate insurance products are screened from the insurance product library, and the candidate insurance products are combined according to the insurance coverage intention data to obtain at least one candidate insurance product combination; Calculating the matching degree between the identity attribute data and each of the candidate insurance product combinations to obtain a matching degree score corresponding to each of the candidate insurance product combinations, and screening the candidate insurance product combinations based on each matching degree score to obtain at least one candidate insurance product combination; Determine the risk tolerance level and risk preference level of the target object according to the identity attribute data, and screen each of the candidate insurance product combinations based on the risk tolerance level and the risk preference level to obtain a target insurance product combination; Product recommendations are made to the target object based on the target insurance product portfolio.

2. The method according to claim 1, characterized in that The calculating the matching degree between the identity attribute data and each of the candidate insurance product combinations to obtain the matching degree score corresponding to each of the candidate insurance product combinations includes: Extracting insurance coverage rules for each of the candidate insurance product combinations to obtain coverage rules for each of the candidate insurance product combinations; Determining a first matching sub-score for each candidate insurance product combination according to the identity attribute data and each of the coverage rules; For each of the candidate insurance product combinations, calculating the product matching degree of each insurance product in the candidate insurance product combination based on the identity attribute data to obtain a second matching degree sub-score; For each of the candidate insurance product combinations, the matching score is determined based on the first matching sub-score and the second matching sub-score of the candidate insurance product combination.

3. The method according to claim 2, characterized in that The calculating the product matching degree of each insurance product in the candidate insurance product combination based on the identity attribute data to obtain a second matching degree sub-score includes: Based on the identity attribute data, each candidate clustering area is screened for similarity to obtain a target clustering area; A product matching degree is calculated for each of the insurance products based on the target cluster area to obtain the second matching degree sub-score.

4. The method according to claim 3, characterized in that The calculating the product matching degree of each of the insurance products based on the target cluster area to obtain the second matching degree sub-score includes: Acquire reference objects in the target cluster area, and use satisfaction data of the reference objects for each of the insurance products as the first score of each of the insurance products; The number of claims paid by each of the insurance products to the reference object is used as a second score for each of the insurance products; Taking the claim settlement value of each of the insurance products for the reference object as the third score of each of the insurance products; determining a product score for each of the insurance products based on the first score, the second score, and the third score for each of the insurance products; The second matching degree sub-score is obtained by performing weighted sum processing based on the scores of the respective products.

5. The method according to claim 1, characterized in that Determining the risk preference level of the target object according to the identity attribute data includes: Constructing a user portrait based on the identity attribute data to obtain a target object portrait; Based on the target object portrait, filter out the policy purchase records, policy renewal records and policy surrender records from the policy record database; Through the risk preference analysis model, preference analysis is performed based on the policy purchase record, the policy renewal record and the policy surrender record to obtain the risk preference level.

6. The method according to claim 1, characterized in that The step of determining the risk tolerance level of the target object according to the identity attribute data includes: Screening a plurality of candidate evaluation indicators according to the identity attribute data to obtain at least one target evaluation indicator; Scoring the identity attribute data according to each of the target evaluation indicators to obtain evaluation scores for each of the target evaluation indicators; A weighted sum is performed on each of the evaluation scores to obtain a target score, and the risk tolerance level is determined based on the target score.

7. The method according to claim 1, characterized in that The step of screening each of the candidate insurance product combinations based on the risk tolerance level and the risk preference level to obtain a target insurance product combination includes: Conducting risk level assessment on each of the alternative insurance product combinations to determine the risk level of each of the alternative insurance product combinations; Filter out the candidate insurance product combinations whose risk levels are greater than the risk tolerance level to obtain a selected insurance product combination; Sorting the selected insurance product combinations based on the risk preference level and the risk level to obtain a selected insurance product combination sequence; The selected insurance product combination sequence is screened to obtain the target insurance product combination.

8. A device for recommending insurance product combinations, characterized in that: The device comprises: A data acquisition module is used to acquire the target object's insurance type intention data, insurance investment intention data and insurance coverage intention data, and acquire the target object's identity attribute data; A product combination module, configured to screen candidate insurance products from an insurance product library based on the insurance type intention data and the insurance investment intention data, and combine the candidate insurance products according to the insurance coverage intention data to obtain at least one candidate insurance product combination; A first screening module is used to calculate the matching degree between the identity attribute data and each of the candidate insurance product combinations, obtain the matching degree score corresponding to each of the candidate insurance product combinations, and screen the candidate insurance product combinations based on each matching degree score to obtain at least one candidate insurance product combination; A second screening module is used to determine the risk tolerance level and risk preference level of the target object according to the identity attribute data, and screen each of the candidate insurance product combinations based on the risk tolerance level and the risk preference level to obtain a target insurance product combination; A product recommendation module is used to recommend products to the target object based on the target insurance product portfolio.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method for recommending an insurance product combination 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 method for recommending an insurance product combination according to any one of claims 1 to 7 is implemented.

Images