Insurance product recommendation method and device, computer equipment and storage medium
By analyzing historical claims records and user information, sorting and screening insurance products, and providing personalized recommendations, it solves the problem of users' choices when repurchasing insurance, improves the accuracy and diversity of product recommendations, and improves user experience and market expand.
Patent Information
- Application Number
- CN202411149512.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-12-27
AI Technical Summary
In the field of digital finance business, when users re-purchase insurance products after claiming, due to the complex professional terms, it is difficult to choose products that meet expectations, resulting in difficulty in choosing and low satisfaction, which affects the user experience and the image of the insurance company, and traditional methods cannot meet the current situation of users. need.
By analyzing historical claims records and target user information, the initial insurance product collection is determined, and the product attributes and user information is sorted to be selected, the target insurance product collection is determined based on the user's preset filtering conditions, and personalized recommendations are provided.
It improves the accuracy and diversity of insurance product recommendations, meets the needs of different user groups, helps users quickly narrow their choices, and improves user experience and insurance companies' market expansion.
Smart Images
Figure CN119205249A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data analysis technology and the field of digital financial business, and in particular to an insurance product recommendation method, device, computer equipment and storage medium. Background Art
[0002] In the field of digital financial business, driven by the current market background, users have no choice when purchasing insurance products again after claims, because most of the insurance company's product terms are professional terms, which are very difficult for non-professionals to understand. When users enter the re-insurance year, they are confused and there are no professionals to provide meaningful guidance, which makes it difficult for users to make choices. In the end, they may buy insurance products that do not meet their expectations, and have disagreements with the insurance company when making claims, which affects the user experience and the image of the insurance company in the minds of users.
[0003] The traditional practice is that insurance companies generate a unified re-insurance link, and users can only choose the insurance products corresponding to the insurance products specified in the current group insurance policy, which does not really meet the user's current demand for insurance products this year, resulting in hesitation and low satisfaction when users make claims, which in turn leads to the company's brand not having an impact on the public and a series of problems in market expansion. Therefore, how to improve the accuracy of recommending insurance products to users in the field of digital financial services has become a technical problem that needs to be solved urgently. Summary of the invention
[0004] The present application provides an insurance product recommendation method, apparatus, computer equipment and storage medium to improve the accuracy of recommending insurance products to users in the field of digital financial services.
[0005] In a first aspect, the present application provides an insurance product recommendation method, the method comprising:
[0006] Determine the initial insurance product set based on historical claims records and target user information of target users;
[0007] Based on the product attributes of each candidate insurance product in the initial insurance product set and the target user information, all the candidate insurance products are sorted, and a candidate insurance product set is generated based on all the sorted candidate insurance products;
[0008] According to the preset screening conditions of the target user, a target insurance product is determined from the set of insurance products to be selected.
[0009] In a second aspect, the present application further provides an insurance product recommendation device, the device comprising:
[0010] An initial insurance product set determination module, used to determine an initial insurance product set based on historical claims records and target user information of target users;
[0011] A module for determining a set of insurance products to be selected, configured to sort all the insurance products to be selected based on the product attributes of each insurance product to be selected in the initial insurance product set and the target user information, and generate a set of insurance products to be selected based on all the sorted insurance products to be selected;
[0012] The target insurance product determination module is used to determine the target insurance product from the set of insurance products to be selected according to the preset screening conditions of the target user.
[0013] In a third aspect, the present application also provides a computer device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the insurance product recommendation method as described above when executing the computer program.
[0014] In a fourth aspect, the present application further provides 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 processor implements the insurance product recommendation method as described above.
[0015] The present application discloses an insurance product recommendation method, device, computer equipment and storage medium, the insurance product recommendation method includes determining an initial insurance product set based on historical claims records and target user information of target users; sorting all the selected insurance products based on the product attributes of each selected insurance product in the initial insurance product set and the target user information, and generating a selected insurance product set based on all the sorted selected insurance products; determining the target insurance product from the selected insurance product set according to the preset screening conditions of the target user. In the above manner, the present application can provide more personalized insurance product recommendations by analyzing historical claims records and specific information of target users. Sorting and screening insurance products can help insurance companies provide more balanced and diversified product combinations to meet the needs of different user groups. When users are faced with many insurance product choices, they can quickly narrow down the selection range through preset screening conditions, thereby improving the accuracy of recommending insurance products to users in the field of digital financial services. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0017] Figure 1 is a schematic flow chart of an insurance product recommendation method provided in the first embodiment of the present application;
[0018] Figure 2 is a schematic flow chart of an insurance product recommendation method provided in the second embodiment of the present application;
[0019] Figure 3 A schematic block diagram of an insurance product recommendation device provided in an embodiment of the present application;
[0020] Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0022] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0023] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0024] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0025] The embodiments of the present application provide an insurance product recommendation method, device, computer equipment and storage medium. Among them, the insurance product recommendation method can be applied to a server, and by analyzing historical claims records and specific information of target users, more personalized insurance product recommendations can be provided. Sorting and screening insurance products can help insurance companies provide a more balanced and diversified product portfolio to meet the needs of different user groups. When users are faced with many insurance product choices, they can quickly narrow down the selection range through preset screening conditions, thereby improving the accuracy of recommending insurance products to users in the field of digital financial services. Among them, the server can be an independent server or a server cluster.
[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0027] See also Figure 1 , Figure 1 This is a schematic flow chart of an insurance product recommendation method provided by the first embodiment of the present application. The insurance product recommendation method can be applied to a server to provide more personalized insurance product recommendations by analyzing historical claims records and specific information of target users. Sorting and screening insurance products helps insurance companies provide a more balanced and diversified product portfolio to meet the needs of different user groups. When users are faced with many insurance product choices, they can quickly narrow down the selection range through preset screening conditions, thereby improving the accuracy of recommending insurance products to users in the field of digital financial services.
[0028] like Figure 1 As shown, the insurance product recommendation method specifically includes steps S10 to S30.
[0029] Step S10: determining an initial insurance product set based on historical claims records and target user information of the target user;
[0030] Specifically, historical claims records and target user information are collected, including age, gender, occupation, income, etc. Based on historical claims records and target user information, the initial insurance product set is determined, including various types of insurance products, such as life insurance, medical insurance, auto insurance, etc.
[0031] Step S20: sorting all the insurance products to be selected based on the product attributes of each insurance product to be selected in the initial insurance product set and the target user information, and generating a set of insurance products to be selected based on all the sorted insurance products to be selected;
[0032] Specifically, the candidate insurance products in the initial insurance product set are sorted and screened according to product attributes and target user information, such as age, gender, occupation, income, etc. A candidate insurance product set is generated based on the sorted candidate insurance products, including insurance products that meet the needs of the target users.
[0033] Step S30: Determine a target insurance product from the set of insurance products to be selected according to the preset screening conditions of the target user.
[0034] Specifically, the target insurance product is determined from the set of insurance products to be selected based on the preset screening conditions of the target user, such as insurance amount, insurance period, insurance cost, etc. The finalized insurance product is recommended to the target user, and related insurance services are provided.
[0035] In one embodiment, when a group insurance order generates a re-insurance link, it will first obtain the historical claims records of all users, perform big data screening on the terms and conditions of the currently sold insurance products based on the user claims records, select several insurance products that are suitable for group order users this year, and sort them.
[0036] Based on the basic needs of the user for this year, such as major illness type, expected protection type, service type and other screening conditions, a recommendation algorithm is used to calculate the best combination of insurance products that meet the user's selection criteria with existing claims records. Insurance products of the same type are then ranked and recommended a second time based on the best premium.
[0037] The insurance application page recommends products based on the filtering criteria selected by the user. The user enters the type of serious illness, premium expectation, and protection type requirement, and the three combinations that best match the user's needs are prioritized. The current combinations that meet the requirements are then sorted again based on the premium. After the re-sorting, the best product ranking is displayed to the user, thereby helping the user to choose the most suitable product that will have the least impact on the claims for this year.
[0038] The present embodiment discloses an insurance product recommendation method, apparatus, computer equipment and storage medium, the insurance product recommendation method comprising determining an initial insurance product set based on historical claims records and target user information of a target user; sorting all the selected insurance products based on the product attributes of each selected insurance product in the initial insurance product set and the target user information, and generating a selected insurance product set based on all the sorted selected insurance products; and determining a target insurance product from the selected insurance product set based on preset screening conditions of the target user. In the above manner, the present application can provide more personalized insurance product recommendations by analyzing historical claims records and specific information of target users. Sorting and screening insurance products can help insurance companies provide more balanced and diversified product combinations to meet the needs of different user groups. When users are faced with many insurance product choices, they can quickly narrow down the selection range through preset screening conditions, thereby improving the accuracy of recommending insurance products to users in the field of digital financial services.
[0039] See also Figure 2 , Figure 2 This is a schematic flow chart of an insurance product recommendation method provided in the second embodiment of the present application. The insurance product recommendation method can be applied to a server, and is used to disassemble user information so that insurance companies can have a deeper understanding of users' specific needs and preferences, thereby providing more accurate insurance product recommendations. Calculating the adaptability score helps to quantify the degree of match between user needs and insurance product attributes, ensuring that the recommended products meet user needs to the greatest extent. Through the sorting mechanism, insurance companies can give priority to recommending insurance products that are most compatible with user needs, helping users and insurance companies to better evaluate and select insurance products, and improving the accuracy of recommending insurance products to users in the field of digital financial services.
[0040] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S20 includes steps S201 to S203.
[0041] Step S201: disassemble the target user information to generate at least one set of user single item information;
[0042] Step S202: Calculate the suitability score of each of the to-be-selected insurance products based on the individual information of each user and the product attributes of each of the to-be-selected insurance products;
[0043] Step S203: sort the insurance products to be selected based on their suitability scores, and select the insurance products to be selected whose suitability scores are greater than a preset suitability score threshold as the insurance product set to be selected.
[0044] In one embodiment, the target user information is broken down into multiple individual information, such as age, gender, occupation, income, etc. According to the product attributes of each candidate insurance product, such as insurance amount, insurance period, insurance cost, etc., the compatibility score with each user's individual information is calculated. The compatibility scores of the candidate insurance products are sorted from high to low. A preset compatibility score threshold is set, and the candidate insurance products with a compatibility score greater than the threshold are taken as a candidate insurance product set. According to the preset screening conditions of the target user, the final target insurance product is determined from the candidate insurance product set.
[0045] The present embodiment discloses an insurance product recommendation method, apparatus, computer equipment and storage medium, the insurance product recommendation method comprising determining an initial insurance product set based on historical claims records and target user information of a target user; disassembling the target user information to generate at least one set of user single information; calculating the adaptability score of each of the selected insurance products based on the user single information and the product attributes of each of the selected insurance products; sorting each of the selected insurance products based on the adaptability score of each of the selected insurance products, and taking the selected insurance products whose adaptability score is greater than a preset adaptability score threshold as the selected insurance product set; and determining a target insurance product from the selected insurance product set according to the preset screening conditions of the target user. In the above manner, by disassembling user information, the present application enables insurance companies to have a deeper understanding of users' specific needs and preferences, thereby providing more accurate insurance product recommendations. Calculating the adaptability score helps to quantify the degree of match between user needs and insurance product attributes, ensuring that the recommended products meet user needs to the greatest extent possible. Through the sorting mechanism, insurance companies can prioritize insurance products that are most compatible with user needs, helping users and insurance companies to better evaluate and select insurance products, thereby improving the accuracy of recommending insurance products to users in the digital financial business field.
[0046] based on Figure 2 In the embodiment shown, in this embodiment, the target user information is disassembled to generate at least one set of user single item information, including:
[0047] Convert the target user information into target information text, and decompose the target information text into at least one group of target keywords based on a preset natural language processing technology NLP;
[0048] Matching each preset single item of information in the preset single item information library with each of the target keywords;
[0049] The preset single item of information matching the target keyword is determined as the user single item of information.
[0050] In a specific embodiment, the target user information is converted into a target information text, such as "30-year-old male, engineer by profession, with an annual income of 80,000 yuan", and the target information text is decomposed into at least one group of target keywords, such as "30 years old", "male", "engineer", and "annual income of 80,000 yuan" using a preset natural language processing technology NLP. Each preset single item of information in the preset single item information library is matched with the target keyword, such as "age", "gender", "occupation", "income", etc. The preset single item of information that matches the target keyword is determined as the user single item information, such as "age", "occupation", "income", etc. in the target user information corresponding to "30-year-old male, engineer by profession, with an annual income of 80,000 yuan".
[0051] The present embodiment discloses an insurance product recommendation method, apparatus, computer equipment and storage medium, the insurance product recommendation method comprising determining an initial insurance product set based on historical claims records and target user information of a target user; converting the target user information into a target information text, and decomposing the target information text into at least one group of target keywords based on a preset natural language processing technology NLP; matching each preset single item of information in a preset single item information library with each target keyword; determining the preset single item of information matching the target keyword as the user single item information; calculating the adaptability score of each of the candidate insurance products based on the product attributes of each of the user single item information and each of the candidate insurance products; sorting each of the candidate insurance products based on the adaptability score of each of the candidate insurance products, and taking the candidate insurance products whose adaptability score is greater than a preset adaptability score threshold as the candidate insurance product set; and determining a target insurance product from the candidate insurance product set according to the preset screening conditions of the target user. Through the above methods, this application uses automated NLP technology to quickly process a large amount of user information, extract key information, deeply analyze user information, tap into users' potential needs and preferences, and provide support for personalized services. While improving the efficiency of information processing, it also improves the accuracy of recommending insurance products to users in the field of digital financial services.
[0052] based on Figure 1 In the embodiment shown, in this embodiment, step S10 includes:
[0053] Based on the historical claims records, determining a claims risk list for the target user;
[0054] Based on the target user information, determining the scenario factor of the target user;
[0055] The initial insurance product set is determined through dynamic programming rules, the claim risk list and the scenario factors.
[0056] In a specific embodiment, based on historical claims records, a detailed analysis of the target user's claims is performed, including the type of claims, amount of claims, frequency of claims, etc., to determine the target user's claims risk list. This step is to understand the potential risks that the target user may face and provide a basis for subsequent insurance product selection.
[0057] Determine the scenario factors of target users based on target user information, such as age, gender, occupation, and living habits. Scenario factors refer to specific environments and conditions that affect users’ purchase and use of insurance products. For example, users with higher occupational risks may need more comprehensive insurance coverage, while older users may be more concerned about health insurance, etc.
[0058] Using dynamic programming rules, combined with the claim risk list and scenario factors, the initial insurance product set is determined. Dynamic programming is a method of solving complex problems by breaking down the original problem into relatively simple sub-problems. Here, a series of decision points can be set, each of which represents the selection or rejection of a certain insurance product. By comparing the costs and benefits of different decision points, the optimal insurance product combination is finally determined as the initial insurance product set.
[0059] It should be noted that the specific implementation of dynamic programming rules may involve complex mathematical models and algorithms, and the products and rules of different insurance companies may be different. Therefore, in practical applications, adjustments and optimizations need to be made according to specific circumstances.
[0060] In a more preferred embodiment, the initial insurance product set is determined by dynamic programming rules, the claim risk list and the scenario factors, including:
[0061] Assigning weights to each of the scenario factors using the dynamic programming rules to establish a dynamic programming model;
[0062] Based on the dynamic programming model and the claim risk list, calculating the insurance recommendation score corresponding to each of the scenario factors with different weights;
[0063] The insurance corresponding to the claim risk list whose insurance recommendation score is greater than the recommendation score threshold is determined as the initial insurance product set.
[0064] Specifically, a weight is assigned to each scenario factor through dynamic programming rules according to the degree of influence of each scenario factor on the insurance demand. For example, for users in high-risk occupations, occupational risk may be an important consideration, so a higher weight can be assigned to it.
[0065] Based on the dynamic programming model and the claim risk list, the insurance recommendation scores corresponding to the scenario factors with different weights are calculated. This can be obtained by scoring each scenario factor and then taking a weighted average according to its weight.
[0066] A recommendation score threshold is set, and the insurance products corresponding to the claim risk list with insurance recommendation scores higher than the threshold are determined as the initial insurance product set. These insurance products meet the needs and risk conditions of target users and can serve as the basis for subsequent screening and recommendation.
[0067] In a more preferred embodiment, the initial insurance product set is determined by dynamic programming rules, the claim risk list and the scenario factors, and further includes:
[0068] According to the recursive algorithm, dynamic programming is performed on the claim risk list and the scenario factors respectively, and initial insurance products corresponding to the claim risk list and the scenario factors are determined respectively;
[0069] After deduplication processing is performed on the claim risk list and the initial insurance products corresponding to the scenario factors, the initial insurance product set is generated.
[0070] Specifically, when performing demand splitting, it is actually the classic idea in dynamic programming, the stair climbing algorithm. The present invention optimizes the recursive algorithm, counts the target test data as the target number of steps (N), starts from the front-end input as the first step (N0), and combines APIs (Application Programming Interface) of different interfaces as multiple methods to reach N. Then, the total number of methods on the N steps is the sum of the number of methods of step (N-1) + step (N-2). All of these methods can generate recommended data one by one. For example, recommending data of an unfinished payment means that the "ladder climbing" method has not actually reached the target step, but it is indeed a data scenario.
[0071] In a more preferred embodiment, before step S10, the following steps are included:
[0072] Obtain historical screening conditions of all users through network big data;
[0073] Adding a product tag to each of the initial insurance products in the initial insurance product set according to the determined historical screening condition and the historical claims records;
[0074] The preset recursive algorithm is generated by training an initial recursive algorithm with the product labels and each of the initial insurance products.
[0075] In a specific embodiment, the historical screening conditions of all users are obtained through network big data, including the factors and preferences of users when they selected insurance products in the past. According to the historical screening conditions and historical claims records, product tags are added to each initial insurance product in the initial insurance product set. These tags may include the type, coverage, price, claims records, etc. of the insurance product.
[0076] Through product labels and initial insurance products, the initial recursive algorithm is trained to generate a preset recursive algorithm. A recursive algorithm is an algorithm that finds the optimal solution through continuous iteration and adjustment. Here, the combination and weight of insurance products can be continuously adjusted to find the insurance product that best meets user needs.
[0077] After obtaining the preset recursive algorithm, the algorithm can be used to recommend insurance products to new target users. Specifically, the preset recursive algorithm can be used to screen and recommend the most suitable insurance products according to the information and needs of the target users.
[0078] See also Figure 3 , Figure 3 The embodiment of the present application provides a schematic block diagram of an insurance product recommendation device, which is used to execute the aforementioned insurance product recommendation method. The insurance product recommendation device can be configured on a server.
[0079] like Figure 3 As shown, the insurance product recommendation device 400 includes:
[0080] An initial insurance product set determination module 410 is used to determine an initial insurance product set based on historical claim settlement records and target user information of a target user;
[0081] The candidate insurance product set determination module 420 is used to sort all the candidate insurance products in the initial insurance product set based on the product attributes of each candidate insurance product in the initial insurance product set and the target user information, and generate a candidate insurance product set based on all the sorted candidate insurance products;
[0082] The target insurance product determination module 430 is used to determine the target insurance product from the set of insurance products to be selected according to the preset screening conditions of the target user.
[0083] Furthermore, the module 420 for determining the set of insurance products to be selected includes:
[0084] A user single item information generating unit, used for disassembling the target user information and generating at least one set of user single item information;
[0085] A suitability score calculation unit, used to calculate the suitability score of each of the to-be-selected insurance products based on each of the user's individual information and the product attributes of each of the to-be-selected insurance products;
[0086] The unit for determining the set of insurance products to be selected is used to sort the insurance products to be selected based on the suitability scores of the insurance products to be selected, and to select the insurance products to be selected whose suitability scores are greater than a preset suitability score threshold as the set of insurance products to be selected.
[0087] Furthermore, the user single item information generating unit includes:
[0088] A target keyword decomposition subunit, used for converting the target user information into a target information text, and decomposing the target information text into at least one group of target keywords based on a preset natural language processing technology NLP;
[0089] A target keyword matching subunit, used to match each preset single item of information in the preset single item information library with each of the target keywords;
[0090] The user single item information determination subunit is used to determine the preset single item information matching the target keyword as the user single item information.
[0091] Furthermore, the initial insurance product set determination module 410 includes:
[0092] A claim risk list determination unit, configured to determine a claim risk list of the target user based on the historical claim records;
[0093] A scenario factor determination unit, configured to determine a scenario factor of the target user based on the target user information;
[0094] The initial insurance product set determination unit is used to determine the initial insurance product set through dynamic programming rules, the claim risk list and the scenario factors.
[0095] Furthermore, the initial insurance product set determination unit includes:
[0096] A dynamic programming model establishment subunit, used to assign weights to each of the scenario factors through the dynamic programming rules to establish a dynamic programming model;
[0097] An insurance recommendation score calculation subunit, used to calculate the insurance recommendation score corresponding to each of the scenario factors with different weights based on the dynamic programming model and the claim risk list;
[0098] The initial insurance product set determination subunit is used to determine the insurance corresponding to the claim risk list whose insurance recommendation score is greater than the recommendation score threshold as the initial insurance product set.
[0099] Furthermore, the initial insurance product set determination unit further includes:
[0100] An initial insurance product determination subunit, configured to perform dynamic programming on the claim risk list and the scenario factors respectively according to the recursive algorithm, and determine initial insurance products corresponding to the claim risk list and the scenario factors respectively;
[0101] The initial insurance product set determination subunit is used to generate the initial insurance product set after deduplication processing of the claim risk list and the initial insurance products corresponding to the scenario factors.
[0102] Furthermore, the insurance product recommendation device 400 further includes:
[0103] The historical screening condition acquisition module is used to obtain the historical screening conditions of all users through network big data;
[0104] A product label adding module, configured to add a product label to each of the initial insurance products in the initial insurance product set according to the determined historical screening conditions and the historical claims records;
[0105] A preset recursive algorithm generation module is used to train an initial recursive algorithm through the product labels and each of the initial insurance products to generate the preset recursive algorithm.
[0106] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0107] The above-mentioned device can be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.
[0108] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.
[0109] See also Figure 4 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
[0110] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any insurance product recommendation method.
[0111] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0112] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any insurance product recommendation method.
[0113] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0114] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0115] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:
[0116] Determine the initial insurance product set based on historical claims records and target user information of target users;
[0117] Based on the product attributes of each candidate insurance product in the initial insurance product set and the target user information, all the candidate insurance products are sorted, and a candidate insurance product set is generated based on all the sorted candidate insurance products;
[0118] According to the preset screening conditions of the target user, a target insurance product is determined from the set of insurance products to be selected.
[0119] In one embodiment, based on the target user information of the target user and the product attributes of each of the insurance products to be selected in the initial insurance product set, all of the insurance products to be selected are sorted, and a set of insurance products to be selected is generated based on all of the sorted insurance products to be selected, so as to achieve:
[0120] Decomposing the target user information to generate at least one set of user single item information;
[0121] Calculate the suitability score of each of the insurance products to be selected based on the individual information of each user and the product attributes of each of the insurance products to be selected;
[0122] Based on the suitability score of each of the insurance products to be selected, the insurance products to be selected are sorted, and the insurance products to be selected whose suitability score is greater than a preset suitability score threshold are taken as the insurance product set to be selected.
[0123] In one embodiment, the target user information is disassembled to generate at least one set of user single item information, so as to achieve:
[0124] Convert the target user information into target information text, and decompose the target information text into at least one group of target keywords based on a preset natural language processing technology NLP;
[0125] Matching each preset single item of information in the preset single item information library with each of the target keywords;
[0126] The preset single item of information matching the target keyword is determined as the user single item of information.
[0127] In one embodiment, based on historical claims records and target user information of target users, an initial insurance product set is determined to achieve:
[0128] Based on the historical claims records, determining a claims risk list for the target user;
[0129] Based on the target user information, determining the scenario factor of the target user;
[0130] The initial insurance product set is determined through dynamic programming rules, the claim risk list and the scenario factors.
[0131] In one embodiment, the initial insurance product set is determined by dynamic programming rules, the claim risk list and the scenario factors to achieve:
[0132] Assigning weights to each of the scenario factors using the dynamic programming rules to establish a dynamic programming model;
[0133] Based on the dynamic programming model and the claim risk list, calculating the insurance recommendation score corresponding to each of the scenario factors with different weights;
[0134] The insurance corresponding to the claim risk list whose insurance recommendation score is greater than the recommendation score threshold is determined as the initial insurance product set.
[0135] In one embodiment, the initial insurance product set is determined by dynamic programming rules, the claim risk list and the scenario factors, and is also used to achieve:
[0136] According to the recursive algorithm, dynamic programming is performed on the claim risk list and the scenario factors respectively, and initial insurance products corresponding to the claim risk list and the scenario factors are determined respectively;
[0137] After deduplication processing is performed on the claim risk list and the initial insurance products corresponding to the scenario factors, the initial insurance product set is generated.
[0138] In one embodiment, before determining the initial insurance product set based on historical claim settlement records and target user information of the target user, it is used to implement:
[0139] Obtain historical screening conditions of all users through network big data;
[0140] Adding a product tag to each of the initial insurance products in the initial insurance product set according to the determined historical screening condition and the historical claims records;
[0141] The preset recursive algorithm is generated by training an initial recursive algorithm with the product labels and each of the initial insurance products.
[0142] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the insurance product recommendation methods provided in the embodiments of the present application.
[0143] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Medi a Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), etc., equipped on the computer device.
[0144] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for recommending insurance products, characterized in that: include: Determine the initial insurance product set based on historical claims records and target user information of target users; Based on the product attributes of each candidate insurance product in the initial insurance product set and the target user information, all the candidate insurance products are sorted, and a candidate insurance product set is generated based on all the sorted candidate insurance products; According to the preset screening conditions of the target user, a target insurance product is determined from the set of insurance products to be selected.
2. The insurance product recommendation method according to claim 1, characterized in that: The step of sorting all the insurance products to be selected based on the target user information of the target user and the product attributes of each insurance product to be selected in the initial insurance product set, and generating a set of insurance products to be selected based on all the sorted insurance products to be selected, includes: Decomposing the target user information to generate at least one set of user single item information; Calculate the suitability score of each of the insurance products to be selected based on the individual information of each user and the product attributes of each of the insurance products to be selected; Based on the suitability score of each of the insurance products to be selected, the insurance products to be selected are sorted, and the insurance products to be selected whose suitability score is greater than a preset suitability score threshold are taken as the insurance product set to be selected.
3. The insurance product recommendation method according to claim 2, characterized in that: The step of disassembling the target user information to generate at least one set of user single item information includes: Convert the target user information into target information text, and decompose the target information text into at least one group of target keywords based on a preset natural language processing technology NLP; Matching each preset single item of information in the preset single item information library with each of the target keywords; The preset single item of information matching the target keyword is determined as the user single item of information.
4. The insurance product recommendation method according to claim 1, characterized in that: The determining of the initial insurance product set based on the historical claims records and the target user information of the target user includes: Based on the historical claims records, determining a claims risk list for the target user; Based on the target user information, determining the scenario factor of the target user; The initial insurance product set is determined through dynamic programming rules, the claim risk list and the scenario factors.
5. The insurance product recommendation method according to claim 4, characterized in that: The determining of the initial insurance product set by using dynamic programming rules, the claim risk list and the scenario factors includes: Assigning weights to each of the scenario factors using the dynamic programming rules to establish a dynamic programming model; Based on the dynamic programming model and the claim risk list, calculating the insurance recommendation score corresponding to each of the scenario factors with different weights; The insurance corresponding to the claim risk list whose insurance recommendation score is greater than the recommendation score threshold is determined as the initial insurance product set.
6. The insurance product recommendation method according to claim 4, characterized in that: The dynamic programming rule includes a recursive algorithm, and the initial insurance product set is determined by the dynamic programming rule, the claim risk list and the scenario factors, and further includes: According to the recursive algorithm, dynamic programming is performed on the claim risk list and the scenario factors respectively, and initial insurance products corresponding to the claim risk list and the scenario factors are determined respectively; After deduplication processing is performed on the claim risk list and the initial insurance products corresponding to the scenario factors, the initial insurance product set is generated.
7. The insurance product recommendation method according to claim 6, characterized in that: Before determining the initial insurance product set based on the historical claims records and the target user information of the target user, the method includes: Obtain historical screening conditions of all users through network big data; Adding a product tag to each of the initial insurance products in the initial insurance product set according to the determined historical screening condition and the historical claims records; The preset recursive algorithm is generated by training an initial recursive algorithm with the product labels and each of the initial insurance products.
8. An insurance product recommendation device, characterized in that: include: An initial insurance product set determination module, used to determine an initial insurance product set based on historical claims records and target user information of target users; A module for determining a set of insurance products to be selected, configured to sort all the insurance products to be selected based on the product attributes of each insurance product to be selected in the initial insurance product set and the target user information, and generate a set of insurance products to be selected based on all the sorted insurance products to be selected; The target insurance product determination module is used to determine the target insurance product from the set of insurance products to be selected according to the preset screening conditions of the target user.
9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the insurance product recommendation method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the insurance product recommendation method according to any one of claims 1 to 7.