Service recommendation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, is suitable for the fields of financial insurance and medical health, and provides a business recommendation method, device and equipment and a storage medium, and the method comprises the steps: obtaining the insurance purchase historical information and health condition information of a plurality of users, and obtaining the target behavior information of each user; based on the insurance purchase historical information and the target behavior information of each user, determining first index information of each user; determining second index information of each user based on insurance purchase historical information and health condition information of each user; and based on the first index information and the second index information of each user, determining at least one target user from the plurality of users to perform service recommendation. According to the method, the association among the insurance purchase historical information, the health condition information and the target behavior information can be deeply analyzed, and interests and demands of the user are fully mined from a deeper level, so that the accuracy of service recommendation is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, is applicable to the field of finance and insurance, and in particular to a business recommendation method, device, equipment and storage medium. Background Art

[0002] In the financial insurance sector, insurance products are developed, designed, and sold by financial insurers based on the needs, risk tolerance, and protection requirements of specific target customer groups. With rising living standards and increased risk awareness, demand for insurance products is increasing, particularly in areas such as health, accidental injuries, and retirement protection.

[0003] However, the user information of current financial insurance companies is mostly scattered across multiple channels or systems, or stored in existing portrait libraries, but some key information is mixed or missing, making it difficult for insurance companies to effectively utilize this information, resulting in low accuracy in business recommendations. Summary of the Invention

[0004] The main purpose of this application is to provide a service recommendation method, device, equipment and storage medium, which help to improve the accuracy of service recommendations.

[0005] In a first aspect, the present application provides a service recommendation method, comprising:

[0006] Obtaining insurance purchase history information and health status information of multiple users, and obtaining target behavior information of each user; wherein the target behavior information is behavior data generated by the user's specific behavior for at least one insurance business;

[0007] Determining first indicator information of each user based on the insurance purchase history information and target behavior information of each user;

[0008] Determining second indicator information for each user based on the insurance purchase history information and health status information of each user;

[0009] Based on the first indicator information and the second indicator information of each user, at least one target user is determined from the multiple users for service recommendation.

[0010] In a second aspect, the present application further provides a service recommendation device, the service recommendation device comprising:

[0011] A data acquisition module is configured to acquire insurance purchase history information and health status information of multiple users, and to acquire target behavior information of each user; wherein the target behavior information is behavior data generated by the user's specific behavior regarding at least one insurance business;

[0012] A first information determination module, configured to determine first indicator information of each user based on the insurance purchase history information and target behavior information of each user;

[0013] A second information determination module, configured to determine the second indicator information of each user based on the insurance purchase history information and health status information of each user;

[0014] The user determination module is used to determine at least one target user from a plurality of users for service recommendation based on the first indicator information and the second indicator information of each user.

[0015] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the business recommendation method described above are implemented.

[0016] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the business recommendation method described above are implemented.

[0017] The present application provides a business recommendation method, apparatus, device, and storage medium. The present application obtains insurance purchase history information and health status information of multiple users, and obtains target behavior information of each user. Based on the insurance purchase history information and target behavior information of each user, the present application determines first indicator information of each user, and the first indicator information is used to characterize the degree of interest of each user in the insurance business; based on the insurance purchase history information and health status information of each user, the present application determines second indicator information of each user, and the second indicator information is used to characterize the degree of demand of the user for the insurance business; based on the first indicator information and the second indicator information of each user, at least one target user is determined from the multiple users for business recommendation. The present application can effectively integrate and analyze data in fields such as finance and insurance, deeply analyze the relationship between insurance purchase history information, health status information, and target behavior information, and fully explore the interests and needs of users at a deeper level, thereby greatly improving the accuracy of business recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. 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 any creative work.

[0019] Figure 1 A flowchart of the steps of a service recommendation method provided in an embodiment of the present application;

[0020] Figure 2 for Figure 1 A schematic diagram of a sub-step flow chart of a business recommendation method;

[0021] Figure 3 for Figure 1 A flowchart of another sub-step of the business recommendation method;

[0022] Figure 4 for Figure 1 A schematic diagram of another sub-step flow chart of the business recommendation method;

[0023] Figure 5 A schematic diagram of a scenario of a service recommendation method provided in an embodiment of the present application;

[0024] Figure 6 A schematic block diagram of a business recommendation device provided in an embodiment of the present application;

[0025] Figure 7 for Figure 6 A schematic block diagram of a submodule of a business recommendation device;

[0026] Figure 8 for Figure 6 A schematic block diagram of another submodule of the business recommendation device;

[0027] Figure 9 for Figure 6 A schematic block diagram of another submodule of the business recommendation device;

[0028] Figure 10 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0029] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all 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 vary depending on the actual situation.

[0032] Embodiments of the present application provide a service recommendation method, apparatus, device, and storage medium. The service recommendation method can be applied to a terminal device or server. The terminal device can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. The following explanation uses the application of the service recommendation method to a server as an example.

[0033] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0034] Please refer to Figure 1 , Figure 1 A flowchart illustrating the steps of a service recommendation method provided in an embodiment of the present application.

[0035] like Figure 1 As shown, the service recommendation method includes steps S101 to S104.

[0036] Step S101: Obtain insurance purchase history information and health status information of multiple users, and obtain target behavior information of each user.

[0037] Among them, insurance purchase history information may include detailed data such as the type of insurance products purchased by the user, purchase time, purchase amount and purchase frequency, which can be obtained through various channels, such as the user's account records, API interfaces provided by insurance companies for obtaining purchase records, etc.

[0038] Health status information can include basic physical information (such as age and gender), medical history (history of major diseases, chronic diseases, and family medical history), and health behavior information (such as healthy living habits and dietary habits). Similarly, health status information can be obtained through various channels, such as third-party health monitoring devices (such as smart watches and health applications), user-provided health records or physical examination reports.

[0039] Target behavior information is behavioral data generated by users' specific actions related to at least one insurance business. Specific behaviors can be online, such as triggering controls set by users for a particular insurance business, such as clicks, searches, browsing, and inquiries. These actions can be collected using technologies like tracking data. Specific behaviors can also be offline, such as users' interest in or inquiries about insurance products in real-world scenarios, such as communicating with sales staff over the phone or participating in offline insurance promotional events.

[0040] The above-mentioned insurance purchase history information and other data can be stored in a centralized data platform, such as managed using a data warehouse or database system.

[0041] For example, the insurance purchase history information, health status information, and target behavior information of four users numbered 1-4 are obtained, and these data are cleaned and standardized, and finally the data shown in Table 1 below is obtained:

[0042] Table 1

[0043]

[0044]

[0045] It should be noted that by obtaining information in multiple dimensions such as insurance purchase history information, health status information, and target behavior information related to the user's insurance business, it helps to accurately identify the user's interests, needs, etc., and provide data support and lay the foundation for subsequent target user screening and insurance business recommendations.

[0046] In one embodiment, the health status information includes current health status information and historical health status information. Obtaining the insurance purchase history information and health status information of multiple users includes: obtaining multiple health check data of each user, and determining the current health status information of each user from the multiple health check data based on a first specific time range; obtaining at least one insurance purchase history information of each user and the insurance purchase time corresponding to each insurance purchase history information, and determining the historical health status information corresponding to each insurance purchase history information from the multiple health check data based on the first specific time range and each insurance purchase time.

[0047] It is understandable that the user's health status usually changes over time, and such changes in health status may directly affect the user's demand for certain types of insurance products. For example, many users choose to purchase insurance products after a physical examination or when their health status changes. In this case, there is a high degree of synchronization between health status and insurance purchase in terms of time. Therefore, determining the user's health status information before purchasing insurance based on the first specific time range (such as three months, six months, etc.) before the purchase time of each insurance will help analyze the correlation between historical health status information and insurance purchase history information, so that the user's current demand for insurance products can be accurately predicted through the user's current status information.

[0048] In one embodiment, the target behavior information includes current behavior information and historical behavior information. Obtaining the target behavior information of each user includes: obtaining a behavior data set generated by each user triggering a relevant control set for any insurance business, and determining the current behavior information of each user from each behavior data set based on a second specific time range; determining the historical behavior information corresponding to each insurance purchase history information from each behavior data set based on the second specific time range and the insurance purchase time corresponding to each insurance purchase history information.

[0049] It's understandable that a user's target behavior information (e.g., behavioral data generated by clicks, browsing, searching, and inquiries) can reflect their interest in specific insurance products. These behaviors are often precursors to purchase decisions, which often occur after a period of accumulated interactions. Therefore, by analyzing the correlation between historical behavior information in target behavior information and insurance purchase history over time, we can more accurately predict users' interests based on their current behavior information, helping to improve user conversion rates.

[0050] It should be noted that in order to further ensure the privacy and security of the above-mentioned users' insurance purchase history information, health status information and other related information, the above-mentioned insurance purchase history information, health status information and other related information can also be stored in a blockchain node. The technical solution of this application can also be applied to adding other data files stored on the blockchain. The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.

[0051] Step S102: Determine first indicator information of each user based on the insurance purchase history information and target behavior information of each user.

[0052] Among them, the first indicator information can be one or more indicators used to characterize the user's interest in various types of insurance products. The first indicator information can be in the form of a level, probability or score. For example, use numbers (such as 1-10 points) to represent the user's interest in a certain type of insurance product, or use scores to reflect the user's interest in the insurance business. The higher the score, the stronger the user's interest. Similarly, on the display end, such as in an APP used by sales staff, the first indicator information can also be displayed in text forms such as labels, such as "High interest in critical illness insurance" and "Prefer health insurance", so that sales staff can intuitively and quickly understand the user's interests.

[0053] In one embodiment, if Figure 2 As shown, step S102 includes: sub-step S1021 to sub-step S1022.

[0054] Sub-step S1021: Based on multiple insurance purchase history information and corresponding historical behavior information, fine-tune the preset first neural network to obtain an interest prediction network.

[0055] The first neural network can be a pre-trained deep learning model, such as a multi-layer perceptron (MLP) or convolutional neural network (CNN), for processing data input and generating prediction results. Fine-tuning the first neural network involves further adjusting its parameters based on multiple pieces of insurance purchase history information and multiple pieces of historical behavior information, enabling it to adapt to data patterns unique to the financial and insurance sectors, thereby enabling the resulting interest prediction network to more accurately predict user interest.

[0056] Sub-step S1022: inputting the current behavior information corresponding to each user into the interest prediction network to obtain the first indicator information of each user.

[0057] The current behavior information generally represents the user's latest interest changes. It should be noted that dynamically updating the user's first indicator information based on the user's latest behavior data (i.e., the current behavior information) ensures that the first indicator information always accurately reflects the user's current interest in various insurance products.

[0058] It is understandable that the interest prediction network is not limited to the above-mentioned method of fine-tuning the trained first neural network model. The interest prediction network can be implemented in various forms and technologies, and the specific choice depends on factors such as task requirements, data type and complexity.

[0059] In some embodiments, based on each user's insurance purchase history information and target behavior information, determining each user's first indicator information includes: inputting each user's corresponding current behavior information into a preset interest prediction network to obtain each user's first indicator information.

[0060] The interest prediction network may be a trained deep learning model such as MLP or CNN.

[0061] In other embodiments, based on each user's insurance purchase history information and target behavior information, the first indicator information of each user is determined, including: inputting the current behavior information corresponding to each user into a preset prediction model, and obtaining the first indicator information of each user through the interest prediction network in the prediction model.

[0062] Among them, the prediction model can be a composite model containing multiple sub-networks, and the interest prediction network is one of the sub-networks. The interest prediction network can be used to predict interest based on the user's target behavior information, while the remaining sub-networks can be used for other tasks, such as data cleaning, to achieve more accurate and comprehensive interest prediction.

[0063] Step S103: Determine the second indicator information of each user based on the insurance purchase history information and health status information of each user.

[0064] Insurance purchase history information can include information such as the type of insurance purchased, the amount purchased, the purchase date, and the frequency of purchases. This information can reflect a user's past insurance needs. For example, if user A has purchased health insurance or critical illness insurance multiple times over the past few years, it can be inferred that user A has a continued demand for this type of insurance.

[0065] Health information can include a user's health status, whether they have chronic diseases, whether they have undergone major surgery or treatment, and whether they have a family history of illness. This information can directly reflect a user's health risk and, in turn, influence their demand for certain insurance services or products. For example, if User B is diagnosed with a major illness or high-risk health condition, it can be inferred that User B's demand for major illness insurance or medical insurance will increase accordingly.

[0066] The second indicator information can be one or more indicators, used to represent the user's demand for insurance services. Similarly, the second indicator information can also be in the form of a grade, probability, or score, as used by the first indicator information. It is understood that the second indicator information is typically presented in the same format as the first indicator information to maintain consistency in subsequent processing, comparison, and presentation, thereby improving system processing efficiency and consistency in result interpretation.

[0067] It should be noted that by combining the user's insurance purchase history information and health status information, the user's needs can be analyzed at a deeper level, so that the user's demand for insurance business can be more accurately assessed, and then more personalized and accurate insurance recommendations can be provided to the user, which will help improve user experience and increase conversion rates.

[0068] In one embodiment, if Figure 3 As shown, step S103 includes: sub-step S1031 to sub-step S1032.

[0069] Sub-step S1031: Based on the multiple insurance purchase history information and the historical health status information corresponding to each insurance purchase history information, fine-tune the preset second neural network model to obtain a demand prediction network.

[0070] The specific model and adjustment process used by the second neural network can be referenced to the fine-tuning process of the first neural network described above and will not be elaborated on here. It should be noted that the parameters of the second neural network are optimized based on the user's historical health information and historical health information, so that the adjusted demand prediction network can better predict the user's demand for insurance products.

[0071] Sub-step S1032: inputting the current health status information corresponding to each user into the demand prediction network to obtain the second indicator information of each user.

[0072] A user's health status is dynamic, and their current health status often reflects the latest changes in their needs. For example, user C has always purchased medical insurance and has no history of health issues (i.e., no prior medical history). However, within the past month, user C was diagnosed with a chronic disease (such as diabetes). This change will significantly affect their need for medical insurance.

[0073] It should be noted that dynamically updating the user's second indicator information based on the user's latest health status (i.e., current health status information) can ensure that the second indicator information can always accurately reflect the user's current demand for various insurance services.

[0074] It should also be noted that the process of deriving the user's second indicator information from the current health status information is not limited to the aforementioned method of fine-tuning the trained second neural network. It is understood that the second indicator information can be obtained through a preset demand forecasting network or through a demand forecasting network within a preset forecasting model. The details can be referenced to the process of determining the first indicator information described above and are not further elaborated here.

[0075] Step S104: Based on the first indicator information and the second indicator information of each user, determine at least one target user from the multiple users to make service recommendations.

[0076] For example, the first indicator information and the second indicator information are both in the form of scores (with a maximum score of 10 points). At the same time, the first indicator information or the second indicator information can also be selectively displayed in the form of user tags on the client for use by sales personnel. Referring to Table 2 below, Table 2 shows the first indicator information and the second indicator information and the user tag corresponding to the user number AD.

[0077] Table 2

[0078]

[0079] It should be noted that Table 2 above displays only the highest values ​​from the multiple first or second indicators. User tags are generated based on the insurance business corresponding to the displayed first or second indicator information, making them more intuitive and effective than directly displaying the first or second indicator information. This approach enables more precise personalized recommendations, helping sales staff identify and reach the most promising users, facilitate transactions based on user preferences or needs for specific insurance services, and effectively improve user satisfaction and loyalty.

[0080] In one embodiment, if Figure 4 As shown, step S104 includes: sub-steps S1041 to S1043.

[0081] Sub-step S1041: determining at least one target user from a plurality of users based on the first indicator information and the second indicator information of each user.

[0082] By comparing the first and second indicator information of multiple users, the user who best meets the recommendation criteria can be selected as the target user. For example, target users can be screened by setting a threshold (e.g., when both the first and second indicator information are greater than a certain value). It should be noted that combining the first and second indicator information can provide a more comprehensive understanding of users' interests and needs, thereby enabling more accurate selection of target users.

[0083] Sub-step S1042: Determine the business recommendation plan and target recommendation personnel corresponding to the target user based on the first indicator information and the second indicator information of the target user.

[0084] Based on the target user's interest and demand, as represented by their first and second indicators, respectively, personalized service recommendations can be developed for them. Target recommendation personnel can be selected based on factors such as the complexity of the service recommendation task, user type, region, and each salesperson's expertise. The most suitable salesperson can be selected from the salesperson database to ensure that subsequent service recommendations are smoothly and accurately communicated to the target user.

[0085] Recommended plans can include specific product types (such as health insurance, critical illness insurance, and medical insurance), product combinations, premium ranges, coverage amounts, and contact methods (SMS, email, in-app messaging, etc.). Specifically, interest reflects the target user's interest in different insurance types, while demand reflects the strength of their actual protection needs. By combining these two factors, we determine the insurance products that the target user is most likely to accept and that best meet their needs, and develop personalized recommendations accordingly.

[0086] In addition to personalized recommendations, business recommendation plans can also be selected from multiple preset recommendation plans in the plan library, and the best plan can be screened out for matching based on the first indicator information and second indicator information of the target user to ensure the pertinence and professionalism of the recommended content, thereby further improving the success rate of recommendations and user satisfaction.

[0087] Sub-step S1043: sending the service recommendation plan to the target recommendation person so that the target recommendation person can make service recommendations to the target user.

[0088] Among them, after determining the business recommendation plan and recommender, the target user and his / her corresponding business recommendation plan are sent to the target recommender. After receiving the business recommendation plan, the target recommender is responsible for contacting and communicating with the user based on the content of the business recommendation plan, and ultimately promoting the target user to make a purchase decision.

[0089] In one embodiment, based on the first indicator information and the second indicator information of the target user, a business recommendation plan and a target recommendation person corresponding to the target user are determined, including: based on the first indicator information and the second indicator information of the target user, determining multiple candidate insurance businesses corresponding to the target user; screening out at least one target insurance business from multiple candidate insurance businesses, and generating a business recommendation plan corresponding to the target insurance business; based on the first indicator information, the second indicator information and the business recommendation plan of the target user, determining the target recommendation person from multiple candidate recommendation persons.

[0090] For example, refer to Figure 5 , Figure 5Schematic diagram of a scenario of a business recommendation method provided in an embodiment of the present application. Among them, user W's insurance purchase history information, health status information, and target behavior information are uploaded to the insurance company's system from multiple channels (such as the terminal device used by the user, etc.). After analysis by the insurance system, the first indicator information and the second indicator information of user W are obtained as 6.0 (critical illness insurance) and 9.0 (critical illness insurance), respectively. It can be seen that user W has a high demand and interest in critical illness insurance. The system will prioritize screening critical illness insurance from the candidate insurance business as the target insurance business, and formulate a business recommendation plan for user W based on critical illness insurance. The business recommendation plan includes critical illness insurance products, additional protection (such as major disease insurance), a premium range of 5,000-8,000 yuan, and a guarantee amount of 500,000 yuan. The system further selects a salesperson who is good at critical illness insurance (such as Zhang San) as the target recommender based on the professionalism in the field of critical illness insurance, and sends user W's personal information and the corresponding business recommendation plan to the terminal device used by Zhang San. Zhang San contacts user W based on the business recommendation plan and makes business recommendations.

[0091] The business recommendation method, apparatus, device and storage medium provided in the above embodiments, the present application obtains the insurance purchase history information and health status information of multiple users, and obtains the target behavior information of each of the users, and determines the first indicator information of each user based on the insurance purchase history information and target behavior information of each user, the first indicator information is used to characterize the degree of interest of each user in the insurance business; determines the second indicator information of each user based on the insurance purchase history information and health status information of each user, the second indicator information is used to characterize the degree of demand of the user for the insurance business; and determines at least one target user from the multiple users for business recommendation based on the first indicator information and the second indicator information of each user. The present application can effectively integrate and analyze data in the financial and insurance fields, deeply analyze the relationship between insurance purchase history information, health status information and target behavior information, and fully explore the interests and needs of users from a deeper level, thereby greatly improving the accuracy of business recommendations in the financial and insurance fields.

[0092] Please refer to Figure 6 , Figure 6 A schematic block diagram of a service recommendation device provided in an embodiment of the present application.

[0093] like Figure 6 As shown, the service recommendation device 200 includes:

[0094] The data acquisition module 201 is used to acquire the insurance purchase history information and health information of multiple users, and acquire the target behavior information of each user; wherein the target behavior information is the behavior data generated by the user's specific behavior for at least one insurance business;

[0095] A first information determination module 202 is configured to determine first indicator information of each user based on the insurance purchase history information and target behavior information of each user;

[0096] A second information determination module 203 is configured to determine the second indicator information of each user based on the insurance purchase history information and health status information of each user;

[0097] The user determination module 204 is configured to determine at least one target user from a plurality of users for service recommendation based on the first indicator information and the second indicator information of each user.

[0098] In one embodiment, the health status information includes current health status information and historical health status information. The data acquisition module 201 is further configured to:

[0099] Obtain multiple health check data of each user, and based on a first specific time range, determine the current health status information of each user from the multiple health check data; obtain at least one insurance purchase history information of each user and the insurance purchase time corresponding to each insurance purchase history information, and based on the first specific time range and each insurance purchase time, determine the historical health status information corresponding to each insurance purchase history information from the multiple health check data.

[0100] In one embodiment, the target behavior information includes current behavior information and historical behavior information. The data acquisition module 201 is further configured to:

[0101] Obtaining a behavior data set generated by each user triggering a relevant control set for any insurance business, and determining current behavior information of each user from each behavior data set based on a second specific time range;

[0102] Based on the second specific time range and the insurance purchase time corresponding to each insurance purchase history information, historical behavior information corresponding to each insurance purchase history information is determined from each behavior data set.

[0103] In one embodiment, Figure 7 As shown, the first information determination module 202 includes:

[0104] The first training submodule 2021 is used to fine-tune the preset first neural network based on multiple insurance purchase history information and corresponding historical behavior information to obtain an interest prediction network.

[0105] The first prediction submodule 2022 is used to input the current behavior information corresponding to each user into the interest prediction network to obtain the first indicator information of each user.

[0106] In one embodiment, Figure 8 As shown, the second information determination module 203 includes:

[0107] The second training submodule 2031 is used to fine-tune the preset second neural network model based on multiple insurance purchase history information and historical health information corresponding to each insurance purchase history information to obtain a demand prediction network.

[0108] The second prediction submodule 2032 is used to input the current health status information corresponding to each user into the demand prediction network to obtain the second indicator information of each user.

[0109] In one embodiment, Figure 9 As shown, the user determination module 204 includes:

[0110] The target user determination submodule 2041 determines at least one target user from a plurality of users based on the first indicator information and the second indicator information of each user.

[0111] The solution personnel determination submodule 2042 determines the business recommendation solution and target recommendation personnel corresponding to the target user based on the first indicator information and the second indicator information of the target user.

[0112] The recommendation plan sending submodule 2043 sends the service recommendation plan to the target recommendation person so that the target recommendation person can make service recommendations to the target user.

[0113] In one embodiment, the recommendation plan determination submodule 2042 is also used to: determine multiple candidate insurance businesses corresponding to the target user based on the first indicator information and the second indicator information of the target user; screen out at least one target insurance business from multiple candidate insurance businesses, and generate a business recommendation plan corresponding to the target insurance business; determine the target recommendation person from multiple candidate recommendation persons based on the first indicator information, the second indicator information and the business recommendation plan of the target user.

[0114] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned business recommendation method embodiment and will not be repeated here.

[0115] The apparatus provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 10 Runs on the computer device shown.

[0116] See also Figure 10 , Figure 10 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0117] like Figure 10 As shown, the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a storage medium and an internal memory, and the storage medium may be non-volatile or volatile.

[0118] The storage medium may store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor may execute any one of the service recommendation methods.

[0119] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0120] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any service recommendation method.

[0121] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 10 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0122] It should be understood that the processor may be a central processing unit (CPU), 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. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0123] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0124] Obtaining insurance purchase history information and health status information of multiple users, and obtaining target behavior information of each user; wherein the target behavior information is the behavior data generated by the user's specific behavior for at least one insurance business;

[0125] Determining first indicator information for each user based on the insurance purchase history information and target behavior information of each user;

[0126] Determining second indicator information for each user based on the insurance purchase history information and health status information of each user;

[0127] Based on the first indicator information and the second indicator information of each user, at least one target user is determined from multiple users for service recommendation.

[0128] In one embodiment, the health status information includes current health status information and historical health status information. When obtaining the insurance purchase history information and health status information of multiple users, the processor is configured to:

[0129] Obtaining multiple health check data of each user, and determining current health status information of each user from the multiple health check data based on a first specific time range;

[0130] Obtain at least one insurance purchase history information of each user and the insurance purchase time corresponding to each insurance purchase history information, and based on the first specific time range and each insurance purchase time, determine the historical health status information corresponding to each insurance purchase history information from multiple health examination data.

[0131] In one embodiment, the target behavior information includes current behavior information and historical behavior information. When obtaining the target behavior information of each user, the processor is configured to:

[0132] Obtaining a behavior data set generated by each user triggering a relevant control set for any insurance business, and determining current behavior information of each user from each behavior data set based on a second specific time range;

[0133] Based on the second specific time range and the insurance purchase time corresponding to each insurance purchase history information, historical behavior information corresponding to each insurance purchase history information is determined from each behavior data set.

[0134] In one embodiment, when determining the first indicator information of each user based on the insurance purchase history information and target behavior information of each user, the processor is configured to:

[0135] Based on the plurality of insurance purchase history information and the corresponding historical behavior information, fine-tuning the preset first neural network to obtain an interest prediction network, and obtaining an interest prediction network;

[0136] The current behavior information corresponding to each user is input into the interest prediction network to obtain the first indicator information of each user.

[0137] In one embodiment, when determining the second indicator information of each user based on the insurance purchase history information and health status information of each user, the processor is configured to:

[0138] Based on the multiple insurance purchase history information and the historical health status information corresponding to each insurance purchase history information, fine-tuning the preset second neural network model to obtain a demand prediction network;

[0139] The current health status information corresponding to each user is input into the demand prediction network to obtain the second indicator information of each user.

[0140] In one embodiment, when determining at least one target user from a plurality of users for service recommendation based on the first indicator information and the second indicator information of each user, the processor is configured to implement:

[0141] Determining at least one target user from a plurality of users based on the first indicator information and the second indicator information of each user;

[0142] Determine a business recommendation plan and a target recommendation person corresponding to the target user based on the first indicator information and the second indicator information of the target user;

[0143] The service recommendation plan is sent to the target recommender so that the target recommender can make service recommendations to the target user.

[0144] In one embodiment, when determining the service recommendation scheme and target recommender corresponding to the target user based on the first indicator information and the second indicator information of the target user, the processor is configured to implement:

[0145] Determining a plurality of candidate insurance businesses corresponding to the target user based on the first indicator information and the second indicator information of the target user;

[0146] Selecting at least one target insurance business from multiple candidate insurance businesses and generating a business recommendation plan corresponding to the target insurance business;

[0147] Based on the first indicator information, the second indicator information and the business recommendation plan of the target user, a target recommendation person is determined from multiple candidate recommendation persons.

[0148] 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 computer device described above can refer to the corresponding process in the aforementioned business recommendation method embodiment, and will not be repeated here.

[0149] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. 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, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0150] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the business recommendation method of the present application.

[0151] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned 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 SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0152] Furthermore, the computer-usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created based on the use of blockchain nodes, etc. The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. The blockchain may include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0153] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0154] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0155] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection 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 this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A business recommendation method, characterized in that: include: Obtaining insurance purchase history information and health status information of multiple users, and obtaining target behavior information of each user; wherein the target behavior information is behavior data generated by the user's specific behavior for at least one insurance business; Determining first indicator information of each user based on the insurance purchase history information and target behavior information of each user; Determining second indicator information for each user based on the insurance purchase history information and health status information of each user; Based on the first indicator information and the second indicator information of each user, at least one target user is determined from the multiple users for service recommendation.

2. The service recommendation method according to claim 1, wherein: The health status information includes current health status information and historical health status information; The obtaining of insurance purchase history information and health status information of multiple users includes: Obtaining multiple health check data of each user, and determining current health status information of each user from the multiple health check data based on a first specific time range; Obtain at least one insurance purchase history information of each user and the insurance purchase time corresponding to each insurance purchase history information, and based on the first specific time range and each insurance purchase time, determine the historical health status information corresponding to each insurance purchase history information from the multiple health examination data.

3. The service recommendation method according to claim 2, wherein: The determining of the first indicator information of each user based on the insurance purchase history information and target behavior information of each user includes: Based on the plurality of insurance purchase history information and corresponding historical behavior information, fine-tuning the preset first neural network to obtain an interest prediction network; The current behavior information corresponding to each of the users is input into the interest prediction network to obtain first indicator information of each of the users; wherein the first indicator information is used to represent the degree of interest of each of the users in the insurance business.

4. The service recommendation method according to claim 1, wherein: The target behavior information includes current behavior information and historical behavior information; The obtaining of target behavior information of each user includes: Obtaining a behavior data set generated by each user triggering a related control set for any insurance business, and determining current behavior information of each user from each behavior data set based on a second specific time range; Based on the second specific time range and the insurance purchase time corresponding to each insurance purchase history information, historical behavior information corresponding to each insurance purchase history information is determined from each behavior data set.

5. The service recommendation method according to claim 4, wherein: The determining of the second indicator information of each user based on the insurance purchase history information and health status information of each user includes: Based on the plurality of insurance purchase history information and the historical health status information corresponding to each insurance purchase history information, fine-tuning the preset second neural network model to obtain a demand prediction network; The current health status information corresponding to each of the users is input into the demand prediction network to obtain second indicator information of each of the users; wherein the second indicator information is used to represent the user's demand for the insurance business.

6. The service recommendation method according to any one of claims 1 to 5, characterized in that: The determining at least one target user from the plurality of users for service recommendation based on the first indicator information and the second indicator information of each user includes: Determining at least one target user from the plurality of users based on the first indicator information and the second indicator information of each user; Determining a business recommendation plan and a target recommendation person corresponding to the target user based on the first indicator information and the second indicator information of the target user; The service recommendation plan is sent to the target recommendation person so that the target recommendation person can make service recommendations to the target user.

7. The service recommendation method according to claim 6, wherein: The determining, based on the first indicator information and the second indicator information of the target user, a business recommendation plan and a target recommendation person corresponding to the target user includes: Determining a plurality of candidate insurance businesses corresponding to the target user based on the first indicator information and the second indicator information of the target user; Selecting at least one target insurance business from the plurality of candidate insurance businesses, and generating a business recommendation plan corresponding to the target insurance business; Based on the first indicator information, the second indicator information of the target user and the business recommendation plan, a target recommendation person is determined from a plurality of candidate recommendation persons.

8. A business recommendation device, characterized in that: include: A data acquisition module is configured to acquire insurance purchase history information and health status information of multiple users, and to acquire target behavior information of each user; wherein the target behavior information is behavior data generated by the user's specific behavior regarding at least one insurance business; A first information determination module, configured to determine first indicator information of each user based on the insurance purchase history information and target behavior information of each user; A second information determination module, configured to determine the second indicator information of each user based on the insurance purchase history information and health status information of each user; The user determination module is used to determine at least one target user from a plurality of users for service recommendation based on the first indicator information and the second indicator information of each user.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the service recommendation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the service recommendation method according to any one of claims 1 to 7 is implemented.

Images