Financial service recommendation method and device, computer program product and electronic equipment

Abstract

The invention discloses a financial service recommendation method and device, a computer program product and electronic equipment. The method comprises the following steps: acquiring related information of a user in a preset period; the related information is input into a behavior analysis model, a behavior evaluation value of each type of data in the related information is obtained, the behavior analysis model is obtained through training of multiple sets of training samples, and each set of training samples comprise historical related information and historical behavior evaluation values; determining a target type of the to-be-recommended financial service, and determining an evaluation weight of each type of data in the related information based on the target type; and calculating a recommendation evaluation value based on the behavior evaluation value and the evaluation weight of each type of data in the related information, and recommending the financial service to the client of the user under the condition that the recommendation evaluation value is greater than or equal to a first evaluation value threshold. Through the method and the device, the problem of relatively low accuracy of financial service recommendation in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a financial service recommendation method, device, computer program product, and electronic device. Background Art

[0002] In the related art, customer behavior analysis usually uses a single model to analyze customer data to obtain customer behavior labels, and recommends products to customers based on customer behavior labels. However, the customer behavior analysis method of a single model has low analysis accuracy for customers and cannot achieve accurate product recommendations based on customer behavior analysis.

[0003] Currently, no effective solution has been proposed to address the problem of low accuracy of financial service recommendations in related technologies. Summary of the invention

[0004] The main purpose of the present application is to provide a financial service recommendation method, device, computer program product and electronic device to solve the problem of low accuracy of financial service recommendations in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for recommending financial services is provided. The method includes: obtaining relevant information of a user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information of operations performed by the user in the application of the financial institution; inputting the relevant information into a behavior analysis model to obtain a behavior evaluation value of each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; determining the target type of the financial service to be recommended, and determining the evaluation weight of each type of data in the relevant information based on the target type; calculating the recommended evaluation value based on the behavior evaluation value and evaluation weight of each type of data in the relevant information, and recommending the financial service to the user's client when the recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0006] Optionally, the behavior analysis model is trained in the following manner: obtaining the financial service recommendation records of the financial institution, extracting the historical relevant information and historically recommended financial services of each user from the financial service recommendation records; determining the recommendation results of the historically recommended financial services, and determining the historical behavior evaluation value of each data in the historical relevant information based on the recommendation results; determining the historical relevant information and historical behavior evaluation value of each user as a set of training samples to obtain multiple sets of training samples; training the machine learning model based on the multiple sets of training samples to obtain a behavior analysis model.

[0007] Optionally, determining the evaluation weight of each data in the relevant information based on the target type includes: determining an evaluation weight mapping relationship table, wherein the evaluation weight mapping relationship table contains multiple groups of mapping relationships, each group of mapping relationships contains a type of financial service and a weight setting method, and the weight setting method sets the evaluation weight of each data in the relevant information; extracting a target weight setting method that has a mapping relationship with the target type from the evaluation weight mapping relationship table, and determining the evaluation weight of each data based on the target weight setting method.

[0008] Optionally, after calculating the recommended evaluation value based on the behavior evaluation value and evaluation weight of each data in the relevant information, the method also includes: when the recommended evaluation value is less than the first evaluation value threshold, judging whether the recommended evaluation value is less than or equal to a third evaluation value threshold, wherein the third evaluation value threshold is less than the first evaluation value threshold; when the recommended evaluation value is less than or equal to the third evaluation value threshold, adding a mark to the user, wherein the mark is used to characterize that the financial service is not recommended; when the recommended evaluation value is greater than the third evaluation value threshold, determining a recommendation period for the financial service; updating the relevant information of the user at preset time intervals within the recommendation period, and calculating an updated recommended evaluation value based on the updated relevant information until the updated recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0009] Optionally, recommending financial services to the user's client includes: for each behavior evaluation value in the relevant information, determining whether the behavior evaluation value is greater than or equal to a second evaluation value threshold, wherein the second evaluation value threshold is less than the first evaluation value threshold; when the behavior evaluation value is greater than or equal to the second evaluation value threshold, determining the data as high-frequency behavior data; obtaining multiple recommendation methods for financial services, and calculating an evaluation value of the degree of association between each recommendation method and the high-frequency behavior data; determining the recommendation method corresponding to the maximum correlation degree evaluation value as the target recommendation method, and recommending the financial services to the user's client according to the target recommendation method.

[0010] Optionally, the method further includes: receiving a change request for relevant information, updating the relevant information based on the change request, and obtaining updated relevant information; and executing the step of inputting the relevant information into the behavior analysis model based on the updated relevant information.

[0011] Optionally, calculating the recommended evaluation value based on the behavior evaluation value and evaluation weight of each data in the relevant information includes: determining all data in the relevant information; and performing weighted summation on all data based on the behavior evaluation value and evaluation weight of each data to obtain the recommended evaluation value.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a financial service recommendation device is provided. The device includes: an acquisition unit, which is used to acquire relevant information of a user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information of operations performed by the user in the application of the financial institution; an input unit, which is used to input the relevant information into a behavior analysis model to obtain a behavior evaluation value of each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; a first determination unit, which is used to determine the target type of the financial service to be recommended, and determine the evaluation weight of each type of data in the relevant information based on the target type; a recommendation unit, which is used to calculate a recommendation evaluation value based on the behavior evaluation value and evaluation weight of each type of data in the relevant information, and recommend the financial service to the user's client when the recommendation evaluation value is greater than or equal to the first evaluation value threshold.

[0013] In an embodiment of the present application, the relevant information of the user within a preset period is obtained, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about the user's operations in the application of the financial institution; the relevant information is input into the behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; the target type of the financial service to be recommended is determined, and the evaluation weight of each type of data in the relevant information is determined based on the target type; the recommended evaluation value is calculated based on the behavior evaluation value and the evaluation weight of each type of data in the relevant information, and the financial service is recommended to the user's client in the case where the recommended evaluation value is greater than or equal to a first evaluation value threshold. The relevant information of the user is evaluated by the behavior analysis model to obtain a behavior evaluation value, and then the recommended evaluation value of the financial service to be recommended is calculated based on the behavior evaluation value. If the recommended evaluation value is greater than or equal to the first evaluation value threshold, the financial service is recommended to the user, thereby achieving a multi-dimensional evaluation of the user's behavior and improving the accuracy of the user's behavior analysis, thereby achieving the technical effect of improving the accuracy of the financial service recommendation, and thus solving the technical problem of low accuracy of the financial service recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a financial service recommendation method is shown;

[0016] Figure 2 is a flowchart of a financial service recommendation method provided according to an embodiment of the present application;

[0017] Figure 3 is a schematic diagram of a financial service recommendation device provided according to an embodiment of the present application;

[0018] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0022] Example 1

[0023] According to an embodiment of the present application, a method embodiment of financial service recommendation is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a financial service recommendation method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as an MCU (Microcontroller Unit) or an FPGA (Field-Programmable Gate Array), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a USB (Universal Serial Bus) port (which may be included as one of the ports of a BUS (Business)), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0025] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the financial service recommendation method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the above-mentioned financial service recommendation method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] The display may be, for example, a touch screen liquid crystal display that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0029] In the above operating environment, the present application provides a method for recommending financial services. Figure 2 is a flowchart of a financial service recommendation method provided according to an embodiment of the present application, such as Figure 2 As shown, the method includes:

[0030] Step S201, obtaining relevant information of the user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about operations performed by the user in an application of a financial institution.

[0031] In step S201, the preset period can be set to one day or one week, and the data entered by the user when registering or updating personal information is collected, including but not limited to the user's name, age, gender, occupation and other identity information. All transactions conducted by the user in the financial institution are recorded in real time or regularly, including deposits, withdrawals, transfers, investments, loans and repayments. In addition, transaction information such as transaction amount, transaction frequency, transaction time, transaction location and transaction channel is also included. With the user's authorization, the user's operations in the application of the financial institution are collected, including but not limited to checking account balances, browsing financial products, searching for loan information, using virtual assistants for consultation, participating in online activities or forums, and reading financial news.

[0032] Step S202, inputting the relevant information into the behavior analysis model to obtain the behavior evaluation value of each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values.

[0033] In step S202, the behavior analysis model can be obtained by training a large amount of historical related information and corresponding historical behavior evaluation values ​​based on machine learning technology. The training data set of the model consists of multiple sets of training samples, each of which contains user identity information, transaction information and behavior information within a preset period, as well as a behavior evaluation value obtained by expert system or historical data analysis.

[0034] It should be noted that before inputting relevant information into the model, the data of multiple sets of training samples need to be preprocessed, including data cleaning, feature selection, data standardization or normalization, to ensure the data quality of the input model. For example, remove outliers and missing values, convert non-numeric data into numeric data, and adjust the data to the same scale to avoid certain features from having too much impact on the model due to the numerical range. The preprocessed relevant data is input into the behavior analysis model, and the model will evaluate each type of data according to the rules it has learned and output the corresponding behavior evaluation value. The behavior evaluation value reflects the user's behavioral characteristics in this dimension, such as the user's trading frequency, risk tolerance, and interest in specific financial products.

[0035] By designing an interpretation mechanism, the behavioral evaluation values ​​are mapped to specific business scenarios or labels, such as "high risk", "active user", "potential investor", etc., so that financial institutions can formulate targeted product recommendation strategies based on the evaluation results.

[0036] In some examples, a corresponding behavior analysis model may be formed based on each dimensional data in the multidimensional data of the relevant information, and the multidimensional data of the current user may be evaluated separately through multiple behavior analysis models to obtain a behavior evaluation value of the user.

[0037] Step S203: determine the target type of the financial service to be recommended, and determine the evaluation weight of each type of data in the relevant information based on the target type.

[0038] In step S203, the target type may include but is not limited to asset management, credit services, insurance products, payment solutions or investment advisors. After determining the target type of the financial service to be recommended, it is necessary to determine the evaluation weight of each type of data in the relevant information based on the target type. The evaluation weight reflects the relative importance of different data types in predicting the user's demand for specific financial services.

[0039] It should be noted that different types of financial services have different evaluation weights for each type of data. For example, when recommending asset management services, the weights for these data are higher because they pay more attention to the user's income level, risk preference and historical investment record; when recommending credit services, they pay more attention to the user's credit history, career status and income stability, and thus set higher weights for these data. Design a corresponding weight setting method for each type of financial service. For example, use an expert system or historical data analysis results to set a weight value for each data type. The sum of these weight values ​​is 1 to ensure the comprehensiveness and fairness of the evaluation. Dynamic weight adjustment: Considering the dynamic changes in user behavior and market environment, the evaluation weight should not be static and can be adjusted at any time. Financial institutions adjust the weight setting method regularly or according to market trends to reflect the latest business needs and user preferences.

[0040] Step S204, calculating a recommended evaluation value based on the behavior evaluation value and evaluation weight of each type of data in the relevant information, and recommending the financial service to the user's client when the recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0041] In step S204, the behavior evaluation value of each type of data is multiplied by the corresponding evaluation weight according to the evaluation weight previously determined for the specific financial service target type to reflect the importance of the data in the recommended evaluation value. All weighted behavior evaluation values ​​are aggregated and the recommended evaluation value is calculated by summing, averaging or other statistical methods. The recommended evaluation value is a comprehensive score of the user's needs and matching degree for specific financial services.

[0042] A first evaluation value threshold is set as a decision criterion for recommending financial services. When the calculated recommendation evaluation value is greater than or equal to the first evaluation value threshold, it indicates that the user has a high degree of acceptance and demand for the recommended financial services and meets the recommendation conditions. When the recommendation evaluation value meets the threshold conditions, the corresponding financial services are pushed to the user through the user's client (such as a mobile application, web page, or email system, etc.), achieving accurate reach of personalized services.

[0043] The financial service recommendation method provided in the embodiment of the present application obtains relevant information of the user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about the user's operations in the application of the financial institution; inputs the relevant information into the behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; determines the target type of the financial service to be recommended, and determines the evaluation weight of each type of data in the relevant information based on the target type; calculates the recommended evaluation value based on the behavior evaluation value and the evaluation weight of each type of data in the relevant information, and recommends the financial service to the user's client when the recommended evaluation value is greater than or equal to a first evaluation value threshold, evaluates the relevant information of the user through the behavior analysis model, obtains the behavior evaluation value, and then calculates the recommended evaluation value of the financial service to be recommended based on the behavior evaluation value, and recommends the financial service to the user if the recommended evaluation value is greater than or equal to the first evaluation value threshold, thereby achieving a multi-dimensional evaluation of the user's behavior and improving the accuracy of the user's behavior analysis, thereby achieving the technical effect of improving the accuracy of the financial service recommendation, and thus solving the technical problem of low accuracy of the financial service recommendation.

[0044] In order to accurately evaluate the user's behavior data, it is necessary to train a behavior analysis model. Optionally, in the financial service recommendation method provided in the embodiment of the present application, the behavior analysis model is trained in the following manner: obtaining the financial service recommendation records of the financial institution, extracting the historical relevant information and the historically recommended financial services of each user from the financial service recommendation records; determining the recommendation results of the historically recommended financial services, and determining the historical behavior evaluation value of each data in the historical relevant information based on the recommendation results; determining the historical relevant information and historical behavior evaluation value of each user as a group of training samples to obtain multiple groups of training samples; training the machine learning model based on the multiple groups of training samples to obtain a behavior analysis model.

[0045] In some examples, first, financial service recommendation records are obtained from the database of the financial institution. These records contain relevant information for each user, as well as the recommended financial service type and the recommendation result (acceptance or rejection). From the financial service recommendation records, historical relevant information and historically recommended financial services for each user are extracted. For historical relevant information, data of different dimensions such as identity information, transaction information, and behavior information are further divided. Based on the recommendation results, it is analyzed which types of data have the most significant impact on the acceptance of financial services. For example, if high-income users are more likely to accept investment products, or users who frequently use mobile payments prefer online financial services, they can be converted into specific historical behavior evaluation values ​​based on specific statistical conditions.

[0046] Combine each user's historical information and historical behavior evaluation values ​​determined based on recommendation results into a set of training samples. Ensure the integrity and accuracy of the sample data so that the machine learning model can learn effective patterns from it. Use multiple sets of training samples to train the machine learning model, which can be logistic regression, decision tree, random forest, support vector machine, or neural network. Through methods such as cross-validation and parameter adjustment, optimize the model's prediction performance to ensure its generalization ability under new users or new situations.

[0047] This embodiment trains the model based on actual recommendation records to ensure that the behavior analysis model can accurately reflect the relationship between user behavior and financial service acceptance, thereby improving the accuracy of recommendations. Using multiple sets of training samples enables the model to adapt to different user groups and market environments, enhancing its application capabilities in different scenarios. By using the behavior analysis model to more accurately predict users' potential demand for financial services, financial institutions can provide more personalized service recommendations and improve user satisfaction.

[0048] After determining the target type of the financial service to be recommended, the evaluation weight of each data in the relevant information is determined based on the target type. Optionally, in the financial service recommendation method provided in the embodiment of the present application, determining the evaluation weight of each data in the relevant information based on the target type includes: determining an evaluation weight mapping relationship table, wherein the evaluation weight mapping relationship table includes multiple groups of mapping relationships, each group of mapping relationships includes a type of financial service and a weight setting method, and the weight setting method sets the evaluation weight of each data in the relevant information; extracting the target weight setting method that has a mapping relationship with the target type from the evaluation weight mapping relationship table, and determining the evaluation weight of each data based on the target weight setting method.

[0049] In some examples, an evaluation weight mapping relationship table is developed in advance, which contains mapping relationships between multiple financial service types and specific weight setting methods. Each financial service type corresponds to one or more weight setting methods, and each weight setting method specifies in detail the evaluation weights of different dimensional data in the relevant information. After the target type of the financial service to be recommended is determined, the weight setting method directly related to the target type is searched from the evaluation weight mapping relationship table. Based on the extracted target weight setting method, the evaluation weight of each data is determined. In addition, the weight setting method can be set according to the amount of each data and the way it is obtained. For example, the larger the amount of data, the higher the weight setting.

[0050] Due to the constant changes in market trends and user behavior, the evaluation weight mapping relationship table needs to be updated regularly. Based on the newly collected data and feedback, the weight settings of existing financial service types can be adjusted, or new service types and their weight setting rules can be added.

[0051] This embodiment applies specific weight setting methods according to different financial service types to ensure that the recommended financial services are closely related to the user's personal characteristics and behavior patterns. By quickly looking up the weight setting method in the mapping relationship table, the complexity and uncertainty of weight determination are reduced, and the efficiency of financial service recommendation is improved.

[0052] Whether to make subsequent recommendations to the user is determined by setting a third evaluation value threshold. Optionally, in the financial service recommendation method provided in the embodiment of the present application, after calculating the recommended evaluation value based on the behavior evaluation value and evaluation weight of each data in the relevant information, the method also includes: when the recommended evaluation value is less than the first evaluation value threshold, judging whether the recommended evaluation value is less than or equal to the third evaluation value threshold, wherein the third evaluation value threshold is less than the first evaluation value threshold; when the recommended evaluation value is less than or equal to the third evaluation value threshold, adding a mark to the user, wherein the mark is used to indicate that the financial service is not recommended; when the recommended evaluation value is greater than the third evaluation value threshold, determining the recommendation period of the financial service; updating the relevant information of the user at preset time intervals within the recommendation period, and calculating an updated recommended evaluation value based on the updated relevant information until the updated recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0053] In some examples, when the calculated recommendation evaluation value is lower than the first evaluation value threshold, but not less than or equal to the lower third evaluation value threshold, a mark is added to the user, indicating that it is not appropriate to recommend financial services to the user at the current time. This mark can prevent unnecessary recommendations to users with potential low response rates and reduce resource waste. If the recommendation evaluation value is higher than the third evaluation value threshold but does not reach the first evaluation value threshold, the user is included in a recommendation cycle for observation. Although the current user's recommendation evaluation value does not meet the higher recommendation standards, it still has certain potential needs and deserves continued attention and periodic evaluation.

[0054] During the recommendation cycle, the user's relevant information is updated regularly (every preset time). This information may include the user's latest transaction data, behavior data, etc. Based on the updated relevant information, the recommendation evaluation value is recalculated. After each evaluation within the cycle, it is again checked whether the updated recommendation evaluation value reaches or exceeds the first evaluation value threshold. Once reached, the financial service is recommended to the user.

[0055] This embodiment avoids wasting resources on low-demand users by marking users who are not recommended, while ensuring that potential demand users receive continuous attention during the recommendation cycle. Periodic information updates and evaluations ensure that financial service recommendations are consistent with the dynamic changes in user needs, provide services that better meet user needs, and improve user experience.

[0056] After obtaining the user's behavior evaluation value, a recommendation method for financial services can be determined based on the behavior evaluation value. Optionally, in the financial service recommendation method provided in the embodiment of the present application, recommending financial services to the user's client includes: for the behavior evaluation value of each type of data in the relevant information, judging whether the behavior evaluation value is greater than or equal to a second evaluation value threshold, wherein the second evaluation value threshold is less than the first evaluation value threshold; when the behavior evaluation value is greater than or equal to the second evaluation value threshold, determining the data as high-frequency behavior data; obtaining multiple recommendation methods for financial services, and calculating the evaluation value of the degree of association between each recommendation method and the high-frequency behavior data; determining the recommendation method corresponding to the maximum correlation degree evaluation value as the target recommendation method, and recommending the financial services to the user's client according to the target recommendation method.

[0057] In some examples, first, the behavior evaluation value of each data is judged. If the behavior evaluation value of a certain data is greater than or equal to the second evaluation value threshold (lower than the first evaluation value threshold, but indicating a behavior of higher frequency or importance), it is determined as high-frequency behavior data. High-frequency behavior data is a significant feature of the user in a certain behavior dimension. Recommendation methods may include but are not limited to email, text messages, phone calls, social media, in-application notifications, etc. Each recommendation method has its own unique advantages and applicable scenarios.

[0058] Next, calculate the association evaluation value between each recommendation method and the high-frequency behavior data. This can be achieved by analyzing historical data to identify successful association cases between specific high-frequency behavior data and recommendation methods, or by formulating evaluation rules based on expert experience. Select the recommendation method with the maximum association evaluation value with the high-frequency behavior data as the target recommendation method. Recommend financial services to the user's client according to the target recommendation method to improve the response rate and success rate of the recommendation.

[0059] For example, if a customer likes to use his mobile phone frequently and his mobile phone usage time score is unusually high in the behavior evaluation value, you can communicate with the customer by sending a mobile phone-related contact method (such as text messages, social software, etc.). If the customer is a person who is greatly influenced by the opinions of social groups, such as participating in many forum comments in the financial institution's application, you can recommend it to the forum user group and use it to influence the target customer.

[0060] This embodiment selects the most matching recommendation method based on the user's high-frequency behavior data, improves the response rate and conversion rate of the recommendation, and improves the recommendation effect. It reaches users through personalized recommendation methods, reduces interference with users, and improves user experience and satisfaction.

[0061] Taking into account the user's real-time relevant information, the behavior analysis results can be adjusted in a timely manner. Optionally, in the financial service recommendation method provided in the embodiment of the present application, the method also includes: receiving a change request for relevant information, updating the relevant information based on the change request, and obtaining updated relevant information; and executing the step of inputting the relevant information into the behavior analysis model based on the updated relevant information.

[0062] In some examples, financial institutions can receive change requests for user-related information in real time or periodically. These requests can come from active updates from users, such as changing contact information, updating income information, or adding new financial goals, or from automatic data synchronization, such as the latest data obtained from social platforms or trading systems. After receiving the change request, the user's relevant information is updated. The latest updated relevant information is input into the behavior analysis model to reflect the user's current behavioral characteristics and demand changes.

[0063] This embodiment ensures that the behavior analysis model makes predictions based on the latest user data by responding to changes in user information in a timely manner, thereby improving the timeliness and accuracy of the model.

[0064] The recommended evaluation value can be calculated by weighted summation. Optionally, in the financial service recommendation method provided in the embodiment of the present application, the recommended evaluation value is calculated based on the behavior evaluation value and evaluation weight of each data in the relevant information, including: determining all data in the relevant information; performing weighted summation of all data based on the behavior evaluation value and evaluation weight of each data to obtain the recommended evaluation value.

[0065] In some examples, all data in the user-related information is determined, including but not limited to the user's basic information, transaction records, behavioral habits, operational interactions on the application, etc. The evaluation weight of each type of data is determined according to the previously defined evaluation weight mapping relationship table. These weights reflect the relative importance of different data in the recommendation evaluation. The behavior evaluation value of each type of data is multiplied by its corresponding evaluation weight, and then all weighted evaluation values ​​are summed to obtain the final recommendation evaluation value.

[0066] In this embodiment, by calculating the recommendation evaluation value using a weighted summation method for the data in all relevant information, financial institutions can more comprehensively and accurately judge users' potential needs for financial services and improve the accuracy and success rate of recommendations.

[0067] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0068] Example 2

[0069] The embodiment of the present application also provides a financial service recommendation device. It should be noted that the financial service recommendation device of the embodiment of the present application can be used to execute the financial service recommendation method provided in the embodiment of the present application. The financial service recommendation device provided in the embodiment of the present application is introduced below.

[0070] According to an embodiment of the present application, a device for implementing the above-mentioned financial service recommendation method is also provided. Figure 3 is a schematic diagram of a financial service recommendation device provided according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0071] The acquisition unit 301 is used to acquire relevant information of the user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about operations performed by the user in an application of a financial institution;

[0072] An input unit 302 is used to input relevant information into a behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple sets of training samples, each set of training samples including historical relevant information and historical behavior evaluation values;

[0073] A first determining unit 303 is used to determine a target type of the financial service to be recommended, and determine an evaluation weight of each type of data in the relevant information based on the target type;

[0074] The recommendation unit 304 is used to calculate a recommendation evaluation value based on the behavior evaluation value and evaluation weight of each data in the relevant information, and recommend the financial service to the user's client when the recommendation evaluation value is greater than or equal to a first evaluation value threshold.

[0075] The financial service recommendation device provided in the embodiment of the present application obtains relevant information of the user within a preset period through an acquisition unit 301, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about the user's operation in the application of the financial institution; the input unit 302 inputs the relevant information into the behavior analysis model to obtain the behavior evaluation value of each data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; the first determination unit 303 determines the target type of the financial service to be recommended, and determines the evaluation weight of each data in the relevant information based on the target type; The recommendation unit 304 calculates a recommendation evaluation value based on the behavior evaluation value and evaluation weight of each data in the relevant information. When the recommendation evaluation value is greater than or equal to a first evaluation value threshold, the financial service is recommended to the user's client. The user's relevant information is evaluated through a behavior analysis model to obtain a behavior evaluation value, and then a recommendation evaluation value of the financial service to be recommended is calculated based on the behavior evaluation value. If the recommendation evaluation value is greater than or equal to the first evaluation value threshold, the financial service is recommended to the user, thereby achieving a multi-dimensional evaluation of the user's behavior and improving the accuracy of the user's behavior analysis, thereby achieving the technical effect of improving the accuracy of the financial service recommendation, and then solving the technical problem of low accuracy of the financial service recommendation.

[0076] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the device also includes: an extraction unit, used to obtain the financial service recommendation records of the financial institution, and extract the historical relevant information and historically recommended financial services of each user from the financial service recommendation records; a second determination unit, used to determine the recommendation results of the historically recommended financial services, and determine the historical behavior evaluation value of each data in the historical relevant information based on the recommendation results; a third determination unit, used to determine the historical relevant information and historical behavior evaluation value of each user as a group of training samples to obtain multiple groups of training samples; a training unit, used to train the machine learning model based on the multiple groups of training samples to obtain a behavior analysis model.

[0077] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the first determination unit 303 includes: a first determination module, used to determine an evaluation weight mapping relationship table, wherein the evaluation weight mapping relationship table includes multiple groups of mapping relationships, each group of mapping relationships includes a type of financial service and a weight setting method, and the weight setting method sets the evaluation weight of each type of data in the relevant information; an extraction module, used to extract a target weight setting method that has a mapping relationship with the target type from the evaluation weight mapping relationship table, and determine the evaluation weight of each type of data based on the target weight setting method.

[0078] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the device also includes: a judgment unit, used to judge whether the recommended evaluation value is less than or equal to a third evaluation value threshold when the recommended evaluation value is less than the first evaluation value threshold, wherein the third evaluation value threshold is less than the first evaluation value threshold; a marking unit, used to add a mark to the user when the recommended evaluation value is less than or equal to the third evaluation value threshold, wherein the mark is used to characterize that the financial service is not recommended; a fourth determination unit, used to determine the recommendation period of the financial service when the recommended evaluation value is greater than the third evaluation value threshold; an updating unit, used to update the relevant information of the user at preset time intervals within the recommendation period, and calculate an updated recommended evaluation value based on the updated relevant information until the updated recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0079] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the recommendation unit 304 includes: a judgment module, used to judge whether the behavior evaluation value of each type of data in the relevant information is greater than or equal to a second evaluation value threshold, wherein the second evaluation value threshold is less than the first evaluation value threshold; a second determination module, used to determine the data as high-frequency behavior data when the behavior evaluation value is greater than or equal to the second evaluation value threshold; a calculation module, used to obtain multiple recommendation methods for financial services, and calculate the evaluation value of the degree of association between each recommendation method and the high-frequency behavior data; a third determination module, used to determine the recommendation method corresponding to the maximum correlation degree evaluation value as the target recommendation method, and recommend the financial services to the user's client according to the target recommendation method.

[0080] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the device also includes: a receiving unit, used to receive a change request for relevant information, update the relevant information based on the change request, and obtain updated relevant information; and an execution unit, used to execute the step of inputting the relevant information into the behavior analysis model based on the updated relevant information.

[0081] Optionally, in the financial service recommendation device provided in an embodiment of the present application, the recommendation unit 304 includes: a fourth determination module, used to determine all data in the relevant information; and a summation module, used to perform weighted summation of all data based on the behavior evaluation value and evaluation weight of each data to obtain a recommended evaluation value.

[0082] It should be noted that the acquisition unit 301, input unit 302, first determination unit 303 and recommendation unit 304 correspond to steps S201 to S204 in Example 1, and the four units and corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules or units can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0083] Example 3

[0084] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0085] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0086] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain relevant information of the user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, and the behavior information is information about the user's operations in the application of the financial institution; input the relevant information into the behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple groups of training samples, and each group of training samples includes historical relevant information and historical behavior evaluation values; determine the target type of the financial service to be recommended, and determine the evaluation weight of each type of data in the relevant information based on the target type; calculate the recommended evaluation value based on the behavior evaluation value and evaluation weight of each type of data in the relevant information, and recommend the financial service to the user's client when the recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0087] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the financial service recommendation records of the financial institution, extract the historical relevant information and historically recommended financial services of each user from the financial service recommendation records; determine the recommendation results of the historically recommended financial services, and determine the historical behavior evaluation value of each data in the historical relevant information based on the recommendation results; determine the historical relevant information and historical behavior evaluation value of each user as a set of training samples to obtain multiple sets of training samples; train the machine learning model based on the multiple sets of training samples to obtain a behavior analysis model.

[0088] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine an evaluation weight mapping relationship table, wherein the evaluation weight mapping relationship table includes multiple groups of mapping relationships, each group of mapping relationships includes a type of financial service and a weight setting method, and the weight setting method sets the evaluation weight of each type of data in the relevant information; extract the target weight setting method that has a mapping relationship with the target type from the evaluation weight mapping relationship table, and determine the evaluation weight of each type of data based on the target weight setting method.

[0089] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: when the recommended evaluation value is less than the first evaluation value threshold, determine whether the recommended evaluation value is less than or equal to the third evaluation value threshold, wherein the third evaluation value threshold is less than the first evaluation value threshold; when the recommended evaluation value is less than or equal to the third evaluation value threshold, add a mark to the user, wherein the mark is used to indicate that the financial service is not recommended; when the recommended evaluation value is greater than the third evaluation value threshold, determine the recommendation period of the financial service; update the relevant information of the user at preset time intervals within the recommendation period, and calculate the updated recommended evaluation value based on the updated relevant information until the updated recommended evaluation value is greater than or equal to the first evaluation value threshold.

[0090] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for the behavior evaluation value of each type of data in the relevant information, determine whether the behavior evaluation value is greater than or equal to a second evaluation value threshold, wherein the second evaluation value threshold is less than the first evaluation value threshold; when the behavior evaluation value is greater than or equal to the second evaluation value threshold, determine the data as high-frequency behavior data; obtain multiple recommendation methods for financial services, and calculate the evaluation value of the degree of association between each recommendation method and the high-frequency behavior data; determine the recommendation method corresponding to the maximum correlation degree evaluation value as the target recommendation method, and recommend the financial services to the user's client according to the target recommendation method.

[0091] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: receiving a change request for relevant information, updating the relevant information based on the change request, and obtaining updated relevant information; and executing the step of inputting the relevant information into the behavior analysis model based on the updated relevant information.

[0092] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine all data in the relevant information; perform weighted summation of all data based on the behavior evaluation value and evaluation weight of each data to obtain a recommended evaluation value.

[0093] According to the embodiment of the present application, there is provided a method for obtaining relevant information of a user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information and behavior information, wherein the behavior information is information of the user's operation in the application of a financial institution; inputting the relevant information into a behavior analysis model to obtain a behavior evaluation value of each data in the relevant information, wherein the behavior analysis model is trained by multiple sets of training samples, each set of training samples includes historical relevant information and historical behavior evaluation values; determining the target type of the financial service to be recommended, and determining the evaluation weight of each data in the relevant information based on the target type; calculating the recommended evaluation value based on the behavior evaluation value and the evaluation weight of each data in the relevant information, and recommending the financial service to the user's client when the recommended evaluation value is greater than or equal to a first evaluation value threshold. The relevant information of the user is evaluated by the behavior analysis model to obtain the behavior evaluation value, and then the recommended evaluation value of the financial service to be recommended is calculated based on the behavior evaluation value, and if the recommended evaluation value is greater than or equal to the first evaluation value threshold, the financial service is recommended to the user, thereby achieving the purpose of multi-dimensional evaluation of user behavior and improving the accuracy of user behavior analysis, thereby achieving the technical effect of improving the accuracy of financial service recommendations, and then solving the technical problem of low accuracy of financial service recommendations.

[0094] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), a PAD or other terminal device. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations shown.

[0095] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0096] Example 4

[0097] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the financial service recommendation method provided in the first embodiment.

[0098] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0099] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the financial service recommendation method.

[0100] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0101] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0106] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for recommending financial services, characterized in that: include: Acquire relevant information of the user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information, and behavior information, wherein the behavior information is information about operations performed by the user in an application of a financial institution; Inputting the relevant information into a behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple sets of training samples, each set of training samples including historical relevant information and historical behavior evaluation values; Determining a target type of the financial service to be recommended, and determining an evaluation weight of each type of data in the relevant information based on the target type; A recommendation evaluation value is calculated based on the behavior evaluation value and the evaluation weight of each type of data in the relevant information, and the financial service is recommended to the user's client when the recommendation evaluation value is greater than or equal to a first evaluation value threshold.

2. The method according to claim 1, characterized in that The behavior analysis model is trained in the following way: Obtaining the financial service recommendation record of the financial institution, and extracting the historical relevant information and historically recommended financial services of each user from the financial service recommendation record; Determine a recommendation result of the historically recommended financial service, and determine a historical behavior evaluation value of each type of data in the historically relevant information based on the recommendation result; Determine each user's historical related information and historical behavior evaluation value as a set of training samples, and obtain multiple sets of training samples; The machine learning model is trained based on the multiple groups of training samples to obtain the behavior analysis model.

3. The method according to claim 1, characterized in that Determining the evaluation weight of each type of data in the relevant information based on the target type includes: Determine an evaluation weight mapping relationship table, wherein the evaluation weight mapping relationship table includes multiple groups of mapping relationships, each group of mapping relationships includes a type of financial service and a weight setting method, and the weight setting method sets the evaluation weight of each type of data in the relevant information; A target weight setting method that has a mapping relationship with the target type is extracted from the evaluation weight mapping relationship table, and an evaluation weight of each type of data is determined based on the target weight setting method.

4. The method according to claim 1, characterized in that After calculating the recommended evaluation value based on the behavior evaluation value and the evaluation weight of each type of data in the relevant information, the method further includes: In the case where the recommended evaluation value is less than the first evaluation value threshold, determining whether the recommended evaluation value is less than or equal to a third evaluation value threshold, wherein the third evaluation value threshold is less than the first evaluation value threshold; In the case where the recommendation evaluation value is less than or equal to the third evaluation value threshold, adding a mark to the user, wherein the mark is used to indicate that the financial service is not recommended; In a case where the recommendation evaluation value is greater than the third evaluation value threshold, determining a recommendation period for the financial service; The relevant information of the user is updated at preset time intervals within the recommendation period, and an updated recommendation evaluation value is calculated based on the updated relevant information until the updated recommendation evaluation value is greater than or equal to the first evaluation value threshold.

5. The method according to claim 1, characterized in that The client terminal recommending the financial service to the user includes: For each behavior evaluation value of the data in the relevant information, determining whether the behavior evaluation value is greater than or equal to a second evaluation value threshold, wherein the second evaluation value threshold is less than the first evaluation value threshold; In a case where the behavior evaluation value is greater than or equal to the second evaluation value threshold, determining the data as high-frequency behavior data; Obtain multiple recommendation methods for the financial services, and calculate an evaluation value of the degree of association between each recommendation method and the high-frequency behavior data; The recommendation method corresponding to the maximum association degree evaluation value is determined as a target recommendation method, and the financial service is recommended to the user's client according to the target recommendation method.

6. The method according to claim 1, characterized in that The method further comprises: receiving a request for changing the relevant information, updating the relevant information based on the change request, and obtaining updated relevant information; The step of inputting the relevant information into the behavior analysis model is performed based on the updated relevant information.

7. The method according to claim 1, characterized in that Calculating the recommended evaluation value based on the behavior evaluation value and the evaluation weight of each type of data in the relevant information includes: Determine all data in the relevant information; The recommended evaluation value is obtained by performing a weighted summation on all the data based on the behavior evaluation value and the evaluation weight of each data.

8. A financial service recommendation device, characterized in that: include: An acquisition unit, configured to acquire relevant information of a user within a preset period, wherein the relevant information includes at least one of the following: identity information, transaction information, and behavior information, wherein the behavior information is information about operations performed by the user in an application of a financial institution; An input unit, used to input the relevant information into a behavior analysis model to obtain a behavior evaluation value for each type of data in the relevant information, wherein the behavior analysis model is trained by multiple sets of training samples, each set of training samples including historical relevant information and historical behavior evaluation values; A first determination unit, configured to determine a target type of the financial service to be recommended, and determine an evaluation weight of each type of data in the relevant information based on the target type; A recommendation unit is used to calculate a recommendation evaluation value based on the behavior evaluation value and the evaluation weight of each data in the relevant information, and recommend the financial service to the user's client when the recommendation evaluation value is greater than or equal to a first evaluation value threshold.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the financial service recommendation method described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the financial service recommendation method described in any one of claims 1 to 7 are implemented.

Images