Information recommendation method, device, computer equipment and storage medium

Abstract

The present application relates to the field of artificial intelligence technology, and provides an information recommendation method, device, computer equipment and storage medium, the method comprising: obtaining the answer data of a questionnaire submitted by a user; inputting the answer data into a risk assessment model to obtain a target risk assessment level; generating major asset allocation recommendation information based on the target risk assessment level, the answer data and the major asset market forecast data; determining the first recommended investment product corresponding to the target risk assessment level; generating the user's investment capacity value; screening the second recommended investment product from the first recommended investment product based on the investment capacity value; screening the target recommended investment product from the second recommended investment product based on the investment product data; and pushing investment recommendation information to the user. The present application can improve the efficiency and accuracy of product information recommendation. The present application can also be applied to the field of blockchain, and the above-mentioned investment recommendation information can be stored on the blockchain.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to an information recommendation method, apparatus, computer equipment and storage medium. Background Art

[0002] With the development of information technology, more and more users use the Internet to interact with information, such as purchasing investment products. With the explosive growth of Internet information, it is becoming increasingly difficult for users to find valuable information. For example, when users need to purchase investment products, they mainly rely on themselves to search from a large number of investment products, or the salesperson recommends investment products to the users. However, when users search for investment products, due to their limited understanding of investment products, they need to search multiple times to find investment products that meet their needs, resulting in poor user experience. When salespeople recommend investment products to users, since the salespeople do not understand the users, the accuracy of the recommendations is low, and they may not be able to recommend investment products that meet the personalized needs of users after multiple recommendations. In addition, it takes a lot of manpower and material resources, and the recommendation cost is high and the intelligence is low. Summary of the invention

[0003] The main purpose of this application is to provide an information recommendation method, device, computer equipment and storage medium, aiming to solve the technical problems of low recommendation accuracy and high recommendation cost in existing product information recommendation methods.

[0004] This application proposes an information recommendation method, which comprises the following steps:

[0005] Obtain the answer data of the preset questionnaire submitted by the user;

[0006] Inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0007] Generate asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and preset asset market forecast data;

[0008] Determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level;

[0009] Acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data;

[0010] Obtaining standard purchase amount values ​​of all the first recommended investment products, and selecting a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0011] Extracting product data features of the investment product data, calculating matching values ​​between the product data features and each of the second recommended investment products, and screening out target recommended investment products whose matching values ​​are greater than a preset matching threshold from all the second recommended investment products;

[0012] Push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0013] Optionally, the questionnaire includes assessment question data of multiple dimensions, each dimension includes at least one multiple-choice question, each multiple-choice question includes at least two options, and each option corresponds to a score; the step of inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user includes:

[0014] Inputting the answer data into the risk assessment model, and obtaining the score of each multiple-choice question according to the answer data through the risk assessment model;

[0015] Set corresponding dimension weights for each dimension respectively, and set corresponding option weights for multiple-choice questions under each dimension in the questionnaire;

[0016] Based on the option weights, the scores of each multiple-choice question under the same dimension in the questionnaire are weighted and summed to obtain the evaluation score of each dimension in the questionnaire;

[0017] Based on the dimension weights, the evaluation scores of each dimension in the questionnaire are weighted and summed to obtain the corresponding comprehensive risk evaluation score;

[0018] Obtain the mapping relationship between the risk assessment score and the risk assessment level from the preset mapping table;

[0019] Based on the mapping relationship, the target risk assessment level corresponding to the comprehensive risk assessment score is determined from the preset mapping table.

[0020] Optionally, the step of generating major asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and preset major asset market forecast data includes:

[0021] Call the preset prediction model;

[0022] Performing income forecasting and risk forecasting on each major asset class through the forecasting model to obtain corresponding forecasting results;

[0023] extracting the user's investment period information from the answer data;

[0024] Based on the prediction result, the target risk assessment level and the investment period information, the major asset allocation recommendation information corresponding to the user is determined.

[0025] Optionally, the step of determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level includes:

[0026] Obtaining a target risk type corresponding to the target risk assessment level;

[0027] Screening out a first investment product corresponding to the target risk type from preset investment products; wherein the number of the first investment products is multiple;

[0028] Obtaining evaluation data of each of the first investment products;

[0029] Calculating a product score for each of the first investment products based on the evaluation data;

[0030] Sort the product ratings in descending order to obtain corresponding ranking results;

[0031] Starting from the first ranked product rating in the ranking result, sequentially obtaining a specified number of specified product ratings;

[0032] Obtaining second investment products corresponding to the scores of the designated products;

[0033] The second investment product is used as the first recommended investment product.

[0034] Optionally, the step of generating the user's investment capacity value based on the account information and the investment product data includes:

[0035] Extracting account balance information and the number of investment products held from the account information based on a preset first regular expression; and,

[0036] Extracting product unit price information and product expiration time information from the investment product data based on a preset second regular expression;

[0037] Based on the account balance information, the number of investment products held, the product unit price information and the product expiration time information, a preset calculation formula is called to calculate the investment capacity value of the user.

[0038] Optionally, the step of pushing investment recommendation information to the user includes:

[0039] Obtaining historical investment product purchase information corresponding to the user;

[0040] Based on a preset user attribute library and the historical investment product purchase information, determining an information recommendation time period corresponding to the user;

[0041] The investment recommendation information is pushed to the user based on the product recommendation time period.

[0042] Optionally, the step of determining the information recommendation time period corresponding to the user based on a preset user attribute library and the historical investment product purchase information includes:

[0043] Calling the user attribute library to determine whether there is user information corresponding to the user in the user attribute library;

[0044] If yes, query the attribute data corresponding to the user information from the user attribute library; wherein the attribute data includes basic attribute data and work attribute data;

[0045] Performing time trajectory analysis on the attribute data to obtain a timetable corresponding to the user;

[0046] Obtaining the purchase time in the historical investment product purchase information;

[0047] The information recommendation time period is determined based on the schedule and the purchase time.

[0048] The present application also provides an information recommendation device, comprising:

[0049] The first acquisition module is used to obtain answer data of a preset questionnaire submitted by a user;

[0050] A first generating module, used for inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0051] A second generating module is used to generate major asset allocation suggestion information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data;

[0052] A determination module, configured to determine, based on the target risk assessment level, a first recommended investment product corresponding to the target risk assessment level;

[0053] A second acquisition module, configured to acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data;

[0054] A first screening module, configured to obtain standard purchase amount values ​​of all the first recommended investment products, and screen out a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0055] A second screening module is used to extract product data features of the investment product data, calculate the matching value between the product data features and each of the second recommended investment products, and screen out target recommended investment products whose matching value is greater than a preset matching threshold from all the second recommended investment products;

[0056] A push module is used to push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0057] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0058] The present application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0059] The information recommendation method, device, computer equipment and storage medium provided in this application have the following beneficial effects:

[0060] The information recommendation method, device, computer equipment and storage medium provided in the present application, after obtaining the answer data of the preset questionnaire submitted by the user, will first call the preset risk assessment model to obtain the corresponding target risk assessment level based on the answer data, and then generate the major asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data, and at the same time determine the first recommended investment product corresponding to the user based on the target risk assessment level, and then generate the corresponding investment capacity value according to the user's account information and investment product data, and screen out the second recommended investment product from the first recommended investment product based on the investment capacity value and the standard purchase amount value, and then screen out the final target recommended investment product from all the second recommended investment products based on the investment product data, and finally push the investment recommendation information containing the major asset allocation recommendation information and the target recommended investment product to the user, so as to realize the automatic, intelligent and rapid completion of the push processing of investment recommendation information to the user, so that there is no need to occupy a large amount of human resources, greatly reduce the manual workload, effectively reduce the cost of investment product information recommendation, improve the recommendation efficiency of investment product information, and also ensure the accuracy of the generated investment recommendation information. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flowchart of an information recommendation method according to an embodiment of the present application;

[0062] Figure 2 is a structural diagram of an information recommendation device according to an embodiment of the present application;

[0063] Figure 3 It is a structural diagram of a computer device according to an embodiment of the present application.

[0064] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0067] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0068] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0069] Reference Figure 1 , an information recommendation method according to an embodiment of the present application includes:

[0070] S10: Obtaining answer data of a preset questionnaire submitted by a user;

[0071] S20: Inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0072] S30: Based on the target risk assessment level, the answer data and the preset major asset market forecast data, generate major asset allocation recommendation information corresponding to the user;

[0073] S40: Determine a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level;

[0074] S50: Acquire the account information and investment product data of the user, and generate the investment capacity value of the user based on the account information and the investment product data;

[0075] S60: Obtaining standard purchase amount values ​​of all the first recommended investment products, and selecting a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0076] S70: extracting product data features of the investment product data, calculating matching values ​​between the product data features and each of the second recommended investment products, and screening out target recommended investment products whose matching values ​​are greater than a preset matching threshold from all the second recommended investment products;

[0077] S80: Pushing investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0078] As described in the above steps S10 to S80, the execution subject of the embodiment of the method is an information recommendation device. In practical applications, the above information recommendation device can be implemented by a virtual device, such as software code, or by a physical device with relevant execution code written or integrated, and can interact with the user through a keyboard, mouse, remote control, touchpad or voice control device. The information recommendation device in this embodiment can automatically, intelligently and quickly complete the push processing of investment recommendation information to the user, improve the recommendation efficiency of investment product information, and ensure the accuracy of investment product information recommendation. Specifically, first obtain the answer data of the preset questionnaire submitted by the user. Among them, the questionnaire is a questionnaire for obtaining relevant information of the user portrait, and the user portrait may include user basic information, assets, risk preference, investment experience, liquidity preference, that is, acceptable investment period, demographic attribute dimension, investment purpose and other multi-dimensional information. The answer data refers to the answer generated by the user after answering the questions in the questionnaire. After obtaining the answer data, the answer data is input into the preset risk assessment model to obtain the target risk assessment level corresponding to the user. The risk assessment model is a model for calculating the corresponding target risk assessment level based on the answer data. In addition, the specific implementation process of inputting the answer data into the preset risk assessment model to obtain the target risk assessment level corresponding to the user will be further described in the subsequent specific embodiments of this application, which will not be repeated here.

[0079] After obtaining the target risk assessment level, based on the target risk assessment level, the answer data and the preset major asset market forecast data, the major asset allocation recommendation information corresponding to the user is generated. Among them, the preset forecasting model can be called first to perform income forecasting and risk forecasting processing on each major asset class to obtain the corresponding forecasting results, and then based on the forecasting results, the target risk assessment level and the investment period information in the answer data, the major asset allocation recommendation information corresponding to the user is determined. Then, based on the target risk assessment level, the first recommended investment product corresponding to the target risk assessment level is determined. Among them, for the specific implementation process of determining the first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level, this application will further describe this in subsequent specific embodiments, which will not be repeated here. After that, the user's account information and investment product data are obtained, and the user's investment capacity value is generated based on the account information and the investment product data. Among them, the account balance information and the number of investment products held can be extracted from the account information, and the product unit price information and product expiration time information can be extracted from the investment product data, and then the preset calculation formula is called based on the obtained information to calculate the user's investment capacity value. The calculation formula will be further described in subsequent specific embodiments.

[0080] Subsequently, the standard purchase amount values ​​of all the first recommended investment products are obtained, and the second recommended investment products are screened out from all the first recommended investment products based on the investment capacity value and the standard purchase amount value. Among them, the second recommended investment product refers to the product whose standard purchase amount value is less than the investment capacity value among all the first recommended investment products. The standard purchase amount value can be obtained by querying the relevant product data of the recommended investment product. The investment capacity value can be understood as the purchasing power of the user. By preliminarily screening the obtained recommended investment products based on the investment capacity value, the accuracy of the obtained second recommended investment products is guaranteed, and only the second recommended investment products and the user's investment products need to be matched and calculated later, which reduces the processing amount of data matching, reduces power consumption, and improves the intelligence of data processing. After obtaining the second recommended investment product, the product data features of the investment product data are extracted, the matching degree values ​​of the product data features and each of the second recommended investment products are calculated, and the target recommended investment products whose matching degree values ​​are greater than the preset matching degree threshold are screened out from all the second recommended investment products. Among them, the product data features include but are not limited to product type, product unit price information, and product expiration time information. Specifically, the formula for calculating the matching degree value is: P is the matching value, x is the product data feature, y is the matching value, nIt is a numerical representation of the data corresponding to the product data feature of the nth product in the second recommended investment product. After the first recommended investment product is initially screened based on the user's purchasing power, that is, the investment ability value, the product data features of the user's investment product data will be analyzed in the future to perform a secondary screening of the second recommended investment product according to the product data features, so as to achieve targeted investment product recommendations for users, further improve the accuracy of investment product recommendations, and thus effectively solve the problem of low accuracy when recommending investment products to users. Finally, the investment recommendation information is pushed to the user. Among them, the investment recommendation information includes the major asset allocation recommendation information and the target recommended investment product. Specifically, the major asset allocation recommendation information and the target recommended investment product can be filled into a preset investment recommendation information template to generate the investment recommendation information. The investment recommendation information template can be pre-written and generated according to actual usage requirements and stored in the device.

[0081] Different from the existing method of manually recommending investment products, after obtaining the answer data of the preset questionnaire submitted by the user, this embodiment will first call the preset risk assessment model to obtain the corresponding target risk assessment level based on the answer data, and then generate the major asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data, and at the same time determine the first recommended investment product corresponding to the user based on the target risk assessment level, and then generate the corresponding investment capacity value according to the user's account information and investment product data, and screen out the second recommended investment product from the first recommended investment product based on the investment capacity value and the standard purchase amount value, and then screen out the final target recommended investment product from all the second recommended investment products based on the investment product data, and finally push the investment recommendation information containing the major asset allocation recommendation information and the target recommended investment product to the user, so as to realize the automatic, intelligent and rapid completion of the push processing of the investment recommendation information to the user, so that there is no need to occupy a large amount of human resources, greatly reduce the manual workload, effectively reduce the cost of recommending investment product information, improve the recommendation efficiency of investment product information, and also ensure the accuracy of the generated investment recommendation information.

[0082] Furthermore, in an embodiment of the present application, the questionnaire includes evaluation question data of multiple dimensions, each dimension includes at least one multiple-choice question, each multiple-choice question includes at least two options, and each option corresponds to a score; the above step S20 includes:

[0083] S200: inputting the answer data into the risk assessment model, and obtaining the score of each multiple-choice question according to the answer data through the risk assessment model;

[0084] S201: setting corresponding dimension weights for each dimension respectively, and setting corresponding option weights for multiple-choice questions under each dimension in the questionnaire;

[0085] S202: Based on the option weights, weighted sum is performed on the scores of each multiple-choice question under the same dimension in the questionnaire to obtain an evaluation score for each dimension in the questionnaire;

[0086] S203: Based on the dimension weights, weighted summing is performed on the evaluation scores of each dimension in the questionnaire to obtain a corresponding comprehensive risk evaluation score;

[0087] S204: Obtaining a mapping relationship between risk assessment scores and risk assessment levels from a preset mapping table;

[0088] S205: Based on the mapping relationship, determine the target risk assessment level corresponding to the comprehensive risk assessment score from the preset mapping table.

[0089] As described in the above steps S200 to S205, the step of inputting the answer data into the preset risk assessment model to obtain the target risk assessment level corresponding to the user may specifically include: first inputting the answer data into the risk assessment model, and obtaining the score of each multiple-choice question according to the answer data through the risk assessment model. Among them, the questionnaire may include multiple dimensional information such as user basic information, assets, risk preference, investment experience, liquidity preference (i.e., acceptable investment period), demographic attribute dimension, investment purpose, etc.; the indicators of the user basic information dimension may include gender, age, marital status, occupation and education. Each question in the questionnaire corresponds to at least two options, and each option has a corresponding score; the scoring basis of the asset dimension is the investment amount, for example, it is divided into 10 sections from 10,000 yuan to 1 million yuan, and each section corresponds to a corresponding score; the scoring basis of the risk preference dimension corresponds to a pre-set designated question, which can be set according to actual needs, for example, the designated question can be: "When all your investment assets depreciate to what extent, will you feel uneasy?", each designated question corresponds to multiple options, and each option has a corresponding score; the investment experience dimension can be divided into five types: "no investment experience", "investment in conservative financial products", "investment in securities under the guidance of others", "independent investment in securities" and "high-risk investment", and each investment type has a corresponding score; the liquidity preference dimension can be divided into multiple types according to the user's acceptable investment period, for example, it can include less than one year, one to two years, two to five years, more than five years, and on-demand type, and each type has a corresponding score. Then set the corresponding dimension weight for each dimension, and set the corresponding option weight for the multiple-choice questions under each dimension in the questionnaire. Wherein, a dimension weight is set for each dimension of information, and preferably the sum of all dimension weights is 1. An option weight is set for each multiple-choice question under each dimension of the questionnaire, and preferably the sum of the option weights of the multiple-choice questions under the same dimension is 1. Then, based on the option weight, the scores of each multiple-choice question under the same dimension in the questionnaire are weighted and summed to obtain the evaluation score of each dimension in the questionnaire. Wherein, the scores of each multiple-choice question under the same dimension in the questionnaire can be multiplied by the corresponding option weights and summed to obtain the evaluation score of each dimension of the questionnaire. Then, based on the dimension weight, the evaluation score of each dimension in the questionnaire is weighted and summed to obtain the corresponding comprehensive risk assessment score. Wherein, the evaluation score of each dimension of the questionnaire is multiplied by the corresponding dimension weights and summed to obtain the sum value corresponding to the information of each dimension of the questionnaire, which is the comprehensive risk assessment score of the user. Subsequently, the mapping relationship between the risk assessment score and the risk assessment level is obtained from the preset mapping table. Among them, the risk assessment levels include conservative, stable, balanced, growth and aggressive.The risk levels of products corresponding to the risk assessment levels include low risk level, medium-low risk level, medium risk level, medium-high risk level, and high risk level. In addition, the specific intervals of the risk assessment scores corresponding to each risk assessment level in the preset mapping table can be set according to actual needs. For example, the interval with a risk assessment score of less than 3 corresponds to a conservative type, the risk assessment score in the interval of 4-5 corresponds to a robust type, the risk assessment score in the interval of 5-7 corresponds to a balanced type, the risk assessment score in the interval of 7-8 corresponds to a growth type, and the risk assessment score greater than 8 corresponds to an aggressive type. Finally, based on the mapping relationship, the target risk assessment level corresponding to the comprehensive risk assessment score is determined from the preset mapping table. In this embodiment, after obtaining the answer data corresponding to the preset questionnaire submitted by the user, the risk assessment model can be used to quickly and accurately divide the users into corresponding risk assessment levels. The basis for division is relatively objective and the method is simple, and it is conducive to the subsequent intelligent and accurate determination of the major asset allocation recommendation information corresponding to the user and the target recommended investment products corresponding to the user based on the target risk assessment level, thereby accurately realizing personalized investment recommendations for users and improving users' usage experience.

[0090] Furthermore, in one embodiment of the present application, the above step S30 includes:

[0091] S300: calling a preset prediction model;

[0092] S301: Performing income prediction and risk prediction processing on each major asset class through the prediction model to obtain corresponding prediction results;

[0093] S302: extracting the user's investment period information from the answer data;

[0094] S303: Based on the prediction result, the target risk assessment level and the investment period information, determine the major asset allocation recommendation information corresponding to the user.

[0095] As described in the above steps S300 to S303, the step of generating the major asset allocation suggestion information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data may specifically include: first calling a preset forecast model. Wherein, the preset forecast model is a time series model, and the Markowitz model may be used specifically. Then, the forecast model is used to perform a return forecast and a risk forecast process on each major asset class to obtain a corresponding forecast result. Wherein, the market forecast for the major asset class may be a risk forecast and a return forecast for various major asset classes currently available in the market, such as cash, security, stock, currency, fixed income, equity, etc. Then, the investment period information of the user is extracted from the answer data. Finally, based on the forecast result, the target risk assessment level and the investment period information, the major asset allocation suggestion information corresponding to the user is determined. Wherein, the major asset allocation suggestion information is the proportion of each major asset class in the asset allocation scheme recommended for the user. Specifically, first of all, assets can be classified, for example, the assets that the current user may hold can be divided into five major categories: cash, security, stock, currency, fixed income and equity, as a basis for market forecasting and major asset allocation. Then, by analyzing more than 400 types of explanatory economic factors at the macro and micro levels, factors that are effective for the above six types of assets in units of years are obtained, and the predicted values ​​and correlation matrices of the factors are given on a monthly basis. Combined with the historical returns of various types of assets, such as returns within 1 year, the exposure to the factors is calculated to obtain the factor exposure and correlation matrix of each asset. After that, the Markowitz model can be used, with the factor exposure and correlation matrix of each asset obtained as the input of the model, combined with the user's target risk assessment level and the investment period information, to obtain the major asset allocation recommendation information for the user. For example, if the user's target risk assessment level is balanced (the corresponding investment product's risk level is medium risk level) and the investment period information is medium, then based on the recent market forecast data for major market categories, the investment research team members can determine the recent risk factors for each major market category, and combine the Markowitz model's predicted values ​​for future factors. After regressing the major market categories, they can obtain forecasts for the future market. Based on the forecast results, the target risk assessment level and the investment period information, corresponding major asset allocation recommendation information will be generated for the user, such as 50% cash, 10% protection, 10% stocks, 10% currency, 10% fixed income, and 10% equity.In this embodiment, the optimal major asset allocation recommendation information can be recommended to the user based on the user's target risk assessment level and investment period information as well as the market forecast results for the returns and risks of each major asset class according to the user's actual situation. Since the major asset allocation recommendation information is generated after comprehensive consideration of user portraits in multiple dimensions, the generated major asset allocation recommendation information has high accuracy, pertinence and reliability.

[0096] Furthermore, in an embodiment of the present application, the above step S40 includes:

[0097] S400: Obtaining a target risk type corresponding to the target risk assessment level;

[0098] S401: Screening out a first investment product corresponding to the target risk type from preset investment products; wherein the number of the first investment products is multiple;

[0099] S402: Obtaining evaluation data of each of the first investment products;

[0100] S403: Calculating a product score for each of the first investment products based on the evaluation data;

[0101] S404: Sort the product ratings in descending order of numerical values ​​to obtain corresponding sorting results;

[0102] S405: Starting from the first ranked product rating in the ranking result, a specified number of specified product ratings are obtained in sequence;

[0103] S406: Acquire second investment products corresponding to the scores of the designated products;

[0104] S407: Use the second investment product as the first recommended investment product.

[0105] As described in the above steps S400 to S407, the step of determining the first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level may specifically include: first obtaining the target risk type corresponding to the target risk assessment level. Among them, the risk assessment level may include conservative, stable, balanced, growth, and aggressive. The risk levels of products corresponding to each risk assessment level include low risk level, medium-low risk level, medium risk level, medium-high risk level, and high risk level. Then, the first investment product corresponding to the target risk type is screened out from the preset investment products. Among them, the number of the first investment products is multiple. In addition, the investment products may be all investment products available on the market. Then, the evaluation data of each of the first investment products is obtained. Among them, the evaluation data may at least include relative return score, maximum drawdown score, and management ability score. Specifically, the calculation method of the relative return score includes: querying the performance benchmark table, obtaining the performance benchmarks corresponding to the three preset time periods, and subtracting the corresponding performance benchmarks from the absolute returns corresponding to the three preset time periods to obtain the relative returns corresponding to the three preset time periods; then multiplying the relative returns corresponding to the three preset time periods by the corresponding preset weight coefficients to obtain the weighted relative returns corresponding to the three preset time periods, and accumulating the weighted relative returns corresponding to the three preset time periods to obtain the final relative return of the investment product. Among them, the performance benchmark of the investment is to define an appropriate benchmark combination for the investment. By comparing the investment return rate with the return rate of the performance benchmark, the performance of the investment product can be measured. The calculation method of the maximum drawdown score includes: querying the preset historical adjusted net value table, obtaining the adjusted net value corresponding to each of the three preset time periods, and dividing the adjusted net value in one of the preset time periods into two groups according to the order of dates, one group includes the first adjusted net value with a larger net value date in one of the preset time periods, and the other group includes the second adjusted net value with a smaller net value date in one of the preset time periods, and then calculating the maximum drawdown in one of the preset time periods according to max((second adjusted net value-first adjusted net value) / first adjusted net value), and calculating the maximum drawdown of the fund product in the other two preset time periods in the same way, and then after obtaining the maximum drawdown corresponding to each of the three preset time periods, multiplying the maximum drawdown corresponding to each of the three preset time periods by the corresponding preset weight coefficient to obtain the weighted maximum drawdown corresponding to each of the three preset time periods, and accumulating the weighted maximum drawdown corresponding to each of the three preset time periods to obtain the final maximum drawdown of the investment product. Among them, the maximum drawdown is the maximum value of the yield drawdown amplitude when the product net value reaches the lowest point when pushing back from any historical point in the selected period.The specific calculation method of the management ability score is as follows: query the investment manager table, obtain the current investment manager of any investment product, and obtain all investment products managed by the current investment manager and the appointment start date of each investment product, then obtain the actual appointment days of each investment product managed by the current investment manager, and obtain the adjusted unit net value on the latest net value date and the adjusted unit net value on the previous trading day before the appointment start date, and finally calculate the average daily rate of return of each investment product according to the formula (adjusted unit net value on the previous trading day of the appointment start date) ^ (365 / actual number of appointment days) -1, and accumulate the average daily rate of return of all investment products to obtain the total average daily rate of return, and then divide the total average daily rate of return by the total number of investments, and then calculate the management ability of the investment product corresponding to each of the three preset time periods according to the monthly difference between the latest adjusted unit net value date and the appointment start date, and then use the management ability corresponding to each of the three preset time periods, multiply by the corresponding preset weight coefficient, to obtain the weighted management ability corresponding to each of the three preset time periods, and accumulate the weighted management ability scores corresponding to each of the three preset time periods to obtain the final management ability score of the investment product. Among them, the management ability score refers to the management situation of the manager of the investment product. Then, the product score of each of the first investment products is calculated based on the evaluation data. The process of calculating the product score of each of the first investment products based on the evaluation data may include: obtaining weight values ​​corresponding to the relative return score, the maximum drawdown score, and the management ability score, respectively, and performing weighted sum processing on the relative return score, the maximum drawdown score, and the management ability score based on the obtained weight values, and the obtained sum value is the corresponding product score. In addition, there is no specific limitation on the value of the weight of the evaluation data, which can be set based on actual conditions. Subsequently, the product scores are sorted in descending order of values ​​to obtain corresponding sorting results. After obtaining the sorting results, starting from the product score ranked first in the sorting results, a specified number of designated product scores are obtained in sequence. There is no limitation on the value of the designated number, which can be set according to actual needs, for example, it can be set to 3. Finally, the second investment products corresponding to each of the designated product scores are obtained, and the second investment products are used as the first recommended investment products. In this embodiment, by first screening out the first investment product corresponding to the target risk type from the preset investment products, it is only necessary to calculate the product score of the first investment product in the subsequent process, which effectively reduces the amount of data processing. In addition, by using the evaluation data of each of the first investment products, the product score of each of the first investment products can be calculated quickly and accurately, and then the first recommended investment product can be accurately determined based on the obtained product score, which is conducive to subsequently screening out target recommended investment products from the first recommended investment products for recommendation to users, so as to achieve personalized investment recommendations for users and improve users' usage experience.

[0106] Furthermore, in an embodiment of the present application, the above step S50 includes:

[0107] S500: extracting account balance information and the number of investment products held from the account information based on a preset first regular expression; and,

[0108] S501: extracting product unit price information and product expiration time information from the investment product data based on a preset second regular expression;

[0109] S502: Based on the account balance information, the number of investment products held, the product unit price information and the product expiration time information, a preset calculation formula is called to calculate the investment capacity value of the user.

[0110] As described in the above steps S500 to S502, the step of generating the investment capacity value of the user based on the account information and the investment product data may specifically include: firstly extracting the account balance information and the number of investment products held from the account information based on a preset first regular expression. Wherein, the account information is the information of the account used by the user when generating transaction data, and the account information includes but is not limited to the account name, account balance, and the number of products held by the account. In addition, the account information authorized to be obtained by the user can be captured through the data embedding point pre-constructed in the interface where the user conducts transactions, and the user data can be captured through the data embedding point, which can improve the real-time performance of capturing the account information. And extracting the product unit price information and product expiration time information from the investment product data based on a preset second regular expression. Wherein, the investment product data of the user refers to the product name, product content description, product price, product expiration time and other data of each product in the investment product. In addition, the pre-stored investment product data of the user can be captured from a pre-constructed storage area through a computer statement with a data capture function, such as a java statement, a python statement, etc., and the storage area can be a database, a blockchain node, or a network cache. Specifically, since the account balance information, the number of investment products held, the unit price of the product and the product expiration device are often present in the account information and the investment product data in a fixed format, the above account information and the investment product data can be extracted using regular expressions. For example, the number of investment products held exists in the investment product data in the form of a fixed "the number of products held is xx". Therefore, the investment product data can be extracted and processed using regular expressions to obtain all data in the investment product data in the form of "the number of products held is xx", and then obtain the product expiration time information of each investment product corresponding to the user. The regular expression is a function compiled from multiple preset characters with a specific field extraction function, and the regular expression can be pre-written and generated according to actual usage requirements. Afterwards, based on the account balance information, the number of investment products held, the unit price information of the product and the product expiration time information, the preset calculation formula is called to calculate the investment capacity value of the user. Specifically, the calculation formula is: Wherein, S is the investment capacity value of the user at the expiration time of the kth investment product, and U is the account balance at the expiration time of the kth investment product. is the number of investment products held for the ith investment product in the account information at the expiration date of the tth investment product, D iis the product unit price of the i-th investment product in the account information at the expiration time of the t-th investment product, and α and β are preset weight coefficients. For example, the account information is that the balance information of the user account on January 1 is 1000, the account holds 5 investment futures products A, and holds 5 investment futures products B, the investment product data includes the investment futures products A and B purchased by the user, wherein the product unit price information of the investment futures product A is 200, the expiration time is March 1, the unit price of the futures product B is 500, the expiration time is May 1, the weight coefficient corresponding to the balance information is 1, and the weight coefficient corresponding to the product unit price information is 1.5; then, according to the account information and the investment product data, the calculation formula can be used to calculate that the investment capacity value of the user is 1*1000+1.5*5*200+1.5*5*500=6250. In this embodiment, by utilizing regular expressions, the required account balance information, investment product holding quantity, product unit price information and product expiration time information can be quickly extracted from the user's account information and the user's investment product data, and then the preset calculation formula can be called to quickly and accurately generate the user's investment capacity value, which is conducive to the subsequent targeted investment product recommendations to the user based on the obtained investment capacity value, so as to improve the intelligence and accuracy of the investment product recommendations.

[0111] Furthermore, in an embodiment of the present application, the above step S80 includes:

[0112] S800: Acquire historical investment product purchase information corresponding to the user;

[0113] S801: Determine an information recommendation time period corresponding to the user based on a preset user attribute library and the historical investment product purchase information;

[0114] S802: Pushing the investment recommendation information to the user based on the product recommendation time period.

[0115] As described in the above steps S800 to S802, the step of pushing investment recommendation information to the user may specifically include: first, obtaining the historical investment product purchase information corresponding to the user. Wherein, the historical investment product purchase information at least includes the purchase time of the historical investment product by the user. Then, based on the preset user attribute library and the historical investment product purchase information, determine the information recommendation time period corresponding to the user. Wherein, for the specific implementation process of determining the information recommendation time period corresponding to the user based on the preset user attribute library and the historical investment product purchase information, this application will be further described in the subsequent specific embodiments, which will not be repeated here. Finally, based on the product recommendation time period, push the investment recommendation information to the user. Specifically, the process of pushing the investment recommendation information to the user based on the product recommendation time period may include: obtaining the preset email login information; and obtaining the target email address corresponding to the user; logging in to the corresponding email server according to the email login information; judging whether the current time is within the product recommendation time period; if so, generating corresponding investment recommendation information based on the major asset allocation suggestion information and the target investment product; and sending the investment recommendation information to the target email address through the email server. In this embodiment, after obtaining the major asset allocation recommendation information and the target investment product, corresponding investment recommendation information will be intelligently generated based on the obtained major asset allocation recommendation information and the target investment product, and the investment recommendation information will be sent to the user's corresponding target email address, so that the user can timely understand the investment recommendation content that is suitable for him / her based on the investment recommendation information, and then execute the required investment behavior based on the investment recommendation content, thereby improving the user's usage experience.

[0116] Furthermore, in an embodiment of the present application, the above step S801 includes:

[0117] S8010: Calling the user attribute library to determine whether there is user information corresponding to the user in the user attribute library;

[0118] S8011: If yes, query the attribute data corresponding to the user information from the user attribute library; wherein the attribute data includes basic attribute data and work attribute data;

[0119] S8012: Perform time trajectory analysis on the attribute data to obtain a timetable corresponding to the user;

[0120] S8013: Obtain the purchase time in the historical investment product purchase information;

[0121] S8014: Based on the schedule and the purchase time, determine the information recommendation time period.

[0122] As described in the above steps S8010 to S8014, the step of determining the information recommendation time period corresponding to the user based on the preset user attribute library and the historical investment product purchase information may specifically include: first calling the user attribute library and judging whether there is user information corresponding to the user in the user attribute library. Wherein, the user attribute library stores the attribute data of each user, and the attribute data is associated with the user information of each user, such as the user identification code or the user name. The attribute data is data related to the basic attribute data and work attribute data of the user. The basic attribute data includes information related to the basic characteristics of the user, such as the user's gender, age, marital status, family situation, etc. The work attribute data includes information on the social nature of the user, such as occupation, income, company, call number list, etc. If yes, query the attribute data corresponding to the user information from the user attribute library. Wherein, the attribute data includes basic attribute data and work attribute data. Then, the attribute data is analyzed for time trajectory to obtain the timetable corresponding to the user. Wherein, the time trajectory analysis is the process of extracting the time dimension in the attribute data, performing time period labeling and analyzing the labels of each time period, and outputting the timetable of the user. The schedule is a time distribution form of the user's estimated day. Then, the purchase time in the historical investment product purchase information is obtained. Finally, based on the schedule and the purchase time, the information recommendation time period is determined. Specifically, the process of determining the information recommendation time period may include: filtering out the first idle time period from the schedule; judging whether there is a first purchase time outside the range of all the time periods included in the schedule among all the purchase times; if the first purchase time exists, filtering out the second purchase time with the smallest value from all the first purchase times, and filtering out the third purchase time with the largest value; generating a corresponding second idle time period based on the second purchase time and the third purchase time; performing a union process on the first idle time period and the second idle time period to obtain a corresponding third idle time period; and using the third idle time period as the information recommendation time period. Among them, the idle time period can be marked according to the schedule, such as removing the user's travel time, working time and sleeping time from the schedule, so as to analyze and obtain the first idle time period. For example, the timetable is that the working hours are 9:00 to 12:30 and 14:00 to 18:00, and the travel time is 8:00 to 8:59 and 18:01 to 19:00, so the time periods corresponding to 12:31 to 13:59 and 19:01 to 23:00 are marked as free time periods, and are determined as the first free time period. In addition, the second purchase time is used as the left endpoint of the second free time period, and the third purchase time is used as the right endpoint of the second free time period.In this embodiment, the first idle time period is screened out from the schedule, and the second idle time period is determined from all the purchase times, and then the first idle time period and the second idle time period are processed by taking the union of the first idle time period and the second idle time period to obtain the corresponding third idle time period and use it as the information recommendation time period. Since the generated information recommendation time period is generated after comprehensive consideration of the schedule and the user's purchase time, it can be ensured that the information recommendation time period is a time period suitable for recommending product information to the user, so that product information can be intelligently recommended to the user in the information recommendation time period later, which can improve the user experience and improve the intelligence of product information recommendation.

[0123] The information recommendation method in the embodiment of the present application can also be applied to the blockchain field, such as storing the target recommended investment products and other data on the blockchain. By using the blockchain to store and manage the target recommended investment products, the security and non-tamperability of the target recommended investment products can be effectively guaranteed.

[0124] The above-mentioned blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0125] The underlying blockchain platform can include processing modules such as user management, basic services, smart contracts, and operation monitoring. Among them, the user management module is responsible for the identity information management of all blockchain participants, including maintaining public and private key generation (account management), key management, and the maintenance of the correspondence between the user's real identity and the blockchain address (authority management), etc., and, under authorization, supervises and audits the transactions of certain real identities and provides risk control rule configuration (risk control audit); the basic service module is deployed on all blockchain node devices to verify the validity of business requests, and records valid requests to storage after consensus is reached. For a new business request, the basic service first adapts the interface for parsing and authentication (interface adaptation), and then encrypts the business information through the consensus algorithm (consensus management). The smart contract module is responsible for the registration and issuance of contracts, as well as contract triggering and contract execution. Developers can define the contract logic in a programming language and publish it to the blockchain (contract registration). According to the logic of the contract terms, the key or other events are called to trigger the execution and complete the contract logic. It also provides the function of contract upgrade and cancellation. The operation monitoring module is mainly responsible for the deployment, configuration modification, contract setting, cloud adaptation and real-time status visualization output of the product during the product release process, such as alarm, network monitoring, node equipment health monitoring, etc.

[0126] Reference Figure 2 In one embodiment of the present application, an information recommendation device is also provided, including:

[0127] The first acquisition module 1 is used to obtain answer data of a preset questionnaire submitted by a user;

[0128] A first generating module 2 is used to input the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0129] The second generating module 3 is used to generate the major asset allocation suggestion information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data;

[0130] Determining module 4, used to determine a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level;

[0131] A second acquisition module 5, configured to acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data;

[0132] A first screening module 6, configured to obtain standard purchase amount values ​​of all the first recommended investment products, and screen out second recommended investment products from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0133] A second screening module 7 is used to extract product data features of the investment product data, calculate the matching value between the product data features and each of the second recommended investment products, and screen out target recommended investment products whose matching value is greater than a preset matching threshold from all the second recommended investment products;

[0134] The push module 8 is used to push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0135] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0136] Furthermore, in an embodiment of the present application, the questionnaire includes evaluation question data of multiple dimensions, each dimension includes at least one multiple-choice question, each multiple-choice question includes at least two options, and each option corresponds to a score; the first generation module 2 includes:

[0137] An input unit, used to input the answer data into the risk assessment model, and obtain the score of each multiple-choice question according to the answer data through the risk assessment model;

[0138] A setting unit, used to set a corresponding dimension weight for each dimension, and set a corresponding option weight for each multiple-choice question under each dimension in the questionnaire;

[0139] A first calculation unit is used to perform weighted summation on the scores of each multiple-choice question under the same dimension in the questionnaire based on the option weights to obtain an evaluation score for each dimension in the questionnaire;

[0140] A second calculation unit is used to perform weighted summation of the evaluation scores of each dimension in the questionnaire based on the dimension weights to obtain a corresponding comprehensive risk evaluation score;

[0141] A first acquisition unit is used to acquire a mapping relationship between a risk assessment score and a risk assessment level from a preset mapping table;

[0142] The first determining unit is used to determine the target risk assessment level corresponding to the comprehensive risk assessment score from the preset mapping table based on the mapping relationship.

[0143] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0144] Furthermore, in one embodiment of the present application, the second generation module 3 includes:

[0145] A calling unit, used for calling a preset prediction model;

[0146] A processing unit, used to perform income forecasting and risk forecasting on each major asset class through the forecasting model to obtain corresponding forecasting results;

[0147] A first extraction unit, configured to extract the user's investment period information from the answer data;

[0148] The second determination unit is used to determine the major asset allocation recommendation information corresponding to the user based on the prediction result, the target risk assessment level and the investment period information.

[0149] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0150] Furthermore, in an embodiment of the present application, the determination module 4 includes:

[0151] A second acquisition unit is used to acquire a target risk type corresponding to the target risk assessment level;

[0152] A screening unit, configured to screen out a first investment product corresponding to the target risk type from preset investment products; wherein the number of the first investment products is multiple;

[0153] A third acquisition unit, used to acquire evaluation data of each of the first investment products;

[0154] A third calculation unit, configured to calculate a product score of each of the first investment products based on the evaluation data;

[0155] A sorting unit, used to sort the product ratings in descending order of numerical values ​​to obtain corresponding sorting results;

[0156] A fourth acquisition unit, configured to sequentially acquire a specified number of specified product scores starting from the first ranked product score in the ranking result;

[0157] A fifth acquisition unit, used to acquire second investment products corresponding to the scores of the designated products;

[0158] The third determining unit is configured to use the second investment product as the first recommended investment product.

[0159] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0160] Furthermore, in an embodiment of the present application, the second acquisition module 5 includes:

[0161] A second extraction unit is used to extract the account balance information and the number of investment products held from the account information based on a preset first regular expression; and

[0162] A third extraction unit, configured to extract product unit price information and product expiration time information from the investment product data based on a preset second regular expression;

[0163] The fourth calculation unit is used to calculate the investment capacity value of the user by calling a preset calculation formula based on the account balance information, the number of investment products held, the product unit price information and the product expiration time information.

[0164] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0165] Furthermore, in one embodiment of the present application, the push module 8 includes:

[0166] A sixth acquisition unit, configured to acquire historical investment product purchase information corresponding to the user;

[0167] A fourth determining unit, configured to determine an information recommendation time period corresponding to the user based on a preset user attribute library and the historical investment product purchase information;

[0168] A push unit is used to push the investment recommendation information to the user based on the product recommendation time period.

[0169] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0170] Furthermore, in an embodiment of the present application, the fourth determining unit includes:

[0171] A calling subunit, used for calling the user attribute library to determine whether there is user information corresponding to the user in the user attribute library;

[0172] A query subunit, for querying attribute data corresponding to the user information from the user attribute library, wherein the attribute data includes basic attribute data and work attribute data;

[0173] An analysis subunit, configured to perform time trajectory analysis on the attribute data to obtain a timetable corresponding to the user;

[0174] An acquisition subunit, used to acquire the purchase time in the historical investment product purchase information;

[0175] The determination subunit is used to determine the information recommendation time period based on the timetable and the purchase time.

[0176] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and will not be described in detail here.

[0177] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface, a display screen, an input device and a database connected through a system bus. Among them, the processor designed for the computer device is used to provide computing and control capabilities. The memory of the computer device includes a storage medium and an internal memory. The storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the storage medium. The database of the computer device is used to store answer data, target risk assessment level, major asset allocation recommendation information, investment ability value, matching value and target recommended investment products. The network interface of the computer device is used to communicate with an external terminal through a network connection. The display screen of the computer device is an indispensable graphic output device in the computer, which is used to convert digital signals into optical signals so that text and graphics are displayed on the screen of the display screen. The input device of the computer device is the main device for information exchange between the computer and the user or other devices, and is used to transmit data, instructions and certain sign information to the computer. When the computer program is executed by the processor, an information recommendation method is implemented.

[0178] The processor executes the following steps of the information recommendation method:

[0179] Obtain the answer data of the preset questionnaire submitted by the user;

[0180] Inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0181] Generate asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and preset asset market forecast data;

[0182] Determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level;

[0183] Acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data;

[0184] Obtaining standard purchase amount values ​​of all the first recommended investment products, and selecting a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0185] Extracting product data features of the investment product data, calculating matching values ​​between the product data features and each of the second recommended investment products, and screening out target recommended investment products whose matching values ​​are greater than a preset matching threshold from all the second recommended investment products;

[0186] Push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0187] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application scheme, and does not constitute a limitation on the devices and computer equipment to which the present application scheme is applied.

[0188] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, an information recommendation method is implemented, specifically:

[0189] Obtain the answer data of the preset questionnaire submitted by the user;

[0190] Inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user;

[0191] Generate asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and preset asset market forecast data;

[0192] Determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level;

[0193] Acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data;

[0194] Obtaining standard purchase amount values ​​of all the first recommended investment products, and selecting a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value;

[0195] Extracting product data features of the investment product data, calculating matching values ​​between the product data features and each of the second recommended investment products, and screening out target recommended investment products whose matching values ​​are greater than a preset matching threshold from all the second recommended investment products;

[0196] Push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

[0197] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0198] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0199] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An information recommendation method, characterized in that: include: Obtain the answer data of the preset questionnaire submitted by the user; Inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user; Generate asset allocation recommendation information corresponding to the user based on the target risk assessment level, the answer data and preset asset market forecast data; Determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level; Acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data; Obtaining standard purchase amount values ​​of all the first recommended investment products, and selecting a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value; Extracting product data features of the investment product data, calculating matching values ​​between the product data features and each of the second recommended investment products, and screening out target recommended investment products whose matching values ​​are greater than a preset matching threshold from all the second recommended investment products; Pushing investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product; The questionnaire includes assessment question data of multiple dimensions, each dimension includes at least one multiple-choice question, each multiple-choice question includes at least two options, and each option corresponds to a score; the step of inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user includes: Inputting the answer data into the risk assessment model, and obtaining the score of each multiple-choice question according to the answer data through the risk assessment model; Set corresponding dimension weights for each dimension respectively, and set corresponding option weights for multiple-choice questions under each dimension in the questionnaire; Based on the option weights, the scores of each multiple-choice question under the same dimension in the questionnaire are weighted and summed to obtain the evaluation score of each dimension in the questionnaire; Based on the dimension weights, the evaluation scores of each dimension in the questionnaire are weighted and summed to obtain the corresponding comprehensive risk evaluation score; Obtain the mapping relationship between the risk assessment score and the risk assessment level from the preset mapping table; Based on the mapping relationship, determining the target risk assessment level corresponding to the comprehensive risk assessment score from the preset mapping table; The step of generating the user's investment capability value based on the account information and the investment product data comprises: Extracting account balance information and the number of investment products held from the account information based on a preset first regular expression; and, Extracting product unit price information and product expiration time information from the investment product data based on a preset second regular expression; Based on the account balance information, the number of investment products held, the product unit price information and the product expiration time information, a preset calculation formula is called to calculate the investment capacity value of the user.

2. The information recommendation method according to claim 1, characterized in that: The step of generating the major asset allocation suggestion information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data comprises: Call the preset prediction model; Performing income forecasting and risk forecasting on each major asset class through the forecasting model to obtain corresponding forecasting results; extracting the user's investment period information from the answer data; Based on the prediction result, the target risk assessment level and the investment period information, the major asset allocation recommendation information corresponding to the user is determined.

3. The information recommendation method according to claim 1, characterized in that: The step of determining a first recommended investment product corresponding to the target risk assessment level based on the target risk assessment level comprises: Obtaining a target risk type corresponding to the target risk assessment level; Screening out a first investment product corresponding to the target risk type from preset investment products; wherein the number of the first investment products is multiple; Obtaining evaluation data of each of the first investment products; Calculating a product score for each of the first investment products based on the evaluation data; Sorting the product ratings in descending order of value to obtain corresponding sorting results; Starting from the first ranked product rating in the ranking result, sequentially obtaining a specified number of specified product ratings; Obtaining second investment products corresponding to the scores of the designated products; The second investment product is used as the first recommended investment product.

4. The information recommendation method according to claim 1, characterized in that: The step of pushing investment recommendation information to the user includes: Obtaining historical investment product purchase information corresponding to the user; Based on a preset user attribute library and the historical investment product purchase information, determining an information recommendation time period corresponding to the user; The investment recommendation information is pushed to the user based on the product recommendation time period.

5. The information recommendation method according to claim 4, characterized in that: The step of determining the information recommendation time period corresponding to the user based on the preset user attribute library and the historical investment product purchase information includes: Calling the user attribute library to determine whether there is user information corresponding to the user in the user attribute library; If yes, query the attribute data corresponding to the user information from the user attribute library; wherein the attribute data includes basic attribute data and work attribute data; Performing time trajectory analysis on the attribute data to obtain a timetable corresponding to the user; Obtaining the purchase time in the historical investment product purchase information; The information recommendation time period is determined based on the schedule and the purchase time.

6. An information recommendation device, used to implement the method according to any one of claims 1 to 5, characterized in that: include: The first acquisition module is used to obtain answer data of a preset questionnaire submitted by a user; A first generating module, used for inputting the answer data into a preset risk assessment model to obtain a target risk assessment level corresponding to the user; A second generating module is used to generate major asset allocation suggestion information corresponding to the user based on the target risk assessment level, the answer data and the preset major asset market forecast data; A determination module, configured to determine, based on the target risk assessment level, a first recommended investment product corresponding to the target risk assessment level; A second acquisition module, configured to acquire the user's account information and investment product data, and generate the user's investment capacity value based on the account information and the investment product data; A first screening module, configured to obtain standard purchase amount values ​​of all the first recommended investment products, and screen out a second recommended investment product from all the first recommended investment products based on the investment capacity value and the standard purchase amount value; A second screening module is used to extract product data features of the investment product data, calculate the matching value between the product data features and each of the second recommended investment products, and screen out target recommended investment products whose matching value is greater than a preset matching threshold from all the second recommended investment products; A push module is used to push investment recommendation information to the user; wherein the investment recommendation information includes the major asset allocation suggestion information and the target recommended investment product.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images