Financial product recommendation method, device and equipment, medium and program product

Abstract

The invention discloses a financial product recommendation method, device and equipment, a medium and a program product. The method comprises the steps that basic information and historical investment information of investors are acquired, feature extraction is performed according to the basic information and the historical investment information, and multiple first investor features are generated; performing standardization processing on the first investor feature to generate a second investor feature; inputting the second investor features into a financial product recommendation model, obtaining a recommendation result of the financial product recommendation model, and determining a plurality of first financial products and recommendation values of the first financial products according to the recommendation result; and obtaining a recommendation coefficient of each financial product, determining at least one second financial product according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and pushing the second financial product to the investor. According to the technical scheme, the method is suitable for the technical field of financial science and technology, investor requirements can be accurately matched, and financial product market resource allocation can be optimized.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a financial product recommendation method, device, equipment, medium and program product. Background Art

[0002] In order to achieve the rational allocation of personal assets, financial platforms provide investors with a large number of financial products for investors to make diversified investment choices. However, for the massive financial products on the financial platform, if reasonable recommendations are not made to investors, investors may mistakenly choose products that do not match their risk tolerance due to lack of professional guidance. Moreover, unreasonable recommendations may cause investors to lose trust in the financial platform, damage the reputation of the platform, and thus affect its long-term development. Therefore, it is particularly important for financial platforms to build a scientific and effective financial product recommendation system, which needs to comprehensively consider multiple factors such as investors' age, investment goals, risk preferences, etc., and select the most suitable financial products for investors through accurate and professional financial analysis.

[0003] Existing financial product recommendations are generally based on content or collaborative filtering methods, which analyze users' past behaviors or the correlations between users to explore users' purchasing needs, or use recommendation algorithms based on association rules to explore the correlations between products, thereby achieving financial product recommendations.

[0004] However, existing financial product recommendation methods are highly dependent on user behavior and have low coverage for new users or new products. Summary of the invention

[0005] The present invention provides a financial product recommendation method, device, equipment, medium and program product, which can accurately match investor needs and optimize financial product market resource allocation.

[0006] According to one aspect of the present invention, a financial product recommendation method is provided, comprising:

[0007] Obtaining basic information and historical investment information of an investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features;

[0008] The first investor characteristics are standardized to generate the second investor characteristics;

[0009] Inputting the second investor characteristic into a financial product recommendation model, obtaining a recommendation result of the financial product recommendation model, and determining a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result;

[0010] The recommendation coefficient of each financial product is obtained, at least one second financial product is determined according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and the second financial product is pushed to the investor.

[0011] Optionally, feature extraction is performed based on the basic information and the historical investment information to generate multiple first investor features, including:

[0012] Extract features based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level, and extract features based on the historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product;

[0013] According to the investor's age and historical investment period, the expected investment period is adjusted to obtain the target investment period, and the risk tolerance is adjusted according to the investor's age to obtain the target risk tolerance;

[0014] According to the actual risk level of each historical financial product, the tolerable risk level is adjusted to obtain the target risk level;

[0015] The target investment period, target risk tolerance, target risk level and expected rate of return are determined as the first investor characteristics.

[0016] The advantage of this setting is that it can take into account the impact of age factors on users' risk tolerance and investment period, and make appropriate adjustments to investor characteristics based on user age, so that investor characteristics are more in line with investors' actual needs, thereby improving the accuracy of financial product recommendations.

[0017] Optionally, obtaining basic information and historical investment information of an investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features, further includes:

[0018] When an investor is investing for the first time, basic information of the investor is obtained, and feature extraction is performed based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level;

[0019] According to the investor's age, the expected investment period and risk tolerance are adjusted to obtain the target investment period and target risk tolerance, and the target investment period, target risk tolerance, expected rate of return and tolerable risk level are determined as the first investor characteristics.

[0020] The advantage of this setting is that for first-time investors, since there is no historical investment information to refer to, by obtaining key characteristics such as age, risk tolerance, expected investment period, expected rate of return and tolerable risk level, it is possible to initially build a framework for the investor's investment profile. By analyzing the basic information to determine these initial characteristics, the foundation is laid for further improvement of the investment analysis.

[0021] Optionally, determining a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result includes:

[0022] According to the score of each financial product by the financial product recommendation model, each financial product with a score higher than the first score value is determined as a first financial product;

[0023] According to the scores of the first financial products, a recommendation value of each first financial product is generated.

[0024] The advantage of this setting is that by setting the first score value as the screening criterion, financial institutions can use the scoring of the financial product recommendation model to quickly and effectively select products with higher scores from a large number of financial products. Through the pre-trained financial product recommendation model, the accuracy of financial product recommendations can be improved.

[0025] Optionally, obtaining a recommendation coefficient for each financial product, and determining at least one second financial product according to the recommendation coefficient for the financial product and the recommendation value of each first financial product, includes:

[0026] Obtaining the expected subscription amount and current subscription amount of each financial product in the financial platform, and determining the recommendation coefficient of each financial product based on the expected subscription amount and current subscription amount;

[0027] Determine the recommendation coefficient of each first financial product according to the recommendation coefficient of each financial product, and update the recommendation value of each first financial product according to the recommendation coefficient of each first product to obtain the recommendation value of the first financial product based on the financial platform;

[0028] The first financial product whose recommendation value based on the financial platform is greater than the second score value is determined as the second financial product.

[0029] The advantage of this setting is that further recommendation optimization can be carried out based on the financial product recommendation coefficient. While ensuring that investors' investment preferences and investment needs are met, the financial product promotion mechanism within the financial platform is optimized, maintaining the operation and development of the financial platform.

[0030] Optionally, the financial product recommendation method also includes:

[0031] Collect basic information and historical investment information of multiple sample investors, perform feature extraction and standardization, and generate investor characteristics of each sample investor; wherein the sample investors have different investment experiences;

[0032] Obtaining various sample financial products currently on sale, and performing feature extraction and standardization processing on each sample financial product to obtain product features of each sample financial product; wherein the product features include an estimated risk level, an estimated investment period, and an estimated rate of return;

[0033] According to the characteristics of each investor and each product, the financial product recommendation model is trained multiple rounds. After each round of training, the current financial product recommendation model is evaluated using model performance evaluation indicators until it is confirmed that the training end conditions are met. The trained financial product recommendation model is then put online on the financial platform.

[0034] The advantage of this setting is that multiple rounds of training of the financial product recommendation model are carried out according to the characteristics of each investor and each product, so that the model can continuously learn and adjust internal parameters, gradually optimize its ability to understand and grasp the complex relationship between investors and financial products, and improve the recommendation accuracy of the financial product recommendation model. The current financial product recommendation model is evaluated by using model performance evaluation indicators, which can objectively and accurately measure the performance of the model after each round of training, so as to obtain a financial product recommendation model with better expressiveness and further improve the quality of recommendations.

[0035] According to another aspect of the present invention, there is provided a financial product recommendation device, comprising:

[0036] A first investor feature acquisition module, used to acquire basic information and historical investment information of an investor, and perform feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features;

[0037] A second investor characteristics acquisition module, used to perform standardization processing on the first investor characteristics to generate second investor characteristics;

[0038] a first financial product determination module, configured to input the second investor characteristics into a financial product recommendation model, obtain a recommendation result of the financial product recommendation model, and determine a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result;

[0039] The second financial product determination module is used to determine at least one second financial product according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and push the second financial product to the investor.

[0040] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0041] at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial product recommendation method described in any embodiment of the present invention.

[0044] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial product recommendation method described in any embodiment of the present invention when executed.

[0045] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the financial product recommendation method according to any embodiment of the present invention is implemented.

[0046] The technical solution of the embodiment of the present invention obtains basic information and historical investment information of investors, and extracts features based on the basic information and historical investment information to generate multiple first investor features, standardizes the first investor features to generate second investor features, inputs the second investor features into the financial product recommendation model, obtains the recommendation results of the financial product recommendation model, and determines multiple first financial products and recommendation values ​​of each first financial product based on the recommendation results, obtains the recommendation coefficient of each financial product, determines at least one second financial product based on the recommendation coefficient of the financial product and the recommendation value of each first financial product, and pushes the second financial product to the investor. It can take into account that age factors will affect the user's risk tolerance and investment period, and appropriately adjust the investor characteristics according to the user's age, thereby improving the accuracy of financial product recommendations. At the same time, further recommendation optimization can be performed based on the financial product recommendation coefficient. On the basis of ensuring that the investment preferences and investment needs of investors are met, the financial product promotion mechanism within the financial platform is optimized, and the operation and development of the financial platform is maintained.

[0047] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 is a flow chart of a financial product recommendation method provided according to Embodiment 1 of the present invention;

[0050] Figure 2 is a flow chart of another financial product recommendation method provided according to Embodiment 2 of the present invention;

[0051] Figure 3 is a schematic diagram of the structure of a financial product recommendation device provided according to Embodiment 3 of the present invention;

[0052] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the financial product recommendation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] Embodiment 1

[0056] Figure 1This is a flowchart of a financial product recommendation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation where financial products are reasonably pushed to investors in a financial platform. The method can be executed by a financial product recommendation device, which can be implemented in the form of hardware and / or software and can generally be configured in a computer or processor with data processing capabilities. Figure 1 As shown, the method includes:

[0057] S110, obtaining basic information and historical investment information of the investor, and performing feature extraction based on the basic information and historical investment information to generate a plurality of first investor features.

[0058] Optionally, the investor's basic information may refer to some basic personal data provided by the investor when registering on the financial platform or conducting investment activities, and the historical investment information may be obtained by analyzing the investor's historical investments on the financial platform.

[0059] It should be noted that the relevant 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 disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in relevant regions.

[0060] Among them, feature extraction is performed based on the basic information and the historical investment information to generate multiple first investor features, including:

[0061] Extract features based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level, and extract features based on the historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product;

[0062] According to the investor's age and historical investment period, the expected investment period is adjusted to obtain the target investment period, and the risk tolerance is adjusted according to the investor's age to obtain the target risk tolerance;

[0063] According to the actual risk level of each historical financial product, the tolerable risk level is adjusted to obtain the target risk level;

[0064] The target investment period, target risk tolerance, target risk level and expected rate of return are determined as the first investor characteristics.

[0065] Optionally, risk tolerance may refer to the psychological and financial ability of investors to withstand investment losses; expected investment period may refer to the time span from the expected investment to the recovery of funds when making a certain investment; expected rate of return may refer to the rate of return that investors hope to obtain based on their own financial goals and market expectations before making investment activities; the tolerable risk level is generally the maximum risk level that investors can accept based on an assessment of basic information such as their financial situation, income stability, asset size, etc., and is usually expressed in a risk rating system, such as low risk, medium-low risk, medium risk, medium-high risk and high risk.

[0066] Optionally, the historical investment period may refer to the actual length of time the investor has spent on each investment in the past. By analyzing the historical investment period, it is possible to understand the investor's previous investment time preferences and investment behavior patterns. The actual risk level of each historical financial product may refer to the actual risk level of each financial product invested by the investor in the past.

[0067] It is understandable that age factors will have an impact on users' risk tolerance and investment period. For users with the same level of risk tolerance, the younger they are, the more likely they are to bear greater risks for a higher rate of return. At the same time, age will also affect the judgment of the investment period. If they are too old or too young, the investment period they can actually bear will often be shorter than the expected investment period they fill in.

[0068] Therefore, the applicant creatively proposed that, in the process of generating the first investor characteristics, the investor characteristics should be appropriately adjusted according to the age factor to obtain characteristics that are more in line with the investor's investment psychology.

[0069] It is understandable that young investors or investors with a history of long-term investments may have greater flexibility and room for adjustment in the expected investment period, while older investors or investors with a history of short-term investments may need to shorten the expected investment period to match changes in their risk preferences and capital needs. Through specific algorithms and analysis models, reasonable adjustments to the expected investment period can be made based on the investor's age and historical investment period, and a target investment period that is more in line with the investor's actual situation can be determined. At the same time, as they age, investors may face reduced income, increased family responsibilities, etc., and their risk tolerance will tend to gradually decrease. Therefore, dynamic adjustments to the original risk tolerance based on the investor's age can calculate a more accurate target risk tolerance.

[0070] Optionally, the actual risk level of each historical financial product can reflect the actual risk conditions experienced by investors in the past. These actual risk experiences will have a corrective effect on the risk level that investors can bear. By conducting in-depth analysis and statistical processing on the actual risk level of each historical financial product and adopting methods such as risk-weighted average, the risk level that investors can bear can be optimized and adjusted, thereby determining a target risk level that is more in line with investors' actual risk tolerance and investment experience.

[0071] The step of obtaining basic information and historical investment information of an investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features also includes:

[0072] When an investor is investing for the first time, basic information of the investor is obtained, and feature extraction is performed based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level;

[0073] According to the investor's age, the expected investment period and risk tolerance are adjusted to obtain the target investment period and target risk tolerance, and the target investment period, target risk tolerance, expected rate of return and tolerable risk level are determined as the first investor characteristics.

[0074] Optionally, the present application also takes into account newly registered users of the financial platform, or users who have not participated in an investment. These users may be missing some historical investment information. In this case, the expected investment period and risk tolerance can be adjusted directly according to the age of the investor. Alternatively, the historical investment period and the actual risk level of each historical financial product of other investors in the same age group with investment experience of less than 1 year can be determined according to the age of the investor, and the median or mode of the historical investment period of other investors and the actual risk level of each historical financial product can be obtained. The median or mode can be used as the historical investment period of first-time investors and the actual risk level of each historical financial product. Then, according to the age of the first-time investor, the historical investment period and the actual risk level of each historical financial product, the expected investment period and risk tolerance can be adjusted.

[0075] S120: Standardize the first investor characteristics to generate second investor characteristics.

[0076] Optionally, the first investor characteristic may refer to a characteristic directly obtained after extraction based on basic information and historical investment information, and the second investor characteristic may refer to a characteristic obtained after standardization of the first investor characteristic.

[0077] Optionally, the standardization process may include missing data completion and data normalization.

[0078] Optionally, when at least one of the first investor characteristics is missing, the remaining investors with similar characteristics can be located based on the first investor characteristics that can be extracted from the investor, and the confirmed characteristics can be completed based on the first investor characteristics of the remaining investors.

[0079] Optionally, after obtaining the complete first investor characteristics, each characteristic may be normalized to serve as input data for the financial product recommendation model.

[0080] S130: Input the second investor characteristics into the financial product recommendation model, obtain the recommendation results of the financial product recommendation model, and determine a plurality of first financial products and a recommendation value of each first financial product according to the recommendation results.

[0081] Optionally, the financial product recommendation model is a pre-trained classification model, and its output may be the score of each financial product sold on the financial platform. When the score is greater than a specified score value, the financial product is determined to be suitable for the investor. The higher the score, the more compatible the product is with the investor, and vice versa.

[0082] Optionally, a financial product with a score greater than a specified score value is determined as a first financial product, and the first financial product is a product that can be recommended to the investor and has a certain degree of matching with the investor.

[0083] Optionally, a recommendation value of each first financial product may be determined based on the score of each first financial product, and the higher the score, the higher the recommendation value.

[0084] S140: Obtain a recommendation coefficient for each financial product, determine at least one second financial product according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and push the second financial product to the investor.

[0085] Optionally, the recommendation coefficient of the financial product may be a recommendation coefficient for the financial product within the financial platform.

[0086] Optionally, the recommendation value of the first financial product may be updated according to the recommendation coefficient of each financial product, the first financial products may be sorted according to the updated recommendation value, and the second financial product may be determined according to the sorting result and the final recommendation value of each first financial product.

[0087] In an optional example, the first 10 first financial products may be recommended as second financial products according to the order of final recommendation value ranking.

[0088] The technical solution of the embodiment of the present invention obtains basic information and historical investment information of investors, and extracts features based on the basic information and historical investment information to generate multiple first investor features, standardizes the first investor features to generate second investor features, inputs the second investor features into the financial product recommendation model, obtains the recommendation results of the financial product recommendation model, and determines multiple first financial products and recommendation values ​​of each first financial product based on the recommendation results, obtains the recommendation coefficient of each financial product, determines at least one second financial product based on the recommendation coefficient of the financial product and the recommendation value of each first financial product, and pushes the second financial product to the investor. It can take into account that age factors will affect the user's risk tolerance and investment period, and appropriately adjust the investor characteristics according to the user's age, thereby improving the accuracy of financial product recommendations. At the same time, further recommendation optimization can be performed based on the financial product recommendation coefficient. On the basis of ensuring that the investment preferences and investment needs of investors are met, the financial product promotion mechanism within the financial platform is optimized, and the operation and development of the financial platform is maintained.

[0089] Embodiment 2

[0090] Figure 2 This is a flowchart of a financial product recommendation method provided by Embodiment 2 of the present invention. This embodiment specifically describes the financial product recommendation method based on the above embodiments. Figure 2 As shown, the method includes:

[0091] S210. Obtain the investor's basic information and historical investment information, perform feature extraction based on the basic information, obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level, and perform feature extraction based on the historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product.

[0092] S220. Extract features based on basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level. Extract features based on historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product.

[0093] S230. According to the actual risk level of each historical financial product, the tolerable risk level is adjusted to obtain the target risk level.

[0094] S240. Determine the target investment period, target risk tolerance, target risk level and expected rate of return as the first investor characteristics.

[0095] S250: Standardize the first investor characteristics to generate second investor characteristics.

[0096] S260: Input the second investor characteristics into the financial product recommendation model to obtain the recommendation result of the financial product recommendation model.

[0097] S270. According to the score of each financial product by the financial product recommendation model, each financial product having a score higher than a first score value is determined as a first financial product.

[0098] S280: Generate a recommendation value for each first financial product according to the score of each first financial product.

[0099] S290. Obtain the expected subscription amount and current subscription amount of each financial product in the financial platform, and determine the recommendation coefficient of each financial product based on the expected subscription amount and the current subscription amount.

[0100] Optionally, the expected subscription amount may refer to the amount of money that the financial platform expects investors to subscribe to for each financial product based on its own business planning, profit targets, product characteristics, market analysis and other factors. It may reflect the ideal sales quota target that the financial platform sets for each financial product from the perspective of operation and development. It is an important reference indicator for the financial platform to measure the marketing effectiveness and sales progress of its products.

[0101] Optionally, the current subscription amount can be counted and updated in real time through the transaction record system of the financial platform, which can accurately reflect the total amount of funds that have actually been subscribed by investors for each financial product at each time point.

[0102] Optionally, the ratio of the current subscription amount to the expected subscription amount can be calculated. The higher the ratio, the lower the recommendation coefficient of the financial product can be appropriately lowered. The lower the ratio, the more capital injection is needed for the financial product, and the recommendation coefficient of the financial product can be appropriately increased.

[0103] Optionally, the recommendation coefficient may also be updated based on factors such as the remaining purchase quantity of the financial product, the issuance threshold of the financial product, the configuration of high-risk products within the financial product, and the investment direction of the financial product evaluated by the financial platform.

[0104] S2100: Determine the recommendation coefficient of each first financial product according to the recommendation coefficient of each financial product, and update the recommendation value of each first financial product according to the recommendation coefficient of each first product to obtain the recommendation value of the first financial product based on the financial platform.

[0105] S2110. Determine a first financial product whose recommendation value based on the financial platform is greater than the second score value as a second financial product.

[0106] The technical solution of the embodiment of the present invention obtains basic information and historical investment information of investors, and extracts features based on the basic information and historical investment information to generate multiple first investor features, standardizes the first investor features to generate second investor features, inputs the second investor features into the financial product recommendation model, obtains the recommendation results of the financial product recommendation model, and determines multiple first financial products and recommendation values ​​of each first financial product based on the recommendation results, obtains the recommendation coefficient of each financial product, determines at least one second financial product based on the recommendation coefficient of the financial product and the recommendation value of each first financial product, and pushes the second financial product to the investor. It can take into account that age factors will affect the user's risk tolerance and investment period, and appropriately adjust the investor characteristics according to the user's age, thereby improving the accuracy of financial product recommendations. At the same time, further recommendation optimization can be performed based on the financial product recommendation coefficient. On the basis of ensuring that the investment preferences and investment needs of investors are met, the financial product promotion mechanism within the financial platform is optimized, and the operation and development of the financial platform is maintained.

[0107] Optionally, the financial product recommendation method also includes:

[0108] Collect basic information and historical investment information of multiple sample investors, perform feature extraction and standardization, and generate investor characteristics of each sample investor; wherein the sample investors have different investment experiences;

[0109] Obtaining various sample financial products currently on sale, and performing feature extraction and standardization processing on each sample financial product to obtain product features of each sample financial product; wherein the product features include an estimated risk level, an estimated investment period, and an estimated rate of return;

[0110] According to the characteristics of each investor and each product, the financial product recommendation model is trained multiple rounds. After each round of training, the current financial product recommendation model is evaluated using model performance evaluation indicators until it is confirmed that the training end conditions are met. The trained financial product recommendation model is then put online on the financial platform.

[0111] Optionally, the investor characteristics include actual investment period, actual risk tolerance, actual risk level and actual rate of return. The actual investment period, actual risk level and actual rate of return can be obtained based on the investor's historical investment information, and the actual risk tolerance can be calculated based on the historical investment buying and selling times and the actual rates of return generated by the buying and selling.

[0112] Optionally, the financial product recommendation model may be a support vector machine (SVM) model, and the model performance evaluation indicator may be an F1-score evaluation indicator.

[0113] Embodiment 3

[0114] Figure 3 This is a schematic diagram of the structure of a financial product recommendation device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a first investor characteristic acquisition module 310 , a second investor characteristic acquisition module 320 , a first financial product determination module 330 and a second financial product determination module 340 .

[0115] The first investor feature acquisition module 310 is used to acquire the basic information and historical investment information of the investor, and perform feature extraction based on the basic information and the historical investment information to generate multiple first investor features.

[0116] The second investor characteristics acquisition module 320 is used to perform standardization processing on the first investor characteristics to generate second investor characteristics.

[0117] The first financial product determination module 330 is used to input the second investor characteristics into the financial product recommendation model, obtain the recommendation results of the financial product recommendation model, and determine multiple first financial products and the recommendation value of each first financial product according to the recommendation results.

[0118] The second financial product determination module 340 is used to determine at least one second financial product according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and push the second financial product to the investor.

[0119] The technical solution of the embodiment of the present invention obtains basic information and historical investment information of investors, and extracts features based on the basic information and historical investment information to generate multiple first investor features, standardizes the first investor features to generate second investor features, inputs the second investor features into the financial product recommendation model, obtains the recommendation results of the financial product recommendation model, and determines multiple first financial products and recommendation values ​​of each first financial product based on the recommendation results, obtains the recommendation coefficient of each financial product, determines at least one second financial product based on the recommendation coefficient of the financial product and the recommendation value of each first financial product, and pushes the second financial product to the investor. It can take into account that age factors will affect the user's risk tolerance and investment period, and appropriately adjust the investor characteristics according to the user's age, thereby improving the accuracy of financial product recommendations. At the same time, further recommendation optimization can be performed based on the financial product recommendation coefficient. On the basis of ensuring that the investment preferences and investment needs of investors are met, the financial product promotion mechanism within the financial platform is optimized, and the operation and development of the financial platform is maintained.

[0120] Based on the above embodiments, the first investor characteristics acquisition module 310 can be specifically used for:

[0121] Extract features based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level, and extract features based on the historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product;

[0122] According to the investor's age and historical investment period, the expected investment period is adjusted to obtain the target investment period, and the risk tolerance is adjusted according to the investor's age to obtain the target risk tolerance;

[0123] According to the actual risk level of each historical financial product, the tolerable risk level is adjusted to obtain the target risk level;

[0124] The target investment period, target risk tolerance, target risk level and expected rate of return are determined as the first investor characteristics.

[0125] Based on the above embodiments, the first investor characteristics acquisition module 310 may also be specifically used for:

[0126] When an investor is investing for the first time, basic information of the investor is obtained, and feature extraction is performed based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level;

[0127] According to the investor's age, the expected investment period and risk tolerance are adjusted to obtain the target investment period and target risk tolerance, and the target investment period, target risk tolerance, expected rate of return and tolerable risk level are determined as the first investor characteristics.

[0128] Based on the above embodiments, the first financial product determination module 330 may be specifically used for:

[0129] According to the score of each financial product given by the financial product recommendation model, each financial product with a score higher than the first score value is determined as a first financial product;

[0130] According to the scores of the first financial products, a recommendation value of each first financial product is generated.

[0131] Based on the above embodiments, the second financial product determination module 340 can be specifically used for:

[0132] Obtaining the expected subscription amount and current subscription amount of each financial product in the financial platform, and determining the recommendation coefficient of each financial product based on the expected subscription amount and current subscription amount;

[0133] Determine the recommendation coefficient of each first financial product according to the recommendation coefficient of each financial product, and update the recommendation value of each first financial product according to the recommendation coefficient of each first product to obtain the recommendation value of the first financial product based on the financial platform;

[0134] The first financial product whose recommendation value based on the financial platform is greater than the second score value is determined as the second financial product.

[0135] Based on the above embodiments, a model training module may also be included, which is used to:

[0136] Collect basic information and historical investment information of multiple sample investors, perform feature extraction and standardization, and generate investor characteristics of each sample investor; wherein the sample investors have different investment experiences;

[0137] Obtaining various sample financial products currently on sale, and performing feature extraction and standardization processing on each sample financial product to obtain product features of each sample financial product; wherein the product features include an estimated risk level, an estimated investment period, and an estimated rate of return;

[0138] According to the characteristics of each investor and each product, the financial product recommendation model is trained multiple rounds. After each round of training, the current financial product recommendation model is evaluated using model performance evaluation indicators until it is confirmed that the training end conditions are met. The trained financial product recommendation model is then put online on the financial platform.

[0139] The financial product recommendation device provided in the embodiment of the present invention can execute the financial product recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0140] Embodiment 4

[0141] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 may be any general and / or dedicated processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the financial product recommendation method described in the embodiment of the present invention. That is:

[0145] Obtaining basic information and historical investment information of an investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features;

[0146] The first investor characteristics are standardized to generate the second investor characteristics;

[0147] Inputting the second investor characteristic into a financial product recommendation model, obtaining a recommendation result of the financial product recommendation model, and determining a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result;

[0148] The recommendation coefficient of each financial product is obtained, at least one second financial product is determined according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and the second financial product is pushed to the investor.

[0149] In some embodiments, the financial product recommendation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the financial product recommendation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the financial product recommendation method in any other appropriate manner (e.g., by means of firmware).

[0150] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0152] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0153] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0154] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0155] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0156] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0157] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A financial product recommendation method, characterized in that: include: Obtaining basic information and historical investment information of an investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features; The first investor characteristics are standardized to generate the second investor characteristics; Inputting the second investor characteristic into a financial product recommendation model, obtaining a recommendation result of the financial product recommendation model, and determining a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result; The recommendation coefficient of each financial product is obtained, at least one second financial product is determined according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and the second financial product is pushed to the investor.

2. The method according to claim 1, characterized in that Feature extraction is performed based on the basic information and the historical investment information to generate multiple first investor features, including: Extract features based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level, and extract features based on the historical investment information to obtain the investor's historical investment period and the actual risk level of each historical financial product; According to the investor's age and historical investment period, the expected investment period is adjusted to obtain the target investment period, and the risk tolerance is adjusted according to the investor's age to obtain the target risk tolerance; According to the actual risk level of each historical financial product, the tolerable risk level is adjusted to obtain the target risk level; The target investment period, target risk tolerance, target risk level and expected rate of return are determined as the first investor characteristics.

3. The method according to claim 2, characterized in that Acquiring basic information and historical investment information of the investor, and performing feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features, further comprising: When an investor is investing for the first time, basic information of the investor is obtained, and feature extraction is performed based on the basic information to obtain the investor's age, risk tolerance, expected investment period, expected rate of return, and tolerable risk level; According to the investor's age, the expected investment period and risk tolerance are adjusted to obtain the target investment period and target risk tolerance, and the target investment period, target risk tolerance, expected rate of return and tolerable risk level are determined as the first investor characteristics.

4. The method according to claim 1, characterized in that: Determining a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result includes: According to the score of each financial product given by the financial product recommendation model, each financial product with a score higher than the first score value is determined as a first financial product; According to the scores of the first financial products, a recommendation value of each first financial product is generated.

5. The method according to claim 1, characterized in that: Obtaining a recommendation coefficient for each financial product, and determining at least one second financial product according to the recommendation coefficient for the financial product and the recommendation value of each first financial product, including: Obtaining the expected subscription amount and current subscription amount of each financial product in the financial platform, and determining the recommendation coefficient of each financial product based on the expected subscription amount and current subscription amount; Determine the recommendation coefficient of each first financial product according to the recommendation coefficient of each financial product, and update the recommendation value of each first financial product according to the recommendation coefficient of each first product to obtain the recommendation value of the first financial product based on the financial platform; The first financial product whose recommendation value based on the financial platform is greater than the second score value is determined as the second financial product.

6. The method according to claim 1, characterized in that Also includes: Collect basic information and historical investment information of multiple sample investors, perform feature extraction and standardization, and generate investor characteristics of each sample investor; wherein the sample investors have different investment experiences; Obtaining various sample financial products currently on sale, and performing feature extraction and standardization processing on each sample financial product to obtain product features of each sample financial product; wherein the product features include an estimated risk level, an estimated investment period, and an estimated rate of return; According to the characteristics of each investor and each product, the financial product recommendation model is trained multiple rounds. After each round of training, the current financial product recommendation model is evaluated using model performance evaluation indicators until it is confirmed that the training end conditions are met. The trained financial product recommendation model is then put online on the financial platform.

7. A financial product recommendation device, characterized in that: include: A first investor feature acquisition module, used to acquire basic information and historical investment information of an investor, and perform feature extraction based on the basic information and the historical investment information to generate a plurality of first investor features; A second investor characteristics acquisition module, used for standardizing the first investor characteristics to generate second investor characteristics; a first financial product determination module, configured to input the second investor characteristics into a financial product recommendation model, obtain a recommendation result of the financial product recommendation model, and determine a plurality of first financial products and a recommendation value of each first financial product according to the recommendation result; The second financial product determination module is used to determine at least one second financial product according to the recommendation coefficient of the financial product and the recommendation value of each first financial product, and push the second financial product to the investor.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial product recommendation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial product recommendation method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the financial product recommendation method according to any one of claims 1 to 6.

Images