Product recommendation method and device, equipment and medium

Through the analysis of customer group classification model based on account data and market data, dynamic tags are generated, which solves the problem of poor recommendation results caused by inaccurate product labels, and achieves more accurate and precise product recommendations.

CN119090606APending Publication Date: 2024-12-06CHINA CONSTRUCTION BANK +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411236807.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, inaccurate product labeling results in poor product recommendation results and low accuracy, which cannot meet the comprehensive, dynamic and refined needs of modern financial markets for products.

Method used

By obtaining account data, including positions, clicks and purchase data, it is input into the customer group classification model completed in the training, obtain the preferred customer group category, and combine market and product data to generate dynamic risk, investment style and other labels to carry out products recommend.

Benefits of technology

It improves the accuracy and effectiveness of product recommendations, meets the refined demand of the financial market for products, and enhances the dynamic and comprehensiveness of recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090606A_ABST
    Figure CN119090606A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, in particular to a product recommendation method and device, equipment and a medium. In the embodiment of the invention, the electronic equipment obtains account data corresponding to a stored to-be-recommended target product, and the account data comprises position sub-data of each account for the target product, click times of each account for the target product and purchase sub-data of each account for the target product; inputting the account data into the trained customer group classification model, and obtaining a preference customer group category corresponding to the account data output by the customer group classification model; therefore, the preference customer group category corresponding to the target product is determined based on the account data, and the target product is recommended to the first account corresponding to the preference customer group category, so that the recommendation of the target product is more accurate, and the recommendation effect and accuracy of the target product are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] With the rapid development of the financial market and the widespread application of big data technology, the industry is facing massive data challenges and opportunities. Traditional product analysis methods are often limited to a single data dimension and static data analysis, which cannot meet the modern financial market's demand for comprehensive, dynamic and refined products.

[0003] The existing product labels are only generated through product information and are only used to describe the characteristics of the product. They cannot be directly associated with the account for analysis, nor can they reflect the market reaction and the investment preferences of the account. Due to inaccurate product labels, when recommending products based on product labels, the recommendation effect is poor and the accuracy is low. Summary of the invention

[0004] The present application provides a product recommendation method, device, equipment and medium to solve the problem in the prior art that due to inaccurate product labels, the recommendation effect is poor and the accuracy is low when recommending products based on product labels.

[0005] The present invention provides a product recommendation method, which includes:

[0006] Obtaining saved account data corresponding to the target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks of each account on the target product, and each account's purchase sub-data of the target product;

[0007] Inputting the account data into a trained customer group classification model to obtain a preferred customer group category corresponding to the account data output by the customer group classification model;

[0008] The target product is recommended to a first account corresponding to the preferred customer group category.

[0009] Furthermore, the customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model and a purchase preference customer group classification sub-model;

[0010] Inputting the account data into the trained customer group classification model to obtain the preferred customer group category corresponding to the account data output by the customer group classification model includes:

[0011] Inputting the holding sub-data of each account for the target product into the holding preference customer group classification sub-model, and obtaining the holding preference customer group category output by the holding preference customer group classification sub-model;

[0012] Inputting the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtaining the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model;

[0013] Inputting the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtaining the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model;

[0014] The holding preference customer group category, the clicking preference customer group category and the purchasing preference customer group category are determined as the preference customer group category corresponding to the account data.

[0015] Furthermore, the method further comprises:

[0016] Obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track;

[0017] Inputting the product data and the market data into a market positioning classification model, and obtaining a target market positioning category corresponding to the target product output by the market positioning classification model;

[0018] The target product is recommended to a second account corresponding to the target market positioning category.

[0019] Furthermore, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0020] Inputting the stored product data of the target product and the account data into a risk classification model, and obtaining a target risk category corresponding to the target product output by the risk classification model;

[0021] Determining the target risk category as a risk label for the target product;

[0022] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0023] The target product and the risk label are recommended to the first account.

[0024] Furthermore, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0025] Obtain the saved basic information tag corresponding to the target product;

[0026] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0027] The target product and the basic information tag are recommended to the first account.

[0028] Furthermore, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0029] Obtain the saved risk-return label corresponding to the target product;

[0030] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0031] The target product and the risk-return label are recommended to the first account.

[0032] Furthermore, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0033] Obtaining the saved investment style label corresponding to the target product;

[0034] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0035] The target product and the investment style label are recommended to the first account.

[0036] The present application also provides a product recommendation device, the device comprising:

[0037] A processing module, configured to obtain the saved account data corresponding to the target product to be recommended, wherein the account data includes the position sub-data of each account for the target product, the number of clicks of each account on the target product, and the purchase sub-data of each account on the target product;

[0038] A classification module, used to input the account data into a trained customer group classification model, and obtain a preferred customer group category corresponding to the account data output by the customer group classification model;

[0039] A recommendation module is used to recommend the target product to the first account corresponding to the preferred customer group category.

[0040] Furthermore, the customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model and a purchase preference customer group classification sub-model;

[0041] The classification module is specifically used to input the holding sub-data of each account on the target product into the holding preference customer group classification sub-model, and obtain the holding preference customer group category output by the holding preference customer group classification sub-model; input the number of clicks of each account on the target product into the click preference customer group classification sub-model, and obtain the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model; input the purchase sub-data of each account on the target product into the purchase preference customer group classification sub-model, and obtain the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model; and determine the holding preference customer group category, click preference customer group category and purchase preference customer group category as the preference customer group category corresponding to the account data.

[0042] Furthermore, the processing module is further used to obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track;

[0043] The classification module is further used to input the product data and the market data into a market positioning classification model to obtain a target market positioning category corresponding to the target product output by the market positioning classification model;

[0044] The recommendation module is further used to recommend the target product to a second account corresponding to the target market positioning category.

[0045] Furthermore, it is also used to input the stored product data of the target product and the account data into a risk classification model, obtain a target risk category corresponding to the target product output by the risk classification model; and determine the target risk category as a risk label of the target product;

[0046] The recommendation module is specifically used to recommend the target product and the risk label to the first account.

[0047] Furthermore, the processing module is further used to obtain the saved basic information tag corresponding to the target product;

[0048] The recommendation module is specifically used to recommend the target product and the basic information tag to the first account.

[0049] Furthermore, the processing module is also used to obtain the saved risk-return label corresponding to the target product;

[0050] The recommendation module is specifically used to recommend the target product and the risk-return label to the first account.

[0051] Furthermore, the processing module is further used to obtain the saved investment style label corresponding to the target product;

[0052] The recommendation module is specifically used to recommend the target product and the investment style label to the first account.

[0053] An embodiment of the present application also provides an electronic device, which includes a processor, and the processor is used to implement the steps of any of the product recommendation methods described above when executing a computer program stored in a memory.

[0054] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, which implements the steps of any of the product recommendation methods described above when executed by a processor.

[0055] An embodiment of the present application further provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the steps of any of the above-mentioned product recommendation methods.

[0056] In an embodiment of the present application, an electronic device obtains saved account data corresponding to a target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks on the target product by each account, and each account's purchase sub-data of the target product; the account data is input into a trained customer classification model to obtain a preferred customer category corresponding to the account data output by the customer classification model; thereby, based on the account data, the preferred customer category corresponding to the target product is determined, and the target product is recommended to a first account corresponding to the preferred customer category, thereby making the recommendation of the target product more accurate and improving the recommendation effect and accuracy of the target product. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 A schematic diagram of a product recommendation process provided in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of a product recommendation process provided in an embodiment of the present application;

[0060] Figure 3 A schematic diagram of the structure of a product recommendation device provided in an embodiment of the present application;

[0061] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0063] The terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. "Multiple" in the present application can mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.

[0064] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0065] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.

[0066] With the rapid development of the financial market and the widespread application of big data technology, the industry is facing massive data challenges and opportunities. Traditional product analysis methods are often limited to a single data dimension and static data analysis, which cannot meet the comprehensive, dynamic and refined needs of the modern financial market for products, resulting in low accuracy in the process of product recommendations based on product tags.

[0067] Therefore, the embodiment of the present application provides a product recommendation method, device, equipment and medium. In the embodiment of the present application, the saved account data corresponding to the target product to be recommended is obtained, wherein the account data includes the holding sub-data of each account for the target product, the number of clicks of each account for the target product and the purchase sub-data of each account for the target product; the account data is input into the trained customer group classification model to obtain the preferred customer group category corresponding to the account data output by the customer group classification model; and the target product is recommended to the first account corresponding to the preferred customer group category.

[0068] Embodiment 1:

[0069] Figure 1 A schematic diagram of a product recommendation process provided in an embodiment of the present application, the process includes:

[0070] S101: Obtain the saved account data corresponding to the target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks on the target product by each account, and each account's purchase sub-data of the target product.

[0071] A product recommendation method provided in an embodiment of the present application is applied to an electronic device, which may be a PC or a server.

[0072] Since the product labels in the relevant technology are only generated through product information, the generated labels are only used to describe the characteristics of the product and cannot be directly associated with the investment attributes of the account for analysis. In addition, the product labels are static rule labels and cannot be dynamically generated according to the investment preferences of the account, which leads to poor product recommendation effects and low accuracy.

[0073] Based on this, in the embodiment of the present application, the electronic device stores the account data corresponding to each product, and determines the preferred customer group category corresponding to the target product to be recommended based on the account data corresponding to the target product to be recommended, so as to recommend the target product to the account of the preferred customer group category. Among them, the account data includes the holding sub-data of the target product by each account since the target product went online, the number of clicks on the target product by each account, and the purchase sub-data of the target product by each account. Among them, the holding sub-data is the holding value of each account for the target product; the purchase sub-data is the quantity or total amount of the target product purchased by each account.

[0074] Specifically, the electronic device stores the corresponding relationship between the product identification and the account data. When recommending products, the electronic device receives the input product recommendation instruction carrying the product identification, determines the product corresponding to the product identification as the target product to be recommended, and obtains the account data corresponding to the stored target product with the identification. The product identification can be a product name, a product serial number, etc., and the product can be a fund product or other financial product.

[0075] S102: Input the account data into a trained customer group classification model, obtain a preferred customer group category corresponding to the account data output by the customer group classification model; and recommend the target product to a first account corresponding to the preferred customer group category.

[0076] In the embodiment of the present application, the electronic device is configured with a trained customer group classification model, and the electronic device can determine the preferred customer group category corresponding to the target product based on the customer group classification model and the account data corresponding to the target product. Among them, the customer group is an account group, which means that the accounts are divided according to certain conditions, and each account in each customer group has the same or similar characteristics, which can be age, assets, etc., which are not limited here. The electronic device also stores the information of the accounts corresponding to each customer group.

[0077] In addition, in the embodiment of the present application, the preferred customer group category corresponding to the target product may be one customer group or multiple customer groups, which is not limited here.

[0078] When determining the preferred customer category of the target product, the electronic device constructs a feature vector based on the account data and inputs the feature vector into the customer classification model. The customer classification model classifies the account data based on the position sub-data of each account on the target product, the number of clicks on the target product by each account and the purchase sub-data of the target product by each account carried in the feature vector corresponding to the account data, and determines and outputs the preferred customer category corresponding to the target product.

[0079] Among them, when the electronic device constructs a feature vector based on account data, the dimensions of the feature vector include three dimensions, corresponding to position sub-data, number of clicks and purchase sub-data respectively; the data written in each dimension is a column vector, and the sub-data corresponding to each customer is written into the corresponding column vector according to a preset order.

[0080] The electronic device also stores the accounts corresponding to each customer group. The electronic device receives the preferred customer group category output by the customer group classification model, determines the first account corresponding to the preferred customer group category, and recommends the target product to the first account. For example, the target product is recommended to the first account in the form of "high-yield products recommended to you", "robust products that match your risk tolerance", etc. The number of the first account can be one or more.

[0081] In an embodiment of the present application, before the electronic device inputs the account data into the customer classification model, the electronic device may also pre-process the account data to remove outliers or duplicate data, and normalize or standardize the data so that different features have the same numerical scale, ensuring that the data is of high quality and can be accurately analyzed and applied.

[0082] In addition, since account data is constantly changing, electronic devices need to update and adjust the preferred customer categories of target products in real time based on the changed account data.

[0083] Furthermore, in an embodiment of the present application, the electronic device uses a machine learning algorithm to train a customer group classification model to automatically classify products by customer group. During the training process, the parameters of the customer group classification model are continuously optimized and adjusted to improve the accuracy and reliability of the customer group classification. The electronic device may also divide the data set into a training set and a test set (which may also include a validation set). The training set is used to train the customer group classification model, and the hyperparameters of the customer group classification model are adjusted to optimize performance.

[0084] In addition, the electronic device can also use an independent test set to evaluate the performance of the customer group classification model, such as calculating the accuracy, recall rate, F1 score, AUC-ROC and other indicators of the customer group classification model through the test set. And optimize and adjust the customer group classification model according to the evaluation results of each indicator, including but not limited to adjusting the parameters of the customer group classification model, improving the feature extraction method, and increasing the training data.

[0085] During the training process of the customer group classification model, manual review can be used to identify and correct incorrect preferred customer group categories, and at the same time discover problems with the model and directions for improvement. During the review process, new preferred customer group categories can be added or existing preferred customer group categories can be modified according to business needs. Manual review can be used to correct label data through actual investment performance, investor feedback, etc.

[0086] In an embodiment of the present application, the electronic device determines the preferred customer category corresponding to the target product through a customer classification model and the account data corresponding to the target product, thereby determining the preferred customer category corresponding to the target product based on the account data, and recommends the target product to the first account corresponding to the preferred customer category, thereby making the recommendation of the target product more accurate and improving the recommendation effect and accuracy of the target product.

[0087] Embodiment 2:

[0088] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiment, in the embodiment of the present application, the customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model and a purchase preference customer group classification sub-model;

[0089] Inputting the account data into the trained customer group classification model to obtain the preferred customer group category corresponding to the account data output by the customer group classification model includes:

[0090] Inputting the holding sub-data of each account for the target product into the holding preference customer group classification sub-model, and obtaining the holding preference customer group category output by the holding preference customer group classification sub-model;

[0091] Inputting the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtaining the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model;

[0092] Inputting the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtaining the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model;

[0093] The holding preference customer group category, the clicking preference customer group category and the purchasing preference customer group category are determined as the preference customer group category corresponding to the account data.

[0094] In order to better classify the target product's preferred customer groups based on account data, the customer group classification model includes at least three sub-models, namely, the holding preference customer group classification sub-model, the click preference customer group classification sub-model and the purchase preference customer group classification sub-model. Among them, the holding preference customer group classification sub-model can classify customers based on the holding sub-data, the click preference customer group classification sub-model can classify customers based on the number of clicks, and the purchase preference customer group classification sub-model can classify customers based on the purchase sub-data.

[0095] Specifically, the electronic device inputs the holding sub-data of the target product for each account into the holding preference customer group classification sub-model. The holding preference sub-model classifies the customer group according to the holding sub-data corresponding to each account, and determines and outputs the holding preference customer group category corresponding to the target product. The electronic device inputs the number of clicks on the target product by each account into the click preference customer group classification sub-model. The click preference customer group classification sub-model classifies the customer group according to the number of clicks of each account, and determines and outputs the click preference customer group category corresponding to the target product. The electronic device inputs the purchase sub-data of the target product for each account into the purchase preference customer group classification sub-model. The purchase preference customer group classification sub-model classifies the customer group according to the purchase sub-data of each account, and determines and outputs the purchase preference customer group category corresponding to the target product.

[0096] After determining the holding preference customer group category, the clicking preference customer group category, and the purchasing preference customer group category, the electronic device determines the holding preference customer group category, the clicking preference customer group category, and the purchasing preference customer group category as the preference customer group category corresponding to the target product.

[0097] In addition, in an embodiment of the present application, the electronic device can also determine the preferred customer group category corresponding to the target product as the account preference label of the target product. The electronic device can subsequently analyze the investment behavior and preferences of the account based on the account preference label, determine the account's product needs and product preferences, and better position the target product.

[0098] For example, the account preference label may be: customer group 1 is suitable for this product, customer group 2 is suitable for this product, customer group 3 is suitable for this product, customer group n is suitable for this product, etc.

[0099] Embodiment 3:

[0100] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0101] Obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track;

[0102] Inputting the product data and the market data into a market positioning classification model, and obtaining a target market positioning category corresponding to the target product output by the market positioning classification model;

[0103] The target product is recommended to a second account corresponding to the target market positioning category.

[0104] In the related art, product labels are static rule labels, and it is impossible to generate product labels dynamically according to market reactions. Based on this, in order to enrich the product labels of each product and make product recommendations more accurate, in the embodiment of the present application, the electronic device also determines the target market positioning category corresponding to the target product.

[0105] Specifically, the electronic device also stores product data and market data corresponding to the target product. Among them, product data includes basic product information, investment information and risk information. Basic product information includes but is not limited to the historical performance of the target product, position status, information of each fund manager, economic data, rate structure and industry classification; investment information includes but is not limited to investment style and investment strategy; risk information includes but is not limited to risk level; market data includes but is not limited to market dynamics, market index data, capital inflow and outflow data of each investment track, capital holdings data of each investment track and capital flow data, etc.

[0106] Among them, historical performance refers to the number of successful historical recommendations of the target product; holdings refer to the current holdings of the target product; the information of each fund manager refers to the performance of each fund manager, such as the number of times each fund manager successfully recommended the target product; economic data refers to the value and return of the target product; investment style refers to what kind of investment is suitable, such as suitable for short-term holding, suitable for long-term holding, etc.; investment strategy refers to how to invest in the target product, such as the recommended number of holdings; rate structure includes subscription rate, application rate, redemption rate, management fee, custody fee, sales service fee, application rate of the transferred-in fund, and redemption rate applicable to the transferred-out fund on the conversion application date; risk level refers to the risk situation of the target product, such as High risk, low risk, medium risk, etc.; industry classification refers to the industry category to which the target product belongs; market dynamics refers to the increase or decrease in the holdings of the target product in the current market, such as an increase or decrease in the number of positions, etc.; market index data refers to an index reference number compiled by various service agencies that indicates changes in a certain market; the capital inflow and outflow data for each investment track refers to the purchase amount and sale amount of each investment track product; the capital holdings data for each investment track refers to the current total holdings of each product of each investment track; the capital flow data refers to the increase or decrease in funds for each investment track, such as a decrease in funds in investment track A and an increase in funds in investment track B, then the capital flow data is considered to be from investment track A to investment track B.

[0107] The electronic device is also equipped with a trained market positioning classification model, which inputs product data and market data into the market positioning classification model, and the market positioning classification model performs classification based on the product data and market data, determines and outputs the target market positioning category corresponding to the target product. The target market positioning category can help compare the differences and advantages of the target product with other similar products, and clarify the positioning of the target product in the market.

[0108] The electronic device determines the target market positioning category as a market label corresponding to the target product, and recommends the target product to a second account corresponding to the saved target market positioning category.

[0109] For example, the market label of the target product may be that market feature 1 is applicable to the product, or market feature 2 is applicable to the product, or market feature n is applicable to the product, etc.

[0110] In addition, since market data is constantly changing, electronic devices need to update and adjust the target market positioning category of target products in real time based on the changed market data.

[0111] Embodiment 4:

[0112] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiments, in the embodiment of the present application, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0113] Inputting the stored product data of the target product and the account data into a risk classification model, and obtaining a target risk category corresponding to the target product output by the risk classification model;

[0114] Determining the target risk category as a risk label for the target product;

[0115] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0116] The target product and the risk label are recommended to the first account.

[0117] In order to increase the purchase rate of the product, in an embodiment of the present application, the electronic device will also determine the risk label corresponding to the target product, and simultaneously recommend the risk label when recommending the target product to the first account, so that the first account can better understand the target product, thereby increasing the purchase rate of the product.

[0118] Specifically, a trained risk classification model is pre-configured in the electronic device. The electronic device obtains the stored product data and account data of the target product, and inputs the product data and account data into the risk classification model. The risk classification model performs risk classification based on the product data and account data, and determines and outputs the target risk category corresponding to the target product.

[0119] In an embodiment of the present application, when the electronic device recommends the target product to the first account corresponding to the preferred customer group category, the electronic device recommends the target product and the risk label to the first account.

[0120] In addition, the electronic device can also save the target product and the risk label accordingly, so that the risk of the target product can be identified and understood based on the risk label later, thereby achieving risk control and avoidance.

[0121] Embodiment 5:

[0122] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiments, in the embodiment of the present application, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0123] Obtain the saved basic information tag corresponding to the target product;

[0124] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0125] The target product and the basic information tag are recommended to the first account.

[0126] In an embodiment of the present application, the electronic device also stores the basic information tag of the target product. When the electronic device recommends the target product to the first account, it can also simultaneously recommend the basic information tag of the target product.

[0127] The basic information tag contains the basic information of the target product, management team, product type and investment strategy for the target product, which is used to describe the basic information characteristics of the target product. The basic information includes but is not limited to the product name and product type.

[0128] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiments, in the embodiment of the present application, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0129] Obtain the saved risk-return label corresponding to the target product;

[0130] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0131] The target product and the risk-return label are recommended to the first account.

[0132] In an embodiment of the present application, the electronic device also stores a risk-return label corresponding to the target product. When the electronic device recommends the target product to the first account, it can also simultaneously recommend the risk-return label of the target product.

[0133] Among them, the risk-return label carries indicators such as historical performance, volatility, risk level, risk exposure and risk-adjusted return corresponding to the target product, which are used to describe the risk-return characteristics of the target product.

[0134] In order to improve the product recommendation effect and recommendation accuracy, based on the above embodiments, in the embodiment of the present application, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0135] Obtaining the saved investment style label corresponding to the target product;

[0136] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0137] The target product and the investment style label are recommended to the first account.

[0138] In an embodiment of the present application, the electronic device also stores an investment style label corresponding to the target product. When the electronic device recommends the target product to the first account, it may also simultaneously recommend the investment style label of the target product.

[0139] Among them, the investment style label is determined based on the industry configuration and stock selection logic of the target product's holdings, and can be used to analyze the investment style of the target product, so as to better understand the investment characteristics of the target product.

[0140] For example, the investment style can be suitable for short-term holding, suitable for long-term holding, etc.

[0141] In the embodiments of the present application, the various labels corresponding to the target products can be used not only to recommend the target products, but also to classify and search the products, provide comprehensive fund information and analysis for the accounts, help them make more informed investment decisions, help sales better understand the characteristics of the products, market positioning and trends, optimize product marketing strategies, and improve marketing effectiveness and operational efficiency. In short, the automatic generation of fund product labels by artificial intelligence is a complex and important process that requires comprehensive consideration of multiple factors such as business needs, data quality, and algorithm selection. By continuously optimizing and improving each classification model, the accuracy and reliability of product labels can be improved.

[0142] Figure 2A schematic diagram of a product recommendation process provided in the embodiment of the present application, such as the Figure 2 As shown, the process includes:

[0143] S201: Construct each preferred customer group category.

[0144] S202: Collect and pre-process account data.

[0145] S203: Training a customer group classification model according to each preferred customer group category and the collected account data.

[0146] S204: Determine the preferred customer group category corresponding to the target product according to the account data of the target product to be recommended and the trained customer group classification model.

[0147] S205: Recommending the target product to the first account corresponding to the preferred customer group category.

[0148] Embodiment 6:

[0149] Based on the same inventive concept, the embodiment of the present application provides a product recommendation device. Figure 3 This is a schematic diagram of a product recommendation device structure provided in an embodiment of the present application. Please refer to Figure 3 , the device comprises:

[0150] Processing module 301 is used to obtain the saved account data corresponding to the target product to be recommended, wherein the account data includes the position sub-data of each account for the target product, the number of clicks of each account on the target product, and the purchase sub-data of each account on the target product;

[0151] A classification module 302 is used to input the account data into a trained customer group classification model to obtain a preferred customer group category corresponding to the account data output by the customer group classification model;

[0152] The recommendation module 303 is used to recommend the target product to the first account corresponding to the preferred customer group category.

[0153] In a possible implementation, the customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model, and a purchase preference customer group classification sub-model;

[0154] The classification module 302 is specifically used to input the holding sub-data of the target product of each account into the holding preference customer group classification sub-model, and obtain the holding preference customer group category output by the holding preference customer group classification sub-model; input the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtain the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model; input the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtain the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model; and determine the holding preference customer group category, click preference customer group category and purchase preference customer group category as the preference customer group category corresponding to the account data.

[0155] In a possible implementation, the processing module 301 is further used to obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; and the market data includes basic market information and investment information of each investment track;

[0156] The classification module 302 is further used to input the product data and the market data into a market positioning classification model to obtain a target market positioning category corresponding to the target product output by the market positioning classification model;

[0157] The recommendation module 303 is further configured to recommend the target product to a second account corresponding to the target market positioning category.

[0158] In a possible implementation manner, the processing module 301 is further used to input the stored product data of the target product and the account data into a risk classification model, obtain a target risk category corresponding to the target product output by the risk classification model; and determine the target risk category as a risk label of the target product;

[0159] The recommendation module 303 is specifically configured to recommend the target product and the risk label to the first account.

[0160] In a possible implementation, the processing module 301 is further used to obtain a saved basic information tag corresponding to the target product;

[0161] The recommendation module 303 is specifically configured to recommend the target product and the basic information tag to the first account.

[0162] In a possible implementation, the processing module 301 is further used to obtain a saved risk-benefit label corresponding to the target product;

[0163] The recommendation module 303 is specifically configured to recommend the target product and the risk-return label to the first account.

[0164] In a possible implementation, the processing module 301 is further used to obtain the saved investment style label corresponding to the target product;

[0165] The recommendation module 303 is specifically configured to recommend the target product and the investment style label to the first account.

[0166] Embodiment 7:

[0167] Based on the same inventive concept, an embodiment of the present application provides an electronic device, which can implement the steps of the product recommendation method discussed above. Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, it includes: a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;

[0168] The memory 403 stores a computer program. When the program is executed by the processor 401, the processor 401 performs the following steps:

[0169] Obtaining saved account data corresponding to the target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks of each account on the target product, and each account's purchase sub-data of the target product;

[0170] Inputting the account data into a trained customer group classification model to obtain a preferred customer group category corresponding to the account data output by the customer group classification model;

[0171] The target product is recommended to a first account corresponding to the preferred customer group category.

[0172] In a possible implementation, the customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model, and a purchase preference customer group classification sub-model;

[0173] Inputting the account data into the trained customer group classification model to obtain the preferred customer group category corresponding to the account data output by the customer group classification model includes:

[0174] Inputting the holding sub-data of each account for the target product into the holding preference customer group classification sub-model, and obtaining the holding preference customer group category output by the holding preference customer group classification sub-model;

[0175] Inputting the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtaining the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model;

[0176] Inputting the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtaining the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model;

[0177] The holding preference customer group category, the clicking preference customer group category and the purchasing preference customer group category are determined as the preference customer group category corresponding to the account data.

[0178] In a possible implementation, the method further includes:

[0179] Obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track;

[0180] Inputting the product data and the market data into a market positioning classification model, and obtaining a target market positioning category corresponding to the target product output by the market positioning classification model;

[0181] The target product is recommended to a second account corresponding to the target market positioning category.

[0182] In a possible implementation manner, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0183] Inputting the stored product data of the target product and the account data into a risk classification model, and obtaining a target risk category corresponding to the target product output by the risk classification model;

[0184] Determining the target risk category as a risk label for the target product;

[0185] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0186] The target product and the risk label are recommended to the first account.

[0187] In a possible implementation manner, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0188] Obtain the saved basic information tag corresponding to the target product;

[0189] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0190] The target product and the basic information tag are recommended to the first account.

[0191] In a possible implementation manner, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0192] Obtain the saved risk-return label corresponding to the target product;

[0193] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0194] The target product and the risk-return label are recommended to the first account.

[0195] In a possible implementation manner, before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes:

[0196] Obtaining the saved investment style label corresponding to the target product;

[0197] The recommending the target product to the first account corresponding to the preferred customer group category includes:

[0198] The target product and the investment style label are recommended to the first account.

[0199] Since the principle of solving the problem by the above electronic device is similar to the product recommendation method, the implementation of the above electronic device can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0200] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface 402 is used for communication between the above electronic device and other devices. The memory may include a random access memory (RAM) and may also include a non-volatile memory (NVM), such as at least one disk storage. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0201] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0202] Embodiment 8:

[0203] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, in which a computer program executable by a processor is stored. When the program runs on the processor, the processor executes any of the product recommendation methods discussed above. Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the product recommendation method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0204] Embodiment 9:

[0205] Based on the same inventive concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any of the product recommendation methods discussed above. Since the principle of solving the problem by the above computer program product is similar to that of the product recommendation method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.

[0206] In an embodiment of the present application, an electronic device obtains saved account data corresponding to a target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks on the target product by each account, and each account's purchase sub-data of the target product; the account data is input into a trained customer classification model to obtain a preferred customer category corresponding to the account data output by the customer classification model; thereby, based on the account data, the preferred customer category corresponding to the target product is determined, and the target product is recommended to a first account corresponding to the preferred customer category, thereby making the recommendation of the target product more accurate and improving the recommendation effect and accuracy of the target product.

[0207] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0208] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0209] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0211] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A product recommendation method, characterized in that: The method comprises: Obtaining saved account data corresponding to the target product to be recommended, wherein the account data includes each account's holding sub-data of the target product, the number of clicks of each account on the target product, and each account's purchase sub-data of the target product; Inputting the account data into a trained customer group classification model to obtain a preferred customer group category corresponding to the account data output by the customer group classification model; The target product is recommended to a first account corresponding to the preferred customer group category.

2. The method according to claim 1, characterized in that The customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model and a purchase preference customer group classification sub-model; Inputting the account data into the trained customer group classification model to obtain the preferred customer group category corresponding to the account data output by the customer group classification model includes: Inputting the holding sub-data of each account for the target product into the holding preference customer group classification sub-model, and obtaining the holding preference customer group category output by the holding preference customer group classification sub-model; Inputting the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtaining the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model; Inputting the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtaining the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model; The holding preference customer group category, the clicking preference customer group category and the purchasing preference customer group category are determined as the preference customer group category corresponding to the account data.

3. The method according to claim 1, characterized in that The method further comprises: Obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track; Inputting the product data and the market data into a market positioning classification model, and obtaining a target market positioning category corresponding to the target product output by the market positioning classification model; The target product is recommended to a second account corresponding to the target market positioning category.

4. The method according to claim 1, characterized in that: Before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes: Inputting the stored product data of the target product and the account data into a risk classification model, and obtaining a target risk category corresponding to the target product output by the risk classification model; Determining the target risk category as a risk label for the target product; The recommending the target product to the first account corresponding to the preferred customer group category includes: The target product and the risk label are recommended to the first account.

5. The method according to claim 1, characterized in that Before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes: Obtain the saved basic information tag corresponding to the target product; The recommending the target product to the first account corresponding to the preferred customer group category includes: The target product and the basic information tag are recommended to the first account.

6. The method according to claim 1, characterized in that Before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes: Obtain the saved risk-return label corresponding to the target product; The recommending the target product to the first account corresponding to the preferred customer group category includes: The target product and the risk-return label are recommended to the first account.

7. The method according to claim 1, characterized in that Before recommending the target product to the first account corresponding to the preferred customer group category, the method further includes: Obtaining the saved investment style label corresponding to the target product; The recommending the target product to the first account corresponding to the preferred customer group category includes: The target product and the investment style label are recommended to the first account.

8. A product recommendation device, characterized in that: The device comprises: A processing module, configured to obtain the saved account data corresponding to the target product to be recommended, wherein the account data includes the position sub-data of each account for the target product, the number of clicks of each account on the target product, and the purchase sub-data of each account on the target product; A classification module, used to input the account data into a trained customer group classification model, and obtain a preferred customer group category corresponding to the account data output by the customer group classification model; A recommendation module is used to recommend the target product to the first account corresponding to the preferred customer group category.

9. The device according to claim 8, characterized in that The customer group classification model includes a holding preference customer group classification sub-model, a click preference customer group classification sub-model and a purchase preference customer group classification sub-model; The classification module is specifically used to input the holding sub-data of the target product of each account into the holding preference customer group classification sub-model, and obtain the holding preference customer group category output by the holding preference customer group classification sub-model; input the number of clicks of the target product by each account into the click preference customer group classification sub-model, and obtain the click preference customer group category corresponding to the target product output by the click preference customer group classification sub-model; input the purchase sub-data of the target product by each account into the purchase preference customer group classification sub-model, and obtain the purchase preference customer group category corresponding to the target product output by the purchase preference customer group classification sub-model; The holding preference customer group category, the clicking preference customer group category and the purchasing preference customer group category are determined as the preference customer group category corresponding to the account data.

10. The device according to claim 8, characterized in that The processing module is further used to obtain pre-saved product data and market data corresponding to the target product; wherein the product data includes basic product information, investment information and risk information; the market data includes basic market information and investment information of each investment track; The classification module is further used to input the product data and the market data into a market positioning classification model to obtain a target market positioning category corresponding to the target product output by the market positioning classification model; The recommendation module is further used to recommend the target product to a second account corresponding to the target market positioning category.

11. The device according to claim 8, characterized in that The processing module is further used to input the stored product data of the target product and the account data into the risk classification model, obtain the target risk category corresponding to the target product output by the risk classification model; and determine the target risk category as the risk label of the target product; The recommendation module is specifically used to recommend the target product and the risk label to the first account.

12. The device according to claim 8, characterized in that The processing module is further used to obtain the saved basic information label corresponding to the target product; The recommendation module is specifically used to recommend the target product and the basic information tag to the first account.

13. The device according to claim 8, characterized in that The processing module is further used to obtain the saved risk-return label corresponding to the target product; The recommendation module is specifically used to recommend the target product and the risk-return label to the first account.

14. The device according to claim 8, characterized in that The processing module is further used to obtain the saved investment style label corresponding to the target product; The recommendation module is specifically used to recommend the target product and the investment style label to the first account.

15. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is used to implement the steps of the product recommendation method as claimed in any one of claims 1 to 7 when executing a computer program stored in a memory.

16. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the product recommendation method as described in any one of claims 1 to 7.

17. A computer program product, characterized in that The computer program product comprises: a computer program code, and when the computer program code is run on a computer, the computer is enabled to execute the steps of the product recommendation method as claimed in any one of claims 1 to 7.