CN118195783A

CN118195783A - Product recommendation method, device, equipment, storage medium and program product

Info

Publication number: CN118195783A
Application number: CN202410363937.9A
Authority: CN
Inventors: 聂艳平
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2024-03-28
Filing date: 2024-03-28
Publication date: 2024-06-14

Abstract

The present disclosure provides a product recommendation method, apparatus, device, storage medium, and program product, which can be applied to the technical field of data processing and the technical field of finance. The method comprises the following steps: responding to the product recommendation request, and determining purchased products of the target user; determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products; for each target product to be recommended, generating product characteristic data of the target product to be recommended based on user attributes of the target user, user behavior data and product attributes of the target product to be recommended; and inputting the product characteristic data of each of the target products to be recommended into a product recommendation model to obtain a product recommendation result.

Description

Product recommendation method, device, equipment, storage medium and program product

Technical Field

The present disclosure relates to the field of data processing technology and financial technology, and in particular, to a product recommendation method, apparatus, device, storage medium, and program product.

Background

When a financial product sales website recommends a financial product to a user, the financial product sales website recommends hot financial products to the user according to sales amount of the financial product on the website, or constructs a user portrait according to purchase history of the user, and recommends interesting financial products to the user according to purchase tendency of the user in the user portrait.

In the process of implementing the disclosed concept, the inventor finds that at least the following problems exist in the related art: the hot financial products are recommended to the user, the user preference is not considered, and the recommended financial products are not the products of interest to the user with high probability, so that the purchase conversion rate of the user is low. Recommending financial products to a user based on a user representation may result in the target user only contacting products that are similar to their interests, while ignoring other financial products that may have a higher conversion rate of purchase. Therefore, there is a need for a financial product recommendation method with high accuracy.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a product recommendation method, apparatus, device, storage medium, and program product.

According to a first aspect of the present disclosure, there is provided a product recommendation method, comprising:

Responding to the product recommendation request, and determining purchased products of the target user;

Determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products;

For each target product to be recommended, generating product characteristic data of the target product to be recommended based on the user attribute of the target user, the user behavior data and the product attribute of the target product to be recommended; and

And inputting the product characteristic data of each of the target products to be recommended into a product recommendation model to obtain a product recommendation result.

According to an embodiment of the present disclosure, the determining, based on the purchased product, a plurality of target products to be recommended from a plurality of products to be recommended includes:

Determining a first user group related to the purchased products and a second user group related to each of the plurality of products to be recommended based on the historical purchase records;

For each product to be recommended, determining the product similarity between the purchased product and each product to be recommended based on the similarity between the first user group and the second user group related to each product to be recommended; and

And determining the target to-be-recommended products from the to-be-recommended products based on the product similarity between the purchased product and each of the to-be-recommended products.

According to an embodiment of the present disclosure, the determining, based on the purchased product, a plurality of target products to be recommended from a plurality of products to be recommended further includes:

for each product to be recommended, determining the product similarity between the purchased product and the product to be recommended based on the similarity between the product attribute of the purchased product and the product attribute of each product to be recommended; and

determining a purchase frequency of the purchased product based on the user behavior data of the target user;

determining the preference of the target user for the purchased products based on the purchase frequency;

Taking the favorites of the target user for the purchased products as weights, and carrying out weighted calculation on the product similarity to obtain initial recommended values; and

And determining the target products to be recommended from the products to be recommended based on the initial recommended values.

According to an embodiment of the present disclosure, before determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products, the method further includes:

determining the type number of the purchased products based on the purchased products of the target user;

Judging whether the purchase proportion of the type number of the purchased products to the total type number is smaller than a preset threshold value or not; and

And determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products under the condition that the purchase proportion is smaller than the preset threshold.

According to an embodiment of the present disclosure, before determining the target to-be-recommended products from the to-be-recommended products based on the purchased products, the method further includes:

determining the selling rate of the product to be recommended based on the historical purchasing record under the condition that the purchasing proportion is larger than or equal to the preset threshold value; and

And determining the target products to be recommended from the products to be recommended based on the selling rate.

According to an embodiment of the present disclosure, the inputting product feature data of each of the plurality of target products to be recommended into a product recommendation model to obtain a product recommendation result includes:

inputting product characteristic data of the target to-be-recommended products into the product recommendation model for each target to-be-recommended product to obtain the predicted purchase rate of the target user on the target to-be-recommended products;

and determining a target recommended product from the target products to be recommended based on the predicted purchase rate.

Another aspect of the present disclosure provides a product recommendation device, comprising:

The request response module is used for responding to the product recommendation request and determining purchased products of the target user;

The product determining module is used for determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products;

the data generation module is used for generating product characteristic data of each target product to be recommended based on the user attribute of the target user, the user behavior data and the product attribute of the target product to be recommended; and

The result acquisition module is used for inputting the product characteristic data of each of the target products to be recommended into the product recommendation model to obtain a product recommendation result.

Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method.

Another aspect of the present disclosure also provides a computer-readable storage medium having stored thereon a computer program or instructions which, when executed by a processor, implement the steps of the above-described method.

Another aspect of the present disclosure also provides a computer program product comprising a computer program or instructions which, when executed by a processor, implement the steps of the above method.

According to the product recommending method, device, equipment, medium and program product, the plurality of target products to be recommended are determined from the plurality of products to be recommended through the purchased products of the target users, and under the condition that the number of the products to be recommended is large, the plurality of target products to be recommended with relatively high purchase conversion rate of the target users can be screened out from the plurality of products to be recommended, so that the accurate obtained product recommending result is ensured, and meanwhile, the data quantity to be processed in the follow-up operation is reduced. Through feature extraction, for each target product to be recommended, product feature data of the target product to be recommended is generated based on user attributes of target users, user behavior data and product attributes of the target product to be recommended, the dimension of the extracted features is increased, and the product feature data of each of a plurality of target products to be recommended is input into a product recommendation model, so that the accuracy of results output by the product recommendation model is improved. In addition, the product recommendation results are obtained through the product recommendation model again for the target products to be recommended after the primary screening, and the accuracy of the product recommendation results is further improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of a product recommendation method according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a product recommendation method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of a product recommendation method according to another embodiment of the present disclosure;

FIG. 4 schematically illustrates a schematic diagram of a target recommended product presentation according to an embodiment of the disclosure;

FIG. 5 schematically illustrates a block diagram of a product recommendation device, according to an embodiment of the present disclosure; and

Fig. 6 schematically illustrates a block diagram of an electronic device adapted to implement a product recommendation method according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a convention should be interpreted in accordance with the meaning of one of skill in the art having generally understood the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical solution of the present disclosure, the related user information (including, but not limited to, user personal information, user image information, user equipment information, such as location information, etc.) and data (including, but not limited to, data for analysis, stored data, displayed data, etc.) are information and data authorized by the user or sufficiently authorized by each party, and the related data is collected, stored, used, processed, transmitted, provided, disclosed, applied, etc. in compliance with relevant laws and regulations and standards, necessary security measures are taken, no prejudice to the public order colloquia is provided, and corresponding operation entries are provided for the user to select authorization or rejection.

At present, when the financial product sales website recommends a financial product to a target user, the following methods may be used, including: (1) randomly presenting a plurality of financial products to a target user; (2) And establishing a target user portrait based on the information of the historical behaviors, the interests, the investment preferences and the like of the target user, and recommending financial products meeting the personalized requirements of the target user to the target user according to the target user portrait. This approach focuses on mining the potential needs of the target user; (3) Recommending financial products similar to historical preferences of the target users by utilizing a collaborative filtering algorithm, recommending the financial products mainly through similarity of behaviors between the target users, and recommending the financial products to the current target users based on products purchased by the other target users under the condition that the behaviors of the two target users are the same, so as to help the current target users to find interesting products. (4) And knowing the tendency of the target user to the financial product by a questionnaire manner, and recommending the financial product which accords with the tendency of the target user to the target user.

For the above-mentioned several recommendation methods, there are mainly the following problems: the scheme (1) does not consider the preference of the target user, and the recommended financial product is not the product of interest to the user with high probability, so that the purchase conversion rate of the product recommended to the target user is low. Although the scheme (2) can infer the interesting products of the target user through the portrait of the target user, the personalized recommendation easily causes the target user to only contact the interesting products similar to the target user, and other financial products with higher purchase conversion rate are ignored. The recommendation method of the scheme (3) through collaborative filtering often needs a large amount of user behavior data to calculate the similarity between target users, and under the condition of sparse data, the algorithm may be difficult to accurately calculate the similarity between the users, so that the purchase conversion rate of products recommended to the target users is low. The scheme (4) obtains the user preference through questionnaire investigation to have certain subjectivity, and the actual preference of the target user is possibly not completely consistent with the filled information, so that the accuracy of the recommendation result is influenced.

In addition, in the process of recommending the products by the target user, a plurality of products can be recommended for improving the purchase conversion rate, however, the energy of the target user is limited, and in order to further improve the purchase conversion rate of the recommended products, the products with higher purchase conversion rate obtained through calculation can be placed in the front of the product recommendation information.

Accordingly, the present disclosure provides a product recommendation method, in response to a product recommendation request, determining purchased products of a target user; determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products; for each target product to be recommended, generating product characteristic data of the target product to be recommended based on user attributes of the target user, user behavior data and product attributes of the target product to be recommended; and inputting the product characteristic data of each of the target products to be recommended into a product recommendation model to obtain a product recommendation result.

Fig. 1 schematically illustrates an application scenario diagram of a product recommendation method according to an embodiment of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages etc. Various communication client applications, such as a web browser application, a financial class application, a search class application, an instant messaging tool, a mailbox client, etc., may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that, the product recommendation method provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the product recommendation device provided by the embodiments of the present disclosure may be generally disposed in the server 105. The product recommendation method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105. Accordingly, the product recommendation apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The product recommendation method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 6 based on the scenario described in fig. 1.

Fig. 2 schematically illustrates a flow chart of a product recommendation method according to an embodiment of the present disclosure.

As shown in fig. 2, the product recommendation method of this embodiment includes operations S210 to S240.

In operation S210, purchased products of the target user are determined in response to the product recommendation request.

In operation S220, a plurality of target products to be recommended are determined from among a plurality of products to be recommended based on the purchased products.

In operation S230, for each target product to be recommended, product characteristic data of the target product to be recommended is generated based on the user attribute of the target user, the user behavior data, and the product attribute of the target product to be recommended.

In operation S240, product feature data of each of the plurality of target products to be recommended is input into the product recommendation model, and a product recommendation result is obtained.

According to the embodiment of the disclosure, in the case that the target user clicks the product recommendation button or enters the recommendation page containing the product recommendation information, the operation action of the target user may generate a product recommendation request, and the server responds to the product recommendation request and obtains a product recommendation result so as to send the product recommendation result to the client where the target user is located.

According to embodiments of the present disclosure, all of the products mentioned in the present disclosure are financial products. The purchased product is a financial product that the user has purchased. In response to the product recommendation request, a historical purchase record of the target user is found in the database based on user information of the target user, such as a login account, a user name, and the like, and the purchased product of the target user is determined based on the historical purchase record of the target user.

According to embodiments of the present disclosure, the purchased products of the target user may include one or more. In the case where the target user is a new user, the target user does not have a purchased product, and in the embodiment of the present disclosure, the case where the target user has a purchased product is mainly considered.

According to the embodiment of the disclosure, the product to be recommended can comprise financial products which are not purchased by the target user and financial products which are purchased by the target user, so that the product to be recommended is designed to guide the user to try new products, and meanwhile, products related to the interests of the user can be provided, and the diversity selection of the user is increased.

According to the embodiment of the disclosure, the target product to be recommended characterizes the primarily determined financial product recommended to the target user. Based on the purchased products of the target users, various methods for determining the target products to be recommended from the target products to be recommended are available, and other products with the shared product characteristics can be determined from the target products to be recommended according to the shared product characteristics among the purchased products, namely the target products to be recommended.

According to the embodiment of the present disclosure, in consideration of the execution time of the product recommendation method of the present disclosure, the number of target products to be recommended may be preset, so as to control the execution time of the subsequent operation, and the subsequent operation is executed at the lowest possible time cost.

According to an embodiment of the present disclosure, the attribute information of the user attribute characterization user may include: the number of times the target user has purchased the financial product, the age of the target user, the occupation of the target user, the city in which the target user is located, etc. within a certain period of time, wherein the period of time may include three days, one week, two weeks, one month, three months, half year, one year.

According to an embodiment of the present disclosure, the user behavior data characterizes data related to financial products generated based on user behavior, may include: the number of times that the target user purchases the target product to be recommended in a certain time period recently, the amount of the target user purchasing the target product to be recommended, the preference degree of the target user for the target product to be recommended, the number of times or amount of purchase of different types of financial products by the target user, the quantity of financial products issued by a company to which the target product to be recommended belongs, the quantity of products maintained by an investment manager to which the user purchases the financial products, and the like, wherein the types of the financial products can comprise fixed income types, stock types and index types. The preference degree of the target user for the target to-be-recommended product can be determined based on the browsing times of the target user for the target to-be-recommended product, and the more the browsing times of the target user are, the higher the preference degree of the target user for the target to-be-recommended product is.

According to the embodiment of the disclosure, the attribute information of the product attribute characterization product may include annual income ratio of the last year or three years of the target product to be recommended, the number of people purchasing the target product to be recommended, the lowest purchase amount of the target product to be recommended, and the amount of the target product to be recommended held by a major institution, wherein the category to which the target product to be recommended belongs includes a fixed income category, a stock category, an index category and the like.

According to the embodiment of the disclosure, for each target product to be recommended, user attribute and user behavior data of a target user are acquired, product attribute of the target product to be recommended is acquired, the extracted data is processed, and product feature data which can be input into a product recommendation model is generated. For example, u1 is used to identify a user, a represents a financial product, the user attribute includes f1, f2, the user behavior data includes f3, f4, and the product attribute includes f5, and then the product feature data of the target product to be recommended a by the user u1 may be in a format of u1, a, f1, f2, f3, f4, f5.

According to an embodiment of the disclosure, the product recommendation model is obtained by training an extreme gradient lifting (eXtreme Gradient Boosting, XGBoost) machine learning algorithm through sample data and performing parameter tuning. The sample data comprises a training sample and a label, wherein the training sample can comprise user attributes of a target user, user behavior data and product attributes of a target product to be recommended, the label represents whether the target product A to be recommended is purchased by the user within a period of time after time t, the label is marked as a positive example, the label is not purchased, the label is marked as a negative example, and the time t represents the ending time point of the period of time in which the sample data are extracted. For example, if the target user u1 purchases the financial product a within a period of time after the time t, the target user u1 is denoted as u1, a,1; if the target user u1 does not purchase the financial product A within a period of time after the time t, the target user u1 is marked as u1, A and 0.

According to the embodiment of the disclosure, the product recommendation result represents financial products to be recommended, which can be displayed to a user through a client. The product recommendation model can calculate the probability value of the target user purchasing the target product to be recommended, and recommending the financial product to the target user through the probability value output by the product recommendation model.

According to the embodiment of the disclosure, the product recommendation model may further sort financial products according to the probability value of purchasing the target product to be recommended by the target user, and determine the financial products to be preferentially displayed based on the sorted financial products due to the limited interface size of displaying the recommended products.

According to an embodiment of the present disclosure, K target data to be recommended to a user may be determined through operation S220, where K is a positive integer greater than 0. And then, sorting the K target data to be recommended through operations S230 and S240, thereby obtaining the order of the financial products recommended to the target object and the recommended financial products.

According to the embodiment of the disclosure, the plurality of target products to be recommended are determined from the plurality of products to be recommended through the purchased products of the target users, and under the condition that the number of the products to be recommended is large, the plurality of target products to be recommended with relatively high purchase conversion rate of the target users can be screened out from the plurality of products to be recommended, so that the accurate obtained product recommendation result is ensured, and meanwhile, the data quantity to be processed in the follow-up operation is reduced. Through feature extraction, for each target product to be recommended, product feature data of the target product to be recommended is generated based on user attributes of target users, user behavior data and product attributes of the target product to be recommended, the dimension of the extracted features is increased, and the product feature data of each of a plurality of target products to be recommended is input into a product recommendation model, so that the accuracy of results output by the product recommendation model is improved. In addition, the product recommendation results are obtained through the product recommendation model again for the target products to be recommended after the primary screening, and the accuracy of the product recommendation results is further improved.

According to an embodiment of the present disclosure, determining a plurality of target products to be recommended from a plurality of products to be recommended based on purchased products, includes:

Determining a first user group related to the purchased products and a second user group related to each of the plurality of products to be recommended based on the historical purchase records; for each product to be recommended, determining a product similarity between the purchased product and each product to be recommended based on the similarity between the first user group and a second user group associated with each product to be recommended; based on the product similarity between the purchased product and each of the plurality of products to be recommended, a plurality of target products to be recommended are determined from the plurality of products to be recommended.

According to embodiments of the present disclosure, for each purchased product of the target user, there may be other users who have purchased the purchased product, and the first user group characterizes a collection of other users who have purchased the purchased product. The second user group characterizes a collection of users who purchased the product to be recommended. And determining the product similarity between the purchased product and the product to be recommended by calculating the similarity between the first user group and the second user group.

According to an embodiment of the present disclosure, assuming that a purchased product a and a product B to be recommended, the number of users of a first user group purchasing the purchased product a is N (i) and the number of users of a second user group purchasing the product B to be recommended is N (j) calculated from a historical purchase record of a target user, and the product similarity of the purchased product a and the product B to be recommended may be calculated by the following formula (1):

Wherein, SIM (A, B) characterizes the product similarity of purchased product A and product B to be recommended; u represents a user who purchases the purchased product A and the product B to be recommended simultaneously; n (u) characterizes the number of users who purchased product A and product B to be recommended simultaneously.

According to the embodiment of the disclosure, for each purchased product, the product similarity between a plurality of products to be recommended and the purchased product can be calculated, and the plurality of products to be recommended with higher product similarity are determined as target products to be recommended through the product similarity obtained for all the purchased products of the target user and the respective products to be recommended.

According to the embodiment of the disclosure, assuming that the purchased products of the target user U include a product a and a product B, products C, D, E are similar to the product a, the product similarity is 0.8,0.6,0.5, products F, G, C are similar to the product B, and the product similarity is 0.9,0.7,0.2, the obtained target products to be recommended may be F, C, G, and the product similarity is 0.9,0.8,0.7.

According to the embodiment of the disclosure, the product to be recommended with higher product similarity is taken as a target product to be recommended by calculating the similarity degree between the first user group related to the purchased product and the second user group related to the product to be recommended. Since the number of products is smaller relative to the number of users, the computational complexity of this method is lower than in the way the target product to be recommended is determined by calculating the similarity between users.

According to an embodiment of the present disclosure, determining a plurality of target products to be recommended from a plurality of products to be recommended based on purchased products, further includes:

For each product to be recommended, determining the product similarity between the purchased product and the product to be recommended based on the similarity between the product attribute of the purchased product and the product attribute of each product to be recommended; and determining a plurality of target products to be recommended from the plurality of products to be recommended based on the product similarity between the purchased product and each of the plurality of products to be recommended.

According to an embodiment of the present disclosure, the obtained product attribute may be further represented as a feature vector by extracting product attributes of the purchased product and the product to be recommended, and the similarity between the purchased product and the product to be recommended may be calculated by a similarity calculation method, where the similarity calculation method may include: cosine similarity, euclidean distance, manhattan distance, etc. And taking a plurality of products to be recommended with higher product similarity as target products to be recommended through the product similarity obtained between all purchased products of the target user and the respective products to be recommended.

According to the embodiment of the present disclosure, the purpose of calculating the product similarity between the purchased product and the product to be recommended is to infer the relationship between the product to be recommended and the purchasing tendency of the target user from the association between the product to be recommended and the purchased product. In the process of similarity calculation, a part of products to be recommended are newly pushed products and cannot be purchased by any user, so that the product similarity cannot be calculated by using the original calculation method, and the product similarity is calculated by the product attributes of the purchased products and the products to be recommended, thereby solving the possible cold start problem of the products to be recommended.

Determining a purchase frequency of the purchased product based on user behavior data of the target user; determining the favorites of the target user for the purchased products based on the purchase frequency; taking the favorites of the target user for the purchased products as weights, and carrying out weighted calculation on the similarity of the products to obtain initial recommended values; and determining a plurality of target products to be recommended from the plurality of products to be recommended based on the initial recommendation value.

According to the embodiment of the disclosure, in a time period for extracting the user behavior data of the target user, the purchase frequency of purchasing the purchased product by the target user is extracted based on the user behavior data of the target user, and the preference of the target user for the purchased product can be obtained through a preset relationship table between the purchase frequency and the preference.

According to the embodiment of the disclosure, the preference of the target user for the purchased product is taken as the weight of each product to be recommended corresponding to the purchased product, and the value obtained by multiplying the similarity of the product and the preference is taken as the initial recommendation value. And taking a plurality of products to be recommended with higher initial recommendation values as target products to be recommended through initial recommendation values obtained for all purchased products of the target user and the respective products to be recommended.

According to the embodiment of the disclosure, the initial recommended value of the product to be recommended is obtained by calculating the favorability of the user for the purchased product as the weight of the product similarity, so that the accuracy of determining the target recommended product from a plurality of products to be recommended is improved.

According to an embodiment of the present disclosure, before determining a plurality of target products to be recommended from a plurality of products to be recommended based on purchased products, the product recommendation method further includes:

Determining the type number of the purchased products based on the purchased products of the target user; judging whether the purchase proportion of the type number of the purchased products to the total type number is smaller than a preset threshold value or not; and determining a plurality of target products to be recommended from the plurality of products to be recommended based on the purchased products under the condition that the purchase proportion is smaller than a preset threshold.

According to an embodiment of the present disclosure, the total type data characterizes the number of types of all products to be recommended, the preset threshold characterizes a value that distinguishes that the target user is able to have a personal purchasing tendency, and the preset threshold can be obtained based on computational analysis. In the case where the purchase ratio is less than the preset threshold, operations S220 to S240 are performed.

Determining the selling rate of the product to be recommended based on the historical purchasing record under the condition that the purchasing proportion is greater than or equal to a preset threshold value; and determining a plurality of target products to be recommended from the plurality of products to be recommended based on the sales rate.

According to embodiments of the present disclosure, the sales rate of the product to be recommended may be the frequency of the purchase of the product to be recommended. The selling rate of the product to be recommended can also be obtained by weighted calculation after quantification of the purchasing frequency, fund scale, number of holders, market public praise and the like of the product to be recommended, wherein the purchasing frequency can be the number of times the product to be recommended is purchased in the period T; the fund scale may be the amount of the product to be recommended that flows out during period T; the market place may be a scoring of the user who purchased the product to be recommended. For example, rate of sales = 0.25 times frequency of purchases +0.25 times fund size +0.25 times holder +0.25 times market public place. And determining a plurality of products to be recommended with higher sales rates as a plurality of target products to be recommended.

Fig. 3 schematically illustrates a flow chart of a product recommendation method according to another embodiment of the present disclosure.

As shown in fig. 3, a product recommendation method according to another embodiment of the present disclosure includes: operations S310 to S380.

In operation S310, purchased products of the target user are determined in response to the product recommendation request.

In operation S320, the number of types of purchased products is determined based on the purchased products of the target user.

In operation S330, it is determined whether the purchase ratio of the number of types of purchased products to the total number of types is less than a preset threshold.

In case that the purchase ratio is less than the preset threshold, operation S340 is performed, and in case that the purchase ratio is greater than or equal to the preset threshold, operation S370 is performed.

In operation S340, a plurality of target products to be recommended are determined from among the plurality of products to be recommended based on the purchased products.

In operation S350, for each target product to be recommended, product characteristic data of the target product to be recommended is generated based on the user attribute of the target user, the user behavior data, and the product attribute of the target product to be recommended.

In operation S360, product feature data of each of the plurality of target products to be recommended is input into the product recommendation model, and a product recommendation result is obtained.

In operation S370, a sales rate of the product to be recommended is determined based on the historical purchase record.

In operation S380, a plurality of target products to be recommended are determined from among the plurality of products to be recommended based on the sales rate.

According to the embodiment of the disclosure, by judging the relation between the purchase proportion of the type number of the purchased products and the total type number and the preset threshold value, and respectively setting the method for determining the target pair recommended products from the plurality of products to be recommended, the target users with purchase tendency and the users with unclear purchase tendency can be distinguished, wherein the users with unclear purchase tendency refer to users interested in purchasing all types of financial products, so that the pertinence of the user group and the accuracy of the recommended results are improved.

According to an embodiment of the present disclosure, inputting product feature data of each of a plurality of target products to be recommended into a product recommendation model to obtain a product recommendation result, including:

for each target product to be recommended, inputting product characteristic data of the target product to be recommended into a product recommendation model to obtain the predicted purchase rate of the target user on the target product to be recommended; a target recommended product is determined from the plurality of target products to be recommended based on the predicted purchase rate.

According to the embodiment of the disclosure, the predicted purchase rate of each target product to be recommended is obtained by inputting the product characteristic data of the target products to be recommended into the product recommendation model, and the target products to be recommended are ranked based on the predicted purchase rates. The method and the system can acquire the accommodating information quantity of the product recommendation pages of the system, and acquire the target product to be recommended with higher predicted purchase rate as the target recommended product. And determining a target recommended product from a plurality of target products to be recommended through the product recommendation model, so that the accuracy of a product recommendation result is further improved.

Fig. 4 schematically illustrates a schematic diagram of a target recommended product presentation according to an embodiment of the present disclosure.

As shown in fig. 4, assuming that the device for logging in the financial product sales website by the target user is a mobile phone, since the data volume that can be presented at one time by the browsed product recommendation page of the target user is limited, the predicted purchase rate of each target product to be recommended is calculated based on the product recommendation model, the target products to be recommended are ranked based on the predicted purchase rates, and the target products to be recommended with higher predicted purchase rates are preferentially displayed. As shown in fig. 4, the predicted purchase rate of the target recommended product 1 is greater than the predicted purchase rate of the target recommended product 2, and the predicted purchase rate of the target recommended product 2 is greater than the predicted purchase rate of the target recommended product 3.

Based on the product recommendation method, the disclosure further provides a product recommendation device. The device will be described in detail below in connection with fig. 5.

Fig. 5 schematically shows a block diagram of a product recommendation device according to an embodiment of the present disclosure.

As shown in fig. 5, the product recommendation apparatus 500 of this embodiment includes a request response module 510, a product determination module 520, a data generation module 530, and a result acquisition module 540.

The request response module 510 is configured to determine a purchased product of the target user in response to the product recommendation request. In an embodiment, the request response module 510 may be configured to perform the operation S210 described above, which is not described herein.

The product determination module 520 is configured to determine a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products. In an embodiment, the product determination module 520 may be configured to perform the operation S220 described above, which is not described herein.

The data generating module 530 is configured to generate, for each target product to be recommended, product feature data of the target product to be recommended based on the user attribute of the target user, the user behavior data, and the product attribute of the target product to be recommended. The data generation module 530 may be used to perform the operation S230 described above in an embodiment, which is not described herein.

The result obtaining module 540 is configured to input product feature data of each of the plurality of target products to be recommended into the product recommendation model, and obtain a product recommendation result. In an embodiment, the result obtaining module 540 may be used to perform the operation S240 described above, which is not described herein.

According to an embodiment of the present disclosure, the product determination module 520 includes: the device comprises a first determining unit, a second determining unit and a third determining unit.

A first determining unit for determining a first user group related to the purchased products and a second user group related to each of the plurality of products to be recommended based on the history purchase record.

And a second determining unit for determining, for each product to be recommended, a product similarity between the purchased product and each product to be recommended based on a degree of similarity between the first user group and a second user group associated with each product to be recommended.

And a third determining unit configured to determine a plurality of target products to be recommended from the plurality of products to be recommended based on the product similarity between the purchased product and each of the plurality of products to be recommended.

According to an embodiment of the present disclosure, the product determination module 520 further includes: a fourth determination unit and a fifth determination unit.

And a fourth determining unit configured to determine, for each of the products to be recommended, a product similarity between the purchased product and the product to be recommended based on a degree of similarity between a product attribute of the purchased product and a product attribute of each of the products to be recommended.

And a fifth determining unit for determining a plurality of target products to be recommended from the plurality of products to be recommended based on the product similarity between the purchased product and each of the plurality of products to be recommended.

According to an embodiment of the present disclosure, the product determination module 520 further includes: a frequency determining unit, a preference determining unit, a weighting calculating unit and a sixth determining unit.

And a frequency determining unit for determining the purchase frequency of the purchased product based on the user behavior data of the target user.

And a preference determining unit for determining the preference of the target user for the purchased products based on the purchase frequency.

And the weighting calculation unit is used for taking the favorites of the target user for the purchased products as weights, and carrying out weighting calculation on the product similarity to obtain initial recommended values.

And a sixth determining unit configured to determine a plurality of target products to be recommended from the plurality of products to be recommended based on the initial recommended value.

According to an embodiment of the present disclosure, the product recommendation device 500 further includes: the device comprises a first determining module, a judging module and a second determining module.

And the first determining module is used for determining the type number of the purchased products based on the purchased products of the target user.

The judging module is used for judging whether the purchase proportion of the type number of the purchased products to the total type number is smaller than a preset threshold value.

And the second determining module is used for determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products under the condition that the purchase proportion is smaller than a preset threshold value.

According to an embodiment of the present disclosure, the product recommendation device 500 further includes: the third determining module is used for selling the third determining module.

And the selling determination module is used for determining the selling rate of the product to be recommended based on the historical purchasing record under the condition that the purchasing proportion is greater than or equal to a preset threshold value.

And the third determining module is used for determining a plurality of target products to be recommended from a plurality of products to be recommended based on the sales rate.

According to an embodiment of the present disclosure, the result acquisition module 540 includes: prediction unit, seventh prediction unit.

The predicting unit is used for inputting the product characteristic data of the target products to be recommended into the product recommendation model for each target product to be recommended, and obtaining the predicted purchase rate of the target users on the target products to be recommended.

And a seventh determining unit for determining a target recommended product from the plurality of target products to be recommended based on the predicted purchase rate.

Any of the request response module 510, the product determination module 520, the data generation module 530, and the result acquisition module 540 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules, according to embodiments of the present disclosure. Or at least some of the functionality of one or more of the modules may be combined with, and implemented in, at least some of the functionality of other modules. At least one of the request response module 510, the product determination module 520, the data generation module 530, and the result acquisition module 540 may be implemented, at least in part, as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or in hardware or firmware, such as any other reasonable manner of integrating or packaging the circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware, in accordance with embodiments of the present disclosure. Or at least one of the request response module 510, the product determination module 520, the data generation module 530, and the result acquisition module 540 may be at least partially implemented as a computer program module that, when executed, performs the corresponding functions.

As shown in fig. 6, an electronic device 600 according to an embodiment of the present disclosure includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. The processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. Processor 601 may also include on-board memory for caching purposes. The processor 601 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or the RAM 603. Note that the program may be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 600 may also include an input/output (I/O) interface 605, the input/output (I/O) interface 605 also being connected to the bus 604. The electronic device 600 may also include one or more of the following components connected to an input/output (I/O) interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to an input/output (I/O) interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 602 and/or RAM 603 and/or one or more memories other than ROM 602 and RAM 603 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to implement the product recommendation method provided by embodiments of the present disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and/or installed from the removable medium 611. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. These examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A method of product recommendation, the method comprising:

For each target product to be recommended, generating product characteristic data of the target product to be recommended based on user attributes of the target user, user behavior data and product attributes of the target product to be recommended; and

2. The method of claim 1, wherein the determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products comprises:

determining a first user population associated with the purchased product and a second user population associated with each of the plurality of products to be recommended based on the historical purchase record;

for each product to be recommended, determining a product similarity between the purchased product and each product to be recommended based on a similarity between the first user population and a second user population associated with each product to be recommended; and

3. The method of claim 2, wherein the determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products, further comprises:

For each product to be recommended, determining a product similarity between the purchased product and the product to be recommended based on a degree of similarity between the product attribute of the purchased product and the product attribute of each product to be recommended; and

4. A method according to claim 2 or 3, wherein said determining a plurality of target products to be recommended from a plurality of products to be recommended based on said purchased products, further comprises:

Determining a purchase frequency of the purchased product based on user behavior data of the target user;

Determining a preference of the target user for the purchased product based on the purchase frequency;

5. The method of claim 1, wherein prior to determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products, the method further comprises:

determining a number of types of purchased products based on the purchased products of the target user;

6. The method of claim 5, wherein prior to determining a plurality of target products to be recommended from a plurality of products to be recommended based on the purchased products, the method further comprises:

determining the selling rate of the product to be recommended based on the historical purchasing record under the condition that the purchasing proportion is greater than or equal to the preset threshold value; and

And determining the target products to be recommended from the products to be recommended based on the sales rate.

7. The method of claim 1, wherein inputting the product feature data of each of the plurality of target products to be recommended into a product recommendation model to obtain a product recommendation result, comprises:

Inputting product characteristic data of the target to-be-recommended products into the product recommendation model for each target to-be-recommended product to obtain predicted purchase rate of the target user on the target to-be-recommended products;

8. A product recommendation device, the device comprising:

9. An electronic device, comprising:

one or more processors;

a memory for storing one or more computer programs,

Characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program or instructions is stored, characterized in that the computer program or instructions, when executed by a processor, implement the steps of the method according to any one of claims 1-7.

11. A computer program product comprising a computer program or instructions which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.