CN116452341A - Financial product recommendation method, apparatus, computer device and storage medium - Google Patents

Financial product recommendation method, apparatus, computer device and storage medium Download PDF

Info

Publication number
CN116452341A
CN116452341A CN202310371468.0A CN202310371468A CN116452341A CN 116452341 A CN116452341 A CN 116452341A CN 202310371468 A CN202310371468 A CN 202310371468A CN 116452341 A CN116452341 A CN 116452341A
Authority
CN
China
Prior art keywords
financial product
user
financial
target
target user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310371468.0A
Other languages
Chinese (zh)
Inventor
莫宇乾
张彬
郑显凌
李慧灵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202310371468.0A priority Critical patent/CN116452341A/en
Publication of CN116452341A publication Critical patent/CN116452341A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Human Resources & Organizations (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Technology Law (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application relates to a financial product recommending method and a financial product recommending device, which can be used in the field of financial science and technology to improve recommending effect on financial products which are not held by target users. The method comprises the following steps: obtaining an evaluation coefficient and recommendation degree of the financial product according to the holding probability of the first neighbor user of the target user to the financial product; obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is obtained according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product; determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user; and sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended, and obtaining the financial product recommendation result of the target user.

Description

Financial product recommendation method, apparatus, computer device and storage medium
Technical Field
The present application relates to the field of computer technology, and in particular, to a financial product recommendation method, apparatus, computer device, storage medium, and computer program product.
Background
In the field of financial science and technology, more and more financial institutions such as banks start to provide services for users online, for example, users can browse financial products such as financial accounting through application programs on intelligent terminals, and can select financial products of a heart instrument to conduct online business transaction.
In the conventional technology, similar financial products are often recommended through subjective demands of users, after a certain type of financial products are successfully recommended, the recommendation of the same type of financial products is increased later, and the idea of continuously recommending other types of financial products to the users is ignored, so that potential investment intention of the users cannot be mined, and the conventional method has poor effect of recommending the non-held financial products to the users.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a financial product recommendation method, apparatus, computer device, computer-readable storage medium, and computer program product that are capable of improving the recommendation effect on financial products that are not held by a user.
In a first aspect, the present application provides a financial product recommendation method. The method comprises the following steps:
obtaining an evaluation coefficient and a recommendation degree of the financial product according to the holding probability of a first neighbor user of a target user to the financial product;
Obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product;
determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user;
and sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain a financial product recommendation result of the target user.
In one embodiment, before obtaining the evaluation coefficient and recommendation degree of the financial product according to the holding probability of the first neighboring user of the target user to the financial product, the method further includes:
acquiring browsing information of the target user on the financial product and browsing information of the candidate user on the financial product;
screening target browsing information matched with the browsing information of the target user on the financial product from the browsing information of the candidate user on the financial product;
And taking the candidate user corresponding to the target browsing information as a first neighbor user of the target user.
In one embodiment, obtaining the evaluation coefficient of the financial product according to the holding probability of the first neighboring user of the target user to the financial product includes:
determining the preference holding probability of a first neighbor user of a target user on a financial product under the browsing information from the holding probability of the first neighbor user of the target user on the financial product;
and obtaining the evaluation coefficient of the financial product according to the importance degree corresponding to the browsing information and the preference holding probability.
In one embodiment, the recommendation of the financial product is obtained by:
screening out a first holding probability meeting a first holding probability condition from the holding probabilities corresponding to the financial products, and screening out a second holding probability meeting a second holding probability condition;
and updating the initial recommendation degree of the financial product according to the frequency of the first holding probability and the frequency of the second holding probability to obtain the recommendation degree of the financial product.
In one embodiment, determining the second neighbor user of the target user according to the target evaluation data includes:
Determining the scoring similarity of the target user and the candidate user to the financial product according to the target evaluation data, wherein the scoring similarity is used as the user similarity between the target user and the candidate user;
screening out target user similarity meeting preset similarity conditions from the user similarity;
and taking the candidate user corresponding to the target user similarity as the second neighbor user.
In one embodiment, sorting the to-be-recommended financial products according to the recommendation degree of the to-be-recommended financial products to obtain the financial product recommendation result of the target user includes:
under the condition that recommendation degrees of all the financial products to be recommended are different, sequencing all the financial products to be recommended according to the sequence of the recommendation degrees from large to small to obtain sequenced financial products;
selecting the first N financial products from the sorted financial products as financial product recommendation results of the target user; wherein N is a positive integer.
In one embodiment, sorting the to-be-recommended financial products according to the recommendation degree of the to-be-recommended financial products to obtain the financial product recommendation result of the target user includes:
Under the condition that the recommendation degrees of at least two financial products in the financial products to be recommended are the same, sequencing all the financial products in the financial products to be recommended according to the sequence from the large recommendation degree to the small recommendation degree, and obtaining an initial recommendation result of the target user;
sequencing the at least two financial products according to the target evaluation data to obtain recommendation results to be updated of the at least two financial products;
and updating the initial recommendation result according to the recommendation result to be updated to obtain the financial product recommendation result of the target user.
In a second aspect, the present application further provides a financial product recommendation device. The device comprises:
the evaluation coefficient acquisition module is used for acquiring the evaluation coefficient and recommendation degree of the financial product according to the holding probability of the first neighbor user of the target user to the financial product;
the evaluation data determining module is used for obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product;
the recommended product determining module is used for determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial products held by the second adjacent user to obtain the financial product to be recommended of the target user;
And the recommendation result determining module is used for sequencing the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain the financial product recommendation result of the target user.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
obtaining an evaluation coefficient and a recommendation degree of the financial product according to the holding probability of a first neighbor user of a target user to the financial product;
obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product;
determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user;
And sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain a financial product recommendation result of the target user.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
obtaining an evaluation coefficient and a recommendation degree of the financial product according to the holding probability of a first neighbor user of a target user to the financial product;
obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product;
determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user;
and sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain a financial product recommendation result of the target user.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
obtaining an evaluation coefficient and a recommendation degree of the financial product according to the holding probability of a first neighbor user of a target user to the financial product;
obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product;
determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user;
and sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain a financial product recommendation result of the target user.
According to the financial product recommendation method, the financial product recommendation device, the computer equipment, the storage medium and the computer program product, the evaluation coefficient and the recommendation degree of the financial product are obtained according to the holding probability of the first neighbor user of the target user on the financial product; then, according to the initial evaluation data and the evaluation coefficient of the financial product, obtaining target evaluation data of the financial product; determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user; and sequencing the financial products to be recommended according to the recommendation degree of the financial products to be recommended, so as to obtain the financial product recommendation result of the target user. By adopting the method, the evaluation coefficient of each financial product can be determined through the holding probability of the first neighbor user on the financial product, and the subjective initial evaluation data of the user on the financial product is further optimized through the evaluation coefficient, so that objective and accurate target evaluation data are obtained, and the second neighbor user is determined; the recommendation ordering is carried out on the to-be-recommended financial products which are not held by the target user through the objective recommendation degree, so that the investment intention of the target user on the to-be-recommended financial products can be further mined, and the recommendation effect on the to-be-recommended financial products of the target user is improved.
Drawings
FIG. 1 is a flow chart of a financial product recommendation method according to one embodiment;
FIG. 2 is a flowchart illustrating steps for obtaining an evaluation coefficient of a financial product according to an embodiment;
FIG. 3 is a flowchart illustrating steps for obtaining a recommendation result of a financial product of a target user according to an embodiment;
FIG. 4 is a flowchart of another embodiment of a financial product recommendation method;
FIG. 5 is a block diagram of a financial product recommendation device in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that the method and the device for recommending the financial product provided by the application can be used in the field of financial technology to improve the recommending effect of the financial product which is not held by the user, and can also be used in any field except the financial field for recommending the financial product, for example, the technical field of computers.
In one embodiment, as shown in fig. 1, a financial product recommendation method is provided, where the method is applied to a terminal to illustrate the application of the embodiment, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server, for example, the server may return the financial product recommendation result to the terminal after processing to obtain the financial product recommendation result, so as to display the financial product recommendation result through the terminal. The terminal may be a device used by a staff member of a financial institution such as a bank. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers. In this embodiment, the method includes the steps of:
step S101, according to the holding probability of the first neighbor user of the target user to the financial product, the evaluation coefficient and recommendation degree of the financial product are obtained.
Wherein the first neighbor user refers to a user that is relatively similar (or perfectly matched) to the browsing information preferences of the target user. Financial products refer to non-physical assets that have economic value and can be transacted or redeemed; for example, the financial products may be financial products, stocks, bonds, and the like. The evaluation coefficient is used for objectively correcting the initial evaluation data of the financial product. The recommendation level is used for measuring whether the financial product is worth recommending to the target user.
Specifically, the terminal acquires browsing information of the target user and the candidate user on the financial product, and determines a first neighbor user of the target user according to the browsing information of the target user and the candidate user. The terminal calculates and obtains the evaluation coefficient of the financial product according to the holding probability of the first neighbor user of the target user on the financial product, and simultaneously, the terminal can respectively determine the recommendation degree of each financial product according to whether the holding probability of the first neighbor user on the financial product meets the first holding probability condition and the second holding probability condition.
Step S102, obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product.
The initial evaluation data is evaluation data obtained by generating subjective evaluation information of the target user and the candidate user on the financial product. The initial ratings data is used to describe ratings information for different financial products by different users (e.g., target users and candidate users). The candidate users refer to users related to browsing and holding of financial products besides the target users.
Specifically, the terminal acquires the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product, for example, the evaluation information can be any one of 'poor, general, good and good', and the evaluation information can also be a rating in Arabic digital form, such as 1 score, 4 scores and 5 scores; and the terminal generates initial evaluation data by using the evaluation information of the target user and the candidate user.
In practical application, the initial evaluation data may be in the form of a matrix, and the initial evaluation data M1 may be expressed by formula (1).
Wherein S is m,n And the evaluation information of the mth user to the nth financial product is represented. The number of users to which the target user belongs in the initial evaluation data is not particularly limited in this embodiment. It will be appreciated that the candidate users may be other users in the initial ratings data than the target user. For example, assuming that the 1 st user in the initial evaluation data M1 is a target user, the candidate users are the 2 nd to M th users in the initial evaluation data M1.
Similarly, the evaluation coefficient M2 may be expressed by the formula (2) in the form of a matrix.
Wherein lambda is m,n Representing the coefficient of evaluation of the nth financial product by the mth user.
As can be seen from the formula (2), the terminal may collect the evaluation information and browsing information of each user in advance, so as to calculate and obtain the initial evaluation matrix and evaluation coefficient in advance, and further, in practical application, the terminal may use the index number M of the target user to rapidly extract the required evaluation information and evaluation coefficient from the matrices M1 and M2.
The terminal calculates target evaluation data by using the initial evaluation data and the evaluation coefficient of the financial product, and may perform matrix dot multiplication on the initial evaluation data and the evaluation coefficient, so that the terminal obtains the target evaluation data of the financial product. The target evaluation data M3 can be expressed by the formula (3).
Wherein P is m,n Representing the objective score of the mth user for the nth financial product.
Step S103, determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial products held by the second adjacent user to obtain the financial products to be recommended of the target user.
The financial products to be recommended refer to primarily obtained financial products which can be recommended to the target user.
Specifically, the target evaluation data comprises target scores of all users on the financial products, the terminal screens out the target scores of the target users on the financial products from the target evaluation data, and the target scores of all candidate users on the financial products, so that the second neighbor users of the target users are determined by using the score similarity between the target evaluation information of the target users and the target evaluation information of all candidate users. The terminal obtains the financial product which the second neighbor user currently holds from a database or a terminal used by the second neighbor user, and marks the financial product as a first financial product; meanwhile, the terminal acquires the financial product which is held by the target user at present from the database or the terminal used by the target user, marks the financial product as a second financial product, and then eliminates the financial product which is the same as the second financial product in the first financial product, so that the terminal obtains the financial product to be recommended of the target user.
For example, assume that the first financial product already held by the second neighboring user is qh= { q2, q3, q8, q10}, and the second financial product already held by the target user is qm= { q1, q3, q7, q8}, where q2 represents the 2 nd financial product in the target evaluation data; the target user's financial product to be recommended Q' = { Q2, Q10}.
Step S104, sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended, and obtaining the financial product recommendation result of the target user.
The financial product recommendation result refers to a financial product which is determined after the processing such as sorting and the like and is required to be recommended to a target user.
Specifically, the terminal may sort each of the financial products to be recommended according to the recommendation degree of each of the financial products to be recommended, so as to obtain sorted financial products; and selecting N financial products from the sorted financial products as financial product recommendation results of the target user.
In the financial product recommendation method, the evaluation coefficient and recommendation degree of the financial product are obtained according to the holding probability of the first neighbor user of the target user on the financial product; then, according to the initial evaluation data and the evaluation coefficient of the financial product, obtaining target evaluation data of the financial product; determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user; and sequencing the financial products to be recommended according to the recommendation degree of the financial products to be recommended, so as to obtain the financial product recommendation result of the target user. By adopting the method, the evaluation coefficient of each financial product can be determined through the holding probability of the first neighbor user on the financial product, and the subjective initial evaluation data of the user on the financial product is further optimized through the evaluation coefficient, so that objective and accurate target evaluation data are obtained, and the second neighbor user is determined; the recommendation ordering is carried out on the to-be-recommended financial products which are not held by the target user through the objective recommendation degree, so that the investment intention of the target user on the to-be-recommended financial products can be further mined, and the recommendation effect on the to-be-recommended financial products of the target user is improved.
In one embodiment, in the step S101, before obtaining the evaluation coefficient and the recommendation degree of the financial product according to the holding probability of the first neighboring user of the target user on the financial product, the method further includes: acquiring browsing information of a target user on a financial product and browsing information of a candidate user on the financial product; screening target browsing information matched with the browsing information of the target user on the financial product from the browsing information of the candidate user on the financial product; and taking the candidate user corresponding to the target browsing information as a first neighbor user of the target user.
The browsing information is used for describing the browsing condition of the user on the financial product. The browsing information may include the frequency of consultation of the user with the financial product, browsing preference, browsing time, etc.
Specifically, the terminal obtains browsing information of the target user on the financial product and browsing information of the candidate user on the financial product from the terminal used by the target user or a local database. Under the condition that the browsing information contains multiple types of information, the terminal can respectively screen out target browsing information matched with each type of browsing information of the target user according to each type of browsing information, so that the terminal obtains a first neighbor user corresponding to the target user under each type of browsing information.
For example, assuming that the consultation frequency of the target user on the financial product No. 1 is 5 times/day and the browsing time of the target user on the financial product No. 1 is 20 minutes, the terminal may inquire whether the consultation frequency of the candidate user on the financial product No. 1 is 5 times/day and the browsing time of the target user on the financial product No. 1 is 20 minutes; and if the query results in that the consultation frequency of the candidate user A and the candidate user B on the No. 1 financial product is 5 times/day and the browsing time of the candidate user C and the candidate user D on the No. 1 financial product is 20 minutes, taking the candidate user A, the candidate user B, the candidate user C and the candidate user D as first neighbor users of the target user. The target user can be obtained in the same way for the first neighbor user of the Q-number financial product; wherein Q is a positive integer.
In the embodiment, the target browsing information matched with the browsing information of the target user on the financial product is screened out from the browsing information of the candidate user on the financial product; and then, the candidate user corresponding to the target browsing information is used as a first adjacent user of the target user, and the first adjacent user matched with the browsing preference of the target user can be determined, so that the recommendation degree and the evaluation coefficient of the financial product can be determined by utilizing the holding probability of the first adjacent user matched with the browsing preference on the financial product, and the reliability and the accuracy of the recommendation degree and the evaluation coefficient obtained by processing are improved.
In one embodiment, as shown in fig. 2, the step S101 obtains the evaluation coefficient of the financial product according to the holding probability of the first neighboring user of the target user to the financial product, which specifically includes the following contents:
step S201, determining the preference holding probability of the first neighbor user on the financial product under the browsing information from the holding probability of the first neighbor user of the target user on the financial product.
The holding probability refers to the probability that the first neighbor user purchases the financial product. The preference holding probability refers to a probability that the first neighbor purchases a financial product under a specific type of browsing information.
Specifically, the terminal obtains the preference holding probability of the first neighbor user on the financial product under each type of browsing information from the financial database according to the browsing information of the first neighbor user on the financial product.
Step S202, according to the importance degree and the preference holding probability corresponding to the browsing information, the evaluation coefficient of the financial product is obtained.
Wherein the importance is used to measure the relative importance of each type of browsing information. For example, the importance may be set to 0.2.
Specifically, the terminal obtains the importance degree corresponding to each type of browsing information and the importance degree of the initial evaluation data, and then calculates to obtain the evaluation coefficient of the financial product by using the importance degree of the initial evaluation data, the importance degree corresponding to the browsing information and the preference holding probability corresponding to each type of browsing information, wherein the importance degree corresponding to each type of browsing information and the preference holding probability corresponding to each type of browsing information can be weighted first, and then the weighted result is added with the importance degree of the initial evaluation data, so that the terminal obtains the evaluation coefficient of the financial product.
For example, assume that 1 has been determinedThe consulting frequency, browsing time and preference type of the financial product of the No. 1 user can also determine the type and holding time of the financial product held by the No. 1 user so as to enhance the side writing of the subjective requirement of the No. 1 user, so that the terminal can search the first neighbor user of the No. 1 user under each type of browsing information, the type and holding time of the financial product held by the No. 1 user, and the preference holding probability of the first neighbor user on the financial product of the No. 1 user is 90%, 80%, 0%, 10% and 20%, respectively. Assuming that the importance degree corresponding to each type of browsing information is 0.2 and the importance degree of the initial evaluation data is 1, the evaluation coefficient of the No. 1 user to the No. 1 financial product is lambda 1,1 ＝1+0.2*90％+0.2*80％+0.2*0+0.2*10％+0.2*20％＝1.4。
In the embodiment, the preferred holding probability of the first neighbor user on the financial product under the browsing information is determined from the holding probabilities of the first neighbor user of the target user on the financial product; according to the importance degree and the preference holding probability corresponding to the browsing information, the evaluation coefficient of the financial product is obtained, the holding probability of the financial product by the first neighbor user matched with the browsing information of the target user can be used, and the evaluation coefficient of each financial product is objectively determined according to the actual holding probability, so that the target evaluation data obtained through the evaluation coefficient processing can be more objective and accurate.
In one embodiment, the recommendation degree of the financial product in the step S101 may be obtained as follows: screening out a first holding probability meeting a first holding probability condition from the holding probabilities corresponding to the financial products, and screening out a second holding probability meeting a second holding probability condition; and updating the initial recommendation degree of the financial product according to the frequency of the first holding probability and the frequency of the second holding probability to obtain the recommendation degree of the financial product.
Wherein the first holding probability condition and the second holding probability condition are judgment conditions set for the holding probability of the financial product by the first neighbor user.
Specifically, the terminal acquires a preset first holding probability condition, a preset second holding probability condition and an initial recommendation degree of each financial product, and then the terminal can determine the holding probability corresponding to (associated with) each financial product according to the holding probability of the first neighbor user on the financial product; and the terminal screens out the first holding probability meeting the first holding probability condition and the second holding probability meeting the second holding probability condition from the holding probabilities corresponding to the financial products, and determines the frequency of the first holding probability and the frequency of the second holding probability. Finally, based on the frequency of the first holding probability and the frequency of the second holding probability, updating the initial recommendation degree of the financial products, namely, increasing the initial recommendation degree of each financial product according to the frequency of the first holding probability of each financial product to obtain the updated recommendation degree; and meanwhile, according to the frequency of the second holding probability, the recommendation degree after updating is reduced, so that the recommendation degree of the financial product is obtained by the terminal.
For example, the first holding probability condition may be set equal to 100%, and the second holding probability may be set to 0%, so that the terminal needs to screen out how many 100% and how many 0% of the holding probabilities corresponding to each financial product are from the holding probabilities corresponding to each financial product. Assuming that the holding probabilities corresponding to the number 3 financial products are 2 to 100%,1 to 0%, and assuming that the initial recommendation degree of the number 3 financial products is 0, the recommendation degree=0+2-1 of the number 3 financial products, namely, the initial recommendation degree is increased according to the frequency (100%, 2 times) of the first holding probability, and the initial recommendation degree is reduced according to the frequency (0%, 1 time) of the second holding probability.
In this embodiment, a first holding probability satisfying a first holding probability condition is screened out from holding probabilities corresponding to financial products, and a second holding probability satisfying a second holding probability condition is screened out; according to the frequency of the first holding probability and the frequency of the second holding probability, the initial recommendation degree of the financial product is updated to obtain the recommendation degree of the financial product, the recommendation degree of the financial product can be determined according to the objective holding probability of the financial product, rather than the recommendation according to the subjective preference of the target user, the investment intention of the financial product with high recommendation degree can be mined, and therefore the recommendation effect of the financial product is improved.
In one embodiment, the step S103 determines the second neighboring user of the target user according to the target evaluation data, which specifically includes the following contents: according to the target evaluation data, determining the scoring similarity of the target user and the candidate user to the financial product as the user similarity between the target user and the candidate user; screening out target user similarity meeting preset similarity conditions from the user similarity; and taking the candidate user corresponding to the target user similarity as a second neighbor user.
The scoring similarity is used for measuring similarity between target scores in the target evaluation data. User similarity is used to measure the similarity between users (e.g., target user and candidate user, or candidate user and candidate user).
Specifically, the terminal obtains target scores of the target users and the candidate users on the financial products from the target evaluation data, and generates target score vectors. Then the terminal calculates the scoring similarity between the target scoring vector of the target user and the target scoring vector of the candidate user through the Pearson correlation coefficient; and taking the scoring similarity of the target user and the candidate user to the financial product as the user similarity between the target user and the candidate user. The preset similarity condition may also be set to exceed a preset similarity threshold (for example, 0.5), and the terminal takes the user similarity exceeding the preset similarity threshold as the target user similarity; and then the candidate user corresponding to the similarity of the target user is used as a second neighbor user.
Taking the matrix of the above formula (3) of the target evaluation data M3 as an example, assuming that the target user is the xth user in the target evaluation data M3 and the candidate user a is the yth user in the target evaluation data M3, the target scoring vector of the target userAnd the target scoring vector of the candidate user A +.>Can be used forRepresented by equation (4) and equation (5), respectively.
Score similarity between target user and candidate user ACan be represented by formula (6).
In the embodiment, the scoring similarity of the target user and the candidate user to the financial product is determined according to the target evaluation data, so that the user similarity between the target user and the candidate user is obtained; and screening out the target user similarity meeting the preset similarity condition from the user similarity so as to take the candidate user corresponding to the target user similarity as a second adjacent user, thereby realizing reasonable acquisition of the second adjacent user, and enabling the second adjacent user obtained by screening based on the target evaluation data processed by the evaluation coefficient to be more objective than the second adjacent user obtained by screening based on the initial evaluation data, and further mining the investment intention of the target user on the non-held financial product.
In one embodiment, the step S104 is to sort the financial products to be recommended according to the recommendation degree of the financial products to be recommended, so as to obtain the recommendation result of the financial products of the target user, and specifically includes the following contents: under the condition that the recommendation degrees of all the financial products to be recommended are different, sequencing all the financial products to be recommended according to the sequence from the large recommendation degree to the small recommendation degree to obtain sequenced financial products; selecting the first N financial products from the sorted financial products as the financial product recommendation results of the target user; wherein N is a positive integer.
Specifically, when the recommendation degrees of the financial products to be recommended are different, the terminal can sort the financial products to be recommended according to the sequence from the large recommendation degree to the small recommendation degree, and then the terminal obtains the sorted financial products; and then the terminal selects the first N financial products from the sorted financial products as the financial product recommendation results of the target user, and the terminal displays the financial product recommendation results on an interface.
In this embodiment, the financial products to be recommended are sequenced according to the order of the recommendation degree from large to small to determine the recommendation result of the financial products of the target user, and the recommendation degree is determined by objective holding probability instead of subjective weight, so that the non-held products to be recommended can be more objectively recommended to the target user, and the recommendation effect of the non-held financial products of the target user is improved.
In one embodiment, as shown in fig. 3, in step S104, according to the recommendation degree of the to-be-recommended financial products, the to-be-recommended financial products are ranked to obtain a financial product recommendation result of the target user, which specifically includes the following contents:
step S301, under the condition that the recommendation degrees of at least two financial products in the financial products to be recommended are the same, sorting all the financial products in the financial products to be recommended according to the sequence from the large recommendation degree to the small recommendation degree, and obtaining an initial recommendation result of a target user.
Step S302, sorting at least two financial products according to the target evaluation data to obtain recommendation results to be updated of the at least two financial products.
Specifically, when the recommendation degrees of at least two financial products in the financial products to be recommended are the same, the terminal may sort each financial product in the financial products to be recommended according to the order of the recommendation degrees from large to small, so as to obtain an initial recommendation result of the target user. And then the terminal ranks the at least two financial products according to the target evaluation data, wherein the at least two financial products can be ranked according to the target scores of the target user on the at least two financial products, or the at least two financial products can be ranked according to the average scores of the target user and the candidate user on the at least two products, and the terminal obtains the recommendation results to be updated of the at least two financial products.
Step S303, updating the initial recommendation result according to the recommendation result to be updated to obtain the recommendation result of the financial product of the target user.
Specifically, if the to-be-updated recommendation results of the at least two financial products are the same as the initial recommendation results of the at least two financial products, the terminal selects the first N financial products from the initial recommendation results of the to-be-recommended financial products as the recommendation results of the financial products of the target user. If the to-be-updated recommendation results of the at least two financial products are different from the initial recommendation results of the at least two financial products, the terminal firstly updates the initial recommendation results of the at least two financial products to be updated recommendation results to obtain updated recommendation results of the to-be-recommended financial products, and then the terminal selects the first N financial products from the updated recommendation results of the to-be-recommended financial products to serve as the financial product recommendation results of the target user.
For example, assuming that the recommendation degree of the financial product P1 is +1, the recommendation degree of the financial product P2 is 0, the recommendation degree of the financial product P3 is 0, the target score of the target user to the financial product P1 is 7, the target score of the target user to the financial product P2 is 7, and the target score of the target user to the financial product P3 is 8; the ordering of the financial products P1, P2, and P3 results in P1> P3> P2.
In this embodiment, each financial product in the financial products to be recommended is firstly ordered according to the order of the recommendation degree from large to small, so as to obtain an initial recommendation result of the target user; then ordering at least two financial products according to the target evaluation data to obtain recommendation results to be updated of the at least two financial products; and updating the initial recommendation result according to the recommendation result to be updated to obtain a financial product recommendation result of the target user, determining the financial product recommendation result through objective recommendation degree and target evaluation data instead of determining the financial product recommendation result through subjective weight, and more objectively recommending the product to be recommended which is not held by the target user to the target user, so that the recommendation effect of the target user on the financial product which is not held by the target user is improved.
In one embodiment, as shown in fig. 4, another financial product recommendation method is provided, and the method is applied to a terminal for illustration, and includes the following steps:
step S401, obtaining browsing information of a target user on the financial product and browsing information of a candidate user on the financial product.
Step S402, screening out target browsing information matched with the browsing information of the target user on the financial product from the browsing information of the candidate user on the financial product; and taking the candidate user corresponding to the target browsing information as a first neighbor user of the target user.
Step S403, determining the preference holding probability of the first neighbor user for the financial product under the browsing information from the holding probability of the first neighbor user for the financial product of the target user.
Step S404, according to the importance degree and the preference holding probability corresponding to the browsing information, the evaluation coefficient of the financial product is obtained.
Step S405, screening out a first holding probability satisfying a first holding probability condition from the holding probabilities corresponding to the financial products, and screening out a second holding probability satisfying a second holding probability condition.
Step S406, updating the initial recommendation degree of the financial product according to the frequency of the first holding probability and the frequency of the second holding probability to obtain the recommendation degree of the financial product.
Step S407, obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product.
Step S408, according to the target evaluation data, determining the scoring similarity of the target user and the candidate user to the financial product as the user similarity between the target user and the candidate user.
Step S409, screening out target user similarity meeting preset similarity conditions from the user similarity; and taking the candidate user corresponding to the target user similarity as a second neighbor user.
Step S410, the second financial product held by the target user is removed from the first financial products held by the second neighboring user, and the financial product to be recommended of the target user is obtained.
Step S411, sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended, and obtaining the financial product recommendation result of the target user.
The financial product recommendation method can realize the following beneficial effects: the evaluation coefficient of each financial product can be determined through the holding probability of the first neighbor user on the financial product, and the subjective initial evaluation data of the user on the financial product is further optimized through the evaluation coefficient, so that objective and accurate target evaluation data are obtained, and the second neighbor user is determined; the recommendation ordering is carried out on the to-be-recommended financial products which are not held by the target user through the objective recommendation degree, so that the investment intention of the target user on the to-be-recommended financial products can be further mined, and the recommendation effect on the to-be-recommended financial products of the target user is improved.
In order to more clearly clarify the financial product recommendation method provided by the embodiment of the present disclosure, the financial product recommendation method will be specifically described in the following with a specific embodiment. The further financial product recommendation method can be applied to the terminal and specifically comprises the following steps:
The terminal acquires evaluation information of the target user on the financial product and evaluation information of the candidate user on the financial product to generate initial evaluation data M1. Then the terminal acquires browsing information of the target user and the candidate user on the financial products, and screens out a first neighbor user of the target user according to the browsing information; and the terminal calculates and obtains an evaluation coefficient M2 of the financial product according to the holding probability of the first neighbor user of the target user on the financial product. The terminal performs dot multiplication on the initial evaluation data M1 and the evaluation coefficient M2 to obtain target evaluation data M3 of the financial product. And the terminal acquires target scores of the target users and the candidate users on the financial products from the target evaluation data, and generates target score vectors. And then the terminal calculates the score similarity between the target score vector of the target user and the target score vector of the candidate user through the Pearson correlation coefficient, and the score similarity is used as the user similarity between the target user and the candidate user. The preset similarity threshold may be set to 0.5, and the terminal uses the candidate users with the user similarity exceeding 0.5 as the second neighboring users of the target users. And removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain the financial product to be recommended of the target user. And sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended, and obtaining the financial product recommendation result of the target user.
In this embodiment, the probability of the first neighboring user holding the financial product is used to determine the evaluation coefficient of each financial product, and the subjective initial evaluation data of the user on the financial product is further optimized through the evaluation coefficient, so as to obtain objective and accurate target evaluation data; the recommendation result of the financial product is determined through the objective recommendation degree and the target evaluation data, rather than the subjective weight, so that the non-held product to be recommended can be more objectively recommended to the target user, and the recommendation effect of the non-held financial product of the target user is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a financial product recommendation device for realizing the above related financial product recommendation method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation of the embodiment of the financial product recommendation apparatus provided in the following may refer to the limitation of the financial product recommendation method hereinabove, and will not be repeated herein.
In one embodiment, as shown in FIG. 5, there is provided a financial product recommendation device 500 comprising: an evaluation coefficient acquisition module 501, an evaluation data determination module 502, a recommended product determination module 503, and a recommendation result determination module 504, wherein:
the evaluation coefficient acquisition module 501 is configured to obtain an evaluation coefficient and a recommendation degree of the financial product according to a holding probability of a first neighboring user of the target user to the financial product.
And the evaluation data determining module 502 is configured to obtain target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product.
And a recommended product determining module 503, configured to determine a second neighboring user of the target user according to the target evaluation data, and reject, from first financial products already held by the second neighboring user, the second financial products already held by the target user, to obtain financial products to be recommended of the target user.
And the recommendation result determining module 504 is configured to sort the to-be-recommended financial products according to the recommendation degree of the to-be-recommended financial products, so as to obtain a recommendation result of the financial products of the target user.
In one embodiment, the financial product recommendation device 500 further includes a first neighbor determining module, configured to obtain browsing information of the target user on the financial product, and browsing information of the candidate user on the financial product; screening target browsing information matched with the browsing information of the target user on the financial product from the browsing information of the candidate user on the financial product; and taking the candidate user corresponding to the target browsing information as a first neighbor user of the target user.
In one embodiment, the evaluation coefficient obtaining module 501 is further configured to determine, from the probability of the first neighboring user of the target user holding the financial product, a preference holding probability of the first neighboring user on the financial product under the browsing information; and obtaining the evaluation coefficient of the financial product according to the importance degree corresponding to the browsing information and the preference holding probability.
In one embodiment, the financial product recommendation device 500 further includes a recommendation degree obtaining module, configured to screen out a first holding probability that satisfies a first holding probability condition and screen out a second holding probability that satisfies a second holding probability condition from holding probabilities corresponding to the financial products; and updating the initial recommendation degree of the financial product according to the frequency of the first holding probability and the frequency of the second holding probability to obtain the recommendation degree of the financial product.
In one embodiment, the recommended product determining module 503 is further configured to determine, according to the target evaluation data, a scoring similarity of the target user and the candidate user to the financial product as a user similarity between the target user and the candidate user; screening out target user similarity meeting preset similarity conditions from the user similarity; and taking the candidate user corresponding to the target user similarity as the second neighbor user.
In one embodiment, the recommendation result determining module 504 is further configured to, when the recommendation degrees of the financial products to be recommended are different, sort the financial products to be recommended according to the order of the recommendation degrees from the big to the small, so as to obtain sorted financial products; selecting the first N financial products from the sorted financial products as financial product recommendation results of the target user; wherein N is a positive integer.
In one embodiment, the recommendation result determining module 504 is further configured to, when the recommendation degrees of at least two of the to-be-recommended financial products are the same, sort each of the to-be-recommended financial products according to the order of the recommendation degrees from the high degree to the low degree, and obtain an initial recommendation result of the target user; sequencing the at least two financial products according to the target evaluation data to obtain recommendation results to be updated of the at least two financial products; and updating the initial recommendation result according to the recommendation result to be updated to obtain the financial product recommendation result of the target user.
The above-described respective modules in the financial product recommendation apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor implements a financial product recommendation method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims (11)

1. A method of recommending a financial product, the method comprising:
obtaining an evaluation coefficient and a recommendation degree of the financial product according to the holding probability of a first neighbor user of a target user to the financial product;
obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product; the initial evaluation data is generated according to the evaluation information of the target user on the financial product and the evaluation information of the candidate user on the financial product;
Determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial product held by the second adjacent user to obtain a financial product to be recommended of the target user;
and sorting the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain a financial product recommendation result of the target user.
2. The method of claim 1, further comprising, before obtaining the evaluation coefficient and recommendation of the financial product according to the probability of holding the financial product by the first neighbor of the target user:
acquiring browsing information of the target user on the financial product and browsing information of the candidate user on the financial product;
screening target browsing information matched with the browsing information of the target user on the financial product from the browsing information of the candidate user on the financial product;
and taking the candidate user corresponding to the target browsing information as a first neighbor user of the target user.
3. The method according to claim 2, wherein the obtaining the evaluation coefficient of the financial product according to the holding probability of the first neighboring user of the target user to the financial product comprises:
Determining the preference holding probability of a first neighbor user of a target user on a financial product under the browsing information from the holding probability of the first neighbor user of the target user on the financial product;
and obtaining the evaluation coefficient of the financial product according to the importance degree corresponding to the browsing information and the preference holding probability.
4. The method of claim 1, wherein the recommendation of the financial product is obtained by:
screening out a first holding probability meeting a first holding probability condition from the holding probabilities corresponding to the financial products, and screening out a second holding probability meeting a second holding probability condition;
and updating the initial recommendation degree of the financial product according to the frequency of the first holding probability and the frequency of the second holding probability to obtain the recommendation degree of the financial product.
5. The method of claim 1, wherein said determining a second neighbor of said target user based on said target rating data comprises:
determining the scoring similarity of the target user and the candidate user to the financial product according to the target evaluation data, wherein the scoring similarity is used as the user similarity between the target user and the candidate user;
Screening out target user similarity meeting preset similarity conditions from the user similarity;
and taking the candidate user corresponding to the target user similarity as the second neighbor user.
6. The method of claim 1, wherein the ranking the to-be-recommended financial products according to the recommendation level of the to-be-recommended financial products to obtain the financial product recommendation result of the target user comprises:
under the condition that recommendation degrees of all the financial products to be recommended are different, sequencing all the financial products to be recommended according to the sequence of the recommendation degrees from large to small to obtain sequenced financial products;
selecting the first N financial products from the sorted financial products as financial product recommendation results of the target user; wherein N is a positive integer.
7. The method of claim 1, wherein the ranking the to-be-recommended financial products according to the recommendation level of the to-be-recommended financial products to obtain the financial product recommendation result of the target user comprises:
in the case that the recommendation degree of at least two financial products is the same, according to the order of the recommendation degree from large to small, sorting all the financial products in the financial products to be recommended to obtain an initial recommendation result of the target user;
Sequencing the at least two financial products according to the target evaluation data to obtain recommendation results to be updated of the at least two financial products;
and updating the initial recommendation result according to the recommendation result to be updated to obtain the financial product recommendation result of the target user.
8. A financial product recommendation device, the device comprising:
the evaluation coefficient acquisition module is used for acquiring the evaluation coefficient and recommendation degree of the financial product according to the holding probability of the first neighbor user of the target user to the financial product;
the evaluation data determining module is used for obtaining target evaluation data of the financial product according to the initial evaluation data and the evaluation coefficient of the financial product;
the recommended product determining module is used for determining a second adjacent user of the target user according to the target evaluation data, and removing the second financial product held by the target user from the first financial products held by the second adjacent user to obtain the financial product to be recommended of the target user;
and the recommendation result determining module is used for sequencing the financial products to be recommended according to the recommendation degree of the financial products to be recommended to obtain the financial product recommendation result of the target user.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
CN202310371468.0A 2023-04-07 2023-04-07 Financial product recommendation method, apparatus, computer device and storage medium Pending CN116452341A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310371468.0A CN116452341A (en) 2023-04-07 2023-04-07 Financial product recommendation method, apparatus, computer device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310371468.0A CN116452341A (en) 2023-04-07 2023-04-07 Financial product recommendation method, apparatus, computer device and storage medium

Publications (1)

Publication Number Publication Date
CN116452341A true CN116452341A (en) 2023-07-18

Family

ID=87121385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310371468.0A Pending CN116452341A (en) 2023-04-07 2023-04-07 Financial product recommendation method, apparatus, computer device and storage medium

Country Status (1)

Country Link
CN (1) CN116452341A (en)

Similar Documents

Publication Publication Date Title
CN108885624B (en) Information recommendation system and method
CN113191838A (en) Shopping recommendation method and system based on heterogeneous graph neural network
CN111161009B (en) Information pushing method, device, computer equipment and storage medium
CN117314557A (en) Recommendation method and device for financial products, computer equipment and storage medium
CN117522519A (en) Product recommendation method, device, apparatus, storage medium and program product
CN117390098A (en) Data analysis method, device, computer equipment and storage medium
CN116467525A (en) Recommendation method, device, equipment and storage medium of business products
CN115758271A (en) Data processing method, data processing device, computer equipment and storage medium
CN114969550A (en) Service recommendation method and device, computer equipment and storage medium
CN116452341A (en) Financial product recommendation method, apparatus, computer device and storage medium
CN114219184A (en) Product transaction data prediction method, device, equipment, medium and program product
CN118484253A (en) Function module display method, device, computer equipment and storage medium
CN117033451A (en) Searching method, searching device, computer equipment and storage medium
CN116151896A (en) Virtual product recommendation method, device, computer equipment and storage medium
CN116881546A (en) Resource recommendation method, device, equipment and storage medium
CN116881543A (en) Financial resource object recommendation method, device, equipment, storage medium and product
CN117372113A (en) Product recommendation method, device, computer equipment and storage medium
CN117541350A (en) Product pushing method, device, computer equipment and storage medium
CN116861208A (en) Training method and device for coarse-ranking model of music, computer equipment and storage medium
Hu et al. A novel two-stage combination model for tourism demand forecasting
CN117519871A (en) Method, device and equipment for configuring operation layout of financial service application
CN117350801A (en) Virtual product recommendation method, device, computer equipment, storage medium and product
CN118170867A (en) Service content acquisition method, device, computer equipment, medium and program product
CN117436972A (en) Resource object recommendation method, device, computer equipment and storage medium
CN116823384A (en) Product recommendation method, device, apparatus, storage medium and computer program product

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination