CN112215680A - Product recommendation method and device, electronic equipment and storage medium - Google Patents

Product recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112215680A
CN112215680A CN202011134118.5A CN202011134118A CN112215680A CN 112215680 A CN112215680 A CN 112215680A CN 202011134118 A CN202011134118 A CN 202011134118A CN 112215680 A CN112215680 A CN 112215680A
Authority
CN
China
Prior art keywords
product
products
determining
similarity
score
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.)
Granted
Application number
CN202011134118.5A
Other languages
Chinese (zh)
Other versions
CN112215680B (en
Inventor
朱泓
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.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
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 Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202011134118.5A priority Critical patent/CN112215680B/en
Publication of CN112215680A publication Critical patent/CN112215680A/en
Application granted granted Critical
Publication of CN112215680B publication Critical patent/CN112215680B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

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

Abstract

The embodiment of the invention provides a product recommendation method, a device, electronic equipment and a storage medium. Based on the scheme provided by the invention, the product similarity recommendation algorithm can be optimized, the influence factor of recent attention behaviors of the client can be constructed, the limitation caused by taking the similarity as the recommendation priority in the traditional real-time recommendation method is effectively improved, and the reliability and the accuracy of the recommendation result are improved.

Description

Product recommendation method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of big data, in particular to a product recommendation method, a product recommendation device, electronic equipment and a storage medium.
Background
In recent years, product recommendation technology has been widely applied in various scenarios, such as: various shopping Applications (APP). The physical products or the virtual products can be recommended for the users through the product recommendation technology.
The current product recommendation technology recommends products to users based on similarity of the products, and the recommended products are often products with the maximum similarity, but the inventor of the application finds that: the recommendation effect of the product with the greatest similarity tends to be low.
Disclosure of Invention
The embodiment of the invention aims to provide a product recommendation method, a product recommendation device, electronic equipment and a storage medium, so that a product similarity recommendation algorithm is optimized, influence factors of recent attention behaviors of customers are constructed, the limitation caused by taking the similarity as a recommendation priority in the traditional real-time recommendation method is effectively improved, and the reliability and the accuracy of a recommendation result are improved. The specific technical scheme is as follows:
in a first aspect, the present disclosure provides a product recommendation method, including:
obtaining a first product set formed by products evaluated by a target user in a first time period, wherein the time interval between the latest moment in the first time period and the current moment is less than a preset interval;
obtaining a second product set consisting of products similar to the product concerned by the target user;
determining the similarity of each product in the second product set and each product in the first product set respectively;
obtaining a third product set formed by products in the first product set with the similarity higher than a preset threshold;
obtaining the score of each product in the third product set, and determining the prediction score sum _ sim of each product in the second product set based on the score and the similaritypi；
Determining an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set;
passing the prediction score sum _ sim of each product in the second set of productspiDetermining a recommendation priority score of each product in the second product set according to the influence factor IF corresponding to each product in the second product set;
recommending at least one product in the second product set to the target user according to the recommendation priority score.
With reference to the first aspect, in some optional embodiments, the recommending at least one product in the second set of products to the target user according to the recommendation priority score includes:
obtaining a fourth product set formed by products recommended to the target user last time;
obtaining a union of the fourth set of products and the second set of products;
recommending at least one product in the union to the target user according to the recommendation priority scores of the products in the union.
With reference to the first aspect, in some optional embodiments, the determining, based on the similarity between each product in the third product set and each product in the second product set, an influence factor IF corresponding to each product in the second product set includes:
determining each product in the second product set as a product to be processed, and respectively processing each product to be processed as follows:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
With reference to the first aspect, in some optional embodiments, the determining, based on the first number and the second number, an influence factor IF corresponding to the product to be processed includes:
determining an influence factor IF corresponding to the product to be processed based on a formula IF ═ lgmax { efcount,1} -lgmax { wfcount,1}, wherein efcount represents the first number, wfcount represents the second number, and lg is a logarithm with a base 2.
With reference to the first aspect, in some optional embodiments, the obtaining a score of each product in the third product set, and determining a pre-score of each product in the second product set based on the score and the similarityMeasurement score sum _ simpiThe method comprises the following steps:
based on the formula
Figure BDA0002736105980000031
Determining a prediction score sum-sim for each product in the second set of productspiWherein S ispiqjIs a product p of the second set of productsiProduct q of said third set of productsjSimilarity of (D), RqjIs product q of the third set of productsjI and j are the serial numbers of the products,lis product q of the third set of productsjThe number of (2).
In a second aspect, the present disclosure provides a product recommendation device, comprising: the system comprises a first set obtaining unit, a second set obtaining unit, a similarity determining unit, a third set obtaining unit, a prediction score determining unit, an influence factor determining unit, a priority determining unit and a product recommending unit;
the first set obtaining unit is configured to perform obtaining of a first product set formed by products evaluated by a target user in a first time period, wherein a time interval between the latest time in the first time period and the current time is smaller than a preset interval;
the second set obtaining unit is configured to execute obtaining of a second product set composed of products similar to the product concerned by the target user;
the similarity determining unit is configured to perform determination of similarity between each product in the second product set and each product in the first product set;
the third set obtaining unit is configured to perform obtaining of a third product set formed by products in the first product set with the similarity higher than a preset threshold;
the prediction score determining unit is configured to obtain a score of each product in the third product set, and determine the second product based on the score and the similarityPrediction score sum-sim of each product in the product setpi；
The influence factor determining unit is configured to determine an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set;
the priority determination unit is configured to execute the prediction score sum _ sim of each product in the second product setpiDetermining a recommendation priority score of each product in the second product set according to the influence factor IF corresponding to each product in the second product set;
the product recommending unit is configured to recommend at least one product in the second product set to the target user according to the recommendation priority score.
With reference to the second aspect, in some optional embodiments, the product recommendation unit includes: the device comprises a first set obtaining unit, a union obtaining unit and a recommending unit;
the first set obtaining unit is configured to execute obtaining of a fourth product set formed by products recommended to the target user last time;
the union obtaining unit is configured to obtain a union of the fourth product set and the second product set;
the recommending unit is configured to recommend at least one product in the union to the target user according to the recommendation priority scores of the products in the union.
With reference to the second aspect, in some optional embodiments, the influence factor determining unit is specifically configured to perform:
determining each product in the second product set as a product to be processed, and respectively processing each product to be processed as follows:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
In a third aspect, the present disclosure provides a storage medium for storing a program that when executed by a processor implements the product recommendation method of any one of the above.
In a fourth aspect, the present disclosure provides an electronic device comprising at least one processor, and at least one memory connected to the processor, a bus; the processor and the memory complete mutual communication through the bus; the processor is configured to call a program in the memory, the program at least being configured to implement the product recommendation method of any of the above.
According to the product recommendation method, the product recommendation device, the electronic equipment and the storage medium, provided by the embodiment of the invention, the product to be recommended can be comprehensively determined based on the product set formed by the products recently evaluated by the user and the product set formed by the products similar to the products concerned by the user. The embodiment of the invention can determine the similarity between the products of the two sets, filter the products based on the similarity, and then determine the prediction score sum _ sim of the products based on the score and the similarity of the filtered productspiThe invention also determines an influence factor IF based on the similarity and combines the influence factor IF with a prediction score sum _ simpiA recommendation priority score is obtained. Therefore, the recommendation priority score obtained by the method considers the products recently evaluated by the user and the products similar to the products concerned by the user, and simultaneously performs product filtering and determines the recommendation priority score based on the similarity between the products. The embodiment of the invention can effectively improve the reliability and accuracy of product recommendation. In the data analysis process, the attention behavior of the target user is considered, the attention behavior of the target user is brought into the calculation process, the attention behavior of the target user is taken as a parameter to calculate the recommendation priority score of the product, and meanwhile, the influence factor IF is used for correctingThe resulting recommendation priority score. Based on the scheme provided by the invention, the product similarity recommendation algorithm can be optimized, the influence factor of recent attention behaviors of the client is constructed, the limitation caused by taking the similarity as the recommendation priority in the traditional real-time recommendation method is effectively improved, and the reliability and the accuracy of the recommendation result are improved. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a product recommendation method according to the present invention;
FIG. 2 is a schematic structural diagram of a product recommendation device according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
With the rapid development of the internet and information technology, it becomes extremely difficult for consumers to obtain the most interesting information or recommended products from massive information in a short time, or for information or recommended product advertisements generated by information publishers to stand out.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present invention provides a product recommendation method, including:
s100, obtaining a first product set formed by products evaluated by a target user in a first time period, wherein the time interval between the latest moment in the first time period and the current moment is smaller than a preset interval.
Optionally, the products in the first product set in the embodiment of the present invention may be entity products, or may also be virtual products. The solid product is an entity occupying a certain space, such as shoes, mobile phones and the like. The virtual products are virtual articles, such as game props, financial products, stocks and the like.
Alternatively, the first product set may be a set of products that the target user has evaluated last m times, and the products that the target user has evaluated may be products purchased or focused on by the user.
Optionally, the time length of the first time period is not limited in the present invention, and any feasible manner falls into the protection scope of the present invention.
It is to be understood that the first set of products includes products that have been recently evaluated by the target user.
S200, obtaining a second product set formed by products similar to the products concerned by the target user.
Optionally, similarity between each two products may be calculated based on the scoring data of a large number of products by a large number of users, where the similarity includes a product P concerned by the target user, and then the second product set may be determined according to the similarity between the product P concerned by the target user and the large number of products.
For example, a product scoring matrix Y is generated based on scoring data of a large number of usersm×n，Ym×nA scoring matrix representing n products by m users;
optionally, the scoring data may be obtained by performing weight addition and normalization processing on the real-time preference data captured by the operation actions such as client browsing, clicking, viewing, collecting, evaluating, scoring, and the like, or the retention time, and the like, which is not limited in the present invention. For example, the score data has a value ranging from 0 to 1, where 0 is the lowest score and 1 is the highest score.
Combined product scoring matrix Ym×nCalculating similarity between products by cosine similarity algorithm to form product similarity matrix Sn×nThe matrix form is:
Figure BDA0002736105980000071
s in the formula (1)1×nRepresenting the degree of similarity between product 1 and product n, as defined by the formula (2):
Figure BDA0002736105980000072
in the formula (2)
Figure BDA0002736105980000073
And
Figure BDA0002736105980000074
from the product scoring matrix Ym×nObtaining a score vector composed of scores of users respectively representing a product 1 and a product n; through the formulas (1) and (2), a product similarity matrix S among a large number of products is obtainedn×nAlso included are products P of interest to the target user.
Optionally, because the product similarity matrix has a large calculation amount, the calculation can be performed in a batch off-line calculation mode, and the product similarity matrix can be effectively separated from a production system, so that system resources are reasonably and maximally utilized.
The similarity between the product P concerned by the target user and other products, and the available vector
Figure BDA0002736105980000075
Expressed as:
Figure BDA0002736105980000076
sorting the elements in the formula (3), taking out k products corresponding to the first k elements (the larger first k elements),i.e., the k products with the greatest degree of similarity to product p (the one product the target user is interested in), constitutes a second product set of product p: a ═ p1…pk}。
Optionally, the steps S100 and S200 do not have a certain sequential execution order, and may be executed in parallel, or after the step S100 is executed, the step S200 may be executed; or, after the step S200 is executed, the step S100 is executed, which is not limited in the present invention.
S300, determining the similarity between each product in the second product set and each product in the first product set.
Optionally, in step S200, k products with the greatest similarity to the product P focused on by the target user, that is, the second product set, are obtained. However, not all of the k products need to be recommended to the target user, but also the similarity between each of the k products and each of the products in the first product set needs to be calculated, so as to determine which of the k products can be recommended to the target user according to the similarity, and therefore the method of step S300 can be executed.
Optionally, for each product in the second product set, the way of calculating the similarity between each product in the second product set and each product in the first product set is not limited in the present invention.
Optionally, the invention may be based on the product similarity matrix Sn×nDetermining the similarity S between each product in the second product set and each product in the first product set respectivelypiqj。
After the similarity between each product in the second product set and each product in the first product set is obtained through calculation, for each product in the second product set, a product with a greater similarity to each product in the first product set may be selected from the first product set, that is, step S400 may be performed.
S400, obtaining a third product set formed by products in the first product set with the similarity higher than a preset threshold.
For each product in the second product set, if a product with the similarity greater than a preset threshold exists in the first product set, obtaining a product with the similarity greater than the preset threshold as a third product set corresponding to the product, without limiting the number of the products; if there is no product in the first product set whose similarity with the product is greater than the preset threshold, it is not necessary to obtain a corresponding product from the first product set, and the present invention does not limit this.
Optionally, for each product in the second product set, a third product set corresponding to the product may be obtained respectively, or a union of the third product sets corresponding to each product in the second product set may also be obtained as a final third product set, and the subsequent steps herein are performed based on a scheme of obtaining the third product set corresponding to each product in the second product set, which is not limited in the present invention.
Optionally, the preset threshold may be set according to actual needs, and the present invention does not limit the specific value of the preset threshold, and any feasible manner belongs to the protection scope of the present invention.
S500, obtaining the score of each product in the third product set, and determining the prediction score sum _ sim of each product in the second product set based on the score and the similaritypi。
Optionally, in the foregoing step S400, a third product set corresponding to each product in the second product set has been obtained, and then for each product in the second product set, the prediction score sum _ sim of each product in the second product set may be calculated based on the third product setpi。
Optionally, if the target user scores the product, the current score is taken, and if the target user does not score the product, an automatic scoring mechanism is set through the service, for example, the product is automatically weighted and scored according to the whole body, which is not limited by the present invention.
Optionally, a prediction score sum _ sim of any one product in the second set of products is calculatedpiThe method of (a) can be set as desired, and the invention is not limited thereto.
For example, in combination with the embodiment shown in fig. 1, in some alternative embodiments, the step S500 includes:
based on the formula
Figure BDA0002736105980000091
Determining a prediction score sum-sim for each product in the second set of productspiWherein S ispiqjIs a product p of the second set of productsiProduct q of said third set of productsjSimilarity of (D), RqjIs product q of the third set of productsjI and j are product numbers, l is product q of the third set of productsjThe number of (2).
Optionally, for each product in the second product set, the prediction score sum _ sim may be calculated by using formula (4)piFor example, p in the above formula (4) can be representediAll modified to p1To thereby determine the product p1Prediction score sum simpi。
S600, determining an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set.
Optionally, in step S500, the prediction score sum _ sim of each product in the second product set may be obtainedpiBut only on the prediction score sum simpiDetermining which products may be recommended to the target user may not be very accurate. Therefore, for each product in the second product set, the number of products in the first product set, which are subjected to the similarity calculation with each product in the second product set, may be considered comprehensively, and if the number of products in the first product set, which are subjected to the similarity calculation with a specific product in the second product set, is large, the prediction score sum _ sim of the specific product in the second product set may be determinedpiIncreasing may be performed by adding the predicted score sum _ sim of the specific one of the second set of productspiAre added with their corresponding influencing factors IF.
Optionally, the present invention does not limit the calculation manner of the impact factor IF, and any feasible manner falls within the protection scope of the present invention.
For example, in combination with the embodiment shown in fig. 1, in some alternative embodiments, the step S600 includes:
determining each product in the second product set as a product to be processed, and respectively processing each product to be processed as follows:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
Optionally, with reference to the previous embodiment, in some optional embodiments, the determining, based on the first number and the second number, an influence factor IF corresponding to the product to be processed includes:
determining an influence factor IF corresponding to the product to be processed based on a formula IF ═ lgmax { efcount,1} -lgmax { wfcount,1}, wherein efcount represents the first number, wfcount represents the second number, and lg is a logarithm with a base 2.
Optionally, the first quantity may be that the similarity between the product to be processed and each product in the third product set is not lower than a preset similarity threshold, and the prediction score sum _ simpiThe number of products to be processed not lower than a preset scoring threshold; the second quantity may be that the similarity between the product to be processed and each product in the third product set is lower than a preset similarity threshold, or the prediction score sum _ simpiThe number of products to be treated that is below a preset scoring threshold.
S700, passing prediction scores sum _ sim of all products in the second product setpiDetermining influence factors IF corresponding to each product in the second product setA recommendation priority score for each product in the second set of products.
Optionally, for each product in the second set of products, the recommendation priority score for a particular product may be based on the formula: eUpi＝sum_simpi+ IF calculation, where EUp1Is any one product p in the second set of productsiIs recommended priority score, sum _ simpiIs a product piPrediction score sum simpiIF is product piIs used, the present invention is not limited in this regard.
S800, recommending at least one product in the second product set to the target user according to the recommendation priority score.
Optionally, at least one product with a higher recommendation priority score may be selected from the second product set according to the recommendation priority score and recommended to the target user, and specifically, an upper limit of the recommended number may be set according to actual needs, which is not limited in the present invention.
Optionally, in addition to recommending the product to the target user according to the recommendation priority score, the result of pushing the product to the target user last time may be referred to, and a suitable product is selected to be recommended to the target user.
For example, in combination with the embodiment shown in fig. 1, in some alternative embodiments, the step S800 includes: step one, step two and step three;
step one, obtaining a fourth product set formed by products recommended to the target user last time;
step two, obtaining a union of the fourth product set and the second product set;
step three, scoring Eu according to the recommended priority of each product in the union setpiRecommending at least one product in the union to the target user.
Optionally, for step two, if the fourth product set and the second product set have the same product, for the same product, the following processing may be performed:
1. and if the recommendation priority score of the same product in the fourth product set is equal to the recommendation priority score in the second product set, taking any one of the recommendation priority scores as the recommendation priority score of the product in the third step.
2. If the recommendation priority scores of the same product in the fourth product set are not equal to the recommendation priority score of the second product set, taking the recommendation priority score of the product in the second product set as the recommendation priority score of the product in step three, or taking the maximum value of the recommendation priority score of the product in the fourth product set and the recommendation priority score of the product in the second product set as the recommendation priority score of the product in step three, or taking the average value of the recommendation priority score of the product in the fourth product set and the recommendation priority score of the product in the second product set as the recommendation priority score of the product in step three, which is not limited by the invention.
As shown in fig. 2, the present invention provides a product recommendation device, including: a first set obtaining unit 100, a second set obtaining unit 200, a similarity determining unit 300, a third set obtaining unit 400, a prediction score determining unit 500, an influence factor determining unit 600, a priority determining unit 700, and a product recommending unit 800;
the first set obtaining unit 100 is configured to perform obtaining of a first product set composed of products evaluated by a target user within a first time period, wherein a time interval from a latest time to a current time in the first time period is smaller than a preset interval;
the second set obtaining unit 200 is configured to perform obtaining a second product set composed of products similar to the product concerned by the target user;
the similarity determination unit 300 is configured to perform determining a similarity between each product in the second product set and each product in the first product set;
the third set obtaining unit 400 is configured to perform obtaining a third product set formed by products in the first product set of which the similarity is higher than a preset threshold;
the prediction score determining unit 500 is configured to perform the steps of obtaining the score of each product in the third product set, and determining the prediction score sum _ sim of each product in the second product set based on the score and the similaritypi；
The influence factor determining unit 600 is configured to determine an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set;
the priority determination unit 700 is configured to execute the prediction score sum _ sim of each product in the second product setpiDetermining a recommendation priority score of each product in the second product set according to the influence factor IF corresponding to each product in the second product set;
the product recommending unit 800 is configured to recommend at least one product in the second product set to the target user according to the recommendation priority score.
In some optional embodiments, in combination with the embodiment shown in fig. 2, the product recommending unit 800 includes: a fourth set obtaining unit, a union obtaining unit and a recommending unit;
the fourth set obtaining unit is configured to execute obtaining of a fourth product set formed by products recommended to the target user last time;
the union obtaining unit is configured to obtain a union of the fourth product set and the second product set;
the recommending unit is configured to recommend at least one product in the union to the target user according to the recommendation priority scores of the products in the union.
With reference to the embodiment shown in fig. 2, in some optional embodiments, the influence factor determining unit 600 is specifically configured to determine each product in the second product set as a product to be processed, and perform the following processing on each product to be processed respectively:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
With reference to the previous embodiment, in some optional embodiments, the influence factor determining unit 600 determines, based on the first number and the second number, an influence factor IF corresponding to the product to be processed, and is specifically configured to perform:
determining an influence factor IF corresponding to the product to be processed based on a formula IF ═ lgmax { efcount,1} -lgmax { wfcount,1}, wherein efcount represents the first number, wfcount represents the second number, and lg is a logarithm with a base 2.
In some optional embodiments, in combination with the embodiment shown in fig. 1, the prediction score determining unit 500 includes: a prediction score determining subunit;
the prediction score determination subunit configured to perform a prediction score determination based on a formula:
Figure BDA0002736105980000131
determining a prediction score sum-sim for each product in the second set of productspiWherein S ispiqjIs a product p of the second set of productsiProduct q of said third set of productsjSimilarity of (D), RqjIs product q of the third set of productsjI and j are product numbers, l is product q of the third set of productsjThe number of (2).
The present invention provides a storage medium for storing a program that when executed by a processor implements a product recommendation method as described in any one of the above.
As shown in fig. 3, the present invention provides an electronic device 70, wherein the electronic device 70 includes at least one processor 701, at least one memory 702 connected to the processor 701, and a bus 703; the processor 701 and the memory 702 complete communication with each other through the bus 703; the processor 701 is configured to call a program in the memory 702, where the program is at least used to implement the product recommendation method of any one of the above embodiments. The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The product recommendation device comprises a processor and a memory, wherein the first set obtaining unit 100, the second set obtaining unit 200, the similarity determining unit 300, the third set obtaining unit 400, the prediction score determining unit 500, the influence factor determining unit 600, the priority determining unit 700, the product recommendation unit 800 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, a product similarity recommendation algorithm is optimized by adjusting kernel parameters, a recent attention behavior influence factor of a client is constructed, the limitation caused by taking the similarity as a recommendation priority in the traditional real-time recommendation method is effectively improved, and the reliability and the accuracy of a recommendation result are improved. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
An embodiment of the present invention provides a storage medium having a program stored thereon, which when executed by a processor implements the product recommendation method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the product recommendation method is executed when the program runs.
The present application also provides a computer program product adapted to execute a program initialized with the steps comprised in the above-mentioned product recommendation method when executed on a data processing device.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. A method for recommending products, comprising:
obtaining a first product set formed by products evaluated by a target user in a first time period, wherein the time interval between the latest moment in the first time period and the current moment is less than a preset interval;
obtaining a second product set consisting of products similar to the product concerned by the target user;
determining the similarity of each product in the second product set and each product in the first product set respectively;
obtaining a third product set formed by products in the first product set with the similarity higher than a preset threshold;
obtaining the score of each product in the third product set, and determining the prediction score sum _ sim of each product in the second product set based on the score and the similaritypi；
Determining an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set;
passing the prediction score sum _ sim of each product in the second set of productspiDetermining a recommendation priority score of each product in the second product set according to the influence factor IF corresponding to each product in the second product set;
recommending at least one product in the second product set to the target user according to the recommendation priority score.
2. The product recommendation method of claim 1, wherein recommending at least one product of the second set of products to the target user based on a recommendation priority score comprises:
obtaining a fourth product set formed by products recommended to the target user last time;
obtaining a union of the fourth set of products and the second set of products;
recommending at least one product in the union to the target user according to the recommendation priority scores of the products in the union.
3. The product recommendation method according to claim 1, wherein the determining the influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set comprises:
determining each product in the second product set as a product to be processed, and respectively processing each product to be processed as follows:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
4. The product recommendation method according to claim 3, wherein said determining an influence factor IF corresponding to said product to be processed based on said first number and said second number comprises:
determining an influence factor IF corresponding to the product to be processed based on a formula IF ═ lgmax { efcount,1} -lgmax { wfcount,1}, wherein efcount represents the first number, wfcount represents the second number, and lg is a logarithm with a base 2.
5. The product recommendation method of claim 1, wherein the obtaining of the score of each product in the third set of products, and the determining of the predicted score sum-sim of each product in the second set of products based on the score and the similarity are performedpiThe method comprises the following steps:
based on the formula
Figure FDA0002736105970000021
Determining a prediction score sum-sim for each product in the second set of productspiWherein S ispiqjIs a product p of the second set of productsiProduct q of said third set of productsjRqj is product q of the third set of productsjI and j are product numbers, l is product q of the third set of productsjThe number of (2).
6. A product recommendation device, comprising: the system comprises a first set obtaining unit, a second set obtaining unit, a similarity determining unit, a third set obtaining unit, a prediction score determining unit, an influence factor determining unit, a priority determining unit and a product recommending unit;
the first set obtaining unit is configured to perform obtaining of a first product set formed by products evaluated by a target user in a first time period, wherein a time interval between the latest time in the first time period and the current time is smaller than a preset interval;
the second set obtaining unit is configured to execute obtaining of a second product set composed of products similar to the product concerned by the target user;
the similarity determining unit is configured to perform determination of similarity between each product in the second product set and each product in the first product set;
the third set obtaining unit is configured to perform obtaining of a third product set formed by products in the first product set with the similarity higher than a preset threshold;
the prediction score determining unit is configured to obtain a score of each product in the third product set, and determine each product in the second product set based on the score and the similarityPrediction score sum simpi；
The influence factor determining unit is configured to determine an influence factor IF corresponding to each product in the second product set based on the similarity between each product in the third product set and each product in the second product set;
the priority determination unit is configured to execute the prediction score sum _ sim of each product in the second product setpiDetermining a recommendation priority score of each product in the second product set according to the influence factor IF corresponding to each product in the second product set;
the product recommending unit is configured to recommend at least one product in the second product set to the target user according to the recommendation priority score.
7. The product recommendation device of claim 6, wherein the product recommendation unit comprises: the device comprises a first set obtaining unit, a union obtaining unit and a recommending unit;
the first set obtaining unit is configured to execute obtaining of a fourth product set formed by products recommended to the target user last time;
the union obtaining unit is configured to obtain a union of the fourth product set and the second product set;
the recommending unit is configured to recommend at least one product in the union to the target user according to the recommendation priority scores of the products in the union.
8. The product recommendation device according to claim 6, wherein the impact factor determination unit is specifically configured to perform:
determining each product in the second product set as a product to be processed, and respectively processing each product to be processed as follows:
determining a first number of similarities which are not lower than a preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, determining a second number of similarities which are lower than the preset similarity threshold in the similarities between the products to be processed and the products in the third product set respectively, and determining an influence factor IF corresponding to the products to be processed based on the first number and the second number.
9. A storage medium characterized by storing a program which when executed by a processor implements the product recommendation method of any one of claims 1 to 5.
10. An electronic device, comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke a program in the memory, the program at least being configured to implement the product recommendation method of any of claims 1-5.
CN202011134118.5A 2020-10-21 2020-10-21 Product recommendation method and device, electronic equipment and storage medium Active CN112215680B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011134118.5A CN112215680B (en) 2020-10-21 2020-10-21 Product recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011134118.5A CN112215680B (en) 2020-10-21 2020-10-21 Product recommendation method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112215680A true CN112215680A (en) 2021-01-12
CN112215680B CN112215680B (en) 2023-09-08

Family

ID=74056412

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011134118.5A Active CN112215680B (en) 2020-10-21 2020-10-21 Product recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112215680B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107256494A (en) * 2017-05-18 2017-10-17 深圳大学 A kind of item recommendation method and device
JP2018181326A (en) * 2017-04-06 2018-11-15 ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ Personalized products recommendation using deep learning
CN110413868A (en) * 2018-11-06 2019-11-05 腾讯科技（深圳）有限公司 Information recommendation method, device, system and storage medium
CN111209486A (en) * 2019-12-19 2020-05-29 杭州安恒信息技术股份有限公司 Management platform data recommendation method based on mixed recommendation rule

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018181326A (en) * 2017-04-06 2018-11-15 ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ Personalized products recommendation using deep learning
CN107256494A (en) * 2017-05-18 2017-10-17 深圳大学 A kind of item recommendation method and device
CN110413868A (en) * 2018-11-06 2019-11-05 腾讯科技（深圳）有限公司 Information recommendation method, device, system and storage medium
CN111209486A (en) * 2019-12-19 2020-05-29 杭州安恒信息技术股份有限公司 Management platform data recommendation method based on mixed recommendation rule

Also Published As

Publication number Publication date
CN112215680B (en) 2023-09-08

Similar Documents

Publication Publication Date Title
CN107563429B (en) Method and device for classifying network user groups
JP6422617B2 (en) Network access operation identification program, server, and storage medium
CN106599047B (en) Information pushing method and device
EP3279806A1 (en) Data processing method and apparatus
CN106708871B (en) Method and device for identifying social service characteristic users
CN110322281B (en) Similar user mining method and device
CN110543603B (en) Collaborative filtering recommendation method, device, equipment and medium based on user behaviors
CN110825977A (en) Data recommendation method and related equipment
CN109446402B (en) Searching method and device
CN109635953A (en) A kind of feature deriving method, device and electronic equipment
CN115238173A (en) Behavior analysis and medical service pushing method, equipment and medium based on big data
CN110874786B (en) False transaction group identification method, device and computer readable medium
CN116362823A (en) Recommendation model training method, recommendation method and recommendation device for behavior sparse scene
CN107133811A (en) The recognition methods of targeted customer a kind of and device
CN108563713B (en) Keyword rule generation method and device and electronic equipment
WO2018177303A1 (en) Media content recommendation method, device, and storage medium
CN111275071B (en) Prediction model training method, prediction device and electronic equipment
CN114581165A (en) Product recommendation method, device, computer storage medium and system
CN111723280B (en) Information processing method and device, storage medium and electronic equipment
CN109582834B (en) Data risk prediction method and device
CN110969379B (en) Screening method of substitute materials and related device
CN112215680B (en) Product recommendation method and device, electronic equipment and storage medium
CN109559245B (en) Method and device for identifying specific user
CN108154377B (en) Advertisement cheating prediction method and device
CN108093013B (en) Webpage data calculation method and server

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
GR01 Patent grant
GR01 Patent grant