CN110889748B - Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium - Google Patents

Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium Download PDF

Info

Publication number
CN110889748B
CN110889748B CN201911215604.7A CN201911215604A CN110889748B CN 110889748 B CN110889748 B CN 110889748B CN 201911215604 A CN201911215604 A CN 201911215604A CN 110889748 B CN110889748 B CN 110889748B
Authority
CN
China
Prior art keywords
user
data
commodity
platform product
product recommendation
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.)
Active
Application number
CN201911215604.7A
Other languages
Chinese (zh)
Other versions
CN110889748A (en
Inventor
郭晋良
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.)
Guangzhou Yidejia Network Technology Co ltd
Original Assignee
Guangzhou Yidejia Network Technology Co 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 Guangzhou Yidejia Network Technology Co ltd filed Critical Guangzhou Yidejia Network Technology Co ltd
Priority to CN201911215604.7A priority Critical patent/CN110889748B/en
Publication of CN110889748A publication Critical patent/CN110889748A/en
Application granted granted Critical
Publication of CN110889748B publication Critical patent/CN110889748B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to the technical field of computer technology, in particular to a shop platform product recommending method, a device, computer equipment and a storage medium, wherein the shop platform product recommending method comprises the following steps: s10: acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log; s20: extracting user characteristic data from the user behavior data, and establishing a user characteristic vector according to the user characteristic data; s30: acquiring an item data set to be recommended according to the user feature vector; s40: and filtering the data set of the articles to be recommended to obtain a corresponding recommendation result. The method and the device have the effects of recommending related commodities to the new user and improving the use experience of the user.

Description

Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and apparatus for recommending a product on a store platform, a computer device, and a storage medium.
Background
Cold start refers to the process of transitioning from a target user to a seed user at the beginning of the product. In the process, the possible states of the product have imperfect functions, a product testing period and a product online period (release period), a wavelet vermicelli is needed to be found to be a user of the product or the vermicelli, and then the mode of the Ethernet burst is increased through the cold-started vermicelli.
The conventional recommendation algorithm in the market at present aims at solving the problem that a user makes a selection of a cardiometer in mass commodities. Such as: "what goods should be recommended to a new user for him, how to complete a cold start? What is the commodity that the user needs? How do "and" do it to push things? "etc., therefore, when a new user enters, there is room for improvement because it is difficult to recommend an appropriate commodity to the new user because there is no relevant history data.
Disclosure of Invention
The application aims to provide a store platform product recommending method, a store platform product recommending device, computer equipment and a storage medium, wherein the store platform product recommending method, the store platform product recommending device, the computer equipment and the storage medium can recommend related commodities to a new user and improve the use experience of the user.
The first object of the present application is achieved by the following technical solutions:
a store platform product recommendation method, the store platform product recommendation method comprising:
s10: acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log;
s20: extracting user characteristic data from the user behavior data, and establishing a user characteristic vector according to the user characteristic data;
s30: acquiring an item data set to be recommended according to the user feature vector;
s40: and filtering the data set of the articles to be recommended to obtain a corresponding recommendation result.
By adopting the technical scheme, when a new user enters, the user characteristic data is built by acquiring the user behavior data of the user and the filled user attribute data, so that the user characteristic vector can be quickly built according to the user attribute data of the user, meanwhile, after the article data set to be recommended is built according to the user characteristic vector, a final recommendation result is generated after filtering, and the credibility of the recommendation result can be improved.
The application is further provided with: step S20 includes:
s21: acquiring user query data from the user behavior data;
s22: according to the user query data, calculating the association degree of the user query data corresponding to the user attribute data as user interestingness data;
s23: and establishing the user characteristic vector according to the user interest degree data and the user attribute data.
By adopting the technical scheme, the user characteristic vector related to the interests of the user can be established by combining the user behavior data of the user and the attribute data of the user, so that the subsequent recommendation of commodities to the user is facilitated.
The application is further provided with: step S30 includes:
s31: acquiring commodity characteristic values;
s32: and comparing the commodity characteristic value with the user characteristic vector, and generating the article data set to be recommended according to a comparison result.
By adopting the technical scheme, the characteristic value of the commodity can be used and compared with the built user characteristic vector by acquiring the characteristic value of the commodity, so that the commodity meeting the user interests and attributes can be recommended to the user.
The application is further provided with: after step S40, the shop platform product recommendation method further includes:
s50: acquiring a user purchase record;
s60: and after the user purchase record is associated with the recommendation result, storing the user purchase record into a preset database.
By adopting the technical scheme, after the user purchases the commodity, the user purchase record is associated with the recommendation result, firstly the data of the user behavior can be stored, and further the interest data of the user can be updated, secondly the comparison between the user purchase record and the final recommendation result can be facilitated, and further the recommendation algorithm can be updated according to the comparison result.
The application is further provided with: after step S50, the shop platform product recommendation method further includes:
s51: acquiring the user feature vector;
s52: and updating the user characteristic vector according to the user purchase record.
By adopting the technical scheme, the user feature vector of the user is updated continuously, so that the user feature vector is more in line with the interests and the attributes of the user, and the recommended commodity is more in line with the current attributes of the user when the commodity is recommended to the user later.
The second object of the present application is achieved by the following technical solutions:
a store platform product recommendation device, the store platform product recommendation device comprising:
the log acquisition module is used for acquiring a user behavior log and establishing user behavior data and user attribute data according to the user behavior log;
the vector building module is used for extracting user characteristic data from the user behavior data and building user characteristic vectors according to the user characteristic data;
the initial recommendation module is used for acquiring an item data set to be recommended according to the user feature vector;
and the main recommendation module is used for filtering the data set of the articles to be recommended to obtain a corresponding recommendation result.
By adopting the technical scheme, when a new user enters, the user characteristic data is built by acquiring the user behavior data of the user and the filled user attribute data, so that the user characteristic vector can be quickly built according to the user attribute data of the user, meanwhile, after the article data set to be recommended is built according to the user characteristic vector, a final recommendation result is generated after filtering, and the credibility of the recommendation result can be improved.
The third object of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the store platform product recommendation method described above when the computer program is executed.
The fourth object of the present application is achieved by the following technical solutions:
a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the store platform product recommendation method described above.
In summary, the beneficial technical effects of the application are as follows:
when a new user enters, user behavior data of the user and filled user attribute data are obtained, and then user feature data are established, so that user feature vectors can be established rapidly according to the user attribute data of the user, meanwhile, after the item data set to be recommended is constructed according to the user feature vectors, a final recommendation result is generated after filtering, and the credibility of the recommendation result can be improved.
Drawings
FIG. 1 is a flow chart of a method for recommending products on a store platform according to an embodiment of the application;
FIG. 2 is a flowchart showing an implementation of step S20 in a product recommendation method for a store platform according to an embodiment of the present application;
FIG. 3 is a flowchart showing an implementation of step S30 in a product recommendation method for a store platform according to an embodiment of the present application;
FIG. 4 is another flow chart of a method for recommending products on a store platform in accordance with an embodiment of the present application;
FIG. 5 is another flow chart of a method for recommending products on a store platform in accordance with an embodiment of the present application;
FIG. 6 is a schematic block diagram of a store platform product recommendation device in accordance with an embodiment of the present application;
FIG. 7 is a schematic diagram of a computer device in accordance with an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
Embodiment one:
in an embodiment, as shown in fig. 1, the application discloses a method for recommending a product of a store platform, which specifically comprises the following steps: s10: and acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log.
In this embodiment, the user behavior log refers to a data table that records, according to a time period, for example, daily, the unique identification and characteristics of the user to which each user operates on the e-commerce platform. The user behavior data refers to data of behavior of a user operating on the electronic commerce platform. The user behavior data comprise the manners of searching, inquiring, purchasing and the like of the commodity on the electronic commerce platform by a user, wherein the manners of searching for the commodity are inquired, such as clicking a link of the commodity, or inputting keywords in a search box. The user attribute data is data indicating personal attributes that identify the user. For example, the user attribute data may be age, gender, occupation, etc. data of the user.
Specifically, when a new user operates in the electronic commerce platform for the first time, user behavior data of the user is recorded, and the user behavior data is associated with user attribute data of the user. The user attribute data may be obtained by letting the user fill out or select at the registration page when the user registers. Or when the user enters the electronic commerce platform, the client of the electronic commerce platform does not detect the automatic login information of the user account, the page for enabling the user to select and/or fill in the attribute information is automatically shot out from the page, and temporary user attribute data of the user are obtained after the user selects and/or fills in the attribute information.
Further, the user attribute data and the user behavior data are composed into the user behavior log.
Preferably, if the new user enters the electronic commerce platform without selecting and/or filling attribute information or pre-registering an account, the user behavior data of the operation of the new user can be pre-recorded by establishing a temporary account, if the user selects to purchase goods, the user is prompted to register the account, further the user attribute data is acquired, and the user attribute data is associated with the user behavior data of the temporary account to be used as a basis for recommending goods to the user subsequently.
S20: user feature data is extracted from the user behavior data, and a user feature vector is established according to the user feature data.
In this embodiment, the user feature data refers to data of features of the user identified by the user. The user feature vector refers to data for reflecting the interests of the user.
Specifically, by counting specific operation behaviors of each type from the user behavior data, based on the operation behaviors of each type, such as search, click, purchase, and the like, as the user feature data. And further counting the types of the commodities interested by the user, and further supervising the user feature vector.
S30: and acquiring a data set of the articles to be recommended according to the user characteristic vector.
In the present embodiment, the item data set to be recommended refers to a set of items to be recommended to the user.
Specifically, by acquiring the characteristics of the attributes of the commodity, such as the class, function, brand and other attributes of the commodity, the characteristic vector of the commodity is compared with the characteristic vector of the user, and then the data set of the commodity to be recommended, which is closest to the characteristic vector of the user, is used as the data set of the commodity to be recommended.
S40: and filtering the item data set to be recommended to obtain a corresponding recommendation result.
In this embodiment, the recommended result refers to a result of a commodity that is finally recommended to the user.
Specifically, according to the use of each commodity in the to-be-recommended commodity data set, a corresponding recommendation reason is generated, so that a user can compare commodities in the recommendation result from the recommendation reason, and meanwhile, the commodities in the to-be-recommended commodity data set can be screened and ranked by combining the evaluation and use experience of other users on the commodities.
In this embodiment, when a new user enters, the user behavior data of the user and the filled user attribute data are obtained, so that the user feature data are further established, so that a user feature vector can be quickly established according to the user attribute data of the user, meanwhile, after the to-be-recommended article data set is constructed according to the user feature vector, a final recommendation result is generated after filtering, and the credibility of the recommendation result can be improved.
In one embodiment, as shown in fig. 2, in step S20, user feature data is extracted from user behavior data, and a user feature vector is established according to the user feature data, which specifically includes the following steps:
s21: user query data is obtained from the user behavior data.
In this embodiment, the user query data refers to data of a user querying a commodity in an e-commerce platform.
Specifically, according to the user behavior data, the names and categories of the checked commodities are acquired from the commodities clicked and checked by the user, and the commodity types corresponding to the keywords/words are acquired from the search keywords/words input by the user.
Further, the user query data is composed from the name and category of the commodity, and the commodity category.
S22: and calculating the association degree of the user query data and the user attribute data according to the user query data, and taking the association degree as user interest degree data.
In this embodiment, the user interest level data refers to the degree of interest of the user in the category of the commodity.
Specifically, the association degree of the user query data corresponding to the user attribute data can be calculated through the following formula:
where i= … N is the label of the commodity in the class c of the commodity, m ci Association between category c of the article and tag i (which may be simply referred to as 1), and n ui The weight value of tag i, referring to user u, n when the user does not have this tag ui ＝0，q c Referring to the quality of category c of the good, the user's click rate (click/pv) of category c of the good may be used to indicate.
Further, r is calculated uc As the user interest level data.
S23: and establishing the user characteristic vector according to the user interest degree data and the user attribute data.
Specifically, the type of commodity and the user attribute data of the user are taken as user characteristics, and then the user characteristic vector is managed.
In one embodiment, as shown in fig. 3, in step S30, a data set of the item to be recommended is obtained according to the user feature vector, which specifically includes the following steps:
s31: and acquiring commodity characteristic values.
In the present embodiment, the commodity feature value refers to the attribute feature of the commodity in the type of the commodity.
Specifically, the method combines manual labeling and automatic machine labeling, wherein the automatic machine labeling realizes labeling of the commodity by adopting Word segmentation and Word2 Vec. For automatic machine labeling, a machine learning related algorithm needs to be adopted to realize, namely, for a series of given labels, a plurality of labels with highest matching degree are selected from the content. The tag is taken as a user characteristic value.
S32: and comparing the commodity characteristic value with the user characteristic vector, and generating an article data set to be recommended according to the comparison result.
Specifically, due to different properties and usage scenarios of different types of commodities, corresponding recommendation algorithms can be preset according to different businesses, namely different types of each commodity, so that the recommendation algorithm corresponding to each type of commodity can recommend the commodity of the type.
Further, a corresponding recommendation algorithm is adopted, commodity characteristic values and user characteristic vectors are compared, and an article data set to be recommended is generated according to the comparison result.
In one embodiment, as shown in fig. 4, after step S40, the shop platform product recommendation method further includes: s50: and acquiring a user purchase record.
In this embodiment, the user purchase record refers to a record of purchasing a commodity after the user acquires the recommendation result.
Specifically, after the recommendation result is sent to the user, if the user purchases the commodity, the information of the commodity purchased by the user is used as the user purchase record. The information of the commodity may correspond to the commodity feature value, including the name, type, purpose, etc. of the commodity.
S60: and after associating the user purchase record with the recommendation result, storing the user purchase record into a preset database.
Specifically, after the user purchase record is associated with the recommendation result, the user purchase record is stored in a preset database and is used for subsequent analysis and optimization of a corresponding recommendation algorithm.
In one embodiment, as shown in fig. 5, after step S50, the shop platform product recommendation method further includes: s51: and obtaining the user characteristic vector.
Specifically, after the user purchase record is acquired, the user feature vector is acquired.
S52: and updating the user characteristic vector according to the user purchase record.
Specifically, information of the commodity purchased by the user is acquired from the user purchase record, and the characteristics of the information of the commodity are updated to the user characteristics, so that the user characteristic vector is updated.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
Embodiment two:
in one embodiment, a shop platform product recommendation device is provided, where the shop platform product recommendation device corresponds to the shop platform product recommendation method in the above embodiment one by one. As shown in fig. 6, the shop platform product recommendation device includes a log acquisition module 10, a vector construction module 20, a primary recommendation module 30, and a primary recommendation module 40. The functional modules are described in detail as follows:
the log obtaining module 10 is configured to obtain a user behavior log, and establish user behavior data and user attribute data according to the user behavior log;
the vector construction module 20 is configured to extract user feature data from the user behavior data, and construct a user feature vector according to the user feature data;
the initial recommendation module 30 is configured to obtain an item data set to be recommended according to the user feature vector;
the main recommendation module 40 is configured to filter the item data set to be recommended to obtain a corresponding recommendation result.
Preferably, the vector construction module 20 comprises:
a data acquisition sub-module 21 for acquiring user query data from the user behavior data;
a calculating sub-module 22, configured to calculate, according to the user query data, a degree of association corresponding to the user query data and the user attribute data, as user interest degree data;
the vector construction sub-module 23 is configured to construct a user feature vector according to the user interest data and the user attribute data.
Preferably, the primary recommendation module 30 includes:
a commodity feature acquisition sub-module 31 for acquiring commodity feature values;
the comparison sub-module 32 is configured to compare the commodity feature value with the user feature vector, and generate an item data set to be recommended according to the comparison result.
Preferably, the store platform product recommendation device further comprises:
a purchase record acquiring module 50 for acquiring a user purchase record;
and the association storage module 60 is used for associating the user purchase record with the recommendation result and storing the user purchase record into a preset database.
Preferably, the store platform product recommendation device further comprises:
a vector acquisition module 51, configured to acquire a user feature vector;
the vector updating module 52 is configured to update the user feature vector according to the user purchase record. For specific limitations on the store platform product recommendation device, reference may be made to the above limitation on the store platform product recommendation method, and no further description is given here. The various modules in the store platform product recommendation device described above may be implemented in whole or in part by software, hardware, and combinations 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.
Embodiment III:
in one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing user feature vectors, user purchase records, and user attribute data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a store platform product recommendation method.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
s10: acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log;
s20: extracting user characteristic data from the user behavior data, and establishing a user characteristic vector according to the user characteristic data;
s30: acquiring an item data set to be recommended according to the user feature vector;
s40: and filtering the item data set to be recommended to obtain a corresponding recommendation result.
Embodiment four:
in one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log;
s20: extracting user characteristic data from the user behavior data, and establishing a user characteristic vector according to the user characteristic data;
s30: acquiring an item data set to be recommended according to the user feature vector;
s40: and filtering the item data set to be recommended to obtain a corresponding recommendation result.
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, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims (8)

1. A store platform product recommendation method, characterized in that the store platform product recommendation method comprises:
s10: acquiring a user behavior log, and establishing user behavior data and user attribute data according to the user behavior log;
s20: extracting user feature data from the user behavior data, and establishing a user feature vector according to the user feature data, wherein step S20 includes:
s21: acquiring user query data from the user behavior data;
s22: according to the user query data, calculating the association degree of the user query data and the user attribute data, wherein the association degree is used as user interest degree data, specifically, the association degree of the user query data of the user corresponding to the user attribute data is calculated through the following formula:
where i= … N is a label of the commodity in the class c of the commodity, m ci Association degree between category c and label i of the indicated commodity, n ui The weight value of tag i, referring to user u, n when the user does not have this tag ui ＝0，q c Refers to the quality of the category c of the commodity, and is represented by the click rate of the user on the category c of the commodity;
further, r is calculated uc As the user interest level data;
s23: establishing the user feature vector according to the user interest degree data and the user attribute data;
s30: acquiring an item data set to be recommended according to the user feature vector;
s40: and filtering the data set of the articles to be recommended to obtain a corresponding recommendation result.
2. The store platform product recommendation method of claim 1, wherein step S30 comprises:
s31: acquiring commodity characteristic values;
s32: and comparing the commodity characteristic value with the user characteristic vector, and generating the article data set to be recommended according to a comparison result.
3. The store platform product recommendation method of claim 1, wherein after step S40, the store platform product recommendation method further comprises:
s50: acquiring a user purchase record;
s60: and after the user purchase record is associated with the recommendation result, storing the user purchase record into a preset database.
4. The store platform product recommendation method of claim 3, wherein after step S50, the store platform product recommendation method further comprises:
s51: acquiring the user feature vector;
s52: and updating the user characteristic vector according to the user purchase record.
5. A store platform product recommendation device, characterized in that the store platform product recommendation device comprises:
the log acquisition module is used for acquiring a user behavior log and establishing user behavior data and user attribute data according to the user behavior log;
the vector construction module is used for extracting user characteristic data from the user behavior data and constructing a user characteristic vector according to the user characteristic data, and comprises:
the data acquisition sub-module is used for acquiring user query data from the user behavior data;
the computing sub-module is used for computing the association degree of the user query data and the user attribute data according to the user query data, and the association degree is used as user interest degree data, specifically, the association degree of the user query data queried by the user corresponding to the user attribute data is computed through the following formula:
where i= … N is a label of the commodity in the class c of the commodity, m ci Association degree between category c and label i of the indicated commodity, n ui The weight value of tag i, referring to user u, n when the user does not have this tag ui ＝0，q c Refers to the quality of the category c of the commodity, and is represented by the click rate of the user on the category c of the commodity;
further, r is calculated uc As the user interest level data;
the vector building sub-module is used for building the user feature vector according to the user interest degree data and the user attribute data;
the initial recommendation module is used for acquiring an item data set to be recommended according to the user feature vector;
and the main recommendation module is used for filtering the data set of the articles to be recommended to obtain a corresponding recommendation result.
6. The store platform product recommendation device of claim 5, wherein the initial recommendation module comprises:
the commodity characteristic obtaining sub-module is used for obtaining commodity characteristic values;
and the comparison sub-module is used for comparing the commodity characteristic value with the user characteristic vector and generating the data set of the article to be recommended according to the comparison result.
7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the store platform product recommendation method according to any one of claims 1 to 4 when the computer program is executed.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the store platform product recommendation method according to any one of claims 1 to 4.
CN201911215604.7A 2019-12-02 2019-12-02 Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium Active CN110889748B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911215604.7A CN110889748B (en) 2019-12-02 2019-12-02 Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911215604.7A CN110889748B (en) 2019-12-02 2019-12-02 Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN110889748A CN110889748A (en) 2020-03-17
CN110889748B true CN110889748B (en) 2023-08-15

Family

ID=69749991

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911215604.7A Active CN110889748B (en) 2019-12-02 2019-12-02 Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110889748B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833146B (en) * 2020-07-03 2023-08-11 深圳爱巧网络有限公司 Snack commodity recommendation method, snack commodity recommendation device, computer equipment and storage medium
CN111899047A (en) * 2020-07-14 2020-11-06 拉扎斯网络科技（上海）有限公司 Resource recommendation method and device, computer equipment and computer-readable storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7720720B1 (en) * 2004-08-05 2010-05-18 Versata Development Group, Inc. System and method for generating effective recommendations
CN108205768A (en) * 2016-12-20 2018-06-26 百度在线网络技术（北京）有限公司 Database building method and data recommendation method and device, equipment and storage medium
CN108648049A (en) * 2018-05-03 2018-10-12 中国科学技术大学 A kind of sequence of recommendation method based on user behavior difference modeling
CN109102127A (en) * 2018-08-31 2018-12-28 杭州贝购科技有限公司 Method of Commodity Recommendation and device
CN110147502A (en) * 2019-04-12 2019-08-20 平安科技（深圳）有限公司 Products Show method, apparatus, medium and server based on big data analysis
CN110415091A (en) * 2019-08-06 2019-11-05 重庆仙桃前沿消费行为大数据有限公司 Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160078520A1 (en) * 2014-09-12 2016-03-17 Microsoft Corporation Modified matrix factorization of content-based model for recommendation system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7720720B1 (en) * 2004-08-05 2010-05-18 Versata Development Group, Inc. System and method for generating effective recommendations
CN108205768A (en) * 2016-12-20 2018-06-26 百度在线网络技术（北京）有限公司 Database building method and data recommendation method and device, equipment and storage medium
CN108648049A (en) * 2018-05-03 2018-10-12 中国科学技术大学 A kind of sequence of recommendation method based on user behavior difference modeling
CN109102127A (en) * 2018-08-31 2018-12-28 杭州贝购科技有限公司 Method of Commodity Recommendation and device
CN110147502A (en) * 2019-04-12 2019-08-20 平安科技（深圳）有限公司 Products Show method, apparatus, medium and server based on big data analysis
CN110415091A (en) * 2019-08-06 2019-11-05 重庆仙桃前沿消费行为大数据有限公司 Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing

Also Published As

Publication number Publication date
CN110889748A (en) 2020-03-17

Similar Documents

Publication Publication Date Title
CN108898459B (en) Commodity recommendation method and device
CN105989004B (en) Information delivery preprocessing method and device
CN109300003B (en) Enterprise recommendation method, enterprise recommendation device, computer equipment and storage medium
CN108985830B (en) Recommendation scoring method and device based on heterogeneous information network
US20190156395A1 (en) System and Method for Analyzing and Searching for Features Associated with Objects
CN106557480B (en) Method and device for realizing query rewriting
CN105469263A (en) Commodity recommendation method and device
CN110008397B (en) Recommendation model training method and device
US20120296900A1 (en) Adaptively learning a similarity model
US20140278778A1 (en) Method, apparatus, and computer-readable medium for predicting sales volume
CN108596695B (en) Entity pushing method and system
CN107633416B (en) Method, device and system for recommending service object
US20120296776A1 (en) Adaptive interactive search
CN110135943B (en) Product recommendation method, device, computer equipment and storage medium
CN111400345A (en) Commodity searching method and device supporting multiple platforms
CN110598118A (en) Resource object recommendation method and device and computer readable medium
CN111753158A (en) Live broadcast platform commodity searching method and device, computer equipment and storage medium
CN110889748B (en) Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium
US20170316100A1 (en) Retrieval of Content Using Link-Based Search
CN111680213B (en) Information recommendation method, data processing method and device
CN108647986B (en) Target user determination method and device and electronic equipment
CN115641179A (en) Information pushing method and device and electronic equipment
CN113220974A (en) Click rate prediction model training and search recall method, device, equipment and medium
CN113112336A (en) Commodity information processing method and device and computer equipment
CN116501979A (en) Information recommendation method, information recommendation device, computer equipment and computer readable storage medium

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