CN111553763A - Article recommendation method and device, electronic equipment and readable storage medium - Google Patents
Article recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111553763A CN111553763A CN202010339576.6A CN202010339576A CN111553763A CN 111553763 A CN111553763 A CN 111553763A CN 202010339576 A CN202010339576 A CN 202010339576A CN 111553763 A CN111553763 A CN 111553763A
- Authority
- CN
- China
- Prior art keywords
- item
- article
- user
- information
- behavior information
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000013598 vector Substances 0.000 claims abstract description 147
- 230000006399 behavior Effects 0.000 claims description 141
- 238000005295 random walk Methods 0.000 claims description 21
- 238000010586 diagram Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000000875 corresponding effect Effects 0.000 description 77
- 239000002537 cosmetic Substances 0.000 description 9
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present application relates to the field of internet technologies, and in particular, to an article recommendation method and apparatus, an electronic device, and a readable storage medium. The method comprises the steps of obtaining behavior information of each user in a plurality of merchant platforms, article category information of newly added articles and article category information of corresponding articles under the behavior information, constructing article association feature vectors, article category feature vectors and article category feature vectors of the newly added articles according to the information, and determining association relations among the articles based on the article association feature vectors and the article category feature vectors; according to the item type feature vector of the item and the item type feature vector of the newly added item, the similarity between the item type information and the item type information of the newly added item is determined, and the newly added item is recommended according to the similarity and the incidence relation between the items.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to an article recommendation method and apparatus, an electronic device, and a readable storage medium.
Background
With the rapid development of the internet technology, the e-commerce platform also develops rapidly along with the development of the internet technology, and most merchants recommend new goods on shelves, discounted goods and hot-sold goods in shops to users according to the goods information and the user information in the e-commerce platform. However, as the e-commerce industry develops and data becomes huge, the requirements of each e-commerce platform on the recommendation algorithm of the e-commerce platform are higher and higher.
In a merchant platform, if user behaviors are not abundant, article recommendation is difficult to be performed on a user through the merchant platform, and data in different merchant platforms cannot be correlated, so that article recommendation cannot be performed on the user when the user behaviors are not abundant or the user behaviors do not exist for a newly opened merchant, and an effective article recommendation method is not proposed for article recommendation on the user in the merchant platform for the newly opened merchant.
Disclosure of Invention
In view of this, an object of the embodiments of the present application is to provide an item recommendation method, an item recommendation device, an electronic device, and a readable storage medium, which can provide a guidance basis for a user to recommend a new item in a merchant platform.
Mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides an item recommendation method, where the item recommendation method includes:
acquiring behavior information of each user in a plurality of merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information;
according to the association relationship between the behavior information of each user and the item type information of the corresponding item under the behavior information, an item association feature vector for expressing the similarity between items is constructed;
according to the item category information of the corresponding item under the behavior information of each user, constructing an item category feature vector of the item;
determining an association relationship between the items in the plurality of merchant platforms based on the item association feature vectors and the item category feature vectors of the items;
according to the article type information of the newly added article, constructing an article type feature vector of the newly added article;
determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added items according to the item type feature vector of the corresponding item under the behavior information of each user and the item type feature vector of the newly added items;
and recommending the newly added article based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
In a possible implementation manner, constructing an item association feature vector for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information includes:
according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information, constructing a data structure diagram of the article associated with each user and the user, wherein each user and each article are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a random walk sequence with a preset number;
calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence;
and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
In a possible implementation manner, constructing an item category feature vector of each item according to item category information of the corresponding item under the behavior information of each user includes:
extracting the article category characteristics of the corresponding articles under the behavior information of each user;
and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
In one possible embodiment, determining the association relationship between the items in the merchant platform based on the item association feature vector and the item category feature vector of each item includes:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
In a second aspect, an embodiment of the present application further provides an article recommendation device, where the article recommendation device includes:
the acquisition module is used for acquiring behavior information of each user in the multiple merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information;
the first calculation module is used for constructing an article association feature vector for expressing the similarity between articles according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information;
the second calculation module is used for constructing an article type feature vector of the article according to the article type information of the article corresponding to the behavior information of each user;
a first determination module, configured to determine association relationships between items in the multiple merchant platforms based on the item association feature vectors and item category feature vectors of the items;
the third calculation module is used for constructing an article type characteristic vector of the newly added article according to the article type information of the newly added article;
the second determining module is used for determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added items according to the item type feature vector of the item corresponding to the behavior information of each user and the item type feature vector of the newly added item;
and the recommending module is used for recommending the newly added articles based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
In a possible implementation manner, when the first calculation module is configured to construct an item association feature vector used for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information, the first calculation module is further configured to:
according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information, constructing a data structure diagram of the article associated with each user and the user, wherein each user and each article are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a random walk sequence with a preset number;
calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence;
and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
In a possible implementation manner, when the second calculation module is configured to construct the item category feature vector of each item according to the item category information of the corresponding item under the behavior information of each user, the second calculation module is further configured to:
extracting the article category characteristics of the corresponding articles under the behavior information of each user;
and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
In one possible implementation, when the first determining module is configured to determine the association relationship between the items in the multiple merchant platforms based on the item association feature vector and the item category feature vector of each item, the first determining module is further configured to:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate with each other through the bus when the electronic device is operated, and the machine-readable instructions are executed by the processor to perform the steps of the item recommendation method according to the first aspect or any one of the possible implementation manners of the first aspect.
In a fourth aspect, this embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of recommending an item described in the first aspect or any possible implementation manner of the first aspect.
The embodiment of the application provides an article recommendation method, an article recommendation device, an electronic device and a readable storage medium, wherein by acquiring behavior information of each user in a plurality of merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information are obtained, that is: behavior information generated by users when browsing and purchasing articles in a plurality of merchant platforms is obtained, and article type information of articles corresponding to each behavior information is obtained, so that articles of the same type can be associated, and article association feature vectors used for expressing similarity between the articles are constructed according to the association relationship between the behavior information of each user and the article type information of the articles corresponding to the behavior information, namely: the article a and the article c are not associated with each other, but the article a and the article c are two articles existing in two merchants, but because the article a and the article c belong to the same class of articles, the article a and the article c generate a certain association, an article association data structure diagram is generated according to the association between the articles, image feature extraction is carried out to construct an article association characteristic vector, an article category characteristic vector of the article is constructed according to the article category information of the corresponding article under the behavior information of each user, the association between the articles in the merchant platform is determined based on the article association characteristic vector and the article category characteristic vector of each article, then the article category characteristic vector of the newly added article is constructed according to the obtained article category information of the newly added article, and thus the article category characteristic vector of the corresponding article and the article category characteristic vector of the newly added article under the behavior information of each user are passed, determining the similarity between the corresponding item type information and the item type information of the newly added item under the behavior information of each user, for example: the method comprises the steps that a user A clicks an article a, purchases an article b, the article category of the article a is beautiful cosmetics, the article category of the article b is clothing, the user b clicks the article b, the user c purchases an article c, the article category of the article c is beautiful cosmetics, when an article d is newly added, the cosine value of an included angle between the article category feature vector of the article d and the article category feature vector of the article a is 1, therefore, the article a and the article c belong to the same category of articles, when a user e browses the article c, a merchant platform recommends the article b to the user e, and therefore the newly added articles are recommended based on the correlation and the similarity between article information corresponding to behavior information of each user and the newly added articles, and guiding basis is provided for recommending the newly added articles in the merchant platform.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart illustrating an item recommendation method provided by an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for constructing an item association feature vector according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram illustrating an article recommendation device according to an embodiment of the present application;
fig. 4 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
With the rapid development of the internet technology, the e-commerce platform also develops rapidly along with the development of the internet technology, and most merchants recommend new goods on shelves, discounted goods and hot-sold goods in shops to users according to the goods information and the user information in the e-commerce platform. However, as the e-commerce industry develops and data becomes huge, the requirements of each e-commerce platform on the recommendation algorithm of the e-commerce platform are higher and higher.
In a merchant platform, if user behaviors are not abundant, article recommendation is difficult to be performed on a user through the merchant platform, and data in different merchant platforms cannot be correlated, so that article recommendation cannot be performed on the user when the user behaviors are not abundant or the user behaviors do not exist for a newly opened merchant, and an effective article recommendation method is not proposed for article recommendation on the user in the merchant platform for the newly opened merchant.
For the convenience of understanding of the present application, the technical solutions provided in the present application will be described in detail below with reference to specific embodiments.
Referring to fig. 1, fig. 1 shows a flowchart of an item recommendation method provided in an embodiment of the present application, where the method includes steps S101 to S107:
s101: behavior information of each user in the multiple merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information are obtained.
In specific implementation, behavior information generated when each user browses and clicks a purchased article or adds a selected article into a shopping cart, article type information of newly added articles, and article type information of articles corresponding to each behavior information are acquired in a plurality of internet merchant platforms.
S102: and constructing an article association feature vector for expressing the similarity between the articles according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information.
In specific implementation, each user in each merchant platform is directly associated with the item browsed, clicked or purchased by the user, the items browsed, clicked or purchased by the users are associated according to categories, indirect association possibly exists between the items in different categories due to the fact that the items in different categories are purchased by the same user, and an item association feature vector used for expressing similarity between the items is constructed according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information.
S103: and according to the item category information of the corresponding item under the behavior information of each user, constructing an item category feature vector of the item.
In specific implementation, each article in the merchant platform has its own article type, which can be distinguished from other articles of different types, the article type information corresponding to the behavior information of each user is extracted, and the article type feature vector of the article is constructed according to the article type information of the article corresponding to the behavior information of each user.
S104: determining an association relationship between the items in the plurality of merchant platforms based on the item association feature vector and the item category feature vector of each item.
In specific implementation, based on the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information, an item association feature vector for representing the similarity between items is constructed, and the item category feature vector of the item is constructed according to the behavior information of each user and the item category feature of the corresponding item under the behavior information, so as to finally determine the association relationship between the items in the multiple merchant platforms.
S105: and constructing an article type feature vector of the newly added article according to the article type information of the newly added article.
In a specific implementation, the newly added articles also have article type feature information, the article type of each newly added article can uniquely represent the article type, and the article type feature vector of each newly added article is constructed according to the article type information of the newly added article.
S106: and determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added item according to the item type feature vector of the item corresponding to the behavior information of each user and the item type feature vector of the newly added item.
In specific implementation, the cosine similarity between two vectors is calculated through the article category feature vector corresponding to each user's behavior information and the article category feature vector of the newly added article, if the cosine value of the included angle between the two vectors is closer to 1, it indicates that the included angle between the two vectors is closer to 0 degree, that is, the two vectors are more similar, and if the cosine value of the included angle between the two vectors is closer to 0, it indicates that the included angle between the two vectors is closer to 180 degrees, that is, the two vectors are not similar, so that the similarity between the article category information corresponding to each user's behavior information and the article category information of the newly added article is determined through the article category feature vector of the article corresponding to each user's behavior information and the article category feature vector of the newly added article.
S107: and recommending the newly added article based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
In a specific implementation, the newly added articles are recommended according to the association relationship between the articles with the user behaviors and the similarity between the corresponding article type information and the newly added article type information under the behavior information of each user, for example, a user a clicks an article a and purchases an article b, the article a is a cosmetic, the article b is a garment, a user c purchases an article c in a shop N, and the article c is a cosmetic.
Referring to fig. 2, a flowchart of a method for constructing an item association feature vector according to an embodiment of the present application is shown, and as shown in fig. 2, the method includes steps S201 to S204, where:
s201: and constructing a data structure chart of the article related to each user and each user according to the association relationship between the behavior information of each user and the article type information of the article corresponding to the behavior information, wherein each user and each article are used as nodes of the data structure chart.
In a specific implementation, a data structure diagram of an article associated with each user and the user is constructed according to an association relationship between behavior information of each user and article type information of the corresponding article under the behavior information, for example, a user a clicks an article a in a shop M, purchases an article B, the article a is a cosmetic, the article B is a garment, a user B adds the article B to a shopping cart in the shop M, a user c browses an article c in the shop N, the article c is a cosmetic, and the user, the article and the article type in the article are used as nodes of the data structure diagram, so that the article a and the article c are associated through the article type.
S202: and uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences.
In a specific implementation, network nodes are uniformly selected by a random walk algorithm according to the data structure diagram between the user and the article, and a predetermined number of random walk sequences are generated, for example, in step S201, a sequence of user a → article a → makeup in category → article c → user c, user a → article b → clothing in category, and the like is formed between the user and the article.
S203: and calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence.
In a specific implementation, according to a predetermined number of random walk sequences generated, a conditional probability that at least two article nodes appear in the same sequence is calculated, for example, the sequence: user a → article a → category makeup → article c → user c, user a → article b → category costume, and so on, for each vertex in the sequence, the conditional probability that an article node appears in the same sequence is calculated.
S204: and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
In a specific implementation, the at least two object nodes are determined based on the probability of appearing in the same sequence, i.e.: and under the condition that the node appears, calculating the log value of the probability of other nodes in the same sequence, and updating the vector of the node by means of a random gradient descent algorithm, wherein the updated vector is the article association feature vector for representing the similarity between the articles.
In a possible implementation manner, constructing an item category feature vector of each item according to item category information of the corresponding item under the behavior information of each user includes:
step (1): and extracting the article category characteristics of the corresponding articles under the behavior information of each user.
In this step, the corresponding item under the behavior information of each user has its own item type feature, and therefore the item type features of the items are extracted, and the association between items of the same type is found by the item type features of the items.
Step (2): and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
In this step, a connection between articles of the same category is found according to the category characteristics of each article, for example, article a and article b both belong to the cosmetic category but the two articles are not in the same shop, but the connection between the two articles can be obtained through the connection of the categories, so that an article category characteristic vector of the corresponding article under each user behavior information is constructed according to the article category characteristics, and the connection relation between the articles is determined.
In one possible embodiment, determining the association relationship between the items in the merchant platform based on the item association feature vector and the item category feature vector of each item includes:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
In specific implementation, the item category feature vector of each item is used as an input parameter of an association relation function between items, and the item association feature vector is used as an output parameter of the association relation function between items to determine the association relation function between items, so as to determine the association relation between items in the merchant platform.
Referring to fig. 3, a schematic structural diagram of an article recommendation device 300 according to an embodiment of the present application is shown, where, as shown in fig. 3, the article recommendation device 300 according to the embodiment of the present application includes:
an obtaining module 310, configured to obtain behavior information of each user in multiple merchant platforms, article category information of a newly added article, and article category information of an article corresponding to each behavior information;
the first calculation module 320 is configured to construct an item association feature vector for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information;
the second calculating module 330 is configured to construct an item category feature vector of each item according to item category information of the item corresponding to the behavior information of each user;
a first determining module 340, configured to determine association relationships between the items in the multiple merchant platforms based on the item association feature vectors and the item category feature vectors of the items;
the third calculating module 350 is configured to construct an article category feature vector of the newly added article according to the article category information of the newly added article;
the second determining module 360 is configured to determine, according to the item category feature vector of the item corresponding to the behavior information of each user and the item category feature vector of the newly added item, a similarity between the item category information corresponding to the behavior information of each user and the item category information of the newly added item;
and the recommending module 370 is configured to recommend the newly added article based on the association relationship and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
In a possible implementation manner, when the first calculating module 320 is configured to construct an item association feature vector for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information, the first calculating module 320 is further configured to:
according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information, constructing a data structure diagram of the article associated with each user and the user, wherein each user and each article are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a random walk sequence with a preset number;
calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence;
and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
In a possible implementation manner, when the second calculating module 330 is configured to construct an item category feature vector of each item according to item category information of the corresponding item under the behavior information of each user, the second calculating module 330 is further configured to:
extracting the article category characteristics of the corresponding articles under the behavior information of each user;
and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
In one possible implementation, when the first determining module 340 is configured to determine the association relationship between the items in the multiple merchant platforms based on the item association feature vector and the item category feature vector of each item, the first determining module 340 is further configured to:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
Based on the same application concept, referring to fig. 4, a schematic structural diagram of an electronic device 400 provided in the embodiment of the present application includes: a processor 410, a memory 420 and a bus 430, wherein the memory 420 stores machine-readable instructions executable by the processor 410, when the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430, and the machine-readable instructions are executed by the processor 410 to perform the steps of the item recommendation method according to any one of the first embodiment and/or the second embodiment.
In particular, the machine readable instructions, when executed by the processor 410, may perform the following:
acquiring behavior information of each user in a plurality of merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information;
according to the association relationship between the behavior information of each user and the item type information of the corresponding item under the behavior information, an item association feature vector for expressing the similarity between items is constructed;
according to the item category information of the corresponding item under the behavior information of each user, constructing an item category feature vector of the item;
determining an association relationship between the items in the plurality of merchant platforms based on the item association feature vectors and the item category feature vectors of the items;
according to the article type information of the newly added article, constructing an article type feature vector of the newly added article;
determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added items according to the item type feature vector of the corresponding item under the behavior information of each user and the item type feature vector of the newly added items;
and recommending the newly added article based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
The embodiment of the application provides an article recommendation method, an article recommendation device, an electronic device and a readable storage medium, wherein by acquiring behavior information of each user in a plurality of merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information are obtained, that is: behavior information generated by users when browsing and purchasing articles in a plurality of merchant platforms is obtained, and article type information of articles corresponding to each behavior information is obtained, so that articles of the same type can be associated, and article association feature vectors used for expressing similarity between the articles are constructed according to the association relationship between the behavior information of each user and the article type information of the articles corresponding to the behavior information, namely: the article a and the article c are not associated with each other, but the article a and the article c are two articles existing in two merchants, but because the article a and the article c belong to the same class of articles, the article a and the article c generate a certain association, an article association data structure diagram is generated according to the association between the articles, image feature extraction is carried out to construct an article association characteristic vector, an article category characteristic vector of the article is constructed according to the article category information of the corresponding article under the behavior information of each user, the association between the articles in the merchant platform is determined based on the article association characteristic vector and the article category characteristic vector of each article, then the article category characteristic vector of the newly added article is constructed according to the obtained article category information of the newly added article, and thus the article category characteristic vector of the corresponding article and the article category characteristic vector of the newly added article under the behavior information of each user are passed, determining the similarity between the corresponding item type information and the item type information of the newly added item under the behavior information of each user, for example: the method comprises the steps that a user A clicks an article a, purchases an article b, the article category of the article a is beautiful cosmetics, the article category of the article b is clothing, the user b clicks the article b, the user c purchases an article c, the article category of the article c is beautiful cosmetics, when an article d is newly added, the cosine value of an included angle between the article category feature vector of the article d and the article category feature vector of the article a is 1, therefore, the article a and the article c belong to the same category of articles, when a user e browses the article c, a merchant platform recommends the article b to the user e, and therefore the newly added articles are recommended based on the correlation and the similarity between article information corresponding to behavior information of each user and the newly added articles, and guiding basis is provided for recommending the newly added articles in the merchant platform.
Based on the same application concept, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of an item recommendation method according to any one of the foregoing embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An item recommendation method, characterized in that the item recommendation method comprises:
acquiring behavior information of each user in a plurality of merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information;
according to the association relationship between the behavior information of each user and the item type information of the corresponding item under the behavior information, an item association feature vector for expressing the similarity between items is constructed;
according to the item category information of the corresponding item under the behavior information of each user, constructing an item category feature vector of the item;
determining an association relationship between the items in the plurality of merchant platforms based on the item association feature vectors and the item category feature vectors of the items;
according to the article type information of the newly added article, constructing an article type feature vector of the newly added article;
determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added items according to the item type feature vector of the corresponding item under the behavior information of each user and the item type feature vector of the newly added items;
and recommending the newly added article based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
2. The item recommendation method according to claim 1, wherein constructing an item association feature vector for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information comprises:
according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information, constructing a data structure diagram of the article associated with each user and the user, wherein each user and each article are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a random walk sequence with a preset number;
calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence;
and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
3. The item recommendation method according to claim 1, wherein constructing the item category feature vector of each item according to the item category information of the corresponding item under the behavior information of each user comprises:
extracting the article category characteristics of the corresponding articles under the behavior information of each user;
and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
4. The item recommendation method according to claim 1, wherein determining the association relationship between the items in the merchant platform based on the item association feature vector and the item category feature vector of each item comprises:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
5. An item recommendation device, characterized in that the item recommendation device comprises:
the acquisition module is used for acquiring behavior information of each user in the multiple merchant platforms, article type information of newly added articles and article type information of articles corresponding to each behavior information;
the first calculation module is used for constructing an article association feature vector for expressing the similarity between articles according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information;
the second calculation module is used for constructing an article type feature vector of the article according to the article type information of the article corresponding to the behavior information of each user;
a first determination module, configured to determine association relationships between items in the multiple merchant platforms based on the item association feature vectors and item category feature vectors of the items;
the third calculation module is used for constructing an article type characteristic vector of the newly added article according to the article type information of the newly added article;
the second determining module is used for determining the similarity between the item type information corresponding to the behavior information of each user and the item type information of the newly added items according to the item type feature vector of the item corresponding to the behavior information of each user and the item type feature vector of the newly added item;
and the recommending module is used for recommending the newly added articles based on the incidence relation and the similarity between the article type information corresponding to the behavior information of each user and the newly added article type information.
6. The item recommendation device according to claim 5, wherein when the first calculation module is configured to construct an item association feature vector for representing similarity between items according to the association relationship between the behavior information of each user and the item category information of the corresponding item under the behavior information, the first calculation module is further configured to:
according to the association relationship between the behavior information of each user and the article type information of the corresponding article under the behavior information, constructing a data structure diagram of the article associated with each user and the user, wherein each user and each article are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a random walk sequence with a preset number;
calculating the probability of the appearance of at least two article nodes in the same sequence according to the random walk sequence;
and calculating an article association feature vector for representing the similarity between the articles according to the probability of the at least two article nodes appearing in the same sequence.
7. The item recommendation device according to claim 5, wherein the second calculation module, when configured to construct the item category feature vector of each item according to the item category information of the corresponding item under the behavior information of each user, is further configured to:
extracting the article category characteristics of the corresponding articles under the behavior information of each user;
and according to the item category characteristics, constructing an item category characteristic vector of the corresponding item under each user behavior information.
8. The item recommendation device of claim 5, wherein the first determination module, when configured to determine the association relationship between the items in the plurality of merchant platforms based on the item association feature vector and the item category feature vector of each item, is further configured to:
and taking the item category characteristic vector of each item as an input parameter of an association relation function between the items, and taking the item association characteristic vector as an output parameter of the association relation function between the items so as to determine the association relation between the items in the merchant platform.
9. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when a computer device is running, the machine-readable instructions when executed by the processor performing the steps of the item recommendation method according to any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the item recommendation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010339576.6A CN111553763B (en) | 2020-04-26 | 2020-04-26 | Article recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010339576.6A CN111553763B (en) | 2020-04-26 | 2020-04-26 | Article recommendation method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553763A true CN111553763A (en) | 2020-08-18 |
| CN111553763B CN111553763B (en) | 2023-03-24 |
Family
ID=72000308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010339576.6A Active CN111553763B (en) | 2020-04-26 | 2020-04-26 | Article recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553763B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669083A (en) * | 2020-12-30 | 2021-04-16 | 杭州趣链科技有限公司 | Commodity recommendation method and device and electronic equipment |
| CN113742532A (en) * | 2021-03-09 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | User portrayal method, device and computer readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956146A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Article information recommending method and device |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN109241449A (en) * | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
| US20190205965A1 (en) * | 2017-12-29 | 2019-07-04 | Samsung Electronics Co., Ltd. | Method and apparatus for recommending customer item based on visual information |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN110162693A (en) * | 2019-03-04 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method and server of information recommendation |
| CN110162689A (en) * | 2018-05-10 | 2019-08-23 | 腾讯科技（北京）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110162700A (en) * | 2019-04-23 | 2019-08-23 | 腾讯科技（深圳）有限公司 | The training method of information recommendation and model, device, equipment and storage medium |
| CN110175895A (en) * | 2019-05-31 | 2019-08-27 | 京东方科技集团股份有限公司 | A kind of item recommendation method and device |
| CN110232152A (en) * | 2019-05-27 | 2019-09-13 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, server and storage medium |
| CN110827129A (en) * | 2019-11-27 | 2020-02-21 | 中国联合网络通信集团有限公司 | Commodity recommendation method and device |
-
2020
- 2020-04-26 CN CN202010339576.6A patent/CN111553763B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956146A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Article information recommending method and device |
| CN108960945A (en) * | 2017-05-18 | 2018-12-07 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and device |
| US20190205965A1 (en) * | 2017-12-29 | 2019-07-04 | Samsung Electronics Co., Ltd. | Method and apparatus for recommending customer item based on visual information |
| CN110162689A (en) * | 2018-05-10 | 2019-08-23 | 腾讯科技（北京）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109241449A (en) * | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
| CN109242649A (en) * | 2018-10-31 | 2019-01-18 | 广州品唯软件有限公司 | A kind of Method of Commodity Recommendation and relevant apparatus |
| CN110162693A (en) * | 2019-03-04 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method and server of information recommendation |
| CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
| CN110162700A (en) * | 2019-04-23 | 2019-08-23 | 腾讯科技（深圳）有限公司 | The training method of information recommendation and model, device, equipment and storage medium |
| CN110232152A (en) * | 2019-05-27 | 2019-09-13 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, server and storage medium |
| CN110175895A (en) * | 2019-05-31 | 2019-08-27 | 京东方科技集团股份有限公司 | A kind of item recommendation method and device |
| CN110827129A (en) * | 2019-11-27 | 2020-02-21 | 中国联合网络通信集团有限公司 | Commodity recommendation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669083A (en) * | 2020-12-30 | 2021-04-16 | 杭州趣链科技有限公司 | Commodity recommendation method and device and electronic equipment |
| CN113742532A (en) * | 2021-03-09 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | User portrayal method, device and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553763B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111292164B (en) | Commodity recommendation method and device, electronic equipment and readable storage medium | |
| CN108898459B (en) | Commodity recommendation method and device | |
| US10580057B2 (en) | Photorealistic recommendation of clothing and apparel based on detected web browser input and content tag analysis | |
| CN108960992A (en) | A kind of information recommendation method and relevant device | |
| CN109191240A (en) | A kind of method and apparatus carrying out commercial product recommending | |
| CN111553763B (en) | Article recommendation method and device, electronic equipment and readable storage medium | |
| CN106055710A (en) | Video-based commodity recommendation method and device | |
| JPH1115842A (en) | Data mining device | |
| CN103377193A (en) | Information providing method, webpage server and webpage browser | |
| JP2018018136A (en) | Electronic commercial transaction system | |
| CN111612585A (en) | Virtual resource distribution method and device | |
| CN111125376A (en) | Knowledge graph generation method and device, data processing equipment and storage medium | |
| US9799065B1 (en) | Associating items based at least in part on physical location information | |
| CN108596712B (en) | Single-class collaborative filtering method based on article sequence, storage medium and server | |
| KR102319997B1 (en) | Machine learning based clothing fit recommending apparatus | |
| CA3138745A1 (en) | Method and device for circling and creating target population | |
| CN107967637B (en) | Commodity object model recommendation method and device and electronic equipment | |
| CN115641179A (en) | Information pushing method and device and electronic equipment | |
| KR102260401B1 (en) | Apparatus and Method for Providing Product information | |
| CN111209925A (en) | Gender prediction method, device and computer-readable storage medium | |
| CN113763079A (en) | Information pushing method and device and storage medium | |
| CN115239413A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
| US20130332320A1 (en) | Virtual reality-based environments including user avatars | |
| KR102023275B1 (en) | Product recommendation method using fp growth | |
| CN112419078A (en) | Product recommendation method and device and electronic equipment |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231201 Address after: 200,030 Unit 5B03, Floor 5, Building 2, No. 277, Longlan Road, Xuhui District, Shanghai Patentee after: SHANGHAI SECOND PICKET NETWORK TECHNOLOGY CO.,LTD. Address before: Floors 4, 5 and 6, No. 3, Lane 1473, Zhenguang Road, Putuo District, Shanghai, 200333 Patentee before: Shanghai Fengzhi Technology Co.,Ltd. |