CN111292164B - Commodity recommendation method and device, electronic equipment and readable storage medium - Google Patents
Commodity recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111292164B CN111292164B CN202010072430.XA CN202010072430A CN111292164B CN 111292164 B CN111292164 B CN 111292164B CN 202010072430 A CN202010072430 A CN 202010072430A CN 111292164 B CN111292164 B CN 111292164B
- Authority
- CN
- China
- Prior art keywords
- commodity
- information
- user
- attribute
- commodities
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims abstract description 134
- 230000006399 behavior Effects 0.000 claims description 136
- 238000010586 diagram Methods 0.000 claims description 27
- 238000005295 random walk Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000004931 aggregating effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present application relates to the field of internet technologies, and in particular, to a method and apparatus for recommending commodities, an electronic device, and a readable storage medium. According to the application, the association relation between commodities in the merchant platform is determined by acquiring behavior information of each user in the merchant platform, commodity information corresponding to each behavior information and attribute information of newly-added commodities, constructing commodity association feature vectors, attribute feature vectors of commodity information and attribute feature vectors of newly-added commodities according to the information, and determining the association relation between the commodities in the merchant platform based on the commodity association feature vectors and the attribute feature vectors of commodity information; according to the attribute feature vector of the commodity information and the attribute feature vector of the newly-added commodity, the similarity between the commodity information and the attribute information of the newly-added commodity is determined, and the newly-added commodity is recommended according to the similarity between the commodity information and the attribute information of the newly-added commodity and the association relationship between the commodity.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method and apparatus for recommending commodities, an electronic device, and a readable storage medium.
Background
With the rapid development of internet technology, the electronic commerce platform closely related to the internet is rapidly developed, and most merchants recommend new and folded commodities and hot-sold commodities in shops to users through the electronic commerce platform. Along with the development of the e-commerce industry, the recommendation algorithm of each e-commerce platform is more and more emphasized. However, for the Software-as-a-service (SaaS) mode of the e-commerce platform, that is, the e-commerce platform serves a certain merchant, the user only sees the merchant's merchandise (similar to purchasing the merchandise in an applet) after entering the platform.
In the commodity recommendation algorithm in the prior art, when the user behavior is not abundant in the merchant platform, commodity recommendation is difficult to be performed on the user through the merchant platform, so that for a newly opened shop, commodity recommendation cannot be performed on the user when the user behavior is not abundant or the user behavior is not available, and for a newly opened shop, no effective commodity recommendation method is proposed for performing commodity recommendation on the user in the merchant platform.
Disclosure of Invention
Accordingly, an object of the embodiments of the present application is to provide a method, an apparatus, an electronic device, and a readable storage medium for recommending a commodity, which can provide guiding basis for recommending a new commodity to a user in a merchant platform.
Mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides a commodity recommendation method, including:
acquiring behavior information of each user in a merchant platform, commodity information corresponding to each behavior information and attribute information of newly-added commodities;
according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, constructing commodity association feature vectors for representing the similarity between commodities;
constructing attribute feature vectors of commodity information according to commodity information corresponding to the behavior information of each user;
determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
constructing an attribute feature vector of the newly-added commodity according to the attribute information of the newly-added commodity;
determining the similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly-added commodity;
recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
In one possible implementation manner, a commodity association feature vector for representing similarity between commodities is constructed according to association relation between behavior information of each user and commodity information corresponding to the behavior information, and the method includes:
constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences;
according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence;
and calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence.
In one possible implementation manner, the construction of the attribute feature vector of the commodity information according to the commodity information corresponding to the behavior information of each user includes:
extracting attribute features of commodity information corresponding to behavior information of each user;
and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
In one possible implementation manner, determining the association relationship between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information includes:
and taking the attribute feature vector of each commodity information as an input parameter of an association relation function between commodities, and taking the commodity association feature vector as an output parameter of the association relation function between commodities so as to determine the association relation between commodities in the merchant platform.
In one possible embodiment, the attribute features of the commodity information include at least one of the following features:
commodity name characteristics, commodity price characteristics, and commodity category characteristics.
In a second aspect, an embodiment of the present application further provides a commodity recommendation device, where the commodity recommendation device includes:
the acquisition module is used for acquiring behavior information of each user in the merchant platform, commodity information corresponding to each behavior information and attribute information of the newly-added commodity;
the first calculation module is used for constructing commodity association feature vectors used for representing the similarity between commodities according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information;
the second calculation module is used for constructing attribute feature vectors of the commodity information according to the commodity information corresponding to the behavior information of each user;
the first determining module is used for determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
the third calculation module is used for constructing an attribute feature vector of the new commodity according to the attribute information of the new commodity;
the second determining module is used for determining the similarity between the corresponding commodity information under the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the corresponding commodity information under the behavior information of each user and the attribute feature vector of the newly-added commodity;
and the recommending module is used for recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
In one possible implementation manner, when the first calculation module is configured to construct a commodity association feature vector for representing similarity between commodities according to the relationship between the behavior information of each user and the commodity information corresponding to the behavior information, the first calculation module is further configured to:
constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences;
according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence;
and calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence.
In one possible implementation manner, the second calculating module is further configured to, when configured to construct an attribute feature vector of the commodity information according to the commodity information corresponding to the behavior information of each user,:
extracting attribute features of commodity information corresponding to behavior information of each user;
and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
In one possible implementation manner, the first determining module, when configured to determine an association relationship between the commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information, is further configured to:
and taking the attribute feature vector of each commodity information as an input parameter of an association relation function between commodities, and taking the commodity association feature vector as an output parameter of the association relation function between commodities so as to determine the association relation between commodities 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, the memory storing machine readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine readable instructions when executed by the processor performing the steps of the article recommendation method described in the first aspect or any of the possible implementation manners of the first aspect.
In a fourth aspect, the embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, the computer program being executed by a processor to perform the steps of commodity recommendation described in the first aspect or any of the possible implementation manners of the first aspect.
The embodiment of the application provides a commodity recommendation method, a commodity recommendation device, electronic equipment and a readable storage medium, wherein behavior information of each user in a merchant is obtained by the method, namely: the method comprises the steps that behavior information generated when a user browses, clicks and purchases commodities is obtained, commodity information corresponding to each piece of behavior information and attribute information of newly-added commodities are obtained, the commodity information and the attribute information of the newly-added commodities comprise information such as names, prices and commodity categories of the commodities, and commodity association feature vectors used for representing similarity among the commodities are constructed according to association relations between the behavior information of each user and the commodity information corresponding to the behavior information, namely: the commodity a and the commodity b are not related, but because the user A clicks the commodity a and browses the commodity b, the commodity a and the commodity b are related, a commodity association data structure diagram is generated according to the association relation between the commodities, graph feature extraction is carried out to construct commodity association characteristic vectors, attribute characteristic vectors of commodity information are constructed according to commodity information corresponding to behavior information of each user, the association relation between the commodities in the merchant platform is determined based on the commodity association characteristic vectors and the attribute characteristic vectors of the commodity information, and then the attribute characteristic vectors of the newly-added commodity are constructed according to the obtained attribute information of the newly-added commodity, so that the similarity of the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity is determined according to the attribute characteristic vectors of the commodity information corresponding to the behavior information of each user, for example: and when the user B browses the commodity a, the merchant platform recommends the commodity c to the user B, so that the newly-added commodity is recommended based on the association relationship and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity, and a guiding basis can be provided for the user to recommend the newly-added commodity in the merchant platform.
In order to make the above 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 needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flowchart of a commodity recommendation method provided by an embodiment of the present application;
FIG. 2 is a flow chart of a method for constructing a merchandise associated feature vector according to an embodiment of the application;
FIG. 3 is a flowchart of a method for constructing an attribute feature vector of merchandise information according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a commodity recommendation device according to an embodiment of the present application;
fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be appreciated that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art based on embodiments of the application without making any inventive effort, fall within the scope of the application.
According to research, with the rapid development of internet technology, the electronic commerce platform closely related to the internet is rapidly developed, and most merchants recommend new and folded commodities in shops and hot-sold commodities to users through the electronic commerce platform. Along with the development of the e-commerce industry, the recommendation algorithm of each e-commerce platform is more and more emphasized. However, for the Software-as-a-service (SaaS) mode of the e-commerce platform, that is, the e-commerce platform serves a certain merchant, the user only sees the merchant's merchandise (similar to purchasing the merchandise in an applet) after entering the platform.
In the commodity recommendation algorithm in the prior art, when the user behavior is not abundant in the merchant platform, commodity recommendation is difficult to be performed on the user through the merchant platform, so that for a newly opened shop, commodity recommendation cannot be performed on the user when the user behavior is not abundant or the user behavior is not available, and for a newly opened shop, no effective commodity recommendation method is proposed for performing commodity recommendation on the user in the merchant platform.
For the convenience of understanding the present application, the following describes in detail the description of a flow chart of a commodity recommendation method according to the embodiment of the present application shown in fig. 1.
Referring to fig. 1, fig. 1 shows a flowchart of a commodity recommendation method according to an embodiment of the present application, where the method includes steps S101 to S107:
s101: and acquiring behavior information of each user in the merchant platform, commodity information corresponding to each behavior information and attribute information of the newly-added commodity.
In the implementation, behavior information generated when each user browses, clicks and purchases the commodity or adds the commodity into the shopping cart, commodity information corresponding to each behavior information and attribute information of a new commodity on the merchant platform are obtained from the internet merchant platform.
S102: and constructing commodity association feature vectors for representing the similarity between commodities according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information.
In the implementation, since the user browses, clicks or purchases the commodities, each user generates direct association with the commodity browsed, clicked or purchased by the user, the user and the commodities of the behavior generated by the user are directly associated, and the commodities are also associated because of the behavior of the user, so that the commodities are indirectly associated with the commodities, and the commodity association feature vector for representing the similarity between the commodities is constructed according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information.
S103: and constructing attribute feature vectors of the commodity information according to the commodity information corresponding to the behavior information of each user.
In the implementation, each commodity in the merchant platform has inherent commodity information, the inherent commodity information can represent the own commodity, the commodity information corresponding to the behavior information of each user is extracted, and the attribute feature vector of the commodity information is constructed according to the attribute features in the commodity information.
S104: and determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information.
In specific implementation, based on the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, a commodity association feature vector for representing the similarity between commodities is constructed, and according to the behavior information of each user and the attribute features in the commodity information corresponding to the behavior information, an attribute feature vector of the commodity information is constructed, so that the association relation between commodities in a merchant platform is finally determined.
S105: and constructing an attribute feature vector of the new commodity according to the attribute information of the new commodity.
In a specific implementation, the newly-added commodities also have attribute characteristic information of the commodities, the attribute information of each newly-added commodity can uniquely represent the commodity, and the attribute characteristic vector of the newly-added commodity is constructed according to the attribute information of the newly-added commodity.
S106: and determining the similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly-added commodity.
In a specific implementation, cosine similarity between two vectors is calculated through the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly added commodity, if the cosine value of the included angle of the two vectors is closer to 1, the included angle of the two vectors is closer to 0 degree, that is to say, the two vectors are more similar, so that the similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly added commodity is determined through the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly added commodity.
S107: recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
In a specific implementation, the newly added product is recommended through the association relationship between products with user behaviors and the similarity of the newly added product, for example, the user A clicks the product a and purchases the product B, so that the product a and the product B have an indirect association relationship, and when the product c is newly added, the product c is similar to the product B, so that the merchant platform can recommend the product c to the user B when the user B browses the product a.
The following is a flowchart of a method for constructing a commodity associated feature vector according to an embodiment of the present application shown in fig. 2, and as shown in fig. 2, the method includes steps S201 to S204, where:
s201: and constructing a data structure diagram of each user and the commodity associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram.
In a specific implementation, according to the association relation between the behavior information of each user and the corresponding commodity information under the behavior information, a data structure diagram of the commodity associated with each user is constructed, for example, the user A clicks the commodity a, the user A purchases the commodity B, the user B adds the commodity B into the shopping cart, and the user B clicks the commodity c, so that the relationship among the user A, the user B, the commodity a, the commodity B and the commodity c forms the association data structure diagram through the clicking purchase behaviors of the user A and the user B, and the relationships among the user A, the user B, the commodity a, the commodity B and the commodity c in the data structure diagram are all nodes of the data structure diagram.
S202: nodes are uniformly selected through a random walk algorithm to generate a predetermined number of random walk sequences.
In a specific implementation, according to the data structure diagram between the user and the commodity, the network nodes are uniformly selected through the random walk algorithm, and a predetermined number of random walk sequences are generated, for example, sequences such as a sequence of user a, commodity B, user B, commodity c, user B, commodity a, user a, commodity a, and the like are formed between the user and the commodity in step S201.
S203: and calculating the probability that at least two commodity nodes appear in the same sequence according to the random walk sequence.
In a specific implementation, the conditional probability that at least two commodity nodes appear in the same sequence is calculated according to the generated random walk sequence with the preset number, for example, the sequence: user a→commodity b→user b→commodity c, user b→commodity a→user a→commodity a, and so on, for each vertex in the sequence, the conditional probability that the commodity node appears in the same sequence is calculated.
S204: and calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence.
In a specific implementation, according to the probability that the at least two commodity nodes appear in the same sequence, namely: under the condition that the node appears, the log value of the probability of other nodes in the same sequence is calculated, and the vector of the node is updated by means of a random gradient descent algorithm, wherein the updated vector is the commodity association feature vector for representing the similarity between commodities.
The following is a flowchart of a method for constructing attribute feature vectors of commodity information according to an embodiment of the present application shown in fig. 3, and as shown in fig. 3, the method includes steps S301 to S302, where:
s301: and extracting attribute characteristics of commodity information corresponding to the behavior information of each user.
In the implementation, in the merchant platform, the commodity information is quite a lot, but only the attribute features of the commodity information corresponding to the behavior information of each user are valuable to use, so that the attribute features of the commodity information corresponding to the behavior information of each user need to be extracted from the merchant platform.
S302: and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
In a specific implementation, the attribute features of the commodity information include commodity price, commodity name and commodity category, wherein the commodity name uses word segmentation technology to segment words, word vector technology is used to extract word segmentation results, and the attribute features of the commodity information are aggregated, namely: and superposing the commodity price, commodity name and attribute feature dimension of commodity category to construct attribute feature vector of commodity information corresponding to each user behavior information.
In one possible implementation manner, determining the association relationship between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information includes:
and taking the attribute feature vector of each commodity information as an input parameter of an association relation function between commodities, and taking the commodity association feature vector as an output parameter of the association relation function between commodities so as to determine the association relation between commodities in the merchant platform.
In a specific implementation, the attribute feature vector of each commodity information is used as an input parameter of the association relation function between commodities, and the commodity association feature vector is used as an output parameter of the association relation function between commodities to determine the association relation function between commodities, so that the association relation between commodities in a merchant platform is determined.
In one possible embodiment, the attribute features of the commodity information include at least one of the following features:
commodity name characteristics, commodity price characteristics, and commodity category characteristics.
In a specific implementation, the attribute features of the merchandise information include at least one of a merchandise name, a merchandise price, and a merchandise category.
Referring to fig. 4, a schematic structural diagram of a commodity recommendation device 400 according to an embodiment of the present application is shown, where, as shown in fig. 4, the commodity recommendation device 400 according to the embodiment of the present application includes:
the acquiring module 410 is configured to acquire behavior information of each user in the merchant platform, commodity information corresponding to each behavior information, and attribute information of a newly added commodity;
the first calculation module 420 is configured to construct a commodity association feature vector for representing similarity between commodities according to the association relationship between the behavior information of each user and the commodity information corresponding to the behavior information;
the second calculation module 430 is configured to construct an attribute feature vector of the commodity information according to the commodity information corresponding to the behavior information of each user;
a first determining module 440, configured to determine an association relationship between the commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
a third calculation module 450, configured to construct an attribute feature vector of the new added commodity according to attribute information of the new added commodity;
a second determining module 460, configured to determine, according to the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly added commodity, a similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly added commodity;
and a recommending module 470, configured to recommend the newly added product based on the association relationship and the similarity between the corresponding product information and the newly added product under the behavior information of each user.
In one possible implementation manner, when the first computing module 420 is configured to construct a commodity association feature vector for representing similarity between commodities according to the association relationship between the behavior information of each user and the commodity information corresponding to the behavior information, the first computing module 420 is further configured to:
constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences;
according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence;
and calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence.
In one possible implementation manner, the second computing module 430 is further configured to, when configured to construct an attribute feature vector of the commodity information according to the commodity information corresponding to the behavior information of each user, the second computing module 430 is further configured to:
extracting attribute features of commodity information corresponding to behavior information of each user;
and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
In one possible implementation manner, the first determining module 440, when configured to determine the association relationship between the commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information, is further configured to:
and taking the attribute feature vector of each commodity information as an input parameter of an association relation function between commodities, and taking the commodity association feature vector as an output parameter of the association relation function between commodities so as to determine the association relation between commodities in the merchant platform.
Based on the same application concept, referring to fig. 5, a schematic structural diagram of an electronic device 500 according to an embodiment of the present application includes:
the system comprises a processor 510, a memory 520 and a bus 530, wherein the memory 520 stores machine readable instructions executable by the processor 510, the processor 510 and the memory 520 communicate through the bus 530 when the electronic device 500 is operated, and the machine readable instructions are executed by the processor 510 to perform the steps of a commodity recommendation method according to the above embodiment.
In particular, the machine-readable instructions, when executed by the processor 510, may perform the following:
acquiring behavior information of each user in a merchant platform, commodity information corresponding to each behavior information and attribute information of newly-added commodities;
according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, constructing commodity association feature vectors for representing the similarity between commodities;
constructing attribute feature vectors of commodity information according to commodity information corresponding to the behavior information of each user;
determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
constructing an attribute feature vector of the newly-added commodity according to the attribute information of the newly-added commodity;
determining the similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly-added commodity;
recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
The embodiment of the application provides a commodity recommendation method, a commodity recommendation device, electronic equipment and a readable storage medium, wherein behavior information of each user in a merchant is obtained by the method, namely: the method comprises the steps that behavior information generated when a user browses, clicks and purchases commodities is obtained, commodity information corresponding to each piece of behavior information and attribute information of newly-added commodities are obtained, the commodity information and the attribute information of the newly-added commodities comprise information such as names, prices and commodity categories of the commodities, and commodity association feature vectors used for representing similarity among the commodities are constructed according to association relations between the behavior information of each user and the commodity information corresponding to the behavior information, namely: the commodity a and the commodity b are not related, but because the user A clicks the commodity a and browses the commodity b, the commodity a and the commodity b are related, a commodity association data structure diagram is generated according to the association relation between the commodities, graph feature extraction is carried out to construct commodity association characteristic vectors, attribute characteristic vectors of commodity information are constructed according to commodity information corresponding to behavior information of each user, the association relation between the commodities in the merchant platform is determined based on the commodity association characteristic vectors and the attribute characteristic vectors of the commodity information, and then the attribute characteristic vectors of the newly-added commodity are constructed according to the obtained attribute information of the newly-added commodity, so that the similarity of the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity is determined according to the attribute characteristic vectors of the commodity information corresponding to the behavior information of each user, for example: and when the user B browses the commodity a, the merchant platform recommends the commodity c to the user B, so that the newly-added commodity is recommended based on the association relationship and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity, and a guiding basis can be provided for the user to recommend the newly-added commodity in the merchant platform.
Based on the same application concept, the embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of a commodity recommendation method according to any one of the above embodiments are performed.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which 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 manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in 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 this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (9)
1. A commodity recommendation method, characterized in that the commodity recommendation method comprises:
acquiring behavior information of each user in a merchant platform, commodity information corresponding to each behavior information and attribute information of newly-added commodities;
constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram; uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences; according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence; calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence;
constructing attribute feature vectors of commodity information according to commodity information corresponding to the behavior information of each user;
determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
constructing an attribute feature vector of the newly-added commodity according to the attribute information of the newly-added commodity;
determining the similarity between the commodity information corresponding to the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the commodity information corresponding to the behavior information of each user and the attribute feature vector of the newly-added commodity;
recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
2. The commodity recommendation method according to claim 1, wherein constructing an attribute feature vector of commodity information according to commodity information corresponding to behavior information of each user comprises:
extracting attribute features of commodity information corresponding to behavior information of each user;
and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
3. The commodity recommendation method according to claim 1, wherein determining an association relationship between commodities in the merchant platform based on the commodity association feature vector and an attribute feature vector of each commodity information comprises:
and taking the attribute feature vector of each commodity information as an input parameter of an association relation function between commodities, and taking the commodity association feature vector as an output parameter of the association relation function between commodities so as to determine the association relation between commodities in the merchant platform.
4. The merchandise recommendation method according to claim 2, wherein the attribute characteristics of the merchandise information include at least one of the following characteristics:
commodity name characteristics, commodity price characteristics, and commodity category characteristics.
5. A commodity recommendation device, characterized in that the commodity recommendation device comprises:
the acquisition module is used for acquiring behavior information of each user in the merchant platform, commodity information corresponding to each behavior information and attribute information of the newly-added commodity;
the first calculation module is used for constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, and each user and each commodity are used as nodes of the data structure diagram; uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences; according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence; calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence;
the second calculation module is used for constructing attribute feature vectors of the commodity information according to the commodity information corresponding to the behavior information of each user;
the first determining module is used for determining the association relation between commodities in the merchant platform based on the commodity association feature vector and the attribute feature vector of each commodity information;
the third calculation module is used for constructing an attribute feature vector of the new commodity according to the attribute information of the new commodity;
the second determining module is used for determining the similarity between the corresponding commodity information under the behavior information of each user and the attribute information of the newly-added commodity according to the attribute feature vector of the corresponding commodity information under the behavior information of each user and the attribute feature vector of the newly-added commodity;
and the recommending module is used for recommending the newly-added commodity based on the association relation and the similarity between the commodity information corresponding to the behavior information of each user and the newly-added commodity.
6. The article recommendation device according to claim 5, wherein the first calculation module is further configured to, when the first calculation module is configured to construct an article association feature vector for representing similarity between articles according to association relationships between behavior information of each user and article information corresponding to the behavior information:
constructing a data structure diagram of each user and commodities associated with the user according to the association relation between the behavior information of each user and the commodity information corresponding to the behavior information, wherein each user and each commodity are used as nodes of the data structure diagram;
uniformly selecting nodes through a random walk algorithm to generate a preset number of random walk sequences;
according to the random walk sequence, calculating the probability that at least two commodity nodes appear in the same sequence;
and calculating commodity association feature vectors used for representing the similarity between commodities according to the probability that the at least two commodity nodes appear in the same sequence.
7. The merchandise recommendation apparatus according to claim 5, wherein the second calculation module, when configured to construct an attribute feature vector of merchandise information according to merchandise information corresponding to behavior information of each user, is further configured to:
extracting attribute features of commodity information corresponding to behavior information of each user;
and aggregating the attribute characteristics of the commodity information to construct attribute characteristic vectors of the commodity information corresponding to each piece of user behavior information.
8. A computer device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating over the bus when the computer device is running, said machine readable instructions when executed by said processor performing the steps of the merchandise recommendation method according to any one of claims 1 to 4.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the commodity recommendation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010072430.XA CN111292164B (en) | 2020-01-21 | 2020-01-21 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010072430.XA CN111292164B (en) | 2020-01-21 | 2020-01-21 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111292164A CN111292164A (en) | 2020-06-16 |
| CN111292164B true CN111292164B (en) | 2023-08-25 |
Family
ID=71023523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010072430.XA Active CN111292164B (en) | 2020-01-21 | 2020-01-21 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111292164B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753206B (en) * | 2020-06-29 | 2024-06-14 | 支付宝(杭州)信息技术有限公司 | Information pushing method and system |
| CN111507812B (en) * | 2020-07-02 | 2020-10-27 | 成都晓多科技有限公司 | Commodity collocation recommendation method and device based on attributes and titles |
| CN113763080A (en) * | 2020-08-26 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining recommended article, electronic equipment and storage medium |
| CN112416945A (en) * | 2020-12-07 | 2021-02-26 | 恩亿科(北京)数据科技有限公司 | Data processing method and system based on big data platform and computer equipment |
| CN113744019A (en) * | 2021-01-12 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
| CN113744021A (en) * | 2021-02-08 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Recommendation method, recommendation device, computer storage medium and recommendation system |
| CN112925993B (en) * | 2021-04-08 | 2022-02-08 | 国网电子商务有限公司 | Collaborative filtering recommendation method and device, storage medium and equipment |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570008B (en) * | 2015-10-09 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Recommendation method and device |
| CN107818105B (en) * | 2016-09-13 | 2021-04-09 | 腾讯科技（深圳）有限公司 | Recommendation method of application program and server |
| CN106815347A (en) * | 2017-01-13 | 2017-06-09 | 沈阳工学院 | Improvement slope one Collaborative Filtering Recommendation Algorithms based on commodity similarity |
| 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 |
| CN107220852A (en) * | 2017-05-26 | 2017-09-29 | 北京小度信息科技有限公司 | Method, device and server for determining target recommended user |
| CN107563833A (en) * | 2017-07-27 | 2018-01-09 | 广州智慧城市发展研究院 | A kind of personalized recommendation method and system based on block chain integration service platform |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
| CN108090807B (en) * | 2017-12-13 | 2021-06-22 | 北京星选科技有限公司 | Information recommendation method and device |
| CN108898459B (en) * | 2018-06-25 | 2020-12-01 | 中国联合网络通信集团有限公司 | Commodity 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 |
-
2020
- 2020-01-21 CN CN202010072430.XA patent/CN111292164B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111292164A (en) | 2020-06-16 |
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 | |
| CN107330445B (en) | User attribute prediction method and device | |
| CN109242649A (en) | A kind of Method of Commodity Recommendation and relevant apparatus | |
| JP2010134733A (en) | Information recommendation device, information recommendation method, and program | |
| JPH1115842A (en) | Data mining device | |
| CN103164804A (en) | Personalized method and personalized device of information push | |
| CN111125376B (en) | Knowledge graph generation method and device, data processing equipment and storage medium | |
| CN110807669B (en) | Cross-platform user information management method and device | |
| CN109101553B (en) | Purchasing user evaluation method and system for industry of non-beneficiary party of purchasing party | |
| CN111553763B (en) | Article recommendation method and device, electronic equipment and readable storage medium | |
| JP5331159B2 (en) | Product recommendation method, product recommendation device, and product recommendation program | |
| CN111612585A (en) | Virtual resource distribution method and device | |
| CN110347887B (en) | Method and device for acquiring time sequence data of service scene | |
| CN108596712B (en) | Single-class collaborative filtering method based on article sequence, storage medium and server | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CA3138745A1 (en) | Method and device for circling and creating target population | |
| WO2017166535A1 (en) | Method and apparatus for uniform settlement of online shopping | |
| CN115641179A (en) | Information pushing method and device and electronic equipment | |
| CN107967637B (en) | Commodity object model recommendation method and device and electronic equipment | |
| CN111353836B (en) | Commodity recommendation method, device and equipment | |
| CN110020135B (en) | Demand determination method, resource recommendation method and related device | |
| CN115511546A (en) | Behavior analysis method, system, equipment and readable medium for E-commerce users | |
| CN115239413A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
| CN114491086A (en) | Clothing personalized matching recommendation method and system, electronic equipment and 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231211 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. |