CN112633978A - Graph neural network model construction method, and method, device and equipment for commodity recommendation - Google Patents
Graph neural network model construction method, and method, device and equipment for commodity recommendation Download PDFInfo
- Publication number
- CN112633978A CN112633978A CN202011528670.2A CN202011528670A CN112633978A CN 112633978 A CN112633978 A CN 112633978A CN 202011528670 A CN202011528670 A CN 202011528670A CN 112633978 A CN112633978 A CN 112633978A
- Authority
- CN
- China
- Prior art keywords
- relationship
- commodities
- merchants
- neural network
- network model
- 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
- 238000003062 neural network model Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000010276 construction Methods 0.000 title abstract description 8
- 239000013598 vector Substances 0.000 claims description 56
- 230000006399 behavior Effects 0.000 claims description 44
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 8
- 238000004220 aggregation Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005295 random walk Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims 1
- 238000003860 storage Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 230000009466 transformation Effects 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of information recommendation, and discloses a graph neural network model construction method for commodity recommendation. The method comprises the following steps: acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants; acquiring a multi-path heteromorphic graph according to the behavior data, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants; and obtaining a graph neural network model according to the multipath metamorphic graph. The graph neural network model obtained by the scheme considers the attributes of multiple dimensions, so that the output result of the graph neural network model is more consistent with the behavior of the user when the graph neural network model is used for commodity recommendation, and the experience of the user when the user obtains a commodity recommendation result is improved. The application also discloses a device and equipment for constructing the neural network model of the graph for recommending the commodity, and a method, a device and equipment for recommending the commodity.
Description
Technical Field
The application relates to the technical field of information recommendation, for example, to a graph neural network model construction method for commodity recommendation, a method, a device and equipment for commodity recommendation.
Background
The prior art for commodity recommendation generally adopts some classical recommendation algorithms, such as: and carrying out algorithms such as matrix decomposition, collaborative filtering, recommendation according to heat ranking and the like. The recommendation algorithm in the prior art can only recommend commodities to users according to a single attribute, and cannot obtain output results for recommending commodities according to attributes of multiple dimensions.
Disclosure of Invention
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview nor is intended to identify key/critical elements or to delineate the scope of such embodiments but rather as a prelude to the more detailed description that is presented later.
The embodiment of the disclosure provides a graph neural network model construction method for commodity recommendation, a method, a device and equipment for commodity recommendation, so that an output result for commodity recommendation can be obtained according to attributes of multiple dimensions.
In some embodiments, the method for building the neural network model for commodity recommendation includes:
acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants;
acquiring a multi-path heteromorphic graph according to the behavior data, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants;
and obtaining a graph neural network model according to the multipath heteromorphic graph.
In some embodiments, the method for merchandise recommendation includes: and recommending the commodity for the user according to the graph neural network model constructed by the method.
In some embodiments, the apparatus comprises: the system comprises a first processor and a first memory, wherein the first memory stores first program instructions, and the first processor is configured to execute the method for constructing the neural network model for commodity recommendation.
In some embodiments, the apparatus comprises: a first processor and a first memory storing first program instructions, the first processor being configured to, upon execution of the first program instructions, perform the method for merchandise recommendation described above.
In some embodiments, the apparatus comprises: the graph neural network model building device for commodity recommendation is described above.
In some embodiments, the apparatus comprises: the device for commodity recommendation is described above.
The method, the device and the equipment for constructing the neural network model for commodity recommendation provided by the embodiment of the disclosure can realize the following technical effects: the multi-path abnormal picture is obtained through the behavior data of the users, the relation between commodities, the relation between merchants, the relation between the users and the relation between the commodities and the merchants, and the graph neural network model is obtained according to the multi-path abnormal picture, so that the obtained graph neural network model takes the attributes of multiple dimensions into consideration, the output result of the graph neural network model is more consistent with the behavior of the users when the graph neural network model is used for commodity recommendation, and the experience of the users when the user obtains the commodity recommendation result is improved.
The method, the device and the equipment for recommending commodities provided by the embodiment of the disclosure can realize the following technical effects: by acquiring the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between users and the relationship between commodities and merchants, inputting the behavior data into the neural network model of the graph, the relevance scores of any two nodes of the commodities, the merchants and the users can be obtained, and the commodities are recommended to the user according to the relevance scores.
The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the accompanying drawings and not in limitation thereof, in which elements having the same reference numeral designations are shown as like elements and not in limitation thereof, and wherein:
FIG. 1 is a schematic diagram of a graphical neural network model construction method for commodity recommendation according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a method for merchandise recommendation provided by embodiments of the present disclosure;
FIG. 3 is a schematic diagram of a neural network model building apparatus for commodity recommendation according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of an apparatus for merchandise recommendation provided by an embodiment of the present disclosure.
Detailed Description
So that the manner in which the features and elements of the disclosed embodiments can be understood in detail, a more particular description of the disclosed embodiments, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown in simplified form in order to simplify the drawing.
The terms "first," "second," and the like in the description and in the claims, and the above-described drawings of embodiments of the present disclosure, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the present disclosure described herein may be made. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
The term "plurality" means two or more unless otherwise specified.
In the embodiment of the present disclosure, the character "/" indicates that the preceding and following objects are in an or relationship. For example, A/B represents: a or B.
The term "and/or" is an associative relationship that describes objects, meaning that three relationships may exist. For example, a and/or B, represents: a or B, or A and B.
With reference to fig. 1, an embodiment of the present disclosure provides a method for building a neural network model for commodity recommendation, including:
step S101, acquiring behavior data of users, relationships among commodities, relationships among merchants, relationships among users and relationships among commodities and merchants; the behavior data comprises one or more of historical purchasing behavior data of the user on the commodity, historical collection behavior data of the user on the commodity and historical comment behavior data of the user on the commodity; the relationship among the commodities comprises one or more of the commodities purchased by the same user, collected by the same user, commented by the same user, the same commodity type, belonging to the same brand or belonging to matched commodities; relationships between merchants include: the method comprises the following steps of (1) having commodities of the same type, commodities purchased by the same user, commodities collected by the same user and commodities commented by the same user; the relationship between the goods and the merchant includes: the merchants include the same type of item or the merchants include the item; the relationship between the user and the user includes: friend relationships, etc.
And step S102, acquiring a multi-path abnormal picture according to the behavior data of the user, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants.
And step S103, obtaining a neural network model according to the multipath metamorphic graph.
By adopting the graph neural network model construction method for commodity recommendation provided by the embodiment of the disclosure, the multi-path abnormal composition is obtained through the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between users and the relationship between commodities and merchants, and the graph neural network model is obtained according to the multi-path abnormal composition.
Optionally, obtaining the multi-path difference graph according to the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants includes: and constructing a multi-path heteromorphic graph by taking the behavior data of the users, the relationship among commodities, the relationship among merchants, the relationship among the users and the relationship among the commodities and the merchants as edges and taking the users, the commodities or the merchants as nodes.
Optionally, the type of the edge corresponding to the behavior data of the user includes: purchase type, collection type, or comment type, etc.; optionally, the types of the edges corresponding to the relationship between the commodities include: purchased by the same user, collected by the same user, commented by the same user, belonging to the same commodity type, belonging to the same brand or belonging to a matched commodity and the like; optionally, the types of the edges corresponding to the relationship between the merchants include: the presence of commodities purchased by the same user, commodities collected by the same user, commodities commented by the same user, belonging to the same type, and the like; optionally, belonging to the same type includes: belonging to the household appliance type, the clothing type, etc.; optionally, the types of the edges corresponding to the relationship between the goods and the merchant include: the merchants include the same type of item or the merchants include the item, etc.; optionally, the types of the edges corresponding to the relationship between the user and the user include: friend types, etc.
Alternatively, the multi-way differential pattern is composed of several nodes and several edges.
Optionally, attribute information of the user, attribute information of the commodity, and attribute information of the merchant are obtained. Optionally, the attribute information of the user includes: the age, sex, location, etc. of the user; the attribute information of the article includes: price, brand, origin, etc. Optionally, the attribute information of the merchant includes: location, audience group, merchant type, etc.
Optionally, after acquiring the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants, preprocessing the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants is further included.
Optionally, preprocessing the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants includes: the behavior data of the users, the relation between commodities, the relation between merchants, the relation between the users and the relation between the commodities and the merchants are processed into data in the formats of < node one type > < node two type > < edge type >, < node one type > < attribute 1> < attribute 2> < attribute 3> < attribute P >, and the like, wherein P is a positive integer.
Optionally, a multi-way differential map is constructed from the preprocessed data. Optionally, behavior data of the user within a preset time period is acquired. In some embodiments, the preset period of time is one week.
Optionally, the feature vector of each node is obtained by quantifying attributes such as age, gender, region, price, brand, origin, and the like.
In some embodiments, in the case that the node is a user, the feature vector of the node is obtained by quantifying attributes such as age, gender, region, and user ID (Identity Document) of the user.
In some embodiments, in the case that the node is a commodity, the attribute of the commodity, such as price, brand, production place, etc., is quantized to obtain a feature vector of the node.
In some embodiments, in the case that the node is a merchant, the feature vector of the node is obtained by quantifying attributes such as a region where the merchant is located, a merchant type, an audience group, and the like. Therefore, the dimensionality of the feature vector obtained by quantifying each attribute is different, and the data has a plurality of different interactions such as purchasing, collecting and commenting, so that the description by using the multi-path heteromorphic graph is more suitable for the requirements of users.
Optionally, obtaining a neural network model from the multipath profile, comprising: acquiring a feature embedded vector of each node and an edge embedded vector of each node in a multi-path heterogeneous graph; acquiring an aggregation feature vector of each node according to the feature embedding vector and the edge embedding vector; solving the inner product of the aggregation characteristic vectors of any two nodes to obtain the correlation score of the two nodes; obtaining a loss value of the correlation score; under the condition that the loss value does not meet the preset condition, adjusting the feature embedding vector and the edge embedding vector according to the loss value until the loss value meets the preset condition; and under the condition that the loss value meets a preset condition, obtaining a graph neural network model, wherein the graph neural network model is used for solving the inner product of the aggregation characteristic vectors of any two nodes in the model to obtain the correlation score of the two nodes.
Optionally, feature embedding and edge embedding are performed on each node respectively to obtain a feature embedded vector and an edge embedded vector of each node.
Optionally, by calculating Xi＝DzxiObtaining a feature embedding vector of each node; wherein, XiEmbedding vectors for the features of node i, DzIs xiA feature transformation matrix of a feature embedding layer of the corresponding node type z; z is a node type, xiIs the initial characteristic vector of the node i, i is more than or equal to 0.
Optionally by calculating vi＝MkUiai,kObtaining edge embedding vectors of all nodes; wherein v isiEmbedding vectors, M, for edges of each nodekEmbedding a feature transformation matrix, U, of a layer for a feature of edge type kiEdge embedding for all edges of node i; a isi,kEmbedding weights for the edge of node i for edge embedding on edge type k.
Optionally, the feature embedding vector and the edge embedding vector of each node are weighted and summed to obtain an aggregate feature vector of each node.
Optionally, by calculating ei＝αXi+βviObtaining the aggregation characteristic vector of each node; wherein e isiIs a cluster feature vector, alpha is the weight of the feature embedding vector, beta is the weight of the edge embedding vector, XiEmbedding vectors, v, for the features of node iiA vector is embedded for each node's edge, optionally α + β ═ 1.
Optionally, an inner product is calculated for the aggregation feature vectors of any two nodes, so as to obtain a correlation score between the two nodes.
Optionally, by calculating ri,j＝ei T·ejObtaining a correlation score between the node i and the node j; wherein r isi,jScore the correlation between node i and node j, ei TAs a transpose of the aggregated feature vector of node i, ejIs the aggregated feature vector for node j.
Alternatively, the loss value of the relevance score is obtained by a BPR (Bayesian Personalized Ranking) loss function.
Optionally by calculation
Obtaining a loss value of a relevance score, wherein LbprLoss value scored for relevance, Nsσ is a Sixmoid (S-shaped growth curve) function as a first normalization parameter; r isi,jIs a correlation score for a pair of positive samples, rf,gA correlation score for a pair of negative samples. Optionally, the positive sample is a correlation score calculated according to two nodes in the same path; negative examples are relevance scores calculated from two nodes not in the same path.
Optionally, a local minimum of the loss value of the correlation score is obtained by a random gradient descent algorithm.
Alternatively, in the case where the local minimum value of the loss value does not reach within the set threshold value range, the matrix D is transformed for the feature embedded in the vectorzAdjusting, and embedding feature transformation matrix M in vectorkAnd adjusting until the local minimum value of the loss value reaches the set threshold value range. And obtaining the graph neural network model under the condition that the local minimum value of the loss value reaches the range of the set threshold value. Thus, by the BPR loss function and at random gradientsThe descent algorithm is used for carrying out perfect training on the model, and the model can be optimized, so that the correlation score calculated by the graph neural network model is more accurate.
Optionally, the obtaining a feature embedding vector of each node and an edge embedding vector of each node in the multi-path heterogeneous graph includes: extracting gamma paths in the multi-path different composition graph through a random walk algorithm, wherein gamma is more than or equal to 2; each path comprises nodes and edges in the multi-path heterogeneous graph; taking any node in the path as a target node, and extracting neighbor nodes of w target nodes from the path containing the target node; acquiring edges between the neighbor nodes and the target node, wherein w is larger than 0; performing feature embedding on the target node to obtain a feature embedding vector of the target node until all nodes in the path are subjected to feature embedding; and performing edge embedding on the target node to obtain an edge embedding vector of the target node until all nodes in the path are subjected to edge embedding.
Optionally, gamma paths are extracted from the multi-path heterogeneous composition through a random walk algorithm, wherein gamma is more than or equal to 2; each path has a length t.
Optionally, the process of transferring information of the feature vector of the neighbor node j to the node i on the k-type edge is as follows:
by calculation of
Embedding the node i on each type of edge is obtained; wherein, Uj→i,kEdge-embedded information passing on edge type k for embedding edges of node j into node i, Ci,jIs a second normalization parameter, WkFor dimensional transformation matrices on different edge types, Uj,kEdge embedding on an edge of type k for node j.
Optionally, Ui＝(Ui,1,Ui,2,…Ui,k)，UiObtained by edge embedding and splicing of all edge types on a node i, Ui,kEdge embedding on node i for different types of edges.
Optionally by calculating ai,k＝softmax(Wk tanh(WkUk))TGet edge-embedded opposite edge of node iThe weight of edge embedding on type k; wherein, WkFor dimensional transformation matrices on different edge types, UkFor vector representations on the same node for different edge types, ai,kEmbedding weights for the edge of node i for edge embedding on edge type k.
Optionally by calculating vi＝MkUiai,kObtaining edge embedding vectors of all nodes; wherein v isiEmbedding vectors, M, for edges of each nodekEmbedding a feature transformation matrix, U, of a layer for a feature of edge type kiEdge embedding for all edges of node i; a isi,kEmbedding weights for the edge of node i for edge embedding on edge type k.
The embodiment of the disclosure provides a method for commodity recommendation, which includes: and the graph neural network model constructed according to the method carries out commodity recommendation on the user.
With reference to fig. 2, another method for recommending commodities is provided in an embodiment of the present disclosure, including:
step S201, acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants within a preset time period;
step S202, inputting the behavior data of the users, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants into a neural network model of a graph for calculation to obtain a correlation score;
and step S203, recommending commodities to the user according to the relevance scores.
By adopting the method for recommending commodities provided by the embodiment of the disclosure, the following technical effects can be realized: by acquiring the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between users and the relationship between commodities and merchants, inputting the behavior data into the neural network model of the graph, the relevance scores of any two nodes of the commodities, the merchants and the users can be obtained, and the commodities are recommended to the user according to the relevance scores.
Optionally, recommending the commodity for the user according to the graph neural network model, including: acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants; inputting the behavior data of the users, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants into a neural network model for calculation to obtain a correlation score; and recommending the commodities to the user according to the relevance scores. The behavior data comprises one or more of historical purchasing behavior data of the user on the commodity, historical collection behavior data of the user on the commodity and historical comment behavior data of the user on the commodity; the relationship among the commodities comprises one or more of the commodities purchased by the same user, collected by the same user, commented by the same user, the same commodity type, belonging to the same brand or belonging to matched commodities; relationships between merchants include: the method comprises the following steps of (1) having commodities of the same type, commodities purchased by the same user, commodities collected by the same user and commodities commented by the same user; the relationship between the goods and the merchant includes: the merchants include the same type of item or the merchants include the item; the relationship between the user and the user includes: friend relationships, etc.
Optionally, the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants within a preset time period are obtained, and the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants are input into the graph neural network model to obtain the correlation score of the behavior data of the user. Optionally, the graph neural network model calculates an inner product of the aggregation feature vectors of any two nodes in the model to obtain a correlation score of any two nodes.
Optionally, in the obtained relevance scores, a commodity corresponding to the relevance score meeting a preset condition, such as the highest score, is selected and recommended to the user.
Optionally, recommending the goods to the user according to the relevance score includes: under the condition that the nodes i and j in the graph neural network model are users and commodities, recommending n commodities with highest relevance scores to the users according to the idea of collaborative filtering, wherein n is a positive integer; under the condition that the node i and the node j in the graph neural network model are both users, the relevance score of the node i and the node j is highest, and commodities purchased, collected or commented by the user j are recommended to the user i according to the idea of collaborative filtering; under the condition that the node i and the node j in the graph neural network model are both commodities, the relevance score of the node i and the node j is highest, and the commodity j is recommended to a user who purchases, collects or reviews the commodity i according to the idea of collaborative filtering; under the condition that the node i is a user and the node j is a merchant in the graph neural network model, the relevance degree score of the node i and the node j is highest, and the commodity of the merchant j is recommended to the user i according to the idea of collaborative filtering.
As shown in fig. 3, an embodiment of the present disclosure provides a neural network model building apparatus for commodity recommendation, including a first processor (processor)100 and a first memory (memory)101 storing a first program instruction. Optionally, the apparatus may further include a first Communication Interface (Communication Interface)102 and a first bus 103. The first processor 100, the first communication interface 102, and the first memory 101 may communicate with each other through the first bus 103. The first communication interface 102 may be used for information transfer. The first processor 100 may call the first program instruction in the first memory 101 to execute the graph neural network model building method for commodity recommendation of the above embodiment.
In addition, the first program instructions in the first memory 101 may be implemented in the form of software functional units and stored in a computer readable storage medium when the first program instructions are sold or used as independent products.
The first memory 101 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The first processor 100 executes functional applications and data processing by executing program instructions/modules stored in the first memory 101, that is, implements the graph neural network model building method for commodity recommendation in the above embodiments.
The first memory 101 may include a first storage program area and a first storage data area, wherein the first storage program area may store a first operating system, a first application program required for at least one function; the first stored data area may store data created according to the use of the terminal device, and the like. In addition, the first memory 101 may include a high-speed random access memory, and may also include a nonvolatile memory.
By adopting the device for constructing the neural network model for commodity recommendation provided by the embodiment of the disclosure, the multi-path heterogeneous patterns are obtained through the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between users and the relationship between commodities and merchants, and the neural network model is obtained according to the multi-path heterogeneous patterns.
As shown in fig. 4, an apparatus for recommending goods according to an embodiment of the present disclosure includes a second processor (processor)200 and a second memory (memory)201 storing second program instructions. Optionally, the apparatus may further include a second Communication Interface (Communication Interface)202 and a second bus 203. The second processor 200, the second communication interface 202 and the second memory 201 can complete communication with each other through the second bus 203. The second communication interface 202 may be used for information transfer. The second processor 200 may call the second program instruction in the second memory 201 to execute the graph neural network model building method for commodity recommendation of the above embodiment.
In addition, the second program instructions in the second memory 201 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products.
The second memory 201 is a computer readable storage medium, and can be used for storing software programs, computer executable programs, such as program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The second processor 200 executes functional applications and data processing by executing the program instructions/modules stored in the second memory 201, that is, implements the graph neural network model building method for commodity recommendation in the above embodiments.
The second memory 201 may include a second storage program area and a second storage data area, wherein the second storage program area may store a second operating system, a second application program required for at least one function; the second storage data area may store data created according to the use of the terminal device, and the like. In addition, the second memory 201 may include a high-speed random access memory, and may also include a nonvolatile memory.
By adopting the device for recommending commodities, provided by the embodiment of the disclosure, the behavior data of the user, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants are obtained and input into the neural network model of the graph, so that the relevance scores of any two nodes of the commodities, the merchants, and the users can be obtained, and the commodities are recommended to the users according to the relevance scores.
The embodiment of the disclosure provides equipment comprising the graph neural network model building device for commodity recommendation. The device obtains the multi-path abnormal composition through the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between the users and the relationship between the commodities and the merchants, and obtains the neural network model according to the multi-path abnormal composition.
Optionally, the device comprises a computer, server, or the like.
The embodiment of the disclosure provides a device, which comprises the above device for recommending commodities. By acquiring the behavior data of the user, the relationship between commodities, the relationship between merchants, the relationship between users and the relationship between commodities and merchants, inputting the behavior data into the neural network model of the graph, the relevance scores of any two nodes of the commodities, the merchants and the users can be obtained, and the commodities are recommended to the user according to the relevance scores
Optionally, the device comprises a cell phone, tablet, computer, or the like.
The embodiment of the disclosure provides a computer-readable storage medium, which stores computer-executable instructions configured to execute the above graph neural network model construction method for commodity recommendation.
The embodiment of the disclosure provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes first program instructions, when the first program instructions are executed by a computer, the computer executes the above-mentioned method for constructing a neural network model for commodity recommendation.
The disclosed embodiments provide another computer-readable storage medium storing computer-executable instructions configured to perform the above-described method for merchandise recommendation.
The disclosed embodiments provide another computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising second program instructions which, when executed by a computer, cause the computer to perform the above-described method for merchandise recommendation.
The computer-readable storage medium described above may be a transitory computer-readable storage medium or a non-transitory computer-readable storage medium.
The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, where the computer software product is stored in a storage medium and includes one or more instructions to enable 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 method of the embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium comprising: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes, and may also be a transient storage medium.
The above description and drawings sufficiently illustrate embodiments of the disclosure to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. The examples merely typify possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in or substituted for those of others. Furthermore, the words used in the specification are words of description only and are not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this application is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, the terms "comprises" and/or "comprising," when used in this application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element. In this document, each embodiment may be described with emphasis on differences from other embodiments, and the same and similar parts between the respective embodiments may be referred to each other. For methods, products, etc. of the embodiment disclosures, reference may be made to the description of the method section for relevance if it corresponds to the method section of the embodiment disclosure.
Those of skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software may depend upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments. It can be clearly understood by the skilled person that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be merely a logical division, and in actual implementation, there may be another division, for example, multiple 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 through some interfaces, devices or units, 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 implement the present embodiment. In addition, functional units in the embodiments of the present disclosure 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 flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than disclosed in the description, and sometimes there is no specific order between the different operations or steps. For example, two sequential operations or steps may in fact be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. Each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Claims (10)
1. A method for constructing a graph neural network model for commodity recommendation is characterized in that,
acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants;
acquiring a multi-path heteromorphic graph according to the behavior data, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants;
and obtaining a graph neural network model according to the multipath heteromorphic graph.
2. The method of claim 1, wherein obtaining a multi-way variogram from the behavioral data, the relationship between the commodities, the relationship between the merchants, the relationship between the users, and the relationship between the commodities and the merchants comprises:
and constructing a multi-path heteromorphic graph by taking the behavior data, the relationship among commodities, the relationship among merchants, the relationship among users and the relationship among the commodities and the merchants as edges and taking the users, the commodities or the merchants as nodes.
3. The method of claim 1, wherein obtaining the graph neural network model from the multi-path metamorphic graph comprises:
acquiring a feature embedded vector of each node in the multi-path heterogeneous graph and an edge embedded vector of each node;
acquiring an aggregation feature vector of each node according to the feature embedding vector and the edge embedding vector;
solving an inner product of the aggregation characteristic vectors of any two nodes to obtain a correlation score of the two nodes;
obtaining a loss value of the relevance score;
under the condition that the loss value does not meet a preset condition, adjusting the feature embedding vector and the edge embedding vector according to the loss value until the loss value meets the preset condition;
and under the condition that the loss value meets the preset condition, obtaining the graph neural network model.
4. The method of claim 3, wherein obtaining the feature embedding vector of each node and the edge embedding vector of each node in the multi-path anomaly map comprises:
extracting gamma paths in the multi-path abnormal composition picture through a random walk algorithm, wherein gamma is more than or equal to 2;
each path comprises a node and an edge in the multipath heterogeneous graph;
taking any node in the path as a target node, and extracting w neighbor nodes of the target node from the path containing the target node;
acquiring edges between the neighbor nodes and the target node, wherein w is larger than 0;
performing feature embedding on the target node to obtain a feature embedding vector of the target node until all nodes in the path are subjected to feature embedding; and performing edge embedding on the target node to obtain an edge embedding vector of the target node until all nodes in the path are subjected to edge embedding.
5. A method for commodity recommendation, characterized in that a commodity recommendation is made to a user according to a graph neural network model constructed according to the method of any one of claims 1 to 4.
6. The method of claim 5, wherein recommending goods to a user according to the graph neural network model comprises:
acquiring behavior data of users, relations among commodities, relations among merchants, relations among users and relations among commodities and merchants;
inputting the behavior data of the users, the relationship among the commodities, the relationship among the merchants, the relationship among the users and the relationship among the commodities and the merchants into the graph neural network model for calculation to obtain a correlation score;
and recommending commodities to the user according to the relevance score.
7. A graphical neural network model building device for commodity recommendation, comprising a first processor and a first memory storing first program instructions, wherein the first processor is configured to execute the graphical neural network model building method for commodity recommendation according to any one of claims 1 to 4 when executing the first program instructions.
8. An apparatus for merchandise recommendation, comprising a second processor and a second memory storing second program instructions, characterized in that the second processor is configured to perform the method for merchandise recommendation according to claim 5 or 6 when executing the second program instructions.
9. An apparatus, characterized by comprising the graph neural network model building apparatus for commodity recommendation according to claim 7.
10. An apparatus, characterized in that it comprises a device for recommendation of goods according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011528670.2A CN112633978B (en) | 2020-12-22 | 2020-12-22 | Method, device and equipment for building graphic neural network model and method, device and equipment for recommending commodities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011528670.2A CN112633978B (en) | 2020-12-22 | 2020-12-22 | Method, device and equipment for building graphic neural network model and method, device and equipment for recommending commodities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633978A true CN112633978A (en) | 2021-04-09 |
| CN112633978B CN112633978B (en) | 2024-03-08 |
Family
ID=75321637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011528670.2A Active CN112633978B (en) | 2020-12-22 | 2020-12-22 | Method, device and equipment for building graphic neural network model and method, device and equipment for recommending commodities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633978B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239232A (en) * | 2021-05-17 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Graph neural network recommendation system, method and device, electronic equipment and storage medium |
| CN113409121A (en) * | 2021-06-29 | 2021-09-17 | 南京财经大学 | Cross-border e-commerce recommendation method based on heterogeneous graph expression learning |
| CN113934929A (en) * | 2021-09-30 | 2022-01-14 | 联想(北京)有限公司 | Recommendation method and device and electronic equipment |
| CN116611897A (en) * | 2023-07-19 | 2023-08-18 | 宜宾叙控科技有限公司 | Message reminding method and system based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180121798A1 (en) * | 2016-10-31 | 2018-05-03 | Microsoft Technology Licensing, Llc | Recommender system |
| CN110209926A (en) * | 2019-04-22 | 2019-09-06 | 北京三快在线科技有限公司 | Merchant recommendation method, device, electronic equipment and readable storage medium storing program for executing |
| WO2020073534A1 (en) * | 2018-10-12 | 2020-04-16 | 平安科技（深圳）有限公司 | Pushing method and apparatus based on re-clustering, and computer device and storage medium |
| CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
-
2020
- 2020-12-22 CN CN202011528670.2A patent/CN112633978B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180121798A1 (en) * | 2016-10-31 | 2018-05-03 | Microsoft Technology Licensing, Llc | Recommender system |
| WO2020073534A1 (en) * | 2018-10-12 | 2020-04-16 | 平安科技（深圳）有限公司 | Pushing method and apparatus based on re-clustering, and computer device and storage medium |
| CN110209926A (en) * | 2019-04-22 | 2019-09-06 | 北京三快在线科技有限公司 | Merchant recommendation method, device, electronic equipment and readable storage medium storing program for executing |
| CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| YIFAN WANG等: "DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation", 《CIKM\'20 :PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION&KNOWLEDGE MANAGEMANT》, 19 October 2020 (2020-10-19), pages 1605 - 1614, XP059104712, DOI: 10.1145/3340531.3411996 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239232A (en) * | 2021-05-17 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Graph neural network recommendation system, method and device, electronic equipment and storage medium |
| CN113239232B (en) * | 2021-05-17 | 2023-12-26 | 北京达佳互联信息技术有限公司 | System, method and device for recommending graph neural network, electronic equipment and storage medium |
| CN113409121A (en) * | 2021-06-29 | 2021-09-17 | 南京财经大学 | Cross-border e-commerce recommendation method based on heterogeneous graph expression learning |
| CN113934929A (en) * | 2021-09-30 | 2022-01-14 | 联想(北京)有限公司 | Recommendation method and device and electronic equipment |
| CN116611897A (en) * | 2023-07-19 | 2023-08-18 | 宜宾叙控科技有限公司 | Message reminding method and system based on artificial intelligence |
| CN116611897B (en) * | 2023-07-19 | 2023-10-13 | 北京快益通科技有限公司 | Message reminding method and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633978B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112633978A (en) | Graph neural network model construction method, and method, device and equipment for commodity recommendation | |
| US11170395B2 (en) | Digital banking platform and architecture | |
| Tuan et al. | 3D convolutional networks for session-based recommendation with content features | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| CN102317962B (en) | Machine optimization device, method and system | |
| CN111611472A (en) | Binding recommendation method and system based on graph convolution neural network | |
| EP2474945A1 (en) | Analyzing transactional data | |
| US20130138531A1 (en) | Social network-based recommendation | |
| CN106447463A (en) | Commodity recommendation method based on Markov decision-making process model | |
| CN110910199A (en) | Item information sorting method and device, computer equipment and storage medium | |
| CN107239993A (en) | A kind of matrix decomposition recommendation method and system based on expansion label | |
| CN111985622A (en) | Graph neural network training method and system | |
| US20120109959A1 (en) | Method and system for-clustering data arising from a database | |
| CN112801425B (en) | Method and device for determining information click rate, computer equipment and storage medium | |
| CN116561424A (en) | Recommendation method combining graph neural network with transducer and applied to intelligent recommendation system | |
| CN107025311A (en) | A kind of Bayes's personalized recommendation method and device based on k nearest neighbor | |
| Lopes et al. | Efficient Bayesian methods for graph-based recommendation | |
| Syah | Optimization Tree Based Inference to Customer Behaviors in Dynamic Control System | |
| Merigo et al. | Decision making in the European Union under risk and uncertainty | |
| CN109063120A (en) | A kind of collaborative filtering recommending method and device based on cluster | |
| CN112801803B (en) | Financial product recommendation method and device | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN112669127B (en) | Method, device and equipment for commodity recommendation | |
| KR102592129B1 (en) | system for recommending clothing based on artificial intelligence |
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 |