CN113191838A - Shopping recommendation method and system based on heterogeneous graph neural network - Google Patents
Shopping recommendation method and system based on heterogeneous graph neural network Download PDFInfo
- Publication number
- CN113191838A CN113191838A CN202110383787.4A CN202110383787A CN113191838A CN 113191838 A CN113191838 A CN 113191838A CN 202110383787 A CN202110383787 A CN 202110383787A CN 113191838 A CN113191838 A CN 113191838A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- neural network
- behavior
- feature vector
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 108
- 230000006399 behavior Effects 0.000 claims abstract description 87
- 238000012549 training Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 239000010410 layer Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000002356 single layer Substances 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
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a shopping recommendation method and system based on a heterogeneous graph neural network, wherein the method comprises the following steps: acquiring historical behavior records of a plurality of users for commodities, and dividing the historical behavior records into a plurality of data sets according to behaviors of the users for the commodities; for each behavior, generating initial user, commodity and user-to-commodity behavior relation characteristic vectors according to the corresponding data sets respectively; training by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the relationship between the user and the commodity; splicing the final user and commodity feature vectors to obtain a user-commodity feature vector; and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector. According to the invention, different users, commodities and commodity-to-commodity behavior relations form a heterogeneous graph, and link prediction of the relation between the users and the commodities is carried out based on the graph convolution neural network, so that richer information can be introduced, and the recommendation precision is higher.
Description
Technical Field
The invention belongs to the technical field of personalized data recommendation, and particularly relates to a shopping recommendation method and system based on a heterogeneous graph neural network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Compared with the traditional shopping websites, the types of commodities, the quantity of commodities and information of other dimensions on the platform in the e-commerce platform are remarkably increased, and the users cannot quickly and accurately find the commodities suitable for the users from the e-commerce website. In order to solve the problem, the recommendation system gradually plays an important role in the application process of the e-commerce website, and therefore, a personalized recommendation algorithm behind the recommendation system becomes a hot point of research.
The traditional recommendation algorithms such as collaborative filtering algorithm, factorization machine algorithm and the like often cannot mine the deep interests of users, and the cold start problem brought by new users or new commodities is not well solved. By means of the strong characterization capability of the neural network, the combination of deep learning and a recommendation system enables the latest recommendation algorithm to generate better effect, but existing deep learning algorithm models such as PNN, NCF and the like only use a multilayer neural network to perform deep level intersection of multiple modes on project characteristics, although new characteristic information is generated by combination, the expression capability of the models is stronger than that of the traditional method, but more other types of information are not introduced, and further research and explanation on the types of operations in the models are not performed. That is to say, the existing recommendation algorithm still has the problems of inaccurate recommendation, weak generalization capability, incapability of mining deep interests of users and the like.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a shopping recommendation method and system based on a heterogeneous graph neural network. The characteristics of different users, the characteristics of different commodities and the different types of relationship characteristics between the users and the commodities form a heterogeneous graph, the link prediction of the relationship between the users and the commodities is carried out in a graph convolution neural network mode, the commodities which the users are interested in are recommended finally, and richer information is introduced.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
a shopping recommendation method based on a heterogeneous graph neural network comprises the following steps:
acquiring historical behavior records of a plurality of users for commodities;
generating initial user, commodity and commodity-to-commodity behavior relation characteristic vectors according to the historical behavior records;
training by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the relationship between the user and the commodity;
splicing the final user and commodity feature vectors to obtain a user-commodity feature vector;
and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
Further, based on the user identification information, the commodity identification information and the user-to-commodity behavior relation information, an initial user characteristic vector, an initial commodity characteristic vector and an initial user-to-commodity behavior relation characteristic vector are generated.
Further, the graph convolution neural network comprises a plurality of sub-graph convolution neural networks with the same number of layers, the number of the sub-graph convolution neural networks is the same as the number of behaviors of the user on the commodity, and the sub-graph convolution neural networks are respectively used for training to obtain a third final feature vector based on the initial user, the initial commodity and two of the feature vectors of the behavior relation of the user on the commodity.
Furthermore, an adjacency matrix of the behavior relation between the user and the commodity is generated according to the plurality of data sets and is used as a parameter of the graph convolution neural network.
Further, after the final characteristic vector of the behavior relation of the user to the commodity is obtained, an attention mechanism is applied to processing.
Further, obtaining the score prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector comprises: and performing product operation on the user-commodity feature vector and the commodity behavior relation feature vector of the user to obtain a scoring prediction matrix.
Further, the method further comprises: recommending commodities to the user according to the scoring prediction matrix, wherein the recommending comprises the following steps: and recommending the commodities with the highest scores to the users according to the scores of the commodities corresponding to the users according to the score prediction matrix.
One or more embodiments provide a shopping recommendation system based on a heterogeneous graph neural network, including:
the data acquisition module is configured to acquire historical behavior records of a plurality of users for the commodities and divide the historical behavior records into a plurality of data sets according to behaviors of the users for the commodities;
the initial vector training module is configured to generate initial user, commodity and user-to-commodity behavior relation feature vectors according to corresponding data sets for each behavior;
the final vector training module is configured to train by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the behavior relation of the user to the commodity;
the recommendation score prediction module is configured to splice the final user and commodity feature vectors to obtain a user-commodity feature vector; and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
One or more embodiments provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the shopping recommendation method based on the heterogeneous graph neural network when executing the program.
One or more embodiments provide a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the heterogeneous graph neural network-based shopping recommendation method.
The above one or more technical solutions have the following beneficial effects:
the characteristics of different users, the characteristics of different commodities and the different types of relationship characteristics between the users and the commodities form a heterogeneous graph, the link prediction of the relationship between the users and the commodities is carried out in a graph convolution neural network mode, and the commodities which the users are interested in are finally recommended, so that the characteristic vectors can be fused with the information of adjacent nodes in the heterogeneous graph, and the heterogeneous graph is richer.
The user is taken into consideration of the types of the commodity behavior relations, and weights are given to the different types of behavior relations by adopting an attention mechanism, so that the memory capacity and generalization capacity of the recommendation effect can be effectively improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow diagram of a shopping recommendation method based on a heterogeneous graph neural network in one or more embodiments of the present invention;
fig. 2 is a schematic diagram illustrating a process of performing score prediction based on a graph convolution neural network according to one or more embodiments of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
The embodiment discloses a shopping recommendation method based on a heterogeneous graph neural network, which comprises the following steps as shown in fig. 1:
step 1: acquiring historical behavior records of a plurality of users for commodities, and dividing the behaviors of the commodities according to the users to obtain corresponding relationship data of the users and the commodities corresponding to the behaviors;
in this embodiment, the user extracts the historical behavior of the commodity through the log of the e-commerce platform. The actions for the good include: the shopping method comprises the following steps of purchasing behaviors of users, adding commodities to a shopping cart by the users and clicking the commodities by the users for checking.
According to the behavior classification storage, specifically, the data set corresponding to each behavior should be sorted in a table form, where the first column is the id of the user, and the following columns represent the commodities that the user of the current id has acted on, respectively, for example, the behavior record purchased by the user may be expressed as: the user id followed by the plurality of article ids indicates that the specified user has performed operations on the plurality of articles.
Step 2: generating initial user, commodity and commodity-to-commodity behavior relation characteristic vectors according to the historical behavior records;
we apply the idea of Item2vec to train and generate an initial vector e of user characteristics by taking a historical behavior record of a user as a sampleuInitial vector e of commodity featurevAnd initial vector e of user to commodity behavior relation characteristicr. Specifically, an initial user characteristic vector, an initial commodity characteristic vector and an initial user-to-commodity behavior relation characteristic vector are generated based on user identification information, commodity identification information and user-to-commodity behavior relation information.
And step 3: according to the initial characteristic vectors of the user, the commodity and the relation of the user to the commodity behavior, a final characteristic vector of the user, the commodity and the relation of the user to the commodity behavior is obtained by adopting graph convolution neural network training;
we apply the graph convolutional neural network GCN to the heterogeneous maps for recommendation. And respectively applying different graph convolution neural networks to the purchasing behavior of the user, the behavior of adding the user to the shopping cart and the behavior of clicking the commodity by the user to extract the feature vectors. The characteristics of the commodity form a vector matrix E, the parameters are set as W, and the formula of the single-layer graph convolution neural network is defined as follows:
E(l)＝σ(AE(l-1)W(l))
wherein E islAnd E(l-1)Respectively represent the ith layer GCN and the ith-1 layer GCN, and sigma is the Relu activation function
Firstly, the user commodity behavior data set obtained in the first step is subjected to graph convolution operation, because the historical data obtained in the first step is presented in a table mode, and according to the conversion between the adjacency list representation of the graph and the adjacency matrix representation of the graph, the adjacency matrix representation of the behavior relation between the user and the commodity can be easily obtained, corresponding rows and columns are respectively represented by id vectors corresponding to the user and the commodity, and the obtained adjacency matrix representation is the parameter A in the graph convolution neural network.
The graph convolution neural network adopted in the embodiment includes a plurality of sub-graph convolution neural networks with the same layer number. The number of the sub-graph convolutional neural networks is the same as the number of behaviors of the user on the commodity. In this embodiment, the graph convolution neural network includes 3 sub-graph convolution neural networks, and a third final feature vector is obtained based on initial user, commodity, and two training of the user on the commodity behavior relationship feature vectors, and these result vectors are used as a candidate set in the personalized recall stage. After obtaining 3 initial vectors, we train the remaining one vector for l times by respectively using two vectors as parameters of the sub-GCN. As shown in fig. 2, the first sub-graph neural network is used to obtain a final user feature vector based on < r1, r2, r3>, and < v1, v2, v3> training, and the second and third sub-graph neural networks are used to obtain a final commodity feature vector and a user-to-commodity behavior relationship feature vector, respectively. Here, taking training the user vector as an example, the training mode of other vectors is the same, and the GCN for training the user vector has the following formula:
wherein N isuAnd NvRespectively representing the set of all direct neighbors of user u and commodity i in the heterogeneous graph,
and expressing the multiplication of corresponding elements of the matrix, wherein the sigma is a Relu activation function. Note that here we are the final formula obtained after applying the parameter a obtained above to the GCN basic formula and finishing.
After each initial vector is trained for l times by a corresponding GCN network layer, the final vector representations obtained are respectively as follows:
and
according to the GCN principle, the vectors at the moment are fused with the information of the adjacent nodes in the heterogeneous graph, so that the vector representation information of the candidate set is richer at the moment.
And 4, step 4: splicing the final user and commodity feature vectors to obtain user-commodity feature vectors, and simultaneously applying an attention mechanism to the commodity behavior relation feature vectors for processing by the user;
in step 3, we have trained separately to obtain representations of user vectors and commodity vectors, which are independent, so here we first splice the user vectors and commodity vectors to obtain a new vector, denoted as euv。
Since we finally aim to consider whether the user purchases the goods as whether to push the userAnd (4) a recommended judgment standard, so that the user applies an attention mechanism to the commodity behavior relation characteristic vector for processing, different weights are given to different kinds of relation vectors, the purchasing behavior is greater than the shopping cart adding behavior and greater than the viewing behavior, the final behavior relation vector representation is obtained by weighting and summing, and the behavior relation vector representation is marked as erf。
And 5: and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
After the two final vectors are obtained, product operation is carried out on the two final vectors, the product operation result is used as v score prediction of a user u on a specified commodity, then sorting is carried out according to the predicted scores, and the sorted top k vectors are recommended to the user.
The product operation formula is as follows:
wherein
Representing the predicted score for user u versus user v.
Example two
The embodiment aims to provide a shopping recommendation system based on a heterogeneous graph neural network. The system comprises:
the data acquisition module is configured to acquire historical behavior records of a plurality of users for commodities;
the initial vector training module is configured to generate initial user, commodity and user-to-commodity behavior relation feature vectors according to the historical behavior records;
the final vector training module is configured to train by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the behavior relation of the user to the commodity;
the recommendation score prediction module is configured to splice the final user and commodity feature vectors to obtain a user-commodity feature vector; and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
EXAMPLE III
The embodiment aims at providing an electronic device.
An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the shopping recommendation method based on the allopatric graph neural network according to an embodiment.
Example four
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements a shopping recommendation method based on a heterogeneous graph neural network according to an embodiment one.
The steps involved in the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
According to the technical scheme, various information is considered and added on the basis of considering the target characteristics. For example, a user a purchases a book of ' how well the steel is trained ', a user B adds a shopping cart to the book of ' how well the steel is trained ', the user B clicks and checks ' kubernets authority guideline ', and the behavior preference of the user on the book of kubernets authority guideline ' is also considered.
The technical scheme makes full use of the data records generated by the user on the E-commerce platform, not only combines the characteristics of the user and the commodity entity, but also considers the relationship characteristics between the user and the commodity entity. More importantly, the influence of the type of the relationship on the preference of the user is also considered, although the behavior preference of the user on the commodity can be explained by operations of adding a shopping cart, clicking to check and the like by the user, the above technical scheme only takes the operation as an auxiliary factor, increases the weight of purchasing behavior by adopting an attention mechanism, and predicts whether the user purchases the commodity, so that a conclusion whether the commodity is recommended to the user is obtained, and the recommendation effect is more accurate by considering the type of the relationship.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A shopping recommendation method based on a heterogeneous graph neural network is characterized by comprising the following steps:
acquiring historical behavior records of a plurality of users for commodities;
generating initial user, commodity and commodity-to-commodity behavior relation characteristic vectors according to the historical behavior records;
training by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the relationship between the user and the commodity;
splicing the final user and commodity feature vectors to obtain a user-commodity feature vector;
and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
2. The shopping recommendation method based on the heterogeneous graph neural network as claimed in claim 1, wherein the initial user feature vector, the initial commodity feature vector and the initial user-to-commodity behavior relationship feature vector are generated based on the user identification information, the commodity identification information and the user-to-commodity behavior relationship information.
3. The shopping recommendation method based on heterogeneous graph neural network as claimed in claim 1, wherein the graph convolutional neural network comprises a plurality of sub-graph convolutional neural networks with the same number of layers, the number of the sub-graph convolutional neural networks is the same as the number of behaviors of the user on the commodity, and the sub-graph convolutional neural networks are respectively used for obtaining a third final feature vector based on two training in the initial user, commodity and user-to-commodity behavior relationship feature vectors.
4. The shopping recommendation method based on heterogeneous graph neural network as claimed in claim 3, wherein based on the historical behavior record, an adjacency matrix of behavior relationship between users and commodities is generated according to behaviors of the users on the commodities as parameters of the graph convolution neural network.
5. The shopping recommendation method based on heterogeneous graph neural network as claimed in claim 1, wherein after the final user behavior relation feature vector to the commodity is obtained, an attention mechanism is applied for processing.
6. The shopping recommendation method based on the heterogeneous graph neural network as claimed in claim 1, wherein obtaining the score prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relationship feature vector comprises: and performing product operation on the user-commodity feature vector and the commodity behavior relation feature vector of the user to obtain a scoring prediction matrix.
7. The heterogeneous graph neural network based shopping recommendation method of claim 1, further comprising: recommending commodities to the user according to the scoring prediction matrix, wherein the recommending comprises the following steps: and recommending the commodities with the highest scores to the users according to the scores of the commodities corresponding to the users according to the score prediction matrix.
8. A shopping recommendation system based on a heterogeneous graph neural network, comprising:
the data acquisition module is configured to acquire historical behavior records of a plurality of users for commodities;
the initial vector training module is configured to generate initial user, commodity and user-to-commodity behavior relation feature vectors according to the historical behavior records;
the final vector training module is configured to train by adopting a graph convolution neural network to obtain final user, commodity and a characteristic vector of the behavior relation of the user to the commodity;
the recommendation score prediction module is configured to splice the final user and commodity feature vectors to obtain a user-commodity feature vector; and obtaining the grade prediction of the user for each commodity according to the user-commodity feature vector and the user-commodity behavior relation feature vector.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the heterogeneous graph neural network based shopping recommendation method of any one of claims 1-7 when executing the program.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the shopping recommendation method based on the heterogeneous graph neural network according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383787.4A CN113191838B (en) | 2021-04-09 | 2021-04-09 | Shopping recommendation method and system based on heterogeneous graph neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383787.4A CN113191838B (en) | 2021-04-09 | 2021-04-09 | Shopping recommendation method and system based on heterogeneous graph neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191838A true CN113191838A (en) | 2021-07-30 |
| CN113191838B CN113191838B (en) | 2024-01-30 |
Family
ID=76975325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110383787.4A Active CN113191838B (en) | 2021-04-09 | 2021-04-09 | Shopping recommendation method and system based on heterogeneous graph neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191838B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113254803A (en) * | 2021-06-24 | 2021-08-13 | 暨南大学 | Social recommendation method based on multi-feature heterogeneous graph neural network |
| CN113643212A (en) * | 2021-08-27 | 2021-11-12 | 复旦大学 | Depth map noise reduction method based on map neural network |
| CN114580794A (en) * | 2022-05-05 | 2022-06-03 | 腾讯科技（深圳）有限公司 | Data processing method, apparatus, program product, computer device and medium |
| CN115080846A (en) * | 2022-05-30 | 2022-09-20 | 广州大学 | Scene information fused graph neural network clothing recommendation method |
| CN117557318A (en) * | 2023-12-29 | 2024-02-13 | 青岛巨商汇网络科技有限公司 | Management intelligent analysis method and system based on virtual shopping |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648163A (en) * | 2019-08-08 | 2020-01-03 | 中山大学 | Recommendation algorithm based on user comments |
| WO2020149897A1 (en) * | 2019-01-17 | 2020-07-23 | Visa International Service Association | A deep learning model for learning program embeddings |
| CN112380435A (en) * | 2020-11-16 | 2021-02-19 | 北京大学 | Literature recommendation method and recommendation system based on heterogeneous graph neural network |
-
2021
- 2021-04-09 CN CN202110383787.4A patent/CN113191838B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020149897A1 (en) * | 2019-01-17 | 2020-07-23 | Visa International Service Association | A deep learning model for learning program embeddings |
| CN110648163A (en) * | 2019-08-08 | 2020-01-03 | 中山大学 | Recommendation algorithm based on user comments |
| CN112380435A (en) * | 2020-11-16 | 2021-02-19 | 北京大学 | Literature recommendation method and recommendation system based on heterogeneous graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| SHAOHUA FAN ET.AL.: "Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation", 《KDD "19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113254803A (en) * | 2021-06-24 | 2021-08-13 | 暨南大学 | Social recommendation method based on multi-feature heterogeneous graph neural network |
| CN113643212A (en) * | 2021-08-27 | 2021-11-12 | 复旦大学 | Depth map noise reduction method based on map neural network |
| CN113643212B (en) * | 2021-08-27 | 2024-04-05 | 复旦大学 | Depth map noise reduction method based on map neural network |
| CN114580794A (en) * | 2022-05-05 | 2022-06-03 | 腾讯科技（深圳）有限公司 | Data processing method, apparatus, program product, computer device and medium |
| CN114580794B (en) * | 2022-05-05 | 2022-07-22 | 腾讯科技（深圳）有限公司 | Data processing method, apparatus, program product, computer device and medium |
| CN115080846A (en) * | 2022-05-30 | 2022-09-20 | 广州大学 | Scene information fused graph neural network clothing recommendation method |
| CN115080846B (en) * | 2022-05-30 | 2024-06-11 | 广州大学 | Scene information-fused graphic neural network clothing recommendation method |
| CN117557318A (en) * | 2023-12-29 | 2024-02-13 | 青岛巨商汇网络科技有限公司 | Management intelligent analysis method and system based on virtual shopping |
| CN117557318B (en) * | 2023-12-29 | 2024-06-11 | 青岛巨商汇网络科技有限公司 | Management intelligent analysis method and system based on virtual shopping |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191838B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113191838A (en) | Shopping recommendation method and system based on heterogeneous graph neural network | |
| CN110717098B (en) | Meta-path-based context-aware user modeling method and sequence recommendation method | |
| CN111461841A (en) | Article recommendation method, device, server and storage medium | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN111506820B (en) | Recommendation model, recommendation method, recommendation device, recommendation equipment and recommendation storage medium | |
| CN110008973B (en) | Model training method, method and device for determining target user based on model | |
| EP2960849A1 (en) | Method and system for recommending an item to a user | |
| CN108182634A (en) | A kind of training method for borrowing or lending money prediction model, debt-credit Forecasting Methodology and device | |
| CN105247507A (en) | Influence score of a brand | |
| CN113268656A (en) | User recommendation method and device, electronic equipment and computer storage medium | |
| EP4202725A1 (en) | Joint personalized search and recommendation with hypergraph convolutional networks | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN110598118A (en) | Resource object recommendation method and device and computer readable medium | |
| CN113609345B (en) | Target object association method and device, computing equipment and storage medium | |
| KR20200088134A (en) | An apparatus for improving way of product recommendation and a method thereof | |
| CN108920665A (en) | Recommendation score method and device based on network structure and comment text | |
| CN113129053B (en) | Information recommendation model training method, information recommendation method and storage medium | |
| CN105894310A (en) | Personalized recommendation method | |
| Xia et al. | Modeling consumer buying decision for recommendation based on multi-task deep learning | |
| EP2983123A1 (en) | Self transfer learning recommendation method and system | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN115238188A (en) | Object recommendation method and system and object recommendation model system | |
| Loukili et al. | Personalizing product recommendations using collaborative filtering in online retail: a machine learning approach | |
| CN111815410B (en) | Commodity recommendation method based on selective neighborhood information | |
| CN111931035B (en) | Service recommendation method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240904 Address after: 230000 b-1018, Woye Garden commercial office building, 81 Ganquan Road, Shushan District, Hefei City, Anhui Province Patentee after: HEFEI WISDOM DRAGON MACHINERY DESIGN Co.,Ltd. Country or region after: China Address before: 250014 No. 88, Wenhua East Road, Lixia District, Shandong, Ji'nan Patentee before: SHANDONG NORMAL University Country or region before: China |
|
| TR01 | Transfer of patent right |