CN114936907B - Commodity recommendation method and system based on node type interaction - Google Patents
Commodity recommendation method and system based on node type interaction Download PDFInfo
- Publication number
- CN114936907B CN114936907B CN202210674885.8A CN202210674885A CN114936907B CN 114936907 B CN114936907 B CN 114936907B CN 202210674885 A CN202210674885 A CN 202210674885A CN 114936907 B CN114936907 B CN 114936907B
- Authority
- CN
- China
- Prior art keywords
- node
- type
- nodes
- commodity
- type interaction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006870 function Effects 0.000 claims abstract description 31
- 238000006243 chemical reaction Methods 0.000 claims abstract description 27
- 230000006399 behavior Effects 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 230000004931 aggregating effect Effects 0.000 claims abstract description 5
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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]
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a commodity recommendation method and system based on node type interaction, comprising the following steps: constructing a heterogeneous information network by taking commodity types, shops and user types as nodes and taking user behaviors as edges; after the feature conversion is carried out on the nodes of different types, mapping all the nodes to the same feature space; constructing type interaction functions among users, commodities, stores and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assigning weights to the nodes after the type interactions according to the edge types; and aggregating neighbor node information of the weighted nodes, updating the heterogeneous information network, and recommending the commodity according to the commodity recommendation task by adopting the updated heterogeneous information network. The recommendation method based on the meta-path is not limited, and feature conversion and interaction functions are designed aiming at node types, so that the acquired network information is more comprehensive, and the problems of data sparseness and cold start are relieved.
Description
Technical Field
The invention relates to the technical field of recommendation systems, in particular to a commodity recommendation method and system based on node type interaction.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The recommendation system learns user preferences, digs potential demands of users deeply, predicts articles interested by the users and makes personalized recommendation for the users. On the network, people can browse and select articles meeting the requirements of themselves from various articles, but with the advent of big data age, the information quantity is increased in an explosive manner, and the general quantity and various types of data are mixed together, so that more purchasing choices are provided for users on one hand, and difficulty in selecting articles and filtering information is improved for users on the other hand.
The commodity-based recommendation system belongs to a heterogeneous information network and consists of various types of nodes and various types of connecting edges. Such as nodes containing items, users, etc., and connecting edges containing clicks, purchases, concerns, etc. The nodes are analyzed according to different visual angles and also have different attribute information, the articles can have attribute information such as clothes, foods, skin care products and the like or attribute information such as necessary commodities and unnecessary commodities and the like, the users can have attribute information such as teenagers, middle-aged and elderly people and the like or attribute information such as students and office workers and the like, and the shops can have attribute information such as men's wear, women's wear and the like or attribute information such as clothes, food and the like.
The basic step of commodity recommendation is to firstly model user-commodity interaction data and all auxiliary information into a heterogeneous information network in a unified way, and then extract network information to design a proper recommendation model. The recommendation based on the heterogeneous information network generally uses a manual designed meta-path to extract network information, but the method has high complexity, and because the heterogeneous information network contains abundant semantic information, a plurality of meta-paths are difficult to exhaust, and the problem of information loss is easy to generate in the process of searching neighbor nodes of a target vertex by using the meta-paths.
Disclosure of Invention
In order to solve the problems, the invention provides a commodity recommendation method and a commodity recommendation system based on node type interaction, which are used for improving the comprehensiveness and accuracy of information acquired by a recommendation system, are not limited to a recommendation method based on a meta-path, and are used for designing feature conversion and interaction functions aiming at the node type, so that the acquired network information is more comprehensive, and the problems of sparse data and cold start are solved.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
In a first aspect, the present invention provides a commodity recommendation method based on node type interaction, including:
constructing a heterogeneous information network by taking commodity types, shops and user types as nodes and taking user behaviors as edges;
After the feature conversion is carried out on the nodes of different types, mapping all the nodes to the same feature space;
Constructing type interaction functions among users, commodities, stores and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assigning weights to the nodes after the type interactions according to the edge types;
and aggregating neighbor node information of the weighted nodes, updating the heterogeneous information network, and recommending the commodity according to the commodity recommendation task by adopting the updated heterogeneous information network.
As an alternative embodiment, each type of node designs a feature transfer functionSuch that each node maps to a d-dimensional vector; feature/>, after feature conversion, of node iThe method comprises the following steps: /(I)Where h i is the initial characteristic of node i.
As an alternative embodiment, the type interaction function H (a u,ag) between the user and the commodity is:
the user-store type interaction function H (a u,as) is:
the type interaction function H (a g,as) between the goods and stores is:
where k j、ki represents two different types of node features that perform type interactions, respectively.
As an alternative embodiment, the node characteristics after the type interaction include:
For node i of the user type, the characteristics h i' (u) after type interaction are expressed as:
For a node i of the commodity type, the characteristics h i' (g) after type interaction are expressed as:
For node i of the store type, the characteristics h i'(s) after type interaction are expressed as:
Wherein, And the characteristics of the node i after the characteristic conversion.
As an alternative embodiment, the characteristic h i "of the weighted node is expressed as: Wherein h i' is the node characteristic after type interaction,/> Is the normalized weight.
As an alternative embodiment, the weights are: where W is the weight matrix and b is the bias vector.
As an alternative embodiment, features after aggregating neighbor node informationExpressed as:
Wherein h i' is the characteristic of the weighted node, For the feature of the node i after feature conversion, H (a i,aj) is a type interaction function of type a i and type a j.
In a second aspect, the present invention provides a commodity recommendation system based on node type interaction, including:
The network construction module is configured to construct a heterogeneous information network by taking commodity types, stores and user types as nodes and taking user behaviors as sides;
The feature conversion module is configured to map all nodes to the same feature space after performing feature conversion on the nodes of different types;
The type interaction module is configured to construct type interaction functions among users, commodities, users, shops and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assign weights to the nodes after the type interactions according to the edge types;
And the information aggregation module is configured to aggregate neighbor node information of the weighted nodes, update the heterogeneous information network and conduct commodity recommendation according to commodity recommendation tasks by adopting the updated heterogeneous information network.
In a third aspect, the invention provides an electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the method of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions which, when executed by a processor, perform the method of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a commodity recommendation method and a commodity recommendation system based on node type interaction, which are used for designing a type interaction function aiming at the node type, so that the acquired network information is more comprehensive, the problems of sparse data and cold start are relieved, and recommendation results are interpretable and trace-circulated.
Big data contains abundant semantic information, and extracting semantic information through meta-paths generally selects meta-paths with rich connection relations and strong semantic characteristics, but more domain knowledge is required for finding such meta-paths. The invention gets rid of the dependence on the meta-path, avoids the complexity of manually designing the meta-path, and extracts more comprehensive network information representation.
The commodity recommending method and system based on node type interaction, provided by the invention, is focused on extracting node information, and rich semantic relations are learned for recommending tasks by keeping the structural characteristics of a network mode.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a commodity recommendation method based on node type interaction provided in embodiment 1 of the present invention;
fig. 2 is a diagram of a heterogeneous information network according to embodiment 1 of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. 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 present invention. As used herein, unless the context clearly indicates otherwise, the singular forms also are intended to include the plural forms, and furthermore, it is to be understood that the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, such as, for example, processes, methods, systems, products or devices that comprise a series of steps or units, are not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or inherent to such processes, methods, products or devices.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
The embodiment provides a commodity recommendation method based on node type interaction, which aims to improve the comprehensiveness and accuracy of information acquired by a recommendation system, is not limited by a recommendation method based on a meta-path, and is used for designing an interaction function aiming at the node type, so that the acquired network information is more comprehensive, and the problems of sparse data and cold start are solved.
As shown in fig. 1, the method specifically includes:
constructing a heterogeneous information network by taking commodity types, shops and user types as nodes and taking user behaviors as edges;
After the feature conversion is carried out on the nodes of different types, mapping all the nodes to the same feature space;
Constructing type interaction functions among users, commodities, stores and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assigning weights to the nodes after the type interactions according to the edge types;
and aggregating neighbor node information of the weighted nodes, updating the heterogeneous information network, and recommending the commodity according to the commodity recommendation task by adopting the updated heterogeneous information network.
In this embodiment, the commodity types include food, make-up, clothes, stationery, numbers, etc., the user includes young and young men and children, the store corresponds to the commodity type, the user behavior includes purchase, collection, putting on shelf, paying attention, etc., and the heterogeneous information network is constructed as shown in fig. 2.
Heterogeneous information networks are represented asWherein/>Representing a node set, epsilon representing an edge set;
setting the node type mapping function and the connection edge type mapping function as respectively Wherein the method comprises the steps ofRepresenting a set of node types,/>A set representing connection edge types; for two adjacent nodes/>Let its node type be a i、aj, connection edge be e= (i, j, r i,j) ∈epsilon, and connection edge be r i,j.
It can be understood that all the data are obtained and legally applied on the basis of meeting laws and regulations and agreements of users.
In this embodiment, the feature transfer function C is designed for different types of nodes of commodity type, store and user type; because the recommended data types are complex, the feature spaces of the nodes of different types are different, and the graph is designedThe initial characteristics of the intermediate nodes i and j are h i、hj respectively, and the node types are classified as/>Designing feature transfer functions for each type of nodeMake/>Mapping all types of nodes into the same feature space, namely mapping each node into a d-dimensional vector;
specifically, the characteristics of the nodes i and j after characteristic conversion are expressed as follows:
in the present embodiment, the type interaction functions H (a u,ag)、H(au,as) and H (a g,as) between the user-commodity, and the commodity-commodity are respectively constructed to learn the correlation and the conversion relationship between the user, the commodity, and the commodity, respectively;
Specifically, the type interaction function H (a u,ag) between the user-commodity nodes is:
The type interaction function H (a u,as) between the user-store nodes is:
The type interaction function H (a g,as) between commodity-store nodes is:
where k j、ki represents two different types of node features that perform type interactions, respectively.
For node i belonging to the user type, the characteristics after interaction are expressed as:
for a node i belonging to a commodity type, the characteristics after interaction are expressed as follows:
for node i belonging to the store type, its interacted features are expressed as:
In the embodiment, weighting is carried out on the nodes after type interaction according to the types of the edges; namely:
Wherein, Is the normalized weight;
where W is the weight matrix and b is the bias vector.
In this embodiment, aggregation of neighbor node information is performed on the weighted nodes to obtain high-order semantic information of the nodes. The neighbor nodes are nodes connected with the node i, node information connected with the node i is aggregated, and meanwhile, a self-ring is added for each node, so that the node keeps own characteristics, extracts more abundant attribute information of the network, and has a certain effect of alleviating the cold start problem.
The characteristics after the neighbor node information is aggregated are expressed as follows:
In this embodiment, according to the above processing on the nodes, the heterogeneous information network is updated, and optimization is performed through the cross entropy loss function, so that after the commodity is ordered according to the commodity recommending task, the top-k recommending strategy is combined for recommending.
Example 2
The embodiment provides a commodity recommendation system based on node type interaction, which comprises the following steps:
The network construction module is configured to construct a heterogeneous information network by taking commodity types, stores and user types as nodes and taking user behaviors as sides;
The feature conversion module is configured to map all nodes to the same feature space after performing feature conversion on the nodes of different types;
The type interaction module is configured to construct type interaction functions among users, commodities, users, shops and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assign weights to the nodes after the type interactions according to the edge types;
And the information aggregation module is configured to aggregate neighbor node information of the weighted nodes, update the heterogeneous information network and conduct commodity recommendation according to commodity recommendation tasks by adopting the updated heterogeneous information network.
It should be noted that the above modules correspond to the steps described in embodiment 1, and the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in embodiment 1. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
In further embodiments, there is also provided:
An electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the method described in embodiment 1. For brevity, the description is omitted here.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include read only memory and random access memory and provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method described in embodiment 1.
The method in embodiment 1 may be directly embodied as a hardware processor executing or executed with a combination of hardware and software modules in the processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.
Those of ordinary skill in the art will appreciate that the elements of the various examples described in connection with the present embodiments, i.e., the algorithm steps, can be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends 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 present application.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (9)
1. The commodity recommendation method based on node type interaction is characterized by comprising the following steps of:
constructing a heterogeneous information network by taking commodity types, shops and user types as nodes and taking user behaviors as edges;
After the feature conversion is carried out on the nodes of different types, mapping all the nodes to the same feature space;
Constructing type interaction functions among users, commodities, stores and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assigning weights to the nodes after the type interactions according to the edge types;
The method comprises the steps that aggregation of neighbor node information is conducted on nodes after weighting, a heterogeneous information network is updated, and commodity recommendation is conducted according to commodity recommendation tasks by means of the updated heterogeneous information network;
the type interaction function H (a u,ag) between the user and the commodity is:
the user-store type interaction function H (a u,as) is:
the type interaction function H (a g,as) between the goods and stores is:
where k j、ki represents two different types of node features that perform type interactions, respectively.
2. The commodity recommendation method based on node type interactions as claimed in claim 1, wherein each type of node design feature transfer functionSuch that each node maps to a d-dimensional vector; feature/>, after feature conversion, of node iThe method comprises the following steps: /(I)Where h i is the initial characteristic of node i.
3. The commodity recommendation method based on node type interaction according to claim 1, wherein the node characteristics after the type interaction comprise:
For node i of the user type, the characteristics h i' (u) after type interaction are expressed as:
For a node i of the commodity type, the characteristics h i' (g) after type interaction are expressed as:
For node i of the store type, the characteristics h i'(s) after type interaction are expressed as:
Wherein, And the characteristics of the node i after the characteristic conversion.
4. The commodity recommendation method based on node type interaction according to claim 1, wherein the characteristic h i "of the weighted node is expressed as: Wherein h i' is the node characteristic after type interaction,/> Is the normalized weight.
5. The commodity recommendation method based on node type interaction according to claim 4, wherein the weights are: where W is the weight matrix and b is the bias vector.
6. The commodity recommending method based on node type interaction as claimed in claim 1, wherein the feature after aggregating neighbor node information is as followsExpressed as:
Wherein h i' is the characteristic of the weighted node, For the feature of the node i after feature conversion, H (a i,aj) is a type interaction function of type a i and type a j.
7. A commodity recommendation system based on node type interactions, comprising:
The network construction module is configured to construct a heterogeneous information network by taking commodity types, stores and user types as nodes and taking user behaviors as sides;
The feature conversion module is configured to map all nodes to the same feature space after performing feature conversion on the nodes of different types;
The type interaction module is configured to construct type interaction functions among users, commodities, users, shops and commodities, so as to perform different types of type interactions on the node characteristics after the characteristic conversion, and assign weights to the nodes after the type interactions according to the edge types;
The information aggregation module is configured to aggregate neighbor node information of the weighted nodes, update the heterogeneous information network, and conduct commodity recommendation according to commodity recommendation tasks by adopting the updated heterogeneous information network;
the type interaction function H (a u,ag) between the user and the commodity is:
the user-store type interaction function H (a u,as) is:
the type interaction function H (a g,as) between the goods and stores is:
where k j、ki represents two different types of node features that perform type interactions, respectively.
8. An electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the method of any one of claims 1-6.
9. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210674885.8A CN114936907B (en) | 2022-06-15 | 2022-06-15 | Commodity recommendation method and system based on node type interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210674885.8A CN114936907B (en) | 2022-06-15 | 2022-06-15 | Commodity recommendation method and system based on node type interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114936907A CN114936907A (en) | 2022-08-23 |
| CN114936907B true CN114936907B (en) | 2024-04-30 |
Family
ID=82866105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210674885.8A Active CN114936907B (en) | 2022-06-15 | 2022-06-15 | Commodity recommendation method and system based on node type interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114936907B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7505921B1 (en) * | 2000-03-03 | 2009-03-17 | Finali Corporation | System and method for optimizing a product configuration |
| CN107944629A (en) * | 2017-11-30 | 2018-04-20 | 北京邮电大学 | A kind of recommendation method and device based on heterogeneous information network representation |
| CN111538827A (en) * | 2020-04-28 | 2020-08-14 | 清华大学 | Case recommendation method and device based on content and graph neural network and storage medium |
| CN112131480A (en) * | 2020-09-30 | 2020-12-25 | 中国海洋大学 | Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning |
| CN112800207A (en) * | 2021-01-13 | 2021-05-14 | 桂林电子科技大学 | Commodity information recommendation method and device and storage medium |
| CN112948625A (en) * | 2021-02-01 | 2021-06-11 | 重庆邮电大学 | Film recommendation method based on attribute heterogeneous information network embedding |
| CN112989842A (en) * | 2021-02-25 | 2021-06-18 | 电子科技大学 | Construction method of universal embedded framework of multi-semantic heterogeneous graph |
| CN113362131A (en) * | 2021-06-02 | 2021-09-07 | 合肥工业大学 | Intelligent commodity recommendation method based on map model and integrating knowledge map and user interaction |
| CN113641920A (en) * | 2021-10-13 | 2021-11-12 | 中南大学 | Commodity personalized recommendation method and system based on community discovery and graph neural network |
| CN114386513A (en) * | 2022-01-13 | 2022-04-22 | 吉林大学 | Interactive grading prediction method and system integrating comment and grading |
-
2022
- 2022-06-15 CN CN202210674885.8A patent/CN114936907B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7505921B1 (en) * | 2000-03-03 | 2009-03-17 | Finali Corporation | System and method for optimizing a product configuration |
| CN107944629A (en) * | 2017-11-30 | 2018-04-20 | 北京邮电大学 | A kind of recommendation method and device based on heterogeneous information network representation |
| CN111538827A (en) * | 2020-04-28 | 2020-08-14 | 清华大学 | Case recommendation method and device based on content and graph neural network and storage medium |
| CN112131480A (en) * | 2020-09-30 | 2020-12-25 | 中国海洋大学 | Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning |
| CN112800207A (en) * | 2021-01-13 | 2021-05-14 | 桂林电子科技大学 | Commodity information recommendation method and device and storage medium |
| CN112948625A (en) * | 2021-02-01 | 2021-06-11 | 重庆邮电大学 | Film recommendation method based on attribute heterogeneous information network embedding |
| CN112989842A (en) * | 2021-02-25 | 2021-06-18 | 电子科技大学 | Construction method of universal embedded framework of multi-semantic heterogeneous graph |
| CN113362131A (en) * | 2021-06-02 | 2021-09-07 | 合肥工业大学 | Intelligent commodity recommendation method based on map model and integrating knowledge map and user interaction |
| CN113641920A (en) * | 2021-10-13 | 2021-11-12 | 中南大学 | Commodity personalized recommendation method and system based on community discovery and graph neural network |
| CN114386513A (en) * | 2022-01-13 | 2022-04-22 | 吉林大学 | Interactive grading prediction method and system integrating comment and grading |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114936907A (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mao et al. | Multiobjective e-commerce recommendations based on hypergraph ranking | |
| Zheng et al. | A novel social network hybrid recommender system based on hypergraph topologic structure | |
| Ma et al. | Combining tag correlation and user social relation for microblog recommendation | |
| CN107590243B (en) | The personalized service recommendation method to be sorted based on random walk and diversity figure | |
| Dao et al. | A novel recommendation model of location-based advertising: Context-Aware Collaborative Filtering using GA approach | |
| US8478785B2 (en) | Measuring node proximity on graphs with side information | |
| CN102929939B (en) | The offer method and device of customized information | |
| Mustafa et al. | Collaborative filtering: Techniques and applications | |
| Yu | The dynamic competitive recommendation algorithm in social network services | |
| CN103353872B (en) | A kind of teaching resource personalized recommendation method based on neutral net | |
| US20160259857A1 (en) | User recommendation using a multi-view deep learning framework | |
| CN106600302A (en) | Hadoop-based commodity recommendation system | |
| CN112613602A (en) | Recommendation method and system based on knowledge-aware hypergraph neural network | |
| Kaya | A hotel recommendation system based on customer location: a link prediction approach | |
| US9767417B1 (en) | Category predictions for user behavior | |
| US9767204B1 (en) | Category predictions identifying a search frequency | |
| CN106844407A (en) | Label network production method and system based on data set correlation | |
| Khatter et al. | An intelligent personalized web blog searching technique using fuzzy-based feedback recurrent neural network | |
| US10474670B1 (en) | Category predictions with browse node probabilities | |
| Liang et al. | Collaborative filtering based on information-theoretic co-clustering | |
| Ben-Shimon et al. | An ensemble method for top-N recommendations from the SVD | |
| CN115689673A (en) | Recommendation method, system, medium and device based on ranking contrast loss | |
| Li et al. | Learning user preferences across multiple aspects for merchant recommendation | |
| Huang et al. | Expected hitting times for random walks on quadrilateral graphs and their applications | |
| US10387934B1 (en) | Method medium and system for category prediction for a changed shopping mission |
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 |