CN116089722B - Implementation method, device, computing equipment and storage medium based on graph yield label - Google Patents
Implementation method, device, computing equipment and storage medium based on graph yield label Download PDFInfo
- Publication number
- CN116089722B CN116089722B CN202310117848.1A CN202310117848A CN116089722B CN 116089722 B CN116089722 B CN 116089722B CN 202310117848 A CN202310117848 A CN 202310117848A CN 116089722 B CN116089722 B CN 116089722B
- Authority
- CN
- China
- Prior art keywords
- node
- label
- path
- probability
- labels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 230000003542 behavioural effect Effects 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 19
- 230000006399 behavior Effects 0.000 claims description 9
- 238000013016 damping Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 239000002537 cosmetic Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a realization method, a device, a computing device and a storage medium based on a graph output label, and relates to the technical field of computers; the method comprises the following steps: constructing a behavioral profile based on the user data and the commodity data; calculating correlation coefficients of two types of labels passing through a specific edge based on the behavior heterograph with the labels, and taking the correlation coefficients as edge weights; in the path related to the correlation coefficient calculation, a node with highest proportion of the input degree and the output degree is taken as a center node; pageRank is carried out on related nodes conforming to a specific path, and the weight of each node is determined; starting from the central node, predicting the target label probability of the neighbor unlabeled node; and after taking the average value of the target label probability of the node to be updated, selecting the target label with the highest probability as a prediction label. According to the application, the behavior weight is mined for the existing tag map data, the propagation center node is determined, and the node propagation quantity is controlled, so that the tag can be mined more accurately based on the behavior map data.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a computing device, and a storage medium for implementing graph-based yield labels.
Background
Based on the development of graph databases, business data such as user behaviors and social networks are widely stored as graphs. And (3) utilizing behavior diagram data to extract richer or interpretable features, and supplementing information such as user portraits, interests and the like through an improved label propagation algorithm under the condition of sparse information on the diagram so as to support applications such as recommendation and the like.
In the recall stage of the recommendation system, the tag data usually plays an important pointing role, and has a great influence on final sorting display. The traditional solution adopts a statistical or manual marking mode to expand the label information, and the guarantee of accuracy rate is lacking.
Large scale graph data semi-supervised learning is typically performed using label propagation with a small number of node labels. However, the current business scenario of the graph data is often an heterogram, and for different business edge types, it is required to determine edge weights, control the propagation amount of information, and how to determine the node and the edge weights is a challenge for the accuracy of label prediction.
Disclosure of Invention
Aiming at the defects existing in the prior art, the application provides a realization method, a device, a computing device and a storage medium based on a graph yield label.
The first object of the present application is to provide a method for implementing a graph-based yield label, which includes:
constructing a behavioral profile based on the user data and the commodity data; wherein, the user nodes in the behavioral profile are covered with different label types;
calculating correlation coefficients of two types of labels passing through a specific edge based on the behavior heterograph with the labels, and taking the correlation coefficients as edge weights;
in the path related to the correlation coefficient calculation, a node with highest proportion of the input degree and the output degree is taken as a center node;
PageRank is carried out on related nodes conforming to a specific path, and the weight of each node is determined;
starting from the central node, predicting the target label probability of the neighbor unlabeled node;
and after taking the average value of the target label probability of the node to be updated, selecting the target label with the highest probability as a prediction label.
As a further improvement of the present application, there is also included:
and traversing the neighbors of the center node in priority from the center node in breadth, and stopping label propagation when the node label update is smaller than the threshold value.
As a further improvement of the present application, the calculation formula of the correlation coefficient of two types of labels through a specific edge is:
in the formula, score oath E is the number of conforming path edges, which is the correlation coefficient.
As a further improvement of the present application, the calculation formula of the node weight is:
wherein V represents nodes, N represents the number of edges conforming to the edge path, L represents the number of node-out nodes, M represents the set of node-in nodes, and d represents the damping coefficient.
As a further improvement of the present application, the calculation formula of the target tag probability is:
wherein T is a probability vector of the node belonging to the target label, and alpha is an edge weight.
The second object of the present application is to provide a device for implementing a graph yield-based label, which is configured to implement the method for implementing a graph yield-based label, including:
the building module is used for building a behavioral heterogram based on the user data and the commodity data; wherein, the user nodes in the behavioral profile are covered with different label types;
the correlation coefficient calculation module is used for calculating the correlation coefficient of two types of labels passing through a specific edge based on the behavior heterograph with the labels and taking the correlation coefficient as edge weight;
the center node determining module is used for taking a node with highest incidence and output specific gravity as a center node in a path related to the correlation coefficient calculation;
the node weight calculation module is used for carrying out PageRank on the related nodes conforming to the specific paths and determining the weight of each node;
the prediction module is used for predicting the target label probability of the neighbor unlabeled node from the central node;
the selecting module is used for selecting the target label with the highest probability as the prediction label after taking the average value of the target label probability of the node to be updated.
A third object of the present application is to provide a computing device comprising: the system comprises a memory and a processor, wherein the memory stores a computer program, and the processor is characterized in that the steps of the implementation method based on the graph yield label are implemented when the processor executes the computer program.
A fourth object of the present application is to provide a computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for implementing a graph yield-based label described above.
Compared with the prior art, the application has the beneficial effects that:
according to the application, the behavior weight is mined for the existing tag map data, the propagation center node is determined, and the node propagation quantity is controlled, so that the tag can be mined more accurately based on the behavior map data.
Drawings
FIG. 1 is a flow chart of a method for implementing a graph-based yield tag of the present application;
FIG. 2 is a behavioral profile of example 1 of the present application;
fig. 3 is a cosmetic path diagram for a male user-purchase- > merchandise < -purchase-user preference category of embodiment 1 of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application is described in further detail below with reference to the attached drawing figures:
as shown in fig. 1, the present application provides a method for implementing a graph-based yield tag, including:
step 1, constructing a behavioral profile based on user data and commodity data; wherein, the user nodes in the behavioral profile are covered with different label types;
step 2, calculating correlation coefficients of two types of labels passing through specific edges based on the behavior heterograms with the labels, and taking the correlation coefficients as edge weights; the calculation formula of the correlation coefficient is as follows:
in the formula, score path E is the number of conforming path edges;
for example, by sex male- > user-order- > merchandise-user- > sports path of merchandise category preference, the correlation coefficient formula for determining the sex male of the user and the sports of merchandise category preference passing the order side is as follows:
step 3, in the path related to the correlation coefficient calculation, taking the node with the highest proportion of the input degree and the output degree as a center node; the calculation formula of the specific gravity of the node input degree and the node output degree is as follows:
wherein V represents a node and E represents an edge;
step 4, pageRank is carried out on the related nodes conforming to the specific paths, and the weight of each node for the subgraph is determined; the calculation formula of the node weight is as follows:
wherein V represents nodes, N represents the number of edges conforming to the edge path, L represents the number of node-out nodes, M represents the set of node-in nodes, and d represents the damping coefficient.
Step 5, starting from the central node, predicting the target label probability of the neighbor unlabeled node; if the node of the user gender label is known, predicting the commodity category label preferred by the user, and the propagation formula is as follows; t is the probability vector that the node belongs to the target label, e.g., user preference categories include: entertainment, sports, make-up, T (user a) = [0.2,0.1,0.7]:
step 6, traversing the neighbors of the central node in breadth first from the central node, and stopping label propagation when the node label update is smaller than a threshold value;
step 7, the target label of the node to be updated has a result updated by a plurality of related label sources, and the target label probability is maximized after the final result is averaged to obtain a predicted label; wherein the predictive labelThe calculation formula of (2) is as follows:
example 1:
s1, constructing behavioural diagram data shown in FIG. 2, wherein the gender of the user comprises: male and female labels, user preference categories include: cosmetic, sports, entertainment labels;
s2, aiming at a man user-purchase- > commodity < -purchase-user preference type makeup path, as shown in figure 3; calculating the gender of the user: male and user preference categories: the coefficient of correlation of the purchasing edge of the cosmetic is 0.22.
S3, determining the node D as a central node.
S4, determining that the weight of the node A, B, C is 0.15, 0.1 and 0.2;
s5, starting tag transmission from a central node D, wherein the tag probability of D is [1, 0] for cosmetic, sports and entertainment tags, the tag probability of A after transmission is [0.1,0.4,0.5], and the tag probability of B is [0.5,0.2,0.3].
S6, obtaining node label probability after the user preference cosmetic label is influenced by a purchase path from the male label, and similarly obtaining node A user label preference label probability [0.23,0.35,0.42] after the user preference cosmetic label is influenced by the female label by a collection path, so that a user A generates a label [ user preference ]: entertainment.
The application provides a realization device based on a graph output label, which comprises:
the construction module is used for realizing the step 1;
the correlation coefficient calculation module is used for realizing the step 2;
a central node determining module, configured to implement the step 3;
the node weight calculation module is used for realizing the step 4;
the prediction module is used for realizing the steps 5 and 6;
and a selecting module, configured to implement the step 7.
In one embodiment, a computer device is provided that includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data, and the network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a graph-yield-tag-based implementation method as described above.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, can implement any of the steps in the method of implementing graph-based yield labels as above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. The implementation method of the label based on the graph output is characterized by comprising the following steps:
constructing a behavioral profile based on the user data and the commodity data; wherein, the user nodes in the behavioral profile are covered with different label types;
calculating correlation coefficients of two types of labels passing through a specific edge based on the behavior heterograph with the labels, and taking the correlation coefficients as edge weights;
in the path related to the correlation coefficient calculation, a node with highest proportion of the input degree and the output degree is taken as a center node;
PageRank is carried out on related nodes conforming to a specific path, and the weight of each node is determined;
starting from the central node, predicting the target label probability of the neighbor unlabeled node; the calculation formula of the target tag probability is as follows:
wherein T is a probability vector of a node belonging to a target label, and alpha is an edge weight; path is path, E is the number of edges of the path, V i 、V j Representing nodes i andnode j, PR (V i Path) is node weight;
and after taking the average value of the target label probability of the node to be updated, selecting the target label with the highest probability as a prediction label.
2. The graph yield tag-based implementation method of claim 1, further comprising:
and traversing the neighbors of the center node in priority from the center node in breadth, and stopping label propagation when the node label update is smaller than the threshold value.
3. The method for implementing graph yield-based labels according to claim 1, wherein the calculation formula of the correlation coefficient of two types of labels through a specific edge is:
in the formula, score path E is the number of conforming path edges, which is the correlation coefficient.
4. The graph yield label-based implementation method of claim 1, wherein the node weight calculation formula is:
wherein V represents nodes, N represents the number of edges conforming to the edge path, L represents the number of node-out nodes, M represents the set of node-in nodes, and d represents the damping coefficient.
5. A graph yield label-based implementation device, configured to implement the graph yield label-based implementation method according to any one of claims 1 to 4, and comprising:
the building module is used for building a behavioral heterogram based on the user data and the commodity data; wherein, the user nodes in the behavioral profile are covered with different label types;
the correlation coefficient calculation module is used for calculating the correlation coefficient of two types of labels passing through a specific edge based on the behavior heterograph with the labels and taking the correlation coefficient as edge weight;
the center node determining module is used for taking a node with highest incidence and output specific gravity as a center node in a path related to the correlation coefficient calculation;
the node weight calculation module is used for carrying out PageRank on the related nodes conforming to the specific paths and determining the weight of each node;
the prediction module is used for predicting the target label probability of the neighbor unlabeled node from the central node;
the selecting module is used for selecting the target label with the highest probability as the prediction label after taking the average value of the target label probability of the node to be updated.
6. A computing device, comprising: a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, implements the steps of the graph yield label based implementation method of any one of claims 1-4.
7. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the graph yield label based implementation method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310117848.1A CN116089722B (en) | 2023-02-15 | 2023-02-15 | Implementation method, device, computing equipment and storage medium based on graph yield label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310117848.1A CN116089722B (en) | 2023-02-15 | 2023-02-15 | Implementation method, device, computing equipment and storage medium based on graph yield label |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116089722A CN116089722A (en) | 2023-05-09 |
| CN116089722B true CN116089722B (en) | 2023-11-21 |
Family
ID=86204330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310117848.1A Active CN116089722B (en) | 2023-02-15 | 2023-02-15 | Implementation method, device, computing equipment and storage medium based on graph yield label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116089722B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108874868A (en) * | 2018-04-24 | 2018-11-23 | 北京邮电大学 | A kind of prediction technique and device of implicit tag co-occurrence |
| CN112069415A (en) * | 2020-08-13 | 2020-12-11 | 中国海洋大学 | Interest point recommendation method based on heterogeneous attribute network characterization learning |
| CN112132305A (en) * | 2019-06-25 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Node type determination method, related device, equipment and storage medium |
| CN112883192A (en) * | 2021-02-09 | 2021-06-01 | 江苏名通信息科技有限公司 | Heterogeneous field user and resource association mining method and system |
| CN113761272A (en) * | 2021-04-19 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN113837252A (en) * | 2021-09-14 | 2021-12-24 | 支付宝(杭州)信息技术有限公司 | Clustering processing method and device |
| CN114065060A (en) * | 2020-07-28 | 2022-02-18 | 中国电信股份有限公司 | Data analysis method, device and storage medium |
| CN114329232A (en) * | 2022-01-06 | 2022-04-12 | 河海大学 | User portrait construction method and system based on scientific research network |
| CN115310762A (en) * | 2022-07-04 | 2022-11-08 | 上海淇玥信息技术有限公司 | Target service determination method and device based on heterogeneous graph neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11526707B2 (en) * | 2020-07-02 | 2022-12-13 | International Business Machines Corporation | Unsupervised contextual label propagation and scoring |
-
2023
- 2023-02-15 CN CN202310117848.1A patent/CN116089722B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108874868A (en) * | 2018-04-24 | 2018-11-23 | 北京邮电大学 | A kind of prediction technique and device of implicit tag co-occurrence |
| CN112132305A (en) * | 2019-06-25 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Node type determination method, related device, equipment and storage medium |
| CN114065060A (en) * | 2020-07-28 | 2022-02-18 | 中国电信股份有限公司 | Data analysis method, device and storage medium |
| CN112069415A (en) * | 2020-08-13 | 2020-12-11 | 中国海洋大学 | Interest point recommendation method based on heterogeneous attribute network characterization learning |
| CN112883192A (en) * | 2021-02-09 | 2021-06-01 | 江苏名通信息科技有限公司 | Heterogeneous field user and resource association mining method and system |
| CN113761272A (en) * | 2021-04-19 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN113837252A (en) * | 2021-09-14 | 2021-12-24 | 支付宝(杭州)信息技术有限公司 | Clustering processing method and device |
| CN114329232A (en) * | 2022-01-06 | 2022-04-12 | 河海大学 | User portrait construction method and system based on scientific research network |
| CN115310762A (en) * | 2022-07-04 | 2022-11-08 | 上海淇玥信息技术有限公司 | Target service determination method and device based on heterogeneous graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| 基于随机游走的图嵌入研究综述;腊志垚 等;《计算机工程与应用》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116089722A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11416268B2 (en) | Aggregate features for machine learning | |
| CN108427708B (en) | Data processing method, data processing apparatus, storage medium, and electronic apparatus | |
| CN114265979B (en) | Method for determining fusion parameters, information recommendation method and model training method | |
| CN113256367B (en) | Commodity recommendation method, system, equipment and medium for user behavior history data | |
| EP4242955A1 (en) | User profile-based object recommendation method and device | |
| CN113537630B (en) | Training method and device of business prediction model | |
| CN110598869B (en) | Classification method and device based on sequence model and electronic equipment | |
| CN110263979A (en) | Method and device based on intensified learning model prediction sample label | |
| CN112785005B (en) | Multi-objective task assistant decision-making method and device, computer equipment and medium | |
| CN114707644B (en) | Training method and device for graphic neural network | |
| CN110033097A (en) | The method and device of the incidence relation of user and article is determined based on multiple data fields | |
| CN112131261A (en) | Community query method and device based on community network and computer equipment | |
| CN109241442A (en) | Item recommendation method, readable storage medium storing program for executing and terminal based on predicted value filling | |
| CN115062779A (en) | Event prediction method and device based on dynamic knowledge graph | |
| CN112288484A (en) | Commodity automatic pricing method and device, electronic equipment and storage medium | |
| CN116089722B (en) | Implementation method, device, computing equipment and storage medium based on graph yield label | |
| CN110851600A (en) | Text data processing method and device based on deep learning | |
| CN115456708A (en) | Recommendation model training method and device, electronic equipment and storage medium | |
| US20160042277A1 (en) | Social action and social tie prediction | |
| CN115690465A (en) | Image multi-label classification method and device, computer equipment and storage medium | |
| CN110321476B (en) | Parallel matrix decomposition calculation implementation method based on locality sensitive hashing | |
| CN114662009A (en) | Industrial internet factory collaborative recommendation algorithm based on graph convolution | |
| CN107688610B (en) | Movie popularity prediction method and system based on network evolution model | |
| CN110489640A (en) | Content recommendation method and system | |
| CN113761388B (en) | Recommendation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |