Graph data edge prediction method and device and terminal equipment
A prediction method and graph data technology, applied in the field of data processing, to achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0035] figure 1 It shows a schematic flowchart of the first edge prediction method for graph data provided by the embodiment of the present application, and the details are as follows:
[0036] In S101, a node feature matrix and an adjacency matrix of graph data are acquired.
[0037] The graph data in the embodiment of the present application is a graph structure data composed of a plurality of nodes and edges between nodes with relationships, such as figure 2 Shown is an example graph of one type of graph data. The graph data may be a social network graph representing user relationships in a social network, a paper citation structure graph representing paper citation relationships, a knowledge graph or a traffic network graph representing knowledge point relationships, and the like. Specifically, the graph data in the embodiment of the present application is directed graph data, that is, each edge in the graph data is a directed edge with a definite start point and end po...
Embodiment 2
[0100] Figure 4 It shows a schematic flow chart of the second graph data edge prediction method provided by the embodiment of the present application, and the details are as follows:
[0101] The embodiment of the present application adds the training steps S401-S402 of the target neural network on the basis of the first embodiment. S403-S406 in this embodiment are completely the same as S101-S104 in the previous embodiment. For details, please refer to the relevant description of S101-S104 in Embodiment 1, which will not be repeated here. Such as Figure 4 Steps S401-S402 in the edge prediction method for graph data shown are described in detail as follows:
[0102] In S401, a sample node feature matrix and a sample adjacency matrix of the sample graph data are acquired.
[0103] The sample graph data can be determined according to the type of graph data to be predicted by the target neural network. For example, if the trained target neural network is used for edge predi...
Embodiment 3
[0111] Figure 5 It shows a schematic flow chart of the third graph data edge prediction method provided by the embodiment of the present application. The graph data in the embodiment of the present application is specifically a social network graph, which is described in detail as follows:
[0112] In S501, a node feature matrix of the social network graph is generated based on personal information of each user node in the social network.
[0113] In a social network, each user has its own personal information and associations with other users. In the embodiment of the present application, each user in the social network is regarded as a user node to construct a social network graph. Wherein, the node feature matrix of the social network graph is constructed according to the personal information of each user node, and the personal information may include the user's gender, age, preference and other information. A node feature vector in the constructed node feature matrix can...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More