Analysis method and system for epidemic propagation based on graph expression technology, and medium
An analysis method and epidemic technology, applied in the direction of epidemic warning system, knowledge expression, neural learning method, etc., can solve the problems of information redundancy, inability to fully adapt to data characteristics in the field of network analysis, technical performance limitations, etc., to achieve improved processing speed, improve quality of results, avoid information loss effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] This embodiment discloses an epidemiological spread analysis method based on graph expression technology, such as figure 1 shown, including:
[0032] S1 prepares network structure diagram and epidemic spread data.
[0033] Download social network data Karate from the Internet and store it in the form of an edge list (Edgelist) as a network structure graph G=(V, E), where V is the point set of the graph and E is the edge set of the graph. Let the number of nodes in the network structure diagram be N, and the nodes in the network structure diagram express the length of the vector d (d<<N). The network structure diagram established according to Karate data includes 34 nodes, namely N=34, and the edges between the nodes represent the social relationship among the 34 members in the community. In this embodiment, the Karete network is used as the target network structure specified by the user, but any suitable network structure may be used in practical applications.
[003...
Embodiment 2
[0076] Based on the same inventive concept, this embodiment discloses an epidemiological spread analysis system based on graph expression technology, including:
[0077] The similarity calculation module simulates discrete-time quantum walks through epidemic spread data and network structure diagrams, and mines the similarity of each node in the network structure diagrams through quantum walks;
[0078] The intermediate expression generation module is used to generate the intermediate expression of each target node according to the node similarity;
[0079] The model training module is used to train the neural network model through the intermediate expression to obtain the expression vector of the node;
[0080] The result output module is used to train the epidemic transmission model with the expression vector of the known node, and input the expression vector of the unknown node into the trained epidemic transmission model to obtain the epidemic transmission analysis and pre...
Embodiment 3
[0082] Based on the same inventive concept, the present embodiment discloses a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and the instructions, when executed by a computing device, cause the computing device to execute any one of the above-mentioned programs. Item-based graph representation technique for analyzing the spread of epidemics.
[0083] To sum up, the present invention uses methods such as node sampling and neural network to realize the node expression of network structure data based on the similarity information of quantum walk nodes, and realizes the prediction of the infection state of unknown nodes based on the node expression. The invention avoids the information loss caused by the classical random walk in the traditional method and the problems that the nonlinear characteristics in the network structure cannot be mined. The method can effectively utilize the high-quality structural info...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More