Training method and detection method for generative adversarial multi-relation graph network
A training method and relational graph technology, applied in biological neural network models, neural learning methods, character and pattern recognition, etc., can solve problems such as poor generalization, deepening of mixing, and difficult detection and recognition of machine accounts, so as to improve the detection ability Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0028] In order to make the objects, technical solutions, and advantages of the present invention, the present invention will be further detailed in connection with the accompanying drawings.
[0029] The embodiment of the present invention discloses a training method for detecting a generating confrontation diagram network model of a machine account, wherein generating a multi-relational diagram network model includes generator G, connection relationship discriminator D and classifier, the training Method includes the construction of accounts on different platforms into node V; modeling interactive operation between accounts into relational R, wherein the number of relationship R is determined by the number of interacts between accounts; Mold the map with nodes and relationships Among them, the diagram The number is determined by the number of relational R; sampling is a pair of connected nodes pairs (V, U), using the generator G to generate a false target node V for source nod...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap