Web log abnormal behavior identification method based on knowledge graph
A technology of knowledge graph and recognition method, which is applied in the direction of using information identifiers to retrieve Web data, natural language data processing, and network data retrieval, etc., which can solve the problems of small role of log analysis, improve recognition rate, increase feature attributes, improve The effect of analysis and recognition ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
experiment example
[0284] 1. Experimental data
[0285] The present invention uses network server logs provided by a scientific research institution as experimental data, and the average daily blocking amount of harmful information by the server reaches hundreds of millions of times. Because the log data involves privacy and security issues, the present invention encrypts the data. Table 8 shows an example of some of the web server log data provided:
[0286] Table 8 Partial data table of web server log
[0287] Table 8Partial data table of web server log
[0288]
[0289]
[0290] 2. Experimental environment
[0291] The experimental environment of the present invention is as follows: the compilation environment is Scala2.12.13 based on Spark 3.1.2 and Hadoop 2.7.1, the database uses Neo4j and MySQL, and the development tool is IntelliJ IDEA 2021.1.3 x64.
[0292] 3. Evaluation Standards
[0293] Accuracy rate P identified by abnormal behavior t , recall rate R e , F 1 Three indic...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com