Research on Service Scanning Supervision Technology Based on Improved Association Algorithm

The scale of data in the Internet environment is becoming increasingly large and complex. Its heterogeneous, dynamic and distributed information characteristics have caused the existing business scanning and monitoring models to be unable to meet its application needs. This project proposes an improved iterative algorithm based on multiple servers. By introducing the idea of local operation of memory nodes, a service scanning and monitoring model that can support concurrency is constructed. A cluster analysis method based on genetic algorithm based on cluster analysis is proposed. It is then synthesized to correlate the largest set of recurring items to achieve data association, extend the iterative service scanning supervision algorithm, and obtain user-interested implicit patterns from server logs. At the same time, personalized service purposes are achieved by recommending implicit interest collections to users. Simulation results show that this method can effectively improve the performance of business search monitoring, and has the characteristics of enhancement as the data size increases.