Intelligent Operation and Maintenance Analysis System Based on Multi-source Heterogeneous Data Fusion, Machine Learning and Customer Service Robot

Abstract

The invention discloses an intelligent Operation and Maintenance Analysis System Based on Multi-source Heterogeneous Data Fusion, Machine Learning and Customer Service RobotBased on multi-source heterogeneous data fusion, In the intelligent operation and maintenance analysis system of machine learning and customer service robot, the analysis and processing module uses the multi-source heterogeneous data fusion technology to preprocess and normalize the real-time data. After the correlation analysis, the model matching is used to output the results, and the root cause of the problem is determined by root cause analysis. The model management module is used for acquiring data for machine learning and outputting various reasoning models to the analysis processing module and the recommendationdecision module. The recommendation decision module recognizes the context and matches the corresponding subsequent processing behavior according to the policy. The invention is based on the multi-source heterogeneous data fusion technology and the operation and maintenance mode of machine learning, which gives consideration to the compatibility problem of the big data, improves the automation degree of the operation and maintenance, guarantees the network safety and the service quality, simultaneously has certain prediction ability, and reduces the related operation and maintenance cost. Theoutput mode of the customer service robot further realizes the intelligence of operation and maintenance.

Description

technical field [0001] The invention relates to an intelligent operation and maintenance analysis system, in particular to an intelligent operation and maintenance analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robots. Background technique [0002] In the traditional IT system operation and maintenance process, fault warning and troubleshooting are very important but time-consuming tasks. Commonly used operation and maintenance methods can usually be abstracted from high-level into four processes: object modeling for operation and maintenance, performance alarm monitoring, and for After analyzing the received data, decision-making is made based on expert experience, and finally the control is delivered to the object to be operated and maintained through the configuration script. In this process, most automation measures and related tools are implemented in the form of rules, which are similar to the rules in the first g...

AI Technical Summary

Problems solved by technology

[0003] However, there are several flaws in the way of setting the rules: first, our logic process should not be too complicated, otherwise it can only be realized by code, and for the sake of flexibility, we hope to define it directly on site, which creates contradictions; It is easier to define when there are a large number of nodes, but if there are a large number of nodes, it is very difficult to define tens of thousands or hundreds of thousands of rules; finally, for large open networks, there is often a certain ecological nature, that is, the operation and maintenance personnel do not know when to A new role will be created in this network, and what relationship will this role have with other roles, so when a problem arises and then set up rules and monitoring, the loss has often occurred. This type of typical problem is the problem of financial risk control.

[0006] At the same time, the operation and maintenance data is heteroge

Images