Domain audit knowledge graph construction method based on machine learning

Abstract

The invention discloses a domain audit knowledge graph construction method based on machine learning. The method comprises the steps of firstly obtaining data through multiple sources; preprocessing the acquired data; adopting an entity identification and relationship processing module and an expert knowledge engineering module to realize entity identification; then entering a natural language understanding module according to entities obtained in the two steps of the entity recognition and relationship processing module and the expert knowledge engineering module, and extracting feature wordsby utilizing a topic model; entering a feature machine learning module according to the feature words extracted by the natural language understanding module, adjusting the weight according to a specific scene, and classifying the feature words; finally, generating a knowledge graph. The knowledge graph constructed by the invention can reveal multi-dimensional association between audit related subjects; therefore, the retrieval and association comparison efficiency of auditing laws and regulations and cases is improved.

Description

technical field [0001] The invention relates to the field of audit map construction, in particular to a machine learning-based domain audit knowledge map construction method. Background technique [0002] In recent years, the application of knowledge graphs has become a symbol of the era of big data. The knowledge graph is essentially a semantic network, a graph-based data structure consisting of nodes (Point) and edges (Edge). In the knowledge graph, each node represents an "entity" that exists in the real world, and each edge is a "relationship" between entities. Knowledge graphs are the most effective representation of relationships. In layman's terms, a knowledge graph is a relational network obtained by connecting all different types of information (Heterogeneous Information). The knowledge graph provides the ability to analyze problems from the perspective of "relationship". Accompanied by the rise of the knowledge map is the machine learning technology and related...

AI Technical Summary

Problems solved by technology

Up to 80% of all data in the world is unstructured and cannot be identified and analyzed by most existing technologies and cloud technologies

In the field of auditing, due to its high professionalism, knowledge and strong logic, most auditors use the experience of auditors to construct mathematical audit rules to process audit data, but this type of data is usually structured data, and the analysis is also common. Text, not suitable for audit text training, less flexible

Not only that, regardless of the immature constructio

Images