Design of Knowledge Service Model Combining Dynamic Knowledge Graph and Enterprise Risk Management based on Bidirectional Encoder Representation from Transformers Bidirectional Long Short- Term Memory

A dynamic knowledge graph and knowledge service model were constructed to address the risk management needs of enterprises. By extracting, integrating, and processing knowledge entities, a complete knowledge graph is formed, and then a knowledge service model is designed to achieve intelligent and dynamic risk management. The experiment shows that the entity extraction method based on TextRank algorithm proposed by the research has an accuracy of 82.7%, a recall rate of 80.9%, and an F1 score of 81.8% in Class A datasets. The relationship fusion method of the Bidirectional Encoder Representation from Transformers Bi directional Long Short-Term Memory (BERT-Bi-LSTM) model based on transformers proposed by the research has an accuracy of about 87.8% for knowledge graph relationship fusion. The response time of the constructed enterprise risk management knowledge service model to 1000 risk management transaction requests is about 11.3 minutes, the maximum sustainable throughput is 1918TPS, the CPU utilization rate is 54.7%, and the memory usage is 3.0GB. The above results indicate that the dynamic knowledge graph and the knowledge service model of enterprise risk management perform well in multiple core indicators, which can effectively improve the intelligence and dynamic level of enterprise risk management.