Intention Recognition Trustworthiness Measurement using a Spatiotemporal Knowledge Graph
Yang Liu, Hao Liu, Tengteng Qu, Wei Chen · 2023
The generalization ability of current intent recognition methods is insufficient, and the evaluation of confidence level of intent recognition is the key to its popularization and application in the high-reliability military and civilian fields. The spatiotemporal Knowledge Graph can uniformly represent and efficiently organize entities containing spatial location information and temporal information. Battlefield situational objectives and their relationships can be abstractly expressed as a triplet composed of two specific types of spatiotemporal entities and combat intent relationships. Using typical confrontation scenario data to train neural networks, and fusing the confidence levels of the entity and Knowledge Graph, the confidence level evaluation results of the intent triple facing the existing spatiotemporal knowledge base are calculated. The simulation test results show that the method can effectively evaluate the confidence level of intent recognition results, and the accuracy rate is improved by more than 9% compared with the KGTTM model. This method breaks the “closed” assumption of the Knowledge Graph update and completion algorithm from the level of algorithm thinking, and completes the last link of the popularization and application of intent recognition methods.