RESUMO
Reservoir dispatching regulations are a crucial basis for reservoir operation, and using information extraction technology to extract entities and relationships from heterogeneous texts to form triples can provide structured knowledge support for professionals in making dispatch decisions and intelligent recommendations. Current information extraction technologies require manual data labeling, consuming a significant amount of time. As the number of dispatch rules increases, this method cannot meet the need for timely generation of dispatch plans during emergency flood control periods. Furthermore, utilizing natural language prompts to guide large language models in completing reservoir dispatch extraction tasks also presents challenges of cognitive load and instability in model output. Therefore, this paper proposes an entity and relationship extraction method for reservoir dispatch based on structured prompt language. Initially, a variety of labels are refined according to the extraction tasks, then organized and defined using the Backus-Naur Form (BNF) to create a structured format, thus better guiding large language models in the extraction work. Moreover, an AI agent based on this method has been developed to facilitate operation by dispatch professionals, allowing for the quick acquisition of structured data. Experimental verification has shown that, in the task of extracting entities and relationships for reservoir dispatch, this AI agent not only effectively reduces cognitive burden and the impact of instability in model output but also demonstrates high extraction performance (with F1 scores for extracting entities and relationships both above 80%), offering a new solution approach for knowledge extraction tasks in other water resource fields.
RESUMO
A deep understanding of the relationship between the knowledge acquired and the graduation requirements is essential for students to precisely meet the graduation requirements and to become human resources with specific knowledge, skills and professionalism. In this paper, we define the ontology layer of the knowledge graph by deeply analyzing the relationship between graduation requirement, course and knowledge. Based on the implementation of the concept of Outcome Based Education, we use Knowledge extraction, fusion, reasoning techniques to construct a hierarchical knowledge graph with the main line of "knowledge-course-graduation requirements. In the process of knowledge extraction, in order to alleviate the huge labor overhead brought by traditional extraction methods, this paper adopts a transfer learning method to extract triadic knowledge using the multi-task framework EERJE, Finally, knowledge reasoning was also performed with the help of LLM to further expand the knowledge scope. The comprehensiveness, correctness and relatedness of the data were evaluated through the experiment, and the F1 value of the ternary group extraction was 87.76%, the accuracy rate of entity classification was 85.42%, the data coverage was more comprehensive, and the results showed that the data quality was better, and the knowledge graph constructed in this way can fully optimize the organization and management of teaching resources, help students intuitively and comprehensively grasp the correlation and difference between graduation requirements and various knowledge points, and let the Students can carry out personalized independent learning through the navigation mode of knowledge graph, strengthen their weak links, and complete the relevant graduation requirements, which effectively improves the degree of students' graduation requirements achievement. This new paradigm of knowledge graph enabled teaching is of reference significance for engineering education majors to improve the degree of graduation requirements achievement.
