Improvement of Knowledge Search Method for Numeral Terms in Power System Based on Multi-source Fusion
Min Hua, Xiaoman Qi, Aiqiang Pan, San-shan Zhao, Xiaoxia Huang, Chao Wu · Journal of Physics Conference Series · 2020
Abstract In the process of energy and power research, it is often necessary to find numeral data information from multiple ways based on searching words, so the domain information can better analyzed and understood, visually discover hidden relationships between information and ultimately improve search efficiency and experience. The article designs a set of numeral entity discovery methods based on NLP and improves a visual search engine. Using CRF for named entity pre-processing extraction, using TF-IDF, etc. to complete multi-source information combination search and information mining method establishment, the power system energy database is used as the information source of the search engine, enabling users to locate the document data of the searching words in the energy database and the context information associated with them quickly, generate summary information, extract the central words based on this, and image the information in the form of word cloud and chart demonstration. Experiments have shown that the searching result are of interest to users, quickly locate the literature and context-related information containing the numeral hotspots, and the search recall rate is significantly improved.