Case Retrieval Method for Crop Diseases and Pests Control Based on Knowledge Graph

Abstract

Traditional case retrieval methods cannot reflect the internal connections between cases, resulting in inaccurate and comprehensive retrieval results. According to the characteristics of crop pest control cases, a case retrieval method combining Knowledge graph and BERT model is proposed to improve the retrieval effect. Comprehensively consider the relationship structure and entity attribute characteristics of the Knowledge graph of crop disease and pest control cases to conduct case retrieval, represent the crop disease and pest control cases in the form of triple groups and build a Knowledge graph. On the one hand, use the Jaccard similarity coefficient to calculate the relationship similarity of cases; On the other hand, the BERT model is used to vectorize attribute features and calculate case attribute similarity. Weighted sum of the two parts is used to obtain the total similarity of the case, and case retrieval is performed. Multiple experiments have verified the effectiveness of this method, and the case retrieval results are more accurate and comprehensive.