CAJ | 학술논문

案例检索是案例推理系统中的一个关键过程，是近年来人工智能领域的研究热点之一。案例相似度的计算方法是案例检索的关键技术。将集对分析理论引入目标案例，与案例库中源案例的相似度比较，建立两个比较案例的集对，通过属性的重要度和联系度构建了本体案例检索模型；通过本体的词义扩展解决检索词的多词同义问题，有效提高了不确定性问题的检索精度。实验结果表明，基于集对分析的本体案例检索模型不仅减少了运算量，还提高了查全率和查准率。
안례검색시안례추리계통중적일개관건과정，시근년래인공지능영역적연구열점지일。안례상사도적계산방법시안례검색적관건기술。장집대분석이론인입목표안례，여안례고중원안례적상사도비교，건립량개비교안례적집대，통과속성적중요도화련계도구건료본체안례검색모형；통과본체적사의확전해결검색사적다사동의문제，유효제고료불학정성문제적검색정도。실험결과표명，기우집대분석적본체안례검색모형불부감소료운산량，환제고료사전솔화사준솔。
Case retrieval is a key process of case-based reasoning(CBR) system, and it is also one of hot research fields of artificial intelligence. The calculation method of case similarity is the key technology of case retrieval. The set pair analysis(SPA) is applied to caculate the similarity of two sets between the target case and source case of case base, and the case retrieval model is built by the property and contact degree.The problem of multi-word synonyms is solved by the semantic extension of ontology, so the accuracy of the retrieval uncertainty is improved effectively. Experimental results show that ontology based on set pair analysis case retrieval model not only reduces the amount of computation, but also improves the recall and precision.