Aimed at the problem of insufficiency of document semantic comprehension and association in current engineering information retrieval, according to the analysis of information retrieval characteristics in engineering environment, a heterogeneous engineering document information retrieval method was proposed, which included content analysis, semantic modeling, multi-dimensional association, semantic inference, expansion, and query process. Ontology based comprehension was utilized to capture engineering semantic and build semantic annotation base, which realized unified description of heterogeneous document content. Multidimensional association architecture was introduced focusing on documents. On the base of semantic comprehension of document content, ontology based internal association was expanded to multiple associations. The result shows that multi-dimensional association can associate documents in product life cycle heuristically, improve query navigation, and support semantic inference and retrieval expansion.
［1］ RADHAKRISHNAN R. Information retrieval at Boeing: plans and successes ［C］∥ Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval. Seattle: ACM, 2006: 380-381.
［2］ LOWE A, MCMAHON C, CULLEY S. Characterising the requirements of engineering information systems ［J］. International Journal of Information Management, 2004, 24(5):401-422.
［3］ CHEN Y J, TSAI T N, CHU H C, et al. Developing a multilayer reference design retrieval technology for knowledge management in engineering design ［J］. Expert Systems with Applications, 2005, 29(4): 839-866.
［4］ DOND A, AGOGINO A M. Text analysis for constructing design representations ［J］. Artificial Intelligence in Engineering, 1997, 11(2):65-75.
［5］ YANG M, WOOD W, CUTKOSKY M. Design information retrieval: a thesauribased approach for reuse of informal design information ［J］. Engineering with Computer, 2005, 21(3):177-192.
［6］ AHMED S, KIM S, WALLACE K M. A methodology for creating ontologies for engineering design ［J］.Journal of Computing and Information Science in Engineering, 2007, 7(2):132-140.
［7］ MCMAHON C, LOWE A, CULLEY S, et al. Waypoint: an integrated search and retrieval system for engineering documents ［J］. Journal of Computing and Information Science in Engineering, 2004, 4(4):329-338.
［8］ LIU S, MCMAHON C, DARLINGTON M, et al. An automatic markup approach for structured document retrieval in engineering design ［J］. The International Journal of Advanced Manufacturing Technology, 2008, 38(3):418-425.
［9］ LI Z, RASKIN V, RAMANI K. Developing ontologies for engineering information retrieval ［C］∥ ASME Proceedings of the IDETC/CIE 2007. Las Vegas: ASME, 2007: 737-745.
［10］ KAMRANI A, VIJAYAN A. A methodology for integrated product development using design and manufacturing templates ［J］. Journal of Manufacturing Technology Management, 2006, 17(5):656-672.
［11］ JONES D, BENCHCAPON T, VISSER P. Methodologies for ontology development ［C］∥ Information Technologies and Knowledge Systems, 15th IFIP World Computer Congress. Vienna, Budapest: ［s. n.］, 1998: 62-75.
［12］ LIN H K, HARDING J A,SHAHBAZ M. Manufacturing system engineering ontology for semantic interoperability across extended project teams ［J］. International Journal of Production Research, 2004, 42(24):5099-5118.
［13］ MLLER H M, KENNY E E, STERNBERG P W. Textpresso: an ontologybased information retrieval and extraction system for biological literature ［J］. PLoS Biology, 2004, 2(11): e309.
［14］ TEEVAN J, ALVARADO C, ACKERMAN M S, et al. The perfect search engine is not enough: a study of orienteering behavior in directed search ［C］∥ Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. Vienna: ACM, 2004: 415-422.
