Ranking the Answers for Autonomous Web Database Fuzzy Queries

An important issue arising from Web databases fuzzy query is how to rank the answers from data sources, this paper investigates the problem of ranking the answers by taking advantage of the user´s needs and preferences. Firstly, based on fuzzy set theory, a satisfaction degree ranking method, which ranks the answer according to the tuple´s satisfaction degree to the fuzzy query, is presented. Next, for the tuples with the same satisfaction degree in the answer, the adapted probabilistic models from Information Retrieval are applied, which leverages data and workload statistics, to derive the strengths of correlations between specified and unspecified attribute values in the query, consequently the tuple´s relevance degree to the user´s preferences can be obtained and used for distinguishing these tuples. Finally, the results of preliminary experiments, which demonstrate the efficiency as well as the quality of the ranking algorithm, are presented.