An efficient incremental method for generating equivalence groups of search results in information retrieval and queries

Today’s widespread web applications bring many challenges to decision support systems (DSS) research for effectively retrieving useful information from online data sources that are of huge volume. Importantly, in a web search and service environment, search results grouping becomes a crucial issue of DSS functionality and service, where the scale of data is dynamically expanding. This paper proposes an intelligent method that generates equivalence groups (classes) in an incremental manner, so as to deal with the evolving nature of the data in web search. Such equivalence groups are derived from λ-cuts of transitive closure of a closeness matrix for the search elements. The proposed incremental method does not need to redo the whole procedure of grouping each time when the overall search outcome changes, which is common in real applications, rather, it only captures the changes and related elements so that the calculation is minimized in both time and space complexity. Theoretical analysis and data experiments show the advantage and effectiveness of the proposed incremental method.