Keyword Query Expansion Paradigm Based on Recommendation and Interpretation in Relational Databases

Algorithm 1

Probabilistic recommendation algorithm.

Input: Keyword query , list of related keywords

Out: , where

Method:

Delete the redundant related keywords

Build Viterbi model

Initialize

     //Variable is the maximum probability in all paths whose state is at time .

     //Variable the th node of path with the maximum probability in state at time .

Loop

     For

End

     Set

     Set

Paths backtracking

     For

Return keyword queries