Learning user synonyms from sequenced query sessions

A query processing system for determining user synonyms, comprising:

• at least one processor and at least one memory;
• a knowledge base having a plurality of documents and metadata configured to be queried;
• a query processor configured to receive a plurality of input queries, the plurality of input queries including at least a first input query and a second input query;
• a matching engine configured to match the plurality of queries with documents in the knowledge base to generate a plurality of results;
• a ranking engine configures to score and rank the plurality of results
• a user identification component configured to identify specific users of the query processing system;
• a session identification component configured to identify contiguous query sessions for at least one user;
• and
• a similarity detector configured to determine a contextual similarity between the first query and the second query, to determine a first term in the first query that is different from a second term in the second query, when the first query and the second query are determined to be contextually similar, and to add the first term and the second term to the thesaurus as a user synonym when the first term and the second term are not listed as synonyms in the thesaurus.

A computer readable storage medium having computer readable instructions that when executed by one or more computers causes the one or more computers to execute a method for determining user synonyms in a query processing system, comprising:

• receiving a first query from a user of the query processing system;
• processing the first query through the query processing system;
• generating results for the first query;
• receiving a second query from the user;
• determining a contextual similarity between the first query and the second query;
• identifying a first term in the first query that is different from a second term in the second query, when the first query and the second query are determined to be contextually similar;
• determining that first term and the second term are not listed as synonyms in a thesaurus;
• and
• adding the first term and the second terms to the thesaurus as a user synonym.