Unsupervised entity and intent identification for improved search query relevance

A computing system that is configured to return a query suggestion to a user, the computing system comprising:

• a processor;
• and
• memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
• receiving a query from a client computing device operated by a user, wherein the query includes a keyword;
• generating a search engine results page (SERP) based upon the query received from the client computing device, where the SERP includes document titles for search results included in the SERP;
• determining that the SERP includes the keyword;
• upon determining that the SERP includes the keyword, computing a number of times that the keyword occurs in the document titles of the search results in the SERP, where the keyword occurs multiple times in the document titles;
• extracting the keyword from the query based upon the number of times that the keyword occurs in the document titles in the SERP;
• identifying a query suggestion based upon the extracted keyword;
• and
• returning the identified query suggestion to the client computing device operated by the user, wherein the search engine returns an updated SERP to the client computing device upon the query suggestion being selected by the user.

A computer-readable memory device comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:

• receiving a query issued by a user of a client computing device, where the query includes a keyword;
• retrieving, by a search engine, search results based upon the query, where the search results represent documents that include titles that are to be presented on a search engine results page (SERF), and further where the keyword occurs multiple times in the titles;
• identifying a number of occurrences of the keyword in the titles of the documents represented by the search results;
• extracting the keyword from the query based upon the number of occurrences of the keyword in the titles of the documents;
• identifying a query suggestion based upon the keyword extracted from the query;
• and
• upon identifying the query suggestion, providing the query suggestion to the client computing device for presentment to the user.