Clustering query refinements by inferred user intent

摘要

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering query refinements. One method includes building a representation of a graph for a first query, wherein the graph has a node for the first query, a node for each of a plurality of refinements for the first query, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first query node to each of the refinement nodes, edges from the first query to each document in the respective document set of the first query, edges from each refinement to each document in the respective document set of the refinement, and edges from each refinement to each co-occurring query of the refinement. The method further includes clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets.

主权项

1. A computer-implemented method, comprising:
identifying a plurality of refinements of a first search query, each refinement being a search query that follows the first search query in a session of queries submitted to a search system; identifying a document set of each of the refinements, the document set of a refinement being documents that are search results presented in response to the refinement by the search system and that have received user selections while being presented as the search results; building a representation of a graph for the first search query, wherein the graph has a node for the first search query, a node for each of the refinements, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first search query node to each of the refinement nodes, edges from the first search query node to each document node in the respective document set of the first search query, edges from each refinement node to each document node in the respective document set of the refinement, and edges from each refinement node to each co-occurring query of the refinement, each co-occurring query of the refinement represented by a different refinement node; clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets based on a similarity of edges extending from each refinement node to each document node in the respective document set of the refinement; receiving the first search query as a query in a search session; and providing, in a response to the first search query, each of one or more of the refinement clusters as a search suggestion.