Web search refinement
AssigneeGoogle Inc.
InventorsJun Wu, Hang Cui, Hangjun Ye
Life of this patent
Estimating the term…
Abstract
Similar queries are identified so that suggested search queries may be provided to a user. A first search query having at least one term associated with a semantic weight is received. A second query having at least one term associated with a semantic weight is received. A first vector is generated based on the first query and the at least one semantic weight of the first query, and a second vector is generated based on the second query and the at least one semantic weight of the second query. A similarity measurement between the first and second search queries is made based at least in part on a comparison of the first vector to the second vector.
Claims19
A method comprising:
- generating a first vector for one or more first n-grams of a first query and calculating a respective first semantic weight for each of the first n-grams based at least in part on an entropy of the particular first n-gram in which the entropy is estimated from a set of search queries;
- generating a second vector for one or more second n-grams of a second query and calculating a respective second semantic weight for each of the second n-grams;
- calculating a similarity measurement between the first query and the second query based on respective similarities of semantically weighted first n-grams to the second vector, and based on respective similarities of the semantically weighted second n-grams to the first vector;
- and
- wherein generating and calculating are performed by one or more computers.
A system comprising:
- one or more servers configured to perform operations comprising:
- generating a first vector for one or more first n-grams of a first query and calculating a respective first semantic weight for each of the first n-grams based at least in part on an entropy of the particular first n-gram in which the entropy is estimated from a set of search queries;
- generating a second vector for one or more second n-grams of a second query and calculating a respective second semantic weight for each of the second n-grams;
- calculating a similarity measurement between the first query and the second query based on respective similarities of semantically weighted first n-grams to the second vector, and based on respective similarities of the semantically weighted second n-grams to the first vector;
- and
- wherein generating and calculating are performed by one or more computers.
A computer program product encoded on a storage device, the computer program product including instructions which when executed by a processor cause the processor to perform operations comprising:
- generating a first vector for one or more first n-grams of a first query and calculating a respective first semantic weight for each of the first n-grams based at least in part on an entropy of the particular first n-gram in which the entropy is estimated from a set of search queries;
- generating a second vector for one or more second n-grams of a second query and calculating a respective second semantic weight for each of the second n-grams;
- and
- calculating a similarity measurement between the first query and the second query based on respective similarities of semantically weighted first n-grams to the second vector, and based on respective similarities of the semantically weighted second n-grams to the first vector.
Dependencies are inferred from the claim text.