Query augmentation
First Claim
Patent Images
1. A computer-implemented method, comprising:
- receiving a query from a user device;
identifying, by a data processing apparatus and based on the received query, a ranking of augmentation queries, the ranking of augmentation queries including one or more user-generated augmentation queries and one or more machine-generated synthetic augmentation queries, wherein;
each user-generated augmentation query is a query previously received from a user; and
each synthetic augmentation query is generated by the data processing apparatus and from a respective structured document of a corpus of structured documents, each structured document including multiple structured sections defined by a structure of the structured document that each include a particular type of data of the structured document, each synthetic augmentation query being generated based on one or more words extracted from one or more particular structured sections of the synthetic augmentation query'"'"'s respective structured document, the one or more particular structured sections being structured sections from which queries that have at least a threshold performance have been generated, wherein the respective structured document from which at least one synthetic augmentation query was generated is different from the respective structured document from which a different synthetic augmentation query was generated;
adjusting, by the data processing apparatus, the ranking of the one or more synthetic augmentation queries relative to the one or more user-generated augmentation queries based on a type of information to which the received query is directed, the adjusting comprising;
increasing a rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a first type; and
reducing the rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a second type different from the first type;
selecting, by the data processing apparatus, a given augmentation query based on the adjusted ranking; and
providing, by the data processing apparatus and to the user device, a search result responsive to the given augmentation query.
4 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems, and apparatus, including computer program products, for generating or using augmentation queries. In one aspect, a first query stored in a query log is identified and a quality signal related to the performance of the first query is compared to a performance threshold. The first query is stored in an augmentation query data store if the quality signal indicates that the first query exceeds a performance threshold.
114 Citations
20 Claims
-
1. A computer-implemented method, comprising:
-
receiving a query from a user device; identifying, by a data processing apparatus and based on the received query, a ranking of augmentation queries, the ranking of augmentation queries including one or more user-generated augmentation queries and one or more machine-generated synthetic augmentation queries, wherein; each user-generated augmentation query is a query previously received from a user; and each synthetic augmentation query is generated by the data processing apparatus and from a respective structured document of a corpus of structured documents, each structured document including multiple structured sections defined by a structure of the structured document that each include a particular type of data of the structured document, each synthetic augmentation query being generated based on one or more words extracted from one or more particular structured sections of the synthetic augmentation query'"'"'s respective structured document, the one or more particular structured sections being structured sections from which queries that have at least a threshold performance have been generated, wherein the respective structured document from which at least one synthetic augmentation query was generated is different from the respective structured document from which a different synthetic augmentation query was generated; adjusting, by the data processing apparatus, the ranking of the one or more synthetic augmentation queries relative to the one or more user-generated augmentation queries based on a type of information to which the received query is directed, the adjusting comprising; increasing a rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a first type; and reducing the rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a second type different from the first type; selecting, by the data processing apparatus, a given augmentation query based on the adjusted ranking; and providing, by the data processing apparatus and to the user device, a search result responsive to the given augmentation query. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system, comprising:
-
a data processing apparatus comprising one or more processors; and a memory storage apparatus in data communication with the data processing apparatus, the memory storage apparatus storing instructions executable by the data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising; receiving a query from a user device; identifying, based on the received query, a ranking of augmentation queries, the ranking of augmentation queries including one or more user-generated augmentation queries and one or more machine-generated synthetic augmentation queries, wherein; each user-generated augmentation query is a query previously received from a user; and each synthetic augmentation query is generated by the data processing apparatus and from a respective structured document of a corpus of structured documents, each structured document including multiple structured sections defined by a structure of the structured document that each include a particular type of data of the structured document, each synthetic augmentation query being generated based on one or more words extracted from one or more particular structured sections of the synthetic augmentation query'"'"'s respective structured document, the one or more particular structured sections being structured sections from which queries that have at least a threshold performance have been generated, wherein the respective structured document from which at least one synthetic augmentation query was generated is different from the respective structured document from which a different synthetic augmentation query was generated; adjusting the ranking of the one or more synthetic augmentation queries relative to the one or more user-generated augmentation queries based on a type of information to which the received query is directed, the adjusting comprising; increasing a rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a first type; and reducing the rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a second type different from the first type; selecting a given augmentation query based on the adjusted ranking; and providing, to the user device, a search result responsive to the given augmentation query. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by a data processing apparatus cause the data processing apparatus to perform operations comprising:
-
receiving a query from a user device; identifying, based on the received query, a ranking of augmentation queries, the ranking of augmentation queries including one or more user-generated augmentation queries and one or more machine-generated synthetic augmentation queries, wherein; each user-generated augmentation query is a query previously received from a user; and each synthetic augmentation query is generated by the data processing apparatus and from a respective structured document of a corpus of structured documents, each structured document including multiple structured sections defined by a structure of the structured document that each include a particular type of data of the structured document, each synthetic augmentation query being generated based on one or more words extracted from one or more particular structured sections of the synthetic augmentation query'"'"'s respective structured document, the one or more particular structured sections being structured sections from which queries that have at least a threshold performance have been generated, wherein the respective structured document from which at least one synthetic augmentation query was generated is different from the respective structured document from which a different synthetic augmentation query was generated; adjusting the ranking of the one or more synthetic augmentation queries relative to the one or more user-generated augmentation queries based on a type of information to which the received query is directed, the adjusting comprising; increasing a rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a first type; and reducing the rank of each synthetic augmentation query relative to each user-generated augmentation query whenever the type of information is a second type different from the first type; selecting a given augmentation query based on the adjusted ranking; and providing, to the user device, a search result responsive to the given augmentation query. - View Dependent Claims (18, 19, 20)
-
Specification