Query completions in the context of a user's own document
First Claim
1. A method comprising:
- receiving a partial query entered into a search field on a computing device, and receiving data indicating a document presented on the computing device during entry of the partial query, wherein the presented document has been edited by a user of the computing device;
obtaining a set of candidate query completions for the partial query;
identifying one or more search result documents for each of one or more respective candidate query completions in the set;
calculating similarity scores for candidate query completions in the set, wherein calculating a similarity score for a given candidate query completion of the set of candidate query completions is based at least in part on a similarity between content in the presented document and content in the one or more search result documents identified for the given candidate query completion;
selecting one or more of the candidate query completions in the set as refined query completions for the partial query based at least in part on the similarity scores; and
providing the refined query completions for presentation by the computing device.
2 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems and apparatus are described herein that include receiving a partial query entered into a search field on a computing device, and data indicating a document presented on the computing device during entry of the partial query. The presented document has been edited by a user of the computing device. Search results are then obtained which identify respective lists of search results documents for corresponding candidate query completions in a set obtained for the partial query. Similarity scores are then calculated for candidate query completions based at least in part on a similarity between content in the displayed document and content in search result documents in the corresponding lists. One or more candidate query completions in the set are then selected as refined query completions for the partial query based at least in part on the similarity scores and provided for presentation by the computing device.
-
Citations
21 Claims
-
1. A method comprising:
-
receiving a partial query entered into a search field on a computing device, and receiving data indicating a document presented on the computing device during entry of the partial query, wherein the presented document has been edited by a user of the computing device; obtaining a set of candidate query completions for the partial query; identifying one or more search result documents for each of one or more respective candidate query completions in the set; calculating similarity scores for candidate query completions in the set, wherein calculating a similarity score for a given candidate query completion of the set of candidate query completions is based at least in part on a similarity between content in the presented document and content in the one or more search result documents identified for the given candidate query completion; selecting one or more of the candidate query completions in the set as refined query completions for the partial query based at least in part on the similarity scores; and providing the refined query completions for presentation by the computing device. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system including memory and one or more processors operable to execute instructions, stored in the memory, including instructions to perform the operations of:
-
receiving a partial query entered into a search field on a computing device, and receiving data indicating a document presented on the computing device during entry of the partial query, wherein the presented document has been edited by a user of the computing device; obtaining a set of candidate query completions for the partial query; identifying one or more search result documents for each of one or more respective candidate query completions in the set; calculating similarity scores for candidate query completions in the set, wherein calculating a similarity score for a given candidate query completion of the set of candidate query completions is based at least in part on a similarity between content in the presented document and content in the one or more search result documents identified for the given candidate query completion; selecting one or more of the candidate query completions in the set as refined query completions for the partial query based at least in part on the similarity scores; and providing the refined query completions for presentation by the computing device. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory computer readable storage medium storing computer instructions executable by a processor to perform a method comprising:
-
receiving a partial query entered into a search field on a computing device, and receiving data indicating a document presented on the computing device during entry of the partial query, wherein the presented document has been edited by a user of the computing device; obtaining a set of candidate query completions for the partial query; identifying one or more search result documents for each of one or more respective candidate query completions in the set; calculating similarity scores for candidate query completions in the set, wherein calculating a similarity score for a given candidate query completion of the set of candidate query completions is based at least in part on a similarity between content in the presented and content in the one or more search result documents identified for the given candidate query completion; selecting one or more of the candidate query completions in the set as refined query completions for the partial query based at least in part on the similarity scores; and providing the refined query completions for presentation by the computing device. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
Specification