Automatic completion of fragments of text
AssigneeGoogle Inc.
InventorsGeorges R. Harik, Simon Tong, David R. Cheng
Life of this patent
Estimating the term…
Abstract
A system offers potential completions for fragments of text. The system may obtain a text fragment and identify documents that include the text fragment. The system may locate sentences within the documents that include at least a portion of the text fragment, identify sentence endings associated with the located sentences, and present the sentence endings as potential completions for the text fragment.
Claims23
A method comprising:
- identifying, by one or more processors, sentences, within one or more documents, that include text represented by a query;
- determining, by one or more processors and from the identified sentences, completions for the query;
- determining, by one or more processors, that two or more of the completions have text in common;
- merging, by one or more processors, the two or more completions based on the text in common;
- and
- outputting, by one or more processors and for presentation, the completions as potential completions for the query.
A non-transitory computer-readable memory device including one or more instructions for execution by one or more processors, the instructions comprising:
- one or more instructions that, when executed by the one or more processors, cause that one or more processors to:
- identify sentences, within one or more documents, that include text represented by a query;
- determine, from the identified sentences, completions for the query;
- determine that two or more of the completions have text in common;
- merge the two or more completions based on the text in common;
- and
- output, for presentation, the completions as potential completions for the query.
A system comprising:
- one or more severs to:
- identify sentences, within one or more documents, that include text represented by a query;
- determine, from the identified sentences, completions for the query;
- determine that two or more of the completions have text in common;
- merge the two or more completions based on the text in common;
- score the completions;
- and
- output, for presentation, the scored completions as potential completions for the query.
Dependencies are inferred from the claim text.