NATURAL LANGUAGE SEARCH RESULTS FOR INTENT QUERIES
First Claim
1. A computer-implemented method comprising:
- parsing, using at least one processor, documents from authoritative sources to generate heading-text pairs; and
for each heading-text pair;
associating, using the at least one processor, the heading-text pair with a first intent template of a plurality of intent templates, the first intent template having an associated question category,determining a topic and a question category for the heading-text pair based on the first intent template, andstoring the heading-text pair in a data store keyed by topic and question category.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods provide natural language search results to clear-intent queries. To provide the natural language search results, a system may parse a document from an authoritative source to generate at least one heading-text pair, the text appearing under the heading in the document. The system may assign a topic and a question category to the heading-text pair and store the heading-text pair in a data store keyed by the topic and the question category. The system determines that a query corresponds to the topic and the question category, and provides the heading-text pair as a natural language search result for the query. In some implementations, the text portion of the heading-text pair may be a paragraph or a list of items and the natural language search result may be provided with conventional snippet-based search results in response to the query.
42 Citations
23 Claims
-
1. A computer-implemented method comprising:
-
parsing, using at least one processor, documents from authoritative sources to generate heading-text pairs; and for each heading-text pair; associating, using the at least one processor, the heading-text pair with a first intent template of a plurality of intent templates, the first intent template having an associated question category, determining a topic and a question category for the heading-text pair based on the first intent template, and storing the heading-text pair in a data store keyed by topic and question category. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computer system comprising:
-
at least one processor; and memory storing instructions that, when executed by the at least one processor, cause the computer system to perform operations comprising; parse a document from an authoritative source to generate at least one heading-text pair, the text appearing under the heading in the document, assign a topic and a question category to the heading-text pair, store the heading-text pair in a data store keyed by the topic and the question category, determine that a query corresponds to the topic and the question category, and provide the heading-text pair as a natural language search result for the query. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A computer system comprising:
-
at least one processor; and memory storing instructions that, when executed by the at least one processor, cause the computer system to perform operations comprising; parse documents from authoritative sources to generate a plurality of heading-text pairs, generate a set of potential templates from the heading-text pairs, determine a quantity of occurrences for at least some of the set of potential templates, and store potential templates with highest quantities as intent templates in a memory of the computer system. - View Dependent Claims (20, 21, 22, 23)
-
Specification