FIELD: information technology.
SUBSTANCE: plurality of candidate queries is received that includes queries generated at least in part by applying one or more methods to extend the queries to the selected text and said additional text. Individual candidate queries from a given plurality of candidate queries are compared with text and context. Values are determined that suitably correspond to the said individual candidate queries, which values represent the probabilities that the corresponding candidate queries from these individual candidate queries correspond to the text and context, wherein each of these values being calculated according to at least language model. Plurality of candidate queries is ranked based, at least in part, on the values mentioned. Given plurality of candidate queries is represented in a list, arranged at least in part, according to the ranking. The second choice is made which is the selection of candidate request from the plurality of candidate queries.
EFFECT: increasing the accuracy of search queries.
20 cl, 5 dwg
Title | Year | Author | Number |
---|---|---|---|
CONSTRUCTION AND APPLICATION OF WEB-CATALOGUES FOR FOCUSED SEARCH | 2005 |
|
RU2382400C2 |
METHOD AND SYSTEM OF SEARCH QUERY PROCESSING | 2015 |
|
RU2640639C2 |
DOCUMENT LENGTH AS RELEVANCY STATISTIC ID FOR SEARCH RESULTS RANGING | 2009 |
|
RU2517271C2 |
DETECTION OF NAVIGATION SEARCH RESULTS | 2014 |
|
RU2730278C2 |
SURFACING NAVIGATIONAL SEARCH RESULTS | 2014 |
|
RU2680757C2 |
STUDYING AND USING CONTEXTUAL RULES OF EXTRACTING CONTENT TO ELIMINATE AMBIGUITY OF REQUESTS | 2015 |
|
RU2701110C2 |
CONTEXTUAL SEARCH IN MULTIMEDIA CONTENT | 2015 |
|
RU2726864C2 |
CONTEXTUAL SEARCH IN MULTIMEDIA CONTENT | 2015 |
|
RU2693915C2 |
ANNOTATION BY MEANS OF SEARCHING | 2007 |
|
RU2439686C2 |
RANKING DIAGRAM | 2007 |
|
RU2449357C2 |
Authors
Dates
2017-10-11—Published
2013-02-01—Filed