Back to results
US 8,898,180 B2Granted
Method and system for querying information
AssigneeAlibaba Group Holding Limited
InventorsYuheng Xie, Wenwu Ou
Life of this patent
Estimating the term…
Abstract
Performing a query includes receiving a user input, determining a first set of query keywords based at least in part on the user input, obtaining, based on at least some of the first set of query keywords, a user feedback log that includes historical query results, determining a second set of query keywords based on the user feedback log, and making a query based on at least some of the second set of query keywords.
Claims14
A method of performing a query, comprising:
- receiving a user input;
- determining a first set of query keywords based at least in part on the user input, comprising:
- determining whether the user input includes characters of a character based language;
- in the event that the user input includes the characters of the character based language:
- partitioning the user input into words based on context;
- and
- adding the partitioned words into the first set of query keywords;
- obtaining, based on at least some of the first set of query keywords, a user feedback log that includes historical query results that are in response to previously made queries using the first set of query keywords, and selection frequencies, wherein the selection frequencies include:
- selection frequencies of the historical query results, selection frequencies of content of the historical query results, or a combination thereof;
- obtaining a user characteristic of the user who generated the user input;
- determining a second set of query keywords based at least in part on the user feedback log and the user characteristic, comprising:
- partitioning the historical query results into a plurality of partitioned words based on context;
- and
- determining the second set of query keywords based at least in part on the plurality of partitioned words;
- and
- making a query based on at least some of the second set of query keywords,
- wherein the user characteristic includes user region, user gender, user age, user career, user taste, or any combination thereof;
- wherein the second set of query keywords includes:
- one or more words that are adjacent to at least some of the plurality of partitioned words, one or more words that include at least a portion of a word of the plurality of partitioned words, one or more words that include at least a partitioned word in the plurality of partitioned words in the event that the first query keyword includes a substring of the partitioned word, or any combination thereof;
- and
- wherein the second set of query keywords includes one or more latent words that correspond to the first set of query keywords, the one or more latent words having a latent meaning with respect to the first set of query keywords, the latent meaning comprising words that appear in pairs, a plurality of words that appear in a certain order, a word or a character that forms another word, or any combination thereof.
18 more elements
A query system comprising:
- an interface configured to receive a user input;
- one or more processors coupled to the interface, configured to:
- determine a first set of query keywords based at least in part on the user input, comprising:
- determine whether the user input includes characters of a character based language;
- in the event that the user input includes the characters of the character based language:
- partition the user input into words based on context;
- and
- add the partitioned words into the first set of query keywords;
- obtain, based on at least some of the first set of query keywords, a user feedback log that includes historical query results that are in response to previously made queries using the first set of query keywords, and selection frequencies, wherein the selection frequencies include:
- selection frequencies of the historical query results, selection frequencies of content of the historical query results, or a combination thereof;
- obtain a user characteristic of the user who generated the user input;
- determine second set of query keywords based at least in part on the user feedback log and the user characteristic, comprising:
- partition the historical query results into a plurality of partitioned words based on context;
- and
- determine the second set of query keywords based at least in part on the plurality of partitioned words;
- and
- make a query based on at least some of the second set of query keywords,
- wherein the user characteristic includes user region, user gender, user age, user career, user taste, or any combination thereof;
- wherein the second set of query keywords includes:
- one or more words that are adjacent to at least some of the plurality of partitioned words, one or more words that include at least a portion of a word of the plurality of partitioned words, one or more words that include at least a partitioned word in the plurality of partitioned words in the event that the first query keyword includes a substring of the partitioned word, or any combination thereof;
- and
- wherein the second set of query keywords includes one or more latent words that correspond to the first set of query keywords, the one or more latent words having a latent meaning with respect to the first set of query keywords, the latent meaning comprising words that appear in pairs, a plurality of words that appear in a certain order, a word or a character that forms another word, or any combination thereof;
- and
- one or more memories coupled to the one or more processors, configured to provide the processors with instructions.
21 more elements
Dependencies are inferred from the claim text.