Method and system for providing context based query suggestions
The present teaching relates to providing a query suggestion. In one example, a request is received for query suggestions with respect to a query prefix input by a user. A plurality of query suggestions is determined based on the query prefix and a preceding query input by the user. A degree of popularity of the preceding query is determined. One or more query suggestions are selected from the plurality of query suggestions based on the degree of popularity of the preceding query. The one or more query suggestions are provided as a response to the request.
1. A method, implemented on a machine having at least one processor, storage, and a communication platform connected to a network for providing a query suggestion, the method comprising:
analyzing query logs stored in a database to generate a similar cluster of queries, wherein the cluster of queries is represented by a canonical query and the queries in the cluster of queries have a common uniform resource locator that corresponds to a most clicked content, wherein the canonical query comprises a most popular query of the cluster of queries;
receiving, via a search application operating on a computing device associated with a user, a first query input by the user during a search session, wherein the first query belongs to the cluster of queries;
receiving, after the first query during the search session via the search application, a query prefix input by the user;
determining whether a first pairing involving the first query and the prefix exists;
in the event that the first pairing does not exist, determining at least one second pairing involving the canonical query and the prefix;
selecting at least one query suggestion based on the at least second pairing; and
providing, via the search application, the at least one query suggestion as a response to the query prefix.
2. The method of claim 1 , wherein determining whether the first pairing exists is based on a query log.
3. The method of claim 1 , further comprising:
identifying, from query logs, one or more queries paired with the canonical query; and
assigning the one or more queries as being associated with the first query.
4. The method of claim 3 , further comprising:
generating a plurality of query pairs each of which comprises a query from the one or more queries and the first query; and
storing the plurality of query pairs in a query pair database.
5. The method of claim 1 , further comprising:
determining frequencies of each query in the cluster of queries;
identifying a query having a highest frequency from the cluster of queries; and
assigning the query having the highest frequency as being the canonical query.
6. The method of claim 5 , further comprising:
updating inverted index information stored in association with the cluster of queries based on changes to the frequencies of each query in the cluster of queries.
7. A system for providing a query suggestion, the system comprising:
memory comprising instructions; and
at least one processor that, in response to executing the instructions, is configured to:
analyze query logs stored in a database to generate a similar cluster of queries, wherein the cluster of queries is represented by a canonical query and the queries in the cluster of queries have a common uniform resource locator that corresponds to a most clicked content, wherein the canonical query comprises a most popular query of the cluster of queries;
receive, via a search application operating on a computing device associated with a user, a first query input by the user during a search session, wherein the first query belongs to the cluster of queries;
receive, after the first query during the search session via the search application, a query prefix input by the user;
determining whether a first pairing involving the first query and the prefix exists;
in the event that the first pairing does not exist, determine at least one second pairing involving the canonical query and the prefix;
select at least one query suggestion based on the at least second pairing; and
provide, via the search application, the at least one query suggestion as a response to the query prefix.
8. The system of claim 7 , wherein determining whether the first pairing exists is based on a query log.
9. The system of claim 7 , wherein the at least one processor is further configured to:
identify, from query logs, one or more queries paired with the canonical query; and
assign the one or more queries as being associated with the first query.
10. The system of claim 9 , wherein the at least one processor is further configured to:
generate a plurality of query pairs each of which comprises a query from the one or more queries and the first query; and
store the plurality of query pairs in a query pair database.
11. The system of claim 7 , wherein the at least one processor is further configured to:
determine frequencies of each query in the cluster of queries;
identify a query having a highest frequency from the cluster of queries; and
assign the query having the highest frequency as being the canonical query.
12. The system of claim 11 , wherein the at least one processor is further configured to:
updating inverted index information stored in association with the cluster of queries based on changes to the frequencies of each query in the cluster of queries.
13. A non-transitory machine-readable medium having information recorded thereon for providing a query suggestion, wherein the information, when read by the machine, causes the machine to perform the following:
analyzing query logs stored in a database to generate a similar cluster of queries, wherein the cluster of queries is represented by a canonical query and the queries in the cluster of queries have a common uniform resource locator that corresponds to a most clicked content, wherein the canonical query comprises a most popular query of the cluster of queries;
receiving, via a search application operating on a computing device associated with a user, a first query input by the user during a search session, wherein the first query belongs to the cluster of queries;
receiving, after the first query during the search session via the search application, a query prefix input by the user;
determining whether a first pairing involving the first query and the prefix exists;
in the event that the first pairing does not exist, determining at least one second pairing involving the canonical query and the prefix;
selecting at least one query suggestion based on the at least second pairing; and
providing, via the search application, the at least one query suggestion as a response to the query prefix.
14. The non-transitory machine-readable medium of claim 13 , wherein determining whether the first pairing exists is based on a query log.
15. The non-transitory machine-readable medium of claim 13 , wherein the machine is further configured to perform the following:
identifying, from query logs, one or more queries paired with the canonical query; and
assigning the one or more queries as being associated with the first query.
16. The non-transitory machine-readable medium of claim 15 , wherein the machine is further configured to perform the following:
generating a plurality of query pairs each of which comprises a query from the one or more queries and the first query; and
storing the plurality of query pairs in a query pair database.
17. The non-transitory machine-readable medium of claim 13 , wherein the machine is further configured to perform the following:
determining frequencies of each query in the cluster of queries;
identifying a query having a highest frequency from the cluster of queries;
assigning the query having the highest frequency as being the canonical query; and
updating inverted index information stored in association with the cluster of queries based on changes to the frequencies of each query in the cluster of queries.