Method and system for providing query suggestions based on user feedback
Methods, systems and programming for providing query suggestions based on user feedback. In one example, a prefix of a query is first received. An input including a prefix of a query is received from a user in a search session. A plurality of query suggestions are fetched based on the prefix of the query. Rankings of the plurality of query suggestions are determined based, at least in part, on the user's previous interactions in the search session with respect to at least one of the plurality of query suggestions. The at least one of the plurality of query suggestions has been previously provided to the user in the search session. The plurality of query suggestions are provided in the search session based on their rankings as a response to the input.
1. A method for providing query suggestions, the method comprising:
receiving, in a search session, an input from a user;
obtaining a plurality of query suggestions based on the input;
determining an initial ranking of the plurality of query suggestions based on bias information comprising one or more of: popularity of each of the plurality of query suggestions, previous query information of the user, time information of each of the plurality of query suggestions, and the user's profile;
machine-learning, via a training model based on historical user interaction data associated with the user within the search session, a weighting parameter indicating the user's prior search behavior patterns, wherein the weighting parameter is a vector in which each element corresponds to a user interaction feature;
monitoring, by an engine in the search session, user feedback with respect to at least one of the plurality of query suggestions which is not selected by the user after being provided by the user;
generating, based on the user feedback monitored in the search session and the weighting parameter, an adaptive ranking score indicating a probability whether the user is interested in a query suggestion;
adjusting the initial ranking based on the adaptive ranking score;
providing, based on the adjusted ranking, the plurality of query suggestions to the user; and
in receipt of the user's selection of one of the plurality of query suggestions provided to the user, providing a hyperlink as a query result.
2. The method of claim 1 , wherein the weighting parameter is estimated offline.
3. The method of claim 1 , wherein the weighting parameter is personalized for the user.
4. The method of claim 1 , wherein the search session extends from receipt of a first character of the input until an execution of a search based on the query submitted by the user.
5. The method of claim 1 , wherein the user feedback indicates negative user feedback or neutral user feedback with respect to a query suggestion based on the input.
6. The method of claim 5 , wherein the negative user feedback is represented by a first time spent by the user on a query suggestion based on the input, and the first time spent indicates that the user has examined the query suggestion before deciding not to select the query suggestion; and
wherein the neutral user feedback is represented by a second time, shorter than the first time, spent by the user on the query suggestion based on the input, and the second time spent indicates that the user did not examine the query suggestion.
7. The method of claim 5 , wherein the adjusted ranking is based on the negative user feedback or neutral user feedback.
8. A non-transitory, computer-readable medium having information recorded thereon for providing query suggestions, when read by at least one processor, effectuate operations comprising:
receiving, in a search session, an input from a user;
obtaining a plurality of query suggestions based on the input;
determining an initial ranking of the plurality of query suggestions based on bias information comprising one or more of: popularity of each of the plurality of query suggestions, previous query information of the user, time information of each of the plurality of query suggestions, and the user's profile;
machine-learning, via a training model based on historical user interaction data associated with the user within the search session, a weighting parameter indicating the user's prior search behavior patterns, wherein the weighting parameter is a vector in which each element corresponds to a user interaction feature;
monitoring, by an engine in the search session, user feedback with respect to at least one of the plurality of query suggestions which is not selected by the user after being provided by the user;
generating, based on the user feedback monitored in the search session and the weighting parameter, an adaptive ranking score indicating a probability whether the user is interested in a query suggestion;
adjusting the initial ranking based on the adaptive ranking score;
providing, based on the adjusted ranking, the plurality of query suggestions to the user; and
in receipt of the user's selection of one of the plurality of query suggestions provided to the user, providing a hyperlink as a query result.
9. The medium of claim 8 , wherein the weighting parameter is estimated offline.
10. The medium of claim 8 , wherein the weighting parameter is personalized for the user.
11. The medium of claim 8 , wherein the search session extends from receipt of a first character of the input until an execution of a search based on the query submitted by the user.
12. The medium of claim 8 , wherein the user feedback indicates negative user feedback or neutral user feedback with respect to a query suggestion based on the input.
13. The medium of claim 12 , wherein the negative user feedback is represented by a first time spent by the user on a query suggestion based on the input, and the first time spent indicates that the user has examined the query suggestion before deciding not to select the query suggestion; and
wherein the neutral user feedback is represented by a second time, shorter than the first time, spent by the user on the query suggestion based on the input, and the second time spent indicates that the user did not examine the query suggestion.
14. The medium of claim 12 , wherein the adjusted ranking is based on the negative user feedback or neutral user feedback.
15. A system for providing query suggestions, the system comprising:
memory storing computer program instructions; and
one or more processors that, in response to executing the computer program instructions, effectuate operations comprising:
receiving, in a search session, an input from a user;
obtaining a plurality of query suggestions based on the input;
determining an initial ranking of the plurality of query suggestions based on bias information comprising one or more of: popularity of each of the plurality of query suggestions, previous query information of the user, time information of each of the plurality of query suggestions, and the user's profile;
machine-learning, via a training model based on historical user interaction data associated with the user within the search session, a weighting parameter indicating the user's prior search behavior patterns, wherein the weighting parameter is a vector in which each element corresponds to a user interaction feature;
monitoring, by an engine in the search session, user feedback with respect to at least one of the plurality of query suggestions which is not selected by the user after being provided by the user;
generating, based on the user feedback monitored in the search session and the weighting parameter, an adaptive ranking score indicating a probability whether the user is interested in a query suggestion;
adjusting the initial ranking based on the adaptive ranking score;
providing, based on the adjusted ranking, the plurality of query suggestions to the user; and
in receipt of the user's selection of one of the plurality of query suggestions provided to the user, providing a hyperlink as a query result.
16. The system of claim 15 , wherein the weighting parameter is estimated offline.
17. The system of claim 15 , wherein the weighting parameter is personalized for the user.
18. The system of claim 15 , wherein the search session extends from receipt of a first character of the input until an execution of a search based on the query submitted by the user.
19. The system of claim 15 , wherein the user feedback indicates negative user feedback or neutral user feedback with respect to a query suggestion based on the input.
20. The system of claim 19 , wherein the negative user feedback is represented by a first time spent by the user on a query suggestion based on the input, and the first time spent indicates that the user has examined the query suggestion before deciding not to select the query suggestion; and
wherein the neutral user feedback is represented by a second time, shorter than the first time, spent by the user on the query suggestion based on the input, and the second time spent indicates that the user did not examine the query suggestion.