Method and system for providing query suggestions including entities
Methods, systems and programming for providing query suggestions including entities. In one example, a prefix of a query is first received. A plurality of query suggestions are then identified based on the prefix of the query. The plurality of query suggestions include at least one entity. Scores of each of the plurality of query suggestions are computed using a first model. The first model includes an adjustable parameter used for computing the score of the at least one entity. The plurality of question suggestions are ranked based, at least in part, on the scores.
1. A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for providing query suggestions, the method comprising the steps of:
receiving a prefix of a query from a user;
identifying a plurality of query suggestions based on the prefix of the query, wherein each of a first group of the plurality of query suggestions includes an entity that corresponds to the prefix;
computing an initial score for each of the plurality of query suggestions;
adjusting the initial score of each of the first group of the plurality of query suggestions based on a first model to generate an updated score for the query suggestion, wherein the first model is a function of an adjustable parameter associated with the query suggestion, and wherein the adjustable parameter associated with the query suggestion is determined based on a category of the query suggestion and a length of the prefix;
ranking the plurality of query suggestions based on the updated scores for the first group of the plurality of query suggestions;
determining a quality measure, indicative of quality of the ranked plurality of query suggestions, based on interaction of the user with respect to the ranked plurality of query suggestions; and
updating the first model based on the quality measure.
2. The method of claim 1 , wherein the adjustable parameter associated with the query suggestion is further updated based on a second model in accordance with activities of the user with respect to the first group of the plurality of query suggestions.
3. The method of claim 2 , wherein the activities of the user with respect to the first group of the plurality of query suggestions include a selection of a query suggestion from the first group of the plurality of query suggestions.
4. The method of claim 1 , wherein, for each of the first group of the plurality of query suggestions, the initial score is calculated based on popularity of the respective entity in the query suggestion and based on relevance between the respective entity in the query suggestion and the user from whom the prefix of the query is received.
5. The method of claim 4 , wherein
the initial score, for each of the first group of the plurality of query suggestions, is calculated based on a profile of the user and a profile of the respective entity in the query suggestion, and
the profile of the respective entity is generated based on a category of the entity.
6. The method of claim 1 , wherein
the plurality of query suggestions include a first entity from a first category, a second entity from a second category, and a non-entity keyword, and
the first model includes a first adjustable parameter for the first entity, a second adjustable parameter for the second entity, and a third adjustable parameter for the non-entity keyword.
7. The method of claim 1 , wherein the plurality of query suggestions includes one or more remaining query suggestions in a second group, and
wherein the ranking of the plurality of query suggestions is further based on the initial scores of the remaining query suggestions.
8. A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for providing query suggestions, the method comprising the steps of:
receiving a prefix of a query from a user;
identifying a plurality of query suggestions including a first group of the plurality of query suggestions and at least one non-entity keyword based on the prefix of the query, wherein each of the first group of the plurality of query suggestions include an entity;
computing an initial score for each of the plurality of query suggestions;
adjusting the initial score of each of the first group of the plurality of query suggestions based on a first model to generate an updated score for the query suggestion, wherein the first model is a function of an adjustable parameter associated with the query suggestion, and wherein the adjustable parameter associated with the query suggestion is determined based on a category of the query suggestion and a length of the prefix;
ranking the plurality of query suggestions based on the updated scores for the first group of the plurality of query suggestions and the initial score for the at least one non-entity keyword;
providing the ranked plurality of query suggestions to the user, wherein the first group of
the plurality of query suggestions and the at least one non-entity keyword are presented in different manners
determining a quality measure, indicative of quality of the ranked plurality of query suggestions, based on interaction of the user with respect to the ranked plurality of query suggestions; and
adjusting the first model based on the quality measure.
9. The method of claim 8 , wherein each of the first group of the plurality of query suggestions is presented with a label indicating a category in which the query suggestion belongs to.
10. A system having at least one processor, storage, and a communication platform for providing query suggestions, the system comprising:
a retrieving module configured to receive a prefix of a query from a user and identify a plurality of query suggestions based on the prefix of the query;
a ranking module configured to compute an initial score for each of the plurality of query suggestions and adjusting the initial score of each of a first group of the plurality of query suggestions based on a first model to generate an updated score for the query suggestion and rank the plurality of query suggestions based on the updated scores for the first group of the plurality of query suggestions,
wherein each of a first group of the plurality of query suggestions includes an entity that corresponds to the prefix, the first model is a function of an adjustable parameter associated with the query suggestion, and the adjustable parameter associated with the query suggestion is determined based on a category of the query suggestion and a length of the prefix; and
a query suggestion evaluating module determining a quality measure, indicative of quality of the ranked plurality of query suggestions, based on interaction of the user with respect to the ranked plurality of query suggestions, for updating the first model based on the quality measure.
11. The system of claim 10 , wherein the adjustable parameter associated with the query suggestion is further updated based on a second model in accordance with activities of the user with respect to the first group of the plurality of query suggestions.
12. The system of claim 11 , wherein the activities of the user with respect to the first group of the plurality of query suggestions include a selection of a query suggestion from the first group of the plurality of query suggestions.
13. The system of claim 10 , wherein, for each of the first group of the plurality of query suggestions, the initial score is calculated based on popularity of the respective entity in the query suggestion and based on relevance between the respective entity in the query suggestion and the user from whom the prefix of the query is received.
14. The system of claim 13 , wherein
the initial score, for each of the first group of the plurality of query suggestions, is calculated based on a profile of the user and a profile of the respective entity in the query suggestion, and
the profile of the respective entity is generated based on a category of the entity.
15. The system of claim 10 , wherein
the plurality of query suggestions include a first entity from a first category, a second entity from a second category, and a non-entity keyword, and
the first model includes a first adjustable parameter for the first entity, a second adjustable parameter for the second entity, and a third adjustable parameter for the non-entity keyword.
16. A non-transitory machine-readable medium having information recorded thereon for providing query suggestions, wherein the information, when read by the machine, causes the machine to perform the following:
receiving a prefix of a query from a user;
identifying a plurality of query suggestions based on the prefix of the query, wherein each of a first group of the plurality of query suggestions includes an entity that corresponds to the prefix;
computing an initial score for each of the plurality of query suggestions;
adjusting the initial score of each of the first group of the plurality of query suggestions based on a first model to generate an updated score for the query suggestion, wherein the first model is a function of an adjustable parameter associated with the query suggestion, and wherein the adjustable parameter associated with the query suggestion is determined based on a category of the query suggestion and a length of the prefix;
ranking the plurality of query suggestions based on the updated scores for the first group of the plurality of query suggestions;
determining a quality measure, indicative of quality of the ranked plurality of query suggestions, based on interaction of the user with respect to the ranked plurality of query suggestions; and
updating the first model based on the quality measure.
17. The medium of claim 16 , wherein the adjustable parameter associated with the query suggestion is further updated based on a second model in accordance with activities of the user with respect to the first group of the plurality of query suggestions.
18. The medium of claim 17 , wherein the activities of the user with respect to the first group of the plurality of query suggestions include a selection of a query suggestion from the first group of the plurality of query suggestions.
19. The medium of claim 16 , wherein, for each of the first group of the plurality of query suggestions, the initial score is calculated based on popularity of the respective entity in the query suggestion and based on relevance between the respective entity in the query suggestion and the user from whom the prefix of the query is received.