Method and system for providing a search result
The present teaching relates to providing a search result. In one example, a search request is received from a user. A plurality of content items is determined based on the search request. One or more content items are selected from the plurality of content items. A framed structure having at least one sub-component is generated. A correspondence is determined between the one or more content items and the at least one sub-component. Each of the one or more content items is arranged with respect to a corresponding sub-component. A search result is generated based on the one or more content items and the framed structure. The search result is provided.
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 a search result, the method comprising:
receiving a search request from a user;
determining a plurality of content items based on the search request;
selecting one or more content items from the plurality of content items;
generating a framed structure having at least one sub-component;
determining a correspondence between the one or more content items and the at least one sub-component;
arranging each of the one or more content items with respect to a corresponding sub-component;
generating a search result based on the one or more content items and the framed structure; and
providing the search result.
2. The method of claim 1 , wherein the one or more content items are selected based on the framed structure.
3. The method of claim 1 , wherein the one or more content items include at least one of: a query suggestion, an advertisement, a multimedia, an image, a video, a link, a map, a snippet, and news.
4. The method of claim 1 , wherein the framed structure is generated based on the one or more content items.
5. The method of claim 1 , wherein determining a correspondence further comprises:
ranking the one or more content items to generate a first ranking list;
ranking the at least one sub-component to generate a second ranking list; and
determining the correspondence between the one or more content items and the at least one sub-component based on the first and second ranking lists.
6. The method of claim 5 , wherein ranking the one or more content items comprises:
extracting a common feature between the search request and each of the one or more content items;
calculating a response probability for each of the one or more content items based on the common feature and a machine learning model, wherein the response probability represents a predicted response rate from the user with respect to the content item; and
ranking the one or more content items based on their respective response probabilities.
7. The method of claim 1 , wherein the determining is based on an objective to maximize at least one of: an overall click through rate on the framed structure, an expected revenue gain from the one or more content items, and a degree of user engagement on the framed structure.
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 a search result, the method comprising:
obtaining a first search result including a plurality of content items;
selecting one or more content items from the plurality of content items;
generating a framed structure having at least one sub-component;
determining a correspondence between the one or more content items and the at least one sub-component;
modifying the first search result by moving each of the one or more content items into a corresponding sub-component;
generating a second search result based on the one or more content items and the framed structure; and
providing the second search result.
9. The method of claim 8 , further comprising providing the modified first search result.
10. A system having at least one processor, storage, and a communication platform connected to a network for providing a search result, the system comprising:
a request analyzer configured for receiving a search request from a user;
an item retrieval unit configured for determining a plurality of content items based on the search request and selecting one or more content items from the plurality of content items;
a framed structure adapter configured for generating a framed structure having at least one sub-component;
an item selection unit configured for determining a correspondence between the one or more content items and the at least one sub-component;
an item assignment unit configured for arranging each of the one or more content items with respect to a corresponding sub-component;
a search result organizer configured for generating a search result based on the one or more content items and the framed structure and providing the search result.
11. The system of claim 10 , wherein the one or more content items are selected based on the framed structure.
12. The system of claim 10 , wherein the one or more content items include at least one of: a query suggestion, an advertisement, a multimedia, an image, a video, a link, a map, a snippet, and news.
13. The system of claim 10 , wherein the framed structure is generated based on the one or more content items.
14. The system of claim 10 , further comprising:
a response probability analyzer configured for ranking the one or more content items to generate a first ranking list; and
a framed structure analyzer configured for ranking the at least one sub-component to generate a second ranking list, wherein the correspondence between the one or more content items and the at least one sub-component is determined based on the first and second ranking lists.
15. The system of claim 14 , further comprising:
a common feature extractor configured for extracting a common feature between the search request and each of the one or more content items;
a response probability calculator configured for calculating a response probability for each of the one or more content items based on the common feature and a machine learning model, wherein
the response probability represents a predicted response rate from the user with respect to the content item, and
the one or more content items are ranked based on their respective response probabilities.
16. The system of claim 10 , wherein the correspondence is determined based on an objective to maximize at least one of: an overall click through rate on the framed structure, an expected revenue gain from the one or more content items, and a degree of user engagement on the framed structure.
17. A system having at least one processor, storage, and a communication platform connected to a network for providing a search result, the system comprising:
a request analyzer configured for obtaining a first search result including a plurality of content items;
an item retrieval unit configured for selecting one or more content items from the plurality of content items;
a framed structure adapter configured for generating a framed structure having at least one sub-component;
an item selection unit configured for determining a correspondence between the one or more content items and the at least one sub-component;
an item assignment unit configured for modifying the first search result by moving each of the one or more content items into a corresponding sub-component; and
a search result organizer configured for generating a second search result based on the one or more content items and the framed structure and providing the second search result.
18. The system of claim 17 , wherein the search result organizer is further configured for providing the modified first search result.
19. A machine-readable tangible and non-transitory medium having information for providing a search result, wherein the information, when read by the machine, causes the machine to perform the following:
receiving a search request from a user;
determining a plurality of content items based on the search request;
selecting one or more content items from the plurality of content items;
generating a framed structure having at least one sub-component;
determining a correspondence between the one or more content items and the at least one sub-component;
arranging each of the one or more content items with respect to a corresponding sub-component;
generating a search result based on the one or more content items and the framed structure; and
providing the search result.
20. A machine-readable tangible and non-transitory medium having information for providing a search result, wherein the information, when read by the machine, causes the machine to perform the following:
obtaining a first search result including a plurality of content items;
selecting one or more content items from the plurality of content items;
generating a framed structure having at least one sub-component;
determining a correspondence between the one or more content items and the at least one sub-component;
modifying the first search result by moving each of the one or more content items into a corresponding sub-component;
generating a second search result based on the one or more content items and the framed structure; and
providing the second search result.