Context-based ranking of search results

• US 9,805,126 B2
• Filed: 10/29/2014
• Issued: 10/31/2017
• Est. Priority Date: 06/03/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Patterson, Ryan, Johnson, Michael Dudley, Tseng, Erick
• Primary Examiner(s): Ahn, Sangwoo
• Application Number:
  US14/526,694
• Publication Number:
  US 20150058332A1
• Time in Patent Office: 1,098 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: H04L 12/1813 for computer conferences, e.g. chat rooms instant messaging H04L51/04; protocols for multimedia communication H04L65/1101; arrangements for multi-party communication H04L65/403; telephonic conference arrangements H04M3/56; television conference systems H04N7/15

Abstract

In one embodiment, a computing device may access a search query provided by a user; identify a set of search results in response to the search query, wherein one or more search results in the set are associated with a feature of a social-networking system; rank the set of search results based on one or more factors; boost one or more ranks of the one or more search results associated with the feature to bring the feature to the user'"'"'s attention; and present the set of search results to the user in order of its ranking.

Claims

1. A method comprising, by one or more computer systems of a social-networking system:

receiving, from a client device of a first user of the social-networking system, a search query comprising one or more characters inputted by the first user, the one or more characters being received as the first user inputs the one or more characters at the client device into a user interface of the social-networking system;

identifying one or more entities associated with the social-networking system matching the one or more characters of the search query;

ranking each of the identified entities matching the search query based on a calculated likelihood that the user will interact with a search result corresponding to the identified entity, wherein the calculated likelihood that the user will interact with the search result corresponding to the identified entity is based at least in part on a historical behavior of the user in selecting one or more prior search results related to the identified entity;

boosting one or more ranks of one or more of the identified entities matching the search query based on;

one or more business objectives of the social-networking system, wherein at least one of the business objectives comprises encouraging the first user to interact with the identified entity based on a level of social relevance of the identified entity with respect to the first user; and

a level of the user'"'"'s interaction with one or more features of the social-networking system associated with the identified entity, wherein the boosting is designed to increase the level of the user'"'"'s interaction with the one or more features of the social-networking system associated with the identified entity; and

sending, to the client device of the first user and in response to the received search query, one or more search results for presentation to the user as the user inputs the one or more characters at the client device into the user interface, each search result corresponding to one of the identified entities, the search results being presented according to the ranking and boosting of the corresponding identified entities, the presentation of the search results to the user enabling the user to select one or more of the search results to interact with.

2. The method of claim 1, wherein the search query is a user-generated character string comprising the one or more characters inputted by the user, the user-generated character string being received from the client device of the first user, and wherein the user-generated character string is entered by the first user in a query field and rendered at the client device as each character of the character string is entered by the user.

3. The method of claim 1, further comprising auto-populating, at the client system, a query field with the search results.

4. The method of claim 1, wherein the search query is received from a client-side process executing within the client device or from a client-side document rendering application in response to one or more instructions from the client-side process.

5. The method of claim 1, wherein the search results are provided as real-time suggestions responsive to the one or more characters thus far inputted by the first user.

6. The method of claim 1, wherein one or more of the business objectives is associated with one or more of the features.

7. The method of claim 1, wherein one or more of the business objectives comprises encouraging users to use one or more of the features.

8. The method of claim 7, wherein the lower level of interaction the user has with the one or more features, the higher the one or more ranks of one or more of the identified entities associated with the one or more features are boosted.

9. The method of claim 1, wherein at least one of the features is the user'"'"'s ability to form a friend connection with other users of the social-networking system.

10. The method of claim 9, wherein the one or more features further comprise an ability to:

form a social group;

organize an event;

upload a photo;

read a digest comprising at least one social-media update;

interact with a new function recently implemented by the social-networking system;

or

play an online game supported by the social-networking system.

11. The method of claim 1, wherein ranking of each of the identified entities is further based on a location of the user.

12. The method of claim 1, wherein boosting one or more ranks of one or more of the identified entities comprises boosting the ranking of the one or more of the identified entities to bring one or more features associated with the identified entities to the user'"'"'s attention.

13. The method of claim 1, wherein ranking each of the identified entities is further based on a level of content relevance of the identified entity to the search query.

14. The method of claim 1, wherein ranking each of the identified entities is further based on a level of social relevance of the identified entity to the search query.

15. The method of claim 1, wherein boosting one or more ranks of one or more of the identified entities is further based on a boosting coefficient determined for the identified entity based on the user'"'"'s level of interaction with one or more features associated with the identified entity.

16. The method of claim 1, wherein:

the social-networking system is associated with a social graph;

the social graph comprises one or more nodes and one or more edges, each node representing an entity, each edge connecting two nodes and representing a relationship between the two entities respectively represented by the two nodes; and

ranking each of the identified entities is further based on, for each identified entity, a distance between a first node representing the identified entity and a second node representing the first user within the social graph.

17. A system comprising:

a memory; and

one or more processors coupled to the memory and configured to perform operations comprising;

receive, from a client device of a first user of a social-networking system, a search query comprising one or more characters inputted by the first user, the one or more characters being received as the first user inputs the one or more characters at the client device into a user interface of the social-networking system;

identify one or more entities associated with the social-networking system matching the one or more characters of the search query;

rank each of the identified entities matching the search query based on a calculated likelihood that the user will interact with a search result corresponding to the identified entity, wherein the calculated likelihood that the user will interact with the search result corresponding to the identified entity is based at least in part on a historical behavior of the user in selecting one or more prior search results related to the identified entity;

boost one or more ranks of one or more of the identified entities matching the search query based on;

one or more business objectives of the social-networking system, wherein at least one of the business objectives comprises encouraging the first user to interact with the identified entity based on a level of social relevance of the identified entity with respect to the first user; and

a level of the user'"'"'s interaction with one or more features of the social-networking system associated with the identified entity, wherein the boosting is designed to increase the level of the user'"'"'s interaction with the one or more features of the social-networking system associated with the identified entity; and

send, to the client device of the first user and in response to the received search query, one or more search results for presentation to the user as the user inputs the one or more characters at the client device into the user interface, each search result corresponding to one of the identified entities, the search results being presented according to the ranking and boosting of the corresponding identified entities, the presentation of the search results to the user enabling the user to select one or more of the search results to interact with.

18. One or more computer-readable non-transitory storage media embodying software operable when executed by one or more computer systems to:

receive, from a client device of a first user of a social-networking system, a search query comprising one or more characters inputted by the first user, the one or more characters being received as the first user inputs the one or more characters at the client device into a user interface of the social-networking system;

identify one or more entities associated with the social-networking system matching the one or more characters of the search query;

rank each of the identified entities matching the search query based on a calculated likelihood that the user will interact with a search result corresponding to the identified entity, wherein the calculated likelihood that the user will interact with the search result corresponding to the identified entity is based at least in part on a historical behavior of the user in selecting one or more prior search results related to the identified entity;

boost one or more ranks of one or more of the identified entities matching the search query based on;

one or more business objectives of the social-networking system, wherein at least one of the business objectives comprises encouraging the first user to interact with the identified entity based on a level of social relevance of the identified entity with respect to the first user; and

a level of the user'"'"'s interaction with one or more features of the social-networking system associated with the identified entity, wherein the boosting is designed to increase the level of the user'"'"'s interaction with the one or more features of the social-networking system associated with the identified entity; and

send, to the client device of the first user and in response to the received search query, one or more search results for presentation to the user as the user inputs the one or more characters at the client device into the user interface, each search result corresponding to one of the identified entities, the search results being presented according to the ranking and boosting of the corresponding identified entities, the presentation of the search results to the user enabling the user to select one or more of the search results to interact with.