Search intent for queries on online social networks

• US 9,483,803 B2
• Filed: 12/29/2015
• Issued: 11/01/2016
• Est. Priority Date: 05/03/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Raina, Rajat, Dhamdhere, Kedar, Chatot, Olivier
• Primary Examiner(s): MACKES, KRIS E
• Application Number:
  US14/983,197
• Publication Number:
  US 20160132507A1
• Time in Patent Office: 308 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24565 Triggers; Constraints
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In one embodiment, a method includes receiving, from a client system of a first user, a structured query comprising references to one or more selected objects accessible by the computing device, generating one or more search results corresponding to the structured query, wherein each search result corresponds to a particular object accessible by the computing device, determining one or more search intents based at least on whether one or more of the selected objects referenced in the structured query match objects corresponding to a search intent indexed in a pattern-detection model, and scoring the search results based on one or more of the search intents.

Claims

1. A method comprising, by a computing device:

receiving, from a client system of a first user, a structured query comprising references to one or more selected objects accessible by the computing device;

generating one or more search results corresponding to the structured query, wherein each search result corresponds to a particular object accessible by the computing device;

determining one or more search intents based at least on whether one or more of the selected objects referenced in the structured query match objects corresponding to a search intent indexed in a pattern-detection model; and

scoring the search results based on one or more of the search intents.

2. The method of claim 1, further comprising:

accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, the nodes comprising;

a first node corresponding to the first user; and

a plurality of second nodes corresponding to a plurality of objects accessible by the computing device, respectively.

3. The method of claim 2, wherein the structured query comprises references to one or more selected nodes from the plurality of nodes and one or more selected edges from the plurality of edges, and wherein the search intents are determined by identifying one or more search intents that correspond to one or more of the selected nodes or one or more of the selected edges.

4. The method of claim 2, wherein scoring the search results based on one or more of the search intents comprise scoring the search results based on a degree of separation between the first node and the second node corresponding to the search result.

5. The method of claim 1, wherein determining the one or more search intents comprises:

accessing the pattern-detection model that indexes one or more objects as corresponding to one or more search intents;

determining whether any of the selected objects referenced in the structured query match the objects indexed in the pattern-detection model; and

identifying, for each matching object, one or more search intents indexed in the pattern-detection model as corresponding to the matching object.

6. The method of claim 1, wherein determining the one or more search intents is further based on a search history associated with the first user.

7. The method of claim 1, wherein the structured query comprises one or more n-grams, and wherein determining the one or more search intents is further based on identifying one or more search intents that correspond to one or more of the n-grams.

8. The method of claim 1, wherein the first user is associated with a profile page of an online social network, and wherein determining the one or more search intents is further based on user information from the profile page.

9. The method of claim 1, further comprising generating a query command based on the structured query, the query command comprising one or more query constraints.

10. The method of claim 9, wherein determining the one or more search intents is further based on one or more of the query constraints of the query command.

11. The method of claim 9, wherein each search result is associated with one or more objects, and wherein each of the one or more query constraints is satisfied by one or more of the objects of the search result.

12. The method of claim 11, wherein scoring the search results based on one or more of the search intents comprises scoring each search result based on a count of the objects of the search result that satisfy the one or more query constraints.

13. The method of claim 11, wherein scoring the search results based on one or more of the search intents comprises scoring each search result based on a ratio of the objects of the search result that satisfy the one or more query constraints to a total number of objects of the search result.

14. The method of claim 11, wherein the query command comprises a plurality of query constraints, and wherein scoring the search results based on one or more of the search intents comprises scoring each search result based on a count of the objects of the search result that satisfy at least two of the plurality of query constraints.

15. The method of claim 11, wherein the one or more objects associated with each search result comprise content of a profile page of an online social network associated with the search result, the profile page being associated with the object corresponding to the search result.

16. The method of claim 1, wherein scoring the search results based on one or more of the search intents comprise scoring the search results based on a social-graph affinity associated with the first user.

17. The method of claim 1, further comprising:

identifying one or more advertisements to display to the user based on one or more of the search intents; and

sending, to the client system, the one or more advertisements for display to the first user.

18. The method of claim 1, further comprising:

sending, to the client system, one or more of the search results for display to the first user.

19. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

receive, from a client system of a first user, a structured query comprising references to one or more selected objects accessible by the computing device;

generate one or more search results corresponding to the structured query, wherein each search result corresponds to a particular object accessible by the computing device;

determine one or more search intents based at least on whether one or more of the selected objects referenced in the structured query match objects corresponding to a search intent indexed in a pattern-detection model; and

score the search results based on one or more of the search intents.

20. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

receive, from a client system of a first user, a structured query comprising references to one or more selected objects accessible by the computing device;

generate one or more search results corresponding to the structured query, wherein each search result corresponds to a particular object accessible by the computing device;

determine one or more search intents based at least on whether one or more of the selected objects referenced in the structured query match objects corresponding to a search intent indexed in a pattern-detection model; and

score the search results based on one or more of the search intents.