Recommendations from comments on online social networks

• US 10,452,671 B2
• Filed: 04/26/2016
• Issued: 10/22/2019
• Est. Priority Date: 04/26/2016
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Liu, Jin, Virtue, Erica Jean, Whalin, Gregory Paul
• Primary Examiner(s): Mobin, Hasanul
• Application Number:
  US15/139,028
• Publication Number:
  US 20170308589A1
• Time in Patent Office: 1,274 Days
• Field of Search: 707748
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06F 16/444 Spatial browsing, e.g. 2D maps, 3D or virtual spaces
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In one embodiment, a method includes receiving a text post from a client system of a first user of an online social network and parsing the text post to identify a query associated with the post. The method includes receiving one or more comments responsive to the text post from one or more second users of the online social network and determining, for each of the comments, whether the comment includes a recommendation responsive to the query. Moreover, the method includes identifying, for each comment with a responsive recommendation, one or more objects of the online social network associated with the recommendation and generating an aggregated recommendation list responsive to the query, where the list includes references to one or more of the identified objects.

Claims

1. A computer-implemented method comprising, by one or more computing devices:

receiving, from a client system of a first user of an online social network, a text post inputted by the first user;

parsing the text post to identify a query associated with the post;

receiving one or more comments responsive to the text post from one or more second users of the online social network, wherein each of the one or more comments includes textual content;

determining, for each of the one or more received comments, whether the textual content of the comment includes a recommendation responsive to the query associated with the post;

identifying, for each comment determined to include a responsive recommendation to the query, one or more objects of the online social network referenced in the textual content of the respective comment;

generating an aggregated recommendation list responsive to the query associated with the post, wherein the list includes references to one or more of the identified objects referenced in the textual content corresponding to the respective recommendation; and

sending, to the client system, instructions for presenting the aggregated recommendation list to the first user.

2. The method of claim 1, further comprising sending, to one or more client systems of one or more second users, instructions for presenting the aggregated recommendation list to the second user.

3. The method of claim 1, further comprising:

retrieving, for each identified object, one or more of a rating associated with the object, an address associated with the object, a snippet associated with the object, a social context associated with the object, or an image associated with the object;

wherein the aggregated recommendation list further includes, for each listed object, one or more of the rating associated with the object, the address associated with the object, the snippet associated with the object, the social context associated with the object, or the image associated with the object.

4. The method of claim 1, further comprising generating a graphical interface for displaying the recommendation list, wherein the graphical interface further comprises a map displaying a location of one or more of the identified objects.

5. The method of claim 1, further comprising generating a graphical interface for displaying the recommendation list, wherein the graphical interface further comprises an image associated with the identified query.

6. The method of claim 1, further comprising generating a graphical interface for displaying the recommendation list, wherein the graphical interface further displays one or more additional comments associated with one or more of the identified objects adjacent to the corresponding one or more references to the identified objects.

7. The method of claim 1, wherein parsing the text post to identify the query associated with the post comprises:

calculating a degree of confidence that the text post is associated with the query; and

identifying the query when the degree of confidence is above a threshold.

8. The method of claim 1, wherein parsing the text post to identify the query associated with the post comprises sending a confirmation prompt for the first user to verify the identified query.

9. The method of claim 1, wherein the text post inputted by the first user comprises one or more characters inputted into a composer interface, and wherein parsing the text post to identify the query associated with the post comprises:

reading, by a frontend-typeahead process, the one or more characters as they are inputted into the compose interface;

identifying, by a backend-typeahead process, one or more potential queries based on the one or more characters; and

sending, to the client system, a prompt listing one or more of the potential queries to the first user for selection.

10. The method of claim 1, further comprising, wherein the one or more comments from the one or more second users comprises one or more characters inputted into a composer interface, and wherein determining whether the comment includes a recommendation comprises:

reading, by a frontend-typeahead process, the one or more characters as they are inputted into the compose interface;

identifying, by a backend-typeahead process, one or more potential objects based on the one or more characters; and

sending, to the one or more second users, a prompt listing one or more of the potential objects for selection.

11. The method of claim 1, further comprising:

ranking the one or more identified objects.

12. The method of claim 11, wherein, for each identified object, the ranking is based on one or more of a rating associated with the identified object, a social-graph affinity of the first user with respect to the identified object, or one or more social signals associated with the identified object.

13. The method of claim 1, further comprising sending a notification to the first user when the first user is within a predetermined distance of one or more of the identified objects.

14. The method of claim 1, further comprising:

detecting that a number of recommendations responsive to the query is below a threshold number of recommendations; and

adding one or more additional recommendations responsive to the query to the aggregated recommendation list.

15. The method of claim 1, wherein the query is associated with a particular object of the online social network, and wherein the method further comprises:

determining one or more second users that have a social-graph affinity with respect to the particular object above a predetermined threshold affinity; and

sending a notification to the one or more second users to provide an additional recommendation responsive to the query.

16. The method of claim 1, further comprising generating an itinerary referencing one or more of the identified objects based on an information associated with the first user.

17. 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 of the online social network, respectively.

18. 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 of an online social network, a text post inputted by the first user;

parse the text post to identify a query associated with the post;

receive one or more comments responsive to the text post from one or more second users of the online social network, wherein each of the one or more comments includes textual content;

determine, for each of the one or more received comments, whether the textual content of the comment includes a recommendation responsive to the query associated with the post;

identify, for each comment determined to include a responsive recommendation to the query, one or more objects of the online social network referenced in the textual content of the respective comment;

generate an aggregated recommendation list responsive to the query associated with the post, wherein the list includes references to one or more of the identified objects referenced in the textual content corresponding to the respective recommendation; and

send, to the client system, instructions for presenting the aggregated recommendation list to the first user.

19. A system comprising:

one or more processors; and

a non-transitory 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 of an online social network, a text post inputted by the first user;

parse the text post to identify a query associated with the post;

receive one or more comments responsive to the text post from one or more second users of the online social network, wherein each of the one or more comments includes textual content;

determine, for each of the one or more received comments, whether the textual content of the comment includes a recommendation responsive to the query associated with the post;

identify, for each comment determined to include a responsive recommendation to the query, one or more objects of the online social network referenced in the textual content of the respective comment;

generate an aggregated recommendation list responsive to the query associated with the post, wherein the list includes references to one or more of the identified objects reference in the textual content corresponding to the respective recommendation; and

send, to the client system, instructions for presenting the aggregated recommendation list to the first user.