Travel recommendations on online social networks

• US 9,820,094 B2
• Filed: 08/10/2015
• Issued: 11/14/2017
• Est. Priority Date: 08/10/2015
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Zhang, Ying, Zhang, Wei, Scheffer, Nicolas, Calvi, Richard, Yan, Xiaohua
• Primary Examiner(s): Ajibade Akonai, Olumide T
• Application Number:
  US14/822,710
• Publication Number:
  US 20170048664A1
• Time in Patent Office: 827 Days
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0267 Wireless devices
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

In one embodiment, a social-networking system may receive, from a client system of a first user of an online social network, an indication that the first user is traveling to a first geographic location, and identify one or more second geographic locations within a threshold distance from the first geographic location. The second geographic locations may be determined based on a travel-recommendation model. The travel-recommendation model may include aggregated user information from the online social network associated with the first user and aggregated travel information from the online social network associated with one or more second users of the online social network who have traveled to the first geographic location. The social-networking system may generate travel recommendations based on the identified second geographic locations, and then send, to the client system of the first user, one or more of the travel recommendations for display to the first user.

Claims

1. A method comprising, by one or more computing devices of an online social network:

receiving, from a client system of a first user of the online social network, an indication that the first user is traveling to a first geographic location;

identifying one or more second geographic locations within a threshold distance from the first geographic location, the one or more second geographic locations being determined based on a travel-recommendation model associated with the first user, the travel-recommendation model comprising;

aggregated user information from the online social network associated with the first user; and

aggregated travel information from the online social network associated with one or more second users of the online social network who have traveled to the first geographic location;

wherein the travel recommendation model comprises using the aggregated user information associated with the first user and the aggregated travel information associated with the one or more second users to generate one or more user-specific models, and when a new user is added to the online social network, the one or more user-specific models are updated to incorporate user information associated with the new user;

generating one or more travel recommendations based on the identified one or more second geographic locations; and

sending, to the client system of the first user, one or more of the travel recommendations for display to the first user.

2. The method of claim 1, wherein the indication that the first user is traveling to the first geographic location is determined based on one or more of:

accessing user-provided information from the online social network indicating that the user is traveling to the first geographic location;

or

analyzing a current geo-location information of the user.

3. The method of claim 2, wherein analyzing the current geo-location information of the first user further comprises:

generating a location history associated with the first user, the location history comprising;

one or more geographic locations associated with the user; and

one or more time stamps corresponding to each of the geographic locations;

determining a plurality of hotspots associated with the first user based on the location history; and

determining that a current geographic location of the first user is more than a threshold distance from one or more of the plurality of hotspots.

4. The method of claim 1, wherein the aggregated user information associated with the first user comprises one or more of:

user preferences of the first user;

personal information of the first user;

historical activities of the first user associated with the online social network;

geo-location information and travel information of the first user;

or

social-networking information of the first user.

5. The method of claim 4, wherein the aggregated travel information associated with the one or more second users comprises content inputted by the one or more second users, wherein the content is associated with the one or more second geographic locations.

6. The method of claim 5, further comprising:

analyzing the content inputted by the one or more second users to categorize the content as relating to sightseeing or traveling, the analysis being based on labeling information, tag information, sentiment analysis of the content.

7. The method of claim 5, wherein the content inputted by the one or more second users comprises posts, upload, reshares and comments.

8. The method of claim 1, wherein the travel-recommendation model further comprises an individual interpolation model generated based on a weighted combination of at least one individual user model and a global user model,

the individual user interpolation model being determined for each of the one or more second users based on all travel information associated with the one or more second users, and

the global user interpolation model being determined based on aggregated travel information for all users of the online social network who have traveled to the first geographic location.

9. The method of claim 1, wherein the travel-recommendation model further comprises a clustering model generated based on:

clustering all users of the online social network into a plurality of groups based on predetermined user characteristics,

determining a travel-recommendation group model for each of these groups, and

determining the group the first user should be identified with based on the predetermined user characteristics, and using the associated travel-recommendation group model as the travel-recommendation model for the first user.

10. The method of claim 1, wherein the travel-recommendation model further comprises a dynamic interpolation model generated based on:

for each user of all users of the online social network, generating an individual model based on all user information collected from each user,

determining one or more users of all the users of the online social network that are similar to the first user based on the user information, and

building a dynamic model for the first user based on a weighed combination of all of the one or more users determined to be similar to the first user.

11. The method of claim 1, wherein the one or more travel recommendations displayed to the first user are ranked based on a relationship between the first user and the one or more second users within a social graph of the online social network.

12. 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;

a plurality of second nodes corresponding to a plurality objects associated with the online social network, respectively.

13. The method of claim 1, wherein the one or more travel recommendations are presented to the first user within a user interface associated with the online social network.

14. The method of claim 1, wherein the one or more travel recommendations are presented to the first user in a user interface associated with a third-party system.

15. The method of claim 1, wherein sending the travel recommendations for display to the first user comprises sending a map labeling the one or more second geographic locations of the one or more travel recommendations.

16. The method of claim 1, wherein the one or more travel recommendations are presented on a user interface that also comprises one or more of posts, uploads, reshares, and comments associated with the one or more second users relating to the one or more second geographic locations.

17. The method of claim 1, wherein the travel-recommendation model is updated in real time based on a current geographic location of the first user.

18. The method of claim 1, further comprising sending one or more advertisements associated with the one or more second geographic locations associated with the travel recommendations.

19. The method of claim 1, wherein the new user added to the online social network corresponds to a second user of the one or more second users with user information comprising new travel information.

20. 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 the online social network, an indication that the first user is traveling to a first geographic location;

identify one or more second geographic locations within a threshold distance from the first geographic location, the one or more second geographic locations being determined based on a travel-recommendation model associated with the first user, the travel-recommendation model comprising;

aggregated user information associated with the first user from the online social network; and

aggregated travel information associated with one or more second users who have traveled to the first geographic location from the online social network, the one or more second users being associated with the online social network;

wherein the travel-recommendation model comprises using the aggregated user information associated with the first user and the aggregated travel information associated with the one or more second users to generate one or more user-specific models, and when a new user is added to the online social network, the one or more user-specific models are updated to incorporate user information associated with the new user;

generate one or more travel recommendations based on the identified one or more geographic locations; and

send, to the client system of the first user, one or more of the travel recommendations for display to the first user.

21. 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 the online social network, an indication that the first user is traveling to a first geographic location;

identify one or more second geographic locations within a threshold distance from the first geographic location, the one or more second geographic locations being determined based on a travel-recommendation model associated with the first user, the travel-recommendation model comprising;

aggregated user information associated with the first user from the online social network; and

aggregated travel information associated with one or more second users who have traveled to the first geographic location from the online social network, the one or more second users being associated with the online social network;

wherein the travel-recommendation model comprises using the aggregated user information associated with the first user and the aggregated travel information associated with the one or more second users to generate one or more user-specific models, and when a new user is added to the online social network, the one or more user-specific models are updated to incorporate user information associated with the new user;

generate one or more travel recommendations based on the identified one or more geographic locations; and

send, to the client system of the first user, one or more of the travel recommendations for display to the first user.