Ranking recommended search queries on online social networks

• US 9,460,215 B2
• Filed: 04/22/2014
• Issued: 10/04/2016
• Est. Priority Date: 12/19/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Garg, Avichal, Hua, Ming, Vernal, Michael, Qin, Yang, Fechete, Dan Ionut
• Primary Examiner(s): LE, UYEN T
• Application Number:
  US14/259,001
• Publication Number:
  US 20150178284A1
• Time in Patent Office: 896 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/3323 using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection
• CPC Class Codes: G06F 16/3328 using graphical result space presentation or visualisation
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/35 Clustering; Classification
• 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: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

In one embodiment, a method includes accessing a social graph that includes a number of nodes and edges connecting the nodes. Each of the edges between two of the nodes representing a single degree of separation between them. The nodes include a first node corresponding to a first user associated with an online social network and a plurality of second nodes that each correspond to a concept or a second user associated with the online social network. The method also includes generating a card cluster including a number of cards. Each card includes a suggested query referencing a query-domain associated with the online social network and zero or more query-filters. Each query-filter references one or more nodes of the plurality of nodes or one or more edges of the plurality of edges.

Claims

1. A method comprising, by a computing device:

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 a first user associated with an online social network; and

a plurality of second nodes that each correspond to a concept or a second user associated with the online social network;

generating a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain associated with the online social network and one or more query-filters, wherein each query-filter references one or more nodes of the plurality of nodes or one or more edges of the plurality of edges;

calculating a predicted click-thru rate (CTR) for each card in the card cluster based on one or more user-engagement factors;

ranking each of the cards in the card cluster based on the predicted CTR; and

sending the card cluster to the first user for display on a page currently accessed by the first user, the cards of the card cluster being ordered based on the rankings associated with the cards.

2. The method of claim 1, wherein one or more of the user-engagement factors comprise one or more of demographic information, current information, or social-graph information of the first user.

3. The method of claim 1, wherein calculating the predicted CTR comprises determining a click-thru behavior of one or more second users with respect to each card, each second user having at least a subset of demographic information in common with demographic information of the first user.

4. The method of claim 1, wherein calculating the predicted CTR comprises determining whether the first user is a tourist with respect to the current location based on a comparison of the current location with demographic information of the first user.

5. The method of claim 1, wherein calculating the predicted CTR comprises calculating a card-affinity of the first user with respect to each card based on the current time of day.

6. The method of claim 1, wherein calculating the predicted CTR comprises calculating a card-affinity of the first user with respect to each card based on an affinity to the query-domain or query-filter of each card.

7. The method of claim 1, wherein calculating the predicted CTR comprises calculating a card-affinity based on an affinity of one or more second users to the query-domain or query-filter of each card, the second users having at least a subset of demographic information in common with demographic information of the first user.

8. The method of claim 1, wherein the calculating the predicted CTR comprises determining social-graph affinity of the first user with respect to one or more second nodes referenced by the query-filters of the suggested query of the card.

9. The method of claim 1, wherein ranking each of the cards in the card cluster is further based on an associated user-interest value associated with each card.

10. The method of claim 1, wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a highest predicted CTR of the cards referencing each query-domain.

11. The method of claim 1, wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a calculated average predicted CTR value of the cards referencing each query-domain.

12. The method of claim 1, wherein ranking each of the cards in the card cluster comprises ranking each query-domain based on a calculated weighted average predicted CTR value of the cards referencing each query-domain.

13. The method of claim 1, wherein ranking each of the cards in the card cluster comprises calculating a card-affinity of each card relative to an inferred intent of the first user.

14. The method of claim 13, wherein the inferred intent of the first user comprises determining the first user is in a discovery mode for recommendations content of interest to the first user.

15. The method of claim 13, wherein the inferred intent of the first user comprises determining the first user is a tourist with respect to the current location based on a comparison of the current location with demographic information of the first user.

16. The method of claim 1, the card cluster is vertically displayed on the page and each displayed card referencing a different query-domain.

17. The method of claim 1, further comprising displaying a subsequent card to the first user in response to detecting an input from the first user corresponding to a swipe of a previously displayed card, the subsequent card having a same query-domain and one or more different query-filters as the previously displayed card.

18. The method of claim 1, wherein the page is a user interface of a native application.

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

access 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 a first user associated with an online social network; and

a plurality of second nodes that each correspond to a concept or a second user associated with the online social network;

generate a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain associated with the online social network and one or more query-filters, wherein each query-filter references one or more nodes of the plurality of nodes or one or more edges of the plurality of edges;

calculate a predicted click-thru rate (CTR) for each card in the card cluster based on one or more user-engagement factors;

rank each of the cards in the card cluster based on the predicted CTR; and

send the card cluster to the first user for display on a page currently accessed by the first user, the cards of the card cluster being ordered based on the rankings associated with the cards.

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;

access 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 a first user associated with an online social network; and

a plurality of second nodes that each correspond to a concept or a second user associated with the online social network;

generate a card cluster comprising a plurality of cards, each card comprising a suggested query referencing a query-domain associated with the online social network and one or more query-filters, wherein each query-filter references one or more nodes of the plurality of nodes or one or more edges of the plurality of edges;

calculate a predicted click-thru rate (CTR) for each card in the card cluster based on one or more user-engagement factors;

rank each of the cards in the card cluster based on the predicted CTR; and

send the card cluster to the first user for display on a page currently accessed by the first user, the cards of the card cluster being ordered based on the rankings associated with the cards.