Context-based queryless presentation of recommendations

• US 9,449,106 B2
• Filed: 03/07/2014
• Issued: 09/20/2016
• Est. Priority Date: 03/08/2013
• Status: Active Grant

• Current Assignee: OpenTable, Inc. (Booking Holdings, Inc., fka Priceline Group Inc.)
• Original Assignee: OpenTable, Inc. (Booking Holdings, Inc., fka Priceline Group Inc.)
• Inventors: Westervelt, Brett Matthew, Reese, Corey Layne, Wang, Yige, Schiff, Jeremy Ryan, Schlansker, Steven Charles
• Primary Examiner(s): Syed, Farhan
• Application Number:
  US14/201,713
• Publication Number:
  US 20140258270A1
• Time in Patent Office: 928 Days
• US Class Current: 1/1
• 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 16/9538 Presentation of query results

Abstract

Techniques for context-based queryless presentation of recommendations are described. Without receiving an explicit query, an inferred query is determined based on a first set of context signals associated with a recommendation triggering event. Items matching the inferred query are selected based on a second set of one or more context signals associated with the recommendation triggering event. One or more results items identifying the one or more matching items are caused to display. A result items may be displayed in association with an explanation that identifies context values used to select an item for recommendation or one or more attributes of the item that are relevant to a user or the inferred query.

Claims

1. A computer-implemented method comprising:

receiving at a computer system an indication that instructions for an application have begun executing on a computer device;

determining, by the computer system, an occurrence of a recommendation triggering event has occurred when the instructions for the application were executed on the computer device;

causing, by executing the instructions for the application, the computer device to provide a group of context signals gathered from the computer device;

receiving, from the computer device, the group of context signals at the computer device;

combining the group of context signals from the computer device with user information stored separately from the computer device to create a first set of one or more context signals wherein the first set of one or more context signals include a time of when the recommendation triggering event occurred and an identity of a user logged onto the computer device when the recommendation triggering event occurred;

without receiving an explicit query from the computer device, determining an inferred query based at least in part on the first set of one or more context signals associated with the recommendation triggering event;

selecting one or more items matching the inferred query based on at least in part on a second set of one or more context signals associated with the recommendation triggering event; and

causing display of one or more results items identifying the one or more matching items at the computer device;

wherein the computer-implemented method is performed using one or more computing devices.

2. The computer-implemented method of claim 1 wherein the first set of one or more context signals includes an indication of one or more of a location of a client device that caused the occurrence of the recommendation triggering event or a time of day at which the recommendation triggering event occurred.

3. The computer-implemented method of claim 1 wherein the second set of one or more context signals includes an indication of items previously selected or liked by a client device that caused the occurrence of the recommendation triggering event.

4. The computer-implemented method of claim 1 wherein the second set of one or more context signals includes an indication of items previously selected by other client devices when presented with results based on certain context signals that belong to the second set of context signals.

5. The computer-implemented method of claim 1 comprising:

determining a mood of a user associated with a client device that caused the occurrence of the recommendation triggering event; and

identifying one or more items matching the inferred query based on the determined mood of the user.

6. The computer-implemented method of claim 1 comprising:

determining an intention of a user associated with a client device that caused the occurrence of the recommendation triggering event based on financial transaction data; and

identifying one or more items matching the inferred query based on the determined intention of the user.

7. The computer-implemented method of claim 6 comprising:

causing display of a prompt identifying the determined intention and requesting verification of the determined intention; and

identifying one or more items matching the inferred query based on a response to the prompt.

8. The computer-implemented method of claim 1 wherein the second set of one or more context signals includes a signal indicating the strength of a relationship between a first user associated with a client device that caused the occurrence of the recommendation triggering event and a second user;

the method comprising;

determining that the second user liked a particular item of a set of items from which the one or more matching items are selected; and

selecting the one or more items matching the inferred query based on the determination that the second user liked the particular item and the signal indicating the strength of a relationship between the first user and the second user.

9. The computer-implemented method of claim 1 comprising:

causing presenting of the results of the inferred query at a particular client device;

receiving feedback associated with a particular result; and

using the received feedback in selecting further recommendations for the particular client device or other client devices.

10. The computer-implemented method of claim 1 comprising:

selecting an explanation type from a plurality of explanation types based on a third set of context values associated with the recommendation triggering event; and

based on the selection of the explanation type, causing display of an explanation of the selected explanation type in association with a result item identifying a particular item matching the inferred query, wherein the explanation identifies one or more particular context signals of the second set of context signals that were a basis for a selection of the particular item as an item matching the inferred query.

11. The computer-implemented method of claim 1 comprising:

selecting, based on a third set of context values associated with the recommendation triggering event, a media item from a plurality of media items associated with a particular item of the one or more items matching the inferred query; and

causing display of the selected media item in association with a result item identifying the particular item.

12. The computer-implemented method of claim 11 comprising:

selecting the media item from the plurality of media items associated with the particular item based on information determined about a user associated with a client device that caused the occurrence of the recommendation triggering event, selection history information indicating result items selected by other client devices after receiving recommendations, and information determined about users of the other client devices.

13. The computer-implemented method of claim 1 comprising:

causing reservation of a particular result item of the one or more result items; and

causing display of a prompt identifying the particular item and requesting confirmation of the reservation.

14. A computer system comprising:

one or more processors;

one or more computer-readable storage media coupled to the one or more processors and storing one or more sequences of instructions which when interpreted cause;

receiving at a computer system an indication that instructions for an application have begun executing on a computer device;

determining, by the computer system, that an occurrence of a recommendation triggering event has occurred when the instructions for the application were executed on the computer device;

causing, by executing the instructions for the application, the computer device to provide a group of context signals gathered from the computer device;

receiving, from the computer device, the group of context signals at the computer device;

combining the group of context signals from the computer device with user information stored separately from the computer device to create a first set of one or more context signals wherein the first set of one or more context signals include a time of when the recommendation triggering event occurred and an identity of a user logged onto the computer device when the recommendation triggering event occurred;

without receiving an explicit query from the computer device, determining an inferred query based at least in part on the first set of one or more context signals associated with the recommendation triggering event;

selecting one or more items matching the inferred query based on at least in part on a second set of one or more context signals associated with the recommendation triggering event; and

causing display of one or more results items identifying the one or more matching items at the computer device.

15. The computer system of claim 14 wherein the first set of one or more context signals includes an indication of one or more of a location of a client device that caused the occurrence of the recommendation triggering event or a time of day at which the recommendation triggering event occurred.

16. The computer system of claim 14 wherein the second set of one or more context signals includes an indication of items previously selected by other client devices when presented with results based on certain context signals that belong to the second set of context signals.

17. The computer system of claim 14 wherein the second set of one or more context signals includes an indication of items previously selected by one or more client devices when presented with results for a second inferred query associated with certain context signals that belong to the second set of context signals.

18. The computer system of claim 14 wherein the sequences of instructions further cause:

determining a mood of a user associated with a client device that caused the occurrence of the recommendation triggering event; and

identifying one or more items matching the inferred query based on the determined mood of the user.

19. The computer system of claim 14 wherein the sequences of instructions further cause:

determining an intention of a user associated with a client device that caused the occurrence of the recommendation triggering event based on financial transaction data; and

identifying one or more items matching the inferred query based on the determined intention of the user.

20. The computer system of claim 14 comprising:

causing display of a prompt identifying the determined intention and requesting verification of the determined intention; and

identifying one or more items matching the inferred query based on a response to the prompt.

21. The computer system of claim 14 wherein the second set of one or more context signals includes a signal indicating the strength of a relationship between a first user associated with a client device that caused the occurrence of the recommendation triggering event and a second user;

wherein the sequences of instructions further cause;

determining that the second user liked a particular item of a set of items from which the one or more matching items are selected; and

selecting the one or more items matching the inferred query based on the determination that the second user liked the particular item and the signal indicating the strength of a relationship between the first user and the second user.

22. The computer system of claim 14 wherein the sequences of instructions further cause:

causing presenting of the results of the inferred query at a particular client device;

receiving feedback associated with a particular result; and

using the received feedback in selecting further recommendations for the particular client device or other client devices.

23. The computer system of claim 14 wherein the sequences of instructions further cause:

selecting an explanation type from a plurality of explanation types based on a third set of context values associated with the recommendation triggering event; and

based on the selection of the explanation type, causing display of an explanation of the selected explanation type in association with a result item identifying a particular item matching the inferred query, wherein the explanation identifies one or more particular context signals of the second set of context signals that were a basis for a selection of the particular item as an item matching the inferred query.

24. The computer system of claim 14 wherein the sequences of instructions further cause:

selecting, based on a third set of context values associated with the recommendation triggering event, a media item from a plurality of media items associated with a particular item of the one or more items matching the inferred query; and

causing display of the selected media item in association with a result item identifying the particular item.

25. The computer system of claim 24 wherein the sequences of instructions further cause:

selecting the media item from the plurality of media items associated with the particular item based on information determined about a user associated with a client device that caused the occurrence of the recommendation triggering event, selection history information indicating result items selected by other client devices after receiving recommendations, and information determined about users of the other client devices.

26. The computer system of claim 14 wherein the sequences of instructions further cause:

causing reservation of a particular result item of the one or more result items; and

causing display of a prompt indicating that the reservation of the particular result item will expire by a certain time if confirmation of the reservation is not received by the certain time.