Personalized group recommendations

• US 10,068,257 B1
• Filed: 08/23/2011
• Issued: 09/04/2018
• Est. Priority Date: 08/23/2011
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Mosthaf, Volker Helmut
• Primary Examiner(s): Hamilton, Matthew L
• Application Number:
  US13/216,135
• Time in Patent Office: 2,569 Days
• Field of Search: 705 14
• CPC Class Codes: G06Q 30/0203 Market surveys; Market polls
• CPC Class Codes: G06Q 30/0207 Discounts or incentives, e.g. coupons or rebates
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A method and system for establishing a group of users and providing item recommendations tailored for the group are described. Users can join a recommendation huddle for the purpose of viewing collective item recommendations tailored for the users participating in the recommendation huddle. The item recommendations can be based on the recommendation profiles of participating users, the nature of the item recommendations to be provided (e.g., movies, restaurants, activities, songs, or the like), and other context information. Recommendations, including information about the recommended items, are provided to users participating in the recommendation huddle. In some embodiments, participating users can vote or otherwise provide feedback on the provided recommendations. One or more final selections can be made based on the recommendations and feedback.

Claims

1. A system for providing group recommendations, the system comprising:

a recommendations module implemented in a first user device comprising memory programmed with instructions and a processor configured to execute the instructions to cause the recommendations module to;

automatically detect that second user devices are in proximity to the first user device based on wireless information received from the second user devices, the second user devices operated by a plurality of users;

in response to said detection, communicate to the second user devices information about a recommendation huddle over a wireless network, without using a server as an intermediary, wherein the information about the recommendation huddle includes an electronic request for users of the second user devices to join the recommendation huddle;

receive electronic acceptances from selected ones of the users over the wireless network, the electronic acceptances indicating that the selected users agree to join the recommendation huddle;

receive an indication from a first user declining to join the recommendation huddle;

output for display on the first user device an indication of those of the selected users that have accepted the electronic request to join the recommendation huddle;

transmit, to a server implementing a recommendation service over the wireless network, a request to programmatically generate, based at least in part on collective preferences of the selected users, a collection of recommended items for the recommendation huddle, the request comprising identification information of the selected users;

notify the recommendation service of the first user declining to join the recommendation huddle to cause the recommendation service to not access the first user'"'"'s recommendation profile when generating recommendations;

receive from the server implementing the recommendation service a collection of recommended items for the recommendation huddle;

receive voting feedback from the second user devices, the voting feedback comprising votes that indicate user preferences for one or more of the recommended items;

calculate a user influence of at least some of the users on the voting feedback based on correspondence between the votes of at least some of the users and the voting feedback;

adjust the collection of recommended items based on the voting feedback and on the calculated user influence;

automatically select one of the recommended items; and

automatically cause the selected recommended item to be streamed to a multimedia device; and

a user interface of the display of the first user device further configured to provide information related to the collection of recommended items and a visual indication based on the voting feedback to one or more of the selected users participating in the recommendation huddle.

2. The system of claim 1, wherein the recommendations module is further configured to transmit to the recommendation service information about the received voting feedback.

3. The system of claim 2, wherein

the recommendations module is further configured to receive from the recommendation service a second collection of recommended items for the recommendation huddle, wherein the second collection of recommended items is generated based at least in part on the transmitted information about the received voting feedback;

and wherein

the user interface is further configured to provide to one or more users participating in the recommendation huddle information about the received second collection of recommended items for the recommendation huddle as said adjustment of the collection of recommended items.

15. The system of claim 1, wherein the recommendations module is further configured to calculate the user influence based at least partly on a frequency with which each of the users'"'"' voting feedback matched a winning vote of the recommendation huddle.

16. The system of claim 15, wherein the recommendations module is further configured to adjust the collection of recommended items based on the voting feedback and on the calculated user influence by at least targeting a second recommended item to one of the users whose voting feedback matched the winning vote of the recommendation huddle.

17. The system of claim 1, wherein the electronic acceptances comprise a digitally signed recommendation huddle invitation from a selected one of the second user devices, the digitally signed recommendation huddle invitation received directly by the first user device in response to the recommendation service being unavailable for communication with the selected one of the second user devices.

18. The system of claim 17, wherein the recommendation module is further configured to subsequently transmit the digitally signed recommendation huddle to the recommendation service to obtain verification of a digital signature associated with the digitally signed recommendation huddle invitation, so as to permit the selected second user device to participate in the recommendation huddle.

19. The system of claim 1, wherein the automatic detection of the second user devices comprises locating and identifying the second user devices that are in wireless range of the first user device.

20. The system of claim 1, wherein the user interface is further configured to:

present a user interface element configured to control the multimedia device for streaming the recommended item; and

wherein the recommendation module is further configured to;

send, by the first user device through the user interface, a request to stream the recommended item to the multimedia device through the server.

4. A system comprising:

a first client device comprising one or more processors, said first client device programmed via executable code to;

automatically detect, without using a server as an intermediary, that second client devices are in proximity to the first client device based on wireless information received from the second client devices;

receive an indication that users of the detected second client devices would like to participate in a recommendation huddle;

present to a user associated with the first client device information about the recommendation huddle on a display of the first client device, wherein the information about the recommendation huddle comprises a selectable option to participate in the recommendation huddle, the selectable option displayed in a user interface on the display of the first client device;

receive from the user associated with the first client device an indication that the user would like to participate in the recommendation huddle;

transmit, to a computing device implementing a recommendation service, a request to obtain recommendations for the recommendation huddle;

receive from the recommendation service a collection of items recommended for the recommendation huddle, wherein the collection of items is generated based at least in part on item preference data associated with the recommendation huddle;

provide to the second client devices participating in the recommendation huddle information about the received collection of recommended items;

receive voting feedback from the user of the first client device and users of the second client devices, the voting feedback comprising votes that indicate a preference of the users for one or more of the recommended items;

calculate a user influence of at least some of the users on the voting feedback based on correspondence between the votes of at least some of the users and the voting feedback;

transmit the voting feedback and data representing the calculated user influence to the recommendation service;

receive from the recommendation service an adjusted collection of recommended items responsive to the voting feedback and on the calculated user influence;

receive a selection of an item of the adjusted collection of recommended items;

output data representing the adjusted collection of recommended items for presentation on a display of the first client device; and

automatically cause the selected recommended item to be streamed to a multimedia device.

5. The system of claim 4, wherein the item preference data associated with the recommendation huddle comprises item preference data of one or more users of the recommendation huddle.

6. The system of claim 4, wherein the item preference data associated with the recommendation huddle comprises past item selection activity of the recommendation huddle as a group.

7. The system of claim 4, said first client device further programmed to transmit to the recommendation service information about the received voting feedback.

8. The system of claim 4, said first client device further programmed to provide to one or more users participating in the recommendation huddle information about the adjusted collection of recommended items for the recommendation huddle.

9. A method of providing group recommendations, the method comprising:

automatically detecting, by a first device, that second devices are in proximity to the first device based on wireless information received from the second devices;

receiving, by the first device, information about a plurality of users of the second devices that would like to participate in a recommendation huddle;

receiving, by the first device, an indication of a first user associated with the first device that the first user would like to join the recommendation huddle;

transmitting, by the first device, a request to obtain recommendations for the recommendation huddle to a computing device implementing a recommendation service;

receiving, by the first device, a collection of items recommended for the recommendation huddle from the recommendation service, wherein the collection of items is generated based at least in part on item preference data associated with the recommendation huddle;

providing, by the first device, to the second devices participating in the recommendation huddle information about the received collection of recommended items;

receiving, by the first device, voting feedback transmitted from the second devices participating in the recommendation huddle, the voting feedback comprising votes that indicate user preferences for one or more of the recommended items;

calculating, by the first device, a user influence of at least some of the plurality of users on the voting feedback based on correspondence between the votes of at least some of the plurality of users and the voting feedback;

transmitting, by the first device, the voting feedback and data representing the calculated user influence to the recommendation service;

receiving, by the first device, an adjusted collection of recommended items responsive to the voting feedback and the calculated user influence from the recommendation service;

receiving, by the first device, a selection of an item of the adjusted collection of recommended items; and

automatically causing, by the first device, the selected recommended item to be streamed to a multimedia device,

wherein the method is performed by one or more hardware processors.

10. The method of claim 9, wherein the item preference data associated with the recommendation huddle comprises item preference data of one or more users of the recommendation huddle.

11. The method of claim 9, further comprising providing, by the first device, to one or more users participating in the recommendation huddle information about the adjusted collection of recommended items for the recommendation huddle.

12. The method of claim 9, further comprising:

identifying, by the first device, a selected item from the collection of recommended items; and

receiving, by the first device, from a user participating in the recommendation huddle feedback on said selected item.

13. The method of claim 12, wherein said feedback on said selected item comprises a rating of the selected item.

14. A non-transitory physical computer storage having stored thereon executable instructions that, when implemented by a first device comprising a hardware processor, cause the first device to implement a method of providing group recommendations, said method comprising:

receiving an indication that one or more users would like to participate in a recommendation group;

automatically detecting, without using a server as an intermediary, information about the one or more users that would like to participate in the recommendation group, said automatically detecting comprising detecting that one or more second devices are in proximity to the first device, the one or more second devices operated by the one or more users;

in response to said detecting, transmitting to a server implementing a recommendation service over a network a request to programmatically generate, based at least in part on collective preferences of the one or more users participating in the recommendation group, a set of recommended items for the recommendation group;

receiving from the recommendation service a set of recommended items for the recommendation group;

providing to the one or more second devices of the one or more users participating in the recommendation group information related to the received set of recommended items for display on the one or more second devices;

receiving voting feedback from the one or more second devices, the voting feedback comprising one or more votes that indicate a preference of the one or more users for one or more of the recommended items;

calculating a user influence of at least some of the one or more users on the voting feedback based on correspondence between the votes of at least some of the one or more users and the voting feedback;

providing the voting feedback and data regarding the calculated user influence over the network to the recommendation service;

receiving over the network from the recommendation service an adjusted collection of recommended items responsive to the voting feedback and the calculated user influence;

displaying data representing the adjusted collection of recommended items on a display of the first device; and

receiving automatically-initiated digital streaming of a selected one of the recommended items.

21. The non-transitory physical computer storage of claim 14, wherein the method further comprises identifying, using a facial recognition technique, a user of a third user device, and in response to said identifying, adding the third user device to the recommendation group.

22. The non-transitory physical computer storage of claim 14, wherein the method further comprises tailoring a user interface comprising information regarding the recommended items to the users based on a location of one or more of the users;

and outputting the user interface for presentation to one or more of the users.