Method for recommendation of audio

• US 8,799,169 B2
• Filed: 02/11/2009
• Issued: 08/05/2014
• Est. Priority Date: 03/10/2008
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Kemp, Thomas
• Primary Examiner(s): Nigh, James D
• Application Number:
  US12/369,352
• Publication Number:
  US 20090228333A1
• Time in Patent Office: 2,001 Days
• Field of Search: 705/26.7, 705/58
• US Class Current: 705/58
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06Q 2220/165 Having origin or program ID
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/41407 embedded in a portable device, e.g. video client on a mobile phone, PDA, laptop constructional details of equipment or arrangements specially adapted for portable computer application G06F1/1626; arrangements specially adapted for mobile receivers in broadcast systems H04H20/57
• CPC Class Codes: H04N 21/439 Processing of audio elementary streams
• CPC Class Codes: H04N 21/44204 Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched monitoring of user activities for profile generation for accessing a video database G06F16/739; protecting generic digital content where the protection is independent of the precise nature of the content G06F21/10; arrangements for monitoring the use made of the broadcast services in broadcast systems H04H60/31
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/4661 Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home user profiles in network data switching protocols H04L67/306
• CPC Class Codes: H04N 21/472 End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content end-user interfaces for retrieving video data from a database G06F16/739; network services for supporting unicast streaming H04L65/612
• CPC Class Codes: H04N 21/4788 communicating with other users, e.g. chatting arrangements for providing for computer conferences, e.g. chat rooms, to substation in data switching networks H04L12/1813; distributed application using peer-to-peer [P2P] networks H04L67/104
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38
• CPC Class Codes: H04N 21/8113 comprising music, e.g. song in MP3 format
• CPC Class Codes: H04N 7/17318 Direct or substantially direct transmission and handling of requests

Abstract

A method for recommendation of a content item, comprising: providing first identifiers for first content items stored on a first device; providing second identifiers for second content items stored on a second device; determining measures for at least a part of said first content items, wherein each measure is associated with a respective content item, and said measure depends on said first and second identifiers; determining or updating, on a third device, an item-to-item matrix based on said measures, wherein said first, second, and third devices are physically separated devices; determining a recommendation for a user based on said item-to-item matrix.

Claims

1. A method of operating a system for recommendation of a content item, the system including at least a portable first device, a portable second device, and a third device, comprising:

determining, by the first device, first identifiers descriptive for first content items stored on the first device, the first device assigned to a first user, each first identifier being fingerprint data extracted from audio information contained in one of the first content items;

determining, by the second device, second identifiers descriptive for second content items stored on the second device, the second device assigned to a second user, each second identifier being fingerprint data extracted from audio information contained in one of the second content items;

sending the second identifiers from the second device to said first device;

determining, by said first device, measures for at least a part of the first content items, wherein each measure is associated with a respective content item, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices;

sending the measures from the first device to said third device;

determining or updating, on said third device, an item-to-item matrix based on said measures, wherein said first, second, and third devices are physically separate devices, wherein to each content item the item-to-item matrix assigns a plurality of second measures, and wherein each second measure is assigned to one of other content items and is a value that is high for content items stored in both the first device and the second device, medium for content items stored in a single one of the first and the second devices, and low for content items stored in neither the first nor the second device; and

determining, by a processor of the third device, a recommendation for the first user, the second user, or another user based on said plurality of second measures assigned to each content item identified by data sent to the third device.

2. The method of claim 1, wherein said determining, by said first device, said measures includes a comparison of user-dependent information stored in the first device and the second device wherein a value of a respective measure is determined to be higher the better the user-dependent information stored in the first and the second devices match.

3. The method of claim 2, wherein said determining, by said first device, said measures includes the comparison of user-dependent information stored in the first device and the second device, wherein said user-dependent information is a user profile, a user gender, a user age, or a user group.

4. The method of claim 1, wherein said determining) by said first device, said measures includes at least a part of said measures that depends on a comparison of a degree of liking of a respective content item.

5. The method of claim 4 further comprising:

determining said degree of liking based on at least one of a playlist, a favorite list, a purchase date, a purchase price, each being associated with a respective content item, and a number of times a respective content item has been played.

6. The method of claim 1, wherein said determining, by said first device, said measures includes at least a part of said measures that depends on a playlist or a favorite list of a user of the second device.

7. The method of claim 1, 2, 3, 4, 5, or 6, further comprising:

sending the first identifiers from the first device to said second device;

determining, by said second device, measures for at least a part of the second content items, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices; and

sending the measures from the second device to said third device.

8. A portable device assigned to a user, comprising:

a storage configured to store first content items;

a receiver unit configured to receive second identifiers descriptive for second content items stored on a further device, the further device assigned to a further user, each second identifier being fingerprint data extracted from audio information contained in one of the second content items;

a data processor configured to determine first identifiers descriptive for said first content items, each first identifier being fingerprint data extracted from audio information contained in one of the first content items, and configured to determine measures for at least a part of said first content items, wherein each measure is associated with a respective content item, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices; and

a transmitter unit configured to send said measures assigned to corresponding first content items to a server, and configured to send a request for a recommendation to said server,

wherein said receiver unit is further configured to receive said recommendation.

9. The portable device of claim 8, wherein said data processor is configured to determine at least a part of said measures on the basis of a comparison of user-dependent information stored in said portable device and said further device, wherein a value of a respective measure is determined to be higher the better the user-dependent information stored in the portable device and the further device match.

10. The portable device of claim 9, wherein said receiver unit is configured to receive said user-dependent information from said further device, and said user-dependent information includes information of a user of said further device.

11. The portable device of claim 9, wherein said receiver unit is configured to receive said user-dependent information that includes a user profile, a user gender, a user age, or a user group.

12. The portable device of claim 8, wherein said data processor is configured to determine at least a part of said measures on the basis of a comparison of a degree of liking of a respective content item.

13. The portable device of claim 12, wherein said data processor is configured to determine at least a part of said measures on the basis of said comparison, wherein said degree of liking is determined based on at least one of a playlist, a favorite list, a purchase date, a purchase price, each associated with a respective content item, and a number of times a respective content item has been played.

14. The portable device of claim 13, wherein said receiver unit is configured to receive said degree of liking from said further device.

15. A server device, comprising:

a receiver unit configured to receive measures for content items, wherein each measure is associated with a respective content item and depends on first and second identifiers, said first and second identifiers being locally determined at a first device assigned to a first user and at a second device assigned to a second user, respectively, and the first and second identifiers being descriptive for first and second content items, respectively, each first identifier being fingerprint data extracted from audio information contained in one of the first content items, each second identifier being fingerprint data extracted from audio information contained in one of the second content items, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices; and

a data processor configured to determine or update an item-to-item matrix based on said measures, wherein to each content item the item-to-item matrix assigns a plurality of second measures, wherein each second measure is assigned to one of other content items and is a value that is high for content items stored in both the first device and the second device, medium for content items stored in a single one of the first and the second devices, and low for content items stored in neither the first nor the second device, and

wherein said receiver unit is further configured to receive a request for a recommendation and said data processor is further configured to determine said recommendation based on said plurality of second measures assigned to each content item identified by data sent to the server device.

16. A method for determining an item-to-item matrix with at least a first device, a second device, and a third device, comprising:

determining, by the first device, first identifiers descriptive for first content items stored on the first device, the first device assigned to a first user, each first identifier being fingerprint data extracted from audio information contained in one of the first content items;

determining, by the second device, second identifiers descriptive for second content items stored on the second device, the second device assigned to a second user, each second identifier being fingerprint data extracted from audio information contained in one of the second content items;

sending the second identifiers from the second device to said first device;

determining, by said first device, measures for at least a part of the first content items, wherein each measure is associated with a respective content item, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices;

sending the measures from the first device to said third device; and

determining or updating, by a processor of the third device, said item-to-item matrix based on said measures, wherein said first, second, and third devices are physically separate devices, wherein to each content item the item-to-item matrix assigns a plurality of second measures, and wherein each second measure is assigned to one of other content items and is a value that is high for content items stored in both the first device and the second device, medium for content items stored in a single one of the first and the second devices, and low for content items stored in neither the first nor the second device.

17. The method of claim 16, wherein said determining, by said first device, said measures includes a comparison of user-dependent information stored in the first device and the second device, wherein a value of a respective measure is determined to be higher the better the user-dependent information stored in the first and the second devices match.

18. A non-transitory computer-readable medium including computer program instructions that respectively cause a first device and a second device to execute a method for recommendation of a content item comprising:

determining first identifiers descriptive for first content items stored on the first device, the first device assigned to a first user, each first identifier being fingerprint data extracted from audio information contained in one of the first content items;

determining second identifiers descriptive for second content items stored on the second device, the second device assigned to a second user, each second identifier being fingerprint data extracted from audio information contained in one of the second content items;

sending the second identifiers from the second device to said first device;

determining, by said first device, measures for at least a part of said first content items, wherein each measure is associated with a respective content item, wherein the measure is a value that is higher for the respective content item stored in both the first device and the second device than for the respective content item stored in a single one of the first and the second devices;

sending the measures to a third device to determine or update, on said third device, an item-to-item matrix based on said measures, wherein said first, second, and third devices are physically separate devices, wherein to each content item the item-to-item matrix assigns a plurality of second measures, and wherein each second measure is assigned to one of other content items and is a value that is high for content items stored in both the first device and the second device, medium for content items stored in a single one of the first and the second devices, and low for content items stored in neither the first nor the second device; and

receiving a recommendation for the first user.

19. The non-transitory computer-readable medium including computer program instructions of claim 18, wherein said determining, by said first device, said measures includes a comparison of user-dependent information stored in the first device and the second device, wherein a value of a respective measure is determined to be higher the better the user-dependent information stored in the first and the second devices match.