CONTENT IDENTIFICATION WITH PRIVACY AND SECURITY

• US 20200137438A1
• Filed: 10/29/2019
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Application

• Current Assignee: Turner Broadcasting System Incorporated (Warner Bros. Discovery, Inc.)
• Original Assignee: Canopy Crest Corp. (Warner Bros. Discovery, Inc.)
• Inventors: Whitman, Brian A., Greene, Erica R., Recht, Benjamin
• Application Number:
  US16/667,331
• Publication Number:
  US 20200137438A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 17/16 Matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization matrix transposition G06F7/78
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/258 Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data arrangements for services using the result on the distributing side of broadcast systems H04H60/66; profiles in network data switching protocols H04L67/30
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4755 for defining user preferences, e.g. favourite actors or genre retrieval personalisation and generation of user profiles for the retrieval of video data G06F16/739; user profiles in network data switching protocols H04L67/306

Abstract

Disclosed examples can relate to obtaining identifications of content (e.g., content recommendations) while keeping at least some interaction data locally private. For a given user and device, content items for which the user may have an affinity can be predicted based on the interactions of the user with other content items. Respective interaction data for respective content items can stay local to the user device by transforming the respective content items into content codes (e.g., determined based on a codebook generated by clustering perceptual values). The affinity for content codes can be transmitted to the server for use in determining identifications of content items to provide to the device.

Claims

1. A method comprising:

for each respective content item of a set of content items;

determining an affinity value for the respective content item; and

determining a classification code for the respective content item;

creating an affinity vector from the determined affinity values and the classification codes;

transmitting the affinity vector to a server; and

receiving, from the server, one or more identifications of content items based on the transmitted affinity vector.

2. The method of claim 1, wherein determining the classification code includes:

determining a perceptual value for the content item,

wherein the classification code is based on the perceptual value.

3. The method of claim 2, wherein determining the classification code further includes:

determining the classification code based on the perceptual value using a codebook.

4. The method of claim 3, further comprising:

receiving the codebook from the server.

5. The method of claim 3, further comprising:

generating the codebook based on clustering performed on perceptual values.

6. The method of claim 1, wherein determining the affinity value is based on data regarding one or more interactions with the respective content item.

7. The method of claim 6, wherein the data regarding the one or more interactions is not transmitted to the server.

8. The method of claim 1, further comprising:

combining multiple affinity vectors, each associated with a different content type, to form a combined affinity vector,

wherein transmitting the affinity vector to the server includes transmitting the affinity vector as part of the combined affinity vector.

9. The method of claim 1, further comprising obscuring the affinity vector prior to transmitting the affinity vector to the server.

10. The method of claim 1, wherein the method is performed by a personalization engine operating on a user device.

11. A method comprising:

obtaining affinity vectors from user devices;

updating a server matrix using the affinity vectors;

determining identifications of content items for a respective user device of the user devices based on the server matrix; and

transmitting the identifications to the respective user device.

12. The method of claim 11, wherein the affinity vectors include associations between affinity values and classification codes.

13. The method of claim 12, further comprising:

generating a codebook based on clustering performed on perceptual values of content items; and

transmitting the codebook to the user devices for use in determining one or more classification codes.

14. The method of claim 11, further comprising decomposing the server matrix, wherein the identifications are based on results of decomposing the server matrix.

15. The method of claim 11, wherein the method is performed by a server.

16. A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:

for each respective content item of a set of content items;

determine an affinity value for the respective content item; and

determine a classification code for the respective content item;

create an affinity vector from the determined affinity values and the classification codes;

transmit the affinity vector to a server; and

receive, from the server, one or more identifications based on the transmitted affinity vector.

17. The non-transitory computer-readable medium of claim 16, wherein to determine the classification code includes:

determine a perceptual value for the content item,

wherein the classification code is based on the perceptual value.

18. The non-transitory computer-readable medium of claim 17, wherein to determine the classification code further includes:

determining the classification code based on the perceptual value using a codebook received from the server.

19. The non-transitory computer-readable medium of claim 16, wherein to determine the affinity value is based on data regarding one or more interactions with the respective content item.

20. The non-transitory computer-readable medium of claim 19, wherein the data regarding the one or more interactions is not transmitted to the server.