System and method for matching targeted advertisements for video content delivery

• US 9,473,828 B2
• Filed: 12/01/2010
• Issued: 10/18/2016
• Est. Priority Date: 01/28/2010
• Status: Active Grant

• Current Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Inventors: Wang, Qi, Wang, Shu, Huang, Yu, Yu, Hong Heather, Zhang, Dong-Qing
• Primary Examiner(s): Chae, Kyu
• Application Number:
  US12/958,102
• Publication Number:
  US 20110185381A1
• Time in Patent Office: 2,148 Days
• Field of Search: 725/32, 725 34- 36, 705 144- 1473
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04N 21/23424 involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
• 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 21/4756 for rating content, e.g. scoring a recommended movie
• 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 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments

Abstract

In accordance with an embodiment, a method of matching video content to advertising content includes electronically receiving a video content metadata from a content provider, and matching the video content metadata to advertising content metadata of a global list of advertisements. The video content metadata corresponds to video content being sent to a user device and includes at least one keyword. Furthermore, the advertising content metadata corresponds to advertising content and includes at least one keyword. Matching the video content metadata to advertising content metadata includes comparing the at least one keyword of the video content metadata to the at least one keyword of the advertising content metadata.

Claims

1. A method of matching video content to insertion content, the method comprising:

electronically receiving a video content metadata from a first server over a network by a second server, the video content metadata corresponding to video content being sent to a user device over the network by the first server, wherein the first server, second server and user device are separate from each other; and

using a processor of a second server, matching the video content metadata to a global list of insertion content metadata corresponding to content configured to be inserted within the video content at the user device, wherein

the video content metadata comprises at least one keyword,

the insertion content metadata comprises at least one keyword,

matching the video content metadata to insertion content metadata comprises comparing the at least one keyword of the video content metadata to the at least one keyword of the insertion content metadata, and

the global list of insertion content metadata is stored on the second server;

receiving, over the network by the processor of the second server, user preference data from the user device;

filtering, by the processor of the second server, results of the matching the video content metadata to insertion content metadata to form filtered results, wherein the filtering comprises

utilizing user preference data from a user preference matrix to perform the filtering results, the user preference matrix comprising preference values according to rows indexed by video categories and columns indexed by a plurality of insertion categories, wherein the user preference matrix comprises values based on the received user preference data, and

adjusting the user preference data according to user profile data in a user profile matrix, the user profile matrix comprising further preference data according to the plurality of insertion categories, wherein the user profile matrix comprises rows indexed by user profile categories and columns indexed by the plurality of insertion categories, wherein the adjusting comprises

selecting a row of the user preference matrix corresponding to a video category,

determining weights from at least one row of the user profile matrix, and

applying the weights to the row of the user preference matrix to form an adjusted row of the user preference matrix;

transmitting, over the network by the second server, the filtered results to the user device to specify actual insertion content for the user device to insert into the video content;

after transmitting the filtered results, receiving, by the second server, a request from the user device for the actual insertion content specified in the filtered results that the user device determined to correspond with video content received by the user device from the first server;

transmitting by the second server over the network the actual insertion content to the user device for subsequent insertion of the actual insertion content in the video content received by the user device from the first server;

receiving, by the user device, the video content from the first server;

receiving, by the user device, the filtered results from the second server;

selecting, by the user device, the actual insertion content specified in the filtered results based on the video content;

transmitting, by the user device, the request for the actual insertion content to the second server;

receiving, by the user device, the actual insertion content from the second server; and

playing back the video content and the actual insertion content.

2. The method of claim 1, wherein the video content comprises a plurality of video segments, and each video segment of the plurality of video segments is associated with a category from a plurality of categories.

3. The method of claim 1, further comprising:

receiving user feedback information the user device; and

adjusting the user preference data based on the user feedback information.

4. The method of claim 3, wherein adjusting the user preference data comprises adjusting the user preference data according to a history of user preference data.

5. The method of claim 4, further comprising applying a sliding window to the history of user preference data.

6. The method of claim 1, wherein matching the video content metadata to the insertion content metadata comprises:

incrementing a match metric in accordance with the comparing;

comparing the incremented match to a predetermined threshold; and

when the incremented match exceeds the predetermined threshold, add the inserted content to a first table of insertion content.

7. The method of claim 1, wherein matching the video content metadata to insertion content metadata further comprises using a lexical database to match keywords.

8. The method of claim 1, wherein

the video content metadata further comprises a first synopsis comprising a written description of the video content;

the insertion content metadata further comprises a second synopsis comprising a written description of the insertion content; and

matching the video content metadata to insertion content metadata further comprises comparing words of the first synopsis with words of the second synopsis, comparing comprising using a lexical database to match similar words.

9. The method of claim 1, wherein:

the video content comprises a plurality of video segments;

each video segment is associated with at least one keyword; and

matching the video content metadata further comprising matching the video content metadata to the insertion content metadata on a segment by segment basis.

10. A method of matching video content to insertion content, the method comprising:

electronically receiving video content metadata from a first server over a network by a second server, the video content metadata corresponding to video content being sent to a user device over the network by the first server, wherein the first server, second server and third server are separate from each other;

using a processor of a second server, matching the video content metadata to insertion content metadata of a global list of insertion content, the insertion content metadata corresponding to insertion content, wherein the video content metadata comprises a first category taken from an ontological structure, and the insertion content metadata comprises a second category taken from the ontological structure, wherein matching the video content metadata to the insertion content metadata further comprises comparing the first category to the second category; and

generating a first list of insertion content based on the matching;

generating, by the second server, a first list of insertion content in accordance with the matching;

receiving, over the network by the second server, user preference data from the user device;

filtering, by the second server, the first list of insertion content prior to transmitting any of the first list of insertion content to form a filtered list of insertion content, wherein the filtering the first list is performed at least in part using the user preference data, wherein the user preference data comprises a user preference matrix, the user preference matrix comprising preference values according to rows indexed by video categories and columns indexed by a plurality of insertion content categories, wherein the user preference matrix comprises values based on the received user preference data;

adjusting the user preference data according to user profile data in a user profile matrix, wherein the user profile matrix comprises further preference data according to the plurality of insertion content categories and comprises rows indexed by user profile categories and columns indexed by the plurality of insertion content categories and wherein the adjusting comprises

selecting a row of the user preference matrix,

selecting at least one row of the user profile matrix,

calculating weights from the at least one row of the user profile matrix, and

applying the weights to the row of the user preference matrix to adjust the row of the user preference matrix;

forwarding, over the network by the second server, the filtered list of insertion content to the user device to specify actual insertion content for the user device to insert into the video content;

after transmitting the filtered list of insertion content, receiving, by the second server, a request from the user device for an actual insertion content specified in the filtered list of insertion content that the user device determined to correspond with video content received by the user device from the first server;

transmitting by the second server over the network the actual insertion content to the user device for subsequent insertion of the actual insertion content in the video content received by the user device from the first server;

receiving, by the user device, the video content from the first server;

receiving, by the user device, the filtered list of insertion content from the second server;

selecting, by the user device, the actual insertion content specified in the filtered list of insertion content based on the video content;

transmitting, by the user device, the request for the actual insertion content to the second server;

receiving, by the user device, the actual insertion content from the second server; and

playing back the video content and the actual insertion content.

11. The method of claim 10, wherein

the ontological structure comprises a first plurality of top level categories;

and

at least one of the first plurality of top level categories comprises a second plurality of subcategories.

12. The method of claim 11, wherein the first plurality of top level categories comprises a combined object and participation category, the combined object and participation category comprising subcategories pertaining to live and inanimate objects.

13. The method of claim 11, wherein the first plurality of top level categories comprises a process category, the process category comprising human event driven subcategories.

14. The method of claim 10, wherein at least one category taken from the ontological structure is applied to a local portion of the video content.

15. A system for matching video content to insertion content, the system comprising:

a user device;

a metadata matcher configured to receive video content metadata from a first server and match the video content metadata to insertion content metadata of a global list of insertion content, wherein

the insertion content metadata corresponds to the insertion content, the video content metadata corresponds to the video content sent to the user device from the first server,

the metadata matcher is implemented with a second server, wherein

the video content metadata comprises at least one keyword,

the insertion content metadata comprises at least one keyword,

the metadata matcher matches the video content metadata to insertion content metadata by comparing the at least one keyword of the video content metadata to the at least one keyword of the insertion content metadata, and

the first server, the second server and the user device are separate from each other;

an insertion content filter of the second server, wherein the insertion content filter configured to receive user preference data from the user device, and to filter a resultant list from the metadata matcher to generate a resultant filtered list, wherein

the insertion content filter is configured to filter the resultant list according to the user preference data in a user preference matrix,

the user preference matrix comprises preference values according to rows indexed by video categories and columns indexed by a plurality of insertion content categories, and

the insertion content filter is further configured to adjust the user preference data according to user profile data, wherein the adjusting the user preference data comprises

selecting a row of the user preference matrix,

selecting a row of a user profile matrix within the user profile data,

wherein the user profile matrix comprises further preference data according to the plurality of insertion content categories and comprises rows indexed by user profile categories and columns indexed by the plurality of insertion content categories,

using the row of the user profile matrix to determine weights, and

applying the weights to the row of the user preference matrix to form an adjusted row of the user preference matrix,

the second server is configured to

transmit, over a network, the filtered list to the user device to specify actual insertion content for the user device to insert into the video content,

after transmitting the filtered list, receive a request from the user device for an actual insertion content specified in the filtered list that the user device determined to correspond with video content received by the user device from the first server, and

transmit over the network the actual insertion content to the user device for subsequent insertion of the actual insertion content in the video content received by the user device from the first server, and

the user device is configured to

receive the video content from the first server,

receive the filtered list from the second server,

select the actual insertion content specified in the filtered list based on the video content,

transmit the request for the actual insertion content to the second server,

receive the actual insertion content from the second server; and

play back the video content and the actual insertion content.

16. The system of claim 15, wherein the metadata matcher matches the video content metadata to the insertion content metadata by incrementing a match metric based on the comparing, comparing the incremented match to a predetermined threshold;

and

if the increment match exceeds the predetermined threshold, add the insertion content to a first table of insertion content.

17. The system of claim 15, wherein the metadata matcher matches the video content metadata to insertion content metadata by using a lexical database to match keywords.

18. The system of claim 15, further comprising a communications adaptor that receives video content metadata from a first server, the video content metadata corresponding to video content being sent to a user device.

19. The system of claim 15, wherein

the video content metadata further comprises a first synopsis comprising a written description of the video content;

the insertion content metadata further comprises a second synopsis comprising a written description of the insertion content; and

the metadata matcher further matches the video content metadata to insertion content metadata by comparing words of the first synopsis with words of the second synopsis, comparing comprising using a lexical database to match similar words.

20. The system of claim 15, wherein:

the video content comprises a plurality of video segments; and

matching the video content metadata further comprising matching the video content metadata to the insertion content metadata on a segment by segment basis.

21. A method of matching video content to insertion content, the method comprising:

electronically receiving user preference data from a user device over a network by a first server; and

filtering, by the first server, matched video content metadata to insertion content metadata to form a filtered results, wherein

the matched video content metadata is based on video content metadata received from a second server over the network,

the matched video content metadata corresponding to video content being sent to the user device, and

the first server, the second server and the user device are separate from each other,

filtering comprises

utilizing, by the first server, user preference data from a user preference matrix to perform the filtering results, the user preference matrix comprising preference values according to rows indexed by video categories and columns indexed by a plurality of insertion content categories, wherein the user preference matrix comprises values based on the received user preference data, and

adjusting, by the first server, the user preference data according to user profile data in a user profile matrix,

the user profile matrix comprises further preference data according to the plurality of insertion content categories,

the user profile matrix comprises rows indexed by user profile categories and columns indexed by the plurality of insertion content categories, and

the adjusting comprises

selecting a row of the user preference matrix corresponding to a video category,

determining weights from at least one row of the user profile matrix, and

applying the weights to the row of the user preference matrix to form an adjusted row of the user preference matrix;

transmitting, over the network by the first server, the filtered results to the user device to specify actual insertion content for the user device to insert into the video content;

after transmitting the filtered results, receiving, by the first server, a request from the user device for an actual insertion content specified in the filtered results that the user device determined to correspond with video content received by the user device from the second server; and

transmitting by the first server over the network the actual insertion content to the user device for subsequent insertion of the actual insertion content in the video content received by the user device from the second server;

receiving, by the user device, the video content from the second server;

receiving, by the user device, the filtered results from the first server;

selecting, by the user device, the actual insertion content specified in the filtered results based on the video content;

transmitting, by the user device, the request for the actual insertion content to the first server;

receiving, by the user device, the actual insertion content from the first server; and

playing back the video content and the actual insertion content.

22. The method of claim 21, further comprising calculating a preference value based on the user preference matrix.

23. The method of claim 22, wherein adjusting the user preference data according to the user profile data and calculating the preference value comprises using a preference and profile (PNP) based Bayesian engine.

24. The method of claim 21, wherein each element in the user profile matrix and the user preference matrix comprises an a_ij^l value denoting a positive user disposition and an a_ij^d value denoting a negative user disposition;

and

the determining weights comprises calculating a weight according to;

25. The method of claim 24, further comprising applying the following expression to elements in the row of the user preference matrix:

26. The method of claim 25, wherein the weight and the preference value are between −

1 and 1.

27. The method of claim 25, wherein:

each element in the user profile matrix and the user preference matrix further comprises a history of a last N user values; and

the method further comprises calculating the a_ij^l and a_ij^d values according to the history of the last N user values.

28. The method of claim 21, further comprising

receiving user feedback information from the user device;

and

adjusting the user preference data based on the user feedback information.

29. The method of claim 28, wherein adjusting the user preference data comprises adjusting the user preference data according to a history of user preference data.

30. The method of claim 29, further comprising applying a sliding window to the history of user preference data.