Automatic rating system using background audio cues

Patent metadata

Field	Value
Publication number	US-10440433-B2
Application number	US-201715434444-A
Country	US
Kind code	B2
Filing date	Feb 16, 2017
Priority date	Jan 2, 2008
Publication date	Oct 8, 2019
Grant date	Oct 8, 2019

Abstract

Methods and systems for capturing, transmitting and processing data for generating ratings relating to multimedia programming based on passively obtained user cues are disclosed herein.

First claim

What is claimed is:

1. A method, comprising:
accessing, by a processing system including a processor, data comprising feedback captured during presentation of a media content item at equipment of an end user to provide cues regarding a reaction of the end user to the media content item, the data being obtained without providing an alert to the end user that the feedback regarding the reaction is being monitored;
processing, by the processing system, the data by identifying the feedback and by determining frequencies and durations of the cues, wherein the frequencies of the cues include a count of the cues;
monitoring, by the processing system, the cues according to a plurality of acoustic models;
determining, by the processing system, types of cues based on the monitoring of the cues, wherein the types of cues include verbal cues and non-verbal cues;
generating, by the processing system, a ratings profile of the media content item based on a temporal correlation of the feedback, the types of cues, and the frequencies and durations of the cues;
based on the feedback obtained from the equipment, distributing, by the processing system, a temporal mapping of the cues against the media content item to a virtual audience, advertisers, service providers, or a combination thereof, wherein the service providers include a television network;
providing, by the processing system, a plurality of programming recommendations based on the temporal mapping; and
providing, by the processing system, producers an indication of a plurality of media content that is most likely to generate revenue based on the temporal mapping, wherein the media content item is included in the plurality of media content.

2. The method of claim 1 , wherein the feedback comprises audible cues of a reaction of the end user to the media content item.

3. The method of claim 2 , wherein the feedback comprises audio cues that are sounds without speech.

4. The method of claim 3 , wherein the feedback includes aurally distinguishable cues, including screams and laughter.

5. The method of claim 1 , wherein the feedback comprises visual cues based on the reaction of the end user to the media content item.

6. The method of claim 1 , wherein the feedback comprises audio-visual cues of the reaction of the end user to the media content item.

7. The method of claim 1 , wherein the processing of the data further comprises monitoring, by the processing system, a frequency of the feedback.

8. The method of claim 1 , further comprising identifying dialog without using speech recognition, wherein the feedback is captured during presentation of a media content item at equipment of an end user to provide one of real-time feedback or near-real-time feedback of the reaction of the end user to the media content item.

9. The method of claim 1 , wherein the accessing of the data comprises measuring, by the processing system, intensities of the cues, and wherein the ratings profile of the media content item is based on the intensities of the cues.

10. A system, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, comprising:
acquiring data comprising feedback regarding a reaction of an end user to a media content item distributed to equipment of the end user over a communication network;
determining frequencies and durations of cues based on the feedback, wherein the frequencies of the cues include a count of the cues;
monitoring the cues according to a plurality of acoustic models;
determining types of the cues based on the monitoring of the cues, wherein the types of the cues include verbal cues and non-verbal cues;
generating, for the media content item, a continuous ratings profile based on the types of the cues, and the frequencies and durations of the cues;
based on the feedback obtained from the equipment, distributing a temporal mapping of the cues against the media content item to a virtual audience, advertisers, service providers, or a combination thereof, wherein the service providers include a television network;
providing a plurality of programming recommendations based on the temporal mapping; and
providing producers an indication of a plurality of media content that is most likely to generate revenue based on the temporal mapping, wherein the media content item is included in the plurality of media content.

11. The system of claim 10 , wherein the feedback is obtained without the end user proactively identifying the feedback in the data, and wherein the operations further comprise measuring the cues without alerting the end user that the reaction of the end user is being monitored.

12. The system of claim 10 , wherein the feedback comprises audible cues of the reaction of the end user to the media content item.

13. The system of claim 10 , wherein the feedback comprises audio cues that are sounds without speech.

14. The system of claim 10 , wherein the feedback comprises visual cues of the reaction of the end user to the media content item.

15. The system of claim 10 , wherein the feedback comprises audio-visual cues of the reaction of the end user to the media content item.

16. The system of claim 15 , wherein the feedback includes aurally distinguishable cues, including screams and laughter.

17. The system of claim 10 , wherein the cues are based on one of frequency, duration, or frequency and duration of the feedback.

18. The system of claim 10 , wherein the feedback is captured during presentation of a media content item at equipment of the end user to provide one of real-time feedback or near-real-time feedback regarding the reaction of the end user to the media content item.

19. A non-transitory, machine-readable storage medium comprising instructions which, responsive to being executed by a processing system including a processor, facilitate performance of operations, comprising:
accessing data comprising cues based on feedback obtained from equipment of an end user regarding captured end user reactions to media content;
processing the cues by measuring cue frequency and duration based on a frequency and duration of the feedback, wherein the cue frequency includes a count of the cues;
monitoring the cues according to a plurality of acoustic models;
determining types of the cues based on the monitoring of the cues, wherein the types of the cues include verbal cues and non-verbal cues;
generating a continuous ratings profile of the media content based on the cue type and the cue frequency and duration;
based on the feedback obtained from the equipment, distributing a temporal mapping of the cues against the media content to a virtual audience, advertisers, service providers, or a combination thereof, wherein the service providers include a television network;
providing a plurality of programming recommendations based on the temporal mapping; and
providing producers an indication of a plurality of media content that is most likely to generate revenue based on the temporal mapping, wherein the media content is included in the plurality of media content.

20. The non-transitory, machine-readable storage medium of claim 19 , wherein the operations further comprise:
temporally correlating the feedback identified from the processing of the cues with the media content; and
generating, for the media content, the continuous ratings profile based on the temporally correlating of the feedback.

Assignees

• At & T Ip Ii Lp

Inventors

• Amento Brian
• Harrison Christopher
• Stead Larry

Classifications

• H04N21/4223

  Cameras (H04N23/00 takes precedence) · CPC title

• G06F3/16

  Sound input; Sound output (speech processing G10L) · CPC title

• H04N21/251

  Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08) · CPC title

• H04N21/45

  Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts · CPC title

• H04N21/42201

  biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user (input arrangements for interaction with the human body based on nervous system activity detection G06F3/015) · CPC title