Systems and methods for active training of broadcast personalization and audience measurement systems using a presence band

• US 9,277,276 B1
• Filed: 08/18/2014
• Issued: 03/01/2016
• Est. Priority Date: 08/18/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Arini, Nick Salvatore, Rowe, Simon Michael
• Primary Examiner(s): Sheleheda, James R
• Application Number:
  US14/461,660
• Publication Number:
  US 20160050456A1
• Time in Patent Office: 561 Days
• Field of Search: 725/9, 725/10, 725/11, 725/12, 725/19
• US Class Current: 1/1
• CPC Class Codes: H04H 60/31 Arrangements for monitoring the use made of the broadcast services
• CPC Class Codes: H04H 60/45 for identifying users
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04N 21/4126 The peripheral being portable, e.g. PDAs or mobile phones
• CPC Class Codes: H04N 21/42201 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 Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• 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 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/4662 characterized by learning algorithms
• 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

Abstract

An audience measurement or personalized recommendation system may be actively trained for each panel member for a training period, during which the presence of each member is recorded while content is displayed. Panel members may carry or wear portable devices with wireless transmitters which may be detected by the measurement system. For example, each panel member may wear a wristband including a wireless transmitter broadcasting an identification code, and a measurement device may include a wireless receiver to receive broadcast identification codes and determine that the corresponding one or more panel members are present during display of content. An inference engine may create personalized profiles of each panel participant during the training period. After the training period, panel participants may stop carrying or wearing the devices, and the inference engine may determine, based on the profiles, which participants are likely present when content is being viewed.

Claims

1. A method for determining presence of individuals during audience measurement, comprising:

receiving, by a first device during display of an item of content, a transmitted signal from a second device associated with a first individual;

generating, by the first device responsive to receiving the transmitted signal from the second device, a first signature associated with the first individual based on the displayed item of content;

receiving, by the first device during display of a second item of content, a second transmitted signal from the second device and a transmitted signal from a third device associated with a second individual;

generating, by the first device responsive to receiving the transmitted signals from the second and third device, a second signature associated with both the first and second individual based on the displayed second item of content;

detecting, by the first device during display of a third item of content, no transmitted signals from the second device or third device;

generating, by the first device during display of the third item of content, a third signature based on the displayed third item of content and the absence of the transmitted signals from the second device and third device;

determining, by the first device, that the third signature matches the first signature by determining that an intersection between the third signature and the first signature is greater than an intersection between the third signature and the second signature; and

recording, by the first device responsive to the determination, an identification of presence of the first individual and absence of the second individual during display of the third item of content.

2. The method of claim 1, wherein determining that the third signature matches the first signature further comprises determining that a difference between a parameter of the first signature and corresponding parameter of the third signature is less than a predetermined threshold.

3. The method of claim 1, wherein determining that the third signature matches the first signature further comprises determining that a distance between the first signature and third signature in a multi-dimensional space is less than a predetermined threshold.

4. The method of claim 1, wherein determining that the third signature matches the first signature further comprises determining that the first signature and third signature overlap by an amount greater than a predetermined threshold.

5. The method of claim 1, wherein determining that the third signature matches the first signature further comprises calculating a confidence score proportional to an amount of matching between the first signature and the third signature, and wherein recording the identification of presence of the first individual during display of the third item of content further comprises recording the confidence score.

6. The method of claim 1, further comprising:

detecting, by the first device during display of a fourth item of content, no transmitted signals from the second device or third device;

generating, by the first device during display of the fourth item of content, a fourth signature based on the displayed fourth item of content and the absence of the transmitted signals from the second device and third device;

determining, by the first device, that the fourth signature matches the second signature; and

recording, by the first device responsive to the determination, an identification of presence of both the first individual and the second individual during display of the fourth item of content.

7. A system for determining presence of individuals during audience measurement, comprising:

a first device comprising a processor executing an inference engine and a receiver;

wherein the receiver is configured for receiving, during display of a first item of content,

a transmitted signal from a second device associated with a first individual, and

receiving, during display of a second item of content, a second transmitted signal from the second device and a transmitted signal from a third device associated with a second individual; and

wherein the inference engine is configured for;

generating a first signature associated with the first individual based on the displayed first item of content and a second signature associated with both the first and second individual based on the displayed second item of content;

subsequently generating, during display of a third item of content and while the receiver is not receiving the transmitted signals from the second device or third device, a third signature based on the displayed third item of content,

determining that the third signature matches the first signature by determining that a difference between the third signature and the first signature is greater than a difference between the third signature and the second signature; and

recording, responsive to the determination, an identification of presence of the first individual and absence of the second individual during display of the third item of content.

8. The system of claim 7, wherein the inference engine is further configured for determining that a difference between a parameter of the first signature and corresponding parameter of the third signature is less than a predetermined threshold.

9. The system of claim 7, wherein the inference engine is further configured for determining that a distance between the first signature and third signature in a multi-dimensional space is less than a predetermined threshold.

10. The system of claim 7, wherein the inference engine is further configured for determining that the first signature and third signature overlap by an amount greater than a predetermined threshold.

11. The system of claim 7, wherein the inference engine is further configured for calculating a confidence score proportional to an amount of matching between the first signature and the third signature, and wherein recording the identification of presence of the first individual during display of the third item of content further comprises recording the confidence score.

12. The system of claim 7, wherein the inference engine is further configured for:

detecting, during display of a fourth item of content, no transmitted signals from the second device or third device;

generating, during display of the fourth item of content, a fourth signature based on the displayed fourth item of content and the absence of the transmitted signals from the second device and third device;

determining that the fourth signature matches the second signature; and

recording, responsive to the determination, an identification of presence of both the first individual and the second individual during display of the fourth item of content.

13. A non-transitory computer-readable storage medium storing instructions that when executed by one or more data processors, cause the one or more data processors to perform operations comprising:

receiving, during display of a first item of content, a transmitted signal from a second device associated with a first individual, and receiving, during display of a second item of content, a second transmitted signal from the second device and a transmitted signal from a third device associated with a second individual;

generating a first signature associated with the first individual based on the displayed first item of content and a second signature associated with both the first and second individual based on the displayed second item of content;

generating, during display of the third item of content, a third signature based on the displayed third item of content and the absence of the transmitted signals from the second device and third device;

determining that the third signature matches the first signature by determining that an intersection between the third signature and the first signature is greater than an intersection between the third signature and the second signature; and

recording, responsive to the determination, an identification of presence of the first individual and absence of the second individual during display of the third item of content.

14. The computer-readable storage medium of claim 13, wherein execution of the instructions further cause the one or more data processors to perform operations including:

detecting, during display of a fourth item of content, no transmitted signals from the second device or third device;

generating, during display of the fourth item of content, a fourth signature based on the displayed fourth item of content and the absence of the transmitted signals from the second device and third device;

determining that the fourth signature matches the second signature; and

recording, responsive to the determination, an identification of presence of both the first individual and the second individual during display of the fourth item of content.