Utilizing semantic analysis to determine how to process measurements of affective response

• US 9,104,969 B1
• Filed: 04/29/2015
• Issued: 08/11/2015
• Est. Priority Date: 10/14/2012
• Status: Expired due to Fees

• Current Assignee: Affectomatics ltd.
• Original Assignee: Ari M. Frank, Gil Thieberger
• Inventors: Frank, Ari M, Thieberger, Gil
• Primary Examiner(s): Tsai, Henry
• Assistant Examiner(s): Roche, John
• Application Number:
  US14/698,936
• Publication Number:
  US 20150227844A1
• Time in Patent Office: 104 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 1/28 Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/3212 Monitoring battery levels, e.g. power saving mode being initiated when battery voltage goes below a certain level
• CPC Class Codes: G06F 1/3234 Power saving characterised by the action undertaken
• CPC Class Codes: G06F 1/3296 by lowering the supply or operating voltage
• CPC Class Codes: G06F 2203/011 Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G06F 3/015 Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 9/46 Multiprogramming arrangements
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Disclosed herein are Systems, methods, and computer program products for utilizing semantic analysis to set a processing level of a processor processing measurements of affective response. A semantic analyzer receives a segment of content, analyzes it utilizing semantic analysis, and outputs an indication regarding whether a value related to a predicted emotional response to the segment reaches a threshold. Based on the indication, a controller selects a processing level, from among at least first and second processing levels, for a processor to process the measurements. The processor is configured to utilize significantly fewer computation cycles to process data operating at the first processing level, compared to the number of computation cycles it utilizes to process data operating at the second processing level.

Claims

1. A system configured to utilize semantic analysis to set a processing level for processing measurements of affective response, comprising:

a semantic analyzer configured to;

receive a first segment of content, analyze the first segment utilizing semantic analysis, and output a first indication that a first value related to a predicted emotional response to the first segment does not reach a first predetermined threshold;

wherein the first segment comprises data representing text; and

a hardware-based controller configured to select, based on the first indication, a first processing level for a processor to process measurements of affective response of a user to the first segment;

wherein the semantic analyzer is further configured to;

receive a second segment of content, analyze the second segment utilizing semantic analysis, and output a second indication that a second value related to a predicted emotional response to the second segment reaches a second predetermined threshold;

wherein the second segment comprises data representing text;

wherein the hardware-based controller is further configured to select, based on the second indication, a second processing level for a processor to process measurements of affective response of the user to the second segment;

wherein, per volume unit of measurement data, the number of computation cycles utilized by the processor to process, at the first processing level, the measurements of the affective response of the user to the first segment, is at least 50% lower than the number of computation cycles utilized by the processor to process, at the second processing level, the measurements of the affective response of the user to the second segment.

2. The system of claim 1, further comprising a device operable to provide measurements of the affective response of the user;

wherein the device is one or more of the following;

a physiological sensor, and an image capturing device.

3. The system of claim 2, further comprising a module configured to train an emotional response predictor (measurement ERP) based on feature values that are a product of measurements of the affective response of the user taken by the device and labels that are a product of the semantic analyzer.

4. The system of claim 2, further comprising an emotional response predictor (measurement ERP) configured to predict emotional response based on feature values that are a product of the affective response of the user taken by the device.

5. The system of claim 1, wherein the first and second predetermined thresholds represent first and second confidence levels in predictions of emotional response, respectively;

and wherein the first and second values represent confidence in predictions of emotional response to the first and second segments, respectively;

whereby the processor is configured to operate at the first processing level to process measurements of affective response of the user to the first segment when the first indication indicates that confidence in a prediction of emotional response to the first segment does not reach the first confidence level, and the processor is configured to operate at the second processing level to process measurements of affective response of the user to the second segment when the second indication indicates that confidence in a prediction of emotional response to the second segment does reach the second confidence level.

6. The system of claim 1, wherein the first and second predetermined thresholds represent first and second magnitudes of change in affective response, respectively;

and wherein the first and second values represent predicted changes in affective response due to exposure to the first and second segments, respectively;

whereby the processor is configured to operate at the first processing level to process measurements of affective response of the user to the first segment when the first indication indicates that a predicted change in affective response due to exposure to the first segment does not reach the first magnitude, and the processor is configured to operate at the second processing level to process measurements of affective response of the user to the second segment when the second indication indicates that a predicted change in affective response due to exposure to the second segment does reach the second magnitude.

7. The system of claim 1, wherein the first and second predetermined thresholds represent first and second benefit levels, respectively;

and wherein the first and second values represent predicted benefits to measuring affective response to the first and second segments, respectively;

whereby the processor is configured to operate at the first processing level to process measurements of affective response of the user to the first segment when the first indication indicates that a benefit of measuring affective response to the first segment does not reach the first benefit level, and the processor is configured to operate at the second processing level to process measurements of affective response of the user to the second segment when the second indication indicates that a benefit of measuring affective response to the second segment does reach the second benefit level.

8. The system of claim 1, wherein the semantic analyzer applies statistics on words that are correlated with certain emotional responses.

9. The system of claim 1, wherein the semantic analyzer applies Latent Semantic Analysis in order to associate a segment of content with a likely subject.

10. The system of claim 1, wherein the semantic analyzer evaluates the second segment shortly before the user is exposed to the second segment, whereby shortly is less than one minute.

11. The system of claim 1, wherein the second segment is received from an interactive computer game that provides context information about the second segment that may be utilized by the semantic analyzer to compute the second indication.

12. A method for utilizing semantic analysis to set a processing level of a processor processing measurements of affective response, comprising:

receiving a first indication derived from an evaluation comprising semantic analysis of a first segment of content;

wherein the first segment comprises data representing text;

determining that the first indication indicates that a first value related to a prediction of emotional response to the first segment does not reach a first predetermined threshold, and configuring a processor to operate at a first processing level to process measurements of affective response of a user to the first segment;

receiving a second indication derived from an evaluation comprising semantic analysis of a second segment of content;

wherein the second segment comprises data representing text; and

determining that the second indication indicates that a second value related to a prediction of emotional response to the second segment reaches a second predetermined threshold, and configuring the processor to operate at a second processing level to process measurements of affective response of the user to the second segment;

wherein, per volume unit of measurement data, the number of computation cycles utilized by the processor to process, at the first processing level, the measurements of the affective response of the user to the first segment, is at least 50% lower than the number of computation cycles utilized by the processor to process, at the second processing level, the measurements of the affective response of the user to the second segment.

13. The method of claim 12, further comprising collecting statistics on words that are correlated with certain emotional responses and utilizing the statistics for conducting the evaluation comprising semantic analysis of the first and second segments.

14. The method of claim 12, further comprising utilizing, for the evaluation comprising semantic analysis of the first and second segments, Latent Semantic Analysis in order to associate each of the first and second segments of content with a likely subject.

15. The method of claim 12, further comprising forwarding, to a module that trains a measurement Emotional Response Predictor (measurement ERP), a label corresponding to an expected emotional response to being exposed to the second segment, and a sample comprising a product of the measurements of the affective response of the user to the second segment.

16. The method of claim 12, further comprising forwarding, to a measurement emotional response predictor, a product of the measurements of the affective response of the user to being exposed to the second segment.

17. A non-transitory computer-readable medium for use in a computer to utilize semantic analysis to set a processing level of a processor processing measurements of affective response;

the computer comprising a processor, and the non-transitory computer-readable medium comprising;

program code for receiving a first indication derived from an evaluation comprising semantic analysis of a first segment of content;

wherein the first segment comprises data representing text;

program code for determining that the first indication indicates that a first value related to a prediction of emotional response to the first segment does not reach a first predetermined threshold, and for configuring a processor to operate at a first processing level to process measurements of affective response of a user to the first segment;

program code for receiving a second indication derived from an evaluation comprising semantic analysis of a second segment of content;

wherein the second segment comprises data representing text; and

program code for determining that the second indication indicates that a second value related to a prediction of emotional response to the second segment reaches a second predetermined threshold, and for configuring the processor to operate at a second processing level to process measurements of affective response of the user to the second segment;

wherein, per volume unit of measurement data, the number of computation cycles utilized by the processor to process, at the first processing level, the measurements of the affective response of the user to the first segment, is at least 50% lower than the number of computation cycles utilized by the processor to process, at the second processing level, the measurements of the affective response of the user to the second segment.

18. The non-transitory computer-readable medium of claim 17, further comprising program code for receiving the second segment from an interactive computer game that provides context information about the second segment that may be utilized for computing the second indication.

19. The non-transitory computer-readable medium of claim 17, further comprising program code for collecting statistics on words that are correlated with certain emotional responses and utilizing the statistics for conducting the evaluation comprising semantic analysis of the first and second segments.

20. The non-transitory computer-readable medium of claim 17, further comprising program code for utilizing, for the evaluation comprising semantic analysis of the first and second segments, Latent Semantic Analysis in order to associate each of the first and second segments of content with a likely subject.