Personalized experience scores based on measurements of affective response

• US 10,198,505 B2
• Filed: 08/21/2015
• Issued: 02/05/2019
• Est. Priority Date: 08/21/2014
• Status: Active Grant

• Current Assignee: Affectomatics ltd.
• Original Assignee: Affectomatics ltd.
• Inventors: Frank, Ari M, Thieberger, Gil
• Primary Examiner(s): Waldron, Scott A.
• Assistant Examiner(s): Mina, Fatima P
• Application Number:
  US14/833,035
• Publication Number:
  US 20160055236A1
• Time in Patent Office: 1,264 Days
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

This disclosure describes systems, methods, and computer program products that may be used to provide crowd-based scores for experiences, which are computed based on measurements of affective response of multiple users who had the experiences. The measurements of affective response may be collected using a wide array of sensors that measure physiological signals and/or behavioral cues. Additionally, the scores may be personalized for a certain user based on similarities between a profile of the certain user and profiles of the multiple users.

Claims

1. A system configured to compute personalized experience scores, comprising:

sensors configured to take measurements of affective response of at least ten users who had an experience;

wherein each measurement of affective response of a user comprises at least one of a value of a physiological signal of the user and a value indicative of a behavioral cue of the user;

a computer configured to;

receive a profile of a certain user and profiles of the at least ten of the users;

wherein a profile of a user comprises data that describes at least one of the following;

a characteristic of the user, and an indication of one or more experiences the user had;

generate an output indicative of similarities between the profile of the certain user and the profiles of the at least ten of the users; and

compute an experience score for the certain user based on the measurements and the output;

wherein, for at least a certain first user and a certain second user, who have different profiles, the computer computes respective first and second experience scores that are different.

2. The system of claim 1, wherein the data describes one or more of the following:

a demographic characteristic of the user, a genetic characteristic of the user, a static attribute describing the body of the user, a medical condition of the user, an indication of a content item consumed by the user, and a value derived from semantic analysis of a communication of the user.

3. The system of claim 1, wherein the first experience score is computed based on at least one measurement that is not utilized for computing the second experience score.

4. The system of claim 1, wherein a measurement utilized to compute both the first and second experience scores has a first weight when utilized to compute the first experience score and the measurement has a second weight, different from the first weight, when utilized to compute the second experience score.

5. The system of claim 1, wherein the computer is further configured to recommend the experience to a user in a manner that belongs to a set comprising first and second manners;

wherein when recommending an experience in the first manner, the computer provides a stronger recommendation for the experience, compared to a recommendation for the experience that the computer provides when recommending in the second manner.

6. The system of claim 5, wherein the computer is further configured to:

recommend the experience in the first manner when an experience score for the experience reaches a predetermined threshold, and to recommend the experience in the second manner when the experience score does not reach the predetermined threshold.

7. The system of claim 6, wherein responsive to the first experience score reaching the predetermined threshold, the experience is recommended to the certain first user in the first manner;

and wherein responsive to the second experience score not reaching the predetermined threshold, the experience is recommended to the certain second user in the second manner.

8. The system of claim 1,

wherein the computer is configured to generate the output by calculating values indicative of a similarity between each of the profiles of the at least ten users and the profile of the certain user, and by utilizing the values to calculate weights for the measurements of the users;

wherein a weight for a measurement of a user, from among the at least ten of the users, is proportional to an extent of a similarity between the profile of the user and the profile of the certain user, such that a weight generated for a measurement of a user whose profile is more similar to the profile of the certain user is higher than a weight generated for a measurement of a user whose profile is less similar to the profile of the certain user;

wherein the output is indicative of the weights;

and wherein the experience score is computed based on the measurements of the at least ten of the users and the weights.

9. The system of claim 1, wherein

the computer is configured to generate the output by clustering the at least ten of the users into clusters based on profile similarity, with each cluster comprising a single user or multiple users with similar profiles, and selecting, based on the profile of the certain user, a subset comprising at most half of the clusters;

wherein, on average, the profile of the certain user is more similar to a profile of a user who is a member of a cluster in the subset, than it is to a profile of a user, from among the at least ten of the users, who is not a member of any of the clusters in the subset;

the computer is further configured to select at least eight users from among the users belonging to clusters in the subset;

wherein the output is indicative of the at least eight users;

and wherein the experience score is computed based on measurements of the at least eight users.

10. The system of claim 9, wherein clustering the at least ten of the users is done utilizing one or more of the following clustering approaches:

hierarchical clustering, partition-based clustering, and clustering utilizing an Expectation-Maximization algorithm.

11. The system of claim 1, wherein the computer is configured to calculate similarities between the profile of the certain user and the profiles of the at least ten of the users by utilizing a distance metric that is applied vectors of feature values representing the profiles;

and wherein utilizing the distance metric is based on one or more of the following metrics applied to a pair of vectors;

a dot-product between the pair of vectors, a Euclidean distance between the pair of vectors, and the Hamming distance between the pair of vectors.

12. A method for computing personalized experience scores, comprising:

taking, utilizing sensors, measurements of affective response of at least ten users who had an experience;

wherein each measurement of affective response of a user comprises at least one of a value of a physiological signal of the user and a value indicative of a behavioral cue of the user;

receiving a first profile of a first user, a second profile of a second user, and profiles of the at least ten of the users;

wherein the first profile is different from the second profile;

wherein a profile of a user comprises data that describes at least one of the following;

a characteristic of the user, and an indication of one or more experiences the user had;

generating a first output indicative of similarities between the profile of the first user and the profiles of the at least ten of the users;

generating a second output indicative of similarities between the profile of the second user and the profiles of the at least ten of the users;

wherein the second output is different from the first output;

computing a first experience score for the first user based on the measurements and the first output; and

computing a second experience score for the second user based on the measurements and the second output;

wherein first and second experience scores that are different.

13. The method of claim 12, further comprising utilizing at least one measurement for computing the first experience score, which is not utilized for computing the second experience score.

14. The method of claim 12, further comprising utilizing a certain measurement to compute both the first and second experience scores;

wherein the certain measurement has a first weight when utilized to compute the first experience score and the certain measurement has a second weight, different from the first weight, when utilized to compute the second experience score.

15. The method of claim 12, further comprising generating the first output by calculating values indicative of a similarity between each of the profiles of the at least ten of the users and the profile of the first user, and utilizing the values to calculate weights for the measurements of the users;

wherein a weight for a measurement of a user, from among the at least ten of the users, is proportional to an extent of a similarity between the profile of the user and the profile of the first user, such that a weight generated for a measurement of a user whose profile is more similar to the profile of the first user is higher than a weight generated for a measurement of a user whose profile is less similar to the profile of the first user; and

wherein the first output is indicative of the weights.

16. The method of claim 12, further comprising generating the first output by clustering the at least ten of the users into clusters based on profile similarity, with each cluster comprising a single user or multiple users with similar profiles, and selecting, based on the profile of the first user, a subset comprising at most half of the clusters;

wherein, on average, the profile of the first user is more similar to a profile of a user who is a member of a cluster in the subset, than it is to a profile of a user, from among the at least ten of the users, who is not a member of any of the clusters in the subset; and

further comprising selecting at least eight users from among the users belonging to clusters in the subset;

wherein the first output is indicative of the at least eight users.

17. A non-transitory computer-readable medium having instructions stored thereon that, in response to execution by a system including a processor and memory, causes the system to perform operations comprising:

taking, utilizing sensors, measurements of affective response of at least ten users who had an experience;

wherein each measurement of affective response of a user comprises at least one of a value of a physiological signal of the user and a value indicative of a behavioral cue of the user;

receiving a first profile of a first user, a second profile of a second user, and profiles of the at least ten of the users;

wherein the first profile is different from the second profile; and

wherein a profile of a user comprises data that describes at least one of the following;

a characteristic of the user, and an indication of one or more experiences the user had;

generating a first output indicative of similarities between the profile of the first user and the profiles of the at least ten of the users;

generating a second output indicative of similarities between the profile of the second user and the profiles of the at least ten of the users;

wherein the second output is different from the first output;

computing a first experience score for the first user based on the measurements and the first output; and

computing a second experience score for the second user based on the measurements and the second output;

wherein first and second experience scores are different.

18. The non-transitory computer-readable medium of claim 17, further comprising instructions for generating the first output by calculating values indicative of a similarity between each of the profiles of the at least ten of the users and the profile of the first user, and utilizing the values to calculate weights for the measurements of the users;

wherein a weight for a measurement of a user, from among the at least ten of the users, is proportional to an extent of a similarity between the profile of the user and the profile of the first user, such that a weight generated for a measurement of a user whose profile is more similar to the profile of the first user is higher than a weight generated for a measurement of a user whose profile is less similar to the profile of the first user; and

wherein the first output is indicative of the weights.

19. The non-transitory computer-readable medium of claim 17, generating the first output by clustering the at least ten of the users into clusters based on profile similarity, with each cluster comprising a single user or multiple users with similar profiles, and selecting, based on the profile of the first user, a subset comprising at most half of the clusters;

wherein, on average, the profile of the first user is more similar to a profile of a user who is a member of a cluster in the subset, than it is to a profile of a user, from among the at least ten of the users, who is not a member of any of the clusters in the subset; and

further comprising instruction for selecting at least eight users from among the users belonging to clusters in the subset;

wherein the first output is indicative of the at least eight users.