Discovering and classifying situations that influence affective response
First Claim
Patent Images
1. A system configured to identify situations, comprising:
- at least one processor and at least one memory, the at least one processor and the at least one memory cooperating to function as;
a sample generator configured to receive temporal windows of token instances to which a user was exposed and affective response annotations, and to generate samples from the windows and annotations;
wherein the temporal windows of token instances comprise token instances that have overlapping instantiation periods;
a clustering module configured to cluster the samples into a plurality of clusters utilizing a distance function that computes a distance between a pair comprising first and second samples;
wherein the distance function assigns weight greater than zero to difference between token instances belonging to the first and second samples, and to difference between the affective response annotations belonging to the first and second samples;
the clustering module is further configured to assign to the samples situation identifiers corresponding to the clusters; and
a machine learning trainer configured to utilize the samples and their corresponding situation identifiers to train a model that may be used by a machine learning-based predictor of situations;
wherein the machine learning based predictor receives a sample comprising a temporal window of token instances and an affective response annotation, and utilizes the model to predict a situation identifier corresponding to the sample.
1 Assignment
0 Petitions
Accused Products
Abstract
Described herein are systems for identifying situations. The system receive samples, each comprising a temporal window of token instances to which a user was exposed and an affective response annotation. One embodiment uses a clustering algorithm to cluster the samples into a plurality of clusters utilizing a distance function that computes a distance between a pair comprising first and second samples. Another embodiment utilizes an Expectation-Maximization approach to assign situation identifiers. And another embodiment involves training, utilizing the samples, a machine learning-based classifier to assign situation identifiers.
50 Citations
20 Claims
-
1. A system configured to identify situations, comprising:
-
at least one processor and at least one memory, the at least one processor and the at least one memory cooperating to function as; a sample generator configured to receive temporal windows of token instances to which a user was exposed and affective response annotations, and to generate samples from the windows and annotations;
wherein the temporal windows of token instances comprise token instances that have overlapping instantiation periods;a clustering module configured to cluster the samples into a plurality of clusters utilizing a distance function that computes a distance between a pair comprising first and second samples;
wherein the distance function assigns weight greater than zero to difference between token instances belonging to the first and second samples, and to difference between the affective response annotations belonging to the first and second samples;the clustering module is further configured to assign to the samples situation identifiers corresponding to the clusters; and a machine learning trainer configured to utilize the samples and their corresponding situation identifiers to train a model that may be used by a machine learning-based predictor of situations;
wherein the machine learning based predictor receives a sample comprising a temporal window of token instances and an affective response annotation, and utilizes the model to predict a situation identifier corresponding to the sample. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system configured to train a model of situations, comprising:
-
at least one processor and at least one memory, the at least one processor and the at least one memory cooperating to function as; a sample generator configured to receive temporal windows of token instances to which a user was exposed and corresponding affective response annotations and to generate samples from the windows and the annotations;
wherein the temporal window of token instances comprises token instances that have overlapping instantiation periods; anda situation annotator configured to receive the samples and situation identifiers corresponding to at least some, but not all, of the samples;
wherein the situation identifiers correspond to a certain number of situations;the situation annotator is further configured to train a model with the samples and the situation identifiers for utilizing an Expectation-Maximization approach;
wherein the model describes probabilities of the samples corresponding to situations from the certain number of situations. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A system configured to train a classifier of situations, comprising:
-
at least one processor and at least one memory, the at least one processor and the at least one memory cooperating to function as; a sample generator configured to receive temporal windows of token instances to which a user was exposed and corresponding affective response annotations and to generate samples from the windows and the annotations;
wherein the temporal window of token instances comprises token instances that have overlapping instantiation periods; anda machine learning classifier trainer configured to receive situation identifiers corresponding to the samples;
wherein the situations identifiers correspond to a plurality of different situations;the machine learning classifier trainer is further configured to utilize the samples and the situation identifiers to train a classifier;
wherein the classifier receives a sample comprising a temporal window of token instances and an affective response annotation, and selects a situation identifier corresponding to the sample. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification