Granted Patent B1

US 12,223,511 · App. 17/456,334 · Granted Feb 11, 2025

Inventors: Abhishek Kumar (Bangalore, IN); Amit Agarwal (Bangalore, IN); Dipanjan Deb (Bangalore, IN); Naveen Gururaja Yeri (Bangalore, IN)

Assignee: Wells Fargo Bank, N.A.

G06Q30/016G06V10/764G06V10/774G06V40/20

Abstract

Claims (60)

1. A computing system comprising:

a memory; and

one or more processors in communication with the memory and configured to:

create a set of training data including a plurality of customer communications, each customer communication associated with at least one of a plurality of emotion factor values, wherein each emotion factor value of the plurality of emotion factor values indicates a measure of a different emotion factor in a communication;

train each machine learning model of a set of machine learning models included in an emotion-based indexer, based on the set of training data, to determine the measure of the different emotion factor as a particular emotion factor value of the plurality of emotion factor values, wherein each machine learning model is trained to output the particular emotion factor value of the plurality of emotion factor values based on input communication data;

receive communication data of a current communication associated with a customer;

apply the communication data to the emotion-based indexer running on the one or more processors as input;

generate, as output from the emotion-based indexer, a set of emotion factor values for the current communication, wherein the set of emotion factor values comprises a determination value for the current communication, an inquisitiveness value for the current communication, a valence value for the current communication, and an aggression value for the current communication;

apply the set of emotion factor values for the current communication to an emotion classification model running on the one or more processors as input;

apply one or more historic sets of emotion factor values stored in a database to the emotion classification model as input, wherein the one or more historic sets of emotion factor values correspond to communication data of one or more historic communications associated with the customer over time, the historic communications occurring prior to the current communication; and

classify, using the emotion classification model, the current communication into an emotion state based on the set of emotion factor values for the current communication associated with the customer and the one or more historic sets of emotion factor values for the one or more historic communications associated with the customer.

2. The computing system of claim 1 , wherein the one or more processors are further configured to store the set of emotion factor values for the current communication in the database.

3. The computing system of claim 1 , wherein the set of machine learning models comprises a determination model trained to determine the determination value in the current communication, an inquisitiveness model trained to determine the inquisitiveness value in the current communication, a valence model trained to determine the valence value in the current communication, and an aggression model trained to determine the aggression value in the current communication.

4. The computing system of claim 3 , wherein to determine the determination value, the one or more processors are configured to:

apply the communication data for the current communication to the determination model as input; and

indicate, as output from the determination model, the determination value for the current communication.

5. The computing system of claim 3 , wherein to determine the inquisitiveness value, the one or more processors are configured to:

apply the communication data for the current communication to the inquisitiveness model as input; and

indicate, as output from the inquisitiveness model, the inquisitiveness value for the current communication.

6. The computing system of claim 3 , wherein to determine the valence value, the one or more processors are configured to:

apply the communication data for the current communication to the valence model as input; and

indicate, as output from the valence model, the valence value for the current communication.

7. The computing system of claim 3 , wherein to determine the aggression value, the one or more processors are configured to:

apply the communication data for the current communication to the aggression model as input; and

indicate, as output from the aggression model, the aggression value for the current communication.

8. The computing system of claim 1 , wherein each customer communication of the plurality of customer communications included in the set of training data comprises communication data and a set of labels indicating the set of emotion factor values for the customer communication.

9. The computing system of claim 1 , wherein the emotion classification model comprises a machine learning model, and wherein to classify the current communication into the emotion state, the one or more processors are configured to:

apply the set of emotion factor values for the current communication and the one or more historic sets of emotion factor values for the one or more historic communications to the emotion classification model as input; and

determine, as output from the emotion classification model, the emotion state for the current communication.

10. The computing system of claim 9 , wherein the set of training data comprises a first set of training data, and wherein the one or more processors are configured to:

create a second set of training data that includes a plurality of communications, wherein each communication of the plurality of communications comprises a corresponding set of emotion factor values and a label identifying an associated emotion state; and

train the machine learning model of the emotion classification model based on the second set of training data.

11. The computing system of claim 1 , wherein the one or more processors are further configured to transmit the emotion state to one or more agent devices for use in determining how to handle the current communication.

12. A method comprising:

creating, by one or more processors, a set of training data including a plurality of customer communications, each customer communication associated with at least one of a plurality of emotion factor values, wherein each emotion factor value of the plurality of emotion factor values indicates a measure of a different emotion factor in a communication;

training, by the one or more processors, each machine learning model of a set of machine learning models included in an emotion-based indexer, based on the set of training data, to determine the measure of the different emotion factor as a particular emotion factor value of the plurality of emotion factor values, wherein each machine learning model is trained to output the particular emotion factor value of the plurality of emotion factor values based on input communication data;

receiving, by the one or more processors, communication data of a current communication associated with a customer;

applying, by the one or more processors, the communication data to the emotion-based indexer running on the one or more processors as input;

generating, by the one or more processors, as output from the emotion-based indexer, a set of emotion factor values for the current communication, wherein the set of emotion factor values comprises a determination value for the current communication, an inquisitiveness value for the current communication, a valence value for the current communication, and an aggression value for the current communication;

applying, by the one or more processors, the set of emotion factor values for the current communication to an emotion classification model running on the one or more processors as input;

applying, by the one or more processors, one or more historic sets of emotion factor values stored in a database to the emotion classification model as input, wherein the one or more historic sets of emotion factor values correspond to communication data of one or more historic communications associated with the customer over time, the historic communications occurring prior to the current communication; and

classifying, by the one or more processors, using the emotion classification model, the current communication into an emotion state based on the set of emotion factor values for the current communication associated with the customer and the one or more historic sets of emotion factor values for the one or more historic communications associated with the customer.

13. The method of claim 12 , wherein the set of machine learning models comprises a determination model trained to determine the determination value in the current communication, an inquisitiveness model trained to determine the inquisitiveness value in the current communication, a valence model trained to determine the valence value in the current communication, and an aggression model trained to determine the aggression value in the current communication.

14. The method of claim 12 , wherein each customer communication of the plurality of customer communications included in the set of training data comprises communication data and a set of labels indicating the set of emotion factor values for the customer communication.

15. The method of claim 12 , wherein the emotion classification model comprises a machine learning model, and wherein classifying the current communication into an emotion state comprises:

applying the set of emotion factor values for the current communication and the one or more historic sets of emotion factor values for the one or more historic communications to the emotion classification model as input; and

determining, as output from the emotion classification model, the emotion state for the current communication.

16. The method of claim 15 , wherein the set of training data comprises a first set of training data, the method further comprising:

creating a second set of training data that includes a plurality of communications, wherein each communication of the plurality of communications comprises a corresponding set of emotion factor values and a label identifying an associated emotion state; and

training the machine learning model of the emotion classification model based on the second set of training data.

17. The method of claim 12 , further comprising transmitting the emotion state to one or more agent devices for use in determining how to handle the current communication.

18. A non-transitory computer-readable medium comprising instructions that, when executed, cause one or more processors to:

create a set of training data including a plurality of customer communications, each customer communication associated with at least one of a plurality of emotion factor values, wherein each emotion factor value of the plurality of emotion factor values indicates a measure of a different emotion factor in a communication;

train each machine learning model of a set of machine learning models included in an emotion-based indexer, based on the set of training data, to determine the measure of the different emotion factor as a particular emotion factor value of the plurality of emotion factor values, wherein each machine learning model is trained to output the particular emotion factor value of the plurality of emotion factor values based on input communication data;

receive communication data of a current communication associated with a customer;

apply the communication data to the emotion-based indexer running on the one or more processors as input;

generate, as output from the emotion-based indexer, a set of emotion factor values for the current communication, wherein the set of emotion factor values comprises a determination value for the current communication, an inquisitiveness value for the current communication, a valence value for the current communication, and an aggression value for the current communication;

apply the set of emotion factor values for the current communication to an emotion classification model running on the one or more processors as input;

apply one or more historic sets of emotion factor values stored in a database to the emotion classification model as input, wherein the one or more historic sets of emotion factor values correspond to communication data of one or more historic communications associated with the customer over time, the historic communications occurring prior to the current communication; and

classify, using the emotion classification model, the current communication into an emotion state based on the set of emotion factor values for the current communication associated with the customer and the one or more historic sets of emotion factor values for the one or more historic communications associated with the customer.

Assignments (2)

References Cited (97)

Cited By (1)

US 12,664,558