US 12,223,511 B1
Emotion analysis using deep learning model
Abhishek Kumar, Bangalore (IN); Amit Agarwal, Bangalore (IN); Dipanjan Deb, Bangalore (IN); and Naveen Gururaja Yeri, Bangalore (IN)
Assigned to Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Nov. 23, 2021, as Appl. No. 17/456,334.
Int. Cl. G06Q 30/016 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 40/20 (2022.01)
CPC G06Q 30/016 (2013.01) [G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 40/20 (2022.01)] 18 Claims
OG exemplary drawing
 
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.