Complaint prioritization using deep learning model

1. A computing system comprising:

a memory; and

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

receive a set of emotion factor values for communication data of a current service inquiry associated with a customer, wherein the set of emotion factor values comprises a determination value for the current service inquiry, an inquisitiveness value for the current service inquiry, a valence value for the current service inquiry, and an aggression value for the current service inquiry, wherein each emotion factor value indicates a measure of a particular emotion factor in the current service inquiry;

generate, using an emotion priority model running on the one or more processors, an emotional priority score for the current service inquiry based on the set of emotion factor values for the current service inquiry associated with the customer; and

determine a response priority order for the current service inquiry based on at least the emotional priority score for the current service inquiry.

2. The computing system of claim 1 , wherein the one or more processors are further configured to:

receive the communication data of the current service inquiry;

apply the communication data to an emotion-based indexer as input, wherein the emotion-based indexer includes a set of machine learning models, each machine learning model trained to determine the measure of the particular emotion factor in the current service inquiry;

generate, as output from the emotion-based indexer, the set of emotion factor values for the current service inquiry; and

store the set of emotion factor values for the current service inquiry in a database.

3. The computing system of claim 1 , wherein the one or more processors are configured to determine the emotional priority score for the current service inquiry based on the set of emotion factor values for the current service inquiry and one or more historic sets of emotion factor values stored in a database, wherein the one or more historic sets of emotion factor values correspond to communication data of one or more historic service inquiries associated with the customer over time, the historic service inquiries occurring prior to the current service inquiry.

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

compute one or more composite scores for the set of emotion factor values for the current service inquiry and for each of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

determine the emotional priority score based on the one or more composite scores for the customer over time.

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

determine a difference between the set of emotion factor values for the current service inquiry and at least one of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

generate an alert in response to the difference exceeding a threshold.

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

extract one or more of aggression values or determination values from the set of emotion factor values for the current service inquiry and from each of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

determine the emotional priority score based on the one or more of the aggression values or the determination values for the customer over time.

7. The computing system of claim 3 , wherein the emotion priority model comprises a machine learning model, and wherein to determine the emotional priority score for the current service inquiry, the one or more processors are configured to:

apply the set of emotion factor values for the current service inquiry and the one or more historic sets of emotion factor values for the historic service inquiries associated with the customer to the emotion priority model as input; and

determine, as output from the emotion priority model, the emotional priority score for the current service inquiry.

8. The computing system of claim 3 , wherein each set of the one or more historic sets of emotion factor values corresponding to the communication data of the one or more historic service inquiries comprise one or more of:

a determination value for the communication data;

an inquisitiveness value for the communication data;

a valance value for the communication data; and

an aggression value for the communication data.

9. The computing system of claim 1 , wherein the emotion priority model comprises a machine learning model, and wherein to determine the emotional priority score for the current service inquiry, the one or more processors are configured to:

apply the set of emotion factor values for the current service inquiry to the emotion priority model as input; and

determine, as output from the emotion priority model, the emotional priority score for the current service inquiry.

10. The computing system of claim 9 , wherein the one or more processors are configured to:

create a set of training data that includes a plurality of service inquiries, wherein each service inquiry of the plurality of service inquiries comprises a corresponding set of emotion factor values and a label identifying an associated emotional priority score; and

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

11. The computing system of claim 1 , wherein, to determine the response priority order for the current service inquiry, the one or more processors are configured to:

determine a severity level for the current service inquiry based on the emotional priority score of the current service inquiry; and

classify the current service inquiry into the response priority order based on the determined severity level for the current service inquiry.

12. A method comprising:

receiving, by one or more processors, a set of emotion factor values for communication data of a current service inquiry associated with a customer, wherein the set of emotion factor values comprises a determination value for the current service inquiry, an inquisitiveness value for the current service inquiry, a valence value for the current service inquiry, and an aggression value for the current service inquiry, wherein each emotion factor value indicates a measure of a particular emotion factor in the current service inquiry;

generating, using an emotion priority model running on the one or more processors, an emotional priority score for the current service inquiry based on the set of emotion factor values for the current service inquiry associated with the customer; and

determining a response priority order for the current service inquiry based on at least the emotional priority score.

13. The method of claim 12 , further comprising:

receiving, by the one or more processors, the communication data of the current service inquiry;

applying the communication data to an emotion-based indexer as input, wherein the emotion-based indexer includes a set of machine learning models, each machine learning model trained to determine the measure of the particular emotion factor in the current service inquiry;

generating, as output from the emotion-based indexer, the set of emotion factor values for the current service inquiry; and

storing the set of emotion factor values for the current service inquiry in a database.

14. The method of claim 12 , wherein determining the emotional priority score for the current service inquiry is further based on the set of emotion factor values for the current service inquiry and one or more historic sets of emotion factor values stored in a database, wherein the one or more historic sets of emotion factor values correspond to communication data of one or more historic service inquiries associated with the customer over time, the historic service inquiries occurring prior to the current service inquiry.

15. The method of claim 14 , wherein determining the emotional priority score further comprises:

computing one or more composite scores for the set of emotion factor values for the current service inquiry and for each of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

determining the emotional priority score based on the one or more composite scores for the customer over time.

16. The method of claim 14 , further comprising:

determining a difference between the set of emotion factor values for the current service inquiry and at least one of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

generating an alert in response to the difference exceeding a threshold.

17. The method of claim 14 , wherein determining the emotional priority score further comprises:

extracting one or more of aggression values or determination values from the set of emotion factor values for the current service inquiry and from each of the historic sets of emotion factor values for the historic service inquiries associated with the customer; and

determining the emotional priority score based on the one or more of the aggression values or the determination values for the customer over time.

18. The method of claim 14 , wherein the emotion priority model comprises a machine learning model, and wherein determining the emotional priority score for the current service inquiry comprises:

applying the set of emotion factor values for the current service inquiry and the one or more historic sets of emotion factor values for the historic service inquiries associated with the customer to the emotion priority model as input; and

determining, as output from the emotion priority model, the emotional priority score for the current service inquiry.

19. The method of claim 12 , wherein the emotion priority model comprises a machine learning model, and wherein determining the emotional priority score for the current service inquiry further comprises:

applying the set of emotion factor values for the current service inquiry to the emotion priority model as input;

determining, as output from the emotion priority model, the emotional priority score for the current service inquiry.

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

receive a set of emotion factor values for communication data of a current service inquiry associated with a customer, wherein the set of emotion factor values comprises a determination value for the current service inquiry, an inquisitiveness value for the current service inquiry, a valence value for the current service inquiry, and an aggression value for the current service inquiry, wherein each emotion factor value indicates a measure of a particular emotion factor in the current service inquiry;

determine, using an emotion priority model running on the one or more processors, an emotional priority score for the current service inquiry based on the set of emotion factor values for the current service inquiry associated with the customer; and

determine a response priority order for the current service inquiry based on at least the emotional priority score for the current service inquiry.