Predictive Communication System

• US 20190095927A1
• Filed: 09/28/2017
• Published: 03/28/2019
• Est. Priority Date: 09/28/2017
• Status: Abandoned Application

• Current Assignee: American Express Travel Related Services Company, Inc. (American Express Company)
• Original Assignee: American Express Travel Related Services Company, Inc. (American Express Company)
• Inventors: Shimpi, Sushil S., Colton, Tyler C., Varma, Meera Girija, Moriarty, Glenn S., Peters, Matthew B., Jandhyala, Padma D.
• Application Number:
  US15/719,327
• Publication Number:
  US 20190095927A1
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

The method includes receiving a communication from a customer; identifying a customer profile associated with the customer; accessing account activity data associated with the customer profile; analyzing the account activity data; and/or determining an intent prediction associated with the communication based on the analyzing the account activity data, wherein the intent prediction comprises a predicted reason for the communication.

Claims

1. A method, comprising:

receiving, by a processor, a communication from a customer;

identifying, by the processor, a customer profile associated with the customer;

accessing, by the processor, account activity data associated with the customer profile;

analyzing, by the processor, the account activity data; and

determining, by the processor, an intent prediction associated with the communication based on the analyzing the account activity data, wherein the intent prediction comprises a predicted reason for the communication.

2. The method of claim 1, further comprising:

presenting, by the processor, the intent prediction to the customer; and

receiving, by the processor, an accuracy response from the customer in response to the presenting the intent prediction.

3. The method of claim 2, further comprising routing, by the processor, the communication to a service system based on the intent prediction.

4. The method of claim 3, further comprising:

detecting, by the processor, completion of an action;

determining, by the processor, a recommended action based on the analyzing the account activity data; and

presenting, by the processor, the recommended action to the customer after the detecting the completion of the action.

5. The method of claim 1, wherein the determining the intent prediction of the customer comprises:

ranking, by the processor, a plurality of intent insights comprised in the account activity data, producing a ranking of the plurality of intent insights; and

determining, by the processor, the intent prediction by identifying, by the processor, a highest ranking intent insight of the plurality of intent insights.

6. The method of claim 5, wherein the determining the intent prediction further comprises:

determining, by the processor, a priority insight of the plurality of intent insights; and

adjusting, by the processor, the ranking of the plurality of intent insights based on a priority insight such that the priority insight is the highest ranking intent insight of the plurality of intent insights.

7. The method of claim 5, wherein the ranking the plurality of intent insights comprises ranking the plurality of intent insights in chronological order, wherein a most recent intent insight comprises a highest rank.

8. The method of claim 3, further comprising transmitting, by the processor, a context message to an operator of the service system receiving the communication in the response to the routing.

9. An article of manufacture including a non-transitory, tangible computer readable storage medium having instructions stored thereon that, in response to execution by a processor of a processing machine, cause the processor to perform operations comprising:

receiving, by the processor, a communication from a customer;

identifying, by the processor, a customer profile associated with the customer;

accessing, by the processor, account activity data associated with the customer profile;

analyzing, by the processor, the account activity data; and

determining, by the processor, an intent prediction associated with the communication based on the analyzing the account activity data, wherein the intent prediction comprises a predicted reason for the communication.

10. The article of claim 9, wherein the operations further comprise:

presenting, by the processor, the intent prediction to the customer; and

receiving, by the processor, an accuracy response from the customer in response to the presenting the intent prediction.

11. The article of claim 10, wherein the operations further comprise routing, by the processor, the communication to a service system based on the intent prediction.

12. The article of claim 11, wherein the operations further comprise:

detecting, by the processor, completion of an action;

determining, by the processor, a recommended action based on the analyzing the account activity data; and

presenting, by the processor, the recommended action to the customer after the detecting the completion of the action.

13. The article of claim 9, wherein the determining the intent prediction of the customer comprises:

ranking, by the processor, a plurality of intent insights comprised in the account activity data, producing a ranking of the plurality of intent insights; and

determining, by the processor, the intent prediction by identifying, by the processor, a highest ranking intent insight of the plurality of intent insights.

14. The article of claim 13, wherein the determining the intent prediction further comprises:

determining, by the processor, a priority insight of the plurality of intent insights; and

adjusting, by the processor, the ranking of the plurality of intent insights based on a priority insight such that the priority insight is the highest ranking intent insight of the plurality of intent insights.

15. The article of claim 13, wherein the ranking the plurality of intent insights comprises ranking the plurality of intent insights in chronological order, wherein a most recent intent insight comprises a highest rank.

16. The article of claim 11, wherein the operations further comprise transmitting, by the processor, a context message to an operator of the service system receiving the communication in the response to the routing.

17. A system comprising:

a processor of a processing machine,

a tangible, non-transitory memory configured to communicate with the processor,

the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the processor, cause the processor to perform operations comprising;

receiving, by the processor, a communication from a customer;

identifying, by the processor, a customer profile associated with the customer;

accessing, by the processor, account activity data associated with the customer profile;

analyzing, by the processor, the account activity data; and

determining, by the processor, an intent prediction associated with the communication based on the analyzing the account activity data, wherein the intent prediction comprises a predicted reason for the communication.

18. The system of claim 17, wherein the operations further comprise:

presenting, by the processor, the intent prediction to the customer; and

receiving, by the processor, an accuracy response from the customer in response to the presenting the intent prediction.

19. The system of claim 18, wherein the operations further comprise routing, by the processor, the communication to a service system based on the intent prediction.

20. The system of claim 17, wherein the determining the intent prediction of the customer comprises:

ranking, by the processor, a plurality of intent insights comprised in the account activity data, producing a ranking of the plurality of intent insights; and

determining, by the processor, the intent prediction by identifying, by the processor, a highest ranking intent insight of the plurality of intent insights.