Cognitive analysis of public communications

Patent metadata

Field	Value
Publication number	US-11335336-B2
Application number	US-202016899003-A
Country	US
Kind code	B2
Filing date	Jun 11, 2020
Priority date	Jun 11, 2020
Publication date	May 17, 2022
Grant date	May 17, 2022

Abstract

Disclosed herein are system, method, and computer program product embodiments for categorizing customer complaints on social media using a model trained on customer voice calls or chats with agents. Additionally, users interested in monitoring regulatory compliance issues based on customer complaints can receive notifications regarding complaints that are linked to regulatory topic areas, without the need to manually scan vast numbers of social media postings.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
training, by the one or more computing devices, a customer complaints model using a first transcript of a first customer complaint, and a topic associated with a first tag of the first customer complaint, wherein the first transcript includes a conversation between a first customer and an agent, wherein the first customer complaint corresponds to a communication initiated by the first customer, and wherein the communication is associated with a selection made by the first customer when the communication was initiated, the method further comprising:
determining, by the one or more computing devices, the topic associated with the first customer complaint from the selection;
tagging, by the one or more computing devices, the first customer complaint with the first tag corresponding to the topic associated with the first customer complaint;
receiving, by the one or more computing devices, a plurality of social media messages from a social media service;
triggering, by the one or more computing devices, analysis of a social media message of the plurality of social media messages based on a mention of a company in the social media message;
parsing, by the one or more computing devices, the social media message to produce a second transcript of a second customer complaint; and
executing, by the one or more computing devices, the trained customer complaints model on the second transcript to produce a second tag according to a topic associated with the second customer complaint.

2. The computer-implemented method of claim 1 , further comprising:
receiving, by the one or more computing devices, an enforcement action associated with the topic associated with the second customer complaint;
mapping, by the one or more computing devices, the enforcement action to the second tag; and
associating, by the one or more computing devices, the enforcement action with the second transcript.

3. The computer-implemented method of claim 2 , further comprising:
storing, by the one or more computing devices, the second transcript in association with the second tag; and
retrieving, by the one or more computing devices, the second transcript from storage by a lookup of the second tag, responsive to receiving the enforcement action.

4. The computer-implemented method of claim 3 , further comprising:
notifying, by the one or more computing devices, a subscriber associated with the topic associated with the second customer complaint of the enforcement action and the second customer complaint responsive to the associating the enforcement action with the second transcript.

5. The computer-implemented method of claim 1 , further comprising:
performing, by the one or more computing devices, speech-to-text processing on a recording of the conversation corresponding to the first customer complaint to produce the first transcript; and
parsing, by the one or more computing devices, the first transcript to remove text corresponding to a portion of the conversation spoken by the agent.

6. The computer-implemented method of claim 1 , wherein the mention of the company comprises tagging the company in the social media message using a social media handle associated with the company.

7. A system, comprising:
a memory configured to store operations; and
one or more processors configured to perform the operations, the operations comprising:
training a customer complaints model using a first transcript of a first customer complaint, and a topic associated with a first tag of the first customer complaint, wherein the first customer complaint corresponds to a communication initiated by a customer, and wherein the communication is associated with a selection made by the customer when the communication was placed, the operations further comprising:
determining the topic associated with the first customer complaint from the selection;
tagging the first customer complaint with the first tag corresponding to the topic associated with the first customer complaint;
receiving a second transcript of a second customer complaint;
executing the trained customer complaints model on the second transcript to produce a second tag according to a topic associated with the second customer complaint;
receiving an enforcement action associated with the topic associated with the second customer complaint;
mapping the enforcement action to the second tag; and
associating the enforcement action with the second transcript.

8. The system of claim 7 , the operations further comprising:
storing the second transcript in association with the second tag; and
retrieving the second transcript from storage by a lookup of the second tag, responsive to receiving the enforcement action.

9. The system of claim 8 , the operations further comprising:
notifying a subscriber associated with the topic associated with the second customer complaint of the enforcement action and the second customer complaint responsive to the associating the enforcement action with the second transcript.

10. The system of claim 7 , the operations further comprising:
performing speech-to-text processing on a recording of the communication corresponding to the first customer complaint to produce the first transcript, wherein the recording of the communication includes a conversation between a customer and an agent; and
parsing the first transcript to remove text corresponding to a portion of the conversation spoken by the agent.

11. The system of claim 7 , the operations further comprising:
receiving a plurality of social media messages from a social media service;
triggering analysis of a social media message of the plurality of social media messages based on a mention of a company in the social media message; and
parsing the social media message to produce the second transcript.

12. The system of claim 11 , wherein the mention of the company comprises tagging the company in the social media message using a social media handle associated with the company.

13. A computer readable storage device having instructions stored thereon, execution of which, by one or more processing devices, causes the one or more processing devices to perform operations comprising:
training a customer complaints model using a first transcript of a first customer complaint, and a topic associated with a first tag of the first customer complaint, wherein the first transcript includes a conversation between a first customer and an agent wherein the first customer complaint corresponds to a communication initiated by the first customer, and wherein the communication is associated with a selection made by the first customer when the communication was initiated, the operations further comprising:
determining the topic associated with the first customer complaint from the selection;
tagging the first customer complaint with the first tag corresponding to the topic associated with the first customer complaint;
receiving a plurality of social media messages from a social media service;
triggering analysis of a social media message of the plurality of social media messages based on a mention of a company in the social media message;
parsing the social media message to produce a second transcript of a second customer complaint; and
executing the trained customer complaints model on the second transcript to produce a second tag according to a topic associated with the second customer complaint.

14. The computer readable storage device of claim 13 , the operations further comprising:
receiving an enforcement action associated with the topic associated with the se

Assignees

• Capital One Services Llc

Inventors

• Kumar Lokesh Vijay
• Raju Poornima Bagare
• Chowdhury Rhic
• Mangal Nimish
• Adair Jacob
• Demchalk Chris
• Aggarwal Lavika
• Sinha Nishant

Classifications

• G06Q10/40 Primary

  Business processes related to social networking or social networking services · CPC title

• H04M3/5175

  Call or contact centers supervision arrangements · CPC title

• G06N20/00

  Machine learning · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G06Q30/016

  After-sales · CPC title