Cognitive analysis of public communications

Patent metadata

Field	Value
Publication number	US-11935522-B2
Application number	US-202217745130-A
Country	US
Kind code	B2
Filing date	May 16, 2022
Priority date	Jun 11, 2020
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

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:
filtering, by one or more computing devices, a plurality of social media messages received from a social media scraping service based on a company name mentioned within the social media message, the filtering generating a stream of company specific social media messages, wherein the social media scraping service is configured to connect to a plurality of social media platforms to be scraped;
storing, by a content media loader, the stream of company specific social media messages as transcripts into a customer complaints database;
executing, by the one or more computing devices, a trained complaints model on the transcripts of the company specific social media messages to identify a topic associated with the company specific social media messages; and
notifying, by the one or more computing devices, a subscriber associated with the topic associated with the company specific social media messages of an enforcement action associated with the topic that is associated with the company specific social media messages.

2. The computer-implemented method of claim 1 , wherein the trained complaints model is trained using customer complaint data tagged with associated topics through supervised machine learning.

3. The computer-implemented method of claim 2 , wherein the customer complaint data further comprises any of: customer chat messages or customer voice calls.

4. The computer-implemented method of claim 1 , wherein the enforcement action references a regulatory mandate or sub-mandate associated with one or more regulatory requirements.

5. The computer-implemented method of claim 1 , further comprising:
relating the enforcement action to the company specific social media messages by common topics.

6. The computer-implemented method of claim 1 , further comprising:
requesting a complaint service to provide an uncategorized transcript to the trained complaints model and receiving a response tag according to a topic associated with a customer complaint within the uncategorized transcript.

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

8. A system comprising:
a memory configured to store operations; and
one or more processors configured to perform the operations, the operations comprising:
filtering, by one or more computing devices, a plurality of social media messages received from a social media scraping service based on a company name mentioned within the social media message, the filtering generating a stream of company specific social media messages wherein the social media scraping service is configured to connect to a plurality of social media platforms to be scraped;
storing, by a content media loader, the stream of company specific social media messages as transcripts into a customer complaints database;
executing, by the one or more computing devices, a trained complaints model on the transcripts of the company specific social media messages to identify a topic associated with the company specific social media messages; and
notifying, by the one or more computing devices, a subscriber associated with the topic associated with the company specific social media messages of an enforcement action associated with the topic that is associated with the company specific social media messages.

9. The system of claim 8 , wherein the trained complaints model is trained using customer complaint data tagged with associated topics through supervised machine learning.

10. The system of claim 9 , wherein the customer complaint data further comprises any of: customer chat messages or customer voice calls.

11. The system of claim 8 , wherein the enforcement action references a regulatory mandate or sub-mandate associated with one or more regulatory requirements.

12. The system of claim 8 , the operations further comprising:
relating the enforcement action to the company specific social media messages by common topics.

13. The system of claim 8 , wherein the executing the trained complaints model further comprising: requesting a complaint service to provide an uncategorized transcript to the trained complaints model and receiving a response tag according to the topic associated with a customer complaint within the uncategorized transcript.

14. The system of claim 8 , the system further comprising:
a complaints notification service allowing a user to register for notifications, and receive those notifications for a given topic, whenever the enforcement action is received that matches a complaint by the topic.

15. 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:
filtering, by one or more computing devices, a plurality of social media messages received from a social media scraping service based on a company name mentioned within the social media message, the filtering generating a stream of company specific social media messages, wherein the social media scraping service is configured to connect to a plurality of social media platforms to be scraped;
storing, by a content media loader, the stream of company specific social media messages as transcripts into a customer complaints database;
executing, by the one or more computing devices, a trained complaints model on the transcripts of the company specific social media messages to identify a topic associated with the company specific social media messages; and
notifying, by the one or more computing devices, a subscriber associated with the topic associated with the company specific social media messages of an enforcement action associated with the topic that is associated with the company specific social media messages.

16. The computer readable storage device of claim 15 , the operations further comprising: requesting a complaint service to provide an uncategorized transcript to the trained complaints model and receive a response tag according to the topic associated with a customer complaint within the uncategorized transcript.

17. The computer readable storage device of claim 15 , the operations further comprising: relating the enforcement action to the company specific social media messages by common topics.

18. The computer readable storage device of claim 15 , wherein the enforcement action references a regulatory mandate or sub-mandate associated with one or more regulatory requirements.

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

• G10L15/1822 Primary

  Parsing for meaning understanding · CPC title

• G06F16/93

  Document management systems · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/016

  After-sales · CPC title