Primary topic identification in text data

Patent metadata

Field	Value
Publication number	US-12248752-B2
Application number	US-202117303231-A
Country	US
Kind code	B2
Filing date	May 25, 2021
Priority date	May 25, 2021
Publication date	Mar 11, 2025
Grant date	Mar 11, 2025

Abstract

An approach for directing a chat agent for an online discussion is provided. A processor retrieves message data from a messaging program. A processor identifies at least one topic present in the message data. A processor, responsive to a determination that the at least one topic is a primary topic, updates the chat agent with the primary topic. A processor modifies message data based on the determined primary topic.

First claim

What is claimed is:

1. A computer-implemented method for directing a chat agent for an online discussion, the method comprising:
retrieving message data and collaborative data from a messaging program;
identifying a plurality of topics present in the message data using topic modeling;
determining a respective topic distance for each of the plurality of the topics present in the message data, wherein the respective topic distance for each of the plurality of the topics is a geodesic distance between two or more messages directed towards a respective topic and a cosine similarity of the two or more messages;
determining a collaborative distance between two or more participants discussing a respective topic for each of the plurality of the topics, wherein the collaborative distance is based on a role assigned to at least one participant in the message data and a frequency of communication between the two or more participants;
analyzing each of the plurality of the topics to determine one or more likelihood probabilities that indicate whether a respective topic is a primary topic or a secondary topic based on the collaborative distances and the respective topic distances for each of the plurality of the topics;
combining each of the plurality of the topic's respective one or more likelihood probabilities to calculate a combined likelihood for each of the plurality of the topics;
comparing each of the plurality of the topic's combined likelihood to a determined threshold value to determine if a respective topic is a primary topic or a secondary topic; and
modifying the message data to designate each of the plurality of the topics as a primary topic or a secondary topic.

2. The computer-implemented method of claim 1 , wherein modifying message data further comprises:
highlighting, by one or more processors, text within the message data that is related to the primary topic.

3. The computer-implemented method of claim 1 , wherein modifying message data further comprises:
responding, by one or more processors, to a new message directed towards the primary topic.

4. The computer-implemented method of claim 1 , wherein modifying message data further comprises:
summarizing, by one or more processors, message data directed towards the primary topic.

5. The computer-implemented method of claim 1 , further comprising:
training the chat agent to assist in interacting with participants of the messaging program using previously determined primary topics and secondary topics;
determining content of each message in the message data; and
processing a participant-submitted question and the determined content of each of the messages through the trained chat agent to assist in an interaction between two or more participants of the online messaging program.

6. The computer-implemented method of claim 5 , further comprising:
processing each of the messages in the message data through the trained chat agent to summarize each of the messages.

7. A computer program product for directing a chat agent for an online discussion, the computer program product comprising:
one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:
program instructions to retrieve message data and collaborative data from a messaging program;
program instructions to identify a plurality of topics present in the message data using topic modeling;
program instructions to determine a respective topic distance for each of the plurality of the topics present in the message data, wherein the respective topic distance for each of the plurality of the topics is a geodesic distance between two or more messages directed towards a respective topic and a cosine similarity of the two or more messages;
program instructions to determine a collaborative distance between two or more participants discussing a respective topic for each of the plurality of the topics, wherein the collaborative distance is based on a role assigned to at least one participant in the message data and a frequency of communication between the two or more participants;
program instructions to analyze each of the plurality of the topics to determine one or more likelihood probabilities that indicate whether a respective topic is a primary topic or a secondary topic based on the collaborative distances and the respective topic distances for each of the plurality of the topics;
program instructions to combine each of the plurality of the topic's respective one or more likelihood probabilities to calculate a combined likelihood for each of the plurality of the topics;
program instructions to compare each of the plurality of the topic's combined likelihood to a determined threshold value to determine if a respective topic is a primary topic or a secondary topic; and
program instructions to modify the message data to designate each of the plurality of the topics as a primary topic or a secondary topic.

8. The computer program product of claim 7 , wherein program instructions to modify message data further comprises:
program instructions to highlight text within the message data that is related to the primary topic.

9. The computer program product of claim 7 , wherein program instructions to modify message data further comprises:
program instructions to respond to a new message directed towards the primary topic.

10. The computer program product of claim 7 , wherein program instructions to modify message data further comprises:
program instructions to summarize message data directed towards the primary topic.

11. The computer program product of claim 7 , further comprising:
program instructions to train the chat agent to assist in interacting with participants of the messaging program using previously determined primary topics and secondary topics;
program instructions to determine content of each message in the message data; and
program instructions process a participant-submitted question and the determined content of each of the messages through the trained chat agent to assist in an interaction between two or more participants of the online messaging program.

12. The computer program product of claim 11 , further comprising:
program instructions to process each of the messages in the message data through the trained chat agent to summarize each of the messages.

13. A computer system for directing a chat agent for an online discussion, the computer system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to retrieve message data and collaborative data from a messaging program;
program instructions to identify a plurality of topics present in the message data using topic modeling;
program instructions to determine a respective topic distance for each of the plurality of the topics present in the message data, wherein the respective topic distance for each of the plurality of the topics is a geodesic distance between two or more messages directed towards a respective topic and a cosine similarity of the two or more messages;
program instructions to determine a collaborative distance between two or more participants discussing a respective topic for each of the plurality of the topics, wherein the collaborative distance is based on a role assigned to at least one participant in the message data and a frequency of communication between the two or more participants;
program inst

Assignees

• IBM

Inventors

• Kochura Nadiya
• Lu Fang
• Anders Kelley
• Dunne Jonathan D

Classifications

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06F40/194

  Calculation of difference between files · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title