Automated QA Question Generation for Chat Session Information Sharing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In electronic communication systems, customer service representatives often need to manually share information between chat sessions, which is time-consuming and inefficient, especially when they need to recognize pertinent information that could quickly resolve customer issues.

Innovation Solution

A method and system that automatically generate questions and share content between communication sessions using a Question and Answer (QA) system, allowing for automated extraction and insertion of information from one session into another, leveraging natural language processing (NLP) to assist in problem resolution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual information sharing between chat sessions is used, then information can be transferred between sessions, but time consumption and operational effort increase significantly

Engineering Contradiction:

Improveinformation sharing efficiencyVSAvoidtime for manual information transfer

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system automatically monitors chat sessions, extracts relevant information, generates questions, and retrieves answers without requiring manual user intervention. The CSR simply initiates the process by indicating information needs, and the system handles the entire information retrieval and sharing workflow autonomously.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of copying and pasting information between chat sessions is replaced with an automated electronic system that uses natural language processing, question generation, and automated information retrieval to transfer information between sessions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Difficulty of detecting and measuring

If manual monitoring of chat content is performed, then pertinent information can be identified, but operational complexity and time requirements increase

Engineering Contradiction:

Improveinformation recognition accuracyVSAvoidoperational simplicity

Core Design Contradiction:

Difficulty of detecting and measuringVSEase of operation

Solution Approach 1:

Manual monitoring and analysis of chat content by human operators is replaced with automated natural language processing systems that can rapidly analyze chat transcripts, identify relevant information, and generate appropriate questions for the QA system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

An automated intermediary system is introduced between the chat sessions and the information retrieval process. This intermediary automatically monitors chat content, determines when additional information is needed, generates questions, and retrieves answers, simplifying the operator's task while maintaining high information recognition accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automated question generation is implemented, then information retrieval efficiency improves, but system complexity increases

Engineering Contradiction:

Improveinformation retrieval speedVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system integrates multiple functions into a unified automated workflow: chat monitoring, information need detection, question generation, answer retrieval, and automatic sharing between sessions. This multi-functional integration improves productivity while managing complexity through a cohesive system architecture.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The automated question generation system serves as an intermediary layer between the chat monitoring function and the QA system. It automatically transforms chat content into structured questions, enabling efficient information retrieval without requiring complex direct integration between all system components.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10275448B2Automatic question generation and answering based on monitored messaging sessions

Publication Date: 2019.04.30 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Mechanisms are provided, in a first computing device, for sharing content of communication sessions. The mechanisms establish a first communication session between the first computing device and a second computing device. The first computing device is operated by a first user and the second computing device is operated by a second user. The apparatus establishes, in response to content of the first communication session indicating subject matter for which additional information is desired by at least one of the first user or the second user, a second communication session between the first computing device and a question and answer (QA) system. In response to an input by the first user requesting sharing of information, the first computing device automatically copies a portion of content of the first communication session to the second communication session as an input question submitted to the QA system.