Meeting Summary Generator Using Featural Script Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional systems for generating meeting minutes are cumbersome due to the need for advance preparation using pre-defined minutes blueprints, which requires significant time and effort.

Innovation Solution

A summary generating device that includes a featural script extracting unit, a segment candidate generating unit, and a structuring estimating unit, which extracts featural script information from voice data, generates segment candidates, and estimates structure information to automatically create a summary document in a format-structured text format based on voice recognition and morphological analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If a minutes blueprint is prepared in advance to create meeting minutes, then the structure and organization of minutes can be ensured, but the advance preparation becomes a cumbersome task requiring significant time and effort

Engineering Contradiction:

Improvestructure organization of minutesVSAvoidadvance preparation time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically generating a minutes blueprint before the meeting based on the meeting topic and participants. This pre-generated blueprint includes anticipated discussion points and structure, eliminating the need for manual advance preparation while ensuring proper organization of minutes

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service by automatically creating and updating the minutes blueprint during the meeting based on real-time speech recognition and analysis. The blueprint adapts itself to the actual discussion flow without requiring manual intervention, thus reducing preparation time while maintaining structural organization

Inventive Principle:

Principle #25Self-service

2Manufacturing precision

If manual creation of meeting minutes is performed to ensure accuracy and completeness, then the quality of minutes can be maintained, but the process requires significant time and effort

Engineering Contradiction:

Improvequality of minutesVSAvoidminutes creation efficiency

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system replaces the mechanical manual process of creating minutes with an automated speech recognition and natural language processing system. The featural script extracting unit, segment candidate generating unit, and structuring estimating unit work together to automatically generate accurate and complete minutes, maintaining quality while dramatically improving productivity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary processing layer between the meeting speech and the final minutes. This intermediary layer includes multiple processing units that analyze speech patterns, extract key information, and generate structured minutes, ensuring both accuracy and efficiency in the minutes creation process

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If conventional speech recognition technology is used to document meeting remarks, then voice-to-text conversion can be achieved, but the output lacks proper structure and organization

Engineering Contradiction:

Improvevoice documentation automationVSAvoidstructure of output text

Core Design Contradiction:

Extent of automationVSManufacturing precision

Solution Approach 1:

The system segments the continuous speech output into structured components using the featural script extracting unit to identify key information elements, the segment candidate generating unit to create potential structure units, and the structuring estimating unit to organize these segments into a coherent hierarchical structure with proper headings, subheadings, and content organization

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts the structure of the minutes based on the actual content and flow of the meeting discussion. The structuring estimating unit adapts the blueprint structure in real-time to match the discussed topics, ensuring the output maintains proper organization while reflecting the dynamic nature of the meeting content

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS10540987B2Summary generating device, summary generating method, and computer program product

Publication Date: 2020.01.21 KK TOSHIBA

AI summary

A summary generating device includes a featural script extracting unit, a segment candidate generating unit, and a structuring estimating unit. The featural script extracting unit extracts featural script information of the words included in text information. Based on the extracted feature script information, the segment candidate generating unit generates candidates of segments that represent the constitutional units for the display purpose. Based on the generated candidates of segments and based on an estimation model for structuring, the structuring estimating unit estimates structure information containing information ranging from information of a comprehensive structure level to information of a local structure level.