Meeting Comment Recording Apparatus with Keyword Matrix Display

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing meeting information recording and playback systems face difficulties in detailed search and retrieval of specific topics or content due to the need for users to remember contextual information and cannot be used during in-progress meetings since minutes have not been prepared.

Innovation Solution

A comment recording apparatus with a voice input device, voice recognition unit, morphological analysis unit, and display generation unit that registers and displays keywords related to topics and participants, allowing for efficient keyword extraction and visualization in a matrix format.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If an algorithm that refers to other comment-delivering participants who have delivered comments before and after the relevant comment-delivering participant is used, then the system can process meeting information, but it becomes difficult to search a particular topic and/or content in more detail because a user needs to remember the context in which one or more relevant comments were delivered

Engineering Contradiction:

Improveease of searchVSAvoidcontext dependency

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent extracts keywords from the original comment text through voice recognition and morphological analysis, separating the essential searchable content from the contextual narrative. This allows users to search for specific topics without needing to remember the full context in which comments were delivered.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system segments the continuous voice data into discrete keywords and organizes them into a matrix structure with topics as rows and participants as columns. This segmentation transforms the contextual comment stream into structured, searchable units that can be accessed independently of their original context.

Inventive Principle:

Principle #1Segmentation

2Productivity

If minutes of meeting are used for keyword extraction, then the system can generate segment information for a same speaker and a same topic, but such system cannot be used for an in-progress meeting because minutes of meeting is not yet been prepared

Engineering Contradiction:

Improveinformation re-useVSAvoiddelay in availability

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary voice recognition and keyword extraction on comment voice as it is being delivered during the meeting, rather than waiting for minutes to be prepared afterward. This preliminary processing enables real-time or near-real-time availability of searchable keywords while the meeting is still in progress.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the manual process of preparing minutes with an automated voice recognition and morphological analysis system. This substitution eliminates the time delay associated with manual minute preparation and enables automatic keyword generation from spoken comments during the meeting itself.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If voice data is registered for each topic and participant with voice recognition and morphological analysis, then detailed search becomes possible, but the device complexity increases

Engineering Contradiction:

Improvesearch precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs a multi-functional integrated system where the voice recognition unit, morphological analysis unit, and keyword extraction functionality are combined into a single comment recording apparatus. This universal device performs multiple functions (voice-to-text conversion, linguistic analysis, keyword extraction, and database organization) without requiring separate specialized systems for each function.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS8862473B2Comment recording apparatus, method, program, and storage medium that conduct a voice recognition process on voice data

Publication Date: 2014.10.14 RICOH CO LTD

AI summary

A comment recording apparatus, including a voice input device and a voice output device for recording and playing back comment voice, includes a voice obtaining unit, a voice recognition unit, a morphological analysis unit, and a display generation unit. The voice obtaining unit obtains comment voice as voice data, and registers the obtained voice data to a voice database for each topic specified by a topic specification device and each comment-delivered participant identified from the voice data. The voice recognition unit conducts a voice recognition process on the voice data to obtain text information. The morphological analysis unit conducts a morphological analysis on the text information, and registers a keyword extracted from words obtained by the morphological analysis unit to a keyword database with topic and comment-delivered participant along with voice. The display generation unit displays the keyword in a matrix while relating the keyword to a topic and a comment-delivering participant.