Voice Recognition Processing Device with Missing Information Complement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current voice recognition systems face challenges in improving user operativity, particularly in handling incomplete voice commands and queries, where missing information needs to be complemented to perform effective processing.

Innovation Solution

A voice recognition processing apparatus and method that includes a voice acquirer, first and second voice recognizers, a sorter, and a processor, which acquires and converts voice information, sorts and stores relevant data, and complements missing information using stored data to perform processing, enhancing user operativity by enabling efficient command recognition and keyword processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If voice recognition systems require complete and accurate voice commands for processing, then processing accuracy is improved, but user operativity deteriorates due to the need to repeat previous inputs

Engineering Contradiction:
Improvevoice command accuracyVSAvoiduser operativity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system performs preliminary voice recognition and stores recognized information (keywords, commands, results) in advance. When a new voice command is received, the system retrieves and complements missing information from previously stored data, eliminating the need for users to repeat inputs while maintaining processing accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by storing recognition results and using them to complement subsequent voice commands. The processor retrieves previously recognized information and integrates it with new voice inputs, creating a feedback loop that improves both user operativity and maintains accuracy through information complementation.

Inventive Principle:
Principle #23Feedback

2Device complexity

If voice recognition systems process each command independently without using previous inputs, then processing simplicity is maintained, but user operativity deteriorates due to increased complexity in continuous operations

Engineering Contradiction:
Improveprocessing simplicityVSAvoiduser operativity
Core Design Contradiction:
Device complexityVSEase of operation

Solution Approach 1:

The system performs preliminary processing by storing recognized voice information including keywords, commands, and results. This preliminary action creates a repository of information that simplifies subsequent processing operations while improving user operativity through automatic information complementation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary storage mechanism that holds previously recognized information. This intermediary component bridges simple independent processing with complex continuous operations, allowing the system to maintain processing simplicity while dramatically improving user operativity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If the system stores and processes multiple types of voice recognition information (keywords, commands, results), then processing capability is improved, but information management complexity increases

Engineering Contradiction:
Improveprocessing capabilityVSAvoidinformation management complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments voice recognition information into distinct categories: keywords, commands, and results. Each segment is stored and managed separately, allowing the system to handle multiple types of information with high processing capability while managing complexity through organized segmentation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The storage device and processor are designed with multi-functionality to handle various types of voice recognition information uniformly. This universal approach allows the system to process keywords, commands, and results through the same mechanisms, improving versatility while avoiding the complexity of separate management systems.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3089157B1Voice recognition processing device, voice recognition processing method, and display device
Publication Date: 2020.09.16 PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
  • EP3089157B1 patent drawingFigure 1
  • EP3089157B1 patent drawingFigure 2
  • EP3089157B1 patent drawingFigure 3

AI summary

Operativity of voice operation is improved. For this purpose, in voice recognition processing apparatus (100), voice processor (102) converts voice information into command information. Voice recognizer (50) converts the voice information into character string information. Intention interpretation processor (104) sorts reserved word information and free word information from the character string information. A storage device stores the command information, reserved word information, and free word information. Search processor (107) performs search processing based on the command information, reserved word information, and free word information. When there are one or two pieces of missing information in the command information, reserved word information, and free word information, search processor (107) reads the missing information from storage device (170) to perform search processing.