Voice Recognition Command Correction via History-Based Supplementation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition services struggle to provide the desired service when a user's utterance does not include a voice assistant or end service name to call.
Innovation Solution
The proposed solution involves an apparatus and method that includes a voice input unit to separate user utterances from noise, a voice recognition unit to extract and classify call words, domain, end service name, and operations information, and a command correction unit to generate a corrected user command by adding missing information based on user history and usage patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the voice recognition service requires complete information (call words, domain, end service name, operations) in user utterance, then the service accuracy is improved, but the ease of operation deteriorates
Solution Approach 1:
The system automatically supplements missing information in user utterances by retrieving it from stored usage history and service data, without requiring the user to provide complete information manually. The command correction unit autonomously identifies missing elements and fills them in based on historical patterns.
Solution Approach 2:
The system pre-stores usage history, service data, and typical command patterns in the classified information storage unit before they are needed. This preliminary preparation enables the command correction unit to quickly supplement missing information during voice recognition processing.
2Adaptability or versatility
If the system stores and processes detailed usage history and service data, then the adaptability is improved, but the device complexity increases
Solution Approach 1:
The system divides information processing into distinct functional units: voice input unit for noise separation and text conversion, voice recognition unit for information extraction, classified information storage unit for data management, and command correction unit for supplementing missing information. This modular segmentation manages complexity while maintaining adaptability.
Solution Approach 2:
The classified information storage unit serves multiple functions: storing usage history, maintaining service data, and providing reference information for command correction. This multi-functionality reduces the need for separate dedicated storage systems for each type of data.
Data Source
AI summary
A method and apparatus for providing a voice recognition service can include separating a user utterance from noise and converting the user utterance into a text to generate content of the user utterance, extracting, from the content of the user utterance, call words information, domain information, end service name information, and operations information, generating a corrected user command by correcting a user command, and generating response information by using the corrected user command.