Translation Device With Evaluation-Based Reinput Request
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing translation systems fail to effectively handle inappropriate results from voice recognition and translation processing, leading to unnecessary subsequent processing and user frustration.
Innovation Solution
A translation device that acquires utterance in a first language, evaluates the voice recognition and translation results, and requests the user to reinput when the evaluation values are below predetermined thresholds, eliminating subsequent processing and providing appropriate reinput messages based on the type of processing error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If voice recognition processing and translation processing are continuously performed without evaluation, then processing completeness is maintained, but unnecessary processing occurs and user time is wasted
Solution Approach 1:
The patent applies preliminary action by evaluating voice recognition results and translation results before proceeding with subsequent processing. The controller calculates evaluation values for voice recognition data and translation data, and only proceeds with further processing when these evaluation values meet predetermined thresholds. This prevents unnecessary subsequent processing when the results are already inappropriate, thereby improving processing efficiency and reducing user time loss.
2Measurement precision
If evaluation values are calculated for voice recognition and translation results, then processing accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements feedback by calculating evaluation values for voice recognition results and translation results, then using these evaluation values to determine whether to request user reinput or proceed with subsequent processing. The controller continuously monitors the quality of processing results through evaluation and adjusts the processing flow accordingly. This feedback mechanism ensures high measurement precision in result evaluation while managing device complexity through systematic control logic.
3Manufacturing precision
If reinput requests are prompted when evaluation values are low, then translation accuracy is improved, but processing duration increases
Solution Approach 1:
The patent applies partial action by selectively requesting reinput only when evaluation values fall below predetermined thresholds. When voice recognition or translation results meet the required quality standards, the system proceeds directly to subsequent processing without additional user input. This approach achieves high translation accuracy through targeted reinput requests while minimizing overall processing duration by avoiding unnecessary delays in cases where the initial results are already sufficient.
Data Source
AI summary
A translation device is configured to acquire utterance spoken by a speaker in a first language and translate contents of the utterance into a second language for information presentation, and includes an input unit, a controller, a notification unit, and a storage. The input unit acquires the utterance in the first language and generates voice data from the utterance. The controller acquires a first evaluation value. The notification unit presents the speaker with information on utterance reinput request. The notification unit presents first information on utterance reinput request when the first evaluation value is less than or equal to a first predetermined value. The controller generates new voice recognition data with reference to the past voice recognition data and voice recognition data of reinput utterance, when the voice recognition data of the reinput utterance has an evaluation value less than or equal to a predetermined value.