Voice Recognition Response Generation for Display Apparatus
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing display apparatuses can only perform operations based on pre-set commands and re-requests when recognizing user voices, failing to provide diverse responses to various user inputs.
Innovation Solution
A display apparatus and interactive server system that collects user voices, extracts utterance elements, and generates response information in different forms to execute corresponding operations, including EPG-related and operation control functions, while handling prohibited or age-restricted inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the display apparatus uses pre-set commands for voice recognition, then the operation control is simple and reliable, but the adaptability to various user voice inputs is limited
Solution Approach 1:
The patent introduces an interactive server as an intermediary between the display apparatus and the user's voice inputs. The server receives voice commands, processes them through advanced recognition systems, and returns appropriate responses. This mediator approach allows the display apparatus to maintain relative simplicity while achieving high adaptability through the server's sophisticated processing capabilities.
Solution Approach 2:
The interactive server is designed to handle multiple types of voice inputs and provide diverse responses including operational commands, information queries, and contextual adjustments. The server can process various utterance elements (EPG-related, operation control-related, prohibited, age-restricted) and generate appropriate responses, making the system universally adaptable to different user needs while maintaining a unified processing architecture.
2Productivity
If the display apparatus only executes functions based on pre-set commands, then the system reliability is maintained, but the productivity in responding to diverse user needs is reduced
Solution Approach 1:
The system implements a feedback loop where the interactive server receives voice inputs, processes them through recognition and analysis, and returns responses to the display apparatus. This feedback mechanism enables the system to adapt to diverse user needs while maintaining reliability through structured processing stages that validate and verify commands before execution.
Solution Approach 2:
The interactive server performs preliminary processing of voice inputs before they are executed by the display apparatus. The server analyzes utterance elements, determines appropriate responses in advance, and prepares execution parameters. This preliminary action allows the display apparatus to maintain reliable execution while improving productivity by having responses pre-prepared and validated.
3Measurement precision
If the display apparatus re-requests user voice input when commands are unclear, then the operation control precision is improved, but the loss of time increases
Solution Approach 1:
The interactive server changes the parameters of voice processing by analyzing multiple utterance elements simultaneously (EPG-related, operation control-related, prohibited, age-restricted). Instead of simple re-requests, the server processes the voice input through multiple analysis dimensions to achieve high precision recognition in a single attempt, reducing time loss while maintaining accuracy.
Solution Approach 2:
The patent replaces the mechanical re-request system with an advanced voice processing mechanism. Instead of simply asking users to repeat themselves, the server uses sophisticated voice recognition and analysis algorithms to extract precise meaning from the original input, eliminating the need for re-requests and reducing time loss while maintaining high recognition precision.
Data Source
AI summary
A display apparatus, an interactive server, and a method for providing response information are provided. The display apparatus includes: a voice collector which collects a user's uttered voice, a communication unit which communicates with an interactive server; and, a controller which, if response information corresponding to the uttered voice which is transmitted to the interactive server is received from the interactive server, controls to perform an operation corresponding to the user's uttered voice based on the response information, wherein the response information is generated in a different form according to a function of the display apparatus which is classified based on an utterance element extracted from the uttered voice. Accordingly the display apparatus can execute the function corresponding to each of the uttered voices and can output the response message corresponding to each of the uttered voices, even if a variety of uttered voices are input from the user.