Display Device Voice Command Website Access via NLP
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing TV speech recognition systems can only access pre-registered websites using voice commands, failing to recognize and connect to websites with non-registered names spoken by users.
Innovation Solution
A display device equipped with a microphone, natural language processing server interface, and controller that transmits voice commands to an NLP server for intention analysis, allowing access to websites even if the name is not pre-registered by selecting a candidate address from search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the TV speech recognition system supports only pre-registered websites, then the system complexity is reduced and reliability is improved, but the adaptability deteriorates and the system cannot recognize non-registered website names
Solution Approach 1:
The patent introduces an NLP server as an intermediary between the TV speech recognition system and website access. The NLP server receives the spoken website name, performs natural language processing to extract the website address, and returns the result to the TV. This mediator handles the complexity of language understanding and website resolution, allowing the TV system to support arbitrary website names without increasing its own complexity.
2Productivity
If the system uses manual NLP server mapping for website recognition, then the reliability of pre-registered sites is improved, but the productivity deteriorates as users cannot access new websites quickly
Solution Approach 1:
The system implements a feedback mechanism where the NLP server analyzes the spoken website name and provides correction or confirmation feedback. When a user speaks a website name, the NLP server processes it and returns the correct website address, even if it wasn't pre-registered. This feedback loop ensures accurate website recognition while enabling fast access to both known and new websites.
3Measurement precision
If the TV system processes voice commands locally without NLP server, then the response time is improved and productivity is enhanced, but the measurement precision deteriorates in understanding complex voice intents
Solution Approach 1:
The NLP server performs preliminary action by pre-processing and analyzing the voice command intent before the TV needs to execute it. The server maintains a database of website mappings and performs language analysis in advance, so when the TV receives the processed result, it can quickly access the intended website without performing complex analysis itself. This distributes the processing workload and optimizes both accuracy and timing.
Data Source
AI summary
Provided is a display device including a display unit, a storage unit configured to store information on a web page, a microphone configured to receive a user's voice command, a network interface unit configured to perform communication with a natural language processing (NLP) server, and a controller configured to transmit text data of the voice command to the NLP server, to receive intention analysis result information corresponding to the voice command from the NLP server, to select, as a final candidate address, one of a plurality of candidate addresses related to a search word included in the received intention analysis result information if the search word is not stored in the storage unit, and to access a website corresponding to the selected final candidate address.