AI Document Display Matching Voice Topics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional machine learning methods fail to identify and display the relevant portion of a document corresponding to a user's voice input, requiring separate hardware or assistants for presentations, and causing listeners to struggle in following the presenter's explanation.
Innovation Solution
An electronic apparatus equipped with a microphone, display unit, and processor that acquires topics from document contents, recognizes user voice inputs, matches them with document topics, and controls the display to show the relevant pages or video frames, even if specific words are not mentioned, using deep learning algorithms and motion sensors for enhanced user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional machine learning methods are used for voice recognition, then basic voice input can be processed, but the system cannot identify and display the relevant portion of a document corresponding to the user's voice input
Solution Approach 1:
The patent introduces an intermediary component (separate hardware or assistant) to bridge the gap between voice recognition and document navigation. This intermediary processes the voice input and maps it to the relevant document portions, enabling context understanding without requiring the basic machine learning system to directly perform document navigation.
Solution Approach 2:
The system segments the document into multiple portions and associates each portion with specific voice commands or context keywords. This segmentation allows the system to identify and display only the relevant portion corresponding to the user's voice input, rather than requiring the user to navigate through the entire document.
2Ease of operation
If separate hardware or assistant is used for presentations, then document navigation can be assisted, but the system complexity increases
Solution Approach 1:
The patent merges the functions of voice recognition, context understanding, and document navigation into a single integrated system. By combining these previously separate functions, the system eliminates the need for separate hardware or assistant components while maintaining presentation assistance capabilities.
Solution Approach 2:
The system is designed with multi-functionality to perform voice recognition, context analysis, and document navigation using a single device. This universal approach allows one system to replace multiple specialized components, reducing overall system complexity while maintaining ease of operation.
3Measurement precision
If specific words must be included in voice input to find document portions, then recognition accuracy is maintained, but user convenience decreases
Solution Approach 1:
The system dynamically adjusts its recognition criteria based on the context. Instead of requiring specific words in all cases, the system can recognize voice inputs with varying levels of specificity depending on the situation, maintaining accuracy while improving flexibility. The recognition threshold and required keywords are dynamically determined based on context analysis.
Data Source
AI summary
The disclosure relates to an artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and an application thereof. In particular, an electronic apparatus, a document displaying method thereof, and a non-transitory computer readable recording medium are provided. An electronic apparatus according to an embodiment of the disclosure includes a display unit displaying a document, a microphone receiving a user voice, and a processor configured to acquire at least one topic from contents included in a plurality of pages constituting the document, recognize a voice input through the microphone, match the recognized voice with one of the acquired at least one topic, and control the display unit to display a page including the matched topic.