Display Device Keyword Extraction with Server Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of display devices like smart TVs face inconvenience in obtaining additional information about actors or actresses in a drama, as existing technologies provide low-confidence information through computer vision, and feedback from multiple users is not effectively integrated to correct keyword extraction.
Innovation Solution
A display device with a tuner, communication module, and controller that captures screen images, extracts keywords, generates confidence levels, and transmits this information to an external server for feedback integration, allowing multiple users' feedback to correct and enhance keyword confidence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If computer vision technology is used to extract keywords from screen captures, then keyword extraction capability is provided, but confidence of the extracted information is very low
Solution Approach 1:
The patent implements a feedback mechanism where user selections and corrections of keyword information are collected and fed back into the system. This feedback is used to retrain and refine the computer vision model, progressively improving the accuracy and confidence of keyword extraction results over time.
Solution Approach 2:
The system enables self-service by allowing users to directly correct and improve keyword information through simple interactions (selecting correct keywords, adding corrections). These user contributions automatically enhance the system's performance without requiring manual retraining by developers.
2Quantity of substance
If machine learning is used to supplement confidence of extracted keywords, then more data can be obtained, but the confidence of acquired information remains very low
Solution Approach 1:
The system collects feedback from users who correct or validate extracted keyword information. This feedback loop allows the machine learning model to learn from actual user behavior patterns, progressively improving the reliability of confidence scores and extracted information quality.
3Loss of information
If only EPG information is used to provide actor information, then current channel actor names can be obtained, but additional information about actors in other dramas is unavailable
Solution Approach 1:
The patent makes the keyword extraction system universal by enabling it to identify and provide information about actors, characters, and other entities across different dramas and channels. The system not only extracts information from current broadcast content but also searches for and provides additional information about these entities from various sources.
Solution Approach 2:
The system introduces an intermediary search and information aggregation layer that connects the extracted keywords to comprehensive databases. This intermediary component enables the system to retrieve additional information about actors and characters from multiple sources beyond the immediate broadcast content.
Data Source
AI summary
The invention relates to a display device and method for controlling the same, the method mainly comprising: capturing a screen in which content is reproduced; extracting a first keyword from an image of the captured screen, generating reliability corresponding to the first keyword, when an input of selecting the first keyword is received from an external remote controller, transmitting the first keyword, feedback information and the reliability to an external server, receiving a second keyword, corrected reliability, and feedback information from the external server, and when an input of selecting the second keyword is received, displaying a screen corresponding to the second keyword.