Video Subtitle Vocabulary Learning via Personalized Second-Screen Display
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing language learning methods from subtitles are inefficient, disruptive, and lack personalization, especially for multiple users watching together, as they require manual interaction and compromise the viewing experience.
Innovation Solution
A system using a second screen device to display predicted unfamiliar words with explanations, synchronized with media playback, allowing minimal user interaction and personalized learning experiences for each viewer, with adaptive word selection based on vocabulary level and history.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If subtitles are displayed in multiple languages simultaneously to help learners, then language learning is supported, but screen space is excessive and users tend to read in their native language instead of learning the new language
Solution Approach 1:
The patent extracts the learning function from the main video display by using a separate second screen device. Subtitles and vocabulary explanations are displayed on the second screen rather than on the main TV screen, allowing the main screen to display only the video content while the learning materials are separated to a different display device.
Solution Approach 2:
The patent moves the subtitle display from the two-dimensional video screen to a separate device (smartphone, tablet, or computer) which adds a spatial dimension to the learning experience. This separates the video viewing area from the subtitle area, allowing both to coexist without competing for the same screen real estate.
2Ease of operation
If users manually click on subtitles to get definitions, then vocabulary learning is interactive, but the viewing experience is disrupted especially for multiple users
Solution Approach 1:
The system automatically identifies and displays vocabulary words that are likely unfamiliar to the user based on their vocabulary level profile, without requiring manual intervention. The second screen device automatically receives and displays explanations for predicted unknown words, making the learning process self-service rather than requiring user initiation.
Solution Approach 2:
The system uses feedback from user interactions with the second screen device to adjust the vocabulary level and refine word predictions. The system learns from whether users view explanations, how long they spend on each word, and which words they bookmark, continuously improving the accuracy of future word predictions.
3Adaptability or versatility
If a second screen device is used to display predicted new words with explanations, then language learning is personalized and non-disruptive, but device complexity increases
Solution Approach 1:
The second screen device serves multiple functions: it displays subtitles, provides vocabulary explanations, tracks user progress, and adapts to different users' needs. The same device can be used by multiple users who each have their own vocabulary level profiles, making the system universally applicable rather than requiring separate systems for each function.
4Measurement precision
If word predictions are based on vocabulary level and learning history, then learning accuracy is improved, but processing requirements and system complexity increase
Solution Approach 1:
The system performs preliminary analysis by building user vocabulary level profiles before actual learning begins. During media consumption, the system has already pre-processed language data from previous viewing sessions to establish baseline vocabulary levels, enabling fast real-time word predictions without heavy processing during playback.
Data Source
AI summary
A vocabulary level of a user in a language to be learned is identified. During playback of a media asset on a first device, subtitles in the language are extracted for at least a portion of the media asset. The extracted subtitles may contain a single word, or a plurality of words in the language in question. Based on the vocabulary level, a subset of words from the extracted subtitles are predicted to be new to the user. The predicted new words are then generated for display on a second device associated with the user, along with an explanation of each word of the subset of words.