Text Data Extraction for Asynchronous Content Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hearing-impaired individuals face challenges in consuming content, such as television programming, as they are forced to read text at the speed of the associated video, which can be inefficient and unappealing, as they may read faster or slower than the video playback.
Innovation Solution
A system and method that extracts and stores text data, such as closed captioning, subtitles, and metadata, from content programs, allowing users to search and associate it with video frames, creating an electronic book or guide, enabling users to search for content segments based on text queries and view them at their preferred speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If text is displayed synchronized with video playback, then hearing-impaired users can access content, but users cannot read at their own preferred speed
Solution Approach 1:
The patent segments the content into separate text and video components, allowing the text to be extracted and presented independently from the video playback. This enables users to read text segments at their own pace while the video plays separately, resolving the contradiction between reading speed flexibility and content consumption efficiency.
Solution Approach 2:
The patent introduces a new dimension by separating text consumption from video playback in time and presentation. Text is extracted and made available as an independent searchable entity, allowing users to navigate and consume text content in a different temporal dimension than the original synchronized playback, thus enabling preferred reading speeds.
2Difficulty of detecting and measuring
If text is extracted and made searchable, then content searchability improves, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by extracting and storing text data from video content in advance, creating a searchable text database before user queries. This preprocessing step enables efficient content searchability while the system complexity is managed through automated extraction processes and structured storage formats.
Solution Approach 2:
The patent creates text copies from video content through automatic transcription and extraction. These text copies are stored separately from the original video, enabling searchable text functionality without requiring modifications to the original video files, thus balancing searchability improvement with system complexity management.
Data Source
AI summary
Methods and systems for using text data in content presentation and content search are disclosed. Text data and a plurality of video frames can be extracted from a content program and stored in a database. Extracted text data can be divided into a plurality of text segments. The plurality of text segments and the plurality of video frames can be presented in the form of an electronic book or guide. In addition, the content program can be divided into a plurality of content segments and stored in the database. The plurality of content segments and the plurality of text segments can be associated by time indices. A user can identify one or more content segments in the database by a query, and notifications can be sent according to the query.