Automated Video Material Selection for News Production
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for matching video material with news text are manual, leading to inefficiencies and inaccuracies in selecting relevant video content for news production.
Innovation Solution
A method and apparatus that recognize person names in news text, search for corresponding videos, extract key frames, and determine video material based on identity information, ensuring the video content aligns with the news text by using named entity recognition, biometric features, and segmenting video frames for optimal play duration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual browsing and selection of video content is used, then the operator can personally verify video relevance, but the news production efficiency is low and the process is time-consuming
Solution Approach 1:
The patent replaces the manual mechanical process of video browsing and selection with an automated computer-based system. The system uses text recognition to extract person names from news text, performs automatic video searching using these names as keywords, and applies identity recognition technology to verify whether the video content matches the news text, thereby eliminating manual intervention and significantly improving efficiency
Solution Approach 2:
The system enables self-service automation where the computer automatically completes the entire video material selection process without human assistance. The automated video searching and identity recognition functions allow the system to independently find and verify matching video content, freeing operators from manual work while maintaining accuracy
2Measurement precision
If manual video selection is used, then the operator can ensure video quality, but the accuracy of matching video material with news text is insufficient due to human error
Solution Approach 1:
The patent replaces manual video selection with an automated computer-based system that uses text recognition to extract person names from news text, performs video searching using these names as keywords, and applies identity recognition technology to verify whether the video content matches the news text, thereby eliminating human error and significantly improving matching accuracy
Solution Approach 2:
The system implements a feedback mechanism where the identity recognition result is used to verify whether the searched video content matches the news text. If the identity information from the video does not match the person name in the news text, the system can identify the mismatch and adjust the selection, ensuring high accuracy through automated verification
Data Source
AI summary
The present disclosure discloses a method and apparatus for determining video material of news. The method for determining video material of news comprises: recognizing a person name in a news text; searching a video based on the person name, to obtain a to-be-selected video; extracting a key frame in the to-be-selected video; recognizing a person in the key frame to obtain identity information of the person; and determining the to-be-selected video as video material of news, in response to the identity information of the person conforming to the person name. The present disclosure improves the consistency between the video material of the news and the news text.