AI Enabled Multimedia Information & Content Extraction
Product Overview
In digitally growing world, explosion of data that is occurring because of smart devices, the Internet of Things, and human internet activity has become a tremendous source of potential information. This information would be impossible for humans to manually process and understand. Moreover, manual processing of large amount of information from heterogeneous sources is cumbersome.
Hence BEL developed a comprehensive AI enabled Automatic Information Extraction and Synthesis which provides functionalities such as:
- Machine Comprehension
- Video Summarization
- Fake Image Detection
- Speaker Diarization
Some of the techniques that are employed for automated information extraction include Naïve Bayes classifier, Support Vector Machine, Decision Trees, Neural Network, etc. The product can help the user by getting the relevant information in timely and precise manner by:
- Automated Information extraction from a block of text either from text file or pdf. The system uses BERT NLP model to learn the context of the text from and provides the answer for the question within the context of the paragraph.
- The system summarizes a video with the key frames, so that the user need not see the whole video.
- System is capable of finding the fake image.
- Speaker Diarization can tell which speaker spoke at what interval of time.
Potential Areas of Application
- All Law Enforcement Agencies
- Military/ Paramilitary / Police Forces
- Users of C4I / C5I Applications
- Intelligence Collection and Analysis Agencies.
