Name of the project: Automatic Content Enrichment
Creators: Better Software Group & Warsaw University of Technology
Project timeframe: Project completion and first implementations are planned for the beginning of Q1 2020.

Project objective

Our goal is to develop intelligent technology that will allow to effectively analyze video materials published on the web, both in the form of live streams and files. The description of video content will be slower than real time, and run at less than 1/2 real time in the case of live content.

Where did the idea for such a project come from?

The project is a direct response to the needs of our clients, which we surveyed during conversations with companies offering video content on the internet and monetizing it through advertising. The biggest challenge faced by creators and broadcasters is the inability to perfectly match the content and the moment of broadcasting of advertisements to the user’s preferences. There currently are no solutions on the market that enable the effective and fully automatic analysis of video content and parameters. We know that current technology already allows it, and because we have the knowledge and skills necessary to create a solution that will revolutionize the video market, we have taken the challenge.

ACE capabilities

According to our assumptions, Automatic Content Enrichment (ACE) will enable, among others,

  • replacement of selected advertising breaks with personalized content from the ad server. The users, unaware that they are watching a targeted advertisement,  will receive it as a part of the live content;
  • analysis of video materials;
  • providing contextual ads targeted to the currently broadcast video content;
  • marking the beginnings and ends of individual programs in live broadcast, in order to sell information to the owners of nPVR and CatchUP services;
  • match the program to the EPG position.

The technology behind ACE

The new technology will be a solution based on inference algorithms and modern machine learning. The implemented methods will include Scale-Invariant Feature Transform (SIFT) and Gradient Location and Orientation Histogram (GLOH) for the image, and FLUX mechanism for audio data – spectrum stream, spectrograms or mel-based cepstral parameters (MFCC). The whole process will be based on deep and convolutional neural networks.

Our mission at Better Software Group is to create software that opens up new business opportunities to our clients, and increases their profits. We have decided to develop this innovative solution to allow all video broadcasters of video content on the Internet to more accurately match the advertising message, thus improving users’ experience and increasing the profits from advertising for the publisher.

THE USE OF ARTIFICIAL INTELLIGENCE IN THE MEDIA CREATES A SERIES OF NEW AMAZING OPPORTUNITIES FOR OUR CLIENTS. AT BSG, WE ALWAYS TRY TO BE THE FOREFRONT OF INNOVATION, FINDING AND IMPLEMENTING THE LATEST TECHNOLOGIES IN THE SOLUTIONS WE CREATE. THE PROJECT DEVELOPED IN COOPERATION WITH WARSAW UNIVERSITY OF TECHNOLOGY WILL GIVE US THE OPPORTUNITY TO ACTUALLY APPLY SOMETHING THAT NOT LONG AGO WAS JUST A PIPE DREAM. – BARTŁOMIEJ LOZIA, CO-CEO OF BETTER SOFTWARE GROUP.

The work on Automatic Content Enrichment is proceeding in accordance with the adopted schedule, which means that we are currently developing a prototype of the algorithm in the form of working software. We will regularly post about the next stages of the project implementation, including the introduction of a ready-made solution to the market. If you are interested in the use of artificial intelligence in video and other innovations – follow our blog for more news.

Due to the innovative character of the solution, we decided to apply for a patent. Our patent application has already been positively reviewed by the Patent Research Department of the Patent Office of the Republic of Poland.