Abstract: A system and a method for automatically identifying key dialogues in media is disclosed herein. In the method disclosed herein, the key dialogues engine receives the media asset and extract transcript data and supplementary data. The key dialogues engine processes the transcript data into a plurality of transcript data elements and associate the transcript data elements with respective data elements selected from the supplementary data.

Abstract: A system and a method for automatically identifying key dialogues in media is disclosed herein. In the method disclosed herein, the key dialogues engine receives the media asset and extract transcript data and supplementary data. The key dialogues engine processes the transcript data into a plurality of transcript data elements and associate the transcript data elements with respective data elements selected from the supplementary data.

Abstract: A system including a key moments engine (KME) and a method for automatically identifying and ranking key moments in a media asset. The KME extracts an audio stream from the media asset and stores the audio stream as an audio file. The KME divides the audio file into sub-second audio segments. The KME computes an audio signal level for each of the sub-second audio segments and generates an array of audio signal levels for the audio file. The KME generates clusters of the audio signal levels from the array of audio signal levels. The KME dynamically determines threshold levels for classifying the audio signal levels in the array using the clusters. The KME identifies the key moments from the classified audio signal levels and computes a rank for each of the identified key moments based on ranking criteria.

Abstract: A system including a key moments engine (KME) and a method for automatically identifying and ranking key moments in a media asset. The KME extracts an audio stream from the media asset and stores the audio stream as an audio file. The KME divides the audio file into sub-second audio segments. The KME computes an audio signal level for each of the sub-second audio segments and generates an array of audio signal levels for the audio file. The KME generates clusters of the audio signal levels from the array of audio signal levels. The KME dynamically determines threshold levels for classifying the audio signal levels in the array using the clusters. The KME identifies the key moments from the classified audio signal levels and computes a rank for each of the identified key moments based on ranking criteria.

Abstract: A system and method for grouping independent machine learnt artificial intelligence to generate collective “machine wisdom” to obtain higher accuracy in identification of tags, objects and actions in a video includes an input module, Media Asset Management (MAM) module, catalogue module and a machine learning module. The input module allows the user to upload one or more videos into a media Enterprise Resource Planning (ERP) solution, a media asset management solution, or an Over-the-Top (OTT) Video Content Management System (CMS). The system further predicts and improves the vision parameters by using collective artificial intelligence machines through mutual learnt models and thereby enables higher accurate video identification resolution and cataloguing of a problem or its prediction in lesser period of time.

Abstract: The present invention overcomes the drawbacks of the technology models available in the state of the art by providing a system and method for grouping independent machine learnt artificial intelligence to generate collective “machine wisdom” to obtain higher accuracy in identification of tags, objects and actions in a video. The system comprises an input module, Media Asset Management (MAM) module, catalogue module and a machine learning module. The input module allows the user(s) to upload one or more videos into a media ERP solution a media asset management solution. The system further predicts and improves the vision parameters by using collective artificial intelligence machines through mutual learnt models and thereby enables higher accurate video identification resolution and cataloguing of a problem or its prediction in lesser period of time.