Intellectual Property India Publishes Patent Application for 'Creativiq: Machine Learning-Based Cross-Platform Engagement Forecasting And Intelligent Content Optimization System' Filed by Prof. Vijaykumar Ghule; Rudra Ingole; Ashish Kumar Panda; Parth Barde; and Akshat Jain

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202621028016 A) filed by Prof. Vijaykumar Ghule; Rudra Ingole; Ashish Kumar Panda; Parth Barde; and Akshat Jain, Pune, Maharashtra, on March 10, for 'creativiq: machine learning-based cross-platform engagement forecasting and intelligent content optimization system.'

Inventor(s) include Prof. Vijaykumar Ghule; Rudra Ingole; Ashish Kumar Panda; Parth Barde; and Akshat Jain.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "The invention disclosed herein relates to an artificial intelligence (AI) based on a machine learning platform, "CreativIQ: A Cloud-Based AED-Based System for Cross-Platform Engagement Forecasting and Optimizing Digital Content," which is intended to be used for predicting future performance of digital content. The four examples of content that can be included in this framework are video, audio, graphics, and text. The integrated multi-platform data ingest module, feature extraction engine, and machine-learning-prediction engine comprise three primary components that make up the engagement prediction engine. The engagement prediction engine is designed to predict the following metrics related to the future engagement that users will generate through various mediums (e.g., Instagram, Facebook, Twitter, Linkedln, Pinterest, TikTok, etc.): (1) the probability of user interaction; (2) an estimate of reach; and (3) a score indicating the performance of content prior to publication. Using the predictive outputs generated by the engagement prediction engine, the system generates a series of dynamic optimization recommendations (e.g., model for best posting time; adaptive hashtags; caption enhancements; strategy revisions) that are based upon the content's categories and the audience's previous behaviors. The system also utilizes a reinforcement-learning mechanism that continuously improves forecast accuracy through on-going re-evaluation of the predictive outputs based on actual post-publication engagement events. As such, model parameters will be continually updated from historical engagement data."

Disclaimer: Curated by HT Syndication.