MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641103818 A) filed by Chennai Institute Of Technology on August 28, 2026, for An Offline,on Device Machine Learning System And Method For Estimating Fair Wages Of Handloom Weavers.
Inventors include Dr. A. R. Kavitha; Dr. D. Lita Pansy; S. Ravi Sankar; M. Brindha; Dr. S. K. Muthu Sundar; and S. Rithanya.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The titled invention discloses a mobile computing device (1) and corresponding method for the offline, on-device estimation of fair wages for handloom-woven products. The device includes a processor (2) and memory (3) storing a quantized machine learning regression model. Feature values such as material type, thread 3.0 count, weave complexity, loom type, estimated labour hours, and regional wage benchmark data are received and converted into a feature vector for on-device inference. The quantized model is executed directly on the mobile computing device (1) independently of network connectivity to generate an estimated fair wage value together with an estimation range or confidence indicator. The regression model is trained using a labelled dataset and converted and quantized into a mobile-optimized format before deployment. An optional synchronization function updates the stored model or regional wage-benchmark data when network connectivity becomes available, while the device continues to operate using the previously stored model whenever offline.
Disclaimer: Curated by HT Syndication.
