Genpact has been granted a patent for a method and system that utilizes machine learning to assess structural damage. The approach involves detecting external parts and classifying damaged regions from video frames, providing a vision-based damage estimate while incorporating audio content for enhanced analysis. GlobalData’s report on Genpact gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Genpact, was a key innovation area identified from patents. Genpact's grant share as of June 2024 was 77%. Grant share is based on the ratio of number of grants to total number of patents.
Vision-based damage assessment method for structures using machine learning
The patent US12039501B2 outlines a method and system for assessing damage to structures using advanced machine learning techniques. The process begins with training two machine learning modules: the first identifies external parts of structures from video frames, while the second detects and classifies damaged regions. The method involves analyzing video footage to determine damaged areas and their severity, removing frames that depict specific damage levels, and classifying remaining damage types. Additionally, the system incorporates audio content from the video, converting it to text and synchronizing it with the video frames to validate the damage classification results. This comprehensive approach aims to provide a vision-based damage estimate for each external part of the structure.
Further enhancements to the method include pixel-level segmentation for precise identification of damage, down-sampling video frames to focus on relevant content, and aggregating damage estimates from multiple subsets of frames to improve accuracy. The system can also generate audio-based damage estimates by identifying keywords from the synchronized text and consolidating these with vision-based estimates. Moreover, it is capable of producing cost estimates for repairs or replacements of damaged parts. The patent emphasizes the use of machine learning to classify various damage types, such as scratches and dents, thereby streamlining the damage assessment process and potentially improving maintenance and repair strategies for structures.
To know more about GlobalData’s detailed insights on Genpact, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
