Larsen & Toubro. has filed a patent for a method and system to extract information from input files. The method involves identifying text data, generating search patterns, mapping patterns, and extracting relevant text entities based on user input. The system aims to streamline information extraction processes efficiently. GlobalData’s report on Larsen & Toubro gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Larsen & Toubro, Solar-powered EVs was a key innovation area identified from patents. Larsen & Toubro's grant share as of January 2024 was 32%. Grant share is based on the ratio of number of grants to total number of patents.

Information extraction method from input file based on search patterns

Source: United States Patent and Trademark Office (USPTO). Credit: Larsen & Toubro Ltd

The patent application (Publication Number: US20240020473A1) describes a method and system for extracting information from the contents of an input file. The method involves identifying text data from the input file, receiving user input to identify relevant text entities, generating search patterns, mapping patterns associated with text entities, identifying matching patterns, and extracting relevant text entities based on the matches. The system includes a processor and memory storing instructions for executing the method steps. The method also includes domain-based extraction, location-based extraction, part-of-speech-based extraction, and machine learning-based extraction to enhance the information extraction process.

Furthermore, the patent application details the generation of recommendations based on historical data using a classification-based machine learning model. The system can handle various types of input files, including image files and PDF files, and perform tasks such as determining domain-based names, identifying entity types, and extracting text entities based on location and part-of-speech. The method also involves identifying unique text entities, determining entity types, and automatically generating search patterns for pattern entities. Overall, the patent application outlines a comprehensive approach to extracting information from input files efficiently and accurately, utilizing a combination of pattern matching, mapping, and machine learning techniques to enhance the extraction process and provide valuable recommendations based on historical data.

To know more about GlobalData’s detailed insights on Larsen & Toubro, buy the report here.

Premium Insights


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.