US 12,340,676 B2
AI based system and method for generating warning alerts for a location to be excavated
Annapurna Sharma, Maharashtra (IN); Maheshakumara Shivakumara, Maharashtra (IN); Phanindra Reddy Vedikola, Maharashtra (IN); Puneet Agarwal, Maharashtra (IN); Sumant Kulkarni, Maharashtra (IN); Saurabh Bobde, Maharashtra (IN); and Sakshi Goyal, Maharashtra (IN)
Assigned to ZENSAR TECHNOLOGIES LIMITED, Maharashtra (IN)
Filed by Zensar Technologies Limited, Maharashtra (IN)
Filed on Aug. 29, 2023, as Appl. No. 18/457,846.
Claims priority of application No. 202221049659 (IN), filed on Aug. 30, 2022.
Prior Publication US 2024/0071199 A1, Feb. 29, 2024
Int. Cl. G08B 21/18 (2006.01); G06F 40/279 (2020.01); G06N 20/00 (2019.01); G06V 10/762 (2022.01); G06V 30/413 (2022.01); G06V 30/422 (2022.01)
CPC G08B 21/18 (2013.01) [G06F 40/279 (2020.01); G06N 20/00 (2019.01); G06V 10/762 (2022.01); G06V 30/413 (2022.01); G06V 30/422 (2022.01)] 15 Claims
OG exemplary drawing
 
1. An artificial intelligence (AI) based method for generating warning alerts for a location to be excavated, comprising:
obtaining, from at least one external source, at least one underground asset map, wherein an underground asset map corresponds to an underground asset at the location to be excavated;
analyzing each of the at least one underground asset map using a pre-trained AI model, wherein analyzing each of the at least one underground asset map comprising:
for each of the at least one underground asset map:
identifying, by performing a text-based analysis on a text area of the underground asset map, a name of a service provider providing underground service corresponding to the underground asset;
locating a region of interest within the underground asset map, the region of interest corresponding to a specific area within the location to be excavated;
extracting at least one feature within the region of interest of the underground asset map;
comparing the at least one extracted feature with a plurality of features stored in a repository to determine a match, wherein each of the plurality of features indicate a risk associated with the underground asset corresponding to the identified service provider; and
in response to the determination of the match, classifying the extracted feature as a risk feature corresponding to the identified underground utility service provider; and
generating one or more warning alerts based on the result of classification, wherein the one or more warnings alerts represents presence of one or more risks within the region of interest of each of the at least one underground asset map.