Rostelecom plans to use neural networks to control the work of public utilities

Rostelecom plans to launch an artificial intelligence system in the regions to control work in the housing and communal services sector, the Izvestia newspaper reported. Such a system, in particular, is planned to be introduced in Kazan. It will automatically determine the need to clean roads from snow, ice and mud, record the passage of the cleaning equipment and the quality of its work.

The Moscow Department of Competition Policy this week also announced a competition for the provision of services for the automatic recording of violations in the housing and communal services sector, its customer is the city’s information technology department. The department told the publication that Moscow has been using a neural network in a video surveillance system for two years to look for potential flaws for the operators of the Center for Automated Recording of Administrative Violations. The previous contract expired, so a new competition was announced.

According to the tender documentation, the initial contract price is 80 million rubles. The conditions say that the neural network should detect errors in the operation of the housing and communal services sector using analysis from the city’s CCTV cameras. Artificial intelligence must recognize 12 types of violations without human intervention: storage of snow on lawns, sidewalks and roadways, ice on benches and footpaths, uncleared snow in playgrounds.

Also, the neural network should record illegally drawn graffiti, potholes and pits on the roads, overflowing garbage containers and empty, dried up or abandoned flower beds. The department explained that the neural network will analyze screenshots of images from video cameras and will send the operators of the Center for Automated Recording of Administrative Violations (CAFAP) those that have violations.



Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Recent News

Editor's Pick