| Developers: | Mains Lab (Meyns Laboratory) |
| Branches: | Transport |
2020: Creation of the Second AI system for determination damage in road accident
On December 21, 2020 the Mains Lab company announced creation as it claims, the Russia's first automation system of settlement process of losses. The technology under the name "Second" will allow to reduce time of receiving the direction for car repairs or money payment at a loss occurrence from several days to 20 minutes.
The artificial intelligence developed by Mains Lab will be able to analyze photos of damages and also to count the repair cost and the amount of insurance payments literally in several minutes. The technology is capable to define damage of the car on the basis of the photo.
A system passed test for 3,000 cases – using use of the online analysis it was succeeded to reach the accuracy of 97%, a system fulfills such percent of cases with an accuracy of the expert-person or it is better, and considerably to reduce choice reaction time on an insured event. Earlier this process took on average several days.
At the first stage there is a loading of photographic materials. The robot accepts both photos of damages, and the documents necessary for calculation of cost of damage – the registration certificate of the car, the insurance policy, etc. Using machining in 1-2 minutes there is an analysis and classification of foreshortenings of photos, determination of zones of the car, segmentation of parts and damages, including hidden, and primary calculation of repair. Further data go to the expert of Mains Lab for confirmation – it takes at most 2 minutes. At a final stage the robot loader brings information in case, makes the choice of model and complete set, automatically selects the damaged parts and creates calculation.
As told TAdviser in Mains Lab, Second will be used by participants top-10 the largest insurance companies of Russia. Start of a system is planned for the first quarter 2021.
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |