System and method for training a damage identification model

#Under 35 U.S.C. 119, this application claims the benefit and right of priority of Chinese Patent Application No. 201811012749.2, filed Aug. 31, 2018.

#This disclosure is generally related to the technical field of machine learning. More specifically, this disclosure is related to a method and system for training a damage identification model for use in intelligent damage assessment of vehicles.

#In conventional vehicle insurance damage assessment approaches, a vehicle insurance company can send a claim adjuster to the site of the damaged vehicle to conduct a manual survey and damage assessment. The survey and damage assessment conducted by the adjuster can include the following tasks: determining a repair solution, estimating an indemnity, taking photographs of the vehicle on the site and archiving the photographs for subsequent assessment of the damage by a damage inspection person at the vehicle insurance company. Since the on-site survey and subsequent damage assessment are performed manually, an indemnity claiming cycle can be as long as 1-3 days. Such long processing times can result in poor user experience with the vehicle insurance company. Furthermore, since the survey and damage assessments are performed manually, the insurance company may incur large labor and professional training costs.

#FIG. 1 shows an exemplary damage identification model training architecture, according to one embodiment of the present invention.

#FIG. 2 presents a flowchart illustrating an exemplary process for training a damage identification model, in accordance with an embodiment of the present invention.

#FIG. 3 presents a flowchart illustrating an exemplary process for reducing noise in a tagged training sample set, in accordance with an embodiment of the present invention.

#In the figures, like reference numerals refer to the same figure elements.

#The following description is presented to enable any person skilled in the art to make and use the embodiments, and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present disclosure. Thus, the present invention is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

#Overview