Systems and methods for automatically determining associations between damaged parts and repair estimate information during damage appraisal
A method, non-transitory computer readable medium, and apparatus that improves automated damage appraisal includes analyzing one or more obtained images of property using a deep neural network with multiple hidden layers of units between an input and output and which has stored knowledge data encoded from one or more stored property damage images to identify the part of the vehicle that has sustained damage. Damage data on an extent of the damage in the identified part of the vehicle is determined using the deep neural network which has stored knowledge data encoded from one or more stored property damage images. The identified generic part of the vehicle is used to obtain a corresponding Part ID Code by using a parts dictionary. Part Qualifier information obtained using VIN information is then used in conjunction with the Part ID to obtain the OEM-specific part and then generate one or more repair lines for the repair estimate.
1. A system for conducting an automatic appraisal of a vehicle damaged during an adverse incident, the system comprising:
a user computing device; and
an appraisal management computing apparatus comprising:
a processor; and
a memory storing computer-executable instructions that, when executed by the processor, cause the appraisal management computing apparatus to:
provide at least one damage evidence file for a damaged part of the vehicle as input to a deep neural network (DNN), wherein responsive to the input, the DNN generates output comprising a part code corresponding to the damaged part, wherein the DNN comprises multiple layers including an input layer, an output layer, and one or more hidden layers between the input layer and the output layer, and wherein the DNN is trained on historic damage data comprising a plurality of damage evidence files associated with corresponding damaged parts previously identified as damaged;
identify an Original Equipment Manufacturer (OEM) part number based on the part code and a vehicle identification number (VIN) associated with the vehicle; and
generate a repair estimate line comprising the OEM part number.
2. The system of claim 1 , wherein the output of the DNN comprises a repair operation for restoring the damaged part.
3. The system of claim 2 , wherein the repair estimate line comprises an OEM repair operation determined based on the repair operation identified by the output of the DNN.
4. The system of claim 3 , wherein the repair estimate line is incorporated into an automatic appraisal of damage to restoring the vehicle damaged during the adverse incident.
5. The system of claim 1 , wherein identifying the OEM part number comprises extracting data from the VIN.
6. The system of claim 1 , wherein identifying the OEM part number comprises using a parts dictionary configured to store associations between generic vehicle parts and OEM part numbers.
7. The system of claim 1 , wherein the at least one damage evidence file comprises at least an image file, a video file, a 3D scan file.
8. The system of claim 1 , wherein OEM part code and OEM repair operation are specific to individual automotive manufacturers.
9. A method for conducting an automatic appraisal of a vehicle damaged during an adverse incident, the method comprising:
providing, by a damage assessment computing apparatus, at least one damage evidence file for a damaged part of the vehicle as input to a deep neural network (DNN), wherein responsive to the input, the DNN generates output comprising a part code corresponding to the damaged part, wherein the DNN comprises multiple layers including an input layer, an output layer, and one or more hidden layers between the input layer and the output layer, and wherein the DNN is trained on historic damage data comprising a plurality of damage evidence files associated with corresponding damaged parts previously identified as damaged;
identifying, by the damage assessment computing apparatus, an Original Equipment Manufacturer (OEM) part number based on the part code and a vehicle identification number (VIN) associated with the vehicle; and
generating, by a repair estimate generating computing apparatus, a repair estimate line comprising the OEM part number.
10. The method of claim 9 , wherein the output of the DNN comprises a repair operation for restoring the damaged part.
11. The method of claim 10 , wherein the repair estimate line comprises an OEM repair operation determined based on the repair operation identified by the output of the DNN.
12. The method of claim 11 , wherein the repair estimate line is incorporated into an automatic appraisal of damage to restoring the vehicle damaged during the adverse incident.
13. The method of claim 9 , wherein identifying the OEM part number comprises extracting data from the VIN.
14. The method of claim 9 , wherein identifying the OEM part number comprises using a parts dictionary configured to store associations between generic vehicle parts and OEM part numbers.
15. The method of claim 9 , wherein responsive to a user selection of an individual evidence file associated with a damaged part, presenting one more vehicle parts determined to be related.
16. The method of claim 9 , wherein the at least one damage evidence file comprises at least an image file, a video file, a 3D scan file.
17. The method of claim 9 , wherein OEM part code and OEM repair operation are specific to individual automotive manufacturers.
18. One or more non-transitory machine-readable storage media encoded with instructions that, when executed by one or more hardware processors of a computing system, cause the computing system to perform operations for conducting an automatic appraisal of a vehicle damaged during an adverse incident, the operations comprising:
providing, by a damage assessment computing apparatus, at least one damage evidence file depicting a damaged part of the vehicle as input to a deep neural network (DNN), wherein responsive to the input, the DNN generates output comprising a part code corresponding to the damaged part, wherein the DNN comprises multiple layers including an input layer, an output layer, and one or more hidden layers between the input layer and the output layer, and wherein the DNN is trained on historic damage data comprising a plurality of damage evidence files associated with corresponding damaged parts previously identified as damaged;
identifying, by the damage assessment computing apparatus, an Original Equipment Manufacturer (OEM) part number based on the part code and a vehicle identification number (VIN) associated with the vehicle; and
generating, by a repair estimate generating computing apparatus, a repair estimate line comprising the OEM part number.
19. The one or more non-transitory machine-readable storage media of claim 18 , wherein the output of the DNN comprises a repair operation for restoring the damaged part.
20. The one or more non-transitory machine-readable storage media of claim 19 , wherein the repair estimate line comprises an OEM repair operation determined based on the repair operation identified by the output of the DNN.