Automated vehicle repair estimation by aggregate ensembling of multiple artificial intelligence functions

Abstract

Automated vehicle repair estimation by aggregate ensembling of multiple artificial intelligence functions is provided. A method comprises receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle; aggregating a plurality of the recommended vehicle repair operations; generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations; and providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems.

What is claimed is: 
     
         1 . A system, comprising:
 a hardware processor; and   a non-transitory machine-readable storage medium encoded with instructions executable by the hardware processor to perform a method comprising:   receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle, wherein each vehicle repair recommendation set identifies a score for each of the recommended vehicle repair operations in the plurality of vehicle repair recommendation sets, wherein each score indicates a projected accuracy of the corresponding recommended vehicle repair operation, wherein each of the vehicle repair recommendation sets includes one or more images of the damaged vehicle, and wherein each of the vehicle repair recommendation sets is generated by a respective first artificial intelligence function, and wherein each of the respective first artificial intelligence functions is trained;   selecting a plurality of the recommended vehicle repair operations, including at least one recommended vehicle repair operation from each of the vehicle repair recommendation sets, by providing the plurality of vehicle repair recommendation sets to a second artificial intelligence function, wherein the second artificial intelligence function is trained using a plurality of vehicle repair training sets,   wherein each vehicle repair training set comprises:
 one or more images of a further second damaged vehicle, and 
 a composite vehicle repair recommendation set for the further second damaged vehicle; 
   aggregating the selected plurality of the recommended vehicle repair operations;   generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations, comprising identifying the scores for the recommended vehicle repair operations in the generated composite vehicle repair recommendation set;   providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems; and   re-training one or more of the first artificial intelligence functions when a predetermined event occurs;   wherein:   each of the vehicle repair recommendation sets identifies a plurality of images of the damaged vehicle; and   the method further comprises:
 selecting one or more of the images of the damaged vehicle, and identifying the selected one or more of the images in the generated composite vehicle repair recommendation set; and 
   the predetermined event comprises at least one of:
 a function of a defined lapsed portion of time; or 
 a result of a comparison between a pre-defined evaluation metric of the one or more of the first artificial intelligence functions and a test data set. 
   
     
     
         2 . The system of  claim 1 , wherein aggregating athe selected plurality of the recommended vehicle repair operations comprises:
 aggregating the plurality of the recommended vehicle repair operations based on statistical aggregation methodologies comprising at least one of mean, max, min, variance, and standard deviation.   
     
     
         3 . A non-transitory machine-readable storage medium encoded with instructions executable by a hardware processor of a computing component, the machine- readable storage medium comprising instructions to cause the hardware processor to perform a method comprising:
 receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle, wherein each vehicle repair recommendation set identifies a score for each of the recommended vehicle repair operations in the plurality of vehicle repair recommendation sets, wherein each score indicates a projected accuracy of the corresponding recommended vehicle repair operation, wherein each of the vehicle repair recommendation sets includes one or more images of the damaged vehicle, and wherein each of the vehicle repair recommendation sets is generated by a respective first artificial intelligence function, and wherein each of the respective first artificial intelligence functions is trained;   selecting a plurality of the recommended vehicle repair operations, including at least one recommended vehicle repair operation from each of the vehicle repair recommendation sets, by providing the plurality of vehicle repair recommendation sets to a second artificial intelligence function, wherein the second artificial intelligence function is trained using a plurality of vehicle repair training sets,   wherein each vehicle repair training set comprises:
 one or more images of a further second damaged vehicle, and 
 a composite vehicle repair recommendation set for the further second damaged vehicle; 
   aggregating the selected plurality of the recommended vehicle repair operations;   generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations, comprising identifying the scores for the recommended vehicle repair operations in the generated composite vehicle repair recommendation set;   providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems; and   re-training one or more of the first artificial intelligence functions when a predetermined event occurs;   wherein:   each of the vehicle repair recommendation sets identifies a plurality of images of the damaged vehicle; and   the method further comprises:
 selecting one or more of the images of the damaged vehicle, and 
 identifying the selected one or more of the images in the generated composite vehicle repair recommendation set; and 
   the predetermined event comprises at least one of:
 a function of a defined lapsed period of time; or 
 a result of a comparison between a pre-defined evaluation metric of the one or more of the first artificial intelligence functions and a test data set. 
   
     
     
         4 . The non-transitory machine-readable storage medium of  claim 3 , wherein aggregating athe selected plurality of the recommended vehicle repair operations comprises:
 aggregating the plurality of the recommended vehicle repair operations based on statistical aggregation methodologies comprising at least one of mean, max, min, variance, and standard deviation.   
     
     
         5 . A method comprising:
 receiving a plurality of vehicle repair recommendation sets for a damaged vehicle, wherein each of the vehicle repair recommendation sets identifies at least one recommended vehicle repair operation of a plurality of the vehicle repair operations for the damaged vehicle, wherein each vehicle repair recommendation set identifies a score for each of the recommended vehicle repair operations in the plurality of vehicle repair recommendation sets, wherein each score indicates a projected accuracy of the corresponding recommended vehicle repair operation, wherein each of the vehicle repair recommendation sets includes one or more images of the damaged vehicle, and wherein each of the vehicle repair recommendation sets is generated by a respective first artificial intelligence function, and wherein each of the respective first artificial intelligence functions is trained;   selecting a plurality of the recommended vehicle repair operations, including at least one recommended vehicle repair operation from each of the vehicle repair recommendation sets, by providing the plurality of vehicle repair recommendation sets to a second artificial intelligence function, wherein the second artificial intelligence function is trained using a plurality of vehicle repair training sets, wherein each vehicle repair training set comprises:   one or more images of a further second damaged vehicle, and   a composite vehicle repair recommendation set for the further second damaged vehicle;   aggregating the selected plurality of the recommended vehicle repair operations; generating a composite vehicle repair recommendation set that identifies the aggregated recommended vehicle repair operations, comprising identifying the scores for the recommended vehicle repair operations in the generated composite vehicle repair recommendation set;   providing the composite vehicle repair recommendation set to one or more vehicle repair insurance claims management systems; and   re-training one or more of the first artificial intelligence functions when a predetermined event occurs;   wherein:   each of the vehicle repair recommendation sets identifies a plurality of images of the damaged vehicle; and   the method further comprises:
 selecting one or more of the images of the damaged vehicle, and 
 identifying the selected one or more of the images in the generated composite vehicle repair recommendation set; and 
   the predetermined event comprises at least one of:
 a function of a defined lapsed period of time; or 
 a result of a comparison between a pre-defined evaluation metric of the one or more of the first artificial intelligence functions and a test data set. 
   
     
     
       6. The method of  claim 5 , wherein aggregating the selected plurality of the recommended vehicle repair operations comprises:
 aggregating the plurality of the recommended vehicle repair operations based on statistical aggregation methodologies comprising at least one of mean, max, min, variance, and standard deviation.    
     
     
       7. The system of  claim 1 , the method further comprising:
 receiving a claim package, the claim package including data describing the damaged vehicle; and   distributing the claim package to the first artificial intelligence functions, wherein the vehicle repair recommendation sets are generated by the first artificial intelligence functions based on the claim package.    
     
     
       8. The system of  claim 1 , wherein aggregating the selected plurality of the recommended vehicle repair operations comprises at least one of:
 combining two or more of the received recommended vehicle repair operations; or   omitting redundant ones of the recommended vehicle repair operations.    
     
     
       9. The system of  claim 1 , the method further comprising:
 determining whether the predetermined event has occurred.    
     
     
       10. The non-transitory machine-readable storage medium of  claim 3 , the method further comprising:
 receiving a claim package, the claim package including data describing the damaged vehicle; and   distributing the claim package to the first artificial intelligence functions, wherein the vehicle repair recommendation sets are generated by the first artificial intelligence functions based on the claim package.    
     
     
       11. The non-transitory machine-readable storage medium of  claim 3 , wherein aggregating the selected plurality of the recommended vehicle repair operations comprises at least one of:
 combining two or more of the received recommended vehicle repair operations; or   omitting redundant ones of the recommended vehicle repair operations.    
     
     
       12. The non-transitory machine-readable storage medium of  claim 3 , wherein aggregating the selected plurality of the recommended vehicle repair operations comprises:
 determining whether the predetermined event has occurred.    
     
     
       13. The method of  claim 5 , further comprising:
 receiving a claim package, the claim package including data describing the damaged vehicle; and   distributing the claim package to the first artificial intelligence functions, wherein the vehicle repair recommendation sets are generated by the first artificial intelligence functions based on the claim package.    
     
     
       14. The method of  claim 5 , wherein aggregating the selected plurality of the recommended vehicle repair operations comprises at least one of:
 combining two or more of the received recommended vehicle repair operations; or   omitting redundant ones of the recommended vehicle repair operations.    
     
     
       15. The method of  claim 5 , further comprising:
 determining whether the predetermined event has occurred.