Systems and methods for identifying advanced driver assistance systems using vehicle diagnostics
Systems, methods, and apparatuses are provided for evaluating the calibration requirements or calibration needs of one or more sensors of a vehicle. A subject matter expert and/or a machine learning model can be used to generate correlations between data scanned from a vehicle and from repair orders or repair estimates. Natural language processing can be used to evaluate information contained in a repair order to generate a CIECA or line code. The machine learning model can use rules when a diagnostic trouble code (DTC) provides a high probability indication that a particular component requires repair. In some examples, a machine learning model can cluster or otherwise identify a likely area of repair based on information embedded or contained in a repair estimate.
1 . A method of determining calibration needs for a vehicle, the method comprising:
receiving, at a computer system comprising a processor and memory, scan data for the vehicle, from a scan tool comprising an interface configured to communicate to an on-board diagnostic system of the vehicle, the scan data comprising one or more diagnostic codes, the diagnostic codes having respective types, and one or more module identifiers;
receiving, at the computer system, estimate data for the vehicle, the estimate data comprising one or more line codes corresponding to a repair order for the vehicle;
analyzing the scan data, using a first class of rules based at least in part on the diagnostic codes, the respective types of the diagnostic codes, and the module identifiers, to determine whether a first condition is met, the first condition corresponding to a result identifying a component of the vehicle requiring calibration;
analyzing the scan data, when it is determined that the first condition based on the first class of rules is not met, using a second class of rules based at least in part on the line codes of the repair order associated with the vehicle to determine whether a second condition is met, the second condition corresponding to a result identifying a component of the vehicle requiring calibration; and
generating an output identifying one or more vehicle components requiring calibration based on the result of the first condition or the second condition,
wherein said analyzing the scan data using the first class of rules comprises comparing the diagnostic codes of the scan data to a defined group of specific diagnostic trouble codes (DTCs) picked as analysis model parameters and designated as golden DTCs for the vehicle, and
wherein the first condition is met upon the scan data matching one of a set of defined combinations of: a golden DTC for the vehicle, a corresponding diagnostic code type, and a corresponding module identifier.
2 . The method of claim 1 wherein the repair order is analyzed using a machine learning model to obtain a first line code.
3 . The method of claim 2 wherein the second class of rules is created based on an analysis of repair data.
4 . The method of claim 3 wherein the repair data comprises at least one of (i) time spent on a task and (ii) cost of a particular task.
5 . The method of claim 4 wherein the repair data is further analyzed by weighing at least one of (i) time spent on a task and (ii) cost of a particular task in generation of the first line code, to generate a first weight.
6 . The method of claim 5 wherein the first weight is different than an output weight from the trained machine learning model.
7 . The method of claim 6 wherein the first weight is generated based on supervised machine learning or manually set by a human operator.
8 . The method of claim 6 wherein the first weight is generated by the machine learning model.
9 . The method of claim 2 wherein the machine learning model is a natural language processing model.
10 . The method of claim 9 wherein the machine learning model is trained using an XGBoost method.
11 . The method of claim 1 , wherein the Golden DTCs are manually tagged by a human operator.
12 . The method of claim 1 , wherein diagnostic trouble codes for a vehicle are classified as Golden DTCs using a machine learning model.
13 . The method of claim 12 wherein the machine learning model is a binary classification model.
14 . The method of claim 12 wherein the machine learning model is a clustering model.
15 . A system for determining calibration needs for a vehicle, the system comprising:
a computer system having one or more processors in communication with a memory, the memory storing instructions executable by said one or more processors to perform:
receiving, at the computer system, scan data for the vehicle, from a scan tool comprising an interface configured to communicate to an on-board diagnostic system of the vehicle, the scan data comprising one or more diagnostic codes, the diagnostic codes having respective types, and one or more module identifiers;
receiving, at the computer system, estimate data for the vehicle, the estimate data comprising one or more line codes corresponding to a repair order for the vehicle;
analyzing the scan data, using a first class of rules based at least in part on the diagnostic codes, the respective types of the diagnostic codes, and the module identifiers, to determine whether a first condition is met, the first condition corresponding to a result identifying a component of the vehicle requiring calibration;
analyzing the scan data, when it is determined that the first condition based on the first class of rules is not met, using a second class of rules based at least in part on the line codes of the repair order associated with the vehicle to determine whether a second condition is met, the second condition corresponding to a result identifying a component of the vehicle requiring calibration; and
generating an output identifying one or more vehicle components requiring calibration based on the result of the first condition or the second condition,
wherein said analyzing the scan data using the first class of rules comprises comparing the diagnostic codes of the scan data to a defined group of specific diagnostic trouble codes (DTCs) picked as analysis model parameters and designated as golden DTCs for the vehicle, and
wherein the first condition is met upon the scan data matching one of a set of defined combinations of: a golden DTC for the vehicle, a corresponding diagnostic code type, and a corresponding module identifier.
16 . The system of claim 15 , wherein the second class of rules is created based on an analysis of repair data.
17 . The system of claim 15 , wherein diagnostic trouble codes for a vehicle are classified as Golden DTCs using a machine learning model.
18 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computer system, cause said one or more processors to perform a method of determining calibration needs for a vehicle, the method comprising:
receiving, at the computer system, scan data for the vehicle, from a scan tool comprising an interface configured to communicate to an on-board diagnostic system of the vehicle, the scan data comprising one or more diagnostic codes, the diagnostic codes having respective types, and one or more module identifiers;
receiving, at the computer system, estimate data for the vehicle, the estimate data comprising one or more line codes corresponding to a repair order for the vehicle;
analyzing the scan data, using a first class of rules based at least in part on the diagnostic codes, the respective types of the diagnostic codes, and the module identifiers, to determine whether a first condition is met, the first condition corresponding to a result identifying a component of the vehicle requiring calibration;
analyzing the scan data, when it is determined that the first condition based on the first class of rules is not met, using a second class of rules based at least in part on the line codes of the repair order associated with the vehicle to determine whether a second condition is met, the second condition corresponding to a result identifying a component of the vehicle requiring calibration; and
generating an output identifying one or more vehicle components requiring calibration based on the result of the first condition or the second condition,
wherein said analyzing the scan data using the first class of rules comprises comparing the diagnostic codes of the scan data to a defined group of specific diagnostic trouble codes (DTCs) picked as analysis model parameters and designated as golden DTCs for the vehicle, and
wherein the first condition is met upon the scan data matching one of a set of defined combinations of: a golden DTC for the vehicle, a corresponding diagnostic code type, and a corresponding module identifier.
19 . The non-transitory computer-readable medium of claim 18 , wherein the second class of rules is created based on an analysis of repair data.
20 . The non-transitory computer-readable medium of claim 18 , wherein diagnostic trouble codes for a vehicle are classified as Golden DTCs using a machine learning model.