Automotive can decoding using supervised machine learning

A system, comprising:

• one or more processors;
• and
• a memory having stored thereon instructions that, upon execution by the one or more processors, cause the one or more processors to:
• provide one or more testing maneuvers to perform on a vehicle via a graphical user interface, wherein the one or more testing maneuvers are associated with a component of the vehicle;
• receive a stream of messages from a controller area network (CAN) bus of the vehicle in response to a technician performing the one or more testing maneuvers, each message comprising a message identifier, a byte number, and a value for the byte number, wherein the byte number represents a location of data within the message;
• isolate a component message identifier and a component byte number associated with the component based on the messages in the stream of messages, wherein isolating the component message identifier and the component byte number comprises using a supervised machine learning algorithm to:
• identify a subset of byte numbers within the stream of messages having changing values;
• select a subset of rules from a plurality of rules associated with the component;
• and
• select the component message identifier and the component byte number based on applying the subset of rules to each byte number of the subset of byte numbers.

A computer-readable media device having stored thereon instructions that, upon execution by one or more processors, cause the one or more processors to:

• provide one or more testing maneuvers to perform on a vehicle via a graphical user interface, wherein the one or more testing maneuvers are associated with a component of the vehicle;
• receive a stream of messages from a controller area network (CAN) bus of the vehicle in response to a technician performing the one or more testing maneuvers, each message comprising a message identifier, a byte number, and a value for the byte number, wherein the byte number represents a location of data within the message;
• isolate a component message identifier and a component byte number associated with the component based on the messages in the stream of messages, wherein isolating the component message identifier and the component byte number comprises using a supervised machine learning algorithm to:
• identify a subset of byte numbers within the stream of messages having changing values;
• select a subset of rules from a plurality of rules associated with the component;
• and
• select the component message identifier and the component byte number based on applying the subset of rules to each byte number of the subset of byte numbers.