Data mapping based on device profiles

A system comprising at least one computing device comprising at least one processor, a memory, and instructions executable by the at least one processor to create an application comprising:

• a) a software module identifying a plurality of data sources associated with an automation environment, wherein each data source comprises a respective data source configuration;
• b) a software module retrieving data from at least one of the identified data sources;
• c) a software module generating a plurality of data source mapping profiles, each data source mapping profile specific to a particular data source configuration, wherein generating a data source mapping profile comprises:
• i) observing network communications for a particular data source, and applying a machine learning model to generate a plurality of preliminary data source mapping profiles;
• ii) determining whether human validation is needed to update one or more of the plurality of preliminary data source mapping profiles'
• iii) conducting human validation to the one or more of the plurality of preliminary data source mapping profiles to generate an output, and sending the output as a training example to the machine learning model;
• and
• iv generating the plurality of data source mapping profiles by the machine learning model,
• d) a first data store comprising the plurality of data source mapping profiles;
• e) a software module selecting a data source mapping profile, from the plurality of data source mapping profiles, that is specific to the respective data source configuration associated with each of the at least one identified data source;
• and
• f) a software module applying a first algorithm to map the retrieved data to a predetermined ontology based on the selected data source mapping profile for the at least one identified data source.

A computer-implemented method comprising:

• a) identifying a data source associated with an automation environment and having a data source configuration;
• b) retrieving data from identified data source;
• c) generating a data source mapping profile specific to the data source configuration by performing operations comprising:
• observing network communications for a particular data source, applying a machine learning model to generate a plurality of preliminary data source mapping profiles, determining whether human validation is needed to update one or more of the plurality of preliminary data source mapping profiles;
• conducting human validation to the one or more of the plurality of preliminary data source mapping profiles to generate an output, sending the output as a training example to the machine learning model, generating a plurality of data source mapping profiles by the machine learning model, selecting a data source mapping profile from the plurality of data source mapping profiles, wherein the selected data source mapping profile is specific o the data source configuration;
• and
• d) applying an algorithm to map the retrieved data to a predetermined ontology based on the data source mapping profile for the identified data source.