Method of training a learning system to classify interfaces

A system, comprising:

• one or more processors;
• memory including executable instructions that, if executed by the one or more processors, cause the system to:
• determine a first object hierarchy path associated with a first interface of a first provider, the first interface being of a first type;
• determine a second object hierarchy path associated with a second interface of the first provider, the second interface being of a second type different from the first type;
• determine that the first object hierarchy path is a mismatch to the second object hierarchy path;
• obtain, from a second provider, a third object hierarchy path corresponding to an additional interface of the first type;
• generate a category dictionary based on a determination that the third object hierarchy path matches the first object hierarchy path;
• generate, based on the category dictionary and the first object hierarchy path, a first vector that corresponds to the first type;
• and
• generate, based on the category dictionary and the second object hierarchy path, a second vector that corresponds to the second type;
• and
• train a machine learning algorithm to categorize interfaces based on:
• the first vector with the first type as a ground truth value;
• and
• the second vector with the second type as the ground truth value.

A non-transitory computer-readable storage medium having stored thereon executable instructions that, if executed by one or more processors of a computer system, cause the computer system to at least:

• determine a set of intersecting object hierarchy paths between a first set of object hierarchy paths of a first interface of a first interface provider and a second set of object hierarchy paths of a second interface provided by a second interface provider, the first interface and the second interface corresponding to a first interface type;
• generate a first set of feature vectors based on:
• the set of intersecting object hierarchy paths;
• and
• the first set of object hierarchy paths;
• generate a second set of feature vectors based on:
• the set of intersecting object hierarchy paths;
• and
• a third set of object hierarchy paths corresponding to a third interface of the first interface provider, the third interface corresponding to a second interface type;
• and
• train, using the first set of feature vectors and the second set of feature vectors, a machine learning algorithm to distinguish between feature vectors corresponding to the first interface type and feature vectors corresponding to a second interface type different from the first interface type.