Anomaly detection of physical assets by auto-creating anomaly detection or prediction models based on data from a knowledge graph of an enterprise

A computer system, comprising:

• a system memory;
• one or more processors configured to execute computer readable program instructions from the system memory for:
• obtaining data from a knowledge graph associated with an enterprise, the knowledge graph including a plurality of node descriptors that indicate locations, assets, and sensor data feeds of the enterprise, and a plurality of relationship descriptors that indicate relationships amongst the locations, the assets, and the sensor data feeds of the enterprise;
• auto-creating an anomaly detection model associated with a selected one of the plurality of node descriptors based on the data from the knowledge graph, which includes selecting one of a plurality of model types for auto-creation of the anomaly detection model based on an identified node type of the selected node descriptor, wherein selecting one of the plurality of model types for auto-creation includes:
• selecting an unsupervised univariable anomaly detection model type as the selected model type based on identifying the identified node type as a leaf node type;
• and
• selecting an unsupervised multivariable anomaly detection model type as the selected model type based on identifying the identified node type as a non-leaf node type;
• monitoring, by the anomaly detection model, a location, asset, or sensor data feed associated with the selected node descriptor to detect an anomaly;
• and
• controlling a machine asset of the enterprise to regulate operating conditions associated with the location, asset, or sensor data feed having the detected anomaly.

A computer program product comprising one or more computer readable storage media having computer readable program instructions collectively stored on the one or more computer readable storage media, the computer readable program instructions being executable by a computer system to cause the computer system to:

• obtain data from a knowledge graph associated with an enterprise, the knowledge graph including a plurality of node descriptors that indicate locations, assets, and sensor data feeds of the enterprise, and a plurality of relationship descriptors that indicate relationships amongst the locations, the assets, and the sensor data feeds of the enterprise;
• auto-create an anomaly detection model associated with a selected one of the plurality of node descriptors based on the data from the knowledge graph, which includes selecting one of a plurality of model types for auto-creation of the anomaly detection model based on an identified node type of the selected node descriptor, wherein selecting one of the plurality of model types for auto-creation includes:
• selecting an unsupervised univariable anomaly detection model type as the selected model type based on identifying the identified node type as a leaf node type;
• and
• selecting an unsupervised multivariable anomaly detection model type as the selected model type based on identifying the identified node type as a non-leaf node type;
• monitor, by the anomaly detection model, a location, asset, or sensor data feed associated with the selected node descriptor to detect an anomaly;
• and
• control a machine asset of the enterprise to regulate operating conditions associated with the location, asset, or sensor data feed having the detected anomaly.