Identifying clusters of similar sensors
AssigneeArundo Analytics, Inc.
InventorsMatthew Strecker Burriesci, Martin Lee
Life of this patent
Estimating the term…
Abstract
A system and method including receiving sets of sensor data associated with sensors configured to monitor one or more systems. Sensor fingerprints are generated for each set of sensor data based on the sensor data. At least one proximity value is computed for each sensor by comparing the fingerprint of that sensor with another fingerprint. Clusters of similar sensors are identified based at least upon the proximity values of the sensors.
Claims8
A computer-implemented method comprising:
- receiving a set of sensor data comprising at least one of sensor readings data and sensor metadata associated with a sensor configured to monitor equipment;
- generating a sensor fingerprint for the sensor based at least in part on the set of sensor data;
- computing at least one proximity value for the sensor, wherein computing the at least one proximity value comprises comparing the sensor fingerprint to another fingerprint which is at least one of another sensor fingerprint and a derivative fingerprint derived from a plurality of other sensors;
- and
- identifying a similarity cluster for the sensor based at least upon the at least one proximity value for the sensor;
- wherein the sensor fingerprint and the other fingerprint are points in an n-dimensional space;
- wherein each of the n-dimensions corresponds to a characteristic of the set of sensor data;
- and
- wherein the proximity value is a distance in the n-dimensional space between the sensor fingerprint and the other fingerprint.
A system comprising:
- one or more processing units;
- and
- one or more memory units coupled to the one or more processing units, wherein:
- the one or more memory units are configured to store instructions,
- the one or more processing units are configured to execute the instructions causing the system to perform operations comprising:
- receiving a set of sensor data comprising at least one of sensor metadata and sensor readings data associated with a sensor configured to monitor equipment;
- generating a sensor fingerprint for the sensor based at least in part on the set of sensor data;
- computing at least one proximity value for the sensor, wherein computing the at least one proximity value comprises comparing the sensor fingerprint to another fingerprint which is at least one of another sensor fingerprint and a derivative fingerprint derived from a plurality of other sensors;
- and
- identifying a similarity cluster for the sensor based at least upon the at least one proximity value for the sensor;
- wherein the sensor fingerprint and the other fingerprint are points in an n-dimensional space;
- wherein each of the n-dimensions corresponds to a characteristic of the set of sensor data;
- and
- wherein the proximity value is a distance in the n-dimensional space between the sensor fingerprint and the other fingerprint.
At least one non-transitory, machine-accessible storage medium having instructions stored thereon, wherein the instructions are configured, when executed on a machine, to cause the machine to perform operations comprising:
- receiving a set of sensor data comprising at least one of sensor metadata and sensor readings data associated with a sensor configured to monitor equipment;
- generating a sensor fingerprint for the sensor based at least in part on the set of sensor data;
- computing at least one proximity value for the sensor, wherein computing the at least one proximity value comprises comparing the sensor fingerprint to another fingerprint which is at least one of another sensor fingerprint and a derivative fingerprint derived from a plurality of other sensors;
- and
- identifying a similarity cluster for the sensor based at least upon the at least one proximity value for the sensor;
- wherein the sensor fingerprint and the other fingerprint are points in an n-dimensional space;
- wherein each of the n-dimensions corresponds to a characteristic of the set of sensor data;
- and
- wherein the proximity value is a distance in the n-dimensional space between the sensor fingerprint and the other fingerprint.
Dependencies are inferred from the claim text.