Dynamic execution of predictive models and workflows

Patent metadata

Field	Value
Publication number	US-10176279-B2
Application number	US-201514744362-A
Country	US
Kind code	B2
Filing date	Jun 19, 2015
Priority date	Jun 5, 2015
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

Disclosed herein are systems, devices, and methods related to assets and predictive models and corresponding workflows that are related to the operation of assets. In particular, examples involve defining and deploying aggregate, predictive models and corresponding workflows, defining and deploying individualized, predictive models and/or corresponding workflows, and dynamically adjusting the execution of model-workflow pairs.

First claim

The invention claimed is:

1. A computing system comprising:
a network interface configured to facilitate communication with a plurality of assets via a communication network;
at least one processor;
a non-transitory computer-readable medium; and
program instructions stored on the non-transitory computer-readable medium that are executable by the at least one processor to cause the computing system to:
centrally define a predictive model that is related to the operation of at least one given asset of the plurality of assets, wherein the given asset is equipped with the capability to locally execute at least a portion of the predictive model;
begin to centrally execute the predictive model for the given asset;
transmit at least a portion of the predictive model to the given asset for local execution;
detect an indication that at least some responsibility for executing the predictive model has been shifted to the given asset;
in response to the detected indication, modify the responsibility of the computing system with respect to central execution of the predictive model for the given asset; and
operate in accordance with the modified responsibility.

2. The computing system of claim 1 , wherein the program instructions that are executable to cause the computing system to detect the indication comprise program instructions that are executable to cause the computing system to:
receive data from the given asset; and
based on the received data, detect that the given asset has begun locally executing at least a portion of the predictive model.

3. The computing system of claim 2 , wherein the program instructions that are executable to cause the computing system to detect that the given asset has begun locally executing at least a portion of the predictive model comprise program instructions that are executable to cause the computing system to detect a change in one or more of (a) a type of the received data, (b) an amount of the received data, and (c) a frequency at which the received data is received.

4. The computing system of claim 2 , wherein the received data comprises data generated by at least one of a plurality of sensors or a plurality of actuators at the given asset, and wherein the program instructions that are executable to cause the computing system to detect that the given asset has begun locally executing at least a portion of the predictive model comprise program instructions that are executable to cause the computing system to detect a change in the at least one of the plurality of sensors or the plurality of actuators that generated the data.

5. The computing system of claim 1 , wherein the program instructions that are executable to cause the computing system to modify the responsibility of the computing system with respect to central execution of the predictive model for the given asset comprise program instructions that are executable to cause the computing system to centrally execute only a portion of the predictive model for the given asset.

6. The computing system of claim 1 , wherein the program instructions that are executable to cause the computing system to modify the responsibility of the computing system with respect to central execution of the predictive model for the given asset comprise program instructions that are executable to cause the computing system to cease central execution of the predictive model for the given asset.

7. The computing system of claim 1 , wherein the program instructions that are executable to cause the computing system to detect the indication comprise program instructions that are executable to cause the computing system to:
detect a change in a characteristic of the communication network that communicatively couples the given asset and the computing system.

8. The computing system of claim 7 , wherein the characteristic of the communication network is a signal strength.

9. A non-transitory computer-readable medium having instructions stored thereon that are executable to cause a computing system to:
centrally define a predictive model that is related to the operation of at least one given asset of a plurality of assets, wherein the given asset is equipped with the capability to locally execute at least a portion of the predictive model;
begin to centrally execute the predictive model for the given asset transmit at least a portion of the predictive model to the given asset for local execution;
detect an indication and that at least some responsibility for executing the predictive model has been shifted to the given asset;
in response to the detected indication, modify the responsibility of the computing system with respect to central execution the predictive model for the given asset; and
operate in accordance with the modified responsibility.

10. The non-transitory computer-readable medium of claim 9 , wherein the instructions that are executable to cause the computing system to detect the indication comprise instructions that are executable to cause the computing system to:
receive data from the given asset; and
based on the received data, detect that the given asset has begun locally executing at least a portion of the predictive model.

11. The non-transitory computer-readable medium of claim 10 , wherein the instructions that are executable to cause the computing system to detect that the given asset has begun locally executing at least a portion of the predictive model comprise instructions that are executable to cause the computing system to detect a change in one or more of (a) a type of the received data, (b) an amount of the received data, and (c) a frequency at which the received data is received.

12. The non-transitory computer-readable medium of claim 10 , wherein the received data comprises data generated by at least one of a plurality of sensors or a plurality of actuators at the given asset, and wherein the instructions that are executable to cause the computing system to detect that the given asset has begun locally executing at least a portion of the predictive model comprise instructions that are executable to cause the computing system to detect a change in the at least one of the plurality of sensors or the plurality of actuators that generated the data.

13. The non-transitory computer-readable medium of claim 9 , wherein the computing system and the given asset are communicatively coupled via a communication network, and wherein the instructions that are executable to cause the computing system to detect the indication comprise instructions that are executable to cause the computing system to:
detect a change in a characteristic of the communication network.

14. The non-transitory computer-readable medium of claim 9 , wherein the instructions that are executable to cause the computing system to modify the responsibility of the computing system with respect to central execution of the predictive model for the given asset comprise instructions that are executable to cause the computing system to either (a) centrally execute only a portion of the predictive model for the given asset or (b) cease central execution of the predictive model for the given asset.

15. A computer-implemented method comprising:
centrally defining, by a computing system, a predictive model that is related to the operation of at least one given asset of a plurality of assets;
transmitting, by the computing system to the given asset, at least a portion of the predictive model for local execution, wherein the given asset is equipped with the capability to locally execute at least a portion of the predictive model;
beginning to centrally execute the predic

Assignees

• Uptake Tech Inc

Inventors

• Nicholas Brad

Classifications

• G05B2219/34477

  Fault prediction, analyzing signal trends · CPC title

• G06F9/46

  Multiprogramming arrangements · CPC title

• G05B23/0254 Primary

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title

• G05B13/048

  using a predictor · CPC title

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title