Cognitive Intelligence Platform for Distributed M2M/ IoT Systems

• US 20170006141A1
• Filed: 07/02/2015
• Published: 01/05/2017
• Est. Priority Date: 07/02/2015
• Status: Active Grant

• Current Assignee: Prasenjit Bhadra
• Original Assignee: Prasenjit Bhadra
• Inventors: Bhadra, Prasenjit
• Granted Patent: US 10,362,113 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

Systems and methods to leverage and manage data and knowledge in a M2M or Internet of Things (IoT) network are provided. More particularly, a cognitive intelligence platform for an IoT network that provides autonomic decision support system at or near real-time and executes a dynamic runtime is provided. The hardware, software and communication design of the platform replicates the structural and operational model of the human nervous system to achieve cognitive intelligence through adaptation, collaborative learning, knowledge sharing and self-adjustment. Further, in one embodiment, the cognitive intelligence platform has three logical processing layers of increasing complexity, each of which has agents that use statistical and machine learning techniques and algorithms to resolve situational needs and update knowledge. Furthermore, each processing layer of the platform has a basic level of intelligence and additionally the hierarchy of layers aggregates the learning and intelligence at each layer.

Claims

1. A system for leveraging and managing data in an Internet of Things (IoT) network, comprising:

(a) one or more IoT devices;

(b) three or more logical levels of processing in a hierarchy, with each level handling increasingly complex processing,

wherein a first level of processing resides in one or more edge controllers, each edge controller being in communication with and supervising one or more IoT devices,

wherein a second level of processing resides in one or more terminal aggregators, each terminal aggregator being in communication with and supervising one or more edge controllers, and

wherein a third level of processing resides in one or more servers, each server being in communication with and supervising one or more terminal aggregators, and

wherein each edge controller, each terminal aggregator, and each server is a participant node and comprises a processor and a memory,

 

wherein there is communication among the participant nodes in the same level of processing and with the nodes in the processing level immediately above and with the nodes in the processing level immediately below,

(c) one or more communication interfaces between the logical levels of processing and between the first logical level of processing and the one or more IoT devices;

(d) one or more programs, rules, action maps and/or knowledge stored in one or more of the memories,

wherein the one or more programs are executed by the three or more logical levels of processing,

 

wherein there is adaptive collaboration among the participant nodes the adaptive collaboration comprising;

communicating with the one or more IoT devices,

retrieving one or more known or unrecognized events or data,

each participant node resolving the one or more known events or data using the rules, action maps and/or knowledge from itself,

broadcasting the one or more unrecognized events or data to one or more of the other participant nodes,

resolving the unrecognized events or data using the rules, action maps and/or knowledge from the other participant nodes,

requesting external input if the unrecognized events or data cannot be resolved internally,

 

wherein the rules, action maps and/or knowledge are changed in response to the resolution of the events or data

 

resulting in new knowledge that is aggregated,

 

wherein the existence of the new knowledge is broadcast across the participant nodes, and

 

wherein the one or more programs are configured to self-adjust the run-time based on the new rules, update knowledge of the participant nodes based on the new knowledge, and optimize the action maps based on the updated knowledge,

whereby a dynamic run-time is established and one or more of the participant nodes acquire greater operational autonomy from the other nodes.

3. The system of claim 1, wherein the collaboration happens in real-time or near real-time.

4. The system of claim 1, wherein the processing in the three or more logical levels of processing comprises recognition of one or more patterns in the event resolution data.

5. The system of claim 1, wherein each of the three or more logical levels of processing comprise:

one or more routing buses for routing the data; and

a plurality of agents wherein the agents, and/or the rules and/or knowledge of the agents move between participant nodes across the three or more logical levels of processing in real-time or near real-time.

6. The system of claim 1, further comprising:

an external system;

an end-user monitoring interface;

or

a notification system,

wherein one or more of the three or more logical levels of processing communicates with the external system, the end-user monitoring interface, or the notification system.

7. The system of claim 1, wherein each of the one or more memories has pre-fed intelligence to process the data.

25. The system of claim 1 wherein the new knowledge resulting from the collaboration is distributed to the participant node that broadcast the event.

26. The system of claim 1 wherein,

the one or more of the edge controllers is embedded in the one or more of the IoT devices, and/or

the one or more of the terminal aggregators is embedded in the one or more of the edge controllers or one or more of the IoT devices.

2. (canceled)

8. (canceled)

9. A computer-implemented method for leveraging and managing data in an Internet of Things (IoT) network, the method comprising:

(a) receiving data from one or more IoT devices;

(b) processing the received data in one or more of three or more logical levels of processing in a hierarchy, with each level handling increasingly complex processing,

wherein a first level of processing resides in one or more edge controllers, each edge controller being in communication with and supervising one or more IoT devices,

wherein a second level of processing resides in one or more terminal aggregators, each terminal aggregator being in communication with and supervising one or more edge controllers, and

wherein a third level of processing resides in one or more servers, each server being in communication with and supervising one or more terminal aggregators, and

wherein each edge controller, each terminal aggregator, and each server is a participant node and comprises a processor and a memory,

(c) collaborating adaptively among the participant nodes, the adaptive collaboration comprising;

communicating with the one or more IoT devices,

retrieving one or more known or unrecognized events or data,

each participant node resolving the one or more known events or data using rules, action maps and/or knowledge from itself,

broadcasting the one or more unrecognized events or data to one or more of the other participant nodes,

resolving the unrecognized events or data using rules, action maps and/or knowledge from the other participant nodes,

requesting external input if the unrecognized events or data cannot be resolved internally,

wherein the rules, action maps and/or knowledge are changed in response to the resolution of the events or data

resulting in new knowledge that is aggregated,

wherein the existence of the new knowledge is broadcast across the participant nodes, and

(d) executing one or more of the programs to, self-adjust the run-time based on the new rules, update knowledge of the participant nodes based on the new knowledge, and optimize the action maps based on the updated knowledge;

whereby a dynamic run-time is established and one or more of the participant nodes acquire greater operational autonomy from the other nodes.

10. The computer-implemented method of claim 9, further comprising

deploying in real-time or near real-time one or more of a plurality of agents, and/or the rules and/or knowledge of the agents to the participant nodes across the three or more logical levels of processing for processing.

11. The computer-implemented method of claim 9, wherein the collaboration happens in real-time or near real-time.

12. The computer-implemented method of claim 9, wherein the processing in the three or more logical levels of processing comprises recognition of one or more patterns in the event resolution data.

13. The computer-implemented method of claim 9, further comprising:

storing the one or more programs, rules, action maps and/or knowledge in one or more of the memories; and

routing the data to a destination in the three or more logical levels of processing.

14. The computer-implemented method of claim 9, wherein each of the one or more memories has pre-fed intelligence to process the data.

15. The computer-implemented method of claim 9, further comprising:

one or more of the three or more logical levels of processing communicating with an external system, an end-user monitoring interface, or a notification system.

27. The system of claim 9 wherein the new knowledge resulting from the collaboration is distributed to the participant node that broadcast the event.

28. The system of claim 9 wherein,

the one or more of the edge controllers is embedded in the one or more of the IoT devices, and/or

the one or more of the terminal aggregators is embedded in the one or more of the edge controllers or one or more of the IoT devices.

16. (canceled)

17. A computer-readable non-transitory storage medium storing executable program instructions for leveraging and managing data in an Internet of Things (IoT) network which when executed by a computer cause the computer to perform operations comprising:

(a) receiving data from one or more IoT devices;

(b) processing the received data in one or more of three or more logical levels of processing in a hierarchy, with each level handling increasingly complex processing,

wherein a first level of processing resides in one or more edge controllers, each edge controller being in communication with and supervising one or more IoT devices,

wherein a second level of processing resides in one or more terminal aggregators, each terminal aggregator being in communication with and supervising one or more edge controllers, and

wherein a third level of processing resides in one or more servers, each server being in communication with and supervising one or more terminal aggregators, and

wherein each edge controller, each terminal aggregator, and each server is a participant node and comprises a processor and a memory,

(c) collaborating adaptively among the participant nodes, the adaptive collaboration comprising;

communicating with the one or more IoT devices,

retrieving one or more known or unrecognized events or data,

each participant node resolving the one or more known events or data using rules, action maps and/or knowledge from itself,

broadcasting the one or more unrecognized events or data to one or more of the other participant nodes,

resolving the unrecognized events or data using rules, action maps and/or knowledge from the other participant nodes,

requesting external input if the unrecognized events or data cannot be resolved internally,

wherein the rules, action maps and/or knowledge are changed in response to the resolution of the events or data

resulting in new knowledge that is aggregated,

wherein the existence of the new knowledge is broadcast across the participant nodes, and

(d) executing one or more of the programs to, self-adjust the run-time based on the new rules, update knowledge of the participant nodes based on the new knowledge, and optimize the action maps based on the updated knowledge;

whereby a dynamic run-time is established and one or more of the participant nodes acquire greater operational autonomy from the other nodes.

18. The computer-readable storage medium of claim 17, further comprising executable program instructions for:

deploying in real-time or near real-time one or more of a plurality of agents, and/or the rules and/or knowledge of the agents to the participant nodes across the three or more logical levels of processing for processing;

19. The computer-readable storage medium of claim 17, wherein the collaboration happens in real-time or near real-time.

20. The computer-readable storage medium of claim 17, wherein the processing in the three or more logical levels of processing comprises recognition of one or more patterns in the event resolution data.

21. The computer-readable storage medium of claim 17, further comprising executable program instructions for:

storing the one or more programs, rules, action maps and/or knowledge in one or more of the memories; and

routing the data to a destination in the three or more logical levels of processing.

22. The computer-readable storage medium of claim 17, wherein each of the one or more memories has pre-fed intelligence to process the data.

23. The computer-readable storage medium of claim 17, further comprising executable program instructions for:

one or more of the three or more logical levels of processing communicating with an external system, an end-user monitoring interface, or a notification system.

29. The system of claim 17 wherein the new knowledge resulting from the collaboration is distributed to the participant node that broadcast the event.

30. The system of claim 17 wherein,

the one or more of the edge controllers is embedded in the one or more of the IoT devices, and/or

the one or more of the terminal aggregators is embedded in the one or more of the edge controllers or one or more of the IoT devices.

24. (canceled)