Cognitive intelligence platform for distributed M2M/ IoT systems

• US 10,362,113 B2
• Filed: 07/02/2015
• Issued: 07/23/2019
• Est. Priority Date: 07/02/2015
• Status: Active Grant

• Current Assignee: Prasenjit Bhadra
• Original Assignee: Prasenjit Bhadra
• Inventors: Bhadra, Prasenjit
• Primary Examiner(s): Survillo, Oleg
• Application Number:
  US14/790,655
• Publication Number:
  US 20170006141A1
• Time in Patent Office: 1,482 Days
• Field of Search: 709217
• 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 computer-implemented method for decision support for an Internet of Things (IoT) network operating in an external environment comprising IoT devices, the method comprising:

(a) retrieving, via one or more edge controllers, inputs from one or more of the IoT devices; and

(b) processing the inputs with one or more edge controllers, one or more terminal aggregators, and one or more servers organized into three or more levels of processing, wherein each of the one or more edge controllers, each of the one or more terminal aggregators, and each of the one or more servers is a participant node;

the processing comprising the steps of;

(i) a first participant node matching the retrieved inputs against currently available knowledge within the first participant node;

(ii) wrapping the inputs into application level events;

(iii) attempting to qualify events using event qualifiers stored in the first participant node;

(iii) classifying each qualifying event as a command, measurement, or application service request; and

(iv) dispatching the qualified events to their respective service end points;

wherein;

at least one of the events is a non qualifying an unqualified event, and the processing further comprises the steps of;

(v) the first participant node broadcasting the unqualified event into the IoT network;

(vi) one or more participant nodes other than the first participant node, attempting to resolve the unqualified event using their respective stored event qualifiers;

(vii) if the unqualified event is qualified at step (vi), classifying the event as a command, measurement, or application service request, and dispatching the event to its service end point;

otherwise,

raising an alarm requesting external input from an external system or from a human operator, receiving the external input, and resolving the event based on the external input;

(viii) changing one or more selected from the group consisting of rules, action maps and knowledge, in response to the resolution of the unqualified event, resulting in new knowledge;

(ix) broadcasting the new knowledge across the participant nodes, thereby updating the available knowledge within the participant nodes; and

(x) optimizing the action maps based on the updated knowledge.

2. The computer-implemented method of claim 1, further comprising deploying in real-time or near real-time one or more selected from the group consisting of agents, changed rules, and updated knowledge of the agents, to the participant nodes across the three or more levels of processing.

3. The computer-implemented method of claim 1, wherein the resolution of the events and the broadcasting of the new knowledge take place in real-time or near real-time.

4. The computer-implemented method of claim 1, wherein the qualifying of the events comprises recognition of one or more event patterns.

5. The computer-implemented method of claim 1, further comprising the participant nodes within the three or more levels of processing communicating with an end-user monitoring interface or a notification system.

6. A computer-readable non-transitory storage medium storing executable program instructions for decision support for an Internet of Things (IoT) network operating in an external environment comprising IoT devices, which when executed by a computer cause the IoT network to perform operations comprising:

(a) retrieving, via one or more edge controllers, inputs from one or more of the IoT devices; and

(b) processing the inputs with one or more edge controllers, one or more terminal aggregators, and one or more servers organized into three or more levels of processing, wherein each of the one or more edge controllers, each of the one or more terminal aggregators, and each of the one or more servers is a participant node;

the processing comprising the steps of;

(i) a first participant node matching the retrieved inputs against currently available knowledge within the first participant node;

(ii) wrapping the inputs into application level events;

(iii) attempting to qualify events using event qualifiers stored in the first participant node;

(iii) classifying each qualifying event as a command, measurement, or application service request; and

(iv) dispatching the qualified events to their respective service end points;

wherein;

at least one of the events is an unqualified event, and the processing further comprises the steps of;

(v) the first participant node broadcasting the unqualified event into the IoT network;

(vi) one or more participant nodes other than the first participant node, attempting to resolve the unqualified event using their respective stored event qualifiers;

(vii) if the unqualified event is qualified at step (vi), classifying the event as a command, measurement, or application service request, and dispatching the event to its service end point;

otherwise,

raising an alarm requesting external input from an external system or from a human operator, receiving the external input, and resolving the event based on the external input;

(viii) changing one or more selected from the group consisting of rules, action maps and knowledge, in response to the resolution of the unqualified event, resulting in new knowledge;

(ix) broadcasting the new knowledge across the participant nodes, thereby updating the available knowledge within the participant nodes; and

(x) optimizing the action maps based on the updated knowledge.

7. The computer-readable storage medium of claim 6, further comprising executable program instructions for resolution of the events and the broadcasting of the new knowledge in real-time or near real-time.

8. The computer-readable storage medium of claim 7, further comprising executable program instructions for deploying in real-time or near real-time one or more selected from the group consisting of agents, the rules, and knowledge of the agents to the participant nodes across the three or more levels of processing.

9. The computer-readable storage medium of claim 6, further comprising executable program instructions for storing data selected from the group consisting of programs, rules, action maps and knowledge in one or more of the memories;

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

10. A decision support system for an Internet of Things (IoT) network, operating in an external environment comprising IoT devices, the support system comprising:

(A) a plurality of edge controllers, a plurality of terminal aggregators, and one or more servers, organized into three or more levels of processing;

the three or more levels of processing being organized in a hierarchy, with each level handling increasingly complex processing,

wherein a first level of processing comprises the plurality of edge controllers, each edge controller being in communication with one or more other edge controllers, and in communication with one or more of the IoT devices;

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

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

wherein each of the plurality of edge controllers, each of the plurality of terminal aggregators, and each of the one or more servers is a participant node and comprises a processor and a memory;

(B) communication interfaces between the levels of processing and between the first level of processing and the IoT devices; and

(C) programs, rules, action maps and knowledge, stored in one or more of the memories, wherein each of the programs is executable in a run-time environment by at least one of the processors in the three or more levels of processing;

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

(a) retrieving, via one or more edge controllers, inputs from one or more of the IoT devices; and

(b) processing the inputs with one or more edge controllers, one or more terminal aggregators, and one or more servers;

the processing comprising the steps of;

(i) a first participant node matching the retrieved inputs against currently available knowledge within the first participant node;

(ii) wrapping the inputs into application level events;

(iii) attempting to qualify events using event qualifiers stored in the first participant node;

(iii) classifying each qualifying event as a command, measurement, or application service request; and

(iv) dispatching the qualified events to their respective service end points;

wherein;

at least one of the events is an unqualified event, and the processing further comprises the steps of;

(v) the first participant node broadcasting the unqualified event into the IoT network;

(vi) one or more participant nodes other than the first participant node, attempting to resolve the unqualified event using their respective stored event qualifiers;

(vii) if the unqualified event is qualified at step (vi), classifying the event as a command, measurement, or application service request, and dispatching the event to its service end point;

otherwise,

raising an alarm requesting external input from an external system or from a human operator, receiving the external input, and resolving the event based on the external input;

(viii) changing one or more selected from the group consisting of rules, action maps and knowledge, in response to the resolution of the unqualified event, resulting in new knowledge;

(ix) broadcasting the new knowledge across the participant nodes, thereby updating the available knowledge within the participant nodes; and

(x) optimizing the action maps based on the updated knowledge.

11. The system of claim 10, wherein the resolution of the events and the broadcasting of the new knowledge take place in real-time or near real-time.

12. The system of claim 10, wherein:

(a) at least one of the edge controllers is embedded in at least one of the IoT devices, or

(b) at least one of the terminal aggregators is embedded in at least one of the edge controllers, or

(c) at least one of the terminal aggregators is embedded in at least one of the IoT devices.

13. The system of claim 10, wherein each of the three or more levels of processing comprises:

one or more routing buses for routing data; and

a plurality of agents;

wherein one or more selected from the group consisting of the agents, the rules, and the knowledge of the agents move between participant nodes across the three or more levels of processing in real-time or near real-time.

14. The system of claim 10, further comprising one or more selected from the group consisting of:

the external system,

an end-user monitoring interface, and

a notification system;

wherein one or more of the three or more levels of processing communicates with one or more selected from the group consisting of the external system, the end-user monitoring interface, and the notification system.