Interoperability mechanisms for internet of things integration platform

• US 10,353,939 B2
• Filed: 01/23/2017
• Issued: 07/16/2019
• Est. Priority Date: 07/11/2013
• Status: Active Grant

• Current Assignee: Neura Inc (Otonomo Technologies Ltd.)
• Original Assignee: Neura Inc (Otonomo Technologies Ltd.)
• Inventors: Shaashua, Triinu Magi, Shaashua, Ori
• Primary Examiner(s): Vostal, Ondrej C
• Application Number:
  US15/413,158
• Publication Number:
  US 20170220940A1
• Time in Patent Office: 904 Days
• Field of Search: 709224
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 43/10 Active monitoring, e.g. heartbeat, ping or trace-route
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• 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]

Abstract

A method of maintaining interoperability amongst Internet of Things (IoT) devices connected via an IoT integration platform is disclosed. The method includes: receiving a selection of a semantic label associated with an IoT device; determining a recommendation of an interoperable rule based on the semantic label, the interoperable rule having a condition trigger and an action policy for execution at satisfaction of the condition trigger; presenting the recommendation on a rule management interface; and receiving a confirmation from a user through the rule management interface to activate the interoperable rule.

Claims

1. A method of deriving semantic meaning of Internet of Things (IoT) devices connected via an IoT integration platform, comprising:

collecting device data from a plurality of IoT devices connected via the IoT integration platform;

determining a set of features by analyzing corresponding time series of events among any of the plurality of IoT devices and generating one or more clusters correlating the device data using natural language processing;

performing behavioral analysis to identify one or more user behaviors, wherein the behavioral analysis comprises incrementally populating a profile with device data associated with either of a particular IoT device or a particular user, and applying a model to the profile to identify behavioral patterns and behavior changes;

determining, by utilizing a probabilistic measure, a semantic meaning associated with any device among the plurality of IoT devices based on any of the set of features and the identified one or more behaviors; and

generating, based on the determined semantic meaning, an interoperable rule to control one or more of the plurality of IoT devices.

2. The method of claim 1, wherein the device data includes geolocation data, broadcast data, device protocol, data received by an IoT device, data transmitted by an IoT device, data services information, or any combination thereof.

3. The method of claim 1, further comprising:

collecting public data from a public library and/or a public device;

mapping the public data to the collected device data; and

determining another set of features based on identified correlation based on the mapping.

4. The method of claim 3, wherein determining the semantic meaning is further based on the determined another set of features.

5. The method of claim 1, wherein determining the set of features is performed using a machine learning model, a statistical model, a rules model, a scoring model, incremental calculations, or any combination thereof.

6. The method of claim 1, wherein determining the set of features is performed by applying an adaptive correlation mechanism to one or more previously generated data models to generate an aggregate data model.

7. The method of claim 1, wherein determining the set of features further comprises:

identifying an event trigger resulting from analyzing the corresponding time series of events.

8. The method of claim 1, wherein determining the set of features further comprises:

labeling any of the one or more clusters with a label corresponding to a meaning identified in the device data associated with a particular cluster.

9. The method of claim 8, wherein determining the semantic meaning is further based on the label corresponding to the meaning identified in the device data associated with a particular cluster.

10. The method of claim 1,

wherein the interoperable rule includes a condition trigger to be detected by at least a first IoT device and an action policy to be executed by at least a second IoT device at satisfaction of the condition trigger, wherein the IoT device associated with the determined semantic meaning is the first IoT device for detecting the condition trigger, the second IoT device for executing the action policy, or both.

11. The method of claim 10, further comprising:

upon detecting the condition trigger, executing the action policy on the second IoT device, wherein the action policy includes inducing a label.

12. A method of deriving semantic meaning of Internet of Things (IoT) devices connected via an IoT integration platform, comprising:

monitoring device data from a plurality of IoT devices connected via the IoT integration platform;

determining a set of features by analyzing corresponding time series of events among any of the plurality of IoT devices by applying an adaptive correlation mechanism to one or more previously generated data models to generate an aggregate data model, and generating one or more clusters correlating the device data using natural language processing;

performing behavioral analysis to identify one or more user behaviors;

determining, by utilizing a probabilistic measure, a semantic meaning associated with any device among the plurality of IoT devices based on any of the set of features and the identified one or more behaviors; and

generating, based on the determined semantic meaning, an interoperable rule to control one or more of the plurality of IoT devices.

13. The method of claim 12, wherein the behavioral analysis comprises incrementally populating a profile with device data associated with either of a particular IoT device or a particular user, and applying a model to the profile to identify behavioral patterns and behavior changes.

14. The method of claim 12, further comprising:

collecting public data from a public library and/or a public device;

mapping the public data to the collected device data; and

determining another set of features based on identified correlation based on the mapping.

15. The method of claim 12, wherein determining the set of features further comprises:

labeling any of the one or more clusters with a label corresponding to a meaning identified in the device data associated with a particular cluster,

wherein determining the semantic meaning is further based on the label corresponding to the meaning identified in the device data associated with a particular cluster.

16. A machine-implemented integration platform system for deriving semantic meaning of Internet of Things (IoT) devices connected thereto, the integration platform system comprising:

a communication interface having protocols to communicate with the plurality of IOT devices;

one or more processors connected to the communication interface, wherein the one or more processors are configured to;

collect device data, via the communication interface, from a plurality of IoT devices;

determine a set of features by analyzing corresponding time series of events among any of the plurality of IoT devices and generating one or more clusters correlating the device data using natural language processing;

perform behavioral analysis to identify one or more user behaviors, wherein the behavioral analysis comprises incrementally populating a profile with device data associated with either of a particular IoT device or a particular user, and applying a model to the profile to identify behavioral patterns and behavior changes;

determine, by utilizing a probabilistic measure, a semantic meaning associated with any device among the plurality of IoT devices based on any of the set of features and the identified one or more behaviors; and

generate, based on the determined semantic meaning, an interoperable rule to control one or more of the plurality of IoT devices.

17. The system of claim 16, wherein the one or more processors are further configured to:

labeling any of the one or more clusters with a label corresponding to a meaning identified in the device data associated with a particular cluster,

wherein determining the semantic meaning is further based on the label corresponding to the meaning identified in the device data associated with a particular cluster.

18. The system of claim 16, wherein the one or more processors are further configured to generate the interoperable rule by:

identifying an event trigger resulting from analyzing the corresponding time series of events.

19. The system of claim 16, further comprising:

an event track module configured to detect an event trigger among the plurality of IoT devices connected to the IoT integration platform by monitoring data collected from one or more sensors of the plurality of IoT devices.

20. The system of claim 19, further comprising:

a rule execution module, coupled to the event track module to receive an indication that the event trigger is detected, configured to execute an action policy by controlling one or more of the plurality of IoT devices when the event trigger is detected by the event track module.