Far edge/IOT intelligence design and apparatus for human operators assistance
One example method is performed at a far edge device and includes collecting data with one or more IoT (Internet of Things) devices, feeding the data to a feedback loop that includes multiple stages, running the feedback loop, providing learning information, comprising output from one or more of the stages of the feedback loop, to a central manager by way of a learn interface, accessing learning information generated by one or more other far edge devices, and updating the feedback loop using the learning information generated by the one or more other far edge devices.
1 . A method, comprising:
performing, by a model running on a far edge knowledge manage instance at a far edge device, operations comprising:
collecting data with one or more IoT (Internet of Things) devices;
feeding the data to a feedback loop that includes multiple stages;
running the feedback loop;
providing learning information, comprising output from one or more of the multiple stages of the feedback loop, to a central manager by way of a learn interface;
accessing learning information, which is generated by the central manager based on data fed by one or more other far edge devices; and
updating the model using the learning information generated by the central manager based on the data fed by the one or more other far edge devices,
wherein the far edge device operates autonomously with respect to the one or more other far edge devices, while also incorporating learnings generated by the one or more other far edge devices.
2 . The method as recited in claim 1 , wherein the data comprises data about an impending situation which, if the impending situation occurs, presents a threat to life and/or property.
3 . The method as recited in claim 1 , wherein running the feedback loop comprises:
processing the data;
detecting an abnormal situation indicated by the data;
generating a warning to a human, wherein the warning concerns the abnormal situation; and
receiving input indicating that the human has taken an action regarding the abnormal situation.
4 . The method as recited in claim 1 , wherein the operations further comprise running the feedback loop after it has been updated.
5 . The method as recited in claim 1 , wherein the operations further comprise determining a macro-state for a system that includes the far edge device and the one or more other far edge devices.
6 . The method as recited in claim 5 , wherein the macro-state is specific to a particular situation.
7 . The method as recited in claim 5 , wherein the macro-state is determined based upon one or more micro-states of the one or more other far edge devices and the far edge device.
8 . The method as recited in claim 1 , wherein the learning information is advertised by the far edge device to one of the one or more other far edge devices.
9 . The method as recited in claim 1 , wherein the feedback loop is updated using a transfer learning process.
10 . A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors of a far edge device to perform operations, by a model running on a far edge knowledge manage instance, comprising:
collecting data with one or more IoT (Internet of Things) devices;
feeding the data to a feedback loop that includes multiple stages;
running the feedback loop;
providing learning information, comprising output from one or more of the multiple stages of the feedback loop, to a central manager by way of a learn interface;
accessing learning information, which is generated by the central manager based on data fed by one or more other far edge devices; and
updating the model using the learning information generated by the central manager based on the data fed by the one or more other far edge devices,
wherein the far edge device operates autonomously with respect to the one or more other far edge devices, while also incorporating learnings generated by the one or more other far edge devices.
11 . The non-transitory storage medium as recited in claim 10 , wherein the data comprises data about an impending situation which, if the impending situation occurs, presents a threat to life and/or property.
12 . The non-transitory storage medium as recited in claim 10 , wherein running the feedback loop comprises:
processing the data;
detecting an abnormal situation indicated by the data;
generating a warning to a human, wherein the warning concerns the abnormal situation; and
receiving input indicating that the human has taken an action regarding the abnormal situation.
13 . The non-transitory storage medium as recited in claim 10 , wherein the operations further comprise running the feedback loop after it has been updated.
14 . The non-transitory storage medium as recited in claim 10 , wherein the operations further comprise determining a macro-state for a system that includes the far edge device and the one or more other far edge devices.
15 . The non-transitory storage medium as recited in claim 14 , wherein the macro-state is specific to a particular situation.
16 . The non-transitory storage medium as recited in claim 14 , wherein the macro-state is determined based upon one or more micro-states of the one or more other far edge devices and the far edge device.
17 . The non-transitory storage medium as recited in claim 10 , wherein the learning information is advertised by the far edge device to one of the one or more other far edge devices.
18 . The non-transitory storage medium as recited in claim 10 , wherein the feedback loop is updated using a transfer learning process.