Systems and methods for creating virtual devices
A virtual device management system for creating and implementing virtual devices and associated methods are provided herein. The system presents to a user a list of devices available for combining to create the virtual device. When the system receives from the user a selection of two or more devices that the user wishes to combine to create the virtual device, the system presents to the user a list of available functions that can be performed by the virtual device based on the selected devices. The system then receives from the user a selection of one or more functions and configures the virtual device to perform the selected functions. The system can also be configured to present, via a user interface via a mobile application running on a user device, a plurality of virtual devices with predetermined functionalities that are created by detecting the various connected devices within an IoT network.
1. A non-transitory medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
obtaining data that indicates usage of a computing system that includes a controller and a plurality of physical devices, each of which is configurably connected to the controller;
generating, based on an analysis of the data, (i) a device set that specifies the plurality of physical devices and (ii) an action set that specifies actions involving the plurality of physical devices;
representing each action in the action set as a feature vector that includes at least one value for at least one feature of that action, so as to generate a set of feature vectors;
applying a machine learning algorithm to the set of feature vectors to identify a pair of physical devices that are used in combination with each other; and
presenting, via an interface, a recommendation to create a virtual device by combining the pair of physical devices.
2. The non-transitory medium of claim 1 , wherein the virtual device is one of multiple virtual devices specified in the recommendation, and wherein each of the multiple virtual devices corresponds to a separate recipe.
3. The non-transitory medium of claim 2 , wherein recipes are presented based on common use cases, frequency of use, frequency of related actions performed by a user, or any combination thereof.
4. The non-transitory medium of claim 2 , wherein the plurality of physical devices includes at least two of a camera, a door lock, a doorbell, a light, a sensor, a robotic vacuum, a speaker, and an electrical outlet.
5. The non-transitory medium of claim 2 , wherein the operations further comprise:
presenting, via the interface, functions associated with the plurality of physical devices; and
receiving input that is indicative of a selection of one of the functions;
wherein the machine learning algorithm is applied to the set of feature vectors to identify the pair of physical devices that are able to achieve the selected function.
6. A method for creating a virtual device that is representative of a combination of a pair of physical devices, the method comprising:
identifying a plurality of physical devices that are configurably connected to at least one controller;
generating, based on an analysis of usage of the plurality of physical devices, an action set that specifies actions involving the plurality of physical devices;
representing each action in the action set as a feature vector, so as to generate a set of feature vectors;
applying a machine learning algorithm to the set of feature vectors to identify a pair of physical devices that are used in combination with each other; and
presenting, via an interface, a recommendation to create a virtual device by combining the pair of physical devices.
7. The method of claim 6 , wherein each feature vector in the set of feature vectors includes at least one value for at least one feature of the corresponding action in the action set.
8. The method of claim 6 , further comprising:
receiving, via the interface, input that is indicative of a confirmation to create the virtual device; and
configuring the virtual device to perform a function by implementing a rule for at least one of the pair of physical devices.
9. The method of claim 8 , further comprising:
extracting, based on an analysis of the action set, the function from actions performed by the pair of physical devices.
10. The method of claim 6 , further comprising:
checking compatibility of the pair of physical devices, so as to ensure that the pair of physical devices are combinable to create the virtual device.
11. The method of claim 10 , wherein checking the compatibility includes checking a logical relationship and/or a spatial relationship of the pair of physical devices.
12. The method of claim 10 , wherein the pair of physical devices includes a first physical device and a second physical device, and wherein checking the compatibility includes:
establishing a first location of the first physical device,
establishing a second location of the second physical device, and
permitting creation of the virtual device in response to a determination, based on an analysis of the first and second locations, that the first and second physical devices are located in a same room or otherwise logically associated with each other.
13. The method of claim 6 , wherein the pair of physical devices includes a first physical device and a second physical device, and wherein the machine learning algorithm identifies the pair of physical devices based on a determination that the first and second physical devices are used within a specified duration of each other.
14. The method of claim 6 , wherein the pair of physical devices includes a first physical device and a second physical device, and wherein the machine learning algorithm identifies the pair of physical devices based on a determination that the first and second physical devices are used in combination with each other more frequently than a given frequency.
15. A non-transitory medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
obtaining data that indicates usage of a plurality of physical devices that operate in a networked environment;
generating, based on an analysis of the data, a set of feature vectors, each of which represents an action involving one of the plurality of physical devices;
applying a machine learning algorithm to the set of feature vectors to identify a pair of physical devices that are used in combination with each other; and
presenting, via an interface, a recommendation to create a virtual device by combining the pair of physical devices.
16. The non-transitory medium of claim 15 , wherein the pair of physical devices includes a first physical device and a second physical device, and wherein the second physical device is one of multiple physical devices that are identified on the interface as candidates for inclusion in the virtual device.
17. The non-transitory medium of claim 16 , wherein the operations further comprise:
receiving input that is indicative of a selection of the second physical device from among the multiple physical devices.
18. The non-transitory medium of claim 15 , wherein the operations further comprise:
receiving, via the interface, input that is indicative of a confirmation to create the virtual device; and
configuring the virtual device to perform a function by implementing a rule for at least one of the pair of physical devices.
19. The non-transitory medium of claim 18 , wherein the pair of physical devices includes a first physical device and a second physical device, and wherein the function specifies that in the event that either (i) the first physical device performs an action or (ii) a criterion is determined to be satisfied through analysis of an output produced by the first physical device, then the second physical device performs another action.