Device, method and computer program for performing an action on an IoT device

Abstract

A method and device for performing an action on an IoT device are disclosed. According to one embodiment, the method performed by an electronic device includes obtaining at least one input from a user, in response to a response corresponding to a predefined action being unable to be identified in response to the obtained input, sending the obtained input to a server, receiving information related to at least one activity mapped onto at least one IoT device based on at least one object or context identified at the server based on the obtained input and characteristic information of the user, identifying an action to be performed on an IoT device of the at least one IoT device based on a correlation between the obtained input and the at least one activity mapped onto the at least one IoT device, and sending an instruction to the IoT device for performing the identified action.

Claims

1. A method for controlling an Internet of Things (IoT) device by an electronic device, the method comprising: Obtain at least one input from the user; If a predefined action corresponding to at least one obtained input cannot be identified, the at least one obtained input is sent to the server, and at least one interaction performed by the user with at least one IoT device is tracked. The server receives information relating to at least one activity of at least one IoT device identified based on at least one input sent, and information relating to at least one object and / or at least one context, wherein the at least one object and / or the at least one context is identified based on the at least one input obtained and the user's feature information; Based on the correlation between the obtained at least one input and the at least one activity mapped to the identified at least one IoT device, information related to at least one object and / or at least one context, and at least one tracked interaction, an action to be performed on the IoT device is identified; and Send instructions to the IoT device to perform the identified action.

2. The method according to claim 1, wherein, Receiving the information includes: Receive from the server probability information relating to at least one candidate action for mapping to at least one activity of the at least one IoT device, and The probability information indicates the likelihood of each of the at least one candidate action corresponding to the at least one obtained input.

3. The method according to claim 2, further comprising: Identify the user action performed after receiving the at least one input; as well as Obtain similarity information indicating the similarity between each of the identified user actions and the at least one obtained input. The recognition actions include: The action to be performed on one of the at least one IoT devices is identified based on the obtained similarity information and the received probability information.

4. The method according to claim 3, wherein, Obtaining the similarity information includes: Based on at least one of the obtained inputs, the identified user actions are classified into predetermined categories; and Based on the category of the user action, a similarity score is obtained for each of the user actions, which is used as the similarity information.

5. The method according to claim 1, wherein, At the server, the at least one activity and the at least one IoT device are mapped based on any one or any combination of a plurality of pre-trained regression functions, and Each of the plurality of pre-trained regression functions is identified based on activity and IoT devices.

6. The method according to claim 1, further comprising: The database is updated based on the identified action mapped to at least one of the obtained inputs; as well as Based on receiving other inputs corresponding to the at least one obtained input after the database is updated, an instruction for performing the identified action is sent to one of the at least one IoT devices.

7. An electronic device for controlling Internet of Things (IoT) devices, the electronic device comprising: Memory, which stores one or more instructions; Communication interface; as well as The processor is configured to execute one or more instructions stored in the memory to perform: Obtain at least one input from the user; If a predefined action corresponding to at least one obtained input cannot be identified, the at least one obtained input is sent to the server via the communication interface, and at least one interaction performed by the user with at least one IoT device is tracked. The server receives, via the communication interface, information relating to at least one activity of at least one IoT device identified based on at least one input sent, and information relating to at least one object and / or at least one context, wherein the at least one object and / or the at least one context is identified based on the at least one input obtained and the user's feature information; Based on the correlation between the obtained at least one input and the at least one activity mapped to the identified at least one IoT device, information relating to at least one object and / or at least one context, and at least one tracked interaction, identify the action to be performed on the IoT device; and The communication interface is used to send instructions to the IoT device to perform the identified action.

8. The electronic device according to claim 7, wherein, The processor is also configured to: The server receives probability information via the communication interface related to at least one candidate action for mapping to at least one activity of the at least one IoT device. The probability information indicates the likelihood of each of the at least one candidate action corresponding to the at least one obtained input.

9. The electronic device according to claim 8, wherein, The processor is also configured to: Identify the user action performed after at least one input has been received. Obtain similarity information indicating the similarity between each of the identified user actions and at least one of the obtained inputs, and The action to be performed on one of the at least one IoT devices is identified based on the obtained similarity information and the received probability information.

10. The electronic device according to claim 9, wherein, The processor is also configured to: Based on at least one of the obtained inputs, the identified user actions are classified into predetermined categories; and Based on the category of the user action, a similarity score is obtained for each of the user actions, which is used as the similarity information.

11. The electronic device according to claim 7, wherein, At the server, the at least one activity and the at least one IoT device are mapped based on any one or any combination of a plurality of pre-trained regression functions, and Each of the plurality of pre-trained regression functions is identified based on activity and IoT devices.

12. The electronic device according to claim 7, wherein, The processor is also configured to: Based on the identified action mapped to at least one of the obtained inputs, update the database; and Based on receiving other inputs corresponding to the at least one obtained input after the database is updated, instructions for performing the identified action are sent to one of the at least one IoT devices via the communication interface.

13. A server for controlling Internet of Things (IoT) devices, the server comprising: Memory, which stores one or more instructions; Communication interface; as well as The processor is configured to execute one or more instructions stored in the memory to perform: Based on the fact that a predefined action corresponding to at least one input cannot be recognized at the electronic device, at least one input from the user is received from the electronic device via the communication interface; Based on the user's feature information and / or at least one received input, identify at least one object and / or at least one context; Based on at least one received input, and at least one identified object and / or at least one identified context, identify at least one activity mapped to at least one IoT device, and The communication interface is used to send information to the electronic device relating to at least one activity identified and mapped to the at least one IoT device, as well as information relating to at least one identified object and / or at least one identified context. Specifically, at the electronic device, an action to be performed on one of the at least one IoT devices is identified based on the correlation between the at least one input and the at least one activity mapped to the at least one IoT device, information related to the at least one identified object and / or the at least one identified context, and at least one interaction of the user tracked by the electronic device.

14. The server according to claim 13, wherein, The processor is also configured to: Obtain probabilistic information related to at least one candidate action for mapping to at least one activity on the at least one IoT device, and The probability information indicates the likelihood of each of the at least one candidate action corresponding to the at least one received input.

15. The server according to claim 13, in, The processor is also configured to: Based on any one or any combination of multiple pre-trained regression functions, the at least one activity is mapped to the at least one IoT device, and Each of the plurality of pre-trained regression functions is identified based on activity and IoT devices.

Images