Device, system and method for controlling a plurality of voice recognition devices
Disclosed is a device for controlling a plurality of voice recognition devices for determining and selecting a first voice recognition device that a user wants to use based on a point in time when the voice of the user is spoken or a place where the user spoke the voice. The device for controlling a plurality of voice recognition devices according to the present disclosure may be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to 5G service, etc.
1. A device for controlling a plurality of voice recognition devices, the device comprising:
a user identification unit configured to identify a user based on a voice spoken by the user at a specific time of day;
a user setting storage unit configured to store usage pattern information of the user including information on a particular function to be performed at a particular location at a particular time of day using a first voice recognition device; and
a processor configured to:
recognize speech of the user based on the voice spoken by the user;
determine a correspondence between the recognized speech of the user, a location where the voice was received, and the specific time of day of the voice spoken by the user with the stored usage pattern information of the user;
select the first voice recognition device based on the stored usage pattern information indicating that the first voice recognition device is associated with the recognized speech of the user, the location where the voice was received, and the specific time of day of the voice spoken by the user; and
cause the first voice recognition device to execute the particular function in response to the voice spoken by the user.
2. The device of claim 1 , wherein the model storage unit further includes:
an intention analysis model configured to analyze the intention; and
a device selection model configured to select the first voice recognition device,
wherein the first voice recognition device is a voice recognition device that the user wants to use among a plurality of voice recognition devices.
3. The device of claim 2 , wherein the intention analysis model includes:
a specific user intention analysis model configured to analyze intention of a specific user, wherein the specific user is defined as a user whose usage pattern information is stored in the user setting storage unit; and
a common user intention analysis model configured to analyze individual intention of a common user, wherein the common user is defined as a user different from the specific user and whose usage pattern information is not stored in the user setting storage unit.
4. The device of claim 3 , wherein the device selection model includes:
a specific user device selection model configured to select the first voice recognition device among the plurality of voice recognition devices in response to the intention of the specific user; and
a common user device selection model configured to select a voice recognition device corresponding to the individual intention of the common user among the plurality of voice recognition devices,
wherein the voice recognition device corresponding to the individual intention of the common user includes at least one of the first voice recognition device and a second voice recognition device that is a device different from the first voice recognition device.
5. The device of claim 1 , further comprising:
a user feedback analysis unit configured to collect and analyze a reaction of the user,
wherein the user feedback analysis unit is configured to compare the intention with the reaction of the user, and determine whether the device that the user wanted to use matches the first voice recognition device.
6. A system for controlling a plurality of voice recognition devices, the system comprising:
a plurality of voice recognition devices;
a server networked with each of the plurality of voice recognition devices; and
a user terminal configured to perform data communication with the server and the voice recognition devices,
wherein the server includes:
a user identification unit configured to identify a user based on a voice spoken by the user at a specific time of day;
a user setting storage unit configured to store usage pattern information of the user including information on a particular function to be performed at a particular location at a particular time of day using a first voice recognition device;
a processor configured to:
recognize speech of the user based on the voice spoken by the user;
determine a correspondence between the recognized speech of the user, a location where the voice was received, and the specific time of day of the voice spoken by the user with the stored usage pattern information of the user;
select the first voice recognition device based on the stored usage pattern information indicating that the first voice recognition device is associated with the recognized speech of the user, the location where the voice was received, and the specific time of day of the voice spoken by the user; and
cause the first voice recognition device to execute the particular function in response to the voice spoken by the user.
7. The system of claim 6 , wherein the plurality of voice recognition devices includes at least a TV, an air conditioner, an air cleaner, a refrigerator, a kimchi refrigerator, a water purifier, a dishwasher, a microwave, a washing machine, a dryer, a styler, a cleaning robot, a massage chair, a PC, or a projector.
8. The system of claim 6 , wherein the model storage unit further includes:
an intention analysis model configured to analyze the intention; and
a device selection model configured to select the first voice recognition device,
wherein the first voice recognition device is a voice recognition device that the user wants to use among the plurality of voice recognition devices.
9. The system of claim 8 , wherein the intention analysis model includes:
a specific user intention analysis model configured to analyze intention of a specific user, wherein the specific user is defined as a user whose usage pattern information is stored in the user setting storage unit; and
a common user intention analysis model configured to analyze individual intention of a common user, wherein the common user is defined as a user different from the specific user and whose usage pattern information is not stored in the user setting storage unit.
10. The system of claim 9 , wherein the device selection model includes:
a specific user device selection model configured to select the first voice recognition device among the plurality of voice recognition devices in response to the intention of the specific user; and
a common user device selection model configured to select a voice recognition device corresponding to the individual intention of the common user among the plurality of voice recognition devices,
wherein the voice recognition device corresponding to the individual intention of the common user includes at least one of the first voice recognition device and a second voice recognition device that is a device different from the first voice recognition device.
11. The system of claim 6 , wherein the server further includes a user feedback analysis unit configured to collect and analyze a reaction of the user, and
wherein the user feedback analysis unit is configured to compare the intention with the reaction of the user, and determine whether the device that the user wanted to use matches the first voice recognition device.
12. A method for controlling a plurality of voice recognition devices, comprising:
receiving a voice of a user at a specific time of day by the voice recognition devices;
recognizing speech of the user and identifying the user based on the voice;
determining a correspondence between the recognized speech of the user, a location where the voice was received, and the specific time of day of the voice spoken by the user with stored usage pattern information of the user stored by a user setting storage unit, wherein the usage pattern information of the user includes information on a particular function to be performed at a particular location at a particular time of day using a first voice recognition device;
selecting the first voice recognition device among the plurality of voice recognition devices based on the stored usage pattern information indicating that the first voice recognition device is associated with the recognized speech of the user, the location where the voice was received, and the specific time of day of the voice spoken by the user; and
causing the particular function to be executed by the first voice recognition device in response to the voice of the user.
13. The method of claim 12 , further comprising:
receiving feedback from the user in response to execution of the function by the first voice recognition device;
determining whether selection of the first voice recognition device correctly corresponded to the intention of the specific user based on the feedback; and
updating an intention analysis model and a device selection model depending on the determination.