Internet of things (IoT) human interface apparatus, system, and method
First Claim
1. A method, comprising:
- receiving, with each of a plurality of microphones of an Internet of Things (“
IoT”
) human interface device, a first voice input from a user, the plurality of microphones being disposed within a plane that is parallel with a cylindrical base of the IoT human interface device;
identifying, with a computing system, one or more explicit commands in the first voice input;
identifying, with the computing system, one or more first IoT-capable devices of a plurality of IoT-capable devices to which the one or more explicit commands are applicable;
receiving, with the computing system, one or more first sensor data from each of at least one first sensor;
analyzing, with the computing system, the first voice input in view of previous voice inputs from the user and in view of the one or more first sensor data, to determine whether the first voice input additionally contains any implicit commands;
based on a determination that the first voice input contains at least one implicit command, identifying, with the computing system, one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable, generating, with the computing system, second instructions for each of the one or more second IoT-capable devices, using a combination of the one or more explicit commands and the at least one implicit command, and sending, with the computing system, the generated second instructions to the one or more second IoT-capable devices; and
for each of the one or more first IoT-capable devices to which the at least one implicit command is not applicable, generating, with the computing system, first instructions, using the one or more explicit commands, and sending, with the computing system, the generated first instructions to the one or more first IoT-capable devices to which the at least one implicit command is not applicable;
wherein analyzing the first voice input to determine whether the first voice input additionally contains any implicit commands comprises;
determining, with the computing system, an intent of the user based at least in part on an identity of the user inputting the first voice input, based at least in part on the previous voice inputs received from the user identified by the computing system and the one or more first sensor data, and based at least in part on a detected mood of the user;
based on the detected mood of the user, determining, with the computing system, whether the at least one implicit command comprises a warning command to warn one or more persons different from the user of the detected mood of the user; and
determining, with the computing system, a match probability that indicates a probability that the determined intent of the user matches actual intent of the user;
wherein identifying, with the computing system, the one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable comprises;
based on a determination that the at least one implicit command comprises the warning command to warn the one or more persons of the detected mood of the user, identifying, with the computing system, the one or more second IoT-capable devices of the one or more first IoT-capable devices to use to warn the one or more persons of the detected mood of the user;
wherein the second instructions comprise a data structure that comprises the determined intent of the user, the determined match probability, and a tagged list listing at least the one or more second IoT-capable devices.
1 Assignment
0 Petitions
Accused Products
Abstract
Novel tools and techniques are provided for implementing Internet of Things (“IoT”) functionality. In some embodiments, microphones of an IoT human interface device might receive user voice input. The IoT human interface device and/or a computing system might identify explicit commands in the voice input, identify first IoT-capable devices to which the explicit commands are applicable, receive sensor data from IoT sensors, and analyze the voice input in view of previous user voice inputs and in view of the sensor data to determine whether the voice input contains any implicit commands. If so, second IoT-capable devices to which an implicit command is additionally applicable might be identified, instructions based on a combination of the explicit and implicit commands may be generated and sent to the second IoT-capable devices. Instructions based only on the explicit commands are generated and sent to first IoT-capable devices to which implicit commands are not applicable.
183 Citations
30 Claims
-
1. A method, comprising:
-
receiving, with each of a plurality of microphones of an Internet of Things (“
IoT”
) human interface device, a first voice input from a user, the plurality of microphones being disposed within a plane that is parallel with a cylindrical base of the IoT human interface device;identifying, with a computing system, one or more explicit commands in the first voice input; identifying, with the computing system, one or more first IoT-capable devices of a plurality of IoT-capable devices to which the one or more explicit commands are applicable; receiving, with the computing system, one or more first sensor data from each of at least one first sensor; analyzing, with the computing system, the first voice input in view of previous voice inputs from the user and in view of the one or more first sensor data, to determine whether the first voice input additionally contains any implicit commands; based on a determination that the first voice input contains at least one implicit command, identifying, with the computing system, one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable, generating, with the computing system, second instructions for each of the one or more second IoT-capable devices, using a combination of the one or more explicit commands and the at least one implicit command, and sending, with the computing system, the generated second instructions to the one or more second IoT-capable devices; and for each of the one or more first IoT-capable devices to which the at least one implicit command is not applicable, generating, with the computing system, first instructions, using the one or more explicit commands, and sending, with the computing system, the generated first instructions to the one or more first IoT-capable devices to which the at least one implicit command is not applicable; wherein analyzing the first voice input to determine whether the first voice input additionally contains any implicit commands comprises; determining, with the computing system, an intent of the user based at least in part on an identity of the user inputting the first voice input, based at least in part on the previous voice inputs received from the user identified by the computing system and the one or more first sensor data, and based at least in part on a detected mood of the user; based on the detected mood of the user, determining, with the computing system, whether the at least one implicit command comprises a warning command to warn one or more persons different from the user of the detected mood of the user; and determining, with the computing system, a match probability that indicates a probability that the determined intent of the user matches actual intent of the user; wherein identifying, with the computing system, the one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable comprises; based on a determination that the at least one implicit command comprises the warning command to warn the one or more persons of the detected mood of the user, identifying, with the computing system, the one or more second IoT-capable devices of the one or more first IoT-capable devices to use to warn the one or more persons of the detected mood of the user; wherein the second instructions comprise a data structure that comprises the determined intent of the user, the determined match probability, and a tagged list listing at least the one or more second IoT-capable devices. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A system, comprising:
-
at least one first sensor; an Internet of Things (“
IoT”
) human interface device, comprising;a cylindrical base; a plurality of microphones that are disposed within a plane that is parallel with the cylindrical base; one or more speakers; at least one first processor; a data store; and a non-transitory computer readable medium in communication with each of the at least one first processor and the data store, the non-transitory computer readable medium having stored thereon computer software comprising a first set of instructions that, when executed by the at least one first processor, causes the IoT human interface device to; receive, with each of the plurality of microphones, a first voice input from a user; and send the first voice input to a computing system; the computing system, comprising; at least one second processor; and a non-transitory computer readable medium in communication with the at least one second processor, the non-transitory computer readable medium having stored thereon computer software comprising a second set of instructions that, when executed by the at least one second processor, causes the computing system to; receive the first voice input from the IoT human interface device; identify one or more explicit commands in the first voice input; identify one or more first IoT-capable devices of a plurality of IoT-capable devices to which the one or more explicit commands are applicable; receive one or more first sensor data from each of the at least one first sensor; analyze the first voice input in view of previous voice inputs from the user and in view of the one or more first sensor data, to determine whether the first voice input additionally contains any implicit commands; based on a determination that the first voice input contains at least one implicit command, identify one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable, generate second instructions for each of the one or more second IoT-capable devices, using a combination of the one or more explicit commands and the at least one implicit command, and send the generated second instructions to the one or more second IoT-capable devices; and for each of the one or more first IoT-capable devices to which the at least one implicit command is not applicable, generate first instructions, using the one or more explicit commands, and send the generated first instructions to the one or more first IoT-capable devices to which the at least one implicit command is not applicable; wherein analyzing the first voice input to determine whether the first voice input additionally contains any implicit commands comprises; determining an intent of the user based at least in part on an identity of the user inputting the first voice input, based at least in part on the previous voice inputs received from the user identified by the computing system and the one or more first sensor data, and based at least in part on a detected mood of the user; based on the detected mood of the user, determining, with the computing system, whether the at least one implicit command comprises a warning command to warn one or more persons different from the user of the detected mood of the user; and determining a match probability that indicates a probability that the determined intent of the user matches actual intent of the user; wherein identifying the one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable comprises; based on a determination that the at least one implicit command comprises the warning command to warn the one or more persons of the detected mood of the user, identifying the one or more second IoT-capable devices of the one or more first IoT-capable devices to use to warn the one or more persons of the detected mood of the user; wherein the second instructions comprise a data structure that comprises the determined intent of the user, the determined match probability, and a tagged list listing at least the one or more second IoT-capable devices; and the plurality of IoT-capable devices, each of the one or more IoT-capable devices of the plurality of IoT-capable devices comprising; at least one third processor; and a non-transitory computer readable medium in communication with the at least one third processor, the non-transitory computer readable medium having stored thereon computer software comprising a third set of instructions that, when executed by the at least one third processor, causes the IoT-capable device to; receive the generated first or second instructions; perform one or more tasks in accordance with the received first or second instructions; and update the computing system with progress of each of the one or more tasks. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21, 22, 23)
-
-
24. An Internet of Things (“
- IoT”
) human interface device, comprising;a cylindrical base; a plurality of microphones that are disposed within a plane that is parallel with the cylindrical base; one or more speakers; one or more communications transceivers; at least one processor; a data store; and a non-transitory computer readable medium in communication with each of the at least one processor and the data store, the non-transitory computer readable medium having stored thereon computer software comprising a set of instructions that, when executed by the at least one processor, causes the IoT human interface device to; receive, with each of the plurality of microphones, a first voice input from a user; identify one or more explicit commands in the first voice input; identify one or more first IoT-capable devices of a plurality of IoT-capable devices to which the one or more explicit commands are applicable; receive one or more first sensor data from each of the at least one first sensor; analyze the first voice input in view of previous voice inputs from the user and in view of the one or more first sensor data, to determine whether the first voice input additionally contains any implicit commands; based on a determination that the first voice input contains at least one implicit command, identify one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable, generate second instructions for each of the one or more second IoT-capable devices, using a combination of the one or more explicit commands and the at least one implicit command, and send the generated second instructions to the one or more second IoT-capable devices; and for each of the one or more first IoT-capable devices to which the at least one implicit command is not applicable, generate first instructions, using the one or more explicit commands, and send the generated first instructions to the one or more first IoT-capable devices to which the at least one implicit command is not applicable; wherein analyzing the first voice input to determine whether the first voice input additionally contains any implicit commands comprises; determining an intent of the user based at least in part on an identity of the user inputting the first voice input, based at least in part on the previous voice inputs received from the user identified by the computing system and the one or more first sensor data, and based at least in part on a detected mood of the user; based on the detected mood of the user, determining whether the at least one implicit command comprises a warning command to warn one or more persons different from the user of the detected mood of the user; and determining a match probability that indicates a probability that the determined intent of the user matches actual intent of the user; wherein identifying the one or more second IoT-capable devices of the one or more first IoT-capable devices to which the at least one implicit command is additionally applicable comprises; based on a determination that the at least one implicit command comprises the warning command to warn the one or more persons of the detected mood of the user, identifying the one or more second IoT-capable devices of the one or more first IoT-capable devices to use to warn the one or more persons of the detected mood of the user; wherein the second instructions comprise a data structure that comprises the determined intent of the user, the determined match probability, and a tagged list listing at least the one or more second IoT-capable devices. - View Dependent Claims (25, 26, 27, 28, 29, 30)
- IoT”
Specification