System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to input a voice instruction; means for analyzing the voice instruction and converting the voice instruction into text; means including a generation-related AI for generating an optimum home appliance operation command based on the user's instruction; means for transmitting the generated operation command to a corresponding home appliance; means for feeding back an operation result of the home appliance; and means for notifying the user of a feedback result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Current smart home technology has not achieved truly integrated home automation, with each home appliance operating independently. As a result, users must use multiple remote controls and applications, making operation cumbersome. Furthermore, voice control is often incomplete and does not accurately reflect the user's intended actions. There is a need to solve this issue and provide a smart home system that allows users to operate home appliances seamlessly and intuitively. [Means for solving the problem]

[0005] The present invention solves this problem by providing the following means: a means for a user to input voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI that generates optimal home appliance operation commands based on the user's instructions, a means for sending the generated operation commands to the relevant home appliances, a means for providing feedback on the operation results of the home appliances, and a means for notifying the user of the feedback results. This system allows users to operate and manage multiple home appliances simultaneously with a single voice instruction. Furthermore, the generative AI can accurately grasp the user's intentions and execute optimal operations, making operation easy and intuitive.

[0006] "User" refers to a person who uses the system to input voice instructions and operate and manage home appliances.

[0007] "Voice instructions" refer to operation commands or requests that a user communicates to a system by voice.

[0008] "Voice recognition module" refers to a device or software that analyzes a user's voice instructions and converts the voice data into text data.

[0009] "Generative AI" refers to artificial intelligence that analyzes the user's intentions based on text data converted by a voice recognition module and generates optimal commands to operate home appliances.

[0010] An "operation command" refers to instruction data that includes specific operation instructions sent to a home appliance.

[0011] "Home appliances" is a general term that refers to electronic devices and electrical appliances used in the home, and in this system it specifically refers to lighting, air conditioners, televisions, etc.

[0012] "Feedback" refers to the process in which a home appliance receives an operation command, performs an operation, sends the results back to the system, and ultimately notifies the user.

[0013] "Notification" refers to the act of informing the user of the system's operation results based on the feedback results. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a smart home system that integrates and manages home appliances based on user voice commands. A specific embodiment of the present invention will be described below. First, the overall flow of the system and the role of each component will be described, followed by a description of specific program processing.

[0036] Overall system configuration

[0037] 1. A means for the user to input voice commands:

[0038] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[0039] 2. Means for analyzing voice instructions and converting them into text data:

[0040] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[0041] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[0042] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[0043] 4. A method for sending the generated operation command to the corresponding home appliance:

[0044] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[0045] 5. Means of feedback on the operation results of home appliances:

[0046] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[0047] 6. Means of notifying the user of the feedback results:

[0048] The server sends the feedback results back to the Hub, which then notifies the user of the results by voice or other notification methods.

[0049] Program processing

[0050] Speech Recognition and Analysis

[0051] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[0052] Generate and send instructions

[0053] The converted text data is sent to the server, where the generative AI module analyzes the text. It accurately understands the user's intention and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0054] Home appliance control and feedback

[0055] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[0056] User Notification

[0057] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is generated.

[0058] Specific examples

[0059] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[0060] Audio prompts

[0061] The user tells the Hub, "Set the air conditioner to 20 degrees."

[0062] Speech Recognition and Analysis

[0063] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0064] Generate and send instructions

[0065] The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[0066] Home appliance control and feedback

[0067] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0068] User Notification

[0069] The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub, which notifies the user that the air conditioner has been set to 20 degrees.

[0070] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[0074] Step 2:

[0075] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[0076] Step 3:

[0077] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[0078] Step 4:

[0079] The terminal (Hub) sends the text data received from the voice recognition module to the server.

[0080] Step 5:

[0081] The server receives the text data and requests processing from the generative AI module. The generative AI module analyzes the text data and generates the optimal operation command. Specifically, it generates the command "TURN_OFF LIGHT LIVING_ROOM."

[0082] Step 6:

[0083] The server sends the generated operation command to the lighting in the living room.

[0084] Step 7:

[0085] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the light.

[0086] Step 8:

[0087] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the Hub.

[0088] Step 9:

[0089] The terminal (Hub) receives the feedback message and sends it to the server.

[0090] Step 10:

[0091] The server verifies the feedback message and sends a confirmation message to the Hub.

[0092] Step 11:

[0093] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice that "The living room lights have been turned off."

[0094] The above is the specific procedure for turning off the living room lights by voice command from the user. This series of steps allows the user to operate home appliances simply and intuitively.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern smart home systems, users must use separate remote controls and applications to operate multiple home appliances individually. This complex operation is burdensome for users and inconvenient. Furthermore, even when operating using voice commands, the accuracy of voice recognition and the transmission of commands to the home appliances can be unstable, resulting in a lack of reliability. Therefore, the present invention aims to comprehensively manage home appliances based on user voice commands, thereby improving ease of operation and reliability.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative model for generating optimal home appliance operation commands based on the user instruction; means for transmitting the generated operation commands to the corresponding devices; means for providing feedback on the operation results of the devices; means for notifying the user of the feedback results; and means for analyzing the user's intention, generating commands using the generative model, transmitting the commands to the corresponding devices, and notifying the results. This allows the user to easily operate multiple devices with a single voice instruction and receive more reliable notifications.

[0100] A "user" is an individual or end user who utilizes the system to input voice instructions and operate a home appliance.

[0101] "Voice instructions" are operational instructions spoken by the user to the system, and refer to voice data captured through a microphone.

[0102] "Input means" refers to components including a microphone and its associated hardware and software that a user uses to input voice.

[0103] "Means for parsing and converting to text data" refers to the process and functionality of converting voice instructions into text using a voice recognition module and associated algorithms.

[0104] A "generative model" is a system that uses a generative AI model and refers to an algorithm that generates optimal home appliance operation commands based on user text data.

[0105] An "operation command" refers to a specific instruction generated to operate a home appliance or other device. An example would be "TURN_OFF LIGHT LIVING_ROOM."

[0106] "Applicable devices" refers to home appliances and other electronic devices that are controlled by voice instructions or operational commands, such as air conditioners, lighting, and televisions.

[0107] The "means for transmitting" refers to a system configuration including communication means and protocols for transmitting the generated operation command to the corresponding device.

[0108] "Feedback means" refers to a means for reporting the results of device operation to the system and returning that information to the user.

[0109] "Means of notification" refers to means such as audio output or display that the system uses to communicate operation results and other information to the user.

[0110] The present invention relates to a smart home system that can manage home appliances in an integrated manner based on user voice commands. This system is designed to allow users to simultaneously control multiple home appliances through voice commands by combining voice recognition technology and generative AI models. A specific embodiment of this system and its program processing are described below.

[0111] Overall system configuration

[0112] This smart home system mainly consists of the following components:

[0113] 1. Voice input method:

[0114] A smart home hub with a built-in microphone that allows the user to input voice commands.

[0115] An example of a prompt sentence is "Set the air conditioner to 20 degrees."

[0116] 2. Audio data analysis methods:

[0117] The voice data is converted into text data by a voice recognition module.

[0118] Specifically, we use technologies such as Google (registered trademark) Cloud Speech-to-Text API.

[0119] 3. Generative AI Model:

[0120] Using a generative AI (e.g., OpenAI's GPT-3 (registered trademark)) installed on the server, text data is analyzed and optimal home appliance operation commands are generated.

[0121] If the user instructs "Turn off the lights in the living room," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0122] 4. Command sending method:

[0123] The server sends the generated home appliance operation command to the relevant device (e.g., air conditioner, lighting).

[0124] Communication protocols include Wi-Fi and Bluetooth.

[0125] 5. Feedback methods:

[0126] When the home appliance completes its operation, it feeds back the results to the Hub, which then reports them to the server.

[0127] For example, if an air conditioner changes the temperature setting to 20 degrees, a feedback message "TEMPERATURE_SET_SUCCESS" is sent to the Hub.

[0128] 6. User Notification Methods:

[0129] The server checks the feedback results and sends a final confirmation message to the Hub.

[0130] The Hub will notify the user with a voice message such as "The air conditioner has been set to 20 degrees."

[0131] Specific examples

[0132] As a concrete example, let's take a look at the process in detail when a user wants to set the air conditioner in the living room to 20 degrees:

[0133] Voice command: The user says to the Hub, "Set the air conditioner to 20 degrees."

[0134] Speech recognition: The Hub's microphone captures the voice and sends the voice data to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0135] Instruction generation: The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20."

[0136] Command transmission: The server sends the generated command to the air conditioner in the living room.

[0137] Feedback: The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0138] User notification: The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub. The Hub notifies the user, "The air conditioner has been set to 20 degrees."

[0139] In this way, users can easily and reliably manage and operate home appliances using voice commands, significantly improving the convenience and reliability of smart homes.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] The user inputs a voice command. The user speaks to the smart home hub, saying, "Set the air conditioner to 20 degrees." The input is voice data, which is captured by the hub's microphone. The voice data is temporarily stored in the hub's buffer memory.

[0143] Step 2:

[0144] The device (Hub) sends the captured voice data to the voice recognition module. The input is the saved voice data, which the voice recognition module analyzes and converts into text data such as "Set the air conditioner to 20 degrees." The output is text data. The voice recognition module uses the Google Cloud Speech-to-Text API.

[0145] Step 3:

[0146] The terminal (hub) sends text data to the server. The input is the converted text data, which the server receives. The server then sends the received text data to a generative AI (e.g., OpenAI's GPT-3) for analysis.

[0147] Step 4:

[0148] The server uses generative AI to analyze text data and generate optimal home appliance operation commands. The input is the text data "Set the air conditioner to 20 degrees," and the generative AI analyzes this to understand the user's intent. The output is the operation command "SET_TEMPERATURE 20."

[0149] Step 5:

[0150] The server sends the generated operation command to the corresponding device (the air conditioner in the living room). The input is the operation command "SET_TEMPERATURE 20", and the server sends this command to the air conditioner using the home appliance's communication protocol (e.g., Wi-Fi, Bluetooth). The output is the sent operation command.

[0151] Step 6:

[0152] The device (air conditioner) receives a command and changes the temperature setting to 20 degrees. The input is the operation command "SET_TEMPERATURE 20", and the air conditioner operates according to that command. The output is the result of the operation completion.

[0153] Step 7:

[0154] After the device (air conditioner) completes its operation, it sends a feedback message to the Hub. The input is the result of the operation completion, and the output is the feedback message "TEMPERATURE_SET_SUCCESS".

[0155] Step 8:

[0156] The terminal (Hub) sends a feedback message to the server. The input is the feedback message "TEMPERATURE_SET_SUCCESS" and sends it to the server. The output is a report to the server.

[0157] Step 9:

[0158] The server checks the feedback results and generates a final confirmation message, where the input is the feedback message and the output is the confirmation message.

[0159] Step 10:

[0160] The terminal (Hub) receives the confirmation message and notifies the user. The input is the confirmation message, and the output is a voice notification to the user: "The air conditioner has been set to 20 degrees."

[0161] (Application example 1)

[0162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0163] Modern smart home systems operate each appliance based on user voice commands to achieve integrated management of home appliances. However, because these systems primarily focus on managing home appliances, they lack integration with external systems for specific service operations, such as food delivery. This means that when ordering food from a restaurant, users must use a separate application or go through multiple steps, which is inconvenient. Therefore, there is a need for a voice-command-based system that can seamlessly integrate with external systems.

[0164] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0165] In this invention, the server includes a means for a user to input voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal data operation commands based on the user instructions, a means for transmitting the generated operation commands to a corresponding external system, a means for providing feedback on the operation results of the external system, and a means for notifying the user of the feedback results. This enables a user to efficiently use an external food delivery system using only voice instructions and consistently manage all processes from ordering to receiving.

[0166] A "user" is an entity that operates the system and inputs voice instructions.

[0167] A "voice instruction" is an instruction given by the user to the system using voice.

[0168] A "voice recognition module" is software or hardware for analyzing voice instructions and converting them into text data.

[0169] "Generative AI" is an artificial intelligence module that generates optimal data manipulation commands based on user instructions.

[0170] "Data manipulation commands" are instructions that the generative AI generates by analyzing the user's voice instructions, instructing an external system to perform specific actions.

[0171] "External systems" refer to external services and devices other than home appliances, including, for example, food delivery systems.

[0172] "Feedback" refers to the process of informing a user of the results of an external system's operation.

[0173] "Notification" refers to the act or means of communicating the feedback results to the user.

[0174] This invention relates to a smart food delivery system that delivers food based on user voice instructions. Specifically, it is a system that enables users to issue voice instructions, analyzes and processes those instructions, and connects them to a delivery service.

[0175] Overall system configuration

[0176] Entering voice commands

[0177] A user inputs voice commands into a smartphone app, such as "order a pizza," which are captured through the smart device's microphone.

[0178] Analysis of voice instructions

[0179] The captured voice data is analyzed through a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converted into text data, which is then sent to a server.

[0180] Generate commands

[0181] The server uses a generative AI (e.g., OpenAI GPT-4®) to analyze the converted text data and understand the user's intent. The generative AI generates optimal data manipulation commands based on the user's intent. These commands are then sent to the food delivery system.

[0182] Sending Commands

[0183] The generated data manipulation commands are sent to an external delivery system (e.g., a restaurant ordering system) to order a particular food item.

[0184] Receiving Feedback

[0185] Once the order is accepted, the external system sends the result as feedback to the server, for example, a message such as "your order has been accepted."

[0186] User Notification

[0187] The server then sends the feedback results to the app, allowing users to check the order completion and progress via a notification on their smartphone screen or through a voice message.

[0188] Hardware and Software Configuration

[0189] 1. Hardware

[0190] Smartphone (any smart device with a microphone and internet connection)

[0191] 2. Software

[0192] Speech recognition API (e.g., Google Cloud Speech-to-Text API)

[0193] Generative AI (e.g. OpenAI GPT-4)

[0194] Cloud servers (Amazon Web Services, Google Cloud, etc.)

[0195] Specific examples

[0196] Audio prompts

[0197] A user says to an app on their smartphone, "Order a pizza."

[0198] Speech recognition and text conversion

[0199] The smartphone captures the audio and uses a speech recognition API to convert it into text data such as "order a pizza."

[0200] Instruction analysis and order generation

[0201] The server receives the converted text data and uses generative AI to generate an order command such as "order one pizza."

[0202] Submitting an Order

[0203] The server sends the generated order command to an external food delivery system.

[0204] Feedback and Notifications

[0205] The external delivery system accepts the order and sends feedback of the order acceptance to the server. The server notifies the app of the feedback result and informs the user that "the pizza order has been completed."

[0206] Prompt Sentence Examples

[0207] User dictates: "Order me a pizza"

[0208] Prompt for generative AI: "The user says they want to order pizza. Please suggest what would be the best order."

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] A user inputs voice commands into a smartphone app. For example, the user says, "Order a pizza." The smartphone captures the voice and obtains the input as voice data.

[0212] Step 2:

[0213] The voice data is sent to the voice recognition module. The smartphone's voice recognition API (for example, Google Cloud Speech-to-Text API) analyzes the voice data and converts it into text data such as "Order a pizza." The text data is then output.

[0214] Step 3:

[0215] Text data is sent to a server. The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the received text data as input. The generative AI analyzes the instruction "order a pizza" and generates the optimal data manipulation command. In this case, a specific action command is generated: "Generate and send a pizza order." This is output as the generated command.

[0216] Step 4:

[0217] The server receives the generated data manipulation commands and sends them to an external food delivery system (e.g., a restaurant ordering system). The server uses the external system's API to input the order as a concrete order, e.g., sending an order for a pizza to a specific restaurant. The output is a feedback message that the order has been completed.

[0218] Step 5:

[0219] An external food delivery system receives the order and sends the result back to the server. For example, a feedback message such as "Order accepted" or "Order number 12345" is sent. The server receives this feedback message.

[0220] Step 6:

[0221] The server notifies the user's smartphone app of the feedback results it has received. The server takes the feedback message as input and sends a notification message to the smartphone app, such as "Your pizza order has been completed." The user's smartphone receives this message and displays it on the screen or as an audio notification. The output is a notification to the user.

[0222] Specific examples

[0223] Step 1:

[0224] A user says to their smartphone, "Order a pizza." Voice data is captured.

[0225] Step 2:

[0226] The voice data is converted into text data of "Order a pizza" by the Google Cloud Speech-to-Text API.

[0227] Step 3:

[0228] The text data is sent to the server, where it is analyzed by a generative AI model (OpenAI GPT-4) and generates a command to "generate and send a pizza order."

[0229] Step 4:

[0230] The server sends a "pizza order" to an external food delivery system, which receives the order as input.

[0231] Step 5:

[0232] The external delivery system accepts the order and sends a feedback message to the server saying "Order accepted."

[0233] Step 6:

[0234] The server sends a feedback message to the user saying, "Your pizza order has been completed." The smartphone app receives this notification and displays it to the user.

[0235] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0236] The present invention combines a smart home system that integrates and manages home appliances based on user voice commands with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below. First, the overall flow of the system and the role of each component are described, followed by a description of specific program processing.

[0237] Overall system configuration

[0238] 1. A means for the user to input voice commands:

[0239] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[0240] 2. Means for analyzing voice instructions and converting them into text data:

[0241] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[0242] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[0243] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[0244] 4. Means including an emotion engine for recognizing a user's emotion based on an analysis of the user's voice instructions:

[0245] The emotion engine uses the analysis of voice commands to recognize the user's emotions, which are then used as a reference for further analysis and command generation by the generative AI.

[0246] 5. Means for sending the generated operation command to the relevant home appliance:

[0247] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[0248] 6. Means of feedback on the operation results of home appliances:

[0249] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[0250] 7. Means of notifying the user of the feedback results:

[0251] The server sends the feedback results back to the Hub, which then notifies the user via voice or other notification methods. The notification method and content are adjusted depending on the user's emotions.

[0252] Program processing

[0253] Speech Recognition and Analysis

[0254] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[0255] Emotion recognition by emotion engine

[0256] The text data sent from the speech recognition module is analyzed by the emotion engine to recognize the user's emotion. This emotion data is used for subsequent processing.

[0257] Generate and send instructions

[0258] The converted text data and emotion data are sent to the server, where the generative AI module analyzes the data. It accurately grasps the user's intentions and emotions and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0259] Home appliance control and feedback

[0260] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[0261] User Notification

[0262] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is played. Furthermore, the tone and details of the notification are adjusted based on the user's emotional data.

[0263] Specific examples

[0264] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[0265] Audio prompts

[0266] The user tells the Hub, "Set the air conditioner to 20 degrees."

[0267] Speech Recognition and Analysis

[0268] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees." This text data is sent to the emotion engine, which recognizes the user's emotion.

[0269] Generate and send instructions

[0270] The server receives the text data and emotion data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[0271] Home appliance control and feedback

[0272] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0273] User Notification

[0274] The Hub sends feedback to the server, which then sends a confirmation message back to the Hub. The Hub then notifies the user, "The air conditioner has been set to 20 degrees." If the user is stressed, for example, the notification will be made in a gentler tone.

[0275] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command, and the system can also respond flexibly based on the user's emotions.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[0279] Step 2:

[0280] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[0281] Step 3:

[0282] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[0283] Step 4:

[0284] The text data converted by the voice recognition module is sent to the emotion engine on the device (Hub). The emotion engine analyzes the text data and recognizes the user's emotion. In this case, it recognizes that the user is relaxed.

[0285] Step 5:

[0286] The terminal (Hub) sends the analysis results obtained from the voice recognition module and emotion engine to the server.

[0287] Step 6:

[0288] Based on the text data and emotion data received by the server, the generative AI module is requested to process the data. The generative AI module analyzes the user's intentions and emotions and generates the optimal operation command: "TURN_OFF LIGHT LIVING_ROOM."

[0289] Step 7:

[0290] The server sends the generated operation command to the terminal (living room light).

[0291] Step 8:

[0292] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the living room light.

[0293] Step 9:

[0294] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the device (Hub).

[0295] Step 10:

[0296] The terminal (Hub) receives the feedback message and sends it to the server.

[0297] Step 11:

[0298] The server checks the feedback message and sends a confirmation message to the terminal (Hub).

[0299] Step 12:

[0300] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice, "The living room lights have been turned off." Since the user is relaxed, the notification is made in a gentle tone.

[0301] The above is the specific procedure for turning off the living room lights in response to a user's voice command. By using the emotion engine, it is possible to respond flexibly according to the user's emotions.

[0302] Example 2

[0303] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0304] In conventional smart home systems, users typically operate home appliances by inputting voice commands, but these systems often lack sufficient flexibility to adapt to the user's emotional state. This can result in reduced user satisfaction and usability. Furthermore, because home appliances are controlled solely based on voice commands, there are limitations in the accuracy of analyzing the command content and the method of notifying the operation results. Therefore, an objective of the present invention is to improve user satisfaction by recognizing the user's emotions and operating and notifying home appliances based on those emotions.

[0305] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for a user to input a voice instruction, means for analyzing the voice instruction and converting it into text data, means including a generative artificial intelligence for generating an optimal home appliance operation command based on the user's instruction, means including an emotion analysis engine for recognizing the user's emotion based on the analysis result of the voice instruction, means for transmitting the generated operation command to the corresponding home appliance, means for feeding back the operation result of the home appliance, and means for notifying the user of the feedback result. This makes it possible to operate and notify the user of the home appliance according to the user's emotional state, thereby improving user satisfaction and usability.

[0306] "User" refers to any individual or entity that uses the System.

[0307] "Voice instructions" refer to instructions input by the user speaking to the system.

[0308] The term "means" refers to hardware or software components provided for performing a specific function or process.

[0309] "Speech recognition module" refers to a technical element for converting voice data into text data.

[0310] "Generative AI" refers to AI that automatically generates specific commands and solutions based on input data.

[0311] An "emotion analysis engine" refers to a technical element that determines a user's emotional state from input data.

[0312] An "operation command" refers to a specific instruction generated to control a home appliance.

[0313] "Home appliances" refers to electronic and electrical devices used in the home.

[0314] "Feedback" refers to the home appliance reporting the results and status of its actions to the system.

[0315] "Notification" refers to conveying feedback results or other information to the user.

[0316] The present invention is a smart home system that integrates and manages home appliances based on user voice commands, and further combines it with an emotion analysis engine that recognizes the user's emotions. In this section, specific embodiments for implementing the invention will be described.

[0317] Basic configuration

[0318] This system consists of the following main components:

[0319] 1. A means for the user to input voice commands: This is a device such as a smart home hub that has a built-in microphone.

[0320] 2. Means for analyzing voice instructions and converting them into text data: This is a voice recognition module within the Hub.

[0321] 3. Means including generative artificial intelligence that generates optimal home appliance operation commands based on user instructions: This applies to generative artificial intelligence installed on a server.

[0322] 4. Means including an emotion analysis engine that recognizes the user's emotions based on the analysis results of voice instructions: This corresponds to an emotion analysis engine installed in the server.

[0323] 5. Means for transmitting the generated operation command to the relevant home appliance: This is a function for transmitting a signal from the server to the home appliance.

[0324] 6. A means of feedback on the operation results of home appliances: This is a function that allows home appliances to send the operation results to the smart home hub.

[0325] 7. Means of notifying the user of the feedback results: The Hub will notify the user of the results by voice notification or other means.

[0326] Hardware and Software Specifications

[0327] Speech Recognition Module: Uses an external speech recognition service, for example the Google Speech API.

[0328] Sentiment analysis engine: For example, an emotion recognition API such as IBM Watson (registered trademark) is used.

[0329] Generative AI: Uses generative AI models such as OpenAI GPT-3.

[0330] Specific examples

[0331] Audio prompts

[0332] The user tells the Hub, "Set the air conditioner in the living room to 20 degrees."

[0333] Audio capture and analysis

[0334] The Smart Home Hub device uses a built-in microphone to capture the user's voice and transmits it to a voice recognition module, which converts the voice data into text data such as "Set the air conditioner in the living room to 20 degrees."

[0335] Emotion recognition by emotion engine

[0336] The text data sent from the device's voice recognition module is passed to the emotion analysis engine, which then recognizes the user's emotions based on this data. For example, it may determine that the user is relaxed.

[0337] Generating commands to operate home appliances

[0338] The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal commands to operate home appliances. For example, the command "SET_TEMPERATURE 20" is generated.

[0339] Sending commands to home appliances

[0340] The server sends the generated operation command to the air conditioner in the living room. The signal "SET_TEMPERATURE 20" is sent via the air conditioner's built-in WiFi module.

[0341] Home appliance behavior and feedback

[0342] The air conditioner in the living room changes the temperature setting based on the received command. When the air conditioner completes the setting, it sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[0343] Notifying the user of the results

[0344] The smart home hub receives the feedback message and passes it on to the server. The server then verifies the feedback and sends a notification back to the user. For example, a message like "The air conditioner has been set to 20 degrees" is generated. The tone and details of the notification are adjusted depending on the user's emotional data. The notification is sent via voice through the hub.

[0345] Prompt Sentence Examples

[0346] The user says, "Set the air conditioner in the living room to 20 degrees." The emotion engine determines that the user is in a relaxed state. Generate an appropriate command to operate the home appliances.

[0347] With the above configuration, this system efficiently manages home appliances based on the user's voice commands and also realizes flexible responses based on emotions, which is expected to improve user satisfaction and ease of use.

[0348] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0349] Step 1: User Enters Voice Command

[0350] Specific action: The user says to the Smart Home Hub, "Set the air conditioner in the living room to 20 degrees."

[0351] Input: User's voice command.

[0352] Output: Audio data captured by the microphone.

[0353] Step 2: Capture and analyze audio

[0354] How it works: The Smart Home Hub device uses its built-in microphone to capture the user's voice and save it as digital audio data.

[0355] Input: The captured audio data.

[0356] Output: Data transfer to the speech recognition module.

[0357] Step 3: Convert audio data to text

[0358] How it works: The voice recognition module analyzes the voice data and converts it into text data. The voice recognition technology used is Google Speech API.

[0359] Input: Audio digital data.

[0360] Output: Text data: "Set the air conditioner in the living room to 20 degrees."

[0361] Step 4: Emotion Recognition with the Emotion Engine

[0362] Specific operation: Text data sent from the device's voice recognition module is passed to the emotion analysis engine. The emotion analysis engine uses the text data to recognize the user's emotions and generate analysis results. An emotion recognition API such as IBM Watson is used.

[0363] Input: Text data from the speech recognition module.

[0364] Output: Data indicating the user's emotional state, such as whether they are relaxed.

[0365] Step 5: Generate commands to operate the appliances

[0366] How it works: The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal home appliance operation commands. OpenAI GPT-3 is used as the generative AI model.

[0367] Input: Text data and emotion data.

[0368] Output: Appliance operation command "SET_TEMPERATURE 20".

[0369] Step 6: Sending commands

[0370] Specific operation: The server sends the generated operation command to the relevant appliance. The WiFi module sends a signal of "SET_TEMPERATURE 20" to the air conditioner in the living room.

[0371] Input: Home appliance operation command.

[0372] Output: Operation command signal sent to the air conditioner.

[0373] Step 7: Appliance behavior and feedback

[0374] Specific operation: The air conditioner in the living room changes the temperature setting based on the received command. After the temperature is set to 20 degrees, the air conditioner sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[0375] Input: Home appliance operation command.

[0376] Output: A feedback message indicating the result of the operation.

[0377] Step 8: Processing and communicating feedback

[0378] Specific operation: The smart home hub receives the feedback message and forwards it to the server. The server analyzes the feedback and generates a message to notify the user of the result. The result notification takes into account the user's emotional data, and sends a voice message to the user via the hub saying, for example, "The air conditioner has been set to 20 degrees."

[0379] Input: The feedback message.

[0380] Output: Final message that is displayed to the user.

[0381] (Application example 2)

[0382] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0383] Conventional smart home systems are limited to controlling home appliances based on user voice commands, and have the drawback of being unable to flexibly respond to the user's emotions or circumstances. Furthermore, there are no systems that can not only control home appliances but also provide the content desired by users, limiting the means to improve the user experience. Therefore, there is a need for a system that can optimally operate home appliances and suggest content based on the user's intentions and emotions.

[0384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0385] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative AI that generates optimal home appliance operation commands based on the user's instructions; means including an emotion engine that recognizes the user's emotions based on the analysis of the voice instruction; means for transmitting the generated operation commands to the relevant home appliance; means for feeding back the operation results of the home appliance; means for notifying the user of the feedback results; means including a generative AI that proposes optimal content that matches the user's intentions based on the voice instruction and emotion data; and means for providing the relevant content to the user. This enables the user to not only control the home appliance with a single voice instruction, but also to receive content that is optimal for their emotions and situation at the time.

[0386] "Voice instructions" refer to commands or requests that a user issues to the system using voice.

[0387] "Speech recognition module" refers to a software or hardware component for analyzing and converting voice instructions from a user into text data.

[0388] "Text data" refers to character string data generated by analyzing a voice instruction.

[0389] "Generative AI" refers to an artificial intelligence system that generates optimal commands and suggestions based on user input and the situation.

[0390] "Emotion engine" refers to a software or hardware component that analyzes and recognizes emotions from a user's voice or text data.

[0391] "Home appliances" refers to electronic devices and electrical appliances used in the home.

[0392] An "operation command" refers to a specific command that instructs a home appliance or other device to perform an operation.

[0393] "Feedback" refers to reporting the results of an appliance's execution or the results of a system's operation to the user.

[0394] "Content" refers to information and entertainment provided to users, such as music, videos, and news.

[0395] "Content suggestion" refers to selecting and providing optimal content based on the user's intentions and emotions.

[0396] The present invention relates to a system for controlling home appliances based on a user's voice instructions and emotional data, and for providing optimal content. The specific configuration and operation of this system are described below.

[0397] Overall system configuration

[0398] 1. Voice command input method

[0399] A user inputs voice instructions by speaking into a smart device (e.g., a smartphone), which is equipped with a microphone and captures the user's voice.

[0400] 2. Means for analyzing voice instructions and converting them into text data

[0401] The captured audio is sent to a speech recognition module (e.g., Google Speech-to-Text API) on the device, which converts the audio data into text data.

[0402] 3. Emotion Recognition Method Using Emotion Engine

[0403] The converted text data is analyzed by an emotion engine (e.g., Affectiva SDK) to recognize the user's emotion. The emotion data is used for subsequent processing.

[0404] 4. How generative AI generates instructions

[0405] The text data and emotion data are sent to a server, where a generative AI (e.g., OpenAI's GPT model) analyzes the data. Based on the user's intentions and emotions, optimal home appliance operation commands and content suggestions are generated.

[0406] 5. Means for transmitting generated operation commands and content

[0407] The server transmits the generated operation command to the corresponding home appliance and further provides the content requested by the user.

[0408] 6. Feedback method for home appliance operation results

[0409] When the home appliance completes its operation, it feeds back the results of its operation to the smart device, which then sends the feedback to the server.

[0410] 7. Means of providing feedback to users

[0411] The server returns the feedback results to the smart device, which then notifies the user of the results using voice or other notification methods, which are adjusted based on the user's emotions.

[0412] Program processing explanation

[0413] Hardware and software used

[0414] Hardware: Smart device (e.g. smartphone, microphone, speaker, internet connection)

[0415] Software: Speech recognition module (Google Speech-to-Text API), emotion recognition engine (Affectiva SDK), generative AI (OpenAI's GPT model)

[0416] The server includes a means for inputting voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal home appliance operation commands and content suggestions based on the user's instructions, a means including an emotion engine for recognizing the user's emotions based on the analysis of the voice instructions, a means for sending the generated operation commands to the relevant home appliances, a means for feeding back the operation results of the home appliances, a means for notifying the user of the feedback results, and a means for providing optimal content to the user. This enables the user to not only control home appliances with a single voice instruction, but also to receive optimal content according to their emotions and circumstances at the time.

[0417] Specific examples

[0418] For example, if a user says, "Show me an uplifting video," the speech recognition module converts the speech into text data. This text data is analyzed by the emotion engine, which recognizes the emotion "I'm feeling a little down." The generative AI then uses this information to suggest an "uplifting video." This allows the user to receive appropriate content.

[0419] Prompt Sentence Examples

[0420] A user says, "Show me an uplifting video" and their emotional state is "I'm feeling a bit down." Suggest the best content.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] The user inputs voice instructions into the smart device, which are captured by the device's microphone and sent to the smart device as voice data.

[0424] Step 2:

[0425] The smart device's voice recognition module (e.g., Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is the user's voice data, and the output is the analysis result, such as "Show me an uplifting video."

[0426] Step 3:

[0427] The text data is sent to an emotion recognition engine (e.g., Affectiva SDK), which takes the text data sent from the speech recognition module as input and analyzes it to output the user's emotional state (e.g., "I'm feeling a little depressed").

[0428] Step 4:

[0429] The smart device sends text data and emotion data to the server. The input is the text data and emotion data from the emotion recognition engine, which is then sent to the server.

[0430] Step 5:

[0431] The server's generative AI (e.g., OpenAI's GPT model) analyzes text data and emotional data and generates optimal content suggestions based on the user's intent. In this case, the input is the text data "Show me an uplifting video" and the emotional data "I'm feeling a little down," and the output is a suggestion for an "uplifting video."

[0432] Step 6:

[0433] The generated content proposals are sent from the server to the smart device. As input, the proposed content data is sent from the server to the smart device, and as output, the smart device prepares to display the content playback screen to the user.

[0434] Step 7:

[0435] The smart device presents the suggested content to the user. The input is the content data sent from the server, and the output is the content played back to the user.

[0436] Step 8:

[0437] After the user has finished viewing the content, the results are sent from the smart device to the server as feedback. The input is the user's operations and viewing results, and the output is the feedback data sent to the server.

[0438] Step 9:

[0439] The server analyzes the feedback data and uses it to further optimize future content suggestions and home appliance operation. The input is feedback data sent from smart devices, and the output is data that will be reflected in future suggestions.

[0440] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0441] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0446] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0447] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0448] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0449] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0450] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0451] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0452] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0453] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0454] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0455] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0456] The present invention relates to a smart home system that integrates and manages home appliances based on user voice commands. A specific embodiment of the present invention will be described below. First, the overall flow of the system and the role of each component will be described, followed by a description of specific program processing.

[0457] Overall system configuration

[0458] 1. A means for the user to input voice commands:

[0459] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[0460] 2. Means for analyzing voice instructions and converting them into text data:

[0461] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[0462] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[0463] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[0464] 4. A method for sending the generated operation command to the corresponding home appliance:

[0465] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[0466] 5. Means of feedback on the operation results of home appliances:

[0467] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[0468] 6. Means of notifying the user of the feedback results:

[0469] The server sends the feedback results back to the Hub, which then notifies the user of the results by voice or other notification methods.

[0470] Program processing

[0471] Speech Recognition and Analysis

[0472] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[0473] Generate and send instructions

[0474] The converted text data is sent to the server, where the generative AI module analyzes the text. It accurately understands the user's intention and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0475] Home appliance control and feedback

[0476] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[0477] User Notification

[0478] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is generated.

[0479] Specific examples

[0480] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[0481] Audio prompts

[0482] The user tells the Hub, "Set the air conditioner to 20 degrees."

[0483] Speech Recognition and Analysis

[0484] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0485] Generate and send instructions

[0486] The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[0487] Home appliance control and feedback

[0488] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0489] User Notification

[0490] The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub, which notifies the user that the air conditioner has been set to 20 degrees.

[0491] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command.

[0492] The processing flow will be explained below.

[0493] Step 1:

[0494] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[0495] Step 2:

[0496] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[0497] Step 3:

[0498] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[0499] Step 4:

[0500] The terminal (Hub) sends the text data received from the voice recognition module to the server.

[0501] Step 5:

[0502] The server receives the text data and requests processing from the generative AI module. The generative AI module analyzes the text data and generates the optimal operation command. Specifically, it generates the command "TURN_OFF LIGHT LIVING_ROOM."

[0503] Step 6:

[0504] The server sends the generated operation command to the lighting in the living room.

[0505] Step 7:

[0506] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the light.

[0507] Step 8:

[0508] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the Hub.

[0509] Step 9:

[0510] The terminal (Hub) receives the feedback message and sends it to the server.

[0511] Step 10:

[0512] The server verifies the feedback message and sends a confirmation message to the Hub.

[0513] Step 11:

[0514] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice that "The living room lights have been turned off."

[0515] The above is the specific procedure for turning off the living room lights by voice command from the user. This series of steps allows the user to operate home appliances simply and intuitively.

[0516] Example 1

[0517] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0518] In modern smart home systems, users must use separate remote controls and applications to operate multiple home appliances individually. This complex operation is burdensome for users and inconvenient. Furthermore, even when operating using voice commands, the accuracy of voice recognition and the transmission of commands to the home appliances can be unstable, resulting in a lack of reliability. Therefore, the present invention aims to comprehensively manage home appliances based on user voice commands, thereby improving ease of operation and reliability.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0520] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative model for generating optimal home appliance operation commands based on the user instruction; means for transmitting the generated operation commands to the corresponding devices; means for providing feedback on the operation results of the devices; means for notifying the user of the feedback results; and means for analyzing the user's intention, generating commands using the generative model, transmitting the commands to the corresponding devices, and notifying the results. This allows the user to easily operate multiple devices with a single voice instruction and receive more reliable notifications.

[0521] A "user" is an individual or end user who utilizes the system to input voice instructions and operate a home appliance.

[0522] "Voice instructions" are operational instructions spoken by the user to the system, and refer to voice data captured through a microphone.

[0523] "Input means" refers to components including a microphone and its associated hardware and software that a user uses to input voice.

[0524] "Means for parsing and converting to text data" refers to the process and functionality of converting voice instructions into text using a voice recognition module and associated algorithms.

[0525] A "generative model" is a system that uses a generative AI model and refers to an algorithm that generates optimal home appliance operation commands based on user text data.

[0526] An "operation command" refers to a specific instruction generated to operate a home appliance or other device. An example would be "TURN_OFF LIGHT LIVING_ROOM."

[0527] "Applicable devices" refers to home appliances and other electronic devices that are controlled by voice instructions or operational commands, such as air conditioners, lighting, and televisions.

[0528] The "means for transmitting" refers to a system configuration including communication means and protocols for transmitting the generated operation command to the corresponding device.

[0529] "Feedback means" refers to a means for reporting the results of device operation to the system and returning that information to the user.

[0530] "Means of notification" refers to means such as audio output or display that the system uses to communicate operation results and other information to the user.

[0531] The present invention relates to a smart home system that can manage home appliances in an integrated manner based on user voice commands. This system is designed to allow users to simultaneously control multiple home appliances through voice commands by combining voice recognition technology and generative AI models. A specific embodiment of this system and its program processing are described below.

[0532] Overall system configuration

[0533] This smart home system mainly consists of the following components:

[0534] 1. Voice input method:

[0535] A smart home hub with a built-in microphone that allows the user to input voice commands.

[0536] An example of a prompt sentence is "Set the air conditioner to 20 degrees."

[0537] 2. Audio data analysis methods:

[0538] The voice data is converted into text data by a voice recognition module.

[0539] Specifically, it uses technologies such as the Google Cloud Speech-to-Text API.

[0540] 3. Generative AI Model:

[0541] Using generative AI (e.g., OpenAI's GPT-3) installed on the server, text data is analyzed and optimal home appliance operation commands are generated.

[0542] If the user instructs "Turn off the lights in the living room," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0543] 4. Command sending method:

[0544] The server sends the generated home appliance operation command to the relevant device (e.g., air conditioner, lighting).

[0545] Communication protocols include Wi-Fi and Bluetooth.

[0546] 5. Feedback methods:

[0547] When the home appliance completes its operation, it feeds back the results to the Hub, which then reports them to the server.

[0548] For example, if an air conditioner changes the temperature setting to 20 degrees, a feedback message "TEMPERATURE_SET_SUCCESS" is sent to the Hub.

[0549] 6. User Notification Methods:

[0550] The server checks the feedback results and sends a final confirmation message to the Hub.

[0551] The Hub will notify the user with a voice message such as "The air conditioner has been set to 20 degrees."

[0552] Specific examples

[0553] As a concrete example, let's take a look at the process in detail when a user wants to set the air conditioner in the living room to 20 degrees:

[0554] Voice command: The user says to the Hub, "Set the air conditioner to 20 degrees."

[0555] Speech recognition: The Hub's microphone captures the voice and sends the voice data to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0556] Instruction generation: The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20."

[0557] Command transmission: The server sends the generated command to the air conditioner in the living room.

[0558] Feedback: The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0559] User notification: The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub. The Hub notifies the user, "The air conditioner has been set to 20 degrees."

[0560] In this way, users can easily and reliably manage and operate home appliances using voice commands, significantly improving the convenience and reliability of smart homes.

[0561] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0562] Step 1:

[0563] The user inputs a voice command. The user speaks to the smart home hub, saying, "Set the air conditioner to 20 degrees." The input is voice data, which is captured by the hub's microphone. The voice data is temporarily stored in the hub's buffer memory.

[0564] Step 2:

[0565] The device (Hub) sends the captured voice data to the voice recognition module. The input is the saved voice data, which the voice recognition module analyzes and converts into text data such as "Set the air conditioner to 20 degrees." The output is text data. The voice recognition module uses the Google Cloud Speech-to-Text API.

[0566] Step 3:

[0567] The terminal (hub) sends text data to the server. The input is the converted text data, which the server receives. The server then sends the received text data to a generative AI (e.g., OpenAI's GPT-3) for analysis.

[0568] Step 4:

[0569] The server uses generative AI to analyze text data and generate optimal home appliance operation commands. The input is the text data "Set the air conditioner to 20 degrees," and the generative AI analyzes this to understand the user's intent. The output is the operation command "SET_TEMPERATURE 20."

[0570] Step 5:

[0571] The server sends the generated operation command to the corresponding device (the air conditioner in the living room). The input is the operation command "SET_TEMPERATURE 20", and the server sends this command to the air conditioner using the home appliance's communication protocol (e.g., Wi-Fi, Bluetooth). The output is the sent operation command.

[0572] Step 6:

[0573] The device (air conditioner) receives a command and changes the temperature setting to 20 degrees. The input is the operation command "SET_TEMPERATURE 20", and the air conditioner operates according to that command. The output is the result of the operation completion.

[0574] Step 7:

[0575] After the device (air conditioner) completes its operation, it sends a feedback message to the Hub. The input is the result of the operation completion, and the output is the feedback message "TEMPERATURE_SET_SUCCESS".

[0576] Step 8:

[0577] The terminal (Hub) sends a feedback message to the server. The input is the feedback message "TEMPERATURE_SET_SUCCESS" and sends it to the server. The output is a report to the server.

[0578] Step 9:

[0579] The server checks the feedback results and generates a final confirmation message, where the input is the feedback message and the output is the confirmation message.

[0580] Step 10:

[0581] The terminal (Hub) receives the confirmation message and notifies the user. The input is the confirmation message, and the output is a voice notification to the user: "The air conditioner has been set to 20 degrees."

[0582] (Application example 1)

[0583] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0584] Modern smart home systems operate each appliance based on user voice commands to achieve integrated management of home appliances. However, because these systems primarily focus on managing home appliances, they lack integration with external systems for specific service operations, such as food delivery. This means that when ordering food from a restaurant, users must use a separate application or go through multiple steps, which is inconvenient. Therefore, there is a need for a voice-command-based system that can seamlessly integrate with external systems.

[0585] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0586] In this invention, the server includes a means for a user to input voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal data operation commands based on the user instructions, a means for transmitting the generated operation commands to a corresponding external system, a means for providing feedback on the operation results of the external system, and a means for notifying the user of the feedback results. This enables a user to efficiently use an external food delivery system using only voice instructions and consistently manage all processes from ordering to receiving.

[0587] A "user" is an entity that operates the system and inputs voice instructions.

[0588] A "voice instruction" is an instruction given by the user to the system using voice.

[0589] A "voice recognition module" is software or hardware for analyzing voice instructions and converting them into text data.

[0590] "Generative AI" is an artificial intelligence module that generates optimal data manipulation commands based on user instructions.

[0591] "Data manipulation commands" are instructions that the generative AI generates by analyzing the user's voice instructions, instructing an external system to perform specific actions.

[0592] "External systems" refer to external services and devices other than home appliances, including, for example, food delivery systems.

[0593] "Feedback" refers to the process of informing a user of the results of an external system's operation.

[0594] "Notification" refers to the act or means of communicating the feedback results to the user.

[0595] This invention relates to a smart food delivery system that delivers food based on user voice instructions. Specifically, it is a system that enables users to issue voice instructions, analyzes and processes those instructions, and connects them to a delivery service.

[0596] Overall system configuration

[0597] Entering voice commands

[0598] A user inputs voice commands into a smartphone app, such as "order a pizza," which are captured through the smart device's microphone.

[0599] Analysis of voice instructions

[0600] The captured voice data is analyzed through a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converted into text data, which is then sent to a server.

[0601] Generate commands

[0602] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data and understand the user's intent. The generative AI generates optimal data manipulation commands based on the user's intent. These commands are then sent to the food delivery system.

[0603] Sending Commands

[0604] The generated data manipulation commands are sent to an external delivery system (e.g., a restaurant ordering system) to order a particular food item.

[0605] Receiving Feedback

[0606] Once the order is accepted, the external system sends the result as feedback to the server, for example, a message such as "your order has been accepted."

[0607] User Notification

[0608] The server then sends the feedback results to the app, allowing users to check the order completion and progress via a notification on their smartphone screen or through a voice message.

[0609] Hardware and Software Configuration

[0610] 1. Hardware

[0611] Smartphone (any smart device with a microphone and internet connection)

[0612] 2. Software

[0613] Speech recognition API (e.g., Google Cloud Speech-to-Text API)

[0614] Generative AI (e.g. OpenAI GPT-4)

[0615] Cloud servers (Amazon Web Services, Google Cloud, etc.)

[0616] Specific examples

[0617] Audio prompts

[0618] A user says to an app on their smartphone, "Order a pizza."

[0619] Speech recognition and text conversion

[0620] The smartphone captures the audio and uses a speech recognition API to convert it into text data such as "order a pizza."

[0621] Instruction analysis and order generation

[0622] The server receives the converted text data and uses generative AI to generate an order command such as "order one pizza."

[0623] Submitting an Order

[0624] The server sends the generated order command to an external food delivery system.

[0625] Feedback and Notifications

[0626] The external delivery system accepts the order and sends feedback of the order acceptance to the server. The server notifies the app of the feedback result and informs the user that "the pizza order has been completed."

[0627] Prompt Sentence Examples

[0628] User dictates: "Order me a pizza"

[0629] Prompt for generative AI: "The user says they want to order pizza. Please suggest what would be the best order."

[0630] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0631] Step 1:

[0632] A user inputs voice commands into a smartphone app. For example, the user says, "Order a pizza." The smartphone captures the voice and obtains the input as voice data.

[0633] Step 2:

[0634] The voice data is sent to the voice recognition module. The smartphone's voice recognition API (for example, Google Cloud Speech-to-Text API) analyzes the voice data and converts it into text data such as "Order a pizza." The text data is then output.

[0635] Step 3:

[0636] Text data is sent to a server. The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the received text data as input. The generative AI analyzes the instruction "order a pizza" and generates the optimal data manipulation command. In this case, a specific action command is generated: "Generate and send a pizza order." This is output as the generated command.

[0637] Step 4:

[0638] The server receives the generated data manipulation commands and sends them to an external food delivery system (e.g., a restaurant ordering system). The server uses the external system's API to input the order as a concrete order, e.g., sending an order for a pizza to a specific restaurant. The output is a feedback message that the order has been completed.

[0639] Step 5:

[0640] An external food delivery system receives the order and sends the result back to the server. For example, a feedback message such as "Order accepted" or "Order number 12345" is sent. The server receives this feedback message.

[0641] Step 6:

[0642] The server notifies the user's smartphone app of the feedback results it has received. The server takes the feedback message as input and sends a notification message to the smartphone app, such as "Your pizza order has been completed." The user's smartphone receives this message and displays it on the screen or as an audio notification. The output is a notification to the user.

[0643] Specific examples

[0644] Step 1:

[0645] A user says to their smartphone, "Order a pizza." Voice data is captured.

[0646] Step 2:

[0647] The voice data is converted into text data of "Order a pizza" by the Google Cloud Speech-to-Text API.

[0648] Step 3:

[0649] The text data is sent to the server, where it is analyzed by a generative AI model (OpenAI GPT-4) and generates a command to "generate and send a pizza order."

[0650] Step 4:

[0651] The server sends a "pizza order" to an external food delivery system, which receives the order as input.

[0652] Step 5:

[0653] The external delivery system accepts the order and sends a feedback message to the server saying "Order accepted."

[0654] Step 6:

[0655] The server sends a feedback message to the user saying, "Your pizza order is complete." The smartphone app receives this notification and displays it to the user.

[0656] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0657] The present invention combines a smart home system that integrates and manages home appliances based on user voice commands with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below. First, the overall flow of the system and the role of each component are described, followed by a description of specific program processing.

[0658] Overall system configuration

[0659] 1. A means for the user to input voice commands:

[0660] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[0661] 2. Means for analyzing voice instructions and converting them into text data:

[0662] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[0663] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[0664] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[0665] 4. Means including an emotion engine for recognizing a user's emotion based on an analysis of the user's voice instructions:

[0666] The emotion engine uses the analysis of voice commands to recognize the user's emotions, which are then used as a reference for further analysis and command generation by the generative AI.

[0667] 5. Means for sending the generated operation command to the relevant home appliance:

[0668] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[0669] 6. Means of feedback on the operation results of home appliances:

[0670] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[0671] 7. Means of notifying the user of the feedback results:

[0672] The server sends the feedback results back to the Hub, which then notifies the user via voice or other notification methods. The notification method and content are adjusted depending on the user's emotions.

[0673] Program processing

[0674] Speech Recognition and Analysis

[0675] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[0676] Emotion recognition by emotion engine

[0677] The text data sent from the speech recognition module is analyzed by the emotion engine to recognize the user's emotion. This emotion data is used for subsequent processing.

[0678] Generate and send instructions

[0679] The converted text data and emotion data are sent to the server, where the generative AI module analyzes the data. It accurately grasps the user's intentions and emotions and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0680] Home appliance control and feedback

[0681] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[0682] User Notification

[0683] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is played. Furthermore, the tone and details of the notification are adjusted based on the user's emotional data.

[0684] Specific examples

[0685] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[0686] Audio prompts

[0687] The user tells the Hub, "Set the air conditioner to 20 degrees."

[0688] Speech Recognition and Analysis

[0689] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees." This text data is sent to the emotion engine, which recognizes the user's emotion.

[0690] Generate and send instructions

[0691] The server receives the text data and emotion data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[0692] Home appliance control and feedback

[0693] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0694] User Notification

[0695] The Hub sends feedback to the server, which then sends a confirmation message back to the Hub. The Hub then notifies the user, "The air conditioner has been set to 20 degrees." If the user is stressed, for example, the notification will be made in a gentler tone.

[0696] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command, and the system can also respond flexibly based on the user's emotions.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[0700] Step 2:

[0701] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[0702] Step 3:

[0703] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[0704] Step 4:

[0705] The text data converted by the voice recognition module is sent to the emotion engine on the device (Hub). The emotion engine analyzes the text data and recognizes the user's emotion. In this case, it recognizes that the user is relaxed.

[0706] Step 5:

[0707] The terminal (Hub) sends the analysis results obtained from the voice recognition module and emotion engine to the server.

[0708] Step 6:

[0709] Based on the text data and emotion data received by the server, the generative AI module is requested to process the data. The generative AI module analyzes the user's intentions and emotions and generates the optimal operation command: "TURN_OFF LIGHT LIVING_ROOM."

[0710] Step 7:

[0711] The server sends the generated operation command to the terminal (living room light).

[0712] Step 8:

[0713] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the living room light.

[0714] Step 9:

[0715] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the device (Hub).

[0716] Step 10:

[0717] The terminal (Hub) receives the feedback message and sends it to the server.

[0718] Step 11:

[0719] The server checks the feedback message and sends a confirmation message to the terminal (Hub).

[0720] Step 12:

[0721] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice, "The living room lights have been turned off." Since the user is relaxed, the notification is made in a gentle tone.

[0722] The above is the specific procedure for turning off the living room lights in response to a user's voice command. By using the emotion engine, it is possible to respond flexibly according to the user's emotions.

[0723] Example 2

[0724] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0725] In conventional smart home systems, users typically operate home appliances by inputting voice commands, but these systems often lack sufficient flexibility to adapt to the user's emotional state. This can result in reduced user satisfaction and usability. Furthermore, because home appliances are controlled solely based on voice commands, there are limitations in the accuracy of analyzing the command content and the method of notifying the operation results. Therefore, an objective of the present invention is to improve user satisfaction by recognizing the user's emotions and operating and notifying home appliances based on those emotions.

[0726] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for a user to input a voice instruction, means for analyzing the voice instruction and converting it into text data, means including a generative artificial intelligence for generating an optimal home appliance operation command based on the user's instruction, means including an emotion analysis engine for recognizing the user's emotion based on the analysis result of the voice instruction, means for transmitting the generated operation command to the corresponding home appliance, means for feeding back the operation result of the home appliance, and means for notifying the user of the feedback result. This makes it possible to operate and notify the user of the home appliance according to the user's emotional state, thereby improving user satisfaction and usability.

[0727] "User" refers to any individual or entity that uses the System.

[0728] "Voice instructions" refer to instructions input by the user speaking to the system.

[0729] The term "means" refers to hardware or software components provided for performing a specific function or process.

[0730] "Speech recognition module" refers to a technical element for converting voice data into text data.

[0731] "Generative AI" refers to AI that automatically generates specific commands and solutions based on input data.

[0732] An "emotion analysis engine" refers to a technical element that determines a user's emotional state from input data.

[0733] An "operation command" refers to a specific instruction generated to control a home appliance.

[0734] "Home appliances" refers to electronic and electrical devices used in the home.

[0735] "Feedback" refers to the home appliance reporting the results and status of its actions to the system.

[0736] "Notification" refers to conveying feedback results or other information to the user.

[0737] The present invention is a smart home system that integrates and manages home appliances based on user voice commands, and further combines it with an emotion analysis engine that recognizes the user's emotions. In this section, specific embodiments for implementing the invention will be described.

[0738] Basic configuration

[0739] This system consists of the following main components:

[0740] 1. A means for the user to input voice commands: This is a device such as a smart home hub that has a built-in microphone.

[0741] 2. Means for analyzing voice instructions and converting them into text data: This is a voice recognition module within the Hub.

[0742] 3. Means including generative artificial intelligence that generates optimal home appliance operation commands based on user instructions: This applies to generative artificial intelligence installed on a server.

[0743] 4. Means including an emotion analysis engine that recognizes the user's emotions based on the analysis results of voice instructions: This corresponds to an emotion analysis engine installed in the server.

[0744] 5. Means for transmitting the generated operation command to the relevant home appliance: This is a function for transmitting a signal from the server to the home appliance.

[0745] 6. A means of feedback on the operation results of home appliances: This is a function that allows home appliances to send the operation results to the smart home hub.

[0746] 7. Means of notifying the user of the feedback results: The Hub will notify the user of the results by voice notification or other means.

[0747] Hardware and Software Specifications

[0748] Speech Recognition Module: Uses an external speech recognition service, for example the Google Speech API.

[0749] Sentiment analysis engine: For example, using an emotion recognition API such as IBM Watson.

[0750] Generative AI: Uses generative AI models such as OpenAI GPT-3.

[0751] Specific examples

[0752] Audio prompts

[0753] The user tells the Hub, "Set the air conditioner in the living room to 20 degrees."

[0754] Audio capture and analysis

[0755] The Smart Home Hub device uses a built-in microphone to capture the user's voice and transmits it to a voice recognition module, which converts the voice data into text data such as "Set the air conditioner in the living room to 20 degrees."

[0756] Emotion recognition by emotion engine

[0757] The text data sent from the device's voice recognition module is passed to the emotion analysis engine, which then recognizes the user's emotions based on this data. For example, it may determine that the user is relaxed.

[0758] Generating commands to operate home appliances

[0759] The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal commands to operate home appliances. For example, the command "SET_TEMPERATURE 20" is generated.

[0760] Sending commands to home appliances

[0761] The server sends the generated operation command to the air conditioner in the living room. The signal "SET_TEMPERATURE 20" is sent via the air conditioner's built-in WiFi module.

[0762] Home appliance behavior and feedback

[0763] The air conditioner in the living room changes the temperature setting based on the received command. When the air conditioner completes the setting, it sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[0764] Notifying the user of the results

[0765] The smart home hub receives the feedback message and passes it on to the server. The server then verifies the feedback and sends a notification back to the user. For example, a message like "The air conditioner has been set to 20 degrees" is generated. The tone and details of the notification are adjusted depending on the user's emotional data. The notification is sent via voice through the hub.

[0766] Prompt Sentence Examples

[0767] The user says, "Set the air conditioner in the living room to 20 degrees." The emotion engine determines that the user is in a relaxed state. Generate an appropriate command to operate the home appliances.

[0768] With the above configuration, this system efficiently manages home appliances based on the user's voice commands and also realizes flexible responses based on emotions, which is expected to improve user satisfaction and ease of use.

[0769] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0770] Step 1: User Enters Voice Command

[0771] Specific action: The user says to the Smart Home Hub, "Set the air conditioner in the living room to 20 degrees."

[0772] Input: User's voice command.

[0773] Output: Audio data captured by the microphone.

[0774] Step 2: Capture and analyze audio

[0775] How it works: The Smart Home Hub device uses its built-in microphone to capture the user's voice and save it as digital audio data.

[0776] Input: The captured audio data.

[0777] Output: Data transfer to the speech recognition module.

[0778] Step 3: Convert audio data to text

[0779] How it works: The voice recognition module analyzes the voice data and converts it into text data. The voice recognition technology used is Google Speech API.

[0780] Input: Audio digital data.

[0781] Output: Text data: "Set the air conditioner in the living room to 20 degrees."

[0782] Step 4: Emotion Recognition with the Emotion Engine

[0783] Specific operation: Text data sent from the device's voice recognition module is passed to the emotion analysis engine. The emotion analysis engine uses the text data to recognize the user's emotions and generate analysis results. An emotion recognition API such as IBM Watson is used.

[0784] Input: Text data from the speech recognition module.

[0785] Output: Data indicating the user's emotional state, such as whether they are relaxed.

[0786] Step 5: Generate commands to operate the appliances

[0787] How it works: The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal home appliance operation commands. OpenAI GPT-3 is used as the generative AI model.

[0788] Input: Text data and emotion data.

[0789] Output: Appliance operation command "SET_TEMPERATURE 20".

[0790] Step 6: Sending commands

[0791] Specific operation: The server sends the generated operation command to the relevant appliance. The WiFi module sends a signal of "SET_TEMPERATURE 20" to the air conditioner in the living room.

[0792] Input: Home appliance operation command.

[0793] Output: Operation command signal sent to the air conditioner.

[0794] Step 7: Appliance behavior and feedback

[0795] Specific operation: The air conditioner in the living room changes the temperature setting based on the received command. After the temperature is set to 20 degrees, the air conditioner sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[0796] Input: Home appliance operation command.

[0797] Output: A feedback message indicating the result of the operation.

[0798] Step 8: Processing and communicating feedback

[0799] Specific operation: The smart home hub receives the feedback message and forwards it to the server. The server analyzes the feedback and generates a message to notify the user of the result. The result notification takes into account the user's emotional data, and sends a voice message to the user via the hub saying, for example, "The air conditioner has been set to 20 degrees."

[0800] Input: The feedback message.

[0801] Output: Final message that is displayed to the user.

[0802] (Application example 2)

[0803] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0804] Conventional smart home systems are limited to controlling home appliances based on user voice commands, and have the drawback of being unable to flexibly respond to the user's emotions or circumstances. Furthermore, there are no systems that can not only control home appliances but also provide the content desired by users, limiting the means to improve the user experience. Therefore, there is a need for a system that can optimally operate home appliances and suggest content based on the user's intentions and emotions.

[0805] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0806] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative AI that generates optimal home appliance operation commands based on the user's instructions; means including an emotion engine that recognizes the user's emotions based on the analysis of the voice instruction; means for transmitting the generated operation commands to the relevant home appliance; means for feeding back the operation results of the home appliance; means for notifying the user of the feedback results; means including a generative AI that proposes optimal content that matches the user's intentions based on the voice instruction and emotion data; and means for providing the relevant content to the user. This enables the user to not only control the home appliance with a single voice instruction, but also to receive content that is optimal for their emotions and situation at the time.

[0807] "Voice instructions" refer to commands or requests that a user issues to the system using voice.

[0808] "Speech recognition module" refers to a software or hardware component for analyzing and converting voice instructions from a user into text data.

[0809] "Text data" refers to character string data generated by analyzing a voice instruction.

[0810] "Generative AI" refers to an artificial intelligence system that generates optimal commands and suggestions based on user input and the situation.

[0811] "Emotion engine" refers to a software or hardware component that analyzes and recognizes emotions from a user's voice or text data.

[0812] "Home appliances" refers to electronic devices and electrical appliances used in the home.

[0813] An "operation command" refers to a specific command that instructs a home appliance or other device to perform an operation.

[0814] "Feedback" refers to reporting the results of an appliance's execution or the results of a system's operation to the user.

[0815] "Content" refers to information and entertainment provided to users, such as music, videos, and news.

[0816] "Content suggestion" refers to selecting and providing optimal content based on the user's intentions and emotions.

[0817] The present invention relates to a system for controlling home appliances based on a user's voice instructions and emotional data, and for providing optimal content. The specific configuration and operation of this system are described below.

[0818] Overall system configuration

[0819] 1. Voice command input method

[0820] A user inputs voice instructions by speaking into a smart device (e.g., a smartphone), which is equipped with a microphone and captures the user's voice.

[0821] 2. Means for analyzing voice instructions and converting them into text data

[0822] The captured audio is sent to a speech recognition module (e.g., Google Speech-to-Text API) on the device, which converts the audio data into text data.

[0823] 3. Emotion Recognition Method Using Emotion Engine

[0824] The converted text data is analyzed by an emotion engine (e.g., Affectiva SDK) to recognize the user's emotion. The emotion data is used for subsequent processing.

[0825] 4. How generative AI generates instructions

[0826] The text data and emotion data are sent to a server, where a generative AI (e.g., OpenAI's GPT model) analyzes the data. Based on the user's intentions and emotions, optimal home appliance operation commands and content suggestions are generated.

[0827] 5. Means for transmitting generated operation commands and content

[0828] The server transmits the generated operation command to the corresponding home appliance and further provides the content requested by the user.

[0829] 6. Feedback method for home appliance operation results

[0830] When the home appliance completes its operation, it feeds back the results of its operation to the smart device, which then sends the feedback to the server.

[0831] 7. Means of providing feedback to users

[0832] The server returns the feedback results to the smart device, which then notifies the user of the results using voice or other notification methods, which are adjusted based on the user's emotions.

[0833] Program processing explanation

[0834] Hardware and software used

[0835] Hardware: Smart device (e.g. smartphone, microphone, speaker, internet connection)

[0836] Software: Speech recognition module (Google Speech-to-Text API), emotion recognition engine (Affectiva SDK), generative AI (OpenAI's GPT model)

[0837] The server includes a means for inputting voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal home appliance operation commands and content suggestions based on the user's instructions, a means including an emotion engine for recognizing the user's emotions based on the analysis of the voice instructions, a means for sending the generated operation commands to the relevant home appliances, a means for feeding back the operation results of the home appliances, a means for notifying the user of the feedback results, and a means for providing optimal content to the user. This enables the user to not only control home appliances with a single voice instruction, but also to receive optimal content according to their emotions and circumstances at the time.

[0838] Specific examples

[0839] For example, if a user says, "Show me an uplifting video," the speech recognition module converts the speech into text data. This text data is analyzed by the emotion engine, which recognizes the emotion "I'm feeling a little down." The generative AI then uses this information to suggest an "uplifting video." This allows the user to receive appropriate content.

[0840] Prompt Sentence Examples

[0841] A user says, "Show me an uplifting video" and their emotional state is "I'm feeling a bit down." Suggest the best content.

[0842] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] The user inputs voice instructions into the smart device, which are captured by the device's microphone and sent to the smart device as voice data.

[0845] Step 2:

[0846] The smart device's voice recognition module (e.g., Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is the user's voice data, and the output is the analysis result, such as "Show me an uplifting video."

[0847] Step 3:

[0848] The text data is sent to an emotion recognition engine (e.g., Affectiva SDK), which takes the text data sent from the speech recognition module as input and analyzes it to output the user's emotional state (e.g., "I'm feeling a little depressed").

[0849] Step 4:

[0850] The smart device sends text data and emotion data to the server. The input is the text data and emotion data from the emotion recognition engine, which is then sent to the server.

[0851] Step 5:

[0852] The server's generative AI (e.g., OpenAI's GPT model) analyzes text data and emotional data and generates optimal content suggestions based on the user's intent. In this case, the input is the text data "Show me an uplifting video" and the emotional data "I'm feeling a little down," and the output is a suggestion for an "uplifting video."

[0853] Step 6:

[0854] The generated content proposals are sent from the server to the smart device. As input, the proposed content data is sent from the server to the smart device, and as output, the smart device prepares to display the content playback screen to the user.

[0855] Step 7:

[0856] The smart device presents the suggested content to the user. The input is the content data sent from the server, and the output is the content played back to the user.

[0857] Step 8:

[0858] After the user has finished viewing the content, the results are sent from the smart device to the server as feedback. The input is the user's operations and viewing results, and the output is the feedback data sent to the server.

[0859] Step 9:

[0860] The server analyzes the feedback data and uses it to further optimize future content suggestions and home appliance operation. The input is feedback data sent from smart devices, and the output is data that will be reflected in future suggestions.

[0861] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0862] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0863] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0864] [Third embodiment]

[0865] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0866] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0867] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0868] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0869] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0870] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0871] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0872] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0873] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0874] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0875] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0876] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0877] The present invention relates to a smart home system that integrates and manages home appliances based on user voice commands. A specific embodiment of the present invention will be described below. First, the overall flow of the system and the role of each component will be described, followed by a description of specific program processing.

[0878] Overall system configuration

[0879] 1. A means for the user to input voice commands:

[0880] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[0881] 2. Means for analyzing voice instructions and converting them into text data:

[0882] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[0883] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[0884] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[0885] 4. A method for sending the generated operation command to the corresponding home appliance:

[0886] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[0887] 5. Means of feedback on the operation results of home appliances:

[0888] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[0889] 6. Means of notifying the user of the feedback results:

[0890] The server sends the feedback results back to the Hub, which then notifies the user of the results by voice or other notification methods.

[0891] Program processing

[0892] Speech Recognition and Analysis

[0893] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[0894] Generate and send instructions

[0895] The converted text data is sent to the server, where the generative AI module analyzes the text. It accurately understands the user's intention and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0896] Home appliance control and feedback

[0897] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[0898] User Notification

[0899] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is generated.

[0900] Specific examples

[0901] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[0902] Audio prompts

[0903] The user tells the Hub, "Set the air conditioner to 20 degrees."

[0904] Speech Recognition and Analysis

[0905] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0906] Generate and send instructions

[0907] The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[0908] Home appliance control and feedback

[0909] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0910] User Notification

[0911] The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub, which notifies the user that the air conditioner has been set to 20 degrees.

[0912] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command.

[0913] The processing flow will be explained below.

[0914] Step 1:

[0915] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[0916] Step 2:

[0917] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[0918] Step 3:

[0919] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[0920] Step 4:

[0921] The terminal (Hub) sends the text data received from the voice recognition module to the server.

[0922] Step 5:

[0923] The server receives the text data and requests processing from the generative AI module. The generative AI module analyzes the text data and generates the optimal operation command. Specifically, it generates the command "TURN_OFF LIGHT LIVING_ROOM."

[0924] Step 6:

[0925] The server sends the generated operation command to the lighting in the living room.

[0926] Step 7:

[0927] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the light.

[0928] Step 8:

[0929] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the Hub.

[0930] Step 9:

[0931] The terminal (Hub) receives the feedback message and sends it to the server.

[0932] Step 10:

[0933] The server verifies the feedback message and sends a confirmation message to the Hub.

[0934] Step 11:

[0935] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice that "The living room lights have been turned off."

[0936] The above is the specific procedure for turning off the living room lights by voice command from the user. This series of steps allows the user to operate home appliances simply and intuitively.

[0937] Example 1

[0938] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0939] In modern smart home systems, users must use separate remote controls and applications to operate multiple home appliances individually. This complex operation is burdensome for users and inconvenient. Furthermore, even when operating using voice commands, the accuracy of voice recognition and the transmission of commands to the home appliances can be unstable, resulting in a lack of reliability. Therefore, the present invention aims to comprehensively manage home appliances based on user voice commands, thereby improving ease of operation and reliability.

[0940] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0941] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative model for generating optimal home appliance operation commands based on the user instruction; means for transmitting the generated operation commands to the corresponding devices; means for providing feedback on the operation results of the devices; means for notifying the user of the feedback results; and means for analyzing the user's intention, generating commands using the generative model, transmitting the commands to the corresponding devices, and notifying the results. This allows the user to easily operate multiple devices with a single voice instruction and receive more reliable notifications.

[0942] A "user" is an individual or end user who utilizes the system to input voice instructions and operate a home appliance.

[0943] "Voice instructions" are operational instructions spoken by the user to the system, and refer to voice data captured through a microphone.

[0944] "Input means" refers to components including a microphone and its associated hardware and software that a user uses to input voice.

[0945] "Means for parsing and converting to text data" refers to the process and functionality of converting voice instructions into text using a voice recognition module and associated algorithms.

[0946] A "generative model" is a system that uses a generative AI model and refers to an algorithm that generates optimal home appliance operation commands based on user text data.

[0947] An "operation command" refers to a specific instruction generated to operate a home appliance or other device. An example would be "TURN_OFF LIGHT LIVING_ROOM."

[0948] "Applicable devices" refers to home appliances and other electronic devices that are controlled by voice instructions or operational commands, such as air conditioners, lighting, and televisions.

[0949] The "means for transmitting" refers to a system configuration including communication means and protocols for transmitting the generated operation command to the corresponding device.

[0950] "Feedback means" refers to a means for reporting the results of device operation to the system and returning that information to the user.

[0951] "Means of notification" refers to means such as audio output or display that the system uses to communicate operation results and other information to the user.

[0952] The present invention relates to a smart home system that can manage home appliances in an integrated manner based on user voice commands. This system is designed to allow users to simultaneously control multiple home appliances through voice commands by combining voice recognition technology and generative AI models. A specific embodiment of this system and its program processing are described below.

[0953] Overall system configuration

[0954] This smart home system mainly consists of the following components:

[0955] 1. Voice input method:

[0956] A smart home hub with a built-in microphone that allows the user to input voice commands.

[0957] An example of a prompt sentence is "Set the air conditioner to 20 degrees."

[0958] 2. Audio data analysis methods:

[0959] The voice data is converted into text data by a voice recognition module.

[0960] Specifically, it uses technologies such as the Google Cloud Speech-to-Text API.

[0961] 3. Generative AI Model:

[0962] Using generative AI (e.g., OpenAI's GPT-3) installed on the server, text data is analyzed and optimal home appliance operation commands are generated.

[0963] If the user instructs "Turn off the lights in the living room," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[0964] 4. Command sending method:

[0965] The server sends the generated home appliance operation command to the relevant device (e.g., air conditioner, lighting).

[0966] Communication protocols include Wi-Fi and Bluetooth.

[0967] 5. Feedback methods:

[0968] When the home appliance completes its operation, it feeds back the results to the Hub, which then reports them to the server.

[0969] For example, if an air conditioner changes the temperature setting to 20 degrees, a feedback message "TEMPERATURE_SET_SUCCESS" is sent to the Hub.

[0970] 6. User Notification Methods:

[0971] The server checks the feedback results and sends a final confirmation message to the Hub.

[0972] The Hub will notify the user with a voice message such as "The air conditioner has been set to 20 degrees."

[0973] Specific examples

[0974] As a concrete example, let's take a look at the process in detail when a user wants to set the air conditioner in the living room to 20 degrees:

[0975] Voice command: The user says to the Hub, "Set the air conditioner to 20 degrees."

[0976] Speech recognition: The Hub's microphone captures the voice and sends the voice data to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[0977] Instruction generation: The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20."

[0978] Command transmission: The server sends the generated command to the air conditioner in the living room.

[0979] Feedback: The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[0980] User notification: The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub. The Hub notifies the user, "The air conditioner has been set to 20 degrees."

[0981] In this way, users can easily and reliably manage and operate home appliances using voice commands, significantly improving the convenience and reliability of smart homes.

[0982] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0983] Step 1:

[0984] The user inputs a voice command. The user speaks to the smart home hub, saying, "Set the air conditioner to 20 degrees." The input is voice data, which is captured by the hub's microphone. The voice data is temporarily stored in the hub's buffer memory.

[0985] Step 2:

[0986] The device (Hub) sends the captured voice data to the voice recognition module. The input is the saved voice data, which the voice recognition module analyzes and converts into text data such as "Set the air conditioner to 20 degrees." The output is text data. The voice recognition module uses the Google Cloud Speech-to-Text API.

[0987] Step 3:

[0988] The terminal (hub) sends text data to the server. The input is the converted text data, which the server receives. The server then sends the received text data to a generative AI (e.g., OpenAI's GPT-3) for analysis.

[0989] Step 4:

[0990] The server uses generative AI to analyze text data and generate optimal home appliance operation commands. The input is the text data "Set the air conditioner to 20 degrees," and the generative AI analyzes this to understand the user's intent. The output is the operation command "SET_TEMPERATURE 20."

[0991] Step 5:

[0992] The server sends the generated operation command to the corresponding device (the air conditioner in the living room). The input is the operation command "SET_TEMPERATURE 20", and the server sends this command to the air conditioner using the home appliance's communication protocol (e.g., Wi-Fi, Bluetooth). The output is the sent operation command.

[0993] Step 6:

[0994] The device (air conditioner) receives a command and changes the temperature setting to 20 degrees. The input is the operation command "SET_TEMPERATURE 20", and the air conditioner operates according to that command. The output is the result of the operation completion.

[0995] Step 7:

[0996] After the device (air conditioner) completes its operation, it sends a feedback message to the Hub. The input is the result of the operation completion, and the output is the feedback message "TEMPERATURE_SET_SUCCESS".

[0997] Step 8:

[0998] The terminal (Hub) sends a feedback message to the server. The input is the feedback message "TEMPERATURE_SET_SUCCESS" and sends it to the server. The output is a report to the server.

[0999] Step 9:

[1000] The server checks the feedback results and generates a final confirmation message, where the input is the feedback message and the output is the confirmation message.

[1001] Step 10:

[1002] The terminal (Hub) receives the confirmation message and notifies the user. The input is the confirmation message, and the output is a voice notification to the user: "The air conditioner has been set to 20 degrees."

[1003] (Application example 1)

[1004] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] Modern smart home systems operate each appliance based on user voice commands to achieve integrated management of home appliances. However, because these systems primarily focus on managing home appliances, they lack integration with external systems for specific service operations, such as food delivery. This means that when ordering food from a restaurant, users must use a separate application or go through multiple steps, which is inconvenient. Therefore, there is a need for a voice-command-based system that can seamlessly integrate with external systems.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1007] In this invention, the server includes a means for a user to input voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal data operation commands based on the user instructions, a means for transmitting the generated operation commands to a corresponding external system, a means for providing feedback on the operation results of the external system, and a means for notifying the user of the feedback results. This enables a user to efficiently use an external food delivery system using only voice instructions and consistently manage all processes from ordering to receiving.

[1008] A "user" is an entity that operates the system and inputs voice instructions.

[1009] A "voice instruction" is an instruction given by the user to the system using voice.

[1010] A "voice recognition module" is software or hardware for analyzing voice instructions and converting them into text data.

[1011] "Generative AI" is an artificial intelligence module that generates optimal data manipulation commands based on user instructions.

[1012] "Data manipulation commands" are instructions that the generative AI generates by analyzing the user's voice instructions, instructing an external system to perform specific actions.

[1013] "External systems" refer to external services and devices other than home appliances, including, for example, food delivery systems.

[1014] "Feedback" refers to the process of informing a user of the results of an external system's operation.

[1015] "Notification" refers to the act or means of communicating the feedback results to the user.

[1016] This invention relates to a smart food delivery system that delivers food based on user voice instructions. Specifically, it is a system that enables users to issue voice instructions, analyzes and processes those instructions, and connects them to a delivery service.

[1017] Overall system configuration

[1018] Entering voice commands

[1019] A user inputs voice commands into a smartphone app, such as "order a pizza," which are captured through the smart device's microphone.

[1020] Analysis of voice instructions

[1021] The captured voice data is analyzed through a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converted into text data, which is then sent to a server.

[1022] Generate commands

[1023] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data and understand the user's intent. The generative AI generates optimal data manipulation commands based on the user's intent. These commands are then sent to the food delivery system.

[1024] Sending Commands

[1025] The generated data manipulation commands are sent to an external delivery system (e.g., a restaurant ordering system) to order a particular food item.

[1026] Receiving Feedback

[1027] Once the order is accepted, the external system sends the result as feedback to the server, for example, a message such as "your order has been accepted."

[1028] User Notification

[1029] The server then sends the feedback results to the app, allowing users to check the order completion and progress via a notification on their smartphone screen or through a voice message.

[1030] Hardware and Software Configuration

[1031] 1. Hardware

[1032] Smartphone (any smart device with a microphone and internet connection)

[1033] 2. Software

[1034] Speech recognition API (e.g., Google Cloud Speech-to-Text API)

[1035] Generative AI (e.g. OpenAI GPT-4)

[1036] Cloud servers (Amazon Web Services, Google Cloud, etc.)

[1037] Specific examples

[1038] Audio prompts

[1039] A user says to an app on their smartphone, "Order a pizza."

[1040] Speech recognition and text conversion

[1041] The smartphone captures the audio and uses a speech recognition API to convert it into text data such as "order a pizza."

[1042] Instruction analysis and order generation

[1043] The server receives the converted text data and uses generative AI to generate an order command such as "order one pizza."

[1044] Submitting an Order

[1045] The server sends the generated order command to an external food delivery system.

[1046] Feedback and Notifications

[1047] The external delivery system accepts the order and sends feedback of the order acceptance to the server. The server notifies the app of the feedback result and informs the user that "the pizza order has been completed."

[1048] Prompt Sentence Examples

[1049] User dictates: "Order me a pizza"

[1050] Prompt for generative AI: "The user says they want to order pizza. Please suggest what would be the best order."

[1051] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1052] Step 1:

[1053] A user inputs voice commands into a smartphone app. For example, the user says, "Order a pizza." The smartphone captures the voice and obtains the input as voice data.

[1054] Step 2:

[1055] The voice data is sent to the voice recognition module. The smartphone's voice recognition API (for example, Google Cloud Speech-to-Text API) analyzes the voice data and converts it into text data such as "Order a pizza." The text data is then output.

[1056] Step 3:

[1057] Text data is sent to a server. The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the received text data as input. The generative AI analyzes the instruction "order a pizza" and generates the optimal data manipulation command. In this case, a specific action command is generated: "Generate and send a pizza order." This is output as the generated command.

[1058] Step 4:

[1059] The server receives the generated data manipulation commands and sends them to an external food delivery system (e.g., a restaurant ordering system). The server uses the external system's API to input the order as a concrete order, e.g., sending an order for a pizza to a specific restaurant. The output is a feedback message that the order has been completed.

[1060] Step 5:

[1061] An external food delivery system receives the order and sends the result back to the server. For example, a feedback message such as "Order accepted" or "Order number 12345" is sent. The server receives this feedback message.

[1062] Step 6:

[1063] The server notifies the user's smartphone app of the feedback results it has received. The server takes the feedback message as input and sends a notification message to the smartphone app, such as "Your pizza order has been completed." The user's smartphone receives this message and displays it on the screen or as an audio notification. The output is a notification to the user.

[1064] Specific examples

[1065] Step 1:

[1066] A user says to their smartphone, "Order a pizza." Voice data is captured.

[1067] Step 2:

[1068] The voice data is converted into text data of "Order a pizza" by the Google Cloud Speech-to-Text API.

[1069] Step 3:

[1070] The text data is sent to the server, where it is analyzed by a generative AI model (OpenAI GPT-4) and generates a command to "generate and send a pizza order."

[1071] Step 4:

[1072] The server sends a "pizza order" to an external food delivery system, which receives the order as input.

[1073] Step 5:

[1074] The external delivery system accepts the order and sends a feedback message to the server saying "Order accepted."

[1075] Step 6:

[1076] The server sends a feedback message to the user saying, "Your pizza order is complete." The smartphone app receives this notification and displays it to the user.

[1077] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1078] The present invention combines a smart home system that integrates and manages home appliances based on user voice commands with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below. First, the overall flow of the system and the role of each component are described, followed by a description of specific program processing.

[1079] Overall system configuration

[1080] 1. A means for the user to input voice commands:

[1081] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[1082] 2. Means for analyzing voice instructions and converting them into text data:

[1083] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[1084] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[1085] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[1086] 4. Means including an emotion engine for recognizing a user's emotion based on an analysis of the user's voice instructions:

[1087] The emotion engine uses the analysis of voice commands to recognize the user's emotions, which are then used as a reference for further analysis and command generation by the generative AI.

[1088] 5. Means for sending the generated operation command to the relevant home appliance:

[1089] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[1090] 6. Means of feedback on the operation results of home appliances:

[1091] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[1092] 7. Means of notifying the user of the feedback results:

[1093] The server sends the feedback results back to the Hub, which then notifies the user via voice or other notification methods. The notification method and content are adjusted depending on the user's emotions.

[1094] Program processing

[1095] Speech Recognition and Analysis

[1096] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[1097] Emotion recognition by emotion engine

[1098] The text data sent from the speech recognition module is analyzed by the emotion engine to recognize the user's emotion. This emotion data is used for subsequent processing.

[1099] Generate and send instructions

[1100] The converted text data and emotion data are sent to the server, where the generative AI module analyzes the data. It accurately grasps the user's intentions and emotions and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[1101] Home appliance control and feedback

[1102] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[1103] User Notification

[1104] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is played. Furthermore, the tone and details of the notification are adjusted based on the user's emotional data.

[1105] Specific examples

[1106] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[1107] Audio prompts

[1108] The user tells the Hub, "Set the air conditioner to 20 degrees."

[1109] Speech Recognition and Analysis

[1110] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees." This text data is sent to the emotion engine, which recognizes the user's emotion.

[1111] Generate and send instructions

[1112] The server receives the text data and emotion data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[1113] Home appliance control and feedback

[1114] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[1115] User Notification

[1116] The Hub sends feedback to the server, which then sends a confirmation message back to the Hub. The Hub then notifies the user, "The air conditioner has been set to 20 degrees." If the user is stressed, for example, the notification will be made in a gentler tone.

[1117] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command, and the system can also respond flexibly based on the user's emotions.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[1121] Step 2:

[1122] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[1123] Step 3:

[1124] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[1125] Step 4:

[1126] The text data converted by the voice recognition module is sent to the emotion engine on the device (Hub). The emotion engine analyzes the text data and recognizes the user's emotion. In this case, it recognizes that the user is relaxed.

[1127] Step 5:

[1128] The terminal (Hub) sends the analysis results obtained from the voice recognition module and emotion engine to the server.

[1129] Step 6:

[1130] Based on the text data and emotion data received by the server, the generative AI module is requested to process the data. The generative AI module analyzes the user's intentions and emotions and generates the optimal operation command: "TURN_OFF LIGHT LIVING_ROOM."

[1131] Step 7:

[1132] The server sends the generated operation command to the terminal (living room light).

[1133] Step 8:

[1134] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the living room light.

[1135] Step 9:

[1136] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the device (Hub).

[1137] Step 10:

[1138] The terminal (Hub) receives the feedback message and sends it to the server.

[1139] Step 11:

[1140] The server checks the feedback message and sends a confirmation message to the terminal (Hub).

[1141] Step 12:

[1142] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice, "The living room lights have been turned off." Since the user is relaxed, the notification is made in a gentle tone.

[1143] The above is the specific procedure for turning off the living room lights in response to a user's voice command. By using the emotion engine, it is possible to respond flexibly according to the user's emotions.

[1144] Example 2

[1145] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1146] In conventional smart home systems, users typically operate home appliances by inputting voice commands, but these systems often lack sufficient flexibility to adapt to the user's emotional state. This can result in reduced user satisfaction and usability. Furthermore, because home appliances are controlled solely based on voice commands, there are limitations in the accuracy of analyzing the command content and the method of notifying the operation results. Therefore, an objective of the present invention is to improve user satisfaction by recognizing the user's emotions and operating and notifying home appliances based on those emotions.

[1147] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for a user to input a voice instruction, means for analyzing the voice instruction and converting it into text data, means including a generative artificial intelligence for generating an optimal home appliance operation command based on the user's instruction, means including an emotion analysis engine for recognizing the user's emotion based on the analysis result of the voice instruction, means for transmitting the generated operation command to the corresponding home appliance, means for feeding back the operation result of the home appliance, and means for notifying the user of the feedback result. This makes it possible to operate and notify the user of the home appliance according to the user's emotional state, thereby improving user satisfaction and usability.

[1148] "User" refers to any individual or entity that uses the System.

[1149] "Voice instructions" refer to instructions input by the user speaking to the system.

[1150] The term "means" refers to hardware or software components provided for performing a specific function or process.

[1151] "Speech recognition module" refers to a technical element for converting voice data into text data.

[1152] "Generative AI" refers to AI that automatically generates specific commands and solutions based on input data.

[1153] An "emotion analysis engine" refers to a technical element that determines a user's emotional state from input data.

[1154] An "operation command" refers to a specific instruction generated to control a home appliance.

[1155] "Home appliances" refers to electronic and electrical devices used in the home.

[1156] "Feedback" refers to the home appliance reporting the results and status of its actions to the system.

[1157] "Notification" refers to conveying feedback results or other information to the user.

[1158] The present invention is a smart home system that integrates and manages home appliances based on user voice commands, and further combines it with an emotion analysis engine that recognizes the user's emotions. In this section, specific embodiments for implementing the invention will be described.

[1159] Basic configuration

[1160] This system consists of the following main components:

[1161] 1. A means for the user to input voice commands: This is a device such as a smart home hub that has a built-in microphone.

[1162] 2. Means for analyzing voice instructions and converting them into text data: This is a voice recognition module within the Hub.

[1163] 3. Means including generative artificial intelligence that generates optimal home appliance operation commands based on user instructions: This applies to generative artificial intelligence installed on a server.

[1164] 4. Means including an emotion analysis engine that recognizes the user's emotions based on the analysis results of voice instructions: This corresponds to an emotion analysis engine installed in the server.

[1165] 5. Means for transmitting the generated operation command to the relevant home appliance: This is a function for transmitting a signal from the server to the home appliance.

[1166] 6. A means of feedback on the operation results of home appliances: This is a function that allows home appliances to send the operation results to the smart home hub.

[1167] 7. Means of notifying the user of the feedback results: The Hub will notify the user of the results by voice notification or other means.

[1168] Hardware and Software Specifications

[1169] Speech Recognition Module: Uses an external speech recognition service, for example the Google Speech API.

[1170] Sentiment analysis engine: For example, using an emotion recognition API such as IBM Watson.

[1171] Generative AI: Uses generative AI models such as OpenAI GPT-3.

[1172] Specific examples

[1173] Audio prompts

[1174] The user tells the Hub, "Set the air conditioner in the living room to 20 degrees."

[1175] Audio capture and analysis

[1176] The Smart Home Hub device uses a built-in microphone to capture the user's voice and transmits it to a voice recognition module, which converts the voice data into text data such as "Set the air conditioner in the living room to 20 degrees."

[1177] Emotion recognition by emotion engine

[1178] The text data sent from the device's voice recognition module is passed to the emotion analysis engine, which then recognizes the user's emotions based on this data. For example, it may determine that the user is relaxed.

[1179] Generating commands to operate home appliances

[1180] The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal commands to operate home appliances. For example, the command "SET_TEMPERATURE 20" is generated.

[1181] Sending commands to home appliances

[1182] The server sends the generated operation command to the air conditioner in the living room. The signal "SET_TEMPERATURE 20" is sent via the air conditioner's built-in WiFi module.

[1183] Home appliance behavior and feedback

[1184] The air conditioner in the living room changes the temperature setting based on the received command. When the air conditioner completes the setting, it sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[1185] Notifying the user of the results

[1186] The smart home hub receives the feedback message and passes it on to the server. The server then verifies the feedback and sends a notification back to the user. For example, a message like "The air conditioner has been set to 20 degrees" is generated. The tone and details of the notification are adjusted depending on the user's emotional data. The notification is sent via voice through the hub.

[1187] Prompt Sentence Examples

[1188] The user says, "Set the air conditioner in the living room to 20 degrees." The emotion engine determines that the user is in a relaxed state. Generate an appropriate command to operate the home appliances.

[1189] With the above configuration, this system efficiently manages home appliances based on the user's voice commands and also realizes flexible responses based on emotions, which is expected to improve user satisfaction and ease of use.

[1190] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1191] Step 1: User Enters Voice Command

[1192] Specific action: The user says to the Smart Home Hub, "Set the air conditioner in the living room to 20 degrees."

[1193] Input: User's voice command.

[1194] Output: Audio data captured by the microphone.

[1195] Step 2: Capture and analyze audio

[1196] How it works: The Smart Home Hub device uses its built-in microphone to capture the user's voice and save it as digital audio data.

[1197] Input: The captured audio data.

[1198] Output: Data transfer to the speech recognition module.

[1199] Step 3: Convert audio data to text

[1200] How it works: The voice recognition module analyzes the voice data and converts it into text data. The voice recognition technology used is Google Speech API.

[1201] Input: Audio digital data.

[1202] Output: Text data: "Set the air conditioner in the living room to 20 degrees."

[1203] Step 4: Emotion Recognition with the Emotion Engine

[1204] Specific operation: Text data sent from the device's voice recognition module is passed to the emotion analysis engine. The emotion analysis engine uses the text data to recognize the user's emotions and generate analysis results. An emotion recognition API such as IBM Watson is used.

[1205] Input: Text data from the speech recognition module.

[1206] Output: Data indicating the user's emotional state, such as whether they are relaxed.

[1207] Step 5: Generate commands to operate the appliances

[1208] How it works: The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal home appliance operation commands. OpenAI GPT-3 is used as the generative AI model.

[1209] Input: Text data and emotion data.

[1210] Output: Appliance operation command "SET_TEMPERATURE 20".

[1211] Step 6: Sending commands

[1212] Specific operation: The server sends the generated operation command to the relevant appliance. The WiFi module sends a signal of "SET_TEMPERATURE 20" to the air conditioner in the living room.

[1213] Input: Home appliance operation command.

[1214] Output: Operation command signal sent to the air conditioner.

[1215] Step 7: Appliance behavior and feedback

[1216] Specific operation: The air conditioner in the living room changes the temperature setting based on the received command. After the temperature is set to 20 degrees, the air conditioner sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[1217] Input: Home appliance operation command.

[1218] Output: A feedback message indicating the result of the operation.

[1219] Step 8: Processing and communicating feedback

[1220] Specific operation: The smart home hub receives the feedback message and forwards it to the server. The server analyzes the feedback and generates a message to notify the user of the result. The result notification takes into account the user's emotional data, and sends a voice message to the user via the hub saying, for example, "The air conditioner has been set to 20 degrees."

[1221] Input: The feedback message.

[1222] Output: Final message that is displayed to the user.

[1223] (Application example 2)

[1224] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1225] Conventional smart home systems are limited to controlling home appliances based on user voice commands, and have the drawback of being unable to flexibly respond to the user's emotions or circumstances. Furthermore, there are no systems that can not only control home appliances but also provide the content desired by users, limiting the means to improve the user experience. Therefore, there is a need for a system that can optimally operate home appliances and suggest content based on the user's intentions and emotions.

[1226] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1227] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative AI that generates optimal home appliance operation commands based on the user's instructions; means including an emotion engine that recognizes the user's emotions based on the analysis of the voice instruction; means for transmitting the generated operation commands to the relevant home appliance; means for feeding back the operation results of the home appliance; means for notifying the user of the feedback results; means including a generative AI that proposes optimal content that matches the user's intentions based on the voice instruction and emotion data; and means for providing the relevant content to the user. This enables the user to not only control the home appliance with a single voice instruction, but also to receive content that is optimal for their emotions and situation at the time.

[1228] "Voice instructions" refer to commands or requests that a user issues to the system using voice.

[1229] "Speech recognition module" refers to a software or hardware component for analyzing and converting voice instructions from a user into text data.

[1230] "Text data" refers to character string data generated by analyzing a voice instruction.

[1231] "Generative AI" refers to an artificial intelligence system that generates optimal commands and suggestions based on user input and the situation.

[1232] "Emotion engine" refers to a software or hardware component that analyzes and recognizes emotions from a user's voice or text data.

[1233] "Home appliances" refers to electronic devices and electrical appliances used in the home.

[1234] An "operation command" refers to a specific command that instructs a home appliance or other device to perform an operation.

[1235] "Feedback" refers to reporting the results of an appliance's execution or the results of a system's operation to the user.

[1236] "Content" refers to information and entertainment provided to users, such as music, videos, and news.

[1237] "Content suggestion" refers to selecting and providing optimal content based on the user's intentions and emotions.

[1238] The present invention relates to a system for controlling home appliances based on a user's voice instructions and emotional data, and for providing optimal content. The specific configuration and operation of this system are described below.

[1239] Overall system configuration

[1240] 1. Voice command input method

[1241] A user inputs voice instructions by speaking into a smart device (e.g., a smartphone), which is equipped with a microphone and captures the user's voice.

[1242] 2. Means for analyzing voice instructions and converting them into text data

[1243] The captured audio is sent to a speech recognition module (e.g., Google Speech-to-Text API) on the device, which converts the audio data into text data.

[1244] 3. Emotion Recognition Method Using Emotion Engine

[1245] The converted text data is analyzed by an emotion engine (e.g., Affectiva SDK) to recognize the user's emotion. The emotion data is used for subsequent processing.

[1246] 4. How generative AI generates instructions

[1247] The text data and emotion data are sent to a server, where a generative AI (e.g., OpenAI's GPT model) analyzes the data. Based on the user's intentions and emotions, optimal home appliance operation commands and content suggestions are generated.

[1248] 5. Means for transmitting generated operation commands and content

[1249] The server transmits the generated operation command to the corresponding home appliance and further provides the content requested by the user.

[1250] 6. Feedback method for home appliance operation results

[1251] When the home appliance completes its operation, it feeds back the results of its operation to the smart device, which then sends the feedback to the server.

[1252] 7. Means of providing feedback to users

[1253] The server returns the feedback results to the smart device, which then notifies the user of the results using voice or other notification methods, which are adjusted based on the user's emotions.

[1254] Program processing explanation

[1255] Hardware and software used

[1256] Hardware: Smart device (e.g. smartphone, microphone, speaker, internet connection)

[1257] Software: Speech recognition module (Google Speech-to-Text API), emotion recognition engine (Affectiva SDK), generative AI (OpenAI's GPT model)

[1258] The server includes a means for inputting voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal home appliance operation commands and content suggestions based on the user's instructions, a means including an emotion engine for recognizing the user's emotions based on the analysis of the voice instructions, a means for sending the generated operation commands to the relevant home appliances, a means for feeding back the operation results of the home appliances, a means for notifying the user of the feedback results, and a means for providing optimal content to the user. This enables the user to not only control home appliances with a single voice instruction, but also to receive optimal content according to their emotions and circumstances at the time.

[1259] Specific examples

[1260] For example, if a user says, "Show me an uplifting video," the speech recognition module converts the speech into text data. This text data is analyzed by the emotion engine, which recognizes the emotion "I'm feeling a little down." The generative AI then uses this information to suggest an "uplifting video." This allows the user to receive appropriate content.

[1261] Prompt Sentence Examples

[1262] A user says, "Show me an uplifting video" and their emotional state is "I'm feeling a bit down." Suggest the best content.

[1263] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1264] Step 1:

[1265] The user inputs voice instructions into the smart device, which are captured by the device's microphone and sent to the smart device as voice data.

[1266] Step 2:

[1267] The smart device's voice recognition module (e.g., Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is the user's voice data, and the output is the analysis result, such as "Show me an uplifting video."

[1268] Step 3:

[1269] The text data is sent to an emotion recognition engine (e.g., Affectiva SDK), which takes the text data sent from the speech recognition module as input and analyzes it to output the user's emotional state (e.g., "I'm feeling a little depressed").

[1270] Step 4:

[1271] The smart device sends text data and emotion data to the server. The input is the text data and emotion data from the emotion recognition engine, which is then sent to the server.

[1272] Step 5:

[1273] The server's generative AI (e.g., OpenAI's GPT model) analyzes text data and emotional data and generates optimal content suggestions based on the user's intent. In this case, the input is the text data "Show me an uplifting video" and the emotional data "I'm feeling a little down," and the output is a suggestion for an "uplifting video."

[1274] Step 6:

[1275] The generated content proposals are sent from the server to the smart device. As input, the proposed content data is sent from the server to the smart device, and as output, the smart device prepares to display the content playback screen to the user.

[1276] Step 7:

[1277] The smart device presents the suggested content to the user. The input is the content data sent from the server, and the output is the content played back to the user.

[1278] Step 8:

[1279] After the user has finished viewing the content, the results are sent from the smart device to the server as feedback. The input is the user's operations and viewing results, and the output is the feedback data sent to the server.

[1280] Step 9:

[1281] The server analyzes the feedback data and uses it to further optimize future content suggestions and home appliance operation. The input is feedback data sent from smart devices, and the output is data that will be reflected in future suggestions.

[1282] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1283] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1284] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1285] [Fourth embodiment]

[1286] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1287] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1288] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1289] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1290] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1291] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1292] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1293] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1294] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1295] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1296] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1297] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1298] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1299] The present invention relates to a smart home system that integrates and manages home appliances based on user voice commands. A specific embodiment of the present invention will be described below. First, the overall flow of the system and the role of each component will be described, followed by a description of specific program processing.

[1300] Overall system configuration

[1301] 1. A means for the user to input voice commands:

[1302] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[1303] 2. Means for analyzing voice instructions and converting them into text data:

[1304] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[1305] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[1306] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[1307] 4. A method for sending the generated operation command to the corresponding home appliance:

[1308] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[1309] 5. Means of feedback on the operation results of home appliances:

[1310] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[1311] 6. Means of notifying the user of the feedback results:

[1312] The server sends the feedback results back to the Hub, which then notifies the user of the results by voice or other notification methods.

[1313] Program processing

[1314] Speech Recognition and Analysis

[1315] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[1316] Generate and send instructions

[1317] The converted text data is sent to the server, where the generative AI module analyzes the text. It accurately understands the user's intention and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[1318] Home appliance control and feedback

[1319] The appliance performs the operation based on the received command. When the appliance completes the operation, it sends the result back to the Hub. For example, to notify the Hub that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent.

[1320] User Notification

[1321] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is generated.

[1322] Specific examples

[1323] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[1324] Audio prompts

[1325] The user tells the Hub, "Set the air conditioner to 20 degrees."

[1326] Speech Recognition and Analysis

[1327] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[1328] Generate and send instructions

[1329] The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[1330] Home appliance control and feedback

[1331] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[1332] User Notification

[1333] The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub, which notifies the user that the air conditioner has been set to 20 degrees.

[1334] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command.

[1335] The processing flow will be explained below.

[1336] Step 1:

[1337] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[1338] Step 2:

[1339] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[1340] Step 3:

[1341] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[1342] Step 4:

[1343] The terminal (Hub) sends the text data received from the voice recognition module to the server.

[1344] Step 5:

[1345] The server receives the text data and requests processing from the generative AI module. The generative AI module analyzes the text data and generates the optimal operation command. Specifically, it generates the command "TURN_OFF LIGHT LIVING_ROOM."

[1346] Step 6:

[1347] The server sends the generated operation command to the lighting in the living room.

[1348] Step 7:

[1349] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the light.

[1350] Step 8:

[1351] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the Hub.

[1352] Step 9:

[1353] The terminal (Hub) receives the feedback message and sends it to the server.

[1354] Step 10:

[1355] The server verifies the feedback message and sends a confirmation message to the Hub.

[1356] Step 11:

[1357] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice that "The living room lights have been turned off."

[1358] The above is the specific procedure for turning off the living room lights by voice command from the user. This series of steps allows the user to operate home appliances simply and intuitively.

[1359] Example 1

[1360] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1361] In modern smart home systems, users must use separate remote controls and applications to operate multiple home appliances individually. This complex operation is burdensome for users and inconvenient. Furthermore, even when operating using voice commands, the accuracy of voice recognition and the transmission of commands to the home appliances can be unstable, resulting in a lack of reliability. Therefore, the present invention aims to comprehensively manage home appliances based on user voice commands, thereby improving ease of operation and reliability.

[1362] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1363] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative model for generating optimal home appliance operation commands based on the user instruction; means for transmitting the generated operation commands to the corresponding devices; means for providing feedback on the operation results of the devices; means for notifying the user of the feedback results; and means for analyzing the user's intention, generating commands using the generative model, transmitting the commands to the corresponding devices, and notifying the results. This allows the user to easily operate multiple devices with a single voice instruction and receive more reliable notifications.

[1364] A "user" is an individual or end user who utilizes the system to input voice instructions and operate a home appliance.

[1365] "Voice instructions" are operational instructions spoken by the user to the system, and refer to voice data captured through a microphone.

[1366] "Input means" refers to components including a microphone and its associated hardware and software that a user uses to input voice.

[1367] "Means for parsing and converting to text data" refers to the process and functionality of converting voice instructions into text using a voice recognition module and associated algorithms.

[1368] A "generative model" is a system that uses a generative AI model and refers to an algorithm that generates optimal home appliance operation commands based on user text data.

[1369] An "operation command" refers to a specific instruction generated to operate a home appliance or other device. An example would be "TURN_OFF LIGHT LIVING_ROOM."

[1370] "Applicable devices" refers to home appliances and other electronic devices that are controlled by voice instructions or operational commands, such as air conditioners, lighting, and televisions.

[1371] The "means for transmitting" refers to a system configuration including communication means and protocols for transmitting the generated operation command to the corresponding device.

[1372] "Feedback means" refers to a means for reporting the results of device operation to the system and returning that information to the user.

[1373] "Means of notification" refers to means such as audio output or display that the system uses to communicate operation results and other information to the user.

[1374] The present invention relates to a smart home system that can manage home appliances in an integrated manner based on user voice commands. This system is designed to allow users to simultaneously control multiple home appliances through voice commands by combining voice recognition technology and generative AI models. A specific embodiment of this system and its program processing are described below.

[1375] Overall system configuration

[1376] This smart home system mainly consists of the following components:

[1377] 1. Voice input method:

[1378] A smart home hub with a built-in microphone that allows the user to input voice commands.

[1379] An example of a prompt sentence is "Set the air conditioner to 20 degrees."

[1380] 2. Audio data analysis methods:

[1381] The voice data is converted into text data by a voice recognition module.

[1382] Specifically, it uses technologies such as the Google Cloud Speech-to-Text API.

[1383] 3. Generative AI Model:

[1384] Using generative AI (e.g., OpenAI's GPT-3) installed on the server, text data is analyzed and optimal home appliance operation commands are generated.

[1385] If the user instructs "Turn off the lights in the living room," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[1386] 4. Command sending method:

[1387] The server sends the generated home appliance operation command to the relevant device (e.g., air conditioner, lighting).

[1388] Communication protocols include Wi-Fi and Bluetooth.

[1389] 5. Feedback methods:

[1390] When the home appliance completes its operation, it feeds back the results to the Hub, which then reports them to the server.

[1391] For example, if an air conditioner changes the temperature setting to 20 degrees, a feedback message "TEMPERATURE_SET_SUCCESS" is sent to the Hub.

[1392] 6. User Notification Methods:

[1393] The server checks the feedback results and sends a final confirmation message to the Hub.

[1394] The Hub will notify the user with a voice message such as "The air conditioner has been set to 20 degrees."

[1395] Specific examples

[1396] As a concrete example, let's take a look at the process in detail when a user wants to set the air conditioner in the living room to 20 degrees:

[1397] Voice command: The user says to the Hub, "Set the air conditioner to 20 degrees."

[1398] Speech recognition: The Hub's microphone captures the voice and sends the voice data to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees."

[1399] Instruction generation: The server receives the text data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20."

[1400] Command transmission: The server sends the generated command to the air conditioner in the living room.

[1401] Feedback: The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[1402] User notification: The Hub sends feedback to the Server, and the Server returns a confirmation message to the Hub. The Hub notifies the user, "The air conditioner has been set to 20 degrees."

[1403] In this way, users can easily and reliably manage and operate home appliances using voice commands, significantly improving the convenience and reliability of smart homes.

[1404] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1405] Step 1:

[1406] The user inputs a voice command. The user speaks to the smart home hub, saying, "Set the air conditioner to 20 degrees." The input is voice data, which is captured by the hub's microphone. The voice data is temporarily stored in the hub's buffer memory.

[1407] Step 2:

[1408] The device (Hub) sends the captured voice data to the voice recognition module. The input is the saved voice data, which the voice recognition module analyzes and converts into text data such as "Set the air conditioner to 20 degrees." The output is text data. The voice recognition module uses the Google Cloud Speech-to-Text API.

[1409] Step 3:

[1410] The terminal (hub) sends text data to the server. The input is the converted text data, which the server receives. The server then sends the received text data to a generative AI (e.g., OpenAI's GPT-3) for analysis.

[1411] Step 4:

[1412] The server uses generative AI to analyze text data and generate optimal home appliance operation commands. The input is the text data "Set the air conditioner to 20 degrees," and the generative AI analyzes this to understand the user's intent. The output is the operation command "SET_TEMPERATURE 20."

[1413] Step 5:

[1414] The server sends the generated operation command to the corresponding device (the air conditioner in the living room). The input is the operation command "SET_TEMPERATURE 20", and the server sends this command to the air conditioner using the home appliance's communication protocol (e.g., Wi-Fi, Bluetooth). The output is the sent operation command.

[1415] Step 6:

[1416] The device (air conditioner) receives a command and changes the temperature setting to 20 degrees. The input is the operation command "SET_TEMPERATURE 20", and the air conditioner operates according to that command. The output is the result of the operation completion.

[1417] Step 7:

[1418] After the device (air conditioner) completes its operation, it sends a feedback message to the Hub. The input is the result of the operation completion, and the output is the feedback message "TEMPERATURE_SET_SUCCESS".

[1419] Step 8:

[1420] The terminal (Hub) sends a feedback message to the server. The input is the feedback message "TEMPERATURE_SET_SUCCESS" and sends it to the server. The output is a report to the server.

[1421] Step 9:

[1422] The server checks the feedback results and generates a final confirmation message, where the input is the feedback message and the output is the confirmation message.

[1423] Step 10:

[1424] The terminal (Hub) receives the confirmation message and notifies the user. The input is the confirmation message, and the output is a voice notification to the user: "The air conditioner has been set to 20 degrees."

[1425] (Application example 1)

[1426] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1427] Modern smart home systems operate each appliance based on user voice commands to achieve integrated management of home appliances. However, because these systems primarily focus on managing home appliances, they lack integration with external systems for specific service operations, such as food delivery. This means that when ordering food from a restaurant, users must use a separate application or go through multiple steps, which is inconvenient. Therefore, there is a need for a voice-command-based system that can seamlessly integrate with external systems.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1429] In this invention, the server includes a means for a user to input voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal data operation commands based on the user instructions, a means for transmitting the generated operation commands to a corresponding external system, a means for providing feedback on the operation results of the external system, and a means for notifying the user of the feedback results. This enables a user to efficiently use an external food delivery system using only voice instructions and consistently manage all processes from ordering to receiving.

[1430] A "user" is an entity that operates the system and inputs voice instructions.

[1431] A "voice instruction" is an instruction given by the user to the system using voice.

[1432] A "voice recognition module" is software or hardware for analyzing voice instructions and converting them into text data.

[1433] "Generative AI" is an artificial intelligence module that generates optimal data manipulation commands based on user instructions.

[1434] "Data manipulation commands" are instructions that the generative AI generates by analyzing the user's voice instructions, instructing an external system to perform specific actions.

[1435] "External systems" refer to external services and devices other than home appliances, including, for example, food delivery systems.

[1436] "Feedback" refers to the process of informing a user of the results of an external system's operation.

[1437] "Notification" refers to the act or means of communicating the feedback results to the user.

[1438] This invention relates to a smart food delivery system that delivers food based on user voice instructions. Specifically, it is a system that enables users to issue voice instructions, analyzes and processes those instructions, and connects them to a delivery service.

[1439] Overall system configuration

[1440] Entering voice commands

[1441] A user inputs voice commands into a smartphone app, such as "order a pizza," which are captured through the smart device's microphone.

[1442] Analysis of voice instructions

[1443] The captured voice data is analyzed through a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converted into text data, which is then sent to a server.

[1444] Generate commands

[1445] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data and understand the user's intent. The generative AI generates optimal data manipulation commands based on the user's intent. These commands are then sent to the food delivery system.

[1446] Sending Commands

[1447] The generated data manipulation commands are sent to an external delivery system (e.g., a restaurant ordering system) to order a particular food item.

[1448] Receiving Feedback

[1449] Once the order is accepted, the external system sends the result as feedback to the server, for example, a message such as "your order has been accepted."

[1450] User Notification

[1451] The server then sends the feedback results to the app, allowing users to check the order completion and progress via a notification on their smartphone screen or through a voice message.

[1452] Hardware and Software Configuration

[1453] 1. Hardware

[1454] Smartphone (any smart device with a microphone and internet connection)

[1455] 2. Software

[1456] Speech recognition API (e.g., Google Cloud Speech-to-Text API)

[1457] Generative AI (e.g. OpenAI GPT-4)

[1458] Cloud servers (Amazon Web Services, Google Cloud, etc.)

[1459] Specific examples

[1460] Audio prompts

[1461] A user says to an app on their smartphone, "Order a pizza."

[1462] Speech recognition and text conversion

[1463] The smartphone captures the audio and uses a speech recognition API to convert it into text data such as "order a pizza."

[1464] Instruction analysis and order generation

[1465] The server receives the converted text data and uses generative AI to generate an order command such as "order one pizza."

[1466] Submitting an Order

[1467] The server sends the generated order command to an external food delivery system.

[1468] Feedback and Notifications

[1469] The external delivery system accepts the order and sends feedback of the order acceptance to the server. The server notifies the app of the feedback result and informs the user that "the pizza order has been completed."

[1470] Prompt Sentence Examples

[1471] User dictates: "Order me a pizza"

[1472] Prompt for generative AI: "The user says they want to order pizza. Please suggest what would be the best order."

[1473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1474] Step 1:

[1475] A user inputs voice commands into a smartphone app. For example, the user says, "Order a pizza." The smartphone captures the voice and obtains the input as voice data.

[1476] Step 2:

[1477] The voice data is sent to the voice recognition module. The smartphone's voice recognition API (for example, Google Cloud Speech-to-Text API) analyzes the voice data and converts it into text data such as "Order a pizza." The text data is then output.

[1478] Step 3:

[1479] Text data is sent to a server. The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the received text data as input. The generative AI analyzes the instruction "order a pizza" and generates the optimal data manipulation command. In this case, a specific action command is generated: "Generate and send a pizza order." This is output as the generated command.

[1480] Step 4:

[1481] The server receives the generated data manipulation commands and sends them to an external food delivery system (e.g., a restaurant ordering system). The server uses the external system's API to input the order as a concrete order, e.g., sending an order for a pizza to a specific restaurant. The output is a feedback message that the order has been completed.

[1482] Step 5:

[1483] An external food delivery system receives the order and sends the result back to the server. For example, a feedback message such as "Order accepted" or "Order number 12345" is sent. The server receives this feedback message.

[1484] Step 6:

[1485] The server notifies the user's smartphone app of the feedback results it has received. The server takes the feedback message as input and sends a notification message to the smartphone app, such as "Your pizza order has been completed." The user's smartphone receives this message and displays it on the screen or as an audio notification. The output is a notification to the user.

[1486] Specific examples

[1487] Step 1:

[1488] A user says to their smartphone, "Order a pizza." Voice data is captured.

[1489] Step 2:

[1490] The voice data is converted into text data of "Order a pizza" by the Google Cloud Speech-to-Text API.

[1491] Step 3:

[1492] The text data is sent to the server, where it is analyzed by a generative AI model (OpenAI GPT-4) and generates a command to "generate and send a pizza order."

[1493] Step 4:

[1494] The server sends a "pizza order" to an external food delivery system, which receives the order as input.

[1495] Step 5:

[1496] The external delivery system accepts the order and sends a feedback message to the server saying "Order accepted."

[1497] Step 6:

[1498] The server sends a feedback message to the user saying, "Your pizza order is complete." The smartphone app receives this notification and displays it to the user.

[1499] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1500] The present invention combines a smart home system that integrates and manages home appliances based on user voice commands with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below. First, the overall flow of the system and the role of each component are described, followed by a description of specific program processing.

[1501] Overall system configuration

[1502] 1. A means for the user to input voice commands:

[1503] Users input voice commands by speaking to the smart home hub, which is equipped with a microphone to capture the user's voice.

[1504] 2. Means for analyzing voice instructions and converting them into text data:

[1505] Spoken commands are sent to and analyzed by a speech recognition module within the Hub, which converts the voice data into text data.

[1506] 3. Means including generative AI that generates optimal home appliance operation commands based on user instructions:

[1507] The converted text data is sent to a server equipped with a generative AI that verifies the user's instructions and generates optimal commands to operate home appliances.

[1508] 4. Means including an emotion engine for recognizing a user's emotion based on an analysis of the user's voice instructions:

[1509] The emotion engine uses the analysis of voice commands to recognize the user's emotions, which are then used as a reference for further analysis and command generation by the generative AI.

[1510] 5. Means for sending the generated operation command to the relevant home appliance:

[1511] The operation command generated by the server is sent to the corresponding home appliance, which then initiates a specific operation.

[1512] 6. Means of feedback on the operation results of home appliances:

[1513] When the appliance completes its operation, it sends the result of its operation back to the Hub, which then receives it and reports it to the server.

[1514] 7. Means of notifying the user of the feedback results:

[1515] The server sends the feedback results back to the Hub, which then notifies the user via voice or other notification methods. The notification method and content are adjusted depending on the user's emotions.

[1516] Program processing

[1517] Speech Recognition and Analysis

[1518] Spoken commands are captured by the Hub and sent to a speech recognition module, which analyzes the speech data and converts it into text.

[1519] Emotion recognition by emotion engine

[1520] The text data sent from the speech recognition module is analyzed by the emotion engine to recognize the user's emotion. This emotion data is used for subsequent processing.

[1521] Generate and send instructions

[1522] The converted text data and emotion data are sent to the server, where the generative AI module analyzes the data. It accurately grasps the user's intentions and emotions and generates the optimal home appliance operation command. This operation command is then sent to the appropriate home appliance. For example, if the user says, "Turn off the living room light," the generated command will be "TURN_OFF LIGHT LIVING_ROOM."

[1523] Home appliance control and feedback

[1524] The appliance performs the operation based on the received command. When the appliance completes the operation, it feeds back the result to the Hub. For example, to notify that the living room light has been turned off, a feedback message such as "LIGHT_OFF_SUCCESS" is sent to the Hub.

[1525] User Notification

[1526] The Hub receives the feedback message and transmits it to the Server. The Server checks the feedback result and finally sends a confirmation message to the Hub. This confirmation message is transmitted to the user via the Hub. For example, a voice notification saying "The living room lights have been turned off" is played. Furthermore, the tone and details of the notification are adjusted based on the user's emotional data.

[1527] Specific examples

[1528] As a specific example, the process when the user wants to set the air conditioner in the living room to 20 degrees will be described.

[1529] Audio prompts

[1530] The user tells the Hub, "Set the air conditioner to 20 degrees."

[1531] Speech Recognition and Analysis

[1532] The Hub captures the voice and sends it to the speech recognition module, which converts the voice data into text data such as "Set the air conditioner to 20 degrees." This text data is sent to the emotion engine, which recognizes the user's emotion.

[1533] Generate and send instructions

[1534] The server receives the text data and emotion data, and the generative AI generates the optimal operation command, "SET_TEMPERATURE 20." The server then sends the generated command to the air conditioner.

[1535] Home appliance control and feedback

[1536] The air conditioner changes the temperature setting to 20 degrees and sends the result to the Hub as feedback such as "TEMPERATURE_SET_SUCCESS".

[1537] User Notification

[1538] The Hub sends feedback to the server, which then sends a confirmation message back to the Hub. The Hub then notifies the user, "The air conditioner has been set to 20 degrees." If the user is stressed, for example, the notification will be made in a gentler tone.

[1539] The above is a specific embodiment for carrying out the present invention. In this way, the user can easily manage multiple home appliances collectively with a single voice command, and the system can also respond flexibly based on the user's emotions.

[1540] The processing flow will be explained below.

[1541] Step 1:

[1542] The user speaks to the Smart Home Hub and says, "Turn off the living room lights."

[1543] Step 2:

[1544] The terminal (Hub) captures the user's voice with a microphone and obtains the voice data.

[1545] Step 3:

[1546] The terminal (Hub) sends the acquired voice data to the voice recognition module, which analyzes the voice data and converts it into text data such as "Turn off the lights in the living room."

[1547] Step 4:

[1548] The text data converted by the voice recognition module is sent to the emotion engine on the device (Hub). The emotion engine analyzes the text data and recognizes the user's emotion. In this case, it recognizes that the user is relaxed.

[1549] Step 5:

[1550] The terminal (Hub) sends the analysis results obtained from the voice recognition module and emotion engine to the server.

[1551] Step 6:

[1552] Based on the text data and emotion data received by the server, the generative AI module is requested to process the data. The generative AI module analyzes the user's intentions and emotions and generates the optimal operation command: "TURN_OFF LIGHT LIVING_ROOM."

[1553] Step 7:

[1554] The server sends the generated operation command to the terminal (living room light).

[1555] Step 8:

[1556] The terminal (living room light) analyzes the received operation command and performs the operation of turning off the living room light.

[1557] Step 9:

[1558] When the device (living room light) completes the operation, it sends a feedback message such as "LIGHT_OFF_SUCCESS" to the device (Hub).

[1559] Step 10:

[1560] The terminal (Hub) receives the feedback message and sends it to the server.

[1561] Step 11:

[1562] The server checks the feedback message and sends a confirmation message to the terminal (Hub).

[1563] Step 12:

[1564] The terminal (Hub) receives the confirmation message from the server and notifies the user by voice, "The living room lights have been turned off." Since the user is relaxed, the notification is made in a gentle tone.

[1565] The above is the specific procedure for turning off the living room lights in response to a user's voice command. By using the emotion engine, it is possible to respond flexibly according to the user's emotions.

[1566] Example 2

[1567] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1568] In conventional smart home systems, users typically operate home appliances by inputting voice commands, but these systems often lack sufficient flexibility to adapt to the user's emotional state. This can result in reduced user satisfaction and usability. Furthermore, because home appliances are controlled solely based on voice commands, there are limitations in the accuracy of analyzing the command content and the method of notifying the operation results. Therefore, an objective of the present invention is to improve user satisfaction by recognizing the user's emotions and operating and notifying home appliances based on those emotions.

[1569] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for a user to input a voice instruction, means for analyzing the voice instruction and converting it into text data, means including a generative artificial intelligence for generating an optimal home appliance operation command based on the user's instruction, means including an emotion analysis engine for recognizing the user's emotion based on the analysis result of the voice instruction, means for transmitting the generated operation command to the corresponding home appliance, means for feeding back the operation result of the home appliance, and means for notifying the user of the feedback result. This makes it possible to operate and notify the user of the home appliance according to the user's emotional state, thereby improving user satisfaction and usability.

[1570] "User" refers to any individual or entity that uses the System.

[1571] "Voice instructions" refer to instructions input by the user speaking to the system.

[1572] The term "means" refers to hardware or software components provided for performing a specific function or process.

[1573] "Speech recognition module" refers to a technical element for converting voice data into text data.

[1574] "Generative AI" refers to AI that automatically generates specific commands and solutions based on input data.

[1575] An "emotion analysis engine" refers to a technical element that determines a user's emotional state from input data.

[1576] An "operation command" refers to a specific instruction generated to control a home appliance.

[1577] "Home appliances" refers to electronic and electrical devices used in the home.

[1578] "Feedback" refers to the home appliance reporting the results and status of its actions to the system.

[1579] "Notification" refers to conveying feedback results or other information to the user.

[1580] The present invention is a smart home system that integrates and manages home appliances based on user voice commands, and further combines it with an emotion analysis engine that recognizes the user's emotions. In this section, specific embodiments for implementing the invention will be described.

[1581] Basic configuration

[1582] This system consists of the following main components:

[1583] 1. A means for the user to input voice commands: This is a device such as a smart home hub that has a built-in microphone.

[1584] 2. Means for analyzing voice instructions and converting them into text data: This is a voice recognition module within the Hub.

[1585] 3. Means including generative artificial intelligence that generates optimal home appliance operation commands based on user instructions: This applies to generative artificial intelligence installed on a server.

[1586] 4. Means including an emotion analysis engine that recognizes the user's emotions based on the analysis results of voice instructions: This corresponds to an emotion analysis engine installed in the server.

[1587] 5. Means for transmitting the generated operation command to the relevant home appliance: This is a function for transmitting a signal from the server to the home appliance.

[1588] 6. A means of feedback on the operation results of home appliances: This is a function that allows home appliances to send the operation results to the smart home hub.

[1589] 7. Means of notifying the user of the feedback results: The Hub will notify the user of the results by voice notification or other means.

[1590] Hardware and Software Specifications

[1591] Speech Recognition Module: Uses an external speech recognition service, for example the Google Speech API.

[1592] Sentiment analysis engine: For example, using an emotion recognition API such as IBM Watson.

[1593] Generative AI: Uses generative AI models such as OpenAI GPT-3.

[1594] Specific examples

[1595] Audio prompts

[1596] The user tells the Hub, "Set the air conditioner in the living room to 20 degrees."

[1597] Audio capture and analysis

[1598] The Smart Home Hub device uses a built-in microphone to capture the user's voice and transmits it to a voice recognition module, which converts the voice data into text data such as "Set the air conditioner in the living room to 20 degrees."

[1599] Emotion recognition by emotion engine

[1600] The text data sent from the device's voice recognition module is passed to the emotion analysis engine, which then recognizes the user's emotions based on this data. For example, it may determine that the user is relaxed.

[1601] Generating commands to operate home appliances

[1602] The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal commands to operate home appliances. For example, the command "SET_TEMPERATURE 20" is generated.

[1603] Sending commands to home appliances

[1604] The server sends the generated operation command to the air conditioner in the living room. The signal "SET_TEMPERATURE 20" is sent via the air conditioner's built-in WiFi module.

[1605] Home appliance behavior and feedback

[1606] The air conditioner in the living room changes the temperature setting based on the received command. When the air conditioner completes the setting, it sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[1607] Notifying the user of the results

[1608] The smart home hub receives the feedback message and passes it on to the server. The server then verifies the feedback and sends a notification back to the user. For example, a message like "The air conditioner has been set to 20 degrees" is generated. The tone and details of the notification are adjusted depending on the user's emotional data. The notification is sent via voice through the hub.

[1609] Prompt Sentence Examples

[1610] The user says, "Set the air conditioner in the living room to 20 degrees." The emotion engine determines that the user is in a relaxed state. Generate an appropriate command to operate the home appliances.

[1611] With the above configuration, this system efficiently manages home appliances based on the user's voice commands and also realizes flexible responses based on emotions, which is expected to improve user satisfaction and ease of use.

[1612] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1613] Step 1: User Enters Voice Command

[1614] Specific action: The user says to the Smart Home Hub, "Set the air conditioner in the living room to 20 degrees."

[1615] Input: User's voice command.

[1616] Output: Audio data captured by the microphone.

[1617] Step 2: Capture and analyze audio

[1618] How it works: The Smart Home Hub device uses its built-in microphone to capture the user's voice and save it as digital audio data.

[1619] Input: The captured audio data.

[1620] Output: Data transfer to the speech recognition module.

[1621] Step 3: Convert audio data to text

[1622] How it works: The voice recognition module analyzes the voice data and converts it into text data. The voice recognition technology used is Google Speech API.

[1623] Input: Audio digital data.

[1624] Output: Text data: "Set the air conditioner in the living room to 20 degrees."

[1625] Step 4: Emotion Recognition with the Emotion Engine

[1626] Specific operation: Text data sent from the device's voice recognition module is passed to the emotion analysis engine. The emotion analysis engine uses the text data to recognize the user's emotions and generate analysis results. An emotion recognition API such as IBM Watson is used.

[1627] Input: Text data from the speech recognition module.

[1628] Output: Data indicating the user's emotional state, such as whether they are relaxed.

[1629] Step 5: Generate commands to operate the appliances

[1630] How it works: The server receives text data from the voice recognition module and emotion data from the emotion analysis engine. The generative AI analyzes this data and generates optimal home appliance operation commands. OpenAI GPT-3 is used as the generative AI model.

[1631] Input: Text data and emotion data.

[1632] Output: Appliance operation command "SET_TEMPERATURE 20".

[1633] Step 6: Sending commands

[1634] Specific operation: The server sends the generated operation command to the relevant appliance. The WiFi module sends a signal of "SET_TEMPERATURE 20" to the air conditioner in the living room.

[1635] Input: Home appliance operation command.

[1636] Output: Operation command signal sent to the air conditioner.

[1637] Step 7: Appliance behavior and feedback

[1638] Specific operation: The air conditioner in the living room changes the temperature setting based on the received command. After the temperature is set to 20 degrees, the air conditioner sends a feedback message "TEMPERATURE_SET_SUCCESS" to the Smart Home Hub.

[1639] Input: Home appliance operation command.

[1640] Output: A feedback message indicating the result of the operation.

[1641] Step 8: Processing and communicating feedback

[1642] Specific operation: The smart home hub receives the feedback message and forwards it to the server. The server analyzes the feedback and generates a message to notify the user of the result. The result notification takes into account the user's emotional data, and sends a voice message to the user via the hub saying, for example, "The air conditioner has been set to 20 degrees."

[1643] Input: The feedback message.

[1644] Output: Final message that is displayed to the user.

[1645] (Application example 2)

[1646] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1647] Conventional smart home systems are limited to controlling home appliances based on user voice commands, and have the drawback of being unable to flexibly respond to the user's emotions or circumstances. Furthermore, there are no systems that can not only control home appliances but also provide the content desired by users, limiting the means to improve the user experience. Therefore, there is a need for a system that can optimally operate home appliances and suggest content based on the user's intentions and emotions.

[1648] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1649] In this invention, the server includes: means for a user to input a voice instruction; means for analyzing the voice instruction and converting it into text data; means including a generative AI that generates optimal home appliance operation commands based on the user's instructions; means including an emotion engine that recognizes the user's emotions based on the analysis of the voice instruction; means for transmitting the generated operation commands to the relevant home appliance; means for feeding back the operation results of the home appliance; means for notifying the user of the feedback results; means including a generative AI that proposes optimal content that matches the user's intentions based on the voice instruction and emotion data; and means for providing the relevant content to the user. This enables the user to not only control the home appliance with a single voice instruction, but also to receive content that is optimal for their emotions and situation at the time.

[1650] "Voice instructions" refer to commands or requests that a user issues to the system using voice.

[1651] "Speech recognition module" refers to a software or hardware component for analyzing and converting voice instructions from a user into text data.

[1652] "Text data" refers to character string data generated by analyzing a voice instruction.

[1653] "Generative AI" refers to an artificial intelligence system that generates optimal commands and suggestions based on user input and the situation.

[1654] "Emotion engine" refers to a software or hardware component that analyzes and recognizes emotions from a user's voice or text data.

[1655] "Home appliances" refers to electronic devices and electrical appliances used in the home.

[1656] An "operation command" refers to a specific command that instructs a home appliance or other device to perform an operation.

[1657] "Feedback" refers to reporting the results of an appliance's execution or the results of a system's operation to the user.

[1658] "Content" refers to information and entertainment provided to users, such as music, videos, and news.

[1659] "Content suggestion" refers to selecting and providing optimal content based on the user's intentions and emotions.

[1660] The present invention relates to a system for controlling home appliances based on a user's voice instructions and emotional data, and for providing optimal content. The specific configuration and operation of this system are described below.

[1661] Overall system configuration

[1662] 1. Voice command input method

[1663] A user inputs voice instructions by speaking into a smart device (e.g., a smartphone), which is equipped with a microphone and captures the user's voice.

[1664] 2. Means for analyzing voice instructions and converting them into text data

[1665] The captured audio is sent to a speech recognition module (e.g., Google Speech-to-Text API) on the device, which converts the audio data into text data.

[1666] 3. Emotion Recognition Method Using Emotion Engine

[1667] The converted text data is analyzed by an emotion engine (e.g., Affectiva SDK) to recognize the user's emotion. The emotion data is used for subsequent processing.

[1668] 4. How generative AI generates instructions

[1669] The text data and emotion data are sent to a server, where a generative AI (e.g., OpenAI's GPT model) analyzes the data. Based on the user's intentions and emotions, optimal home appliance operation commands and content suggestions are generated.

[1670] 5. Means for transmitting generated operation commands and content

[1671] The server transmits the generated operation command to the corresponding home appliance and further provides the content requested by the user.

[1672] 6. Feedback method for home appliance operation results

[1673] When the home appliance completes its operation, it feeds back the results of its operation to the smart device, which then sends the feedback to the server.

[1674] 7. Means of providing feedback to users

[1675] The server returns the feedback results to the smart device, which then notifies the user of the results using voice or other notification methods, which are adjusted based on the user's emotions.

[1676] Program processing explanation

[1677] Hardware and software used

[1678] Hardware: Smart device (e.g. smartphone, microphone, speaker, internet connection)

[1679] Software: Speech recognition module (Google Speech-to-Text API), emotion recognition engine (Affectiva SDK), generative AI (OpenAI's GPT model)

[1680] The server includes a means for inputting voice instructions, a means for analyzing the voice instructions and converting them into text data, a means including a generative AI for generating optimal home appliance operation commands and content suggestions based on the user's instructions, a means including an emotion engine for recognizing the user's emotions based on the analysis of the voice instructions, a means for sending the generated operation commands to the relevant home appliances, a means for feeding back the operation results of the home appliances, a means for notifying the user of the feedback results, and a means for providing optimal content to the user. This enables the user to not only control home appliances with a single voice instruction, but also to receive optimal content according to their emotions and circumstances at the time.

[1681] Specific examples

[1682] For example, if a user says, "Show me an uplifting video," the speech recognition module converts the speech into text data. This text data is analyzed by the emotion engine, which recognizes the emotion "I'm feeling a little down." The generative AI then uses this information to suggest an "uplifting video." This allows the user to receive appropriate content.

[1683] Prompt Sentence Examples

[1684] A user says, "Show me an uplifting video" and their emotional state is "I'm feeling a bit down." Suggest the best content.

[1685] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1686] Step 1:

[1687] The user inputs voice instructions into the smart device, which are captured by the device's microphone and sent to the smart device as voice data.

[1688] Step 2:

[1689] The smart device's voice recognition module (e.g., Google Speech-to-Text API) analyzes the voice data and converts it into text data. The input is the user's voice data, and the output is the analysis result, such as "Show me an uplifting video."

[1690] Step 3:

[1691] The text data is sent to an emotion recognition engine (e.g., Affectiva SDK), which takes the text data sent from the speech recognition module as input and analyzes it to output the user's emotional state (e.g., "I'm feeling a little depressed").

[1692] Step 4:

[1693] The smart device sends text data and emotion data to the server. The input is the text data and emotion data from the emotion recognition engine, which is then sent to the server.

[1694] Step 5:

[1695] The server's generative AI (e.g., OpenAI's GPT model) analyzes text data and emotional data and generates optimal content suggestions based on the user's intent. In this case, the input is the text data "Show me an uplifting video" and the emotional data "I'm feeling a little down," and the output is a suggestion for an "uplifting video."

[1696] Step 6:

[1697] The generated content proposals are sent from the server to the smart device. As input, the proposed content data is sent from the server to the smart device, and as output, the smart device prepares to display the content playback screen to the user.

[1698] Step 7:

[1699] The smart device presents the suggested content to the user. The input is the content data sent from the server, and the output is the content played back to the user.

[1700] Step 8:

[1701] After the user has finished viewing the content, the results are sent from the smart device to the server as feedback. The input is the user's operations and viewing results, and the output is the feedback data sent to the server.

[1702] Step 9:

[1703] The server analyzes the feedback data and uses it to further optimize future content suggestions and home appliance operation. The input is feedback data sent from smart devices, and the output is data that will be reflected in future suggestions.

[1704] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1705] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1706] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1707] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1708] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1709] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1710] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1711] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1712] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1713] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1714] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1715] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1716] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1717] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1718] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1719] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1720] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1721] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1722] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1723] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1724] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1725] The following is further disclosed regarding the above embodiment.

[1726] (Claim 1)

[1727] means for a user to input voice instructions;

[1728] means for analyzing and converting voice instructions into text data;

[1729] A means including a generative AI that generates optimal home appliance operation commands based on user instructions;

[1730] means for transmitting the generated operation command to the corresponding home appliance;

[1731] A means for providing feedback on the operation results of the home appliance;

[1732] A means of notifying users of feedback results

[1733] A system including:

[1734] (Claim 2)

[1735] 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding user intent.

[1736] (Claim 3)

[1737] 2. The system according to claim 1, further comprising means for controlling the operation of each home appliance based on the generated home appliance operation command.

[1738] "Example 1"

[1739] (Claim 1)

[1740] means for a user to input voice instructions;

[1741] means for analyzing and converting voice instructions into text data;

[1742] means including a generative model that generates optimal home appliance operation commands based on user instructions;

[1743] means for transmitting the generated operation command to the corresponding device;

[1744] A means for feeding back the results of the operation of the device;

[1745] a means for notifying the user of the feedback result;

[1746] A system that includes a means for analyzing a user's intention, generating commands using a generative model, sending the commands to the relevant device, and notifying the results.

[1747] (Claim 2)

[1748] 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding user intent.

[1749] (Claim 3)

[1750] 2. The system according to claim 1, further comprising means for controlling the operation of each device based on the generated device operation command.

[1751] "Application Example 1"

[1752] (Claim 1)

[1753] means for a user to input voice instructions;

[1754] means for analyzing and converting voice instructions into text data;

[1755] A means including a generative AI that generates optimal data manipulation commands based on user instructions;

[1756] means for transmitting the generated operation command to a corresponding external system;

[1757] A means for feeding back the operation results of the external system;

[1758] A means of notifying users of feedback results

[1759] A system including:

[1760] (Claim 2)

[1761] 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding user intent.

[1762] (Claim 3)

[1763] 10. The system of claim 1, further comprising means for controlling the operation of an external system based on the generated data manipulation commands.

[1764] "Example 2: Combining Emotion Engines"

[1765] (Claim 1)

[1766] means for a user to input voice instructions;

[1767] means for analyzing and converting voice instructions into text data;

[1768] means including a generative artificial intelligence that generates optimal home appliance operation commands based on user instructions;

[1769] means including an emotion analysis engine for recognizing a user's emotion based on an analysis result of the voice instruction;

[1770] means for transmitting the generated operation command to the corresponding home appliance;

[1771] A means for providing feedback on the operation results of the home appliance;

[1772] A means of notifying users of feedback results

[1773] A system including:

[1774] (Claim 2)

[1775] 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding user intent.

[1776] (Claim 3)

[1777] 2. The system according to claim 1, further comprising means for controlling the operation of each home appliance based on the generated home appliance operation command.

[1778] "Application example 2 when combining emotion engines"

[1779] (Claim 1)

[1780] means for a user to input voice instructions;

[1781] means for analyzing and converting voice instructions into text data;

[1782] A means including a generative AI that generates optimal home appliance operation commands based on user instructions;

[1783] means including an emotion engine for recognizing an emotion of a user based on an analysis result of a voice instruction;

[1784] means for transmitting the generated operation command to the corresponding home appliance;

[1785] A means for providing feedback on the operation results of the home appliance;

[1786] a means for notifying the user of the feedback result;

[1787] A means including a generative AI that suggests optimal content that matches the user's intentions based on voice instructions and emotional data;

[1788] means for providing the relevant content to the user;

[1789] A system including:

[1790] (Claim 2)

[1791] 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding user intent.

[1792] (Claim 3)

[1793] 2. The system according to claim 1, further comprising means for controlling the operation of each home appliance or providing content based on the generated home appliance operation command and content proposal. [Explanation of symbols]

[1794] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to input voice instructions; means for analyzing and converting voice instructions into text data; A means including a generative AI that generates optimal home appliance operation commands based on user instructions; means for transmitting the generated operation command to the corresponding home appliance; A means for providing feedback on the operation results of the home appliance; A means of notifying users of feedback results A system including:

2. 10. The system of claim 1, further comprising a voice recognition module for analyzing voice instructions and understanding the user's intent.

3. The system according to claim 1, further comprising means for controlling the operation of each home appliance based on the generated home appliance operation command.

Images