system

Abstract

A system is provided.SOLUTION: A system comprising: means for parsing a natural language instruction using a generative model; means for generating a control instruction for building equipment based on the parsed instruction; means for sending the generated control instruction to an API of the building equipment; means for monitoring a state of the building equipment; and means for providing feedback to a user.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] In modern building management, making the equipment in older buildings smarter requires a great deal of time and money, and system integration is difficult due to the different connection specifications of each piece of equipment. It is also difficult to manage efficiently with limited budgets and personnel, and there is a need to optimize energy consumption. To solve these issues, it is necessary to develop a system that can control and manage building equipment using natural language on a unified platform. [Means for solving the problem]

[0005] The present invention provides a system that uses a generative model to analyze natural language instructions and generates control instructions for building facilities based on the analysis results. This system includes a means for sending the generated control instructions to the building facilities' API and monitoring the facilities' status. It can also use sensors to detect malfunctions in building facilities and generate control instructions to improve energy efficiency. This enables efficient smart facility management and management, even in older buildings, with limited budgets and personnel.

[0006] A "generative model" is an algorithm or program that analyzes given natural language instructions, understands their content, and converts them into appropriate control instructions.

[0007] A "natural language instruction" is an operation or request that a user makes to building facilities in normal language, such as "Turn on the air conditioning in the conference room."

[0008] "Building facilities" refers to various facilities and equipment installed within a building, including, for example, air conditioning, elevators, lighting, etc.

[0009] "Control instructions" are commands or instructions for performing specific operations on building facilities, generated based on analyzed natural language instructions.

[0010] An "API" is an interface that allows building facilities and other systems to communicate with each other, and is a standardized means for software to work together.

[0011] A "sensor" is a device that detects the state of building facilities and environmental conditions, collecting data such as temperature, humidity, and operating status.

[0012] "Feedback" is information that informs users of the current status of building facilities and the results of operations, and may be provided in natural language. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention relates to a control system using natural language instructions in building facility management. A specific embodiment of this system will be described below.

[0035] This system is designed for efficient and smart building management, and allows users to issue instructions to building facilities in natural language. The system is mainly composed of three elements: a server, a terminal, and a user.

[0036] Server Roles

[0037] The server has the central function of analyzing received natural language instructions and generating control instructions for building facilities. It uses a generative model to analyze and interpret the natural language instructions received from the user. It then generates specific control instructions for the building facilities' APIs based on the interpreted instructions. In addition, the server monitors the status of the building facilities and provides feedback as needed.

[0038] For example, if a user instructs the server to "turn on the air conditioning in the conference room," the server analyzes the instruction, generates a control command to turn on the air conditioning, and sends this control command to the API of the air conditioning equipment to turn on the air conditioning.

[0039] Device Role

[0040] The terminal acts as a user interface, receiving natural language instructions from the user and sending them to the server, and also receiving feedback from the server and providing it to the user.

[0041] For example, if a user types "Turn on the air conditioning in the conference room" into a terminal, the command is sent to the server. When feedback is returned from the server, the terminal displays it to the user. The feedback is displayed as a message such as "The air conditioning has been turned on."

[0042] User Roles

[0043] The user is the entity that controls and manages the building facilities. The user inputs natural language instructions into the terminal and checks the operating status of the building facilities through feedback from the terminal.

[0044] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user can then confirm that the air conditioning has been turned on through feedback from the server.

[0045] Thus, the present invention provides a system for analyzing natural language instructions and controlling and managing building facilities. This system allows building managers and users to operate building facilities efficiently and easily. It also contributes to environmental protection by realizing control that improves the energy efficiency of buildings. Specific program processing steps will be described in detail as necessary.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0049] Step 2:

[0050] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0051] Step 3:

[0052] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0053] Step 4:

[0054] Based on the analysis results, the server generates control commands for the building's facilities, such as API commands to turn on the air conditioning equipment.

[0055] Step 5:

[0056] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0057] Step 6:

[0058] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0059] Step 7:

[0060] Based on the results of the check, the server generates a feedback message, such as "The air conditioning has been turned on."

[0061] Step 8:

[0062] The server sends the generated feedback message to the terminal.

[0063] Step 9:

[0064] The terminal receives the feedback message from the server and displays it to the user, who can then confirm through the terminal that the instruction has been executed correctly.

[0065] Example 1

[0066] 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."

[0067] Building facility management is complex and time-consuming, and is extremely inefficient, especially when there are many pieces of equipment, as each piece must be controlled individually. There is a need to solve this problem, improve the efficiency of building management, and further increase energy efficiency. Another challenge is to provide an interface that allows users to operate intuitively.

[0068] 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.

[0069] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, and means for transmitting the generated control instructions to the API of the building facilities, which enables users to intuitively control building facilities using natural language, thereby improving the efficiency of building management and energy efficiency.

[0070] "Natural language instructions" is an input format that allows a user to use ordinary language to perform operations or give instructions to a system.

[0071] A "generative AI model" is an algorithm automatically generated based on collected data, and is a machine learning model for analyzing and generating natural language.

[0072] "Analysis" refers to the process of understanding received information or data and analyzing its meaning and structure.

[0073] "Control instructions" refers to specific commands and instructions for operating and managing building facilities.

[0074] "API" is an abbreviation for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[0075] "Building facilities" refers to all equipment and systems used within a building (e.g., air conditioning, lighting, elevators, etc.).

[0076] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user interacts with the system.

[0077] A "feedback message" is a message that the system uses to return operation results and status information to the user.

[0078] "Condition monitoring" is the process of monitoring the current state of building facilities in real time and detecting abnormalities or malfunctions.

[0079] A "sensor" is a device that detects physical conditions and acquires them as data.

[0080] "Energy efficiency" refers to the degree to which equipment and systems minimize the waste of energy they use and function efficiently.

[0081] This invention relates to a control system that uses natural language instructions in building facility management. A specific embodiment of this system will be described below. The main components are a server, a terminal, and a user.

[0082] Server embodiment

[0083] The server plays a central role in analyzing natural language instructions received from users and generating control instructions for building facilities. Specifically, it performs the following processes:

[0084] 1. The server parses the natural language instructions using a generative AI model (e.g., OpenAI's GPT-4). This model uses natural language processing techniques to interpret the user's input and understand their intent.

[0085] 2. The server generates specific control instructions for the APIs of the building facilities (e.g., air conditioning, lighting systems) based on the analyzed instructions. This generation is done using a program that constructs appropriate API calls based on the analysis results.

[0086] 3. The server sends the generated control command to the API of the building equipment. For example, it turns on the air conditioning by sending an HTTP request to the API endpoint of the air conditioning system.

[0087] 4. The server monitors the status of the building facilities and generates feedback messages as needed. It receives responses from the building facilities and generates user-friendly feedback messages (e.g., "The air conditioning has been turned on").

[0088] Terminal embodiment

[0089] The terminal functions as a user interface, receiving natural language instructions from the user and transmitting them to the server, and is also responsible for providing feedback from the server to the user.

[0090] 1. The user enters a natural language command using the device interface, for example, "Turn on the air conditioning in the conference room" using a smartphone, tablet PC, or PC.

[0091] 2. The terminal sends this instruction to the server using a communication protocol such as an HTTP POST request.

[0092] 3. When the server sends a feedback message, the device receives it and displays it to the user, for example, a message saying "The air conditioning has been turned on."

[0093] User's embodiment

[0094] The user is the entity that controls and manages the building equipment. They input natural language instructions into the terminal and check the operating status of the building equipment through feedback from the terminal.

[0095] Specifically, the user inputs "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user then confirms that the air conditioning has been turned on through a feedback message displayed on the terminal.

[0096] Examples of concrete examples and prompts

[0097] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters the following into the terminal:

[0098] Example prompt sentence:

[0099] "Turn on the air conditioning in the conference room."

[0100] The server receives this instruction, analyzes it using a generative AI model, and generates and executes an API call to "turn on the air conditioning." As a result, the air conditioning turns on and a feedback message such as "The air conditioning has been turned on" is displayed to the user on their device.

[0101] This concludes the detailed description of the preferred embodiment of the present invention, which allows users to control building equipment in an efficient and intuitive manner, while also improving the energy efficiency of buildings.

[0102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0103] Step 1: The user enters natural language instructions into the terminal.

[0104] The user inputs a natural language instruction into the terminal interface, such as "Turn on the air conditioning in the conference room." The input is in text format, and the terminal proceeds to the next step in that format. This input starts the system's processing.

[0105] Step 2: The device sends a natural language instruction to the server

[0106] The terminal sends the natural language instructions entered by the user to the server. Specifically, it uses a communication protocol such as an HTTP POST request to send the entered natural language instructions to the server as a payload. The input of this step is the user's instructions, and the output is an HTTP request to the server.

[0107] Step 3: The server receives and parses the natural language instructions

[0108] The server receives natural language instructions sent from the device. Based on the received data, it analyzes the instructions using a generative AI model (e.g., OpenAI's GPT-4). Specifically, it inputs the instructions into the model and extracts the resulting analysis data. The input for this step is the natural language instructions from the device, and the output is the analysis results.

[0109] Step 4: Server generates control commands

[0110] The server generates a control command for the building equipment based on the analyzed instructions. For example, based on the analysis result "Turn on the air conditioning in the conference room," it creates a specific command (e.g., an HTTP request) to send to the air conditioning system's API. The input to this step is the analysis result, and the output is the control command.

[0111] Step 5: The server sends the control command to the building equipment API

[0112] The server sends the generated control command to the building equipment's API. Specifically, it performs the operation of turning on the air conditioning by sending the generated HTTP request to the air conditioning system's API endpoint. The input to this step is the control command, and the output is an API request to the building equipment.

[0113] Step 6: The server receives feedback from the building equipment

[0114] The building equipment executes the control command from the server and feeds back the results to the server. The server receives this feedback and checks the processing results. For example, it receives feedback that "the air conditioning was successfully turned on." The input of this step is the feedback from the building equipment, and the output is the feedback data.

[0115] Step 7: Server generates feedback message

[0116] Based on the received feedback, the server generates a feedback message to inform the user. Specifically, it creates a message saying "The air conditioning has been turned on." The input of this step is the feedback data, and the output is the feedback message.

[0117] Step 8: The server sends a feedback message to the device

[0118] The server sends the generated feedback message to the terminal. The message is sent using an HTTP POST request, etc. The input of this step is the feedback message, and the output is an HTTP request to the terminal.

[0119] Step 9: The device displays a feedback message to the user

[0120] The terminal receives the feedback message sent from the server and displays it to the user. For example, the terminal screen displays "The air conditioning has been turned on." The input of this step is the feedback message from the server, and the output is the message displayed on the user interface.

[0121] The above is the specific processing flow of this system.

[0122] (Application example 1)

[0123] 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."

[0124] Conventional building facility management systems require manual control of facilities, requiring a great deal of time and effort. Furthermore, in brick-and-mortar stores, facilities need to be managed and controlled quickly and flexibly to improve customer comfort, but conventional systems have difficulty meeting this requirement. Furthermore, it has been difficult to centrally grasp the status of multiple facilities and control them efficiently. For this reason, there is a demand for a system that can control facilities with simple instructions in natural language and that can be operated instantly using smart devices.

[0125] 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.

[0126] In this invention, the server includes a means for analyzing natural language instructions using a generative model, a means for generating control instructions for building facilities based on the analyzed instructions, and a means for transmitting the generated control instructions to the API of the building facilities. This makes it possible to monitor the status of the building facilities and provide feedback to users. Furthermore, smart devices can be used to flexibly control facilities in physical stores, thereby improving customer comfort in the stores.

[0127] A "generative model" is an artificial intelligence model that analyzes a user's natural language instructions and generates appropriate control instructions.

[0128] "Natural language instructions" are instructions that users input in the same way as in everyday conversation, and are commands for controlling the facilities of buildings and stores.

[0129] "Building facilities" refers to various controlled objects within a building or store, such as air conditioning, lighting, and music.

[0130] "API" stands for Application Programming Interface, and refers to an interface that allows data to be exchanged between different software programs.

[0131] A "smart device" is a terminal with advanced functions that can connect to the Internet, such as a smartphone or smart glasses.

[0132] "Feedback" is the process of providing information about the execution results and current equipment status in response to instructions entered by the user.

[0133] A "brick and mortar store" is a store that exists in a physical location and that customers can visit in person.

[0134] "Customer comfort" means the degree of comfort felt by customers in a physical store due to the control of the equipment.

[0135] The present invention is a system for efficiently and comfortably managing facilities in a physical store. Specific embodiments of the system are described below.

[0136] Server Roles

[0137] The server has the central function of analyzing natural language instructions using a generative model and generating control instructions for store equipment. When a user inputs natural language instructions into a smart device (such as a smartphone or smart glasses), the instructions are sent to the server. The server then analyzes the natural language instructions using a generative AI model and converts them into appropriate control instructions. These control instructions are used to control store equipment such as lighting, air conditioning, and music. The server then sends these control instructions to the store equipment's API to manage the equipment's operation.

[0138] Device Role

[0139] The terminal functions as a user interface, receiving natural language instructions from the user and sending them to the server. It also provides feedback returned from the server to the user. For example, if a store manager types "It's 10 o'clock, so turn on the lights" into his smartphone, the instruction is sent directly to the server. When the server returns feedback saying "The lights are on," the content is displayed on the terminal, allowing the user to check the status of the equipment.

[0140] User Roles

[0141] Users are the entities that control and manage store equipment. They use smart devices to input natural language commands and check the equipment's operating status through feedback from the terminal. This allows for easy and quick equipment management.

[0142] Examples and prompts

[0143] For example, if a store manager inputs an instruction into the smart glasses, such as "We've seen an increase in customers. Please turn up the volume of the music in the store," the server analyzes this instruction and generates a control command to turn up the music volume. This control command is then sent to the API of the store's music equipment, which turns up the music volume. The result is then returned to the user as feedback, such as "The music volume has been turned up."

[0144] Thus, this invention is a system that uses smart devices to analyze natural language instructions and quickly and efficiently control equipment in a physical store. Specific hardware used includes smartphones and smart glasses, and software uses a generative AI model (e.g., OpenAI's API). An HTTP server is used for communication. This allows for easy operation in natural language and rapid equipment control.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] A user inputs natural language instructions into a smart device.

[0148] Input: A user types the natural language instruction "It's 10 o'clock, turn on the lights" into their smartphone.

[0149] What happens: A user enters natural language instructions using the voice or text input features of their smartphone.

[0150] Step 2:

[0151] The terminal sends a natural language instruction to the server.

[0152] Input: Natural language instructions entered into a smart device.

[0153] Output: Natural language instructions are sent to the server.

[0154] Specific operation: The terminal converts the input natural language instructions into packets and sends an HTTP request to the server.

[0155] Step 3:

[0156] The server uses a generative AI model to parse the natural language instructions.

[0157] Input: Natural language instruction data sent from the terminal.

[0158] Output: Parsed instructions (control commands).

[0159] Specific operation: The server calls a generative AI model (e.g., OpenAI API) to analyze natural language instructions and converts the instruction "It's 10 o'clock, so turn on the lights" into the control command "Turn on the lights."

[0160] Step 4:

[0161] The server generates control instructions for the building equipment based on the analyzed instructions.

[0162] Input: The analysis result obtained from the generative AI model (the control command "turn on the lights").

[0163] Output: Specific control instructions to send to the building equipment API.

[0164] Specific action: The server converts the control command into a format acceptable to the store equipment's API and prepares a specific API call to turn on the light.

[0165] Step 5:

[0166] The server sends the generated control instructions to the building equipment's API.

[0167] Input: API call for specific control instructions.

[0168] Output: Light fixture turns on.

[0169] Specific operation: The server sends the prepared control instructions as an HTTP request, calls the building equipment API, and turns on the lights.

[0170] Step 6:

[0171] It monitors the status of building facilities and sends feedback to the server.

[0172] Input: The operational state of the building equipment (lights turned on).

[0173] Output: Feedback information (confirmation that the light is on).

[0174] Specific operation: After the lighting equipment is turned on, the sensor detects its status and returns the information to the server via API.

[0175] Step 7:

[0176] The server sends feedback information to the terminal.

[0177] Input: Feedback information (confirmation that the light is on).

[0178] Output: Feedback information is sent to the terminal.

[0179] Specific operation: The server packets the feedback information and sends it to the terminal using an HTTP request.

[0180] Step 8:

[0181] The terminal provides feedback information to the user.

[0182] Input: Feedback information sent by the server.

[0183] Output: The user checks the feedback information.

[0184] Specific behavior: The device displays feedback information on the display and notifies the user that "The lights are on."

[0185] 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.

[0186] This invention combines a control system that uses natural language instructions to streamline building facility management with an emotion engine that recognizes user emotions. This system, in particular, has the function of analyzing natural language instructions using a generative model and generating control instructions for building facilities. The system also transmits the generated control instructions to the building facilities' API, monitors the facility's status, and provides appropriate feedback to the user. Furthermore, by incorporating the emotion engine, it is possible to recognize user emotions and provide appropriate control instructions and feedback.

[0187] Server Roles

[0188] The server plays a central role, analyzing the received natural language instructions and generating control instructions for the building facilities. It also uses an emotion engine to analyze the user's emotions and generate appropriate control instructions based on those emotions. It also monitors the status of the building facilities and provides feedback as needed.

[0189] For example, if a user issues an impatient command such as "Turn on the air conditioning in the conference room," the server will use its emotion engine to recognize the user's impatience, generate a control command to quickly turn on the air conditioning, and then generate a feedback message such as "The air conditioning has been turned on immediately" to alleviate the user's impatience.

[0190] Device Role

[0191] The device receives natural language instructions from the user and sends them to the server. It also receives feedback from the server and displays it to the user. Voice and text data that the emotion engine uses to recognize the user's emotions are also acquired through the device and sent to the server.

[0192] For example, if a user types "Turn on the air conditioning in the conference room" into the device, the instruction is sent to the server. When the server returns feedback, the device displays it to the user. Based on the emotion recognition results, the feedback is adjusted to something like "The air conditioning was turned on quickly."

[0193] User Roles

[0194] The user is the entity that controls and manages the building facilities. They input natural language commands into the terminal and receive feedback from the terminal. The emotion engine also recognizes the user's emotions and provides optimal control commands and feedback accordingly.

[0195] For example, if a user expresses irritation when requesting that the air conditioning be turned on before a meeting begins, the system will recognize that emotion and respond quickly. If the air conditioning is turned on quickly, the system will display feedback to the user, such as "The air conditioning was turned on quickly," to alleviate the irritation.

[0196] In this way, by incorporating an emotion engine, the system recognizes the user's natural language instructions and emotions, and provides appropriate control and feedback for building equipment. This system enables building managers and users to operate building equipment more efficiently and in a user-centered manner. It can also contribute to improving energy efficiency and early detection of malfunctions. Specific program processing steps will be explained in detail as necessary.

[0197] The processing flow will be explained below.

[0198] Step 1:

[0199] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0200] Step 2:

[0201] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0202] Step 3:

[0203] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0204] Step 4:

[0205] The server uses an emotion engine to analyze the user's emotions from the natural language instructions sent, for example recognizing emotions such as irritation or joy from the tone of voice and sentences.

[0206] Step 5:

[0207] The server generates control commands for the building's facilities based on the analysis results. The results of the user's emotion recognition are also taken into account, so prompt responses and specific feedback are included. For example, if irritation is recognized, a quick response is required.

[0208] Step 6:

[0209] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0210] Step 7:

[0211] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0212] Step 8:

[0213] The server generates a feedback message based on the results, taking into account the user's emotions, such as "The air conditioning has been turned on quickly."

[0214] Step 9:

[0215] The server sends the generated feedback message to the terminal.

[0216] Step 10:

[0217] The terminal receives the feedback message from the server and displays it to the user, who can confirm through the terminal that the instruction was executed correctly. The content of the feedback message is adjusted according to the user's emotions.

[0218] Example 2

[0219] 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."

[0220] Efficient management is required for building facilities management, but conventional methods often fail to correctly understand user instructions and are unable to respond quickly. Furthermore, there is also the problem of a lack of appropriate feedback that takes into account the user's emotions, resulting in a decline in user satisfaction. In particular, a prompt and appropriate response is required for users who are feeling irritated or anxious, but such a response is difficult to achieve. Furthermore, early detection of building facility failures and improving energy efficiency have also been challenges.

[0221] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0222] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, means for transmitting the generated control instructions to the building facilities' API, means for analyzing a user's emotions when analyzing the natural language instructions, means for adjusting the control instructions and feedback based on the analyzed emotions, means for monitoring the status of the building facilities, and means for providing feedback to the user. This allows the user's instructions to be correctly understood, enabling prompt and appropriate responses, thereby improving user satisfaction. It also enables early detection of building facilities failures and improved energy efficiency.

[0223] A "generative AI model" is an artificial intelligence model that analyzes natural language and generates appropriate control instructions and responses based on the results.

[0224] "Natural language instructions" refer to instructions provided by a user in spoken or text format that are written in language that is intuitively understandable to humans.

[0225] A "Building Facilities API" is an application programming interface for programmatically controlling building facilities (e.g., air conditioning, lighting, elevators, etc.).

[0226] An "emotion engine" is a technology or algorithm for analyzing emotions or emotional states from user-provided voice or text input.

[0227] "Feedback" is a response that the system provides to the user, including reporting how the user's instructions were processed.

[0228] "Means for monitoring the status of building facilities" refers to sensors and monitoring systems for detecting the operating status of building facilities and whether or not they have malfunctioned.

[0229] "Control instructions" are specific instructions generated by the system to operate building equipment, so that the equipment operates as expected.

[0230] This invention combines a control system that uses natural language instructions to improve the efficiency of building facility management with an emotion engine that recognizes user emotions. Detailed embodiments are described below.

[0231] Server Roles

[0232] The server is the central controller of the system. It first receives the natural language instructions sent by the device and analyzes them using a generative AI model (e.g., a publicly available natural language processing model) to understand exactly what the user wants.

[0233] The server then uses an emotion engine (e.g., a cloud-based emotion recognition service) to analyze the user's emotions. Based on the emotion recognition results, the server adjusts the appropriateness of the generated control instructions and feedback messages. In this way, it is possible to respond according to the user's level of frustration or satisfaction.

[0234] The server generates specific building equipment control instructions based on the analysis results and sends them to the building equipment's API, for example, to operate the air conditioning system or lighting system. It also checks the execution results of the control instructions, generates appropriate feedback messages, and sends them to the terminal.

[0235] Device Role

[0236] The terminal functions as a user interface. The user can use the terminal to input instructions in natural language. The input is sent to the server for processing. Instructions can be accepted in a variety of formats, including voice input and text input.

[0237] The terminal receives feedback from the server and displays it to the user, for example, a feedback message such as "The air conditioning was turned on quickly" so that the user can be sure that their instruction was carried out correctly.

[0238] User Roles

[0239] The user is the entity that uses this system to control the building equipment. They input instructions in natural language into the terminal and operate the equipment. They also check feedback from the server and issue instructions again if necessary to manage the equipment status.

[0240] Specific examples

[0241] As a concrete example, consider the following scenario.

[0242] The user inputs "Turn on the air conditioning in the conference room" into the device. This command is sent from the device to the server. The server analyzes this command using a generative AI model and generates a control command to turn on the air conditioning.

[0243] At the same time, the emotion engine recognizes the user's frustration. The server determines that this frustration requires a quick response, generates a command to "quickly turn on the air conditioning" and sends it to the building equipment's API. After the air conditioning is turned on, the server generates a feedback message saying "The air conditioning has been turned on quickly" and sends it to the device. The user confirms this feedback on the device and understands that the command was processed appropriately.

[0244] Prompt Sentence Examples

[0245] User command: "Turn on the air conditioning in the conference room."

[0246] Context to analyze: A user issues a command to turn on the air conditioning in a conference room. If this command is accompanied by irritation, a quick response is required.

[0247] Emotion recognition result: Irritated

[0248] Generate control instructions: Quickly turn on air conditioning.

[0249] Feedback message: "Air conditioning turned on quickly"

[0250] In this way, the system of the present invention recognizes the user's natural language commands and emotions, and provides appropriate control and feedback for building facilities. This enables building managers and users to operate building facilities more efficiently and in a user-centered manner. It also contributes to improving energy efficiency and early detection of malfunctions.

[0251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0252] Step 1:

[0253] The user inputs a natural language command into the device, for example, "Turn on the air conditioning in the conference room," either by speaking or by typing it into the device.

[0254] Input: User's natural language instructions

[0255] Output: Voice or text input data to the device

[0256] Step 2:

[0257] The device receives the user's natural language instructions and transmits the data to the server using HTTP requests over the network.

[0258] Input: Voice or text input data

[0259] Output: HTTP request to the server

[0260] Step 3:

[0261] The server inputs the received natural language instructions into a generative AI model, which analyzes the instructions and identifies the specific action the user wants to take (e.g., turn on the air conditioning).

[0262] Input: HTTP request received by the server

[0263] Output: Parsed instructions

[0264] Step 4:

[0265] The server uses an emotion engine to analyze the emotion contained in the user's natural language instructions, and this process provides emotional information such as whether the user is annoyed.

[0266] Input: Natural language instruction data

[0267] Output: Sentiment analysis result (e.g., irritated)

[0268] Step 5:

[0269] The server generates appropriate building facility control instructions based on the analysis results. For example, if a user is frustrated, a control instruction is generated that calls for a quick response.

[0270] Input: Analyzed instructions and sentiment analysis results

[0271] Output: Generated control instructions

[0272] Step 6:

[0273] The server sends the generated control instructions to the API of the building equipment, for example, via an HTTP request via a REST API.

[0274] Input: Generated control instructions

[0275] Output: API request to building equipment

[0276] Step 7:

[0277] The server receives the response from the building equipment API and checks whether the control was successful. If the control was successful, the next step is to generate a feedback message.

[0278] Input: API response from building equipment

[0279] Output: Check the control results

[0280] Step 8:

[0281] The server generates an appropriate feedback message and sends it to the device, taking into account the sentiment analysis results, for example, generating a message such as "The air conditioning was quickly turned on."

[0282] Input: Control results and sentiment analysis results

[0283] Output: The generated feedback message

[0284] Step 9:

[0285] The terminal receives the feedback message from the server and displays it to the user, who can see that the instruction has been executed correctly.

[0286] Input: Feedback message from the server

[0287] Output: Display feedback to the user

[0288] Through the above processing steps, the user's natural language instructions are correctly analyzed, appropriate control instructions are generated, and building facilities are operated, resulting in the user receiving prompt and accurate feedback in accordance with their instructions.

[0289] (Application example 2)

[0290] 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."

[0291] Conventional facility management systems for buildings and brick-and-mortar stores control equipment based on users' natural language instructions, but do not take the user's emotions into consideration. This means that appropriate feedback is not provided to the user, resulting in frustration and inconvenience for the user. Furthermore, in brick-and-mortar stores, equipment control based on the emotions of users and store staff is required, but current systems lack such functionality. Furthermore, there is also room for improvement in terms of optimizing energy efficiency to achieve efficient equipment control.

[0292] 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.

[0293] In this invention, the server includes means for analyzing natural language instructions using a generative model, means for generating control instructions for building facilities based on the analyzed instructions, means for sending the generated control instructions to the building facilities' API, means for analyzing user emotions using an emotion engine and generating control instructions and feedback according to the emotions, and means for controlling various facilities (lighting, air conditioning, music, etc.) in the physical store. This enables quick and appropriate control of facilities and provision of feedback that takes user emotions into consideration, thereby improving user satisfaction and optimizing energy efficiency.

[0294] A "generative model" is an artificial intelligence technology that analyzes natural language instructions and generates appropriate control instructions based on their content.

[0295] "Natural language instructions" are commands or requests entered by the user in everyday language, and by analyzing these, instructions for operating various devices are extracted.

[0296] "Building facilities" refers to the various devices and systems installed within a building, including air conditioning, lighting, elevators, etc.

[0297] A "control instruction" is a command or instruction that causes building facilities or physical store equipment to perform a specific operation based on the analyzed natural language instruction.

[0298] "API" stands for Application Programming Interface, an interface for exchanging data and functions between software programs.

[0299] An "emotion engine" is a technology that analyzes emotions from a user's voice or text and generates appropriate feedback and control instructions based on those emotions.

[0300] "Feedback" refers to a response or result report from the system to an instruction from the user, and notifies the user whether the instruction was processed correctly.

[0301] "Brick and mortar store" refers to a physical commercial establishment or retail outlet, including lighting, air conditioning, music, and other amenities.

[0302] This invention provides a system that combines natural language instruction analysis and emotion recognition to improve the efficiency of facility management in buildings and brick-and-mortar stores. This system operates in three roles: server, terminal, and user.

[0303] Server Roles

[0304] The server plays a central role and has the following functions:

[0305] Function to analyze natural language instructions using generative models: Analyzes natural language instructions sent by the user and converts them into specific control commands. For example, if a user instructs the robot to "dim the lights in the store a little," the robot analyzes this instruction and generates a lighting control command.

[0306] Emotion analysis function using emotion engine: Recognizes emotions from the user's voice or text and generates appropriate control instructions and feedback based on those emotions. For example, if the emotion engine determines that the user is irritated, it will respond quickly and generate feedback such as "The lights have been dimmed immediately" to alleviate the user's irritation.

[0307] A function to send control instructions to the APIs of various facilities in buildings and physical stores: The generated control commands are sent to the APIs of the building facilities and physical store facilities, and the actual control is performed.

[0308] Function to monitor equipment status and provide feedback: Monitor the status of each piece of equipment, detect faults and provide feedback to the user.

[0309] Device Role

[0310] The device is responsible for receiving natural language instructions from the user and sending them to the server. Specifically:

[0311] A natural language instruction entered by the user is sent to the server.

[0312] Receives feedback from the server and displays it to the user.

[0313] Voice and text data for emotion recognition is collected and sent to a server.

[0314] For example, if the device is a smartphone, when the user inputs an instruction such as "Adjust the air conditioning in the store," the device sends this to the server and displays feedback from the server to the user, such as "The air conditioning has been adjusted."

[0315] User Roles

[0316] The user is the entity that operates the system, controlling and managing the facilities of the building or physical store. The user inputs instructions in natural language and receives feedback from the device. The emotion engine recognizes emotions and provides optimal feedback and control instructions.

[0317] For example, if a user says, "The music is too loud, please be quieter. I'm very tired," the server analyzes the instruction, generates a command to lower the music volume, and provides feedback such as, "The music volume has been lowered. We will provide you with a relaxing environment."

[0318] Hardware and software used

[0319] Hardware: Users use smartphones, tablets, or in-store interactive displays.

[0320] Software: Uses emotion recognition engines (e.g., Microsoft Azure Emotion API), natural language processing engines (e.g., OpenAI GPT-3).

[0321] Examples of concrete examples and prompts

[0322] To illustrate, consider the following scenario:

[0323] scenario

[0324] If the store is a little noisy and a customer says, "Please make the music quieter in the store, I'm very tired."

[0325] Prompt Sentence Examples

[0326] User Input: Please make the music quieter in the store, I'm so tired

[0327] Objective: Recognize the user's emotions, generate control instructions to lower the music volume, and provide appropriate feedback to the user.

[0328] This invention makes it possible to control equipment quickly and appropriately and provide feedback that takes into account the user's feelings, thereby improving user satisfaction and optimizing energy efficiency.

[0329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0330] Step 1:

[0331] A user enters natural language instructions into a terminal.

[0332] As a specific example, the user uses a smartphone to input instructions via voice or text, such as "Please turn down the music in the store; I'm very tired."

[0333] Input: User's natural language instructions (voice or text)

[0334] Output: Natural language instructions entered into the terminal

[0335] Step 2:

[0336] The terminal transmits the input natural language instruction to the server.

[0337] The terminal is responsible for receiving user instruction data and transmitting it to the server.

[0338] Input: Natural language instruction data entered into the terminal

[0339] Output: Natural language instructions sent to the server

[0340] Step 3:

[0341] The server analyzes the received natural language instructions using a generative model.

[0342] For the analysis, a generative AI model (e.g., OpenAI GPT-3) is used to analyze the user's instructions and generate specific control commands.

[0343] Input: Natural language instructions sent to the server

[0344] Output: Generated control command data

[0345] Step 4:

[0346] The server analyzes the user's emotions using an emotion engine.

[0347] Using natural language instruction data as input, an emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's emotions.

[0348] Input: Natural language instruction data

[0349] Output: Parsed emotion data

[0350] Step 5:

[0351] The server generates appropriate feedback based on the generated control commands and the analyzed emotion data.

[0352] Based on the analysis results, a feedback message is generated, such as "The music has been quickly quieted down to provide a relaxing environment."

[0353] Input: Generated control command data, analyzed emotion data

[0354] Output: The generated feedback message

[0355] Step 6:

[0356] The server sends control commands to the API of the building equipment or physical store equipment to execute the control.

[0357] For example, sending a command to a music system's API to turn down the volume.

[0358] Input: Generated control command data

[0359] Output: Control action taken (music volume is reduced)

[0360] Step 7:

[0361] The server transmits the generated feedback to the terminal.

[0362] The generated feedback is sent to the terminal to provide a feedback message to the user.

[0363] Input: The generated feedback message

[0364] Output: Feedback message sent to the terminal

[0365] Step 8:

[0366] The terminal displays the received feedback message to the user.

[0367] For example, a message could appear on a smartphone screen saying, "The music volume has been lowered to provide a relaxing environment."

[0368] Input: Feedback message sent to the device

[0369] Output: The feedback message displayed to the user

[0370] 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.

[0371] 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.

[0372] 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.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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."

[0386] The present invention relates to a control system using natural language instructions in building facility management. A specific embodiment of this system will be described below.

[0387] This system is designed for efficient and smart building management, and allows users to issue instructions to building facilities in natural language. The system is mainly composed of three elements: a server, a terminal, and a user.

[0388] Server Roles

[0389] The server has the central function of analyzing received natural language instructions and generating control instructions for building facilities. It uses a generative model to analyze and interpret the natural language instructions received from the user. It then generates specific control instructions for the building facilities' APIs based on the interpreted instructions. In addition, the server monitors the status of the building facilities and provides feedback as needed.

[0390] For example, if a user instructs the server to "turn on the air conditioning in the conference room," the server analyzes the instruction, generates a control command to turn on the air conditioning, and sends this control command to the API of the air conditioning equipment to turn on the air conditioning.

[0391] Device Role

[0392] The terminal acts as a user interface, receiving natural language instructions from the user and sending them to the server, and also receiving feedback from the server and providing it to the user.

[0393] For example, if a user types "Turn on the air conditioning in the conference room" into a terminal, the command is sent to the server. When feedback is returned from the server, the terminal displays it to the user. The feedback is displayed as a message such as "The air conditioning has been turned on."

[0394] User Roles

[0395] The user is the entity that controls and manages the building facilities. The user inputs natural language instructions into the terminal and checks the operating status of the building facilities through feedback from the terminal.

[0396] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user can then confirm that the air conditioning has been turned on through feedback from the server.

[0397] Thus, the present invention provides a system for analyzing natural language instructions and controlling and managing building facilities. This system allows building managers and users to operate building facilities efficiently and easily. It also contributes to environmental protection by realizing control that improves the energy efficiency of buildings. Specific program processing steps will be described in detail as necessary.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0401] Step 2:

[0402] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0403] Step 3:

[0404] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0405] Step 4:

[0406] Based on the analysis results, the server generates control commands for the building's facilities, such as API commands to turn on the air conditioning equipment.

[0407] Step 5:

[0408] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0409] Step 6:

[0410] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0411] Step 7:

[0412] Based on the results of the check, the server generates a feedback message, such as "The air conditioning has been turned on."

[0413] Step 8:

[0414] The server sends the generated feedback message to the terminal.

[0415] Step 9:

[0416] The terminal receives the feedback message from the server and displays it to the user, who can then confirm through the terminal that the instruction has been executed correctly.

[0417] Example 1

[0418] 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."

[0419] Building facility management is complex and time-consuming, and is extremely inefficient, especially when there are many pieces of equipment, as each piece must be controlled individually. There is a need to solve this problem, improve the efficiency of building management, and further increase energy efficiency. Another challenge is to provide an interface that allows users to operate intuitively.

[0420] 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.

[0421] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, and means for transmitting the generated control instructions to the API of the building facilities, which enables users to intuitively control building facilities using natural language, thereby improving the efficiency of building management and energy efficiency.

[0422] "Natural language instructions" is an input format that allows a user to use ordinary language to perform operations or give instructions to a system.

[0423] A "generative AI model" is an algorithm automatically generated based on collected data, and is a machine learning model for analyzing and generating natural language.

[0424] "Analysis" refers to the process of understanding received information or data and analyzing its meaning and structure.

[0425] "Control instructions" refers to specific commands and instructions for operating and managing building facilities.

[0426] "API" is an abbreviation for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[0427] "Building facilities" refers to all equipment and systems used within a building (e.g., air conditioning, lighting, elevators, etc.).

[0428] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user interacts with the system.

[0429] A "feedback message" is a message that the system uses to return operation results and status information to the user.

[0430] "Condition monitoring" is the process of monitoring the current state of building facilities in real time and detecting abnormalities or malfunctions.

[0431] A "sensor" is a device that detects physical conditions and acquires them as data.

[0432] "Energy efficiency" refers to the degree to which equipment and systems minimize the waste of energy they use and function efficiently.

[0433] This invention relates to a control system that uses natural language instructions in building facility management. A specific embodiment of this system will be described below. The main components are a server, a terminal, and a user.

[0434] Server embodiment

[0435] The server plays a central role in analyzing natural language instructions received from users and generating control instructions for building facilities. Specifically, it performs the following processes:

[0436] 1. The server parses the natural language instructions using a generative AI model (e.g., OpenAI's GPT-4). This model uses natural language processing techniques to interpret the user's input and understand their intent.

[0437] 2. The server generates specific control instructions for the APIs of the building facilities (e.g., air conditioning, lighting systems) based on the analyzed instructions. This generation is done using a program that constructs appropriate API calls based on the analysis results.

[0438] 3. The server sends the generated control command to the API of the building equipment. For example, it turns on the air conditioning by sending an HTTP request to the API endpoint of the air conditioning system.

[0439] 4. The server monitors the status of the building facilities and generates feedback messages as needed. It receives responses from the building facilities and generates user-friendly feedback messages (e.g., "The air conditioning has been turned on").

[0440] Terminal embodiment

[0441] The terminal functions as a user interface, receiving natural language instructions from the user and transmitting them to the server, and is also responsible for providing feedback from the server to the user.

[0442] 1. The user enters a natural language command using the device interface, for example, "Turn on the air conditioning in the conference room" using a smartphone, tablet PC, or PC.

[0443] 2. The terminal sends this instruction to the server using a communication protocol such as an HTTP POST request.

[0444] 3. When the server sends a feedback message, the device receives it and displays it to the user, for example, a message saying "The air conditioning has been turned on."

[0445] User's embodiment

[0446] The user is the entity that controls and manages the building equipment. They input natural language instructions into the terminal and check the operating status of the building equipment through feedback from the terminal.

[0447] Specifically, the user inputs "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user then confirms that the air conditioning has been turned on through a feedback message displayed on the terminal.

[0448] Examples of concrete examples and prompts

[0449] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters the following into the terminal:

[0450] Example prompt sentence:

[0451] "Turn on the air conditioning in the conference room."

[0452] The server receives this instruction, analyzes it using a generative AI model, and generates and executes an API call to "turn on the air conditioning." As a result, the air conditioning turns on and a feedback message such as "The air conditioning has been turned on" is displayed to the user on their device.

[0453] This concludes the detailed description of the preferred embodiment of the present invention, which allows users to control building equipment in an efficient and intuitive manner, while also improving the energy efficiency of buildings.

[0454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0455] Step 1: The user enters natural language instructions into the terminal.

[0456] The user inputs a natural language instruction into the terminal interface, such as "Turn on the air conditioning in the conference room." The input is in text format, and the terminal proceeds to the next step in that format. This input starts the system's processing.

[0457] Step 2: The device sends a natural language instruction to the server

[0458] The terminal sends the natural language instructions entered by the user to the server. Specifically, it uses a communication protocol such as an HTTP POST request to send the entered natural language instructions to the server as a payload. The input of this step is the user's instructions, and the output is an HTTP request to the server.

[0459] Step 3: The server receives and parses the natural language instructions

[0460] The server receives natural language instructions sent from the device. Based on the received data, it analyzes the instructions using a generative AI model (e.g., OpenAI's GPT-4). Specifically, it inputs the instructions into the model and extracts the resulting analysis data. The input for this step is the natural language instructions from the device, and the output is the analysis results.

[0461] Step 4: Server generates control commands

[0462] The server generates a control command for the building equipment based on the analyzed instructions. For example, based on the analysis result "Turn on the air conditioning in the conference room," it creates a specific command (e.g., an HTTP request) to send to the air conditioning system's API. The input to this step is the analysis result, and the output is the control command.

[0463] Step 5: The server sends the control command to the building equipment API

[0464] The server sends the generated control command to the building equipment's API. Specifically, it performs the operation of turning on the air conditioning by sending the generated HTTP request to the air conditioning system's API endpoint. The input to this step is the control command, and the output is an API request to the building equipment.

[0465] Step 6: The server receives feedback from the building equipment

[0466] The building equipment executes the control command from the server and feeds back the results to the server. The server receives this feedback and checks the processing results. For example, it receives feedback that "the air conditioning was successfully turned on." The input of this step is the feedback from the building equipment, and the output is the feedback data.

[0467] Step 7: Server generates feedback message

[0468] Based on the received feedback, the server generates a feedback message to inform the user. Specifically, it creates a message saying "The air conditioning has been turned on." The input of this step is the feedback data, and the output is the feedback message.

[0469] Step 8: The server sends a feedback message to the device

[0470] The server sends the generated feedback message to the terminal. The message is sent using an HTTP POST request, etc. The input of this step is the feedback message, and the output is an HTTP request to the terminal.

[0471] Step 9: The device displays a feedback message to the user

[0472] The terminal receives the feedback message sent from the server and displays it to the user. For example, the terminal screen displays "The air conditioning has been turned on." The input of this step is the feedback message from the server, and the output is the message displayed on the user interface.

[0473] The above is the specific processing flow of this system.

[0474] (Application example 1)

[0475] 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."

[0476] Conventional building facility management systems require manual control of facilities, requiring a great deal of time and effort. Furthermore, in brick-and-mortar stores, facilities need to be managed and controlled quickly and flexibly to improve customer comfort, but conventional systems have difficulty meeting this requirement. Furthermore, it has been difficult to centrally grasp the status of multiple facilities and control them efficiently. For this reason, there is a demand for a system that can control facilities with simple instructions in natural language and that can be operated instantly using smart devices.

[0477] 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.

[0478] In this invention, the server includes a means for analyzing natural language instructions using a generative model, a means for generating control instructions for building facilities based on the analyzed instructions, and a means for transmitting the generated control instructions to the API of the building facilities. This makes it possible to monitor the status of the building facilities and provide feedback to users. Furthermore, smart devices can be used to flexibly control facilities in physical stores, thereby improving customer comfort in the stores.

[0479] A "generative model" is an artificial intelligence model that analyzes a user's natural language instructions and generates appropriate control instructions.

[0480] "Natural language instructions" are instructions that users input in the same way as in everyday conversation, and are commands for controlling the facilities of buildings and stores.

[0481] "Building facilities" refers to various controlled objects within a building or store, such as air conditioning, lighting, and music.

[0482] "API" stands for Application Programming Interface, and refers to an interface that allows data to be exchanged between different software programs.

[0483] A "smart device" is a terminal with advanced functions that can connect to the Internet, such as a smartphone or smart glasses.

[0484] "Feedback" is the process of providing information about the execution results and current equipment status in response to instructions entered by the user.

[0485] A "brick and mortar store" is a store that exists in a physical location and that customers can visit in person.

[0486] "Customer comfort" means the degree of comfort felt by customers in a physical store due to the control of the equipment.

[0487] The present invention is a system for efficiently and comfortably managing facilities in a physical store. Specific embodiments of the system are described below.

[0488] Server Roles

[0489] The server has the central function of analyzing natural language instructions using a generative model and generating control instructions for store equipment. When a user inputs natural language instructions into a smart device (such as a smartphone or smart glasses), the instructions are sent to the server. The server then analyzes the natural language instructions using a generative AI model and converts them into appropriate control instructions. These control instructions are used to control store equipment such as lighting, air conditioning, and music. The server then sends these control instructions to the store equipment's API to manage the equipment's operation.

[0490] Device Role

[0491] The terminal functions as a user interface, receiving natural language instructions from the user and sending them to the server. It also provides feedback returned from the server to the user. For example, if a store manager types "It's 10 o'clock, so turn on the lights" into his smartphone, the instruction is sent directly to the server. When the server returns feedback saying "The lights are on," the content is displayed on the terminal, allowing the user to check the status of the equipment.

[0492] User Roles

[0493] Users are the entities that control and manage store equipment. They use smart devices to input natural language commands and check the equipment's operating status through feedback from the terminal. This allows for easy and quick equipment management.

[0494] Examples and prompts

[0495] For example, if a store manager inputs an instruction into the smart glasses, such as "We've seen an increase in customers. Please turn up the volume of the music in the store," the server analyzes this instruction and generates a control command to turn up the music volume. This control command is then sent to the API of the store's music equipment, which turns up the music volume. The result is then returned to the user as feedback, such as "The music volume has been turned up."

[0496] Thus, this invention is a system that uses smart devices to analyze natural language instructions and quickly and efficiently control equipment in a physical store. Specific hardware used includes smartphones and smart glasses, and software uses a generative AI model (e.g., OpenAI's API). An HTTP server is used for communication. This allows for easy operation in natural language and rapid equipment control.

[0497] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0498] Step 1:

[0499] A user inputs natural language instructions into a smart device.

[0500] Input: A user types the natural language instruction "It's 10 o'clock, turn on the lights" into their smartphone.

[0501] What happens: A user enters natural language instructions using the voice or text input features of their smartphone.

[0502] Step 2:

[0503] The terminal sends a natural language instruction to the server.

[0504] Input: Natural language instructions entered into a smart device.

[0505] Output: Natural language instructions are sent to the server.

[0506] Specific operation: The terminal converts the input natural language instructions into packets and sends an HTTP request to the server.

[0507] Step 3:

[0508] The server uses a generative AI model to parse the natural language instructions.

[0509] Input: Natural language instruction data sent from the terminal.

[0510] Output: Parsed instructions (control commands).

[0511] Specific operation: The server calls a generative AI model (e.g., OpenAI API) to analyze natural language instructions and converts the instruction "It's 10 o'clock, so turn on the lights" into the control command "Turn on the lights."

[0512] Step 4:

[0513] The server generates control instructions for the building equipment based on the analyzed instructions.

[0514] Input: The analysis result obtained from the generative AI model (the control command "turn on the lights").

[0515] Output: Specific control instructions to send to the building equipment API.

[0516] Specific action: The server converts the control command into a format acceptable to the store equipment's API and prepares a specific API call to turn on the light.

[0517] Step 5:

[0518] The server sends the generated control instructions to the building equipment's API.

[0519] Input: API call for specific control instructions.

[0520] Output: Light fixture turns on.

[0521] Specific operation: The server sends the prepared control instructions as an HTTP request, calls the building equipment API, and turns on the lights.

[0522] Step 6:

[0523] It monitors the status of building facilities and sends feedback to the server.

[0524] Input: The operational state of the building equipment (lights turned on).

[0525] Output: Feedback information (confirmation that the light is on).

[0526] Specific operation: After the lighting equipment is turned on, the sensor detects its status and returns the information to the server via API.

[0527] Step 7:

[0528] The server sends feedback information to the terminal.

[0529] Input: Feedback information (confirmation that the light is on).

[0530] Output: Feedback information is sent to the terminal.

[0531] Specific operation: The server packets the feedback information and sends it to the terminal using an HTTP request.

[0532] Step 8:

[0533] The terminal provides feedback information to the user.

[0534] Input: Feedback information sent by the server.

[0535] Output: The user checks the feedback information.

[0536] Specific behavior: The device displays feedback information on the display and notifies the user that "The lights are on."

[0537] 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.

[0538] This invention combines a control system that uses natural language instructions to streamline building facility management with an emotion engine that recognizes user emotions. This system, in particular, has the function of analyzing natural language instructions using a generative model and generating control instructions for building facilities. The system also transmits the generated control instructions to the building facilities' API, monitors the facility's status, and provides appropriate feedback to the user. Furthermore, by incorporating the emotion engine, it is possible to recognize user emotions and provide appropriate control instructions and feedback.

[0539] Server Roles

[0540] The server plays a central role, analyzing the received natural language instructions and generating control instructions for the building facilities. It also uses an emotion engine to analyze the user's emotions and generate appropriate control instructions based on those emotions. It also monitors the status of the building facilities and provides feedback as needed.

[0541] For example, if a user issues an impatient command such as "Turn on the air conditioning in the conference room," the server will use its emotion engine to recognize the user's impatience, generate a control command to quickly turn on the air conditioning, and then generate a feedback message such as "The air conditioning has been turned on immediately" to alleviate the user's impatience.

[0542] Device Role

[0543] The device receives natural language instructions from the user and sends them to the server. It also receives feedback from the server and displays it to the user. Voice and text data that the emotion engine uses to recognize the user's emotions are also acquired through the device and sent to the server.

[0544] For example, if a user types "Turn on the air conditioning in the conference room" into the device, the instruction is sent to the server. When the server returns feedback, the device displays it to the user. Based on the emotion recognition results, the feedback is adjusted to something like "The air conditioning was turned on quickly."

[0545] User Roles

[0546] The user is the entity that controls and manages the building facilities. They input natural language commands into the terminal and receive feedback from the terminal. The emotion engine also recognizes the user's emotions and provides optimal control commands and feedback accordingly.

[0547] For example, if a user expresses irritation when requesting that the air conditioning be turned on before a meeting begins, the system will recognize that emotion and respond quickly. If the air conditioning is turned on quickly, the system will display feedback to the user, such as "The air conditioning was turned on quickly," to alleviate the irritation.

[0548] In this way, by incorporating an emotion engine, the system recognizes the user's natural language instructions and emotions, and provides appropriate control and feedback for building equipment. This system enables building managers and users to operate building equipment more efficiently and in a user-centered manner. It can also contribute to improving energy efficiency and early detection of malfunctions. Specific program processing steps will be explained in detail as necessary.

[0549] The processing flow will be explained below.

[0550] Step 1:

[0551] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0552] Step 2:

[0553] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0554] Step 3:

[0555] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0556] Step 4:

[0557] The server uses an emotion engine to analyze the user's emotions from the natural language instructions sent, for example recognizing emotions such as irritation or joy from the tone of voice and sentences.

[0558] Step 5:

[0559] The server generates control commands for the building's facilities based on the analysis results. The results of the user's emotion recognition are also taken into account, so prompt responses and specific feedback are included. For example, if irritation is recognized, a quick response is required.

[0560] Step 6:

[0561] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0562] Step 7:

[0563] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0564] Step 8:

[0565] The server generates a feedback message based on the results, taking into account the user's emotions, such as "The air conditioning has been turned on quickly."

[0566] Step 9:

[0567] The server sends the generated feedback message to the terminal.

[0568] Step 10:

[0569] The terminal receives the feedback message from the server and displays it to the user, who can confirm through the terminal that the instruction was executed correctly. The content of the feedback message is adjusted according to the user's emotions.

[0570] Example 2

[0571] 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."

[0572] Efficient management is required for building facilities management, but conventional methods often fail to correctly understand user instructions and are unable to respond quickly. Furthermore, there is also the problem of a lack of appropriate feedback that takes into account the user's emotions, resulting in a decline in user satisfaction. In particular, a prompt and appropriate response is required for users who are feeling irritated or anxious, but such a response is difficult to achieve. Furthermore, early detection of building facility failures and improving energy efficiency have also been challenges.

[0573] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0574] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, means for transmitting the generated control instructions to the building facilities' API, means for analyzing a user's emotions when analyzing the natural language instructions, means for adjusting the control instructions and feedback based on the analyzed emotions, means for monitoring the status of the building facilities, and means for providing feedback to the user. This allows the user's instructions to be correctly understood, enabling prompt and appropriate responses, thereby improving user satisfaction. It also enables early detection of building facilities failures and improved energy efficiency.

[0575] A "generative AI model" is an artificial intelligence model that analyzes natural language and generates appropriate control instructions and responses based on the results.

[0576] "Natural language instructions" refer to instructions provided by a user in spoken or text format that are written in language that is intuitively understandable to humans.

[0577] A "Building Facilities API" is an application programming interface for programmatically controlling building facilities (e.g., air conditioning, lighting, elevators, etc.).

[0578] An "emotion engine" is a technology or algorithm for analyzing emotions or emotional states from user-provided voice or text input.

[0579] "Feedback" is a response that the system provides to the user, including reporting how the user's instructions were processed.

[0580] "Means for monitoring the status of building facilities" refers to sensors and monitoring systems for detecting the operating status of building facilities and whether or not they have malfunctioned.

[0581] "Control instructions" are specific instructions generated by the system to operate building equipment, so that the equipment operates as expected.

[0582] This invention combines a control system that uses natural language instructions to improve the efficiency of building facility management with an emotion engine that recognizes user emotions. Detailed embodiments are described below.

[0583] Server Roles

[0584] The server is the central controller of the system. It first receives the natural language instructions sent by the device and analyzes them using a generative AI model (e.g., a publicly available natural language processing model) to understand exactly what the user wants.

[0585] The server then uses an emotion engine (e.g., a cloud-based emotion recognition service) to analyze the user's emotions. Based on the emotion recognition results, the server adjusts the appropriateness of the generated control instructions and feedback messages. In this way, it is possible to respond according to the user's level of frustration or satisfaction.

[0586] The server generates specific building equipment control instructions based on the analysis results and sends them to the building equipment's API, for example, to operate the air conditioning system or lighting system. It also checks the execution results of the control instructions, generates appropriate feedback messages, and sends them to the terminal.

[0587] Device Role

[0588] The terminal functions as a user interface. The user can use the terminal to input instructions in natural language. The input is sent to the server for processing. Instructions can be accepted in a variety of formats, including voice input and text input.

[0589] The terminal receives feedback from the server and displays it to the user, for example, a feedback message such as "The air conditioning was turned on quickly" so that the user can be sure that their instruction was carried out correctly.

[0590] User Roles

[0591] The user is the entity that uses this system to control the building equipment. They input instructions in natural language into the terminal and operate the equipment. They also check feedback from the server and issue instructions again if necessary to manage the equipment status.

[0592] Specific examples

[0593] As a concrete example, consider the following scenario.

[0594] The user inputs "Turn on the air conditioning in the conference room" into the device. This command is sent from the device to the server. The server analyzes this command using a generative AI model and generates a control command to turn on the air conditioning.

[0595] At the same time, the emotion engine recognizes the user's frustration. The server determines that this frustration requires a quick response, generates a command to "quickly turn on the air conditioning" and sends it to the building equipment's API. After the air conditioning is turned on, the server generates a feedback message saying "The air conditioning has been turned on quickly" and sends it to the device. The user confirms this feedback on the device and understands that the command was processed appropriately.

[0596] Prompt Sentence Examples

[0597] User command: "Turn on the air conditioning in the conference room."

[0598] Context to analyze: A user issues a command to turn on the air conditioning in a conference room. If this command is accompanied by irritation, a quick response is required.

[0599] Emotion recognition result: Irritated

[0600] Generate control instructions: Quickly turn on air conditioning.

[0601] Feedback message: "Air conditioning turned on quickly"

[0602] In this way, the system of the present invention recognizes the user's natural language commands and emotions, and provides appropriate control and feedback for building facilities. This enables building managers and users to operate building facilities more efficiently and in a user-centered manner. It also contributes to improving energy efficiency and early detection of malfunctions.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The user inputs a natural language command into the device, for example, "Turn on the air conditioning in the conference room," either by speaking or by typing it into the device.

[0606] Input: User's natural language instructions

[0607] Output: Voice or text input data to the device

[0608] Step 2:

[0609] The device receives the user's natural language instructions and transmits the data to the server using HTTP requests over the network.

[0610] Input: Voice or text input data

[0611] Output: HTTP request to the server

[0612] Step 3:

[0613] The server inputs the received natural language instructions into a generative AI model, which analyzes the instructions and identifies the specific action the user wants to take (e.g., turn on the air conditioning).

[0614] Input: HTTP request received by the server

[0615] Output: Parsed instructions

[0616] Step 4:

[0617] The server uses an emotion engine to analyze the emotion contained in the user's natural language instructions, and this process provides emotional information such as whether the user is annoyed.

[0618] Input: Natural language instruction data

[0619] Output: Sentiment analysis result (e.g., irritated)

[0620] Step 5:

[0621] The server generates appropriate building facility control instructions based on the analysis results. For example, if a user is frustrated, a control instruction is generated that calls for a quick response.

[0622] Input: Analyzed instructions and sentiment analysis results

[0623] Output: Generated control instructions

[0624] Step 6:

[0625] The server sends the generated control instructions to the API of the building equipment, for example, via an HTTP request via a REST API.

[0626] Input: Generated control instructions

[0627] Output: API request to building equipment

[0628] Step 7:

[0629] The server receives the response from the building equipment API and checks whether the control was successful. If the control was successful, the next step is to generate a feedback message.

[0630] Input: API response from building equipment

[0631] Output: Check the control results

[0632] Step 8:

[0633] The server generates an appropriate feedback message and sends it to the device, taking into account the sentiment analysis results, for example, generating a message such as "The air conditioning was quickly turned on."

[0634] Input: Control results and sentiment analysis results

[0635] Output: The generated feedback message

[0636] Step 9:

[0637] The terminal receives the feedback message from the server and displays it to the user, who can see that the instruction has been executed correctly.

[0638] Input: Feedback message from the server

[0639] Output: Display feedback to the user

[0640] Through the above processing steps, the user's natural language instructions are correctly analyzed, appropriate control instructions are generated, and building facilities are operated, resulting in the user receiving prompt and accurate feedback in accordance with their instructions.

[0641] (Application example 2)

[0642] 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."

[0643] Conventional facility management systems for buildings and brick-and-mortar stores control equipment based on users' natural language instructions, but do not take the user's emotions into consideration. This means that appropriate feedback is not provided to the user, resulting in frustration and inconvenience for the user. Furthermore, in brick-and-mortar stores, equipment control based on the emotions of users and store staff is required, but current systems lack such functionality. Furthermore, there is also room for improvement in terms of optimizing energy efficiency to achieve efficient equipment control.

[0644] 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.

[0645] In this invention, the server includes means for analyzing natural language instructions using a generative model, means for generating control instructions for building facilities based on the analyzed instructions, means for sending the generated control instructions to the building facilities' API, means for analyzing user emotions using an emotion engine and generating control instructions and feedback according to the emotions, and means for controlling various facilities (lighting, air conditioning, music, etc.) in the physical store. This enables quick and appropriate control of facilities and provision of feedback that takes user emotions into consideration, thereby improving user satisfaction and optimizing energy efficiency.

[0646] A "generative model" is an artificial intelligence technology that analyzes natural language instructions and generates appropriate control instructions based on their content.

[0647] "Natural language instructions" are commands or requests entered by the user in everyday language, and by analyzing these, instructions for operating various devices are extracted.

[0648] "Building facilities" refers to the various devices and systems installed within a building, including air conditioning, lighting, elevators, etc.

[0649] A "control instruction" is a command or instruction that causes building facilities or physical store equipment to perform a specific operation based on the analyzed natural language instruction.

[0650] "API" stands for Application Programming Interface, an interface for exchanging data and functions between software programs.

[0651] An "emotion engine" is a technology that analyzes emotions from a user's voice or text and generates appropriate feedback and control instructions based on those emotions.

[0652] "Feedback" refers to a response or result report from the system to an instruction from the user, and notifies the user whether the instruction was processed correctly.

[0653] "Brick and mortar store" refers to a physical commercial establishment or retail outlet, including lighting, air conditioning, music, and other amenities.

[0654] This invention provides a system that combines natural language instruction analysis and emotion recognition to improve the efficiency of facility management in buildings and brick-and-mortar stores. This system operates in three roles: server, terminal, and user.

[0655] Server Roles

[0656] The server plays a central role and has the following functions:

[0657] Function to analyze natural language instructions using generative models: Analyzes natural language instructions sent by the user and converts them into specific control commands. For example, if a user instructs the robot to "dim the lights in the store a little," the robot analyzes this instruction and generates a lighting control command.

[0658] Emotion analysis function using emotion engine: Recognizes emotions from the user's voice or text and generates appropriate control instructions and feedback based on those emotions. For example, if the emotion engine determines that the user is irritated, it will respond quickly and generate feedback such as "The lights have been dimmed immediately" to alleviate the user's irritation.

[0659] A function to send control instructions to the APIs of various facilities in buildings and physical stores: The generated control commands are sent to the APIs of the building facilities and physical store facilities, and the actual control is performed.

[0660] Function to monitor equipment status and provide feedback: Monitor the status of each piece of equipment, detect faults and provide feedback to the user.

[0661] Device Role

[0662] The device is responsible for receiving natural language instructions from the user and sending them to the server. Specifically:

[0663] A natural language instruction entered by the user is sent to the server.

[0664] Receives feedback from the server and displays it to the user.

[0665] Voice and text data for emotion recognition is collected and sent to a server.

[0666] For example, if the device is a smartphone, when the user inputs an instruction such as "Adjust the air conditioning in the store," the device sends this to the server and displays feedback from the server to the user, such as "The air conditioning has been adjusted."

[0667] User Roles

[0668] The user is the entity that operates the system, controlling and managing the facilities of the building or physical store. The user inputs instructions in natural language and receives feedback from the device. The emotion engine recognizes emotions and provides optimal feedback and control instructions.

[0669] For example, if a user says, "The music is too loud, please be quieter. I'm very tired," the server analyzes the instruction, generates a command to lower the music volume, and provides feedback such as, "The music volume has been lowered. We will provide you with a relaxing environment."

[0670] Hardware and software used

[0671] Hardware: Users use smartphones, tablets, or in-store interactive displays.

[0672] Software: Uses emotion recognition engines (e.g., Microsoft Azure Emotion API), natural language processing engines (e.g., OpenAI GPT-3).

[0673] Examples of concrete examples and prompts

[0674] To illustrate, consider the following scenario:

[0675] scenario

[0676] If the store is a little noisy and a customer says, "Please make the music quieter in the store, I'm very tired."

[0677] Prompt Sentence Examples

[0678] User Input: Please make the music quieter in the store, I'm so tired

[0679] Objective: Recognize the user's emotions, generate control instructions to lower the music volume, and provide appropriate feedback to the user.

[0680] This invention makes it possible to control equipment quickly and appropriately and provide feedback that takes into account the user's feelings, thereby improving user satisfaction and optimizing energy efficiency.

[0681] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0682] Step 1:

[0683] A user enters natural language instructions into a terminal.

[0684] As a specific example, the user uses a smartphone to input instructions via voice or text, such as "Please turn down the music in the store; I'm very tired."

[0685] Input: User's natural language instructions (voice or text)

[0686] Output: Natural language instructions entered into the terminal

[0687] Step 2:

[0688] The terminal transmits the input natural language instruction to the server.

[0689] The terminal is responsible for receiving user instruction data and transmitting it to the server.

[0690] Input: Natural language instruction data entered into the terminal

[0691] Output: Natural language instructions sent to the server

[0692] Step 3:

[0693] The server analyzes the received natural language instructions using a generative model.

[0694] For the analysis, a generative AI model (e.g., OpenAI GPT-3) is used to analyze the user's instructions and generate specific control commands.

[0695] Input: Natural language instructions sent to the server

[0696] Output: Generated control command data

[0697] Step 4:

[0698] The server analyzes the user's emotions using an emotion engine.

[0699] Using natural language instruction data as input, an emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's emotions.

[0700] Input: Natural language instruction data

[0701] Output: Parsed emotion data

[0702] Step 5:

[0703] The server generates appropriate feedback based on the generated control commands and the analyzed emotion data.

[0704] Based on the analysis results, a feedback message is generated, such as "The music has been quickly quieted down to provide a relaxing environment."

[0705] Input: Generated control command data, analyzed emotion data

[0706] Output: The generated feedback message

[0707] Step 6:

[0708] The server sends control commands to the API of the building equipment or physical store equipment to execute the control.

[0709] For example, sending a command to a music system's API to turn down the volume.

[0710] Input: Generated control command data

[0711] Output: Control action taken (music volume is reduced)

[0712] Step 7:

[0713] The server transmits the generated feedback to the terminal.

[0714] The generated feedback is sent to the terminal to provide a feedback message to the user.

[0715] Input: The generated feedback message

[0716] Output: Feedback message sent to the terminal

[0717] Step 8:

[0718] The terminal displays the received feedback message to the user.

[0719] For example, a message could appear on a smartphone screen saying, "The music volume has been lowered to provide a relaxing environment."

[0720] Input: Feedback message sent to the device

[0721] Output: The feedback message displayed to the user

[0722] 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.

[0723] 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.

[0724] 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.

[0725] [Third embodiment]

[0726] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0727] 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.

[0728] 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).

[0729] 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.

[0730] 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.

[0731] 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).

[0732] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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."

[0738] The present invention relates to a control system using natural language instructions in building facility management. A specific embodiment of this system will be described below.

[0739] This system is designed for efficient and smart building management, and allows users to issue instructions to building facilities in natural language. The system is mainly composed of three elements: a server, a terminal, and a user.

[0740] Server Roles

[0741] The server has the central function of analyzing received natural language instructions and generating control instructions for building facilities. It uses a generative model to analyze and interpret the natural language instructions received from the user. It then generates specific control instructions for the building facilities' APIs based on the interpreted instructions. In addition, the server monitors the status of the building facilities and provides feedback as needed.

[0742] For example, if a user instructs the server to "turn on the air conditioning in the conference room," the server analyzes the instruction, generates a control command to turn on the air conditioning, and sends this control command to the API of the air conditioning equipment to turn on the air conditioning.

[0743] Device Role

[0744] The terminal acts as a user interface, receiving natural language instructions from the user and sending them to the server, and also receiving feedback from the server and providing it to the user.

[0745] For example, if a user types "Turn on the air conditioning in the conference room" into a terminal, the command is sent to the server. When feedback is returned from the server, the terminal displays it to the user. The feedback is displayed as a message such as "The air conditioning has been turned on."

[0746] User Roles

[0747] The user is the entity that controls and manages the building facilities. The user inputs natural language instructions into the terminal and checks the operating status of the building facilities through feedback from the terminal.

[0748] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user can then confirm that the air conditioning has been turned on through feedback from the server.

[0749] Thus, the present invention provides a system for analyzing natural language instructions and controlling and managing building facilities. This system allows building managers and users to operate building facilities efficiently and easily. It also contributes to environmental protection by realizing control that improves the energy efficiency of buildings. Specific program processing steps will be described in detail as necessary.

[0750] The processing flow will be explained below.

[0751] Step 1:

[0752] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0753] Step 2:

[0754] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0755] Step 3:

[0756] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0757] Step 4:

[0758] Based on the analysis results, the server generates control commands for the building's facilities, such as API commands to turn on the air conditioning equipment.

[0759] Step 5:

[0760] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0761] Step 6:

[0762] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0763] Step 7:

[0764] Based on the results of the check, the server generates a feedback message, such as "The air conditioning has been turned on."

[0765] Step 8:

[0766] The server sends the generated feedback message to the terminal.

[0767] Step 9:

[0768] The terminal receives the feedback message from the server and displays it to the user, who can then confirm through the terminal that the instruction has been executed correctly.

[0769] Example 1

[0770] 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."

[0771] Building facility management is complex and time-consuming, and is extremely inefficient, especially when there are many pieces of equipment, as each piece must be controlled individually. There is a need to solve this problem, improve the efficiency of building management, and further increase energy efficiency. Another challenge is to provide an interface that allows users to operate intuitively.

[0772] 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.

[0773] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, and means for transmitting the generated control instructions to the API of the building facilities, which enables users to intuitively control building facilities using natural language, thereby improving the efficiency of building management and energy efficiency.

[0774] "Natural language instructions" is an input format that allows a user to use ordinary language to perform operations or give instructions to a system.

[0775] A "generative AI model" is an algorithm automatically generated based on collected data, and is a machine learning model for analyzing and generating natural language.

[0776] "Analysis" refers to the process of understanding received information or data and analyzing its meaning and structure.

[0777] "Control instructions" refers to specific commands and instructions for operating and managing building facilities.

[0778] "API" is an abbreviation for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[0779] "Building facilities" refers to all equipment and systems used within a building (e.g., air conditioning, lighting, elevators, etc.).

[0780] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user interacts with the system.

[0781] A "feedback message" is a message that the system uses to return operation results and status information to the user.

[0782] "Condition monitoring" is the process of monitoring the current state of building facilities in real time and detecting abnormalities or malfunctions.

[0783] A "sensor" is a device that detects physical conditions and acquires them as data.

[0784] "Energy efficiency" refers to the degree to which equipment and systems minimize the waste of energy they use and function efficiently.

[0785] This invention relates to a control system that uses natural language instructions in building facility management. A specific embodiment of this system will be described below. The main components are a server, a terminal, and a user.

[0786] Server embodiment

[0787] The server plays a central role in analyzing natural language instructions received from users and generating control instructions for building facilities. Specifically, it performs the following processes:

[0788] 1. The server parses the natural language instructions using a generative AI model (e.g., OpenAI's GPT-4). This model uses natural language processing techniques to interpret the user's input and understand their intent.

[0789] 2. The server generates specific control instructions for the APIs of the building facilities (e.g., air conditioning, lighting systems) based on the analyzed instructions. This generation is done using a program that constructs appropriate API calls based on the analysis results.

[0790] 3. The server sends the generated control command to the API of the building equipment. For example, it turns on the air conditioning by sending an HTTP request to the API endpoint of the air conditioning system.

[0791] 4. The server monitors the status of the building facilities and generates feedback messages as needed. It receives responses from the building facilities and generates user-friendly feedback messages (e.g., "The air conditioning has been turned on").

[0792] Terminal embodiment

[0793] The terminal functions as a user interface, receiving natural language instructions from the user and transmitting them to the server, and is also responsible for providing feedback from the server to the user.

[0794] 1. The user enters a natural language command using the device interface, for example, "Turn on the air conditioning in the conference room" using a smartphone, tablet PC, or PC.

[0795] 2. The terminal sends this instruction to the server using a communication protocol such as an HTTP POST request.

[0796] 3. When the server sends a feedback message, the device receives it and displays it to the user, for example, a message saying "The air conditioning has been turned on."

[0797] User's embodiment

[0798] The user is the entity that controls and manages the building equipment. They input natural language instructions into the terminal and check the operating status of the building equipment through feedback from the terminal.

[0799] Specifically, the user inputs "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user then confirms that the air conditioning has been turned on through a feedback message displayed on the terminal.

[0800] Examples of concrete examples and prompts

[0801] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters the following into the terminal:

[0802] Example prompt sentence:

[0803] "Turn on the air conditioning in the conference room."

[0804] The server receives this instruction, analyzes it using a generative AI model, and generates and executes an API call to "turn on the air conditioning." As a result, the air conditioning turns on and a feedback message such as "The air conditioning has been turned on" is displayed to the user on their device.

[0805] This concludes the detailed description of the preferred embodiment of the present invention, which allows users to control building equipment in an efficient and intuitive manner, while also improving the energy efficiency of buildings.

[0806] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0807] Step 1: The user enters natural language instructions into the terminal.

[0808] The user inputs a natural language instruction into the terminal interface, such as "Turn on the air conditioning in the conference room." The input is in text format, and the terminal proceeds to the next step in that format. This input starts the system's processing.

[0809] Step 2: The device sends a natural language instruction to the server

[0810] The terminal sends the natural language instructions entered by the user to the server. Specifically, it uses a communication protocol such as an HTTP POST request to send the entered natural language instructions to the server as a payload. The input of this step is the user's instructions, and the output is an HTTP request to the server.

[0811] Step 3: The server receives and parses the natural language instructions

[0812] The server receives natural language instructions sent from the device. Based on the received data, it analyzes the instructions using a generative AI model (e.g., OpenAI's GPT-4). Specifically, it inputs the instructions into the model and extracts the resulting analysis data. The input for this step is the natural language instructions from the device, and the output is the analysis results.

[0813] Step 4: Server generates control commands

[0814] The server generates a control command for the building equipment based on the analyzed instructions. For example, based on the analysis result "Turn on the air conditioning in the conference room," it creates a specific command (e.g., an HTTP request) to send to the air conditioning system's API. The input to this step is the analysis result, and the output is the control command.

[0815] Step 5: The server sends the control command to the building equipment API

[0816] The server sends the generated control command to the building equipment's API. Specifically, it performs the operation of turning on the air conditioning by sending the generated HTTP request to the air conditioning system's API endpoint. The input to this step is the control command, and the output is an API request to the building equipment.

[0817] Step 6: The server receives feedback from the building equipment

[0818] The building equipment executes the control command from the server and feeds back the results to the server. The server receives this feedback and checks the processing results. For example, it receives feedback that "the air conditioning was successfully turned on." The input of this step is the feedback from the building equipment, and the output is the feedback data.

[0819] Step 7: Server generates feedback message

[0820] Based on the received feedback, the server generates a feedback message to inform the user. Specifically, it creates a message saying "The air conditioning has been turned on." The input of this step is the feedback data, and the output is the feedback message.

[0821] Step 8: The server sends a feedback message to the device

[0822] The server sends the generated feedback message to the terminal. The message is sent using an HTTP POST request, etc. The input of this step is the feedback message, and the output is an HTTP request to the terminal.

[0823] Step 9: The device displays a feedback message to the user

[0824] The terminal receives the feedback message sent from the server and displays it to the user. For example, the terminal screen displays "The air conditioning has been turned on." The input of this step is the feedback message from the server, and the output is the message displayed on the user interface.

[0825] The above is the specific processing flow of this system.

[0826] (Application example 1)

[0827] 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."

[0828] Conventional building facility management systems require manual control of facilities, requiring a great deal of time and effort. Furthermore, in brick-and-mortar stores, facilities need to be managed and controlled quickly and flexibly to improve customer comfort, but conventional systems have difficulty meeting this requirement. Furthermore, it has been difficult to centrally grasp the status of multiple facilities and control them efficiently. For this reason, there is a demand for a system that can control facilities with simple instructions in natural language and that can be operated instantly using smart devices.

[0829] 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.

[0830] In this invention, the server includes a means for analyzing natural language instructions using a generative model, a means for generating control instructions for building facilities based on the analyzed instructions, and a means for transmitting the generated control instructions to the API of the building facilities. This makes it possible to monitor the status of the building facilities and provide feedback to users. Furthermore, smart devices can be used to flexibly control facilities in physical stores, thereby improving customer comfort in the stores.

[0831] A "generative model" is an artificial intelligence model that analyzes a user's natural language instructions and generates appropriate control instructions.

[0832] "Natural language instructions" are instructions that users input in the same way as in everyday conversation, and are commands for controlling the facilities of buildings and stores.

[0833] "Building facilities" refers to various controlled objects within a building or store, such as air conditioning, lighting, and music.

[0834] "API" stands for Application Programming Interface, and refers to an interface that allows data to be exchanged between different software programs.

[0835] A "smart device" is a terminal with advanced functions that can connect to the Internet, such as a smartphone or smart glasses.

[0836] "Feedback" is the process of providing information about the execution results and current equipment status in response to instructions entered by the user.

[0837] A "brick and mortar store" is a store that exists in a physical location and that customers can visit in person.

[0838] "Customer comfort" means the degree of comfort felt by customers in a physical store due to the control of the equipment.

[0839] The present invention is a system for efficiently and comfortably managing facilities in a physical store. Specific embodiments of the system are described below.

[0840] Server Roles

[0841] The server has the central function of analyzing natural language instructions using a generative model and generating control instructions for store equipment. When a user inputs natural language instructions into a smart device (such as a smartphone or smart glasses), the instructions are sent to the server. The server then analyzes the natural language instructions using a generative AI model and converts them into appropriate control instructions. These control instructions are used to control store equipment such as lighting, air conditioning, and music. The server then sends these control instructions to the store equipment's API to manage the equipment's operation.

[0842] Device Role

[0843] The terminal functions as a user interface, receiving natural language instructions from the user and sending them to the server. It also provides feedback returned from the server to the user. For example, if a store manager types "It's 10 o'clock, so turn on the lights" into his smartphone, the instruction is sent directly to the server. When the server returns feedback saying "The lights are on," the content is displayed on the terminal, allowing the user to check the status of the equipment.

[0844] User Roles

[0845] Users are the entities that control and manage store equipment. They use smart devices to input natural language commands and check the equipment's operating status through feedback from the terminal. This allows for easy and quick equipment management.

[0846] Examples and prompts

[0847] For example, if a store manager inputs an instruction into the smart glasses, such as "We've seen an increase in customers. Please turn up the volume of the music in the store," the server analyzes this instruction and generates a control command to turn up the music volume. This control command is then sent to the API of the store's music equipment, which turns up the music volume. The result is then returned to the user as feedback, such as "The music volume has been turned up."

[0848] Thus, this invention is a system that uses smart devices to analyze natural language instructions and quickly and efficiently control equipment in a physical store. Specific hardware used includes smartphones and smart glasses, and software uses a generative AI model (e.g., OpenAI's API). An HTTP server is used for communication. This allows for easy operation in natural language and rapid equipment control.

[0849] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0850] Step 1:

[0851] A user inputs natural language instructions into a smart device.

[0852] Input: A user types the natural language instruction "It's 10 o'clock, turn on the lights" into their smartphone.

[0853] What happens: A user enters natural language instructions using the voice or text input features of their smartphone.

[0854] Step 2:

[0855] The terminal sends a natural language instruction to the server.

[0856] Input: Natural language instructions entered into a smart device.

[0857] Output: Natural language instructions are sent to the server.

[0858] Specific operation: The terminal converts the input natural language instructions into packets and sends an HTTP request to the server.

[0859] Step 3:

[0860] The server uses a generative AI model to parse the natural language instructions.

[0861] Input: Natural language instruction data sent from the terminal.

[0862] Output: Parsed instructions (control commands).

[0863] Specific operation: The server calls a generative AI model (e.g., OpenAI API) to analyze natural language instructions and converts the instruction "It's 10 o'clock, so turn on the lights" into the control command "Turn on the lights."

[0864] Step 4:

[0865] The server generates control instructions for the building equipment based on the analyzed instructions.

[0866] Input: The analysis result obtained from the generative AI model (the control command "turn on the lights").

[0867] Output: Specific control instructions to send to the building equipment API.

[0868] Specific action: The server converts the control command into a format acceptable to the store equipment's API and prepares a specific API call to turn on the light.

[0869] Step 5:

[0870] The server sends the generated control instructions to the building equipment's API.

[0871] Input: API call for specific control instructions.

[0872] Output: Light fixture turns on.

[0873] Specific operation: The server sends the prepared control instructions as an HTTP request, calls the building equipment API, and turns on the lights.

[0874] Step 6:

[0875] It monitors the status of building facilities and sends feedback to the server.

[0876] Input: The operational state of the building equipment (lights turned on).

[0877] Output: Feedback information (confirmation that the light is on).

[0878] Specific operation: After the lighting equipment is turned on, the sensor detects its status and returns the information to the server via API.

[0879] Step 7:

[0880] The server sends feedback information to the terminal.

[0881] Input: Feedback information (confirmation that the light is on).

[0882] Output: Feedback information is sent to the terminal.

[0883] Specific operation: The server packets the feedback information and sends it to the terminal using an HTTP request.

[0884] Step 8:

[0885] The terminal provides feedback information to the user.

[0886] Input: Feedback information sent by the server.

[0887] Output: The user checks the feedback information.

[0888] Specific behavior: The device displays feedback information on the display and notifies the user that "The lights are on."

[0889] 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.

[0890] This invention combines a control system that uses natural language instructions to streamline building facility management with an emotion engine that recognizes user emotions. This system, in particular, has the function of analyzing natural language instructions using a generative model and generating control instructions for building facilities. The system also transmits the generated control instructions to the building facilities' API, monitors the facility's status, and provides appropriate feedback to the user. Furthermore, by incorporating the emotion engine, it is possible to recognize user emotions and provide appropriate control instructions and feedback.

[0891] Server Roles

[0892] The server plays a central role, analyzing the received natural language instructions and generating control instructions for the building facilities. It also uses an emotion engine to analyze the user's emotions and generate appropriate control instructions based on those emotions. It also monitors the status of the building facilities and provides feedback as needed.

[0893] For example, if a user issues an impatient command such as "Turn on the air conditioning in the conference room," the server will use its emotion engine to recognize the user's impatience, generate a control command to quickly turn on the air conditioning, and then generate a feedback message such as "The air conditioning has been turned on immediately" to alleviate the user's impatience.

[0894] Device Role

[0895] The device receives natural language instructions from the user and sends them to the server. It also receives feedback from the server and displays it to the user. Voice and text data that the emotion engine uses to recognize the user's emotions are also acquired through the device and sent to the server.

[0896] For example, if a user types "Turn on the air conditioning in the conference room" into the device, the instruction is sent to the server. When the server returns feedback, the device displays it to the user. Based on the emotion recognition results, the feedback is adjusted to something like "The air conditioning was turned on quickly."

[0897] User Roles

[0898] The user is the entity that controls and manages the building facilities. They input natural language commands into the terminal and receive feedback from the terminal. The emotion engine also recognizes the user's emotions and provides optimal control commands and feedback accordingly.

[0899] For example, if a user expresses irritation when requesting that the air conditioning be turned on before a meeting begins, the system will recognize that emotion and respond quickly. If the air conditioning is turned on quickly, the system will display feedback to the user, such as "The air conditioning was turned on quickly," to alleviate the irritation.

[0900] In this way, by incorporating an emotion engine, the system recognizes the user's natural language instructions and emotions, and provides appropriate control and feedback for building equipment. This system enables building managers and users to operate building equipment more efficiently and in a user-centered manner. It can also contribute to improving energy efficiency and early detection of malfunctions. Specific program processing steps will be explained in detail as necessary.

[0901] The processing flow will be explained below.

[0902] Step 1:

[0903] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[0904] Step 2:

[0905] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[0906] Step 3:

[0907] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[0908] Step 4:

[0909] The server uses an emotion engine to analyze the user's emotions from the natural language instructions sent, for example recognizing emotions such as irritation or joy from the tone of voice and sentences.

[0910] Step 5:

[0911] The server generates control commands for the building's facilities based on the analysis results. The results of the user's emotion recognition are also taken into account, so prompt responses and specific feedback are included. For example, if irritation is recognized, a quick response is required.

[0912] Step 6:

[0913] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[0914] Step 7:

[0915] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[0916] Step 8:

[0917] The server generates a feedback message based on the results, taking into account the user's emotions, such as "The air conditioning has been turned on quickly."

[0918] Step 9:

[0919] The server sends the generated feedback message to the terminal.

[0920] Step 10:

[0921] The terminal receives the feedback message from the server and displays it to the user, who can confirm through the terminal that the instruction was executed correctly. The content of the feedback message is adjusted according to the user's emotions.

[0922] Example 2

[0923] 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."

[0924] Efficient management is required for building facilities management, but conventional methods often fail to correctly understand user instructions and are unable to respond quickly. Furthermore, there is also the problem of a lack of appropriate feedback that takes into account the user's emotions, resulting in a decline in user satisfaction. In particular, a prompt and appropriate response is required for users who are feeling irritated or anxious, but such a response is difficult to achieve. Furthermore, early detection of building facility failures and improving energy efficiency have also been challenges.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0926] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, means for transmitting the generated control instructions to the building facilities' API, means for analyzing a user's emotions when analyzing the natural language instructions, means for adjusting the control instructions and feedback based on the analyzed emotions, means for monitoring the status of the building facilities, and means for providing feedback to the user. This allows the user's instructions to be correctly understood, enabling prompt and appropriate responses, thereby improving user satisfaction. It also enables early detection of building facilities failures and improved energy efficiency.

[0927] A "generative AI model" is an artificial intelligence model that analyzes natural language and generates appropriate control instructions and responses based on the results.

[0928] "Natural language instructions" refer to instructions provided by a user in spoken or text format that are written in language that is intuitively understandable to humans.

[0929] A "Building Facilities API" is an application programming interface for programmatically controlling building facilities (e.g., air conditioning, lighting, elevators, etc.).

[0930] An "emotion engine" is a technology or algorithm for analyzing emotions or emotional states from user-provided voice or text input.

[0931] "Feedback" is a response that the system provides to the user, including reporting how the user's instructions were processed.

[0932] "Means for monitoring the status of building facilities" refers to sensors and monitoring systems for detecting the operating status of building facilities and whether or not they have malfunctioned.

[0933] "Control instructions" are specific instructions generated by the system to operate building equipment, so that the equipment operates as expected.

[0934] This invention combines a control system that uses natural language instructions to improve the efficiency of building facility management with an emotion engine that recognizes user emotions. Detailed embodiments are described below.

[0935] Server Roles

[0936] The server is the central controller of the system. It first receives the natural language instructions sent by the device and analyzes them using a generative AI model (e.g., a publicly available natural language processing model) to understand exactly what the user wants.

[0937] The server then uses an emotion engine (e.g., a cloud-based emotion recognition service) to analyze the user's emotions. Based on the emotion recognition results, the server adjusts the appropriateness of the generated control instructions and feedback messages. In this way, it is possible to respond according to the user's level of frustration or satisfaction.

[0938] The server generates specific building equipment control instructions based on the analysis results and sends them to the building equipment's API, for example, to operate the air conditioning system or lighting system. It also checks the execution results of the control instructions, generates appropriate feedback messages, and sends them to the terminal.

[0939] Device Role

[0940] The terminal functions as a user interface. The user can use the terminal to input instructions in natural language. The input is sent to the server for processing. Instructions can be accepted in a variety of formats, including voice input and text input.

[0941] The terminal receives feedback from the server and displays it to the user, for example, a feedback message such as "The air conditioning was turned on quickly" so that the user can be sure that their instruction was carried out correctly.

[0942] User Roles

[0943] The user is the entity that uses this system to control the building equipment. They input instructions in natural language into the terminal and operate the equipment. They also check feedback from the server and issue instructions again if necessary to manage the equipment status.

[0944] Specific examples

[0945] As a concrete example, consider the following scenario.

[0946] The user inputs "Turn on the air conditioning in the conference room" into the device. This command is sent from the device to the server. The server analyzes this command using a generative AI model and generates a control command to turn on the air conditioning.

[0947] At the same time, the emotion engine recognizes the user's frustration. The server determines that this frustration requires a quick response, generates a command to "quickly turn on the air conditioning" and sends it to the building equipment's API. After the air conditioning is turned on, the server generates a feedback message saying "The air conditioning has been turned on quickly" and sends it to the device. The user confirms this feedback on the device and understands that the command was processed appropriately.

[0948] Prompt Sentence Examples

[0949] User command: "Turn on the air conditioning in the conference room."

[0950] Context to analyze: A user issues a command to turn on the air conditioning in a conference room. If this command is accompanied by irritation, a quick response is required.

[0951] Emotion recognition result: Irritated

[0952] Generate control instructions: Quickly turn on air conditioning.

[0953] Feedback message: "Air conditioning turned on quickly"

[0954] In this way, the system of the present invention recognizes the user's natural language commands and emotions, and provides appropriate control and feedback for building facilities. This enables building managers and users to operate building facilities more efficiently and in a user-centered manner. It also contributes to improving energy efficiency and early detection of malfunctions.

[0955] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0956] Step 1:

[0957] The user inputs a natural language command into the device, for example, "Turn on the air conditioning in the conference room," either by speaking or by typing it into the device.

[0958] Input: User's natural language instructions

[0959] Output: Voice or text input data to the device

[0960] Step 2:

[0961] The device receives the user's natural language instructions and transmits the data to the server using HTTP requests over the network.

[0962] Input: Voice or text input data

[0963] Output: HTTP request to the server

[0964] Step 3:

[0965] The server inputs the received natural language instructions into a generative AI model, which analyzes the instructions and identifies the specific action the user wants to take (e.g., turn on the air conditioning).

[0966] Input: HTTP request received by the server

[0967] Output: Parsed instructions

[0968] Step 4:

[0969] The server uses an emotion engine to analyze the emotion contained in the user's natural language instructions, and this process provides emotional information such as whether the user is annoyed.

[0970] Input: Natural language instruction data

[0971] Output: Sentiment analysis result (e.g., irritated)

[0972] Step 5:

[0973] The server generates appropriate building facility control instructions based on the analysis results. For example, if a user is frustrated, a control instruction is generated that calls for a quick response.

[0974] Input: Analyzed instructions and sentiment analysis results

[0975] Output: Generated control instructions

[0976] Step 6:

[0977] The server sends the generated control instructions to the API of the building equipment, for example, via an HTTP request via a REST API.

[0978] Input: Generated control instructions

[0979] Output: API request to building equipment

[0980] Step 7:

[0981] The server receives the response from the building equipment API and checks whether the control was successful. If the control was successful, the next step is to generate a feedback message.

[0982] Input: API response from building equipment

[0983] Output: Check the control results

[0984] Step 8:

[0985] The server generates an appropriate feedback message and sends it to the device, taking into account the sentiment analysis results, for example, generating a message such as "The air conditioning was quickly turned on."

[0986] Input: Control results and sentiment analysis results

[0987] Output: The generated feedback message

[0988] Step 9:

[0989] The terminal receives the feedback message from the server and displays it to the user, who can see that the instruction has been executed correctly.

[0990] Input: Feedback message from the server

[0991] Output: Display feedback to the user

[0992] Through the above processing steps, the user's natural language instructions are correctly analyzed, appropriate control instructions are generated, and building facilities are operated, resulting in the user receiving prompt and accurate feedback in accordance with their instructions.

[0993] (Application example 2)

[0994] 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."

[0995] Conventional facility management systems for buildings and brick-and-mortar stores control equipment based on users' natural language instructions, but do not take the user's emotions into consideration. This means that appropriate feedback is not provided to the user, resulting in frustration and inconvenience for the user. Furthermore, in brick-and-mortar stores, equipment control based on the emotions of users and store staff is required, but current systems lack such functionality. Furthermore, there is also room for improvement in terms of optimizing energy efficiency to achieve efficient equipment control.

[0996] 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.

[0997] In this invention, the server includes means for analyzing natural language instructions using a generative model, means for generating control instructions for building facilities based on the analyzed instructions, means for sending the generated control instructions to the building facilities' API, means for analyzing user emotions using an emotion engine and generating control instructions and feedback according to the emotions, and means for controlling various facilities (lighting, air conditioning, music, etc.) in the physical store. This enables quick and appropriate control of facilities and provision of feedback that takes user emotions into consideration, thereby improving user satisfaction and optimizing energy efficiency.

[0998] A "generative model" is an artificial intelligence technology that analyzes natural language instructions and generates appropriate control instructions based on their content.

[0999] "Natural language instructions" are commands or requests entered by the user in everyday language, and by analyzing these, instructions for operating various devices are extracted.

[1000] "Building facilities" refers to the various devices and systems installed within a building, including air conditioning, lighting, elevators, etc.

[1001] A "control instruction" is a command or instruction that causes building facilities or physical store equipment to perform a specific operation based on the analyzed natural language instruction.

[1002] "API" stands for Application Programming Interface, an interface for exchanging data and functions between software programs.

[1003] An "emotion engine" is a technology that analyzes emotions from a user's voice or text and generates appropriate feedback and control instructions based on those emotions.

[1004] "Feedback" refers to a response or result report from the system to an instruction from the user, and notifies the user whether the instruction was processed correctly.

[1005] "Brick and mortar store" refers to a physical commercial establishment or retail outlet, including lighting, air conditioning, music, and other amenities.

[1006] This invention provides a system that combines natural language instruction analysis and emotion recognition to improve the efficiency of facility management in buildings and brick-and-mortar stores. This system operates in three roles: server, terminal, and user.

[1007] Server Roles

[1008] The server plays a central role and has the following functions:

[1009] Function to analyze natural language instructions using generative models: Analyzes natural language instructions sent by the user and converts them into specific control commands. For example, if a user instructs the robot to "dim the lights in the store a little," the robot analyzes this instruction and generates a lighting control command.

[1010] Emotion analysis function using emotion engine: Recognizes emotions from the user's voice or text and generates appropriate control instructions and feedback based on those emotions. For example, if the emotion engine determines that the user is irritated, it will respond quickly and generate feedback such as "The lights have been dimmed immediately" to alleviate the user's irritation.

[1011] A function to send control instructions to the APIs of various facilities in buildings and physical stores: The generated control commands are sent to the APIs of the building facilities and physical store facilities, and the actual control is performed.

[1012] Function to monitor equipment status and provide feedback: Monitor the status of each piece of equipment, detect faults and provide feedback to the user.

[1013] Device Role

[1014] The device is responsible for receiving natural language instructions from the user and sending them to the server. Specifically:

[1015] A natural language instruction entered by the user is sent to the server.

[1016] Receives feedback from the server and displays it to the user.

[1017] Voice and text data for emotion recognition is collected and sent to a server.

[1018] For example, if the device is a smartphone, when the user inputs an instruction such as "Adjust the air conditioning in the store," the device sends this to the server and displays feedback from the server to the user, such as "The air conditioning has been adjusted."

[1019] User Roles

[1020] The user is the entity that operates the system, controlling and managing the facilities of the building or physical store. The user inputs instructions in natural language and receives feedback from the device. The emotion engine recognizes emotions and provides optimal feedback and control instructions.

[1021] For example, if a user says, "The music is too loud, please be quieter. I'm very tired," the server analyzes the instruction, generates a command to lower the music volume, and provides feedback such as, "The music volume has been lowered. We will provide you with a relaxing environment."

[1022] Hardware and software used

[1023] Hardware: Users use smartphones, tablets, or in-store interactive displays.

[1024] Software: Uses emotion recognition engines (e.g., Microsoft Azure Emotion API), natural language processing engines (e.g., OpenAI GPT-3).

[1025] Examples of concrete examples and prompts

[1026] To illustrate, consider the following scenario:

[1027] scenario

[1028] If the store is a little noisy and a customer says, "Please make the music quieter in the store, I'm very tired."

[1029] Prompt Sentence Examples

[1030] User Input: Please make the music quieter in the store, I'm so tired

[1031] Objective: Recognize the user's emotions, generate control instructions to lower the music volume, and provide appropriate feedback to the user.

[1032] This invention makes it possible to control equipment quickly and appropriately and provide feedback that takes into account the user's feelings, thereby improving user satisfaction and optimizing energy efficiency.

[1033] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1034] Step 1:

[1035] A user enters natural language instructions into a terminal.

[1036] As a specific example, the user uses a smartphone to input instructions via voice or text, such as "Please turn down the music in the store; I'm very tired."

[1037] Input: User's natural language instructions (voice or text)

[1038] Output: Natural language instructions entered into the terminal

[1039] Step 2:

[1040] The terminal transmits the input natural language instruction to the server.

[1041] The terminal is responsible for receiving user instruction data and transmitting it to the server.

[1042] Input: Natural language instruction data entered into the terminal

[1043] Output: Natural language instructions sent to the server

[1044] Step 3:

[1045] The server analyzes the received natural language instructions using a generative model.

[1046] For the analysis, a generative AI model (e.g., OpenAI GPT-3) is used to analyze the user's instructions and generate specific control commands.

[1047] Input: Natural language instructions sent to the server

[1048] Output: Generated control command data

[1049] Step 4:

[1050] The server analyzes the user's emotions using an emotion engine.

[1051] Using natural language instruction data as input, an emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's emotions.

[1052] Input: Natural language instruction data

[1053] Output: Parsed emotion data

[1054] Step 5:

[1055] The server generates appropriate feedback based on the generated control commands and the analyzed emotion data.

[1056] Based on the analysis results, a feedback message is generated, such as "The music has been quickly quieted down to provide a relaxing environment."

[1057] Input: Generated control command data, analyzed emotion data

[1058] Output: The generated feedback message

[1059] Step 6:

[1060] The server sends control commands to the API of the building equipment or physical store equipment to execute the control.

[1061] For example, sending a command to a music system's API to turn down the volume.

[1062] Input: Generated control command data

[1063] Output: Control action taken (music volume is reduced)

[1064] Step 7:

[1065] The server transmits the generated feedback to the terminal.

[1066] The generated feedback is sent to the terminal to provide a feedback message to the user.

[1067] Input: The generated feedback message

[1068] Output: Feedback message sent to the terminal

[1069] Step 8:

[1070] The terminal displays the received feedback message to the user.

[1071] For example, a message could appear on a smartphone screen saying, "The music volume has been lowered to provide a relaxing environment."

[1072] Input: Feedback message sent to the device

[1073] Output: The feedback message displayed to the user

[1074] 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.

[1075] 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.

[1076] 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.

[1077] [Fourth embodiment]

[1078] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1079] 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.

[1080] 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).

[1081] 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.

[1082] 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.

[1083] 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).

[1084] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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."

[1091] The present invention relates to a control system using natural language instructions in building facility management. A specific embodiment of this system will be described below.

[1092] This system is designed for efficient and smart building management, and allows users to issue instructions to building facilities in natural language. The system is mainly composed of three elements: a server, a terminal, and a user.

[1093] Server Roles

[1094] The server has the central function of analyzing received natural language instructions and generating control instructions for building facilities. It uses a generative model to analyze and interpret the natural language instructions received from the user. It then generates specific control instructions for the building facilities' APIs based on the interpreted instructions. In addition, the server monitors the status of the building facilities and provides feedback as needed.

[1095] For example, if a user instructs the server to "turn on the air conditioning in the conference room," the server analyzes the instruction, generates a control command to turn on the air conditioning, and sends this control command to the API of the air conditioning equipment to turn on the air conditioning.

[1096] Device Role

[1097] The terminal acts as a user interface, receiving natural language instructions from the user and sending them to the server, and also receiving feedback from the server and providing it to the user.

[1098] For example, if a user types "Turn on the air conditioning in the conference room" into a terminal, the command is sent to the server. When feedback is returned from the server, the terminal displays it to the user. The feedback is displayed as a message such as "The air conditioning has been turned on."

[1099] User Roles

[1100] The user is the entity that controls and manages the building facilities. The user inputs natural language instructions into the terminal and checks the operating status of the building facilities through feedback from the terminal.

[1101] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user can then confirm that the air conditioning has been turned on through feedback from the server.

[1102] Thus, the present invention provides a system for analyzing natural language instructions and controlling and managing building facilities. This system allows building managers and users to operate building facilities efficiently and easily. It also contributes to environmental protection by realizing control that improves the energy efficiency of buildings. Specific program processing steps will be described in detail as necessary.

[1103] The processing flow will be explained below.

[1104] Step 1:

[1105] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[1106] Step 2:

[1107] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[1108] Step 3:

[1109] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[1110] Step 4:

[1111] Based on the analysis results, the server generates control commands for the building's facilities, such as API commands to turn on the air conditioning equipment.

[1112] Step 5:

[1113] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[1114] Step 6:

[1115] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[1116] Step 7:

[1117] Based on the results of the check, the server generates a feedback message, such as "The air conditioning has been turned on."

[1118] Step 8:

[1119] The server sends the generated feedback message to the terminal.

[1120] Step 9:

[1121] The terminal receives the feedback message from the server and displays it to the user, who can then confirm through the terminal that the instruction has been executed correctly.

[1122] Example 1

[1123] 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."

[1124] Building facility management is complex and time-consuming, and is extremely inefficient, especially when there are many pieces of equipment, as each piece must be controlled individually. There is a need to solve this problem, improve the efficiency of building management, and further increase energy efficiency. Another challenge is to provide an interface that allows users to operate intuitively.

[1125] 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.

[1126] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, and means for transmitting the generated control instructions to the API of the building facilities, which enables users to intuitively control building facilities using natural language, thereby improving the efficiency of building management and energy efficiency.

[1127] "Natural language instructions" is an input format that allows a user to use ordinary language to perform operations or give instructions to a system.

[1128] A "generative AI model" is an algorithm automatically generated based on collected data, and is a machine learning model for analyzing and generating natural language.

[1129] "Analysis" refers to the process of understanding received information or data and analyzing its meaning and structure.

[1130] "Control instructions" refers to specific commands and instructions for operating and managing building facilities.

[1131] "API" is an abbreviation for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[1132] "Building facilities" refers to all equipment and systems used within a building (e.g., air conditioning, lighting, elevators, etc.).

[1133] "Terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) through which a user interacts with the system.

[1134] A "feedback message" is a message that the system uses to return operation results and status information to the user.

[1135] "Condition monitoring" is the process of monitoring the current state of building facilities in real time and detecting abnormalities or malfunctions.

[1136] A "sensor" is a device that detects physical conditions and acquires them as data.

[1137] "Energy efficiency" refers to the degree to which equipment and systems minimize the waste of energy they use and function efficiently.

[1138] This invention relates to a control system that uses natural language instructions in building facility management. A specific embodiment of this system will be described below. The main components are a server, a terminal, and a user.

[1139] Server embodiment

[1140] The server plays a central role in analyzing natural language instructions received from users and generating control instructions for building facilities. Specifically, it performs the following processes:

[1141] 1. The server parses the natural language instructions using a generative AI model (e.g., OpenAI's GPT-4). This model uses natural language processing techniques to interpret the user's input and understand their intent.

[1142] 2. The server generates specific control instructions for the APIs of the building facilities (e.g., air conditioning, lighting systems) based on the analyzed instructions. This generation is done using a program that constructs appropriate API calls based on the analysis results.

[1143] 3. The server sends the generated control command to the API of the building equipment. For example, it turns on the air conditioning by sending an HTTP request to the API endpoint of the air conditioning system.

[1144] 4. The server monitors the status of the building facilities and generates feedback messages as needed. It receives responses from the building facilities and generates user-friendly feedback messages (e.g., "The air conditioning has been turned on").

[1145] Terminal embodiment

[1146] The terminal functions as a user interface, receiving natural language instructions from the user and transmitting them to the server, and is also responsible for providing feedback from the server to the user.

[1147] 1. The user enters a natural language command using the device interface, for example, "Turn on the air conditioning in the conference room" using a smartphone, tablet PC, or PC.

[1148] 2. The terminal sends this instruction to the server using a communication protocol such as an HTTP POST request.

[1149] 3. When the server sends a feedback message, the device receives it and displays it to the user, for example, a message saying "The air conditioning has been turned on."

[1150] User's embodiment

[1151] The user is the entity that controls and manages the building equipment. They input natural language instructions into the terminal and check the operating status of the building equipment through feedback from the terminal.

[1152] Specifically, the user inputs "Turn on the air conditioning in the conference room" into the terminal. The server then analyzes the instruction, generates a control command, and turns on the air conditioning. The user then confirms that the air conditioning has been turned on through a feedback message displayed on the terminal.

[1153] Examples of concrete examples and prompts

[1154] For example, if a user wants to turn on the air conditioning in a conference room, he or she enters the following into the terminal:

[1155] Example prompt sentence:

[1156] "Turn on the air conditioning in the conference room."

[1157] The server receives this instruction, analyzes it using a generative AI model, and generates and executes an API call to "turn on the air conditioning." As a result, the air conditioning turns on and a feedback message such as "The air conditioning has been turned on" is displayed to the user on their device.

[1158] This concludes the detailed description of the preferred embodiment of the present invention, which allows users to control building equipment in an efficient and intuitive manner, while also improving the energy efficiency of buildings.

[1159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1160] Step 1: The user enters natural language instructions into the terminal.

[1161] The user inputs a natural language instruction into the terminal interface, such as "Turn on the air conditioning in the conference room." The input is in text format, and the terminal proceeds to the next step in that format. This input starts the system's processing.

[1162] Step 2: The device sends a natural language instruction to the server

[1163] The terminal sends the natural language instructions entered by the user to the server. Specifically, it uses a communication protocol such as an HTTP POST request to send the entered natural language instructions to the server as a payload. The input of this step is the user's instructions, and the output is an HTTP request to the server.

[1164] Step 3: The server receives and parses the natural language instructions

[1165] The server receives natural language instructions sent from the device. Based on the received data, it analyzes the instructions using a generative AI model (e.g., OpenAI's GPT-4). Specifically, it inputs the instructions into the model and extracts the resulting analysis data. The input for this step is the natural language instructions from the device, and the output is the analysis results.

[1166] Step 4: Server generates control commands

[1167] The server generates a control command for the building equipment based on the analyzed instructions. For example, based on the analysis result "Turn on the air conditioning in the conference room," it creates a specific command (e.g., an HTTP request) to send to the air conditioning system's API. The input to this step is the analysis result, and the output is the control command.

[1168] Step 5: The server sends the control command to the building equipment API

[1169] The server sends the generated control command to the building equipment's API. Specifically, it performs the operation of turning on the air conditioning by sending the generated HTTP request to the air conditioning system's API endpoint. The input to this step is the control command, and the output is an API request to the building equipment.

[1170] Step 6: The server receives feedback from the building equipment

[1171] The building equipment executes the control command from the server and feeds back the results to the server. The server receives this feedback and checks the processing results. For example, it receives feedback that "the air conditioning was successfully turned on." The input of this step is the feedback from the building equipment, and the output is the feedback data.

[1172] Step 7: Server generates feedback message

[1173] Based on the received feedback, the server generates a feedback message to inform the user. Specifically, it creates a message saying "The air conditioning has been turned on." The input of this step is the feedback data, and the output is the feedback message.

[1174] Step 8: The server sends a feedback message to the device

[1175] The server sends the generated feedback message to the terminal. The message is sent using an HTTP POST request, etc. The input of this step is the feedback message, and the output is an HTTP request to the terminal.

[1176] Step 9: The device displays a feedback message to the user

[1177] The terminal receives the feedback message sent from the server and displays it to the user. For example, the terminal screen displays "The air conditioning has been turned on." The input of this step is the feedback message from the server, and the output is the message displayed on the user interface.

[1178] The above is the specific processing flow of this system.

[1179] (Application example 1)

[1180] 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."

[1181] Conventional building facility management systems require manual control of facilities, requiring a great deal of time and effort. Furthermore, in brick-and-mortar stores, facilities need to be managed and controlled quickly and flexibly to improve customer comfort, but conventional systems have difficulty meeting this requirement. Furthermore, it has been difficult to centrally grasp the status of multiple facilities and control them efficiently. For this reason, there is a demand for a system that can control facilities with simple instructions in natural language and that can be operated instantly using smart devices.

[1182] 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.

[1183] In this invention, the server includes a means for analyzing natural language instructions using a generative model, a means for generating control instructions for building facilities based on the analyzed instructions, and a means for transmitting the generated control instructions to the API of the building facilities. This makes it possible to monitor the status of the building facilities and provide feedback to users. Furthermore, smart devices can be used to flexibly control facilities in physical stores, thereby improving customer comfort in the stores.

[1184] A "generative model" is an artificial intelligence model that analyzes a user's natural language instructions and generates appropriate control instructions.

[1185] "Natural language instructions" are instructions that users input in the same way as in everyday conversation, and are commands for controlling the facilities of buildings and stores.

[1186] "Building facilities" refers to various controlled objects within a building or store, such as air conditioning, lighting, and music.

[1187] "API" stands for Application Programming Interface, and refers to an interface that allows data to be exchanged between different software programs.

[1188] A "smart device" is a terminal with advanced functions that can connect to the Internet, such as a smartphone or smart glasses.

[1189] "Feedback" is the process of providing information about the execution results and current equipment status in response to instructions entered by the user.

[1190] A "brick and mortar store" is a store that exists in a physical location and that customers can visit in person.

[1191] "Customer comfort" means the degree of comfort felt by customers in a physical store due to the control of the equipment.

[1192] The present invention is a system for efficiently and comfortably managing facilities in a physical store. Specific embodiments of the system are described below.

[1193] Server Roles

[1194] The server has the central function of analyzing natural language instructions using a generative model and generating control instructions for store equipment. When a user inputs natural language instructions into a smart device (such as a smartphone or smart glasses), the instructions are sent to the server. The server then analyzes the natural language instructions using a generative AI model and converts them into appropriate control instructions. These control instructions are used to control store equipment such as lighting, air conditioning, and music. The server then sends these control instructions to the store equipment's API to manage the equipment's operation.

[1195] Device Role

[1196] The terminal functions as a user interface, receiving natural language instructions from the user and sending them to the server. It also provides feedback returned from the server to the user. For example, if a store manager types "It's 10 o'clock, so turn on the lights" into his smartphone, the instruction is sent directly to the server. When the server returns feedback saying "The lights are on," the content is displayed on the terminal, allowing the user to check the status of the equipment.

[1197] User Roles

[1198] Users are the entities that control and manage store equipment. They use smart devices to input natural language commands and check the equipment's operating status through feedback from the terminal. This allows for easy and quick equipment management.

[1199] Examples and prompts

[1200] For example, if a store manager inputs an instruction into the smart glasses, such as "We've seen an increase in customers. Please turn up the volume of the music in the store," the server analyzes this instruction and generates a control command to turn up the music volume. This control command is then sent to the API of the store's music equipment, which turns up the music volume. The result is then returned to the user as feedback, such as "The music volume has been turned up."

[1201] Thus, this invention is a system that uses smart devices to analyze natural language instructions and quickly and efficiently control equipment in a physical store. Specific hardware used includes smartphones and smart glasses, and software uses a generative AI model (e.g., OpenAI's API). An HTTP server is used for communication. This allows for easy operation in natural language and rapid equipment control.

[1202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1203] Step 1:

[1204] A user inputs natural language instructions into a smart device.

[1205] Input: A user types the natural language instruction "It's 10 o'clock, turn on the lights" into their smartphone.

[1206] What happens: A user enters natural language instructions using the voice or text input features of their smartphone.

[1207] Step 2:

[1208] The terminal sends a natural language instruction to the server.

[1209] Input: Natural language instructions entered into a smart device.

[1210] Output: Natural language instructions are sent to the server.

[1211] Specific operation: The terminal converts the input natural language instructions into packets and sends an HTTP request to the server.

[1212] Step 3:

[1213] The server uses a generative AI model to parse the natural language instructions.

[1214] Input: Natural language instruction data sent from the terminal.

[1215] Output: Parsed instructions (control commands).

[1216] Specific operation: The server calls a generative AI model (e.g., OpenAI API) to analyze natural language instructions and converts the instruction "It's 10 o'clock, so turn on the lights" into the control command "Turn on the lights."

[1217] Step 4:

[1218] The server generates control instructions for the building equipment based on the analyzed instructions.

[1219] Input: The analysis result obtained from the generative AI model (the control command "turn on the lights").

[1220] Output: Specific control instructions to send to the building equipment API.

[1221] Specific action: The server converts the control command into a format acceptable to the store equipment's API and prepares a specific API call to turn on the light.

[1222] Step 5:

[1223] The server sends the generated control instructions to the building equipment's API.

[1224] Input: API call for specific control instructions.

[1225] Output: Light fixture turns on.

[1226] Specific operation: The server sends the prepared control instructions as an HTTP request, calls the building equipment API, and turns on the lights.

[1227] Step 6:

[1228] It monitors the status of building facilities and sends feedback to the server.

[1229] Input: The operational state of the building equipment (lights turned on).

[1230] Output: Feedback information (confirmation that the light is on).

[1231] Specific operation: After the lighting equipment is turned on, the sensor detects its status and returns the information to the server via API.

[1232] Step 7:

[1233] The server sends feedback information to the terminal.

[1234] Input: Feedback information (confirmation that the light is on).

[1235] Output: Feedback information is sent to the terminal.

[1236] Specific operation: The server packets the feedback information and sends it to the terminal using an HTTP request.

[1237] Step 8:

[1238] The terminal provides feedback information to the user.

[1239] Input: Feedback information sent by the server.

[1240] Output: The user checks the feedback information.

[1241] Specific behavior: The device displays feedback information on the display and notifies the user that "The lights are on."

[1242] 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.

[1243] This invention combines a control system that uses natural language instructions to streamline building facility management with an emotion engine that recognizes user emotions. This system, in particular, has the function of analyzing natural language instructions using a generative model and generating control instructions for building facilities. The system also transmits the generated control instructions to the building facilities' API, monitors the facility's status, and provides appropriate feedback to the user. Furthermore, by incorporating the emotion engine, it is possible to recognize user emotions and provide appropriate control instructions and feedback.

[1244] Server Roles

[1245] The server plays a central role, analyzing the received natural language instructions and generating control instructions for the building facilities. It also uses an emotion engine to analyze the user's emotions and generate appropriate control instructions based on those emotions. It also monitors the status of the building facilities and provides feedback as needed.

[1246] For example, if a user issues an impatient command such as "Turn on the air conditioning in the conference room," the server will use its emotion engine to recognize the user's impatience, generate a control command to quickly turn on the air conditioning, and then generate a feedback message such as "The air conditioning has been turned on immediately" to alleviate the user's impatience.

[1247] Device Role

[1248] The device receives natural language instructions from the user and sends them to the server. It also receives feedback from the server and displays it to the user. Voice and text data that the emotion engine uses to recognize the user's emotions are also acquired through the device and sent to the server.

[1249] For example, if a user types "Turn on the air conditioning in the conference room" into the device, the instruction is sent to the server. When the server returns feedback, the device displays it to the user. Based on the emotion recognition results, the feedback is adjusted to something like "The air conditioning was turned on quickly."

[1250] User Roles

[1251] The user is the entity that controls and manages the building facilities. They input natural language commands into the terminal and receive feedback from the terminal. The emotion engine also recognizes the user's emotions and provides optimal control commands and feedback accordingly.

[1252] For example, if a user expresses irritation when requesting that the air conditioning be turned on before a meeting begins, the system will recognize that emotion and respond quickly. If the air conditioning is turned on quickly, the system will display feedback to the user, such as "The air conditioning was turned on quickly," to alleviate the irritation.

[1253] In this way, by incorporating an emotion engine, the system recognizes the user's natural language instructions and emotions, and provides appropriate control and feedback for building equipment. This system enables building managers and users to operate building equipment more efficiently and in a user-centered manner. It can also contribute to improving energy efficiency and early detection of malfunctions. Specific program processing steps will be explained in detail as necessary.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] The user inputs a natural language instruction, for example, "Turn on the air conditioning in the conference room" into the terminal.

[1257] Step 2:

[1258] The terminal receives natural language instructions from the user and transmits the instructions to the server, where the data is in the form of a string.

[1259] Step 3:

[1260] The server receives natural language instructions and passes them as input to a generative model for analysis. The generative model analyzes the instructions and extracts specific operation content.

[1261] Step 4:

[1262] The server uses an emotion engine to analyze the user's emotions from the natural language instructions sent, for example recognizing emotions such as irritation or joy from the tone of voice and sentences.

[1263] Step 5:

[1264] The server generates control commands for the building's facilities based on the analysis results. The results of the user's emotion recognition are also taken into account, so prompt responses and specific feedback are included. For example, if irritation is recognized, a quick response is required.

[1265] Step 6:

[1266] The server generates a control command and sends it to the building equipment's API, which then sends an instruction to turn on the air conditioning equipment.

[1267] Step 7:

[1268] The server checks the status of the building equipment and verifies whether the control was successful, specifically by checking whether the air conditioning is turned on correctly through feedback from sensors and equipment.

[1269] Step 8:

[1270] The server generates a feedback message based on the results, taking into account the user's emotions, such as "The air conditioning has been turned on quickly."

[1271] Step 9:

[1272] The server sends the generated feedback message to the terminal.

[1273] Step 10:

[1274] The terminal receives the feedback message from the server and displays it to the user, who can confirm through the terminal that the instruction was executed correctly. The content of the feedback message is adjusted according to the user's emotions.

[1275] Example 2

[1276] 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."

[1277] Efficient management is required for building facilities management, but conventional methods often fail to correctly understand user instructions and are unable to respond quickly. Furthermore, there is also the problem of a lack of appropriate feedback that takes into account the user's emotions, resulting in a decline in user satisfaction. In particular, a prompt and appropriate response is required for users who are feeling irritated or anxious, but such a response is difficult to achieve. Furthermore, early detection of building facility failures and improving energy efficiency have also been challenges.

[1278] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1279] In this invention, the server includes means for analyzing natural language instructions using a generative AI model, means for generating control instructions for building facilities based on the analyzed instructions, means for transmitting the generated control instructions to the building facilities' API, means for analyzing a user's emotions when analyzing the natural language instructions, means for adjusting the control instructions and feedback based on the analyzed emotions, means for monitoring the status of the building facilities, and means for providing feedback to the user. This allows the user's instructions to be correctly understood, enabling prompt and appropriate responses, thereby improving user satisfaction. It also enables early detection of building facilities failures and improved energy efficiency.

[1280] A "generative AI model" is an artificial intelligence model that analyzes natural language and generates appropriate control instructions and responses based on the results.

[1281] "Natural language instructions" refer to instructions provided by a user in spoken or text format that are written in language that is intuitively understandable to humans.

[1282] A "Building Facilities API" is an application programming interface for programmatically controlling building facilities (e.g., air conditioning, lighting, elevators, etc.).

[1283] An "emotion engine" is a technology or algorithm for analyzing emotions or emotional states from user-provided voice or text input.

[1284] "Feedback" is a response that the system provides to the user, including reporting how the user's instructions were processed.

[1285] "Means for monitoring the status of building facilities" refers to sensors and monitoring systems for detecting the operating status of building facilities and whether or not they have malfunctioned.

[1286] "Control instructions" are specific instructions generated by the system to operate building equipment, so that the equipment operates as expected.

[1287] This invention combines a control system that uses natural language instructions to improve the efficiency of building facility management with an emotion engine that recognizes user emotions. Detailed embodiments are described below.

[1288] Server Roles

[1289] The server is the central controller of the system. It first receives the natural language instructions sent by the device and analyzes them using a generative AI model (e.g., a publicly available natural language processing model) to understand exactly what the user wants.

[1290] The server then uses an emotion engine (e.g., a cloud-based emotion recognition service) to analyze the user's emotions. Based on the emotion recognition results, the server adjusts the appropriateness of the generated control instructions and feedback messages. In this way, it is possible to respond according to the user's level of frustration or satisfaction.

[1291] The server generates specific building equipment control instructions based on the analysis results and sends them to the building equipment's API, for example, to operate the air conditioning system or lighting system. It also checks the execution results of the control instructions, generates appropriate feedback messages, and sends them to the terminal.

[1292] Device Role

[1293] The terminal functions as a user interface. The user can use the terminal to input instructions in natural language. The input is sent to the server for processing. Instructions can be accepted in a variety of formats, including voice input and text input.

[1294] The terminal receives feedback from the server and displays it to the user, for example, a feedback message such as "The air conditioning was turned on quickly" so that the user can be sure that their instruction was carried out correctly.

[1295] User Roles

[1296] The user is the entity that uses this system to control the building equipment. They input instructions in natural language into the terminal and operate the equipment. They also check feedback from the server and issue instructions again if necessary to manage the equipment status.

[1297] Specific examples

[1298] As a concrete example, consider the following scenario.

[1299] The user inputs "Turn on the air conditioning in the conference room" into the device. This command is sent from the device to the server. The server analyzes this command using a generative AI model and generates a control command to turn on the air conditioning.

[1300] At the same time, the emotion engine recognizes the user's frustration. The server determines that this frustration requires a quick response, generates a command to "quickly turn on the air conditioning" and sends it to the building equipment's API. After the air conditioning is turned on, the server generates a feedback message saying "The air conditioning has been turned on quickly" and sends it to the device. The user confirms this feedback on the device and understands that the command was processed appropriately.

[1301] Prompt Sentence Examples

[1302] User command: "Turn on the air conditioning in the conference room."

[1303] Context to analyze: A user issues a command to turn on the air conditioning in a conference room. If this command is accompanied by irritation, a quick response is required.

[1304] Emotion recognition result: Irritated

[1305] Generate control instructions: Quickly turn on air conditioning.

[1306] Feedback message: "Air conditioning turned on quickly"

[1307] In this way, the system of the present invention recognizes the user's natural language commands and emotions, and provides appropriate control and feedback for building facilities. This enables building managers and users to operate building facilities more efficiently and in a user-centered manner. It also contributes to improving energy efficiency and early detection of malfunctions.

[1308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1309] Step 1:

[1310] The user inputs a natural language command into the device, for example, "Turn on the air conditioning in the conference room," either by speaking or by typing it into the device.

[1311] Input: User's natural language instructions

[1312] Output: Voice or text input data to the device

[1313] Step 2:

[1314] The device receives the user's natural language instructions and transmits the data to the server using HTTP requests over the network.

[1315] Input: Voice or text input data

[1316] Output: HTTP request to the server

[1317] Step 3:

[1318] The server inputs the received natural language instructions into a generative AI model, which analyzes the instructions and identifies the specific action the user wants to take (e.g., turn on the air conditioning).

[1319] Input: HTTP request received by the server

[1320] Output: Parsed instructions

[1321] Step 4:

[1322] The server uses an emotion engine to analyze the emotion contained in the user's natural language instructions, and this process provides emotional information such as whether the user is annoyed.

[1323] Input: Natural language instruction data

[1324] Output: Sentiment analysis result (e.g., irritated)

[1325] Step 5:

[1326] The server generates appropriate building facility control instructions based on the analysis results. For example, if a user is frustrated, a control instruction is generated that calls for a quick response.

[1327] Input: Analyzed instructions and sentiment analysis results

[1328] Output: Generated control instructions

[1329] Step 6:

[1330] The server sends the generated control instructions to the API of the building equipment, for example, via an HTTP request via a REST API.

[1331] Input: Generated control instructions

[1332] Output: API request to building equipment

[1333] Step 7:

[1334] The server receives the response from the building equipment API and checks whether the control was successful. If the control was successful, the next step is to generate a feedback message.

[1335] Input: API response from building equipment

[1336] Output: Check the control results

[1337] Step 8:

[1338] The server generates an appropriate feedback message and sends it to the device, taking into account the sentiment analysis results, for example, generating a message such as "The air conditioning was quickly turned on."

[1339] Input: Control results and sentiment analysis results

[1340] Output: The generated feedback message

[1341] Step 9:

[1342] The terminal receives the feedback message from the server and displays it to the user, who can see that the instruction has been executed correctly.

[1343] Input: Feedback message from the server

[1344] Output: Display feedback to the user

[1345] Through the above processing steps, the user's natural language instructions are correctly analyzed, appropriate control instructions are generated, and building facilities are operated, resulting in the user receiving prompt and accurate feedback in accordance with their instructions.

[1346] (Application example 2)

[1347] 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."

[1348] Conventional facility management systems for buildings and brick-and-mortar stores control equipment based on users' natural language instructions, but do not take the user's emotions into consideration. This means that appropriate feedback is not provided to the user, resulting in frustration and inconvenience for the user. Furthermore, in brick-and-mortar stores, equipment control based on the emotions of users and store staff is required, but current systems lack such functionality. Furthermore, there is also room for improvement in terms of optimizing energy efficiency to achieve efficient equipment control.

[1349] 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.

[1350] In this invention, the server includes means for analyzing natural language instructions using a generative model, means for generating control instructions for building facilities based on the analyzed instructions, means for sending the generated control instructions to the building facilities' API, means for analyzing user emotions using an emotion engine and generating control instructions and feedback according to the emotions, and means for controlling various facilities (lighting, air conditioning, music, etc.) in the physical store. This enables quick and appropriate control of facilities and provision of feedback that takes user emotions into consideration, thereby improving user satisfaction and optimizing energy efficiency.

[1351] A "generative model" is an artificial intelligence technology that analyzes natural language instructions and generates appropriate control instructions based on their content.

[1352] "Natural language instructions" are commands or requests entered by the user in everyday language, and by analyzing these, instructions for operating various devices are extracted.

[1353] "Building facilities" refers to the various devices and systems installed within a building, including air conditioning, lighting, elevators, etc.

[1354] A "control instruction" is a command or instruction that causes building facilities or physical store equipment to perform a specific operation based on the analyzed natural language instruction.

[1355] "API" stands for Application Programming Interface, an interface for exchanging data and functions between software programs.

[1356] An "emotion engine" is a technology that analyzes emotions from a user's voice or text and generates appropriate feedback and control instructions based on those emotions.

[1357] "Feedback" refers to a response or result report from the system to an instruction from the user, and notifies the user whether the instruction was processed correctly.

[1358] "Brick and mortar store" refers to a physical commercial establishment or retail outlet, including lighting, air conditioning, music, and other amenities.

[1359] This invention provides a system that combines natural language instruction analysis and emotion recognition to improve the efficiency of facility management in buildings and brick-and-mortar stores. This system operates in three roles: server, terminal, and user.

[1360] Server Roles

[1361] The server plays a central role and has the following functions:

[1362] Function to analyze natural language instructions using generative models: Analyzes natural language instructions sent by the user and converts them into specific control commands. For example, if a user instructs the robot to "dim the lights in the store a little," the robot analyzes this instruction and generates a lighting control command.

[1363] Emotion analysis function using emotion engine: Recognizes emotions from the user's voice or text and generates appropriate control instructions and feedback based on those emotions. For example, if the emotion engine determines that the user is irritated, it will respond quickly and generate feedback such as "The lights have been dimmed immediately" to alleviate the user's irritation.

[1364] A function to send control instructions to the APIs of various facilities in buildings and physical stores: The generated control commands are sent to the APIs of the building facilities and physical store facilities, and the actual control is performed.

[1365] Function to monitor equipment status and provide feedback: Monitor the status of each piece of equipment, detect faults and provide feedback to the user.

[1366] Device Role

[1367] The device is responsible for receiving natural language instructions from the user and sending them to the server. Specifically:

[1368] A natural language instruction entered by the user is sent to the server.

[1369] Receives feedback from the server and displays it to the user.

[1370] Voice and text data for emotion recognition is collected and sent to a server.

[1371] For example, if the device is a smartphone, when the user inputs an instruction such as "Adjust the air conditioning in the store," the device sends this to the server and displays feedback from the server to the user, such as "The air conditioning has been adjusted."

[1372] User Roles

[1373] The user is the entity that operates the system, controlling and managing the facilities of the building or physical store. The user inputs instructions in natural language and receives feedback from the device. The emotion engine recognizes emotions and provides optimal feedback and control instructions.

[1374] For example, if a user says, "The music is too loud, please be quieter. I'm very tired," the server analyzes the instruction, generates a command to lower the music volume, and provides feedback such as, "The music volume has been lowered. We will provide you with a relaxing environment."

[1375] Hardware and software used

[1376] Hardware: Users use smartphones, tablets, or in-store interactive displays.

[1377] Software: Uses emotion recognition engines (e.g., Microsoft Azure Emotion API), natural language processing engines (e.g., OpenAI GPT-3).

[1378] Examples of concrete examples and prompts

[1379] To illustrate, consider the following scenario:

[1380] scenario

[1381] If the store is a little noisy and a customer says, "Please make the music quieter in the store, I'm very tired."

[1382] Prompt Sentence Examples

[1383] User Input: Please make the music quieter in the store, I'm so tired

[1384] Objective: Recognize the user's emotions, generate control instructions to lower the music volume, and provide appropriate feedback to the user.

[1385] This invention makes it possible to control equipment quickly and appropriately and provide feedback that takes into account the user's feelings, thereby improving user satisfaction and optimizing energy efficiency.

[1386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1387] Step 1:

[1388] A user enters natural language instructions into a terminal.

[1389] As a specific example, the user uses a smartphone to input instructions via voice or text, such as "Please turn down the music in the store; I'm very tired."

[1390] Input: User's natural language instructions (voice or text)

[1391] Output: Natural language instructions entered into the terminal

[1392] Step 2:

[1393] The terminal transmits the input natural language instruction to the server.

[1394] The terminal is responsible for receiving user instruction data and transmitting it to the server.

[1395] Input: Natural language instruction data entered into the terminal

[1396] Output: Natural language instructions sent to the server

[1397] Step 3:

[1398] The server analyzes the received natural language instructions using a generative model.

[1399] For the analysis, a generative AI model (e.g., OpenAI GPT-3) is used to analyze the user's instructions and generate specific control commands.

[1400] Input: Natural language instructions sent to the server

[1401] Output: Generated control command data

[1402] Step 4:

[1403] The server analyzes the user's emotions using an emotion engine.

[1404] Using natural language instruction data as input, an emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's emotions.

[1405] Input: Natural language instruction data

[1406] Output: Parsed emotion data

[1407] Step 5:

[1408] The server generates appropriate feedback based on the generated control commands and the analyzed emotion data.

[1409] Based on the analysis results, a feedback message is generated, such as "The music has been quickly quieted down to provide a relaxing environment."

[1410] Input: Generated control command data, analyzed emotion data

[1411] Output: The generated feedback message

[1412] Step 6:

[1413] The server sends control commands to the API of the building equipment or physical store equipment to execute the control.

[1414] For example, sending a command to a music system's API to turn down the volume.

[1415] Input: Generated control command data

[1416] Output: Control action taken (music volume is reduced)

[1417] Step 7:

[1418] The server transmits the generated feedback to the terminal.

[1419] The generated feedback is sent to the terminal to provide a feedback message to the user.

[1420] Input: The generated feedback message

[1421] Output: Feedback message sent to the terminal

[1422] Step 8:

[1423] The terminal displays the received feedback message to the user.

[1424] For example, a message could appear on a smartphone screen saying, "The music volume has been lowered to provide a relaxing environment."

[1425] Input: Feedback message sent to the device

[1426] Output: The feedback message displayed to the user

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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).

[1434] 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.

[1435] 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."

[1436] 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.

[1437] 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).

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] The following is further disclosed regarding the above embodiment.

[1449] (Claim 1)

[1450] means for parsing the natural language instruction using a generative model;

[1451] means for generating control instructions for building equipment based on the analyzed instructions;

[1452] means for transmitting the generated control instructions to the API of the building equipment;

[1453] a means for monitoring the condition of building equipment;

[1454] a means for providing feedback to the user;

[1455] A system including:

[1456] (Claim 2)

[1457] The system according to claim 1, characterized in that the building equipment status monitoring means uses sensors to detect failures in each building equipment.

[1458] (Claim 3)

[1459] 10. The system of claim 1, wherein the generated control instructions are for improving the energy efficiency of the building.

[1460] "Example 1"

[1461] (Claim 1)

[1462] a means for inputting natural language instructions;

[1463] means for transmitting the input natural language instructions to a server;

[1464] a means for parsing the natural language instruction using a generative AI model;

[1465] means for generating control instructions for building equipment based on the analyzed instructions;

[1466] means for transmitting the generated control instructions to the API of the building equipment;

[1467] a means for monitoring the condition of building equipment;

[1468] means for generating a feedback message;

[1469] means for transmitting the generated feedback message to the terminal;

[1470] means for displaying a feedback message to the user;

[1471] A system including:

[1472] (Claim 2)

[1473] The system according to claim 1, characterized in that the building equipment status monitoring means uses sensors to detect failures in each building equipment.

[1474] (Claim 3)

[1475] 10. The system of claim 1, wherein the generated control instructions are for improving the energy efficiency of the building.

[1476] "Application Example 1"

[1477] (Claim 1)

[1478] means for parsing the natural language instruction using a generative model;

[1479] means for generating control instructions for building equipment based on the analyzed instructions;

[1480] means for transmitting the generated control instructions to the API of the building equipment;

[1481] a means for monitoring the condition of building equipment;

[1482] a means for providing feedback to the user;

[1483] A means for controlling equipment in a physical store using a smart device;

[1484] A system including:

[1485] (Claim 2)

[1486] The system according to claim 1, characterized in that the smart device is a smartphone or smart glasses.

[1487] (Claim 3)

[1488] 2. The system of claim 1, wherein the generated control instructions are for improving customer comfort in the store.

[1489] "Example 2: Combining Emotion Engines"

[1490] (Claim 1)

[1491] a means for parsing the natural language instruction using a generative AI model;

[1492] means for generating control instructions for building equipment based on the analyzed instructions;

[1493] means for transmitting the generated control instructions to the API of the building equipment;

[1494] means for analyzing a user's sentiment when parsing the natural language instructions;

[1495] a means for adjusting control instructions or feedback based on the analyzed emotions;

[1496] a means for monitoring the condition of building equipment;

[1497] a means for providing feedback to the user;

[1498] A system including:

[1499] (Claim 2)

[1500] The system according to claim 1, characterized in that the building equipment status monitoring means uses sensors to detect failures in each building equipment.

[1501] (Claim 3)

[1502] 10. The system of claim 1, wherein the generated control instructions are for improving the energy efficiency of the building.

[1503] "Application example 2 when combining emotion engines"

[1504] (Claim 1)

[1505] means for parsing the natural language instruction using a generative model;

[1506] means for generating control instructions for building equipment based on the analyzed instructions;

[1507] means for transmitting the generated control instructions to the API of the building equipment;

[1508] a means for monitoring the condition of building equipment;

[1509] a means for providing feedback to the user;

[1510] means for analyzing a user's emotions using an emotion engine and generating control instructions and feedback according to the emotions;

[1511] A means to control various facilities in physical stores (lighting, air conditioning, music, etc.)

[1512] A system including:

[1513] (Claim 2)

[1514] The system according to claim 1, characterized in that the building equipment status monitoring means uses sensors to detect failures in each building equipment.

[1515] (Claim 3)

[1516] 10. The system of claim 1, wherein the generated control instructions are for improving the energy efficiency of the building. [Explanation of symbols]

[1517] 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 parsing the natural language instruction using a generative model; means for generating control instructions for building equipment based on the analyzed instructions; means for transmitting the generated control instructions to the API of the building equipment; a means for monitoring the condition of building equipment; a means for providing feedback to the user; A system including:

2. 2. The system according to claim 1, wherein the building equipment status monitoring means uses sensors to detect failures in each building equipment.

3. 10. The system of claim 1, wherein the generated control instructions are for improving the energy efficiency of the building.

Images