Computer program, information processing method, information processing system, and air conditioner

Abstract

Provided are a computer program, an information processing method, an information processing system, and an air conditioner.　In the present invention, feedback on a degree of comfort from a plurality of users staying in a space air-conditioned by an air conditioner is collected, at least one of reliability and priority of the collected feedback from each of the users is evaluated using a generative AI model, and, if there is a difference in the feedback among the plurality of users, a control parameter for the air conditioner is adjusted with reference to the at least one of the reliability and the priority evaluated using the generative AI model.

Description

Computer Program, Information Processing Method, Information Processing System, and Air Conditioner

[0001] The present disclosure relates to a computer program, an information processing method, an information processing system, and an air conditioner.

[0002] Patent Literature 1 discloses an air conditioner system that acquires a user's comfort level regarding temperature and humidity, and in which a control determination unit determines control details such as air volume and air direction in consideration of the comfort level.

[0003] Japanese Unexamined Patent Publication No. 2020-198498

[0004] In Patent Literature 1, when there are a plurality of users using the same room, appropriate control cannot be performed.

[0005] An object of the present disclosure is to provide a computer program, an information processing method, an information processing system, and an air conditioner that can adjust control parameters for the air conditioner based on feedback from a plurality of users.

[0006] A computer program according to a first aspect of the present disclosure is a computer program for causing a computer to execute processing of: collecting feedback regarding comfort level from a plurality of users staying in a space air-conditioned by an air conditioner; evaluating at least one of reliability and priority of the collected feedback from each user using a generative AI model; and when there is a difference in the feedback among the plurality of users, adjusting a control parameter for the air conditioner with reference to at least one of the reliability and priority evaluated using the generative AI model.

[0007] A computer program according to a second aspect of the present disclosure is the computer program according to the first aspect, and causes the computer to execute processing of adjusting the control parameter for the air conditioner such that an intermediate comfort level is achieved among a plurality of users whose reliability or priority is relatively high.

[0008] The computer program relating to the third aspect of this disclosure causes the computer to perform a process to adjust control parameters for the air conditioner in order to improve the level of comfort of a particular user whose reliability or priority is relatively high, as described in the computer program relating to the first or second aspect.

[0009] The computer program relating to the fourth aspect of this disclosure causes the computer to perform a process in which it recollects feedback from the multiple users and readjusts the control parameters based on the recollected feedback, in addition to the computer program relating to any one of the first to third aspects.

[0010] The computer program relating to the fifth aspect of this disclosure causes the computer to perform a process of collecting feedback from each user by performing an interactive process with a user terminal used by each user, in a computer program relating to any one of the first to fourth aspects.

[0011] The computer program relating to the sixth aspect of this disclosure is a computer program relating to any one of the first to fifth aspects, wherein the dialogue processing includes generating questions using the generation AI model to confirm the level of comfort of the air conditioning provided by the air conditioner, sending the generated questions to each user's user terminal, and receiving each user's answers to the questions from each user's user terminal.

[0012] The computer program relating to the seventh aspect of this disclosure, in a computer program relating to any one of the first to sixth aspects, causes the computer to perform a process to convert the collected feedback information regarding the degree of comfort into numerical information using the generating AI model if the feedback information is non-numerical.

[0013] The computer program relating to the eighth aspect of this disclosure collects at least one of each user's feedback history, each user's biometric information, and the environmental information of the space, and causes the computer to perform a process of evaluating the reliability of feedback from each user using the generated AI model that refers to at least one of the collected feedback history, biometric information, and environmental information.

[0014] A computer program relating to the ninth aspect of this disclosure collects at least one of the user's stay time in the space, the feedback history from each user, and the feedback timing, and causes the computer to perform a process of evaluating the priority of the feedback from each user using the generated AI model which refers to at least one of the collected stay time, feedback history, and feedback timing.

[0015] The information processing method relating to the tenth aspect of this disclosure includes collecting feedback on the degree of comfort from multiple users staying in a space air-conditioned by an air conditioner, evaluating at least one of the reliability and priority of the collected user feedback using a generating AI model, and if there are differences in the feedback among the multiple users, performing a process by at least one computer to adjust the control parameters for the air conditioner by referring to at least one of the reliability and priority evaluated using the generating AI model.

[0016] The information processing system relating to the eleventh aspect of this disclosure comprises at least one processing unit, which collects feedback on the degree of comfort from multiple users staying in a space air-conditioned by an air conditioner, evaluates at least one of the reliability and priority of the collected user feedback using a generating AI model, and adjusts the control parameters for the air conditioner by referring to at least one of the reliability and priority evaluated using the generating AI model if there are differences in the feedback among the multiple users.

[0017] The air conditioner relating to the twelfth aspect of this disclosure is an air conditioner that air conditions a target space, the air conditioner collects feedback on the degree of comfort from multiple users staying in the target space, evaluates at least one of the reliability and priority of the feedback collected from each user using a generative AI model, and adjusts the control parameters in the unit by referring to at least one of the reliability and priority evaluated using the generative AI model if there are differences in the feedback among the multiple users.

[0018] According to this disclosure, control parameters for air conditioners can be adjusted based on feedback from multiple users.

[0019] This is a schematic diagram showing the overall configuration of an air conditioning system according to an embodiment. This is a block diagram showing the configuration of the air conditioning control system. This is a block diagram showing the configuration of the user terminal control system. This is a block diagram showing the configuration of the first server control system. This is a block diagram showing the configuration of the second server control system. This is a diagram illustrating an example of dialogue during feedback collection. This is a diagram showing an example of prompts used for conversion to numerical representation. This is a conceptual diagram showing an example of a user table that stores user-specific feedback regarding comfort level. This is a diagram showing an example of prompts used for reliability evaluation. This is a diagram showing an example of prompts used for priority evaluation. This is a flowchart showing the procedure of processing executed by the first server.

[0020] The information processing system according to the embodiment will be described in detail below with reference to the drawings. Figure 1 is a schematic diagram showing the overall configuration of the air conditioning system according to the embodiment. The air conditioning system 1 according to the embodiment comprises an air conditioner 100 and a user terminal 200. The air conditioner 100 and the user terminal 200 are connected to each other via a local communication network NW1 such as Wi-Fi (registered trademark).

[0021] The air conditioner 100 is a household or commercial air conditioner for adjusting the temperature, humidity, air cleanliness, etc., of a room, and comprises an indoor unit and an outdoor unit. The air conditioner 100 adjusts the temperature, humidity, etc., of a room by operating in accordance with control commands output from a remote controller 150 or a user terminal 200.

[0022] The user terminal 200 is a device such as a smartphone, tablet, personal computer, or smart speaker operated by the user of the air conditioner 100. The user terminal 200 is equipped with artificial intelligence (AI). The artificial intelligence installed in the user terminal 200 is constructed by the artificial intelligence model MD2, which generates new content in response to inputs such as text, voice, still images, and videos. The artificial intelligence model MD2 may be a proprietary model that has been fine-tuned and / or distilled (lightened) for a specific application. The content generated by the artificial intelligence model MD2 includes text, sound such as voice or music, and images such as still images or videos. The user terminal 200 can create the indoor environment desired by the user by using the artificial intelligence to interact with the user, generate control commands for the air conditioner 100, and control the operation of the air conditioner 100 based on the generated control commands.

[0023] In the example shown in Figure 1, there is one user terminal 200, but there may be multiple user terminals 200 capable of controlling the air conditioner 100.

[0024] The air conditioning system 1 may further include an air purifier 151, a circulator 152, a diffuser 153, lighting equipment 154, and sound equipment 155. The air purifier 151 is a device for purifying the indoor air and providing clean air. The circulator 152 is a device for circulating the indoor air. The diffuser 153 is a device for diffusing fragrance. The lighting equipment 154 is a device for illuminating the indoor space. The sound equipment 155 is a device for playing music, ambient sounds, etc. These devices 151 to 155 are connected to at least one of the air conditioner 100 and the user terminal 200 via a communication network NW1 so as to be able to communicate.

[0025] The air conditioning system 1 may further include a wearable device 250 worn by the user. The wearable device 250 measures, for example, at least one of the user's heart rate, body temperature, sweating, blood pressure, respiration, brain waves, and body composition, and outputs the measurement results as the user's biometric information. The output destination may be the air conditioning unit 100 or the user terminal 200.

[0026] The air conditioning system 1 may further include a first server 310 or a second server 320 accessible from the air conditioner 100 or a user terminal 200. The air conditioner 100 or the user terminal 200 and the first server 310 or the second server 320 are connected to each other via an external communication network NW2, such as the Internet.

[0027] The first server 310 is equipped with a generative AI. The generative AI in the first server 310 is constructed by a generative AI model MD3 that generates new content in response to inputs such as text, audio, still images, and videos. The generative AI model MD3 may include existing models such as GPT (Generative Pretrained Transformer, registered trademark), BERT (Bidirectional Encoder Representations from Transformers), GAN (Generative Adversarial Network), Wave Net, DALL-E, and Stable Diffusion, or it may be a unique model that has been fine-tuned for a specific application from an existing model. The first server 310 generates content such as text, audio, still images, and videos in response to a request from the air conditioner 100 or user terminal 200, and returns the generated content to the requester.

[0028] The second server 320 is a search server that searches for relevant documents or information in response to an input query and returns the relevant documents or information to the requester. Existing search engines such as vector search are used to search for relevant documents and information. In one example, the second server 320 is a general-purpose search server that returns search results in response to external search requests. Alternatively, the second server 320 may be a dedicated search server that can access a database DB that stores information such as operation manuals, service guides, technical handbooks, installation instructions, customer information, operation data during trial operation, and operation data after the start of operation for the air conditioner 100, and searches the database DB in response to external search requests and returns the search results to the requester. The database DB may also register construction information when the air conditioner 100 was installed (installation location of indoor and outdoor units, piping length, floor plan, year of construction), information about the installed air conditioner 100 (model, Ua value, horsepower, etc.), and sales information for each employee.

[0029] The air conditioning system 1 according to the embodiment implements the information processing method described herein by utilizing at least one of the generation AI model MD2 installed on the user terminal 200 and the generation AI model MD3 installed on the first server 310. This information processing method may be implemented using only the content output from the generation AI model MD2 installed on the user terminal 200, or it may be implemented using only the content output from the generation AI model MD3 installed on the first server 310.

[0030] Furthermore, the information processing method disclosed herein may be realized through cooperation between the generation AI model MD2 installed on the user terminal 200 and the generation AI model MD3 installed on the first server 310.

[0031] Furthermore, the information processing method disclosed herein may be implemented using a RAG (Retrieval-Augmented Generation) mechanism. That is, in response to an input query from the air conditioner 100 or user terminal 200, the second server 320 may output documents or information related to the input query, and the first server 310 may generate content based on the documents or information output from the second server 320 and return the content to the air conditioner 100 or user terminal 200. By using a RAG mechanism, more accurate and relevant content can be provided.

[0032] In this embodiment, the user terminal 200 is configured to be equipped with the generation AI model MD2. Alternatively, the generation AI model may be equipped on the air conditioner 100. In this case, the information processing method of this disclosure may be implemented using the generation AI model MD1 (see Figure 2) equipped on the air conditioner 100. Furthermore, the information processing method of this disclosure may be implemented by the cooperation of the generation AI model MD1 of the air conditioner 100 and the generation AI model MD3 of the first server 310.

[0033] Furthermore, both the air conditioner 100 and the user terminal 200 may be equipped with generation AI models. In this case, at least two of the generation AI models MD1 of the air conditioner 100, MD2 of the user terminal 200, and MD3 of the first server 310 may work together to realize the information processing method of this disclosure.

[0034] Figure 2 is a block diagram showing the configuration of the control system of the air conditioner 100. The air conditioner 100 comprises a control unit 101, a storage unit 102, a communication unit 103, a sensor unit 104, and a drive unit 110.

[0035] The control unit 101 includes a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and the like. The ROM in the control unit 101 stores control programs for controlling the operation of the drive unit 110. The CPU in the control unit 101 executes the control programs stored in the ROM and various computer programs stored in the memory unit 102, and controls the operation of the drive unit 110, thereby making the entire device function as the air conditioner 100 in this disclosure.

[0036] The storage unit 102 is equipped with a storage device such as flash memory. The storage unit 102 stores various computer programs to be executed by the control unit 101, as well as data necessary for the execution of these programs.

[0037] The computer program (program product) stored in the memory unit 102 includes a control program PG1 for realizing the information processing method of this disclosure. The control program PG1 may be a single computer program or a group of programs composed of multiple computer programs. The control program PG1 may be executed collaboratively by multiple computers.

[0038] The computer program, including the control program PG1, is provided, for example, on a non-temporary recording medium RM1 on which the computer program is recorded in a readable format. The recording medium RM1 is a portable memory such as a CD-ROM, USB memory, SD card, microSD card, or CompactFlash®. The control unit 101 reads various computer programs from the recording medium RM1 using a reading device (not shown in the figure) and stores the read computer programs in the storage unit 102. The computer programs stored in the storage unit 102 may also be provided via communication. In this case, the control unit 101 acquires the computer programs via communication through the communication unit 103 and stores the acquired computer programs in the storage unit 102.

[0039] The data stored in the memory unit 102 may include at least one of the following: an operation manual, a service guide, a technical handbook, installation instructions, customer information, operational data during commissioning, and operational data after the start of operation.

[0040] When the air conditioner 100 is equipped with a generation AI, the generation AI model MD1 that constructs the generation AI is stored in the memory unit 102. The generation AI model MD1 is a model that generates new content in response to inputs such as text, voice, still images, and videos. The content generated by the generation AI model MD1 includes text, sound such as voice or music, and images such as still images or videos. The generation AI model MD1 is a unique model that has been fine-tuned and / or distilled (lightened) for a specific application from existing models such as GPT (registered trademark), BERT, GAN, Wave Net, DALL-E, and Stable Diffusion. The generation AI model MD1 may be a multimodal model, or it may be a unimodal language model that outputs a response (text) in response to the input of a prompt (text).

[0041] The communication unit 103 is equipped with a communication interface for communicating with the user terminal 200 and the like. The communication interface provided by the communication unit 103 can be a communication interface compliant with a wireless LAN (Local Area Network) communication standard such as Wi-Fi (registered trademark). Alternatively, a communication interface compliant with a short-range wireless communication standard such as Bluetooth may be used. In addition to the user terminal 200, the communication unit 103 may be configured to communicate with an air purifier 151, a circulator 152, a diffuser 153, lighting equipment 154, sound equipment 155, and the like.

[0042] The communication unit 103 may further include a communication interface for communicating with the first server 310 or the second server 320. Such a communication interface can be a wireless communication interface such as Wi-Fi®, 3G, 4G, 5G, or LTE (Long Term Evolution).

[0043] The sensor unit 104 includes one or more sensors that measure various physical quantities in an indoor environment or the user's condition. The sensors included in the sensor unit 104 include sensors that measure at least one of indoor temperature, humidity, heat, CO₂ concentration, and illuminance. The sensor unit 104 may also include sensors that measure the user's movement, facial expression, and the like.

[0044] The drive unit 110 includes a compressor 111, a four-way switching valve 112, an indoor fan 113, a flap 114, and the like. The compressor 111 is a device for sucking in a constant-temperature low-pressure gaseous refrigerant and compressing it into a high-temperature high-pressure gas. During cooling operation, the refrigerant compressed by the compressor 111 returns to the suction side of the compressor 111 via the outdoor heat exchanger, the expansion valve, the first indoor heat exchanger, the solenoid valve, and the second indoor heat exchanger. In this refrigeration cycle, heat is dissipated by the outdoor heat exchanger functioning as a condenser, and indoor air is cooled by the first and second indoor heat exchangers functioning as evaporators to perform cooling. During heating operation, the four-way switching valve 112 switches the refrigerant path, and heating is performed in a cycle reverse to that in cooling operation.

[0045] The indoor fan 113 is a device for evenly circulating cooled air or warmed air throughout the room. The air volume of the indoor fan 113 is controlled by a control command from the control unit 101. By adjusting the air volume of the indoor fan 113, the efficiency of cooling and heating can be improved, and energy consumption can be reduced.

[0046] The flap 114 is a device for adjusting the direction of air blown out from the air conditioner 100. The orientation of the flap 114 is controlled by a control command from the control unit 101. By ensuring an appropriate air flow through the flap 114, the efficiency of cooling and heating can be improved, and energy consumption can be reduced.

[0047] FIG. 3 is a block diagram showing the configuration of a control system of the user terminal 200. The user terminal 200 is a terminal device such as a smartphone, a tablet terminal, a personal computer, or a smart speaker, and includes a control unit 201, a storage unit 202, a communication unit 203, an imaging unit 204, a voice input unit 205, a voice output unit 206, a positioning unit 207, an operation unit 208, a display unit 209, and the like.

[0048] The control unit 201 includes a CPU, a ROM, a RAM, and the like. The ROM included in the control unit 201 stores a control program and the like for controlling the operation of each hardware unit included in the user terminal 200. The CPU in the control unit 201 reads and executes the control program stored in the ROM and the computer program stored in the storage unit 202, and controls the operation of each of the above hardware units, thereby causing the entire apparatus to function as the user terminal 200 of the present disclosure. The RAM included in the control unit 201 temporarily stores data used during the execution of calculations.

[0049] In the embodiment, the control unit 201 is configured to include a CPU, a ROM, and a RAM. Alternatively, the control unit 201 may be, for example, one or more control circuits or processing circuits including a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, a volatile or non-volatile memory, or the like. Further, the control unit 201 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given to when a measurement end instruction is given, and a counter that counts numbers.

[0050] The storage unit 202 includes a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 202 stores various computer programs executed by the control unit 201 and various data used by the control unit 201.

[0051] The computer program (program product) stored in the memory unit 202 includes a control program PG2 for realizing the information processing method of the present disclosure. The control program PG2 may be a single computer program or a group of programs composed of multiple computer programs. The control program PG2 may be executed collaboratively by multiple computers. For example, the information processing method of the present disclosure may be realized by the collaboration of a control program PG1 installed in the air conditioner 100 and a control program PG2 installed in the user terminal 200.

[0052] The computer program, including the control program PG2, is provided, for example, on a non-temporary recording medium RM2 on which the computer program is recorded in a readable format. The recording medium RM2 is a portable memory such as a CD-ROM, USB memory, SD card, microSD card, or CompactFlash®. The control unit 201 reads various computer programs from the recording medium RM2 using a reading device (not shown in the figure) and stores the read computer programs in the storage unit 202. The computer programs stored in the storage unit 202 may also be provided via communication. In this case, the control unit 201 acquires the computer programs via communication through the communication unit 203 and stores the acquired computer programs in the storage unit 202.

[0053] The memory unit 202 may include a generation AI model MD2. The generation AI model MD2 is a model that generates new content in response to inputs such as text, voice, still images, and videos. The content generated by the generation AI model MD2 includes text, sound such as voice or music, and images such as still images or videos. The generation AI model MD2 is a unique model that has been distilled (lightened) for a specific purpose from existing models such as GPT®, BERT, GAN, Wave Net, DALL-E, and Stable Diffusion. The generation AI model MD2 may be a multimodal model, or it may be a unimodal language model that outputs a response (text) in response to a prompt (text) input.

[0054] The communication unit 203 is equipped with a communication interface for communicating with the air conditioner 100 and the like. The communication interface provided by the communication unit 203 can be a communication interface compliant with a wireless LAN communication standard such as Wi-Fi (registered trademark). Alternatively, a communication interface compliant with a short-range wireless communication standard such as Bluetooth may be used. In addition to the air conditioner 100, the communication unit 203 may be configured to communicate with an air purifier 151, a circulator 152, a diffuser 153, lighting equipment 154, sound equipment 155, and the like.

[0055] The communication unit 203 further includes a communication interface for communicating with the first server 310 or the second server 320. Such a communication interface can be a wireless communication interface such as Wi-Fi®, 3G, 4G, 5G, or LTE (Long Term Evolution).

[0056] The imaging unit 204 is equipped with an image sensor such as a CMOS (Complementary Metal Oxide Semiconductor) or a CCD (Charge-Coupled Device), and generates an image (still image or video) of the object to be imaged by imaging the object. The imaging unit 204 outputs the image data related to the generated image to the control unit 201. The control unit 201 stores the input image data in the storage unit 202. The control unit 201 may display the image based on the image data on the display unit 209, or transmit it to the outside via the communication unit 203.

[0057] The audio input unit 205 includes a microphone for collecting sound, a processing circuit for converting the collected sound into a digital signal (audio data), and the like. The audio data generated in the audio input unit 205 is sent to the control unit 201, where appropriate processing such as noise reduction is performed. The audio data generated in the audio input unit 205 is also stored in the storage unit 202 or transmitted to the first server 310 via the communication unit 203.

[0058] The audio output unit 206 is equipped with a speaker that outputs sound. The audio output unit 206 reproduces sound based on the audio data provided by the control unit 201. In this embodiment, the audio input unit 205 and the audio output unit 206 are configured to input and output sound, but sounds other than voice (ambient sounds, music, etc.) may be input to the audio input unit 205 and sounds other than voice (ambient sounds, music, etc.) may be output from the audio output unit 206.

[0059] The positioning unit 207, for example, is equipped with a GPS (Global Positioning System) receiver and receives radio waves transmitted from GPS satellites to determine the current location of the user terminal 200. The positioning unit 207 outputs location information related to the determined current location of the user terminal 200 to the control unit 201.

[0060] The operation unit 208 is equipped with operating devices such as a touch panel, keyboard, and switches, and accepts various inputs and operations from the user. The control unit 201 acquires information input through the operation unit 208 and performs appropriate control based on the various operation information provided by the operation unit 208.

[0061] The display unit 209 is equipped with a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence) monitor, and displays information that should be notified to the user in response to instructions from the control unit 201.

[0062] Figure 4 is a block diagram showing the configuration of the control system of the first server 310. The first server 310 is a dedicated or general-purpose server computer and includes a control unit 311, a storage unit 312, a communication unit 313, and the like.

[0063] The control unit 311 includes a CPU, ROM, RAM, etc. The ROM in the control unit 311 stores control programs and the like that control the operation of each hardware component of the first server 310. The CPU in the control unit 311 reads and executes the control programs stored in the ROM and the computer programs stored in the memory unit 312, and controls the operation of each hardware component, thereby making the entire device function as the first server 310 in this disclosure. The RAM in the control unit 311 temporarily stores data used during the execution of calculations.

[0064] In this embodiment, the control unit 311 is configured to include a CPU, ROM, and RAM, but the configuration of the control unit 311 is not limited to the above. The control unit 311 may also include functions such as a clock for outputting date and time information, a timer for measuring the elapsed time from the time a measurement start instruction is given until a measurement end instruction is given, and a counter for counting numbers.

[0065] The storage unit 312 includes a storage device such as an HDD or SSD. The storage unit 312 stores various computer programs executed by the control unit 311, various data acquired through the communication unit 313, and various data used by the control unit 311.

[0066] The computer program (program product) stored in the memory unit 312 may include a control program PG3 for realizing the information processing method of the present disclosure. The control program PG3 may be a single computer program or a group of programs composed of multiple computer programs. The control program PG3 may be executed collaboratively by multiple computers. For example, the control program PG3 may realize the information processing method of the present disclosure by collaborating with a control program PG1 installed in the air conditioner 100 or a control program PG2 installed in the user terminal 200.

[0067] The computer program, including the control program PG3, is provided, for example, on a non-temporary recording medium RM3 on which the computer program is recorded in a readable format. The recording medium RM3 is a portable memory such as a CD-ROM, USB memory, SD card, microSD card, or CompactFlash®. The control unit 311 reads various computer programs from the recording medium RM3 using a reading device (not shown in the figure) and stores the read computer programs in the storage unit 312. The computer programs stored in the storage unit 312 may also be provided via communication. In this case, the control unit 311 acquires the computer programs via communication through the communication unit 313 and stores the acquired computer programs in the storage unit 312.

[0068] The memory unit 312 may include a generation AI model MD3. The generation AI model MD3 is a model that generates new content in response to inputs such as text, voice, still images, and videos. The content generated by the generation AI model MD3 includes text, voice or music, images such as still images or videos, etc. The generation AI model MD3 may be an existing model such as GPT®, BERT, GAN, Wave Net, DALL-E, or Stable Diffusion, or it may be a unique model fine-tuned for a specific application. The generation AI model MD3 may be a multimodal model, or it may be a unimodal language model that outputs a response (text) in response to a prompt (text) input.

[0069] The communication unit 313 is equipped with a communication interface for communicating with a user terminal 200 or the like. The communication interface provided by the communication unit 313 can be a wireless communication interface such as 3G, 4G, 5G, or LTE (Long Term Evolution).

[0070] The first server 310 may include an operation unit for receiving operations from administrators, a display unit for displaying information to be notified to administrators, etc. The first server 310 may be a single computer, or it may be a computer system composed of multiple computers and peripheral devices.

[0071] Figure 5 is a block diagram showing the configuration of the control system of the second server 320. The second server 320 is a dedicated or general-purpose server computer and includes a control unit 321, a storage unit 322, a communication unit 323, and the like.

[0072] The control unit 321 includes a CPU, ROM, RAM, etc. The ROM in the control unit 321 stores control programs and the like that control the operation of each hardware component of the second server 320. The CPU in the control unit 321 reads and executes the control programs stored in the ROM and the computer programs stored in the memory unit 322, and controls the operation of each hardware component, thereby making the entire device function as the second server 320 in this disclosure. The RAM in the control unit 321 temporarily stores data used during the execution of calculations.

[0073] In this embodiment, the control unit 321 is configured to include a CPU, ROM, and RAM, but the configuration of the control unit 321 is not limited to the above. The control unit 321 may also include functions such as a clock for outputting date and time information, a timer for measuring the elapsed time from the time a measurement start instruction is given until a measurement end instruction is given, and a counter for counting numbers.

[0074] The storage unit 322 includes a storage device such as an HDD or SSD. The storage unit 322 stores various computer programs executed by the control unit 321, various data acquired through the communication unit 323, and various data used by the control unit 321.

[0075] The storage unit 322 may also include a database DB for storing information such as the operation manual, service guide, technical handbook, installation instructions, customer information, operation data during trial operation, and operation data after the start of operation for the air conditioner 100. The database DB may further register construction information when the air conditioner 100 was installed (installation location of indoor and outdoor units, piping length, floor plan, and year of construction), information about the installed air conditioner 100 (model, Ua value, horsepower, etc.), and sales information for each employee.

[0076] The communication unit 323 is equipped with a communication interface for communicating with a user terminal 200 or the like. The communication interface provided by the communication unit 323 can be a wireless communication interface such as 3G, 4G, 5G, or LTE (Long Term Evolution).

[0077] The second server 320 may include an operation unit for receiving commands from administrators, a display unit for displaying information to be communicated to administrators, etc. The second server 320 may be a single computer, or it may be a computer system composed of multiple computers and peripheral devices.

[0078] In this embodiment, it is assumed that multiple users are staying in a space (hereinafter referred to as a "room") that is air-conditioned by the air conditioner 100. Each user in the room carries a user terminal 200, and the air conditioner 100, each user's user terminal 200, and the first server 310 are capable of communicating with each other. In addition, each user in the room carries a wearable device 250, and the biometric information of each user measured by the wearable device 250 is notified to the first server 310 via each user's user terminal 200.

[0079] Figure 6 illustrates an example of a dialogue during feedback collection. The first server 310 performs a dialogue process in which it sends a question to each user's user terminal 200 at an appropriate time to inquire about the user's level of comfort, and receives the user's response from each user's user terminal 200. The timing of when the first server 310 inquires about the user's level of comfort is arbitrary. For example, the first server 310 may inquire about the user's level of comfort when a set time has elapsed since the air conditioner 100 was powered on, or when a set time has elapsed since the set temperature, airflow, airflow direction, etc. of the air conditioner 100 were changed. The first server 310 may also inquire about the user's level of comfort at regular intervals after the air conditioner 100 was powered on. Furthermore, the first server 310 may also inquire about the user's level of comfort when the user's biometric information measured by the wearable device 250 exceeds or falls below a standard value. The first server 310 may simultaneously inquire about the level of comfort of each user, or it may inquire about the level of comfort of each user at individual times.

[0080] The dialogue screen in Figure 6 shows an example of a screen displayed on the display unit 209 of user terminals 200 carried by users A and B. Figure 6 shows that the first server 310 sends a message to user terminals 200 of users A and B asking about their comfort level, "How is the current room temperature?", and user A's user terminal 200 sends the reply "It's very hot", and user B's user terminal 200 sends the reply "It's a little cold" to the first server 310.

[0081] Such a dialogue is initiated when the control unit 311 of the first server 310 gives a dialogue start prompt to the generated AI model MD3. The dialogue start prompt is a standard phrase such as, "Start a dialogue with the users in the room and obtain feedback from each user regarding the comfort level of the room." The dialogue start prompt is stored in advance in the storage unit 312 as a parameter used by the control program PG3, for example.

[0082] In the example shown in Figure 6, the interaction is conducted by displaying text on the display unit 209 of the user terminal 200. However, the interaction may also be conducted using voice by utilizing the voice input unit 205 and voice output unit 206 of the user terminal 200.

[0083] In the example shown in Figure 6, the generated AI model MD3 queries the user's level of comfort (subjective evaluation) regarding room temperature as a measure of comfort within the living space. However, it may also query the user's level of comfort for other evaluation indicators such as humidity, airflow, and airflow direction, or it may query the overall level of comfort in the living space without limiting the evaluation indicators.

[0084] In the example in Figure 6, the user provides feedback on their comfort level using non-numerical expressions such as "It's very hot" or "It's a little cold," but they may also provide feedback on their comfort level using numerical expressions. To obtain feedback on comfort level using numerical expressions, the generating AI model MD3 may send an inquiry to the user's terminal 200, for example, "How is the room temperature now? Please rate your comfort level on a scale of 1 to 10."

[0085] When the control unit 311 of the first server 310 receives feedback on the degree of comfort in a non-numerical form from the user terminal 200, it uses the generating AI model MD3 to convert the received feedback into a numerical form.

[0086] Figure 7 shows an example of a prompt used for conversion to a numerical expression. When the control unit 311 of the first server 310 receives non-numerical feedback such as "It's very hot" from the user terminal 200, it generates a prompt as shown in Figure 7 (hereinafter referred to as a numerical conversion prompt) in order to convert the received feedback into a numerical expression.

[0087] The numerical conversion prompt includes instructions to the generating AI model MD3 and user feedback. The instructions to the generating AI model MD3 include an explanation that the user feedback concerns the comfort level of the air conditioning in the living room, and an instruction to convert the feedback into a numerical score from 1 to 10 (hereinafter referred to as the comfort score). The user feedback includes feedback received from the user terminal 200 (text entered by the user in a non-numerical expression). The comfort score is not limited to a 10-level score from 1 to 10, but may be set as appropriate.

[0088] The control unit 311 inputs the generated numerical conversion prompt to the generating AI model MD3, thereby converting the user's non-numerical feedback on comfort level into a numerical comfort score. For example, the non-numerical expression "It's very hot" from user A is converted to a comfort score of 2, and the non-numerical expression "It's a little cold" from user B is converted to a comfort score of 4.

[0089] The control unit 311 stores the comfort level feedback collected from the user in a table. The table is created in the storage unit 312. Figure 8 is a conceptual diagram showing an example of a user table that stores user-specific comfort level feedback. The user table TB stores the comfort level feedback collected from each user. The example in Figure 8 shows the user table TB with feedback from user A and user B stored.

[0090] The user table TB stores the date and time of feedback reception, the content of the feedback, the comfort score, environmental information, and biometric information in association with each other. The date and time of feedback reception is the date and time when the first server 310 received the feedback from the user terminal 200. The content of the feedback is the user's response to the inquiry from the generating AI model MD3. The user's response may be expressed in a non-numerical or numerical form. The comfort score is the score converted by the generating AI model MD3 if the user's response is expressed in a non-numerical form. If the user's response is expressed in a numerical form, the user's response may be used as is as the comfort score. Environmental information is information such as the temperature and humidity of the room measured by the sensor unit 104 of the air conditioner 100. Biometric information is information such as heart rate, body temperature, sweating, blood pressure, respiration, brain waves, and body composition measured by the wearable device 250.

[0091] In addition to the above information, the user table TB may also store the user's entry time. The entry time is estimated as the time when communication between the air conditioner 100 and the user terminal 200 began. If the entry time is stored in the user table TB, the control unit 311 can calculate the user's stay time by taking the difference between the entry time and the current time.

[0092] The control unit 311 stores the content of the feedback, the comfort score, etc., in the user table TB each time it receives feedback from a user staying in the room. The user table TB may store multiple pieces of feedback received from the same user during their stay.

[0093] In this embodiment, the purpose is to adjust the control parameters for the air conditioner 100 based on feedback from users staying in the room. Therefore, it is sufficient for only feedback from users currently staying in the room to be stored in the user table TB, and feedback from users who have left the room may be deleted from the user table TB. If past user feedback is to be saved as history, the control unit 311 may create a history table that stores user feedback associated with an identifier that identifies the user.

[0094] The control unit 311 can evaluate the reliability of feedback from each user by using the generated AI model MD3.

[0095] Figure 9 shows an example of a prompt used for reliability evaluation. When the control unit 311 evaluates the reliability of feedback from each user, it generates a prompt for reliability evaluation that includes an instruction to the generated AI model MD3, as shown in Figure 9. The user table TB is specified as the reference information for the prompt. In addition to the user table TB, the history table that stores the feedback history may also be specified as the reference information. The instruction to the generated AI model MD3 includes, for example, an instruction to evaluate the reliability of each user's feedback on a scale of 1 to 10 (hereinafter referred to as the reliability score) by referring to the feedback, environmental information, and biometric information of each user stored in the user table TB. The reliability score is not limited to a scale of 1 to 10, but may be set as appropriate.

[0096] The control unit 311 evaluates the reliability of feedback from each user by inputting the generated reliability evaluation prompt to the generating AI model MD3. When the generating AI model MD3 receives such a reliability evaluation prompt, it evaluates the reliability of the feedback based on the degree of discrepancy between the user's level of comfort estimated from at least one of environmental information and biometric information, and the user's feedback (comfort score), and outputs a reliability score on a 10-point scale from 1 to 10.

[0097] For example, if environmental information indicates that the room temperature is at a suitable temperature and biometric information indicates that the user is sweating little, it can be estimated that the user's level of comfort is high (comfort score of 7 or higher). However, if the user themselves provides extreme feedback such as "it's very hot" (comfort score of less than 3), the discrepancy between the two is large. In this case, the generative AI model MD3 evaluates the reliability of the user's feedback as low and outputs a relatively low reliability score (e.g., less than 3).

[0098] On the other hand, if environmental information indicates that the room temperature is at an appropriate temperature and biometric information indicates that the user is sweating little, it can be estimated that the user's level of comfort is high (comfort score of 7 or higher). However, if the user themselves provides positive feedback stating that they are "comfortable" (feedback with a comfort score of 7 or higher), the discrepancy between the two is small. In this case, the generative AI model MD3 evaluates the reliability of the user's feedback as high and outputs a relatively high reliability score (e.g., 7 or higher).

[0099] The control unit 311 may evaluate the priority of feedback from each user by using the generated AI model MD3.

[0100] Figure 10 shows an example of a prompt used for priority evaluation. When the control unit 311 evaluates the priority of feedback from each user, it generates a prompt for priority evaluation that includes an instruction to the generated AI model MD3, as shown in Figure 10. The user table TB is specified as the reference information for the prompt. In addition to the user table TB, the history table that stores the feedback history may also be specified as the reference information. The instruction to the generated AI model MD3 includes, for example, an instruction to evaluate the priority of each user's feedback on a scale of 1 to 10 (hereinafter referred to as the priority score) by referring to the information stored in the user table TB. The priority score is not limited to 10 levels from 1 to 10, but may be set as appropriate.

[0101] The control unit 311 evaluates the priority of feedback from each user by inputting the generated priority evaluation prompt to the generating AI model MD3. For example, if the most recent feedback is stored in the user table TB, it is preferable that this feedback be reflected in the air conditioning control, so the generating AI model MD3 assigns a relatively higher priority score to it than to older feedback. Also, feedback from users who stay in a room for a long time may be given more respect than feedback from other users who stay for a shorter time, so the generating AI model MD3 assigns a relatively higher priority score to it. Furthermore, users who provide feedback frequently may be given more respect than other users who provide less feedback, so the generating AI model MD3 assigns a relatively higher priority score to them.

[0102] Figure 11 is a flowchart showing the procedure of processing performed by the first server 310. The control unit 311 of the first server 310 collects feedback on the level of comfort from multiple users in a room air-conditioned by the air conditioner 100 (step S101). The control unit 311 collects feedback from each user by communicating with the user terminal 200 carried by each user. The control unit 311, for example, uses the generated AI model MD3 to ask each user questions such as "How is the current room temperature?" and receives the answer to the question from the user terminal 200. Each user uses the user terminal 200 to voluntarily send feedback on the level of comfort to the first server 310.

[0103] The control unit 311 stores the feedback regarding comfort levels received from the user terminal 200 in the user table TB for each user (step S102). If the feedback regarding comfort levels received from the user terminal 200 is expressed in a non-numerical form, the control unit 311 converts it into a numerical form using the generated AI model MD3 to obtain a comfort score. The control unit 311 also collects environmental information such as temperature and humidity in the room measured by the sensor unit 104 of the air conditioner 100, and biological information such as heart rate, body temperature, sweating, blood pressure, respiration, brain waves, and body composition measured by the wearable device 250. The control unit 311 stores the date and time of feedback reception, the content of the feedback, the comfort score, environmental information, and biological information in association with each other in the user table TB.

[0104] The control unit 311 evaluates the reliability of each user's feedback using the generated AI model MD3 (step S103). The control unit 311 can evaluate the reliability of each user's feedback by generating prompts as shown in Figure 9 and inputting the generated prompts into the generated AI model MD3.

[0105] The control unit 311 evaluates the priority of each user's feedback using the generated AI model MD3 (step S104). The control unit 311 generates prompts as shown in Figure 10 and evaluates the priority of each user's feedback by inputting the generated prompts into the generated AI model MD3.

[0106] The control unit 311 performs at least one of steps S103 and S104 at an appropriate timing. For example, the control unit 311 may perform steps S103 and S104 each time it receives feedback from the user terminal 200 to evaluate the reliability and priority of the feedback from each user. Alternatively, the control unit 311 may perform steps S103 and S104 at regular intervals to evaluate the reliability and priority of the feedback from each user. Furthermore, in step S105, described later, the control unit 311 may evaluate the reliability and priority after determining that there are differences in feedback among multiple users.

[0107] Furthermore, the order of processing in steps S103 and S104 is arbitrary, and the control unit 311 may evaluate reliability after evaluating priority. Moreover, the control unit 311 may evaluate only reliability or priority.

[0108] The control unit 311 refers to the user table TB for each user and determines whether there are differences in feedback among multiple users (step S105). For example, the control unit 311 extracts feedback from each user received within a set time (for example, within 30 minutes) from the current time from the user table TB and determines whether there are differences in feedback among multiple users. The control unit 311 compares the comfort scores of each user and determines that there are differences in feedback among multiple users if the comfort scores differ by a set value (the set value is an integer of 1 or more).

[0109] If it is determined that no difference has occurred (S105: NO), the control unit 311 returns to step S101. Even if no difference has occurred, if the comfort level of each user is low, the control unit 311 may adjust the control parameters of the air conditioner 100 to improve the comfort level of each user. In this case, the control unit 311 gives an adjustment instruction to the air conditioner 100 via the communication unit 313. Alternatively, the control unit 311 may generate control parameters for the air conditioner 100 and transmit the generated control parameters to the air conditioner 100 via the communication unit 313.

[0110] If the control unit 311 determines that a difference exists (S105: YES), it adjusts the control parameters for the air conditioner 100 by referring to at least one of the reliability evaluated in step S103 and the priority evaluated in step S104 (step S106). The control unit 311 adjusts the room temperature, humidity, airflow rate, airflow direction, etc. to achieve a comfort level that is intermediate between the differing feedbacks. At this time, it is preferable for the control unit 311 to make adjustments that favor users with higher reliability or priority. Alternatively, the control unit 311 may locally adjust the room temperature, humidity, airflow rate, airflow direction, etc. to improve the comfort level of a specific user with high reliability or priority. The control unit 311 may give adjustment instructions to the air conditioner 100 via the communication unit 313, or it may generate control parameters for the air conditioner 100 and transmit the generated control parameters to the air conditioner 100 via the communication unit 313.

[0111] After adjusting the control parameters in step S106, the control unit 311 returns to step S101, collects feedback from each user, and readjusts the control parameters as necessary.

[0112] As described above, in this embodiment, when multiple users are staying in a room air-conditioned by the air conditioner 100, and there are differences in the feedback from multiple users regarding their level of comfort, the control parameters for the air conditioner 100 can be adjusted by referring to the reliability and priority of the users. In this embodiment, dynamic adjustments are possible even in the case of differing opinions within the same room, thereby ensuring comfort.

[0113] In this embodiment, the first server 310 collects feedback on comfort levels from multiple users, and if there are differences in feedback among the multiple users, it adjusts the control parameters for the air conditioner 100 by referring to at least one of the user's reliability and priority. However, the air conditioner 100 may also be equipped with the functions of the first server 310. That is, the air conditioner 100 may collect feedback on comfort levels from each user staying in the space it air-conditions, evaluate the reliability and priority of the feedback using the generated AI model MD1, and if there are differences in feedback among the multiple users, it may adjust the control parameters for itself by referring to at least one of the user's reliability and priority.

[0114] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended.

[0115] 100 Air conditioner 200 User terminal 310 First server 320 Second server 101, 201, 311, 321 Control unit 102, 202, 312, 322 Storage unit 103, 203, 313, 323 Communication unit PG1, PG2, PG3 Control program MD1, MD2, MD3 Generated AI model RM1, RM2, RM3 Recording medium

Claims

1. A computer program that collects feedback on the level of comfort from multiple users staying in a space air-conditioned by an air conditioner, evaluates at least one of the reliability and priority of the collected user feedback using a generating AI model, and, if there are differences in the feedback among the multiple users, causes a computer to perform a process of adjusting the control parameters for the air conditioner by referring to at least one of the reliability and priority evaluated using the generating AI model.

2. The computer program according to claim 1, which causes the computer to perform a process of adjusting the control parameters for the air conditioner so that the level of comfort is intermediate among a plurality of users with relatively high reliability or priority.

3. A computer program according to claim 1 or 2, which causes the computer to perform a process of adjusting control parameters for the air conditioner in order to improve the level of comfort of a particular user whose reliability or priority is relatively high.

4. A computer program according to any one of claims 1 to 3, which causes the computer to perform a process of recollecting feedback from the multiple users and readjusting the control parameters based on the recollected feedback.

5. A computer program according to any one of claims 1 to 4, which causes the computer to perform a process of collecting feedback from each user by performing an interactive process with the user terminal used by each user.

6. The computer program according to claim 5, wherein the dialogue processing includes generating questions using the generation AI model to confirm the degree of comfort of the air conditioning provided by the air conditioner, sending the generated questions to each user's user terminal, and receiving each user's answers to the questions from each user's user terminal.

7. A computer program according to any one of claims 1 to 6, which causes the computer to perform a process to convert the collected feedback information regarding the degree of comfort into numerical information using the generating AI model, if the collected feedback information is non-numerical information.

8. A computer program according to any one of claims 1 to 7, which causes the computer to perform a process of evaluating the reliability of feedback from each user using a generative AI model that references at least one of the feedback history of each user, biometric information of each user, and environmental information of the space, and which references at least one of the collected feedback history, biometric information, and environmental information.

9. A computer program according to any one of claims 1 to 8, which collects at least one of the user's stay time in the space, the feedback history from each user, and the feedback timing, and causes the computer to perform a process of evaluating the priority of the feedback from each user using the generated AI model which refers to at least one of the collected stay time, feedback history, and feedback timing.

10. An information processing method comprising: collecting feedback on the degree of comfort from multiple users staying in a space air-conditioned by an air conditioner; evaluating at least one of the reliability and priority of the collected user feedback using a generating AI model; and, if there are differences in the feedback among the multiple users, performing a process by at least one computer to adjust the control parameters for the air conditioner by referring to at least one of the reliability and priority evaluated using the generating AI model.

11. An information processing system comprising at least one processing unit, wherein the processing unit collects feedback on the degree of comfort from multiple users staying in a space air-conditioned by an air conditioner, evaluates at least one of the reliability and priority of the collected user feedback using a generating AI model, and adjusts the control parameters for the air conditioner by referring to at least one of the reliability and priority evaluated using the generating AI model if there are differences in the feedback among the multiple users.

12. An air conditioner for air conditioning a target space, wherein the air conditioner collects feedback on the degree of comfort from multiple users staying in the target space, evaluates at least one of the reliability and priority of the collected feedback from each user using a generating AI model, and adjusts the control parameters of the unit by referring to at least one of the reliability and priority evaluated using the generating AI model if there are differences in the feedback among the multiple users.

Images