Information processing method, information processing device, and computer program

Abstract

An apparatus control device 20 acquires premise information relating to control of a target apparatus (for example, a circulator 16). The apparatus control device 20 acquires option information including a plurality of options that correspond to a plurality of control modes of the target apparatus. The apparatus control device 20 creates an input sentence which is based on the premise information and the option information. The apparatus control device 20 inputs the input sentence to a generative AI of a chatbot server 18, and acquires, from the generative AI, output information in which a specific option has been selected from among the plurality of options.

Description

Information processing method, information processing device, and computer program

[0001] The present disclosure relates to data processing technology, and more particularly to an information processing method, an information processing device, and a computer program.

[0002] A system has been proposed that acquires environmental information for a target space, estimates and selects any number of lifestyle scenes from a number of lifestyle scenes that have been preset based on that environmental information, and, if all of the environmental conditions corresponding to the selected lifestyle scenes can be realized simultaneously, controls air conditioning equipment based on the control content that realizes those environmental conditions (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2022-182719

[0004] In recent years, generative AI has begun to be utilized in various fields. The present inventors have considered utilizing generative AI for efficient control of devices. One objective of the present disclosure is to provide a technology for controlling devices by utilizing generative AI.

[0005] In order to solve the above problem, an information processing method of one embodiment of the present disclosure is executed by a computer to acquire premise information regarding the control of an equipment, acquire option information including multiple options corresponding to multiple control modes of the equipment, create an input sentence based on the premise information and the option information, input the input sentence to a generation AI, and acquire output information from the generation AI in which a specific option is selected from the multiple options.

[0006] Another aspect of the present disclosure is an information processing device including: a premise acquisition unit that acquires premise information related to device control; an option acquisition unit that acquires option information including multiple options corresponding to multiple control modes of the device; an input sentence creation unit that creates an input sentence based on the premise information and the option information; and an output information acquisition unit that inputs the input sentence to a generation AI and acquires output information from the generation AI in which a specific option is selected from the multiple options.

[0007] Any combination of the above components, or any conversion of the expression of the present disclosure between a system, a computer program, a recording medium on which a computer program is recorded, etc., is also valid as an aspect of the present disclosure.

[0008] According to the technology disclosed herein, it is possible to realize control of equipment using generative AI.

[0009] 7 is a diagram illustrating a configuration of a device control system according to an embodiment. FIG. 1 is a block diagram illustrating functional blocks of the device control device of FIG. 1. FIG. 2 is a diagram illustrating an example of a template. FIG. 3 is a diagram illustrating an example of sensor information. FIG. 4 is a diagram illustrating an example of device information. FIG. 5 is a diagram illustrating an example of option information. FIG. 6 is a flowchart illustrating the operation of the device control device. FIG. 7 is a flowchart illustrating details of the prompt generation process of S11 of FIG. 7. FIG. 8 is a flowchart illustrating details of the process of S22 of FIG. 8. FIG. 9 is a flowchart illustrating details of the process of S23 of FIG. 8. FIG. 10 is a diagram illustrating an example of answer information of the generation AI acquired in S12 of FIG. 7. FIG. 11 is a flowchart illustrating details of the interpretation process of S13 of FIG. 7. FIG. 12 is a flowchart illustrating details of the device control process of S15 of FIG. 7. FIG. 13 is a flowchart illustrating details of the pointed-out prompt generation process of S16 of FIG. 7. FIG. 14 is a diagram illustrating an example of a prompt according to a first modified example. FIG. 15 is a diagram illustrating an example of a prompt according to a second modified example. FIG. 16 is a diagram illustrating another example of a prompt according to the second modified example. FIG. 17 is a diagram illustrating an example of an input screen.

[0010] The subject of the device or method of the present disclosure includes a computer. The computer executes a program to realize the functions of the subject of the device or method of the present disclosure. The computer includes, as its main hardware configuration, a processor that operates according to the program. The processor may be of any type as long as it can realize the functions by executing the program. The processor is composed of one or more electronic circuits, including a semiconductor integrated circuit (IC) or an LSI (large scale integration). While the terms IC and LSI are used here, the term may be changed depending on the degree of integration, and may also be called a system LSI, a VLSI (very large scale integration), or an ULSI (ultra large scale integration). A field programmable gate array (FPGA), which is programmed after the LSI is manufactured, or a reconfigurable logic device that can reconfigure the connections within the LSI or set up circuit partitions within the LSI, can also be used for the same purpose. Multiple electronic circuits may be integrated on a single chip or may be provided on multiple chips. Multiple chips may be integrated into a single device or may be provided on multiple devices. The program may be recorded on a non-transitory recording medium such as a computer-readable read-only memory (ROM), optical disk, or hard disk drive, or on a temporary storage medium such as a computer-readable random access memory (RAM). The program may be pre-stored on a recording medium or may be supplied to a recording medium or storage medium via a wide area communication network, including the Internet.

[0011] In the embodiment, a technology for controlling devices is proposed that utilizes generative AI. Generative AI, also known as generative artificial intelligence, is an artificial intelligence system that generates text, images, etc. in response to prompts. The prompt is text (in other words, a sentence) written in natural language that describes the task to be performed by the generative AI. The generative AI used by the device control device of the embodiment is an artificial intelligence chatbot that mimics human conversation through text-based dialogue. Hereinafter, when simply referred to as generative AI, it refers to an artificial intelligence chatbot.

[0012] 1 shows the configuration of an equipment control system 10 according to an embodiment. The equipment control system 10 includes a plurality of sensors 14 and a plurality of circulators 16 installed in a target space 12, a chatbot server 18, and an equipment control device 20. These devices are connected via a communication network 22, which may include a LAN, a WAN, the Internet, or the like.

[0013] The multiple sensors 14 measure predetermined physical quantities in the target space 12. The multiple sensors 14 may include sensors that measure different types of physical quantities. For example, the multiple sensors 14 may include a CO2 sensor that measures the ambient carbon dioxide (CO2) concentration, or a human presence sensor or camera that measures the number of people. The multiple sensors 14 include sensor 14a, sensor 14b, sensor 14c, and sensor 14d.

[0014] The multiple circulators 16 generate wind and circulate air in the target space 12. The multiple circulators 16 include a circulator 16a, a circulator 16b, a circulator 16c, and a circulator 16d.

[0015] The target space 12 is a space that is the target of environmental control, such as a room in an office or a home. The target space 12 is divided into multiple areas, and in this embodiment, the target space 12 is divided into area 1 (northeast), area 2 (northwest), area 3 (southwest), and area 4 (southeast). A sensor 14a and a circulator 16a are installed in area 1. A sensor 14b and a circulator 16b are installed in area 2. A sensor 14c and a circulator 16c are installed in area 3. A sensor 14d and a circulator 16d are installed in area 4. Note that the target space 12 is not limited to a room in an office or a home. For example, the target space 12 may be an indoor space such as a factory, warehouse, or restaurant, or may be the interior of a train or automobile. In other words, the technology disclosed herein is applicable to any space that can be divided into areas and contains one or more circulators (devices to be controlled). Furthermore, some of the multiple areas in the target space 12 may not contain a circulator (devices to be controlled).

[0016] The chatbot server 18 is an information processing device that has the function of a generation AI (artificial intelligence chatbot) and provides a chat service using the generation AI to an external device.

[0017] The device control device 20 is an information processing device that controls multiple circulators 16 using a chat service using generation AI provided by the chatbot server 18. The device control device 20 may be a dedicated device installed in the user's home (e.g., a remote control that controls the circulators 16). Alternatively, the device control device 20 may be a user's smartphone or tablet terminal on which a device control application is installed. The functions of the device control device 20 and the functions of the chatbot server 18 may be implemented in a single information processing device.

[0018] Figure 2 is a block diagram showing the functional blocks of the device control device 20 in Figure 1. Each block shown in the block diagram of the present disclosure can be realized in terms of hardware by elements and mechanical devices such as a computer's CPU and memory, and in terms of software by a computer program, etc., but here, the functional blocks are depicted as being realized by the cooperation of these elements. Those skilled in the art will understand that these functional blocks can be realized in various ways by combining hardware and software.

[0019] The device control device 20 includes a processing unit 30, a storage unit 32, a communication unit 34, and an operation input unit 36. The processing unit 30 executes various data processing operations. The processing unit 30 may be implemented by a processor (such as a CPU) of the device control device 20. The storage unit 32 stores data referenced or updated by the processing unit 30. The communication unit 34 communicates with external devices in accordance with a predetermined communication protocol. The processing unit 30 transmits and receives data to and from the sensor 14, the circulator 16, and the chatbot server 18 via the communication unit 34.

[0020] The operation input unit 36 ​​accepts user operations and inputs operation information to the processing unit 30. The operation input unit 36 ​​may include a button, a touch panel, or a keyboard. As a variation, the operation input unit 36 ​​may be provided in a device external to the device control device 20. For example, a user's smartphone or tablet terminal that communicates with the device control device 20 via the communication network 22 may operate as the operation input unit 36. Furthermore, the operation input unit 36 ​​may be realized by combining devices without direct human operation. For example, a device that uses a timer may function as the operation input unit 36 ​​and input instructions corresponding to the seasons of spring, summer, autumn, and winter to the processing unit 30.

[0021] The storage unit 32 includes a template storage unit 38, a spatial information storage unit 40, a sensor information storage unit 42, a device information storage unit 44, and an option storage unit 46. The template storage unit 38 stores a plurality of templates corresponding to a plurality of predetermined questions that can be answered by the generation AI. The plurality of questions may include, for example, a ventilation question (in other words, a circulator control question), a lighting control question, an air purifier control question, and a speaker control question. Each template is a sentence containing a specific question to be presented to the generation AI and serves as a model sentence for creating a prompt.

[0022] Specifically, the template storage unit 38 stores a set of template IDs, question types, and associated templates. FIG. 3 shows an example of a template. A template 70 includes premise information 72 and an option field 78. The premise information 72 is information that serves as a premise for the control of a target device (e.g., the circulator 16) that is determined for each question. The premise information 72 includes a space information field 74 and a sensor value field 76. Although not shown in FIG. 3, the premise information 72 further includes prerequisites, as will be described later.

[0023] The space information field 74 is a text field in which information about the space in which the target device operates (hereinafter also referred to as "space information") is set. In the embodiment, the space information includes information indicating that the target space 12 is divided into multiple areas. The space information may also include the position and size of each area provided in the target space 12.

[0024] The sensor value field 76 is a text field in which information detected by the sensor and related to the situation of the space in which the target device operates (hereinafter also referred to as "sensor value information") is set. In this embodiment, the sensor value information includes the CO2 concentration in the target space 12 in which the circulator 16 operates, detected by the sensor 14. Specifically, it includes the CO2 concentration for each area in which each sensor 14 is installed.

[0025] The option field 78 is a text field in which information including multiple options corresponding to multiple control modes of the target device (hereinafter also referred to as "option information") is set. The option information for the circulator 16 may include multiple options regarding the airflow direction. The option information in the embodiment is determined based on multiple areas provided in the target space 12. For example, the option information may include multiple options that determine from which area and toward which area the circulator 16 should blow air. In other words, the option information may include multiple options that specify the airflow direction of the circulator 16 using the area.

[0026] 2 , the space information storage unit 40 stores space information. Specifically, the space information storage unit 40 includes a space ID and space information. The space information includes information about the shape, size, area, etc. of the target space 12.

[0027] The sensor information storage unit 42 stores information (hereinafter referred to as "sensor information") about one or more sensors (in this embodiment, a plurality of sensors 14) installed in the target space 12. FIG. 4 shows an example of sensor information. The sensor information includes the ID of the sensor 14, the ID of the space in which the sensor 14 is installed, the ID of the area (within the space) in which the sensor 14 is installed, and the sensor value type. The sensor value type is information indicating the type of physical quantity measured by the sensor 14. CO2 sensor 1 in FIG. 4 corresponds, for example, to sensor 14a in FIG. 1. CO2 sensor 2 in FIG. 4 corresponds, for example, to sensor 14b in FIG. 1.

[0028] Returning to FIG. 2 , the device information storage unit 44 stores information (hereinafter referred to as "device information") about one or more devices (in this embodiment, multiple circulators 16) that are to be controlled and installed in the target space 12. FIG. 5 shows an example of the device information. The device information includes the ID and device type of the circulator 16, the ID of the space in which the circulator 16 is installed, and the ID of the area. Circulator 1 in FIG. 5 corresponds, for example, to circulator 16a in FIG. 1. Circulator 2 in FIG. 5 corresponds, for example, to circulator 16b in FIG. 1.

[0029] Returning to FIG. 2 , the option storage unit 46 stores option information. FIG. 6 shows an example of option information. The option information includes the ID of the controlled device (the circulator 16 in this embodiment), an option number, an action, and a control parameter. Option numbers 1-A to 1-D in FIG. 6 are options related to the circulator 1. The action is information indicating the control mode of the controlled device, in other words, information indicating the operating mode of the controlled device. For example, the action is information that determines from which area and to which area the circulator 16 should blow air. The control parameter is a parameter required when instructing the device to perform the operation specified by the action. For example, the control parameter includes information that specifies power on / off and the air blowing angle.

[0030] 2 , the processing unit 30 includes a premise acquisition unit 50, an option acquisition unit 52, a prompt generation unit 54, an answer acquisition unit 56, an interpretation unit 58, and a device control unit 60. The functions of these multiple functional blocks may be implemented in a computer program. This computer program may be installed in the storage of the device control device 20. The processor of the device control device 20 may perform the functions of the multiple functional blocks by reading this computer program into main memory and executing it.

[0031] The premise acquisition unit 50 acquires premise information regarding the control of the control-target device corresponding to the problem selected by the user, based on the data in the template storage unit 38, the spatial information storage unit 40, and the sensor information storage unit 42. For example, the control-target device corresponding to the ventilation problem is the circulator 16.

[0032] The option acquisition unit 52 acquires option information including a plurality of options corresponding to a plurality of control modes of the control-target device based on the data in the device information storage unit 44 and the option storage unit 46 .

[0033] The prompt generation unit 54 generates data of an input sentence (prompt) to the generation AI based on the premise information acquired by the premise acquisition unit 50 and the option information acquired by the option acquisition unit 52.

[0034] The answer acquisition unit 56 inputs the prompt to the generation AI by transmitting data of the prompt generated by the prompt generation unit 54 to the chatbot server 18. The answer acquisition unit 56 acquires output information (hereinafter also referred to as "answer information") from the chatbot server 18, in which a specific option is selected from multiple options set in the prompt, output from the generation AI.

[0035] The interpretation unit 58 interprets the answer information of the generated AI acquired by the answer acquisition unit 56. If an error exists in the answer information of the generated AI, the interpretation unit 58 detects the error.

[0036] The device control unit 60 executes processing related to the control of the controlled device using the response information of the generated AI. In the embodiment, if there is no error in the response information of the generated AI, the device control unit 60 controls the controlled device based on the response information. The device control unit 60 controls the controlled device so that it operates in the manner indicated by the option selected in the response information.

[0037] The operation of a device control device 20 in a user's home configured as described above will now be described. The template storage unit 38 of the device control device 20 may store templates created by a service provider or the user. The service provider is, for example, the provider of the device control device 20 or the provider of a device control application installed on the device control device 20. Alternatively, the template storage unit 38 may store templates created by other users and distributed via a communication network.

[0038] The spatial information storage unit 40 of the device control device 20 may store spatial information created by the user. Alternatively, the spatial information storage unit 40 may store spatial information in which a floor plan created by the user is written using a known method. Alternatively, the spatial information storage unit 40 may store spatial information in which the user has modified a template of spatial information provided by a service provider. Alternatively, the spatial information storage unit 40 may store, as spatial information, an explanatory text of the space created using a known method based on a photo of the space input by the user.

[0039] The sensor information storage unit 42 of the device control device 20 may store sensor information created by a user. The areas in the sensor information may be set based on the positions of the sensors 14 described on the floor plan used to create the spatial information. The areas in the sensor information may also be set based on the results of self-location estimation of each sensor 14 using Wi-Fi (registered trademark) or Bluetooth (registered trademark).

[0040] The device information storage unit 44 of the device control device 20 may store device information created by a user. The spaces and areas in the device information may be set based on the positions of the devices described in the floor plan used to create the space information. The spaces and areas in the device information may also be set based on the results of self-location estimation of each device using Wi-Fi (registered trademark) or Bluetooth (registered trademark).

[0041] The option storage unit 46 of the device control device 20 may store option information created by a user. Option information for multiple control target devices may be provided by the providers of the respective devices. Option information may be set based on the positions of the devices described in the floor plan used to create the space information.

[0042] 7 is a flowchart showing the operation of the equipment control device 20. The user inputs an operation (hereinafter also referred to as a "problem selection operation") to the operation input unit 36 ​​to select a problem to be solved (e.g., a ventilation problem) from among a plurality of predetermined problems and a space in which the problem should be solved (e.g., the target space 12). When the problem selection operation is input (Y in S10), the premise acquisition unit 50, option acquisition unit 52, and prompt generation unit 54 of the equipment control device 20 execute a process to generate a prompt corresponding to the selected problem (S11).

[0043] The answer acquisition unit 56 of the device control device 20 inputs the prompt to the generated AI by transmitting the prompt generated in S11 to the chatbot server 18. The answer acquisition unit 56 acquires the generated AI's answer information to the prompt transmitted from the chatbot server 18 (S12).

[0044] The interpretation unit 58 of the device control device 20 interprets the response information acquired in S12 and identifies the option (which can also be called the control mode) selected by the generation AI for each device to be controlled (S13). If the response information contains an error, the interpretation unit 58 detects the error. For example, the interpretation unit 58 detects an error if it cannot identify one option selected by the generation AI for at least one device from the response information.

[0045] If no error is detected from the answer information (N in S14), the device control unit 60 of the device control device 20 executes processing to control the controlled device (S15). If an error is detected from the answer information (Y in S14), the prompt generation unit 54 of the device control device 20 generates a prompt indicating the error (hereinafter also referred to as an "indication prompt") (S16). The indication prompt can also be considered a prompt instructing the output of a new answer in which the error has been resolved.

[0046] Thereafter, the process returns to S12, and the answer acquisition unit 56 of the device control device 20 inputs the indicated prompt to the generation AI by sending the indicated prompt generated in S16 to the chatbot server 18. The answer acquisition unit 56 acquires answer information of the generation AI in response to the indicated prompt. If the question selection operation has not been input (N in S10), the process from S11 onwards is skipped.

[0047] Fig. 8 is a flowchart showing the details of the prompt generation process of S11 in Fig. 7. The premise acquisition unit 50 of the equipment control device 20 reads out a template corresponding to a problem selected by the user from among a plurality of templates stored in the template storage unit 38 (S20). In this example, it is assumed that a ventilation problem has been selected, and the template 70 in Fig. 3 corresponding to the ventilation problem is read out.

[0048] Figure 9 shows an example of a prompt. The prompt 80 in Figure 9 is a prompt corresponding to a ventilation problem, and is obtained by adding spatial information, sensor value information, option information, etc. to the template 70 in Figure 3. The prompt 80 (template 70) includes a question sentence 81 for the generation AI according to the problem to be solved. The question sentence 81 in Figure 9 includes a question regarding the control method of the circulator 16.

[0049] 3 , the template 70 includes predetermined premise information 72 corresponding to the problem. The premise information 72 includes a precondition 82 in addition to a space information field 74 and a sensor value field 76. The precondition 82 is a condition that must be met to improve the environment of the space in which the controlled device operates. In the embodiment, the precondition 82 is a condition that must be met to improve the air environment of the target space 12 in which the circulator 16 operates.

[0050] The prerequisites 82 of the embodiment include efficiency information 84, an airflow mode 86, and an activation condition 88. The efficiency information 84 is information related to improving ventilation efficiency. For example, the efficiency information 84 is information indicating how ventilation efficiency can be improved. The airflow mode 86 is information related to how air is sent by the circulator 16. For example, the airflow mode 86 is information indicating in which direction air should be sent. The activation condition 88 is information related to the activation condition of the circulator 16. For example, the activation condition 88 is information indicating under what circumstances the circulator 16 should be activated, or information indicating under what circumstances the circulator 16 should not be activated.

[0051] 8 , the premise acquisition unit 50 of the device control device 20 reads out spatial information related to the space in which the problem specified in the problem selection operation should be solved (here, the target space 12) from the plurality of pieces of spatial information stored in the spatial information storage unit 40. The prompt generation unit 54 of the device control device 20 sets the spatial information of the target space 12 in the spatial information field 74 of the template 70 (S21).

[0052] As will be described later in relation to Fig. 10, the premise acquisition unit 50 and the prompt generation unit 54 of the device control device 20 set sensor value information in the sensor value field 76 of the template 70 (S22). As will be described later in relation to Fig. 11, the option acquisition unit 52 and the prompt generation unit 54 of the device control device 20 set option information in the option field 78 of the template 70 (S23).

[0053] 10 is a flowchart showing the details of the sensor value information setting process of S22 in FIG. 8. A placeholder indicating the sensor value type to be set in the sensor value field 76 of the template 70 is provided. The premise acquisition unit 50 acquires the sensor value type (e.g., "CO2 concentration") from the placeholder in the sensor value field 76 (S30). The prompt generation unit 54 sets the output string to an empty string (S31). The prompt generation unit 54 adds a sensor value type line (e.g., "CO2 concentration") to the output string (S32).

[0054] The premise acquisition unit 50 acquires information on sensors (hereinafter also referred to as "corresponding sensors") corresponding to the target space 12, which is the space to be solved, and the sensor value type from among the multiple sensors stored in the sensor information storage unit 42 (S33). For example, information on multiple CO2 sensors is acquired as the information on the multiple corresponding sensors. The premise acquisition unit 50 selects one corresponding sensor from the multiple corresponding sensors (S34). The premise acquisition unit 50 acquires a current sensor value output from the one corresponding sensor selected in S34 (S35). The current sensor value is, for example, the current CO2 concentration measured by the CO2 sensor serving as the corresponding sensor in the area where the sensor is installed.

[0055] The prompt generation unit 54 adds the current sensor value acquired in S35 to the output string (S36). For example, as shown in the sensor value field 76 in Fig. 9, the prompt generation unit 54 adds a string indicating the installation area and sensor value of the one corresponding sensor selected in S34 (e.g., "Area 1 (Northeast): 495.0 ppm") to the output string.

[0056] If the sensor values ​​of all the corresponding sensors acquired in S33 have been added to the output string (Y in S37), the prompt generation unit 54 sets the output string in the sensor value field 76. In other words, the prompt generation unit 54 replaces the placeholder in the sensor value field 76 with the output string (S38). If the sensor values ​​of some of the corresponding sensors have not yet been set in the output string (N in S37), the process returns to S34.

[0057] 11 is a flowchart showing the details of the option information setting process of S23 in FIG. 8. An option field 78 of the template 70 has a placeholder indicating the device type to be set in that field. The option acquisition unit 52 acquires the device type (e.g., "circulator") from the placeholder in the option field 78 (S40). The prompt generation unit 54 sets the output string to an empty string (S41). The prompt generation unit 54 adds the device type (e.g., "circulator") to the output string (S42).

[0058] The option acquisition unit 52 acquires information on devices (hereinafter also referred to as "compatible devices") that correspond to the target space 12 and device type from the device information stored in the device information storage unit 44 (S43). A compatible device can also be considered a device to be controlled. For example, information on multiple circulators 16 installed in the target space 12 is acquired as information on multiple compatible devices. The option acquisition unit 52 selects one compatible device from the multiple compatible devices (S44). The prompt generation unit 54 adds an device line (e.g., "Circulator 1") or an area line (e.g., "Area 1") related to the one compatible device selected in S44 to the output character string (S45).

[0059] The option acquisition unit 52 acquires option information (e.g., the four options 1-A to 1-D in FIG. 6 ) related to the compatible device selected in S44 from the option information stored in the option storage unit 46 (S46). The prompt generation unit 54 adds the option information acquired in S46 to the output character string (S47). For example, as shown in the option field 78 in FIG. 9 , the prompt generation unit 54 adds four options (1-A to 1-D) related to the control mode of the circulator 1 installed in area 1 to the output character string.

[0060] If the option information for all compatible devices acquired in S43 has been added to the output string (Y in S48), the prompt generation unit 54 sets the output string in the option field 78, in other words, replaces the placeholder in the option field 78 with the output string (S49). If option information for some compatible devices has not been set in the output string (N in S48), the process returns to S44.

[0061] FIG. 12 shows an example of the response information of the generation AI acquired in S12 of FIG. 7. The response information 90 includes information indicating the options selected by the generation AI for each unit of control target (e.g., equipment or area) specified in the prompt. The response information 90 of FIG. 12 indicates that option 1-C (e.g., blowing air from area 1 toward area 3) was selected as the control mode for the circulator 16a installed in area 1. The response information 90 of FIG. 12 also indicates that option 2-D (e.g., blowing air from area 2 toward area 4) was selected as the control mode for the circulator 16b installed in area 2.

[0062] 13 is a flowchart showing details of the interpretation process of S13 in FIG. 7. The interpretation unit 58 of the device control device 20 extracts options corresponding to each device from the response information of the generation AI (S50). For example, the interpretation unit 58 extracts option 1-C as the operation mode of the circulator 16a installed in area 1 and option 2-D as the operation mode of the circulator 16b installed in area 2 based on the response information 90 of FIG. 12. The interpretation unit 58 may extract options for each device using known natural language processing (e.g., rule-based or machine learning), or may extract options for each device based on a predetermined response format.

[0063] The interpretation unit 58 determines whether or not there is an error in the answer information of the generation AI. For example, the interpretation unit 58 determines whether or not one valid option has been selected in the answer information for each of the devices set in the prompt 80. If one valid option has been selected in the answer information for each of the devices set in the prompt 80, the interpretation unit 58 determines that there is no error in the answer information. Furthermore, the interpretation unit 58 determines that there is an error in the answer information if (1) an option that does not exist in the answer information has been selected, (2) multiple options have been selected for one device in the answer information, or (3) an option for each device could not be extracted from the answer information.

[0064] If it is determined that there is no error in the response information of the generation AI (N in S51), the device control unit 60 of the device control device 20 refers to the option information stored in the option storage unit 46 and acquires the control parameters associated with the option selected for each compatible device (S52).If it is determined that there is an error in the response information of the generation AI (Y in S51), the interpretation unit 58 detects the error (S53).

[0065] Fig. 14 is a flowchart showing details of the device control process of S15 in Fig. 7. The device control unit 60 of the device control device 20 controls a certain compatible device using the control parameters acquired in S52 (S60). If there is a compatible device that has not yet been controlled (N in S61), the process of S60 is repeated. When control of all compatible devices is completed (Y in S61), the device control process ends.

[0066] Fig. 15 is a flowchart showing the details of the indication prompt generation process of S16 in Fig. 7. The prompt generation unit 54 of the device control device 20 generates a sentence (hereinafter also referred to as a "indication sentence") indicating that there is an error in the answer (S70). The prompt generation unit 54 generates an indication prompt, which is a prompt that adds the indication sentence to the flow of the dialogue up to that point (S71).

[0067] For example, if the reason for the error is that a non-existent option was selected, the comment may be, "You have selected option 1-E for circulator 16a in area 1, but that option does not exist. Please choose from the options given earlier." Also, if the reason for the error is that multiple options were selected for one device, the comment may be, "You have selected options 1-A and 1-B for circulator 16a in area 1, but only one option can be selected for one device. Please choose one."

[0068] Also, if the reason for the error is that an option could not be extracted from the answer information, the comment may be, "It was not possible to interpret from your previous answers which option you selected for each device. Please answer more clearly and in an easier-to-interpret way." Also, if the answer format is specified in the prompt, the comment may be, "It was not possible to interpret from your previous answers which option you selected for each device. Please answer in the specified format."

[0069] According to the device control device 20 of the embodiment, it is possible to efficiently select an appropriate control mode for a device using the generation AI, and to automate the operation of the device in the mode selected by the generation AI. Furthermore, according to the device control device 20, by inputting a single template that brings together multiple types of independent parameters such as spatial information and sensor information into the generation AI, it is possible to efficiently determine the control mode for the device taking these multiple types of parameters into account.

[0070] In addition, in the embodiment, the controlled device is a circulator, and according to the device control device 20, by including in the prompt prerequisite information for improving the environment of the space in which the circulator operates, the generation AI can be made to select a control mode of the circulator for improving the environment of the space. Furthermore, according to the device control device 20, by including efficiency information, airflow mode, and startup conditions in the prerequisite information prerequisites, the generation AI can be made to more appropriately select a control mode of the circulator.

[0071] The present disclosure has been described above based on the embodiments. The embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of each component or each treatment process of the embodiments, and that such modifications are also within the scope of the present disclosure.

[0072] A first modification will now be described. Fig. 16 shows an example of a prompt 80 according to the first modification. The option fields 78 of the prompt 80 may be written in the order shown in Fig. 16 instead of the order shown in Fig. 9.

[0073] A second modified example will now be described. Multiple types of control target devices may be installed in one target space. FIG. 17 shows an example of a prompt 80 in the second modified example. In this example, a circulator and an air conditioner are installed in each of areas 1 to 4 of the target space. FIG. 18 shows another example of the prompt 80 in the second modified example. The option fields 78 of the prompt 80 may be written in the order shown in FIG. 18 instead of the order shown in FIG. 17.

[0074] A third modified example will be described. Instead of directly controlling the devices, the device control device 20 may act as a server and transmit information based on the options for each device selected by the generation AI to a client device (such as a user terminal). The information based on the options for each device may be information indicating a control mode corresponding to the option, or may include control parameters corresponding to the option. The user terminal may control the devices based on the information provided by the device control device 20.

[0075] A fourth modification will be described. The technical concept of the above embodiment can be applied to the control of various devices (for example, devices that change the environment of a space) other than the circulator 16. An example of controlling a device other than the circulator 16 will be described below.

[0076] (1) The technical concept of the above embodiment can be applied to the control of lighting devices. In this case, the spatial information includes the position of the lighting within the space. The prerequisites include at least one of information regarding lighting control and information regarding the activation conditions of the lighting devices. The sensors include a sensor that measures illuminance, a sensor that measures time, and a sensor that measures the number of people. The options include combinations of lighting brightness and color.

[0077] (2) The technical concept of the above embodiment can be applied to the control of an air purifier. In this case, the spatial information includes the location of the air purifier. The sensors include sensors that measure air quality (e.g., dust, PM2.5, and pollen concentrations). The options include air purification intensity and the direction of the circulator. The technical concept of the above embodiment can also be applied to the control of an air conditioner. In this case, the spatial information includes the location of the air conditioner. The prerequisites include at least one of information regarding the control of the air conditioner and information regarding the activation conditions of the air conditioner. The sensors include sensors that measure temperature or humidity and sensors that measure the number of people. The options include the set temperature and the air conditioner's wind direction and air volume.

[0078] (3) The technical concept of the above embodiment can be applied to the control of audio equipment (speakers). In this case, the spatial information includes the type of space (which can also be called the type of room, such as living room, work room, or bedroom). The prerequisites include at least one of the type of audio content, information about volume, and information about the activation conditions of the equipment. The sensors include sensors that count the number of people and sensors that recognize human behavior. The options include the type and volume of audio content to be output.

[0079] A fifth modification will now be described. In the above embodiment, the user selected a problem to be solved by controlling the device. As a modification, the system may automatically select a problem and repeat optimization. An example in which the system automatically selects a problem will be shown below.

[0080] (1) The device control device 20 may generate prompts for all of a predetermined number of questions at regular time intervals, obtain the answers from the generation AI, and control the devices. Note that if the devices to be controlled overlap among the multiple questions, the device control device 20 may set priorities for each question based on predetermined rules and process the questions with the highest priority first.

[0081] (2) The equipment control device 20 may select a problem based on a predetermined problem selection rule. For example, the problem selection rule may be defined such that a problem related to air conditioning control (e.g., circulator control) is selected when the average CO concentration in the target space 12 exceeds 600 ppm.

[0082] (3) The device control device 20 may sequentially provide the sensor values ​​of the sensors 14 installed in the target space 12 to the chatbot server 18 (generation AI) and have the generation AI determine which question to select from a plurality of predetermined questions. The entity that selects the questions is not limited to the generation AI, and may be a general machine learning model.

[0083] As a sixth modified example, an example of a display that supports the question selection operation input at S10 in Fig. 7 will be described. In this modified example, the device control device 20 further includes an input screen generation unit, a display control unit, and a display unit. The display unit may include a liquid crystal display or an organic EL display. The input screen generation unit generates data for an input screen that supports the user in the question selection operation input. The display control unit displays the input screen generated by the input screen generation unit on the display unit.

[0084] FIG. 19 shows an example of an input screen 100. The input screen 100 includes a target space image diagram 102, which is an image diagram of the target space 12. The target space image diagram 102 may be a schematic diagram, a block diagram like FIG. 1, or a photograph of the actual target space 12. The target space image diagram 102 clearly shows the division of the target space 12 into areas. The target space image diagram 102 in FIG. 19 shows the target space 12 including four areas, area 1 to area 4.

[0085] The input screen 100 includes an equipment operation status 104. The equipment operation status 104 displays the operation status of the equipment for each area. The equipment operation status 104 in Fig. 19 shows the operation status of each of four equipment items: air conditioners, lighting equipment, ventilation equipment, and circulators, in each of the four areas. The operation status of equipment that is not installed in a certain area is not displayed (in the example of Fig. 19, the ventilation equipment in areas 2 and 4).

[0086] When the sensor tab 106 of the appliance operation status 104 is selected, the input screen generation unit may generate and display the input screen 100 in which sensor information such as that shown in FIG. 4 is set in the appliance operation status 104. The drop-down list 108 is a screen element that presents a plurality of predetermined problems to the user and allows the user to select a problem that the user wishes to solve from the plurality of problems. The input screen generation unit sets information about the problem selected in the drop-down list 108 in the selection result area 110.

[0087] The options in the drop-down list 108 may include one or both of information about the space in which the appliance operates and information about the controlled appliance, which are to be included in the premise information. Hereinafter, for simplicity of explanation, the options are assumed to include both information about the space in which the appliance operates and information about the controlled appliance. The operation input unit 36 ​​of the appliance control device 20 may accept information about the option selected in the drop-down list 108, i.e., the selected information about the space in which the appliance operates and the selected information about the controlled appliance. The premise acquisition unit 50 of the appliance control device 20 may acquire, as premise information, the information about the space in which the appliance operates and the information about the controlled appliance, which are selected in the drop-down list 108. The prompt generation unit 54 of the appliance control device 20 may generate a prompt based on the premise information and the corresponding option information.

[0088] The user may select a space in which the problem should be solved in the target space image diagram 102. In addition, when specifying the space in which the problem should be solved, the user may select the Area 1-Area 4 tab in the appliance operation status 104. In another aspect, the user may (1) select the appliance to be controlled (horizontal axis) in the appliance operation status 104, or (2) select a combination of the appliance and area to be controlled in the appliance operation status 104 (for example, air conditioner-area 1, etc.).

[0089] In the case of (1), all areas in which the selected devices are installed may be input as the "space where the problem should be solved." In the case of (2), the selected area may be input as the "space where the problem should be solved." For example, if four items, air conditioner areas 1 and 2 and circulator areas 1 and 4, are selected in the device operation status 104, areas 1, 2, and 4 may be input as the "space where the problem should be solved." In both cases (1) and (2), the input screen generation unit may obtain only the options related to the selected devices and / or areas and set them in the drop-down list 108.

[0090] In yet another aspect, the input screen generation unit may set the option information on the input screen 100, in other words, may output the option information to the user. The input screen generation unit may always display the option information on the input screen 100, or may display the option information when any device or item is selected.

[0091] In S10 of FIG. 7 , the input is not limited to a predetermined problem, but may also be a problem the user wishes to solve. For example, the user may input information about an arbitrary problem the user wishes to solve into the input screen 100 of FIG. 19 . The prompt generation unit 54 of the device control device 20 may set information about the arbitrary problem the user wishes to solve, input into the input screen 100, as a prompt. Furthermore, the premise acquisition unit 50 of the device control device 20 may infer which of a plurality of predetermined problems the arbitrary problem the user wishes to solve, input into the input screen 100, corresponds to, and acquire premise information based on the result. Similarly, the option acquisition unit 52 may infer which of a plurality of predetermined problems the problem the user wishes to solve, input into the input screen 100, corresponds to, and acquire options based on the result.

[0092] As a seventh modified example, a modified example of the device control process of S15 in FIG. 7 will be described. In the device control process, in addition to controlling the device, information regarding the device's control status may be output (displayed) to the user. The information regarding the device's control status may also be considered the control content of the device selected by the generation AI. For example, the input screen generation unit shown in the sixth modified example may acquire the device's control content from the device control unit 60 and set the device's control content in the device operation status 104 of the input screen 100 shown in the sixth modified example ( FIG. 19 ). In this case, the input screen generation unit may set information of the option (i.e., the output result) selected by the generation AI in the selection result area 110 of the input screen 100. Furthermore, if the generation AI generates information other than the option, such as the selection reason or additional information, the input screen generation unit may set that information in the selection result area 110 of the input screen 100.

[0093] An eighth modification will now be described. When the multiple sensors 14 include a motion sensor or a camera that measures the number of people present in the target space 12, (1) the sensor value field 76 may include the number of people in the target space 12 detected by the sensor 14 instead of the CO2 concentration in the target space 12, or (2) the sensor value field 76 may include the number of people in the target space 12 detected by the sensor 14 in addition to the CO2 concentration in the target space 12. In either case (1) or (2), specifically, the number of people in each area in the target space 12 is included.

[0094] In the case of (1), the precondition 82 may include a precondition based on the number of people instead of the CO2 concentration. For example, the airflow mode 86 may be, "By sending air from an area with many people to an area with few people, it is expected that the area with many people will be made more comfortable." Furthermore, the activation condition 88 may be, "In rooms with two or fewer people, it is less necessary to use a circulator." In the case of (2), the precondition 82 may include a precondition based on at least one of the CO2 concentration and the number of people. For example, the airflow mode 86 may be, "By sending air from an area with many people to an area with few people, it is expected that the CO2 concentration will be even." Furthermore, the activation condition 88 may be, "In rooms where either the CO2 concentration is 600 or higher or the number of people is five or more, it is highly necessary to use a circulator." Furthermore, if the precondition 82 is a precondition related to an air conditioning device, the airflow mode 86 may include, for example, "By increasing the degree of control over the area with many people (by lowering the set temperature or increasing the airflow), it is expected that the area will be made more comfortable." These preconditions may be included in any field of the premise information 72 .

[0095] According to the configuration of the eighth modified example, the prompt can include prerequisites and sensor information according to the type of sensors 14 provided in the target space 12 and the situation of the target space 12. This allows the generation AI to more appropriately select the control mode of the equipment to improve the environment of the space.

[0096] A ninth modification will be described. The equipment control device 20 may acquire information about the space outside the target space 12 via the communication unit 34. The acquired information about the external space and preconditions related to the information may be included in the premise information 72. Here, the space outside the target space 12 may be, for example, a space within the same building as the target space 12 but different from the target space 12, or may be outside the building, i.e., an outdoor space. The information about the external space may be, for example, (1) information about the air quality, temperature, and humidity in the external space, or (2) weather information including wind volume, rainfall, etc.

[0097] In the case of (1), for example, the precondition 82 may include, as the activation condition 88, "When the air quality in the external space may adversely affect the human body or when the temperature and humidity in the external space deviate from the temperature and humidity in the room by a predetermined amount or more, ventilation with the external space should not be performed." Furthermore, if the precondition 82 is a precondition related to an air conditioner, the activation condition 88 may include, for example, "When the temperature in the external space or outdoors deviates from the temperature in the room by a predetermined amount or more, the air conditioner should be controlled by setting the set temperature higher or lower than normal to avoid heat shock." In the case of (2), for example, the precondition 82 may include, as the activation condition 88, "When the outdoor wind volume or rainfall is greater than a predetermined amount, ventilation with the external space should not be performed." Note that these preconditions may be included in any field of the precondition information 72.

[0098] According to the configuration of the ninth modification, in addition to information from the sensors 14 provided in the target space 12, information about the space outside the target space 12 can be included in the prompt as premise information. This allows the generation AI to more appropriately select the control mode of the equipment to improve the environment of the space, taking into account the environment of the external space.

[0099] A tenth modification will be described. The preconditions 82 may further include preconditions based on time information and the operating costs of the equipment. For example, the preconditions 82 may include "Between 12:00 and 1:00 PM, the number of people in the area decreases due to lunch breaks, so the need for equipment control is lower than at other times." Alternatively, the preconditions 82 may include "Between 2:00 PM and 4:00 PM, the CO2 concentration or temperature in the entire area tends to be high, so preliminary equipment control is required from a time before this time." Furthermore, the preconditions 82 may include "In order to reduce operating costs (or power consumption), it is necessary to control the equipment so that the hourly operating cost (or power consumption) resulting from equipment control is below a predetermined level." These preconditions may be included in any field of the precondition information 72. In addition to the preconditions, the precondition information 72 may also include data information related to time information and the operating costs of the equipment. The data information related to the operating costs of the equipment may include, for example, information related to power consumption and electricity charges. Furthermore, if the building to which the target space 12 belongs generates its own electricity using renewable energy or other sources, it may also include information related to the amount of electricity sold in addition to the amount of electricity generated.

[0100] An eleventh modification will be described. In addition to devices that change the environment of a space, such as a circulator, the device control device 20 may control other devices related to the target space 12. The other devices may be, for example, devices that cover the opening of a ventilation device to the outside space, or devices such as curtains or shutters that block light or protect windows provided in the target space 12.

[0101] A twelfth modification will be described. The equipment control device 20 may further display supplemental information for a user present in the target space 12. The supplemental information is, for example, information other than information related to the selected option that is included in the response information of the generation AI. The equipment control device 20 may also cause the generation AI to generate suggestions or instructions for the user and display the generated information as supplemental information. The suggestions or instructions for the user are information indicating actions that are desirable for the user to perform, separate from the controls that are specified by the options and that the equipment control device 20 can control. Examples of suggestions or instructions for the user include, "People are concentrated in a specific area, so avoiding people concentrating in one area will improve the efficiency of ventilation and air conditioning," or "It is difficult to make the room comfortable with the current equipment alone, so it is desirable to add more equipment."

[0102] In addition, the equipment control device 20 may further cause the generation AI to generate information regarding recommended equipment layouts in the target space 12, and display the generated information as supplemental information. The information regarding recommended equipment layouts may be, for example, "By installing a new air conditioning or ventilation device in area 2, the room can be ventilated more efficiently." In particular, when equipment that changes the environment of the space includes equipment that is easy to relocate, such as a circulator, information regarding the layout of equipment that is easy to relocate may be displayed. In this case, the information regarding recommended equipment layouts may be, for example, "By moving the circulator installed in area 1 to area 4, the room can be ventilated more efficiently."

[0103] The display to assist in inputting a question selection operation and the display of information relating to the control status of the device have been described in the sixth and seventh modifications, but the display of supplementary information to the user in the twelfth modification may be in addition to or instead of the above. The display in the eleventh modification may be displayed on the display unit of the device control device 20 in the sixth and seventh modifications, or may be displayed on a separate display device.

[0104] Any combination of the above-described embodiments and modifications is also useful as an embodiment of the present disclosure. A new embodiment resulting from a combination combines the effects of the combined embodiments and modifications. It will also be understood by those skilled in the art that the functions to be performed by each component recited in the claims can be realized by each component shown in the embodiments and modifications, either alone or in combination.

[0105] <Additional Notes> The above description of the embodiments and variations discloses the following technologies. [Technology 1] An information processing method executed by a computer includes: acquiring premise information regarding control of a device; acquiring option information including multiple options corresponding to multiple control modes of the device; creating an input sentence based on the premise information and the option information; inputting the input sentence to a generation AI; and acquiring output information from the generation AI in which a specific option is selected from the multiple options. This information processing method enables efficient selection of an appropriate control mode for the device using the generation AI. [Technology 2] The information processing method described in Technology 1, in which the computer further controls the operation of the device based on the output information. This information processing method enables automation of operating the device in the mode selected by the generation AI. [Technology 3] The information processing method described in Technology 1 or 2, in which the premise information includes prerequisites for improving the environment of a space in which the device operates. This information processing method allows the generation AI to select a control mode that improves the environment of the space. [Technology 4] The information processing method described in Technology 3, in which the device is a device that changes the environment of the space. According to this information processing method, the generation AI can be made to select a control mode for a device that changes the environment of a space, thereby improving the environment of the space. [Technology 5] The information processing method described in Technology 4, wherein the device is an air conditioning device or a ventilation device, and the preconditions include at least one of information related to device control, information related to ventilation efficiency, and information related to activation conditions. According to this information processing method, the generation AI can be made to select a control mode for the air conditioning device or the ventilation device, thereby improving the environment of the space. [Technology 6] The information processing method described in Technology 4, wherein the device is a lighting device, and the preconditions include at least one of information related to lighting control and information related to activation conditions. According to this information processing method, the generation AI can be made to select a control mode for the lighting device, thereby improving the environment of the space. [Technology 7] The information processing method described in Technology 4, wherein the device is an audio device, and the preconditions include at least one of information related to the type of audio content, information related to volume, and information related to activation conditions.This information processing method allows the generating AI to select a control mode for an audio device, thereby improving the spatial environment. [Technology 8] The information processing method according to Technology 1 or 2, wherein the premise information includes information about the space in which the device operates. This information processing method allows the generating AI to more appropriately select a control mode for the device. [Technology 9] The information processing method according to Technology 8, wherein the information about the space includes information indicating that the space has been divided into a plurality of areas, and the option information is determined based on the plurality of areas. This information processing method allows the generating AI to more appropriately select a control mode for the device. [Technology 10] The information processing method according to Technology 8, wherein the information about the space includes information indicating that the space has been divided into a plurality of areas, and the option information is determined based on one or both of the selected device and the area. This information processing method allows the generating AI to more appropriately select a control mode for the device. [Technology 11] The information processing method according to Technology 1 or 2, wherein the premise information includes information about the state of the space in which the device operates, detected by a sensor. This information processing method allows the generation AI to more appropriately select the control mode of the device. [Technology 12] The information processing method according to Technology 1 or 2, in which, in acquiring the premise information, options are output for at least one of information about the space in which the device operates and information about the device to be controlled, which are to be included in the premise information. This information processing method can assist the user in selecting appropriate premise information. [Technology 13] The information processing method according to Technology 1 or 2, in which a user input is accepted for at least one of information about the space in which the device operates and information about the device to be controlled, and an input sentence is created based on the input information. This information processing method can create an input sentence (prompt) that reflects the user's intention. [Technology 14] The information processing method according to Technology 1 or 2, in which information about the specific option included in the output information, or information about the control status of the device based on the output information, is output.This information processing method allows the user to easily understand the selection results made by the generation AI. [Technology 15] An information processing device comprising: a premise acquisition unit that acquires premise information related to device control; an option acquisition unit that acquires option information including multiple options corresponding to multiple control modes of the device; an input sentence creation unit that creates an input sentence based on the premise information and the option information; and an output information acquisition unit that inputs the input sentence to the generation AI and acquires output information from the generation AI in which a specific option is selected from the multiple options. This information processing device allows the generation AI to efficiently select an appropriate control mode for the device. [Technology 16] A computer program that causes a computer to execute the following steps: acquire premise information related to device control; acquire option information including multiple options corresponding to multiple control modes of the device; create an input sentence based on the premise information and the option information; input the input sentence to the generation AI; and acquire from the generation AI output information in which a specific option is selected from the multiple options. This computer program allows the computer to efficiently select an appropriate control mode for the device using the generation AI.

[0106] The technology of the present disclosure can be applied to an information processing device or an information processing system.

[0107] 10 Equipment control system, 14 Sensor, 16 Circulator, 18 Chatbot server, 20 Equipment control device, 50 Premise acquisition unit, 52 Choice acquisition unit, 54 Prompt generation unit, 56 Answer acquisition unit, 58 Interpretation unit, 60 Equipment control unit.

Claims

1. An information processing method executed by a computer, comprising the steps of: acquiring premise information regarding the control of a device; acquiring option information including a plurality of options corresponding to a plurality of control modes of the device; creating an input sentence based on the premise information and the option information; inputting the input sentence into a generation AI; and acquiring output information from the generation AI in which a specific option is selected from the plurality of options.

2. The information processing method according to claim 1, further comprising the step of: controlling the device based on the output information.

3. The information processing method according to claim 1 or 2, wherein the premise information includes prerequisites for improving the environment of a space in which the device operates.

4. The information processing method according to claim 3, wherein the device is a device that changes the spatial environment.

5. The information processing method according to claim 4, wherein the equipment is an air conditioning equipment or an equipment that performs ventilation, and the prerequisite conditions include at least one of information regarding control of the equipment, information regarding ventilation efficiency, and information regarding start-up conditions.

6. The information processing method according to claim 4, wherein the device is a lighting device, and the prerequisites include at least one of information regarding lighting control and information regarding activation conditions.

7. The information processing method according to claim 4, wherein the device is an audio device, and the prerequisite conditions include at least one of the type of audio content, information about volume, and information about activation conditions.

8. The information processing method according to claim 1 or 2, wherein the premise information includes information about a space in which the device operates.

9. The information processing method according to claim 8, wherein the information relating to the space includes information indicating that the space is divided into a plurality of areas, and the option information is determined based on the plurality of areas.

10. The information processing method according to claim 8, wherein the information regarding the space includes information indicating that the space is divided into a plurality of areas, and the option information is determined based on one or both of the selected device and area.

11. The information processing method according to claim 1 or 2, wherein the premise information includes information about a spatial situation in which the device operates, detected by a sensor.

12. The information processing method according to claim 1 or 2, further comprising, in acquiring the premise information, outputting options for at least one of information regarding the space in which the device operates and information regarding the device to be controlled, which are to be included in the premise information.

13. The information processing method according to claim 1 or 2, further comprising accepting user input regarding at least one of information regarding the space in which the device operates and information regarding the device to be controlled, and creating an input sentence based on the input information.

14. The information processing method according to claim 1 or 2, further comprising the step of outputting information on the specific option included in the output information, or information on a control state of the device based on the output information.

15. An information processing device comprising: a premise acquisition unit that acquires premise information regarding the control of a device; an option acquisition unit that acquires option information including a plurality of options corresponding to a plurality of control modes of the device; an input sentence creation unit that creates an input sentence based on the premise information and the option information; and an output information acquisition unit that inputs the input sentence to a generation AI and acquires output information from the generation AI in which a specific option is selected from the plurality of options.

16. A computer program for causing a computer to execute the following steps: acquire premise information regarding the control of a device; acquire option information including a plurality of options corresponding to a plurality of control modes of the device; create an input sentence based on the premise information and the option information; input the input sentence to a generation AI; and acquire output information from the generation AI in which a specific option is selected from the plurality of options.

Images