Device and method

Abstract

An apparatus according to one aspect comprises: a request implementation unit that generates, on the basis of a user input including information indicating a user's request related to a smart home, a first prompt instructing a generative AI model to output information indicating an IoT device used to respond to the user's request and information indicating an operation condition of the IoT device; and a program generation unit that generates a second prompt instructing the generative AI model to generate a program for operating the IoT device according to the operation condition obtained by inputting the first prompt to the generative AI model.

Description

Device and Method

[0001] The present disclosure relates to a device and a method for assisting in constructing a smart home.

[0002] There is known a smart home having a home automation function for automatically controlling home appliances by using IoT devices connected to a network. As a technology related to smart homes, Patent Document 1 describes control request data for controlling home appliances such as lighting fixtures, electric locks, and air conditioning equipment in a residential house being sent to a gateway through the Internet and a LAN within a condominium, and a control signal obtained by protocol conversion at the gateway being given to a transmission unit. A home automation system having such a control function is described.

[0003] Japanese Patent Application Laid-Open No. 2004-214937

[0004] As described in Patent Document 1, in order to construct a smart home having a function of automatically controlling home appliances, it is required to select one or more IoT devices necessary for realizing a desired control and set a complicated program for operating these one or more IoT devices in conjunction with each other. Therefore, in order to realize a smart home, specialized knowledge is required and a lot of labor is needed.

[0005] Therefore, an object of the present disclosure is to provide a device and a method that can easily construct a smart home without specialized knowledge.

[0006] A device according to one aspect assists in constructing a smart home. This device includes a desire specification unit that generates a first prompt for instructing a generation AI model to output information indicating an IoT device used to meet a user's desire and information indicating an operating condition of the IoT device based on a user input including information indicating the user's desire for the smart home, and a program generation unit that generates a second prompt for instructing the generation AI model to generate a program for operating the IoT device according to the operating condition obtained by inputting the first prompt into the generation AI model.

[0007] In the apparatus according to the above embodiment, IoT devices are selected according to the user's requirements for a smart home, and a program is generated to operate the IoT devices according to the operating conditions specified in those requirements. Therefore, even without specialized knowledge, users can easily build a smart home using the generated program.

[0008] According to this disclosure, smart homes can be easily built even without specialized knowledge.

[0009] This is a block diagram showing the functional configuration of a smart home construction support device according to one embodiment. This is a diagram showing an example of a first prompt generated by the request concretization unit. This is a diagram showing an example of the output of the generated AI model when the first prompt is input. This is a diagram showing an example of a second prompt generated by the program generation unit. This is a diagram showing an example of the output of the generated AI model when the second prompt is input. This is a diagram showing an example of a third prompt generated by the incident check unit. This is a diagram showing an example of the output of the generated AI model when the third prompt is input. This is a flowchart showing a smart home construction method according to one embodiment. This is a flowchart showing the steps following Figure 8. This is a block diagram showing the functional configuration of a smart home construction support program according to one embodiment. This is a block diagram showing the functional configuration of a smart home construction support device according to another embodiment. This is a block diagram showing the hardware configuration of a smart home construction support device.

[0010] Embodiments of the present disclosure will be described below with reference to the drawings. In the following description, the same or equivalent elements will be denoted by the same reference numerals, and redundant descriptions will not be repeated.

[0011] Figure 1 is a block diagram showing the functional configuration of a smart home construction support device according to one embodiment. The smart home construction support device 1 shown in Figure 1 (hereinafter referred to as "support device 1") provides information to support the construction of a smart home. A smart home is a house that has a home automation function that automates the operation of equipment within the house. Examples of home equipment automated by home automation include lighting equipment, air conditioning equipment, kitchen appliances, washing machines, monitoring equipment, and curtains. These home devices are controlled using IoT devices connected to the internet. Examples of IoT devices include smart remote controls, smart switches, various sensors, and smart hubs. Smart remote controls and smart switches remotely control home equipment. Examples of various sensors include motion detection sensors, temperature sensors, humidity sensors, and CO2 sensors. ２ Examples of sensors include optical sensors, sound sensors, and pressure sensors. The smart hub controls these various sensors. Home appliances are automatically controlled according to the sensor values ​​measured by the various sensors. The home appliances themselves may also be IoT devices connected to the internet.

[0012] As shown in Figure 1, the support device 1 is connected to the user terminal 2 in a communication manner. The user terminal 2 can access the support device 1 via a network. The user terminal 2 is, for example, a personal computer, tablet, smartphone, game console, PDA (Personal Digital Assistant), etc., and is operated by the user. Note that there may be two or more user terminals 2 connected to the support device 1.

[0013] Furthermore, the support device 1 is connected to the server device 4 in a communication manner. The server device 4 includes a storage unit 41 and a generated AI model 42. The storage unit 41 is a database accessible from each functional element of the support device 1. The storage unit 41 stores user attribute information that indicates the user's attributes, such as a user ID for user identification, the user's gender, age, and family structure.

[0014] The generation AI model 42 is accessible from each functional element of the support device 1. The generation AI model 42 takes prompts generated by the support device 1 as input and outputs text data corresponding to the prompts. In response to the input of a prompt containing input data, the generation AI model 42 generates content according to one or a combination of the instructions, context, questions, and output format indicated by the prompt, and outputs that content as generated data. The generation AI model 42 may be an interactive AI model that includes, for example, a Large Language Model (LLM) and a user interface (UI) for interaction with the user, enabling text chat or voice chat with the user. Examples of such generation AI models include ChatGPT, GPT®-3.5, GPT-4V, PaLM2, etc. Although a large language model is described as an example above, other AI models may also be used.

[0015] A prompt is information indicating an instruction or question input to an AI model in an interactive system such as a command-line interface (CLI). A prompt input to the generating AI model 42 is text data that includes information such as the command to be executed by the generating AI model 42, the task to be executed by the generating AI model 42, the background / context that the generating AI model 42 should consider (e.g., role, conditions), the question that the generating AI model 42 should answer, and the output format of the response information from the generating AI model 42. In addition, the prompt may be supplemented with input information that is the target of the command / task to be executed by the generating AI model 42. Examples of such input information include data files with filenames that have a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0016] The generated AI model 42 may be stored in the server device 4, or it may be stored in another device connected to the server device 4 via a network, and configured to allow information exchange with the support device 1 via the server device 4.

[0017] Support device 1 is, for example, a RAG (Retrieval-Augmented Generation) device positioned between the user terminal 2 and the server device 4. Support device 1 receives input data containing keywords from the user terminal 2 and sends a prompt containing those keywords to the server device 4. Support device 1 also sends output data generated by support device 1 or the generation AI model 42 to the user terminal 2.

[0018] As shown in Figure 1, the support device 1 has a functional configuration comprising a request concretization unit 10, a program generation unit 20, and an incident check unit 30. In the example shown in Figure 1, the request concretization unit 10, the program generation unit 20, and the incident check unit 30 are realized by a single support device 1, but these functional elements may be distributed and arranged across multiple devices.

[0019] The request concretization unit 10 has the function of concretizing the user's requests regarding smart homes. Specifically, the request concretization unit 10 outputs information indicating one or more IoT devices necessary to realize the user's requests, and information indicating the operating conditions of said one or more IoT devices. As shown in Figure 1, the request concretization unit 10 includes a reception unit 11, a question generation unit 12, an output unit 13, a prompt generation unit 14, and a device search unit 15.

[0020] The reception unit 11 receives input data (user input) from the user terminal 2 that includes information indicating the user's requests regarding the smart home. The input data is text data containing the user's requests regarding the smart home. For example, the reception unit 11 obtains input data from a user who wishes to build a smart home that includes the text data "I want to have a comfortable room at all times." The text data entered by the user may be displayed on the display device of the user terminal 2. The reception unit 11 may also search the storage unit 41 to obtain information indicating the user's attributes on the user terminal 2.

[0021] The question generation unit 12 generates a question to narrow down the IoT devices to be used to fulfill the user's request, based on the input data received by the reception unit 11. For example, the question generation unit 12 generates a prompt (fourth prompt) to instruct the generation AI model 42 to generate a question to ask the user about their home appliances. The question generation unit 12 then inputs the generated prompt to the generation AI model 42 to generate the question.

[0022] The output unit 13 transmits output data, including the question text generated by the question generation unit 12, to the user terminal 2. The output data is text data including the question text. In the following description, the support device 1 and the user terminal 2 communicate by sending and receiving text data, but they are not limited to this, and may communicate using image data or audio data.

[0023] The user inputs their answers to the questions into user terminal 2. For example, in response to a question about the home appliances the user owns, the user inputs the answer, "There is an air conditioner and a heater installed in the room. Both the air conditioner and the heater are operated by infrared remote controls. The air conditioner only has a cooling function." and sends the answer data, including this answer, to support device 1. The reception unit 11 of support device 1 receives the answer data from user terminal 2. Support device 1 may also generate additional questions to clarify the user's requests and send them to user terminal 2.

[0024] The prompt generation unit 14 generates a first prompt P1 that instructs the generation AI model 42 to output information indicating one or more IoT devices to be used to fulfill the user's request, and the operating conditions of said one or more IoT devices, based on the input data and response data received by the reception unit 11.

[0025] Figure 2 shows an example of a first prompt P1 generated by the prompt generation unit 14. As shown in Figure 2, the first prompt P1 includes information indicating the user's request, "Please create operating conditions for IoT devices to keep the room comfortable at all times. Also, please recommend the necessary IoT devices manufactured by XXX company," and instructions to output the IoT devices necessary to fulfill that request and the operating conditions for those IoT devices to the generating AI model 42. The first prompt P1 also includes information indicating response data, such as "The room has an air conditioner and a heater," "Both the air conditioner and heater are operated by infrared remote controls," and "The air conditioner only has a cooling function." The first prompt P1 may also include information indicating the user's attributes, such as age or family structure. The prompt generation unit 14 outputs the generated first prompt P1 to the generating AI model 42.

[0026] The generating AI model 42 receives the first prompt P1 generated by the prompt generation unit 14 and outputs information indicating one or more IoT devices necessary to fulfill the user's request contained in the first prompt P1, as well as the operating conditions for said one or more IoT devices. Figure 3 shows an example of the generated data output by the generating AI model 42 when the first prompt P1 is input. The generated data G1 shown in Figure 3 includes "XXX Corporation Smart Remote Control AAA" and "XXX Corporation Temperature and Humidity Meter BBB" as a list of IoT devices necessary to fulfill the user's request. The generated data G1 also includes the operating conditions OC for "XXX Corporation Smart Remote Control AAA" and "XXX Corporation Temperature and Humidity Meter BBB". The operating conditions OC shown in Figure 3 indicate the conditions for turning the air conditioner or heater on / off according to the room temperature.

[0027] The device search unit 15 obtains generated data from the generated AI model 42 and searches for IoT devices included in the generated data. For example, the device search unit 15 generates a search query to find IoT devices included in the generated data of the generated AI model 42, and uses the generated search query to search an EC (Electronic Commerce) site. For example, the device search unit 15 searches an EC site using a search query that includes the product name of the IoT device and obtains search results that include a hyperlink to the product page of the IoT device.

[0028] The device search unit 15 may search for IoT devices before the first prompt P1 is generated. In this case, the prompt generation unit 14 may include a list of multiple IoT devices found by the device search unit 15 in the first prompt P1. The generated AI model 42 may select one or more IoT devices necessary to fulfill the user's request from the list of IoT devices and output them as generated data.

[0029] The output unit 13 outputs a list of IoT devices included in the generated data of the generated AI model 42, along with information indicating the operating conditions of the IoT devices, as output data to the user terminal 2. The list of IoT devices may include hyperlinks to access the product pages of the IoT devices. The user of the user terminal 2 can access the product pages included in the list and purchase the IoT devices necessary for building a smart home.

[0030] As shown in Figure 1, the program generation unit 20 includes an acquisition unit 21, an API search unit 22, and a prompt generation unit 23. The program generation unit 20 inputs a first prompt P1 to the generation AI model 42 and generates a program to operate the IoT device according to the operating conditions of the IoT device obtained.

[0031] The acquisition unit 21 acquires the generated data G1 generated by the generation AI model 42 from the request concretization unit 10. The API search unit 22 acquires APIs (Application Programming Interfaces) from an external system based on the generated data G1. An API is software that can be called from a program to control an IoT device. In many cases, the supplier of an IoT device publishes the API for operating the IoT device. The API search unit 22 searches for and acquires the APIs of IoT devices included as a list in the generated data G1 of the generation AI model 42 from an external system (for example, the supplier's website).

[0032] The prompt generation unit 23 generates a second prompt P2 to instruct the generating AI model 42 to generate a program for operating the IoT device according to the operating conditions of the IoT device generated by the generating AI model 42, based on the generated data G1 of the generating AI model 42 acquired by the acquisition unit 21 and the API acquired by the API search unit 22.

[0033] Figure 4 shows an example of a second prompt P2 generated by the prompt generation unit 23. As shown in Figure 4, the second prompt P2 includes the operating conditions OC of the IoT device generated by the generation AI model 42. The second prompt P2 also includes an instruction to generate a program to operate the IoT device, which states, "Create a Python program that uses the API to control the air conditioner and heater based on the specified operating conditions." The prompt generation unit 23 adds the API of the IoT device obtained by the API search unit 22 to the second prompt P2 and inputs it to the generation AI model 42.

[0034] When the second prompt P2 and API are input, the generating AI model 42 outputs a program corresponding to the operating conditions OC of the IoT device according to the instructions of the second prompt P2. Figure 5 shows an example of generated data output from the generating AI model 42 in response to the input of the second prompt P2. The generated data G2 shown in Figure 5 includes a program PR1 for operating the IoT devices "Smart Remote Control AAA" and "Temperature and Humidity Meter BBB" according to the operating conditions OC of the IoT devices shown in Figure 4.

[0035] As shown in Figure 1, the incident check unit 30 includes an acquisition unit 31 and a prompt generation unit 32. The incident check unit 30 inputs a second prompt P2 to the generation AI model 42 and generates a third prompt P3 instructing the generation AI model 42 to check the safety of the program PR1 obtained.

[0036] The acquisition unit 31 acquires the program PR1 output from the generating AI model 42 based on the instructions of the second prompt P2. The prompt generation unit 32 generates a third prompt P3 that instructs the generating AI model 42 to search for past incident cases and check the safety of the program. An incident case is a specific example of an accident, problem, or event that has occurred in the past.

[0037] Figure 6 shows an example of a third prompt P3 generated by the prompt generation unit 32. As shown in Figure 6, the third prompt P3 includes program PR1 generated by the generation AI model 42. The third prompt P3 also includes an instruction to check the safety of program PR1, which states, "Investigate past incident cases involving heaters and air conditioners to determine whether the following program can prevent incidents, and decide whether it is sufficient or not." Furthermore, the third prompt P3 includes an instruction to modify program PR1, which states, "If it is not sufficient, create a program to resolve the issue." The prompt generation unit 32 inputs the generated third prompt P3 to the generation AI model 42.

[0038] When the third prompt P3 is input, the generating AI model 42 searches for past incident cases according to the instructions of the third prompt P3 and modifies program PR1 if necessary. Figure 7 shows an example of generated data output from the generating AI model 42 in response to the input of the third prompt P3. The generated data G3 shown in Figure 7 includes incident cases related to residential equipment controlled by IoT devices and program PR2 modified to avoid those incident cases.

[0039] Support device 1 transmits the modified program PR2 to user terminal 2. The user registers the modified program PR2 in an application installed on user terminal 2 for configuring IoT devices. Alternatively, support device 1 may be configured to automatically add the modified program PR2 to the application on user terminal 2 without user intervention. By registering the modified program PR2, the IoT device operates according to the operating conditions OC. In other words, it becomes possible to realize a smart home that meets the user's requirements.

[0040] Next, a method for constructing a smart home according to one embodiment will be described with reference to Figures 8 and 9. Figures 8 and 9 are flowcharts showing a method for constructing a smart home according to one embodiment.

[0041] As shown in Figure 8, in the smart home construction method, first the receiving unit 11 of the request concretization unit 10 receives input data from the user terminal 2 that includes information indicating the user's requests regarding the smart home (step ST1). The input data is, for example, text data containing the user's requests regarding the smart home.

[0042] Next, the question generation unit 12 inputs a prompt to the generation AI model 42 to generate a question for the user to inquire about the home appliances they own, and generates a question sentence for the user to inquire about the home appliances they own. Then, the output unit 13 sends the generated question sentence to the user terminal 2 (step ST2). The reception unit 11 receives the user's answer to the question sentence.

[0043] The prompt generation unit 23 generates a first prompt P1 that instructs the generation AI model to output information indicating an IoT device used to meet the user's desires and information indicating the operating conditions of the IoT device based on the input data and the user's response to the question sentence. When the first prompt P1 is input, the generation AI model 42 outputs information indicating one or more IoT devices and information indicating the operating conditions OC of the IoT device according to the user's desires included in the first prompt P1 (step ST3). At this time, the first prompt P1 may include an instruction to cause the generation AI model 42 to generate a plurality of operating conditions OC.

[0044] When the generation AI model 42 outputs information indicating an IoT device and information indicating a plurality of operating conditions OC of the IoT device, the output unit 13 outputs the information indicating the IoT device and the information indicating the plurality of operating conditions OC to the user terminal 2 and presents them to the user (step ST4). Next, the output unit 13 asks the user whether there is a desired operating condition among the presented plurality of operating conditions OC (step ST5). Information indicating whether there is a desired operating condition is transmitted from the user terminal 2 to the support device 1. If there is no desired operating condition of the user, steps ST3 and ST4 are repeatedly executed until the desired operating condition of the user is reached.

[0045] If there is a desired operating condition, the output unit 13 transmits a message to the user terminal 2 asking the user whether the operating condition needs to be modified (step ST6). If no modification is required, the IoT device and the operating condition OC of the IoT device selected by the user are output to the program generation unit 20 (step ST7).

[0046] On the other hand, in step ST6, when information indicating that the user desires a modification is received from the user terminal 2, the prompt generation unit 23 generates a prompt for modifying the operating condition OC of the IoT device according to the user's desire, and outputs the prompt to the generation AI model 42. The generation AI model 42 inputs the prompt and outputs the modified operating condition OC (step ST8). Then, the output unit 13 outputs the modified operating condition of the IoT device by the IoT device and the user to the program generation unit 20 (step ST9). The acquisition unit 21 of the program generation unit 20 acquires a device list including one or more IoT devices and information indicating the operating condition OC of these IoT devices.

[0047] Next, as shown in FIG. 9, the API search unit 22 of the program generation unit 20 searches an external system using one or more IoT devices included in the device list as a query, and acquires the APIs of these IoT devices (step ST9). Next, the prompt generation unit 23 generates a second prompt P2 based on the acquired operating condition OC of the IoT device, and inputs the second prompt P2 to the generation AI model 42. The generation AI model 42 generates a program PR1 for operating the IoT device using the API according to the specified operating condition OC (step ST10). The program generation unit 20 outputs the generated program PR1 to the incident check unit 30. The acquisition unit 31 of the incident check unit 30 acquires the program PR1 output from the program generation unit 20.

[0048] Next, the prompt generation unit 23 generates a third prompt P3 based on the acquired program PR1. The generation AI model 42 inputs the third prompt P3, and searches for past incident cases related to the household appliances operated by the IoT devices in the device list based on the instruction of the third prompt P3 (step ST11). Also, the generation AI model 42 modifies the program PR1 based on the incident cases related to the household appliances (step ST12). Then, the support device 1 transmits the modified program PR2 to the user terminal 2.

[0049] Next, with reference to Figure 10, a smart home construction support program for causing a computer to function as a support device 1 according to one embodiment will be described. Figure 10 is a diagram showing the functional configuration of the smart home construction support program P. The smart home construction support program P comprises a main module M1, a request concretization module M10, a program generation module M20, and an incident check module M30. The main module M1 comprehensively controls the processing of the support device 1.

[0050] The request concretization module M10 comprises a reception module M11, a question generation module M12, an output module M13, a prompt generation module M14, and a device search module M15. The functions realized by executing the reception module M11, question generation module M12, output module M13, prompt generation module M14, and device search module M15 are the same as the functions of the reception unit 11, question generation unit 12, output unit 13, prompt generation unit 14, and device search unit 15 described above.

[0051] The program generation module M20 includes an acquisition module M21, an API search module M22, and a prompt generation module M23. The functions realized by executing the acquisition module M21, the API search module M22, and the prompt generation module M23 are the same as the functions of the acquisition unit 21, the API search unit 22, and the prompt generation unit 23 described above.

[0052] The incident check module M30 includes an acquisition module M31 and a prompt generation module M32. The functions realized by executing the acquisition module M31 and the prompt generation module M32 are the same as the functions of the acquisition unit 31 and the prompt generation unit 32 described above.

[0053] The smart home construction support program P is provided, for example, in the form of data recorded on a recording medium M such as a CD-ROM or DVD-ROM, or on semiconductor memory. Alternatively, the smart home construction support program P may be provided via a communication network as a computer data signal superimposed on a carrier wave.

[0054] As explained above, in the support device 1, an IoT device is selected according to the user's request, and a program PR1 is generated to operate the IoT device according to the operating conditions OC corresponding to that request. Therefore, the user can easily build a smart home even without specialized knowledge of IoT devices and programs.

[0055] Furthermore, in the support device 1, the incident check unit 30 checks the safety of the generated program PR1 based on past incident cases, and if necessary, program PR1 is modified into program PR2 that avoids past incident cases. Therefore, a highly safe program can be provided to the user.

[0056] Furthermore, the support device 1 is not limited to the configuration shown in Figure 1, and as shown in Figure 11, at least a portion of the storage unit 41 and the generated AI model 42 may be located within the support device 1. Also, each component of the support device 1 may be implemented in the user terminal 2. In this case, the user terminal 2 constitutes the support device 1.

[0057] The block diagram shown in Figure 1 represents functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more devices described above.

[0058] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0059] For example, the support device 1 in one embodiment may function as a computer. Figure 12 shows an example of the hardware configuration of the support device 1 according to this embodiment. Physically, the support device 1 may be configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0060] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the support device 1 may include one or more of the devices shown in Figure 12, or it may be configured to omit some of the devices.

[0061] Each function in the support device 1 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, allowing the processor 1001 to perform calculations and control communication by the communication device 1004, as well as the reading and / or writing of data in the memory 1002 and storage 1003.

[0062] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may consist of a central processing unit (CPU) that includes interfaces with peripheral devices, control units, arithmetic units, registers, etc. For example, each component shown in Figure 1 may be implemented in the processor 1001.

[0063] Furthermore, the processor 1001 reads programs (program code), software modules, and data from the storage 1003 and / or communication device 1004 into the memory 1002, and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, each component of the support device 1 may be stored in the memory 1002 and implemented by a control program that runs on the processor 1001. Although the above-described processes have been explained as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0064] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out an information processing method according to one embodiment of the present invention.

[0065] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including memory 1002 and / or storage 1003.

[0066] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via a wired and / or wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0067] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0068] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may consist of a single bus, or different buses may be used for communication between devices.

[0069] Furthermore, the support device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0070] The notification of information is not limited to the embodiments described herein and may be carried out by other means. For example, the notification of information may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0071] Each aspect / embodiment described in this disclosure may be applied to at least one of the following systems: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0072] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0073] The specific operations described in this disclosure as being performed by a base station may, in some cases, be performed by its upper node. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal can be performed by the base station and at least one other network node (for example, an MME or S-GW, but not limited to these). Although the above example illustrates the case where there is one other network node besides the base station, it may also be a combination of multiple other network nodes (for example, an MME and an S-GW).

[0074] Information can be output from a higher layer (or lower layer) to a lower layer (or higher layer). Input and output may also occur via multiple network nodes.

[0075] Input and output information may be stored in a specific location (e.g., memory) or managed in a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0076] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0077] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0078] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0079] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0080] Furthermore, software, instructions, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and digital subscriber lines (DSL) and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included in the definition of a transmission medium.

[0081] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0082] In addition, terms described in this disclosure and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meaning.

[0083] The terms “system” and “network” as used in this disclosure are interchangeable.

[0084] Furthermore, the information, parameters, etc., described in this disclosure may be expressed as absolute values, relative values ​​from a given value, or by corresponding other information. For example, wireless resources may be indicated by an index.

[0085] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.

[0086] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0087] As used in this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based on at least."

[0088] Where the terms “first,” “second,” etc., are used in this disclosure, no reference to those elements shall generally limit the quantity or order of those elements. These terms may be used herein as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements shall not imply that only two elements may be employed therein, or that the first element must precede the second element in any way.

[0089] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0090] To the extent that “include,” “including,” and their variations are used herein or in the claims, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used herein or in the claims is not intended to be exclusive OR.

[0091] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0092] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0093] The support device 1 and smart home construction support method of this disclosure may have the following configurations.

[0094] [1] A device for supporting the construction of a smart home, comprising: a request concretization unit that generates a first prompt to instruct a generating AI model to output information indicating an IoT device to be used to meet the user's requests and information indicating the operating conditions of the IoT device, based on user input including information indicating the user's requests regarding the smart home; and a program generation unit that generates a second prompt to instruct the generating AI model to generate a program for operating the IoT device in accordance with the operating conditions obtained by inputting the first prompt to the generating AI model. [2] The device according to [1], further comprising an incident check unit that generates a third prompt to instruct the generating AI model to check the safety of the program obtained by inputting the second prompt to the generating AI model. [3] The request concretization unit generates a fourth prompt that instructs the generation AI model to generate a question sentence inquiring about the home appliances owned by the user, inputs the fourth prompt to the generation AI model and obtains an answer from the user to the question sentence obtained, and the first prompt includes information indicating the user's answer, as described in [1] or [2]. [4] The first prompt includes an instruction to cause the generation AI model to output a plurality of operating conditions for the IoT device, as described in any one of [1] to [3]. [5] The request concretization unit is configured to obtain information indicating the user's attributes, and the first prompt includes information indicating the attributes, as described in any one of [1] to [4]. [6] The program generation unit is configured to obtain an API for controlling the IoT device, and the second prompt includes an instruction to cause the generation AI model to generate the program using the obtained API, as described in any one of [1] to [5]. [7] The apparatus according to [2], wherein the third prompt includes an instruction to cause the generating AI model to modify the program so as to avoid past incident cases.[8] A method for supporting the construction of a smart home, comprising: acquiring user input including information indicating the user's requests relating to the smart home; generating a first prompt to instruct a generating AI model to output information indicating an IoT device to be used to meet the user's requests and information indicating the operating conditions of the IoT device, based on the user input; inputting the first prompt to the generating AI model to acquire information indicating the IoT device and information indicating the operating conditions of the IoT device; generating a second prompt to instruct the generating AI model to generate a program for operating the IoT device in accordance with the acquired operating conditions; and inputting the second prompt to the generating AI model to generate the program. [9] The method according to [8], further comprising: generating a third prompt to instruct the generating AI model to check the safety of the generated program; and inputting the third prompt to the generating AI model to generate the program whose safety has been checked.

[0095] 1...Smart home construction support device, 10...Request concretization unit, 20...Program generation unit, 30...Incident check unit, 42...Generated AI model, P1...First prompt, P2...Second prompt, P3...Third prompt.

Claims

1. A device for supporting the construction of a smart home, comprising: a request concretization unit that generates a first prompt to instruct a generating AI model to output information indicating an IoT device to be used to meet the user's requests and information indicating the operating conditions of the IoT device, based on user input including information indicating the user's requests regarding the smart home; and a program generation unit that generates a second prompt to instruct the generating AI model to generate a program for operating the IoT device in accordance with the operating conditions obtained by inputting the first prompt to the generating AI model.

2. The apparatus according to claim 1, further comprising an incident check unit that generates a third prompt for instructing the generating AI model to check the safety of the program obtained by inputting the second prompt to the generating AI model.

3. The apparatus according to claim 1, wherein the request concretization unit generates a fourth prompt that instructs the generation AI model to generate a question sentence inquiring about the home appliances owned by the user, inputs the fourth prompt to the generation AI model and obtains an answer from the user to the question sentence obtained, and the first prompt includes information indicating the user's answer.

4. The apparatus according to claim 1, wherein the first prompt includes an instruction to cause the generating AI model to output a plurality of operating conditions for the IoT device.

5. The apparatus according to claim 1, wherein the request concretization unit is configured to acquire information indicating the user's attributes, and the first prompt includes the information indicating the attributes.

6. The apparatus according to claim 1, wherein the program generation unit is configured to acquire an API for controlling the IoT device, and the second prompt includes an instruction to cause the generated AI model to generate the program using the acquired API.

7. The apparatus according to claim 2, wherein the third prompt includes an instruction to cause the generating AI model to modify the program so as to avoid past incident cases.

8. A method for supporting the construction of a smart home, comprising: acquiring user input including information indicating the user's requests regarding the smart home; generating a first prompt to instruct a generating AI model to output information indicating an IoT device to be used to meet the user's requests and information indicating the operating conditions of the IoT device, based on the user input; inputting the first prompt to the generating AI model to acquire information indicating the IoT device and information indicating the operating conditions of the IoT device; generating a second prompt to instruct the generating AI model to generate a program for operating the IoT device according to the acquired operating conditions; and inputting the second prompt to the generating AI model to generate the program.

9. The method according to claim 8, further comprising the steps of: generating a third prompt for instructing the generating AI model to check the safety of the generated program; and inputting the third prompt into the generating AI model to generate the program whose safety has been checked.

Images