Information processing device and information processing method

Abstract

An information processing device (10) comprises: a reception unit (11) that receives at least generation request information of content related to the design of a next process following a current process whose design has been completed in a plurality of processes related to architectural design, and information relating to sketch images created in each process up to the current process in a design process; a determination unit (12) that, on the basis of information relating to a condition of a building, determines an architect suited for the condition; and an output unit (13) that, on the basis of at least information on the determined architect and the information relating to the sketch images of each process up to the current process, outputs a sentence to be input into a prompt for providing instruction regarding the generation of content related to the design of the next process.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] In earthquake-prone Japan, many buildings (facilities, residences, etc.) designed and constructed by various architects are rarely preserved for long periods of time and are often demolished, except for those that are preserved as valuable cultural heritage. Therefore, it is desirable to preserve related information so that their architectural designs can be recreated. In addition, there are architects who were not highly regarded during their lifetime but became highly regarded after their deaths, and it is desirable to preserve related information so that the architectural designs of these architects can also be recreated.

[0003] Meanwhile, in recent years, various types of content have been generated using generative artificial intelligence (AI) models. A generative AI model is a model that can generate content (generation results) in response to a prompt containing input information, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and return the content as response information. Non-Patent Document 1 listed below mentions the use of a generative AI model to create an architectural design that follows the style of a famous architect.

[0004] Nikkei CrossTech online article "Ask Kengo Kuma about how to interact with generative AI" https: / / xtech.nikkei.com / atcl / nxt / column / 18 / 02449 / 053000006 /

[0005] In general, in architectural design, architects repeatedly create sketches (esquisse images) to refine designs and design concepts during the design process. However, the above-mentioned Non-Patent Document 1 does not mention the effective use of a generative AI model in the process of refining the esquisse images.

[0006] Therefore, the present disclosure aims to utilize a generative AI model to easily obtain accurate sketch images based on an architect's style that matches the architectural conditions.

[0007] The information processing device of the present disclosure includes at least a reception unit that receives request information for generating content related to the design of a process next to a current process that has been completed in multiple processes related to architectural design, and information related to sketch images created in each process up to the current process in the design process; a determination unit that determines an architect who meets the conditions based on information related to the conditions of the building; and an output unit that outputs input text to a prompt to instruct the generation of content related to the design of the next process based on at least the information related to the determined architect and the information related to the sketch images in each process up to the current process.

[0008] According to the present disclosure, by utilizing a generative AI model, it is possible to easily obtain accurate sketch images based on the architect's style that match the architectural conditions.

[0009] FIG. 1 is a configuration diagram of an entire system including an information processing device. FIG. 2 is a flow diagram of processing executed by the information processing device. FIG. 3 is a diagram showing an example of an sketch image of a current step, and FIG. 4 is a diagram showing an example of an sketch image of a next step. FIG. 4 is a diagram showing an example of an input sentence to a prompt. FIG. 5 is a diagram showing an example of an sketch image generated through all steps. FIG. 6 is a configuration diagram in a form in which an output unit refers to a learning model. FIG. 7 is a diagram showing another example configuration of an entire system. FIG. 8 is a diagram showing an example hardware configuration of an information processing device.

[0010] Hereinafter, an embodiment of an information processing device and an information processing method according to the present disclosure will be described with reference to the drawings. In the following embodiment, a form will be described in which a large language model (LLM) that is mainly used for text generation is used as an example of a generative AI model.

[0011] [Configuration of a system including an information processing device] Fig. 1 shows a configuration diagram of a system 1 including an information processing device 10 according to the present disclosure. As shown in Fig. 1, the system 1 includes an external server 30A on which a large-scale language model (LLM) 30 runs, the information processing device 10, and an in-house server 20A on which an in-house system runs. The in-house server 20A includes an in-house database (in-house DB) 20 that stores in advance various data to be processed in the in-house system (such as related information on building conditions and related information on sketch images, which will be described later). Note that the information processing device 10 can employ various information processing devices (such as a smartphone, a mobile phone, a smartwatch, a wearable device, a laptop computer, a desktop computer, or a server) as its hardware.

[0012] An RAG (Retrieval-Augmented Generation) system application is installed on the information processing device 10, and the RAG system operates. The RAG system is a type of prompt extension technology used for corporate information sharing between LLMs. Specifically, when a generation request is made to an LLM using an instruction (input text in response to a prompt) based on a content generation request, the system searches for related information (reference information) in advance if necessary and requests the LLM to generate the content together with the instruction. The present disclosure corresponds to an invention that extends and improves the functionality of the RAG system. It has an aspect of enriching and optimizing the instruction (input text in response to a prompt) for the LLM 30 using various information obtained from an internal database 20 or an external server (not shown) that cannot be directly accessed by the LLM 30. The information processing device 10 includes a receiving unit 11, a determining unit 12, and an output unit 13 to realize the functions related to the present disclosure. The functions of each unit are described below.

[0013] The reception unit 11 is a functional unit that receives (1) content generation request information regarding the design of the next process after the current process, which has been completed in multiple processes related to architectural design, (2) information regarding the conditions of the building, and (3) information regarding sketch images created in each process up to the current process in the design process. However, (2) information regarding the conditions of the building is not required as information to be received, and predetermined information or information acquired in advance may be used. The content generation request information (1) above is request information that is notified to the reception unit 11 when a generation request button provided on a web page or application page displayed on the display of the information processing device 10 is pressed.

[0014] The information relating to the conditions for construction in (2) above includes at least one of the following: - The use of the building to be constructed (private residence, apartment complex, office building, etc.); - The specifications of the building (area, height, lot area, shape, color, pattern, materials, etc.); - Information relating to costs (budget, selling price, average rental price, etc.); - Information relating to the location and surrounding environment (cliff area, restricted roads, number of floors limit, sunlight, environment, climate, restrictions based on relevant laws and regulations such as the Building Standards Act, etc.); - Information relating to the client of the construction (preference information (strong preference for design, etc.), attribute information (public housing manager, etc.)), etc.).

[0015] The "sketch image" in (3) above refers to a sketch drawn to refine a design or concept during the architectural design process, such as the image shown in Figure 3(a), which shows a design concept in which a portion of a building protrudes horizontally from the side wall of the building. Sketch images are often actually hand-drawn images. Information about the sketch image in (3) above includes the image file of the current process and the image files from the previous process, as well as text information recorded at each process (e.g., the designer's notes, requests received from the building client, etc.).

[0016] Furthermore, if there are deficiencies or gaps in the received (2) information about the conditions of the building and (3) information about the sketch images created in each step up to the current step in the design process, the reception unit 11 may complement the deficiencies or gaps in the (2) information about the conditions of the building and (3) information about the sketch images by searching the in-house DB 20 or an external server (not shown) using keywords included in the content generation request information (1). Note that such complementation processing may be performed by the determination unit 12 (described later) instead of the reception unit 11.

[0017] The determination unit 12 is a functional unit that determines an architect who meets the building conditions based on information about the building conditions. Specifically, the determination unit 12 determines the architect who meets the building conditions based on at least one of the following: (a) design experience according to the building's intended use (e.g., experience designing buildings on cliffs, experience designing buildings on narrow urban lots, etc.); (b) reputation regarding cost consideration (e.g., reputation for designing buildings that are cost-effective with a budget lower than the market rate, reputation for design content that is acceptable but lacks cost consideration); (c) track record or reputation for design that takes the surrounding environment into consideration (e.g., track record and high reputation for designing buildings that are environmentally friendly in locations near the sea and exposed to strong sea breezes); or (d) design award history (e.g., Good Design Award, Japan Space Design Award, etc.). The determination unit 12 may obtain the information (a) to (d) that serves as the basis for the determination not only from the reception unit 11 but also by searching the in-house database 20 or an external server (not shown) using keywords related to the required information. The determination unit 12 may also determine multiple architects who meet the architectural requirements, and in this case, determine the ratio of each of the multiple architects according to their degree of suitability for the requirements. For example, the determination unit 12 may determine that architect A will be assigned 70% and architect B will be assigned 30%.

[0018] The output unit 13 is a functional unit that outputs input text (instructions to the LLM 30) to a prompt to instruct the creation of content (including image files related to the design of the next process and a description of the concept for the image files) based on information about the building conditions, information about the selected architect, and information about sketch images of each process up to the current process. However, the "information about the building conditions" is not essential as the basic information; information about the selected architect based on the "information about the building conditions" and information about sketch images of each process up to the current process may also be used as the basic information. Furthermore, the output unit 13 receives and outputs content related to the design of the next process (here, content including image files related to the design of the next process and a description of the concept for the image files) as the creation result output from the LLM 30 in response to the input of the input text. Examples of input text to the prompt and examples of content output from the LLM 30 are described in detail in the processing description of FIG. 2 .

[0019] Furthermore, the output unit 13 may include information indicating the "degree" of the conditions for content generation in the sentence input to the prompt (the instruction sentence to the LLM 30). For example, as described above, if the determination unit 12 determines that architect A and architect B are 70% and 30%, respectively, as architects who meet the architectural conditions, the output unit 13 may include information indicating the degree of the architects, such as "architect A is 70%, architect B is 30%," in the sentence input to the prompt. This makes it possible to instruct content generation based on a complex architectural style, such as using architect A's architectural style as a base and partially incorporating architect B's architectural style, as if it were thought up by a human being. Note that the information indicating the degree may be information determined by the determination unit 12 as described above, information received from the user, or information registered in advance by the administrator.

[0020] [Regarding Processing Executed in Information Processing Apparatus] Hereinafter, processing executed in the information processing apparatus 10 (processing related to the information processing method of the present disclosure) will be described with reference to the flow diagram of FIG.

[0021] When a user presses a generation request button provided on a web page or application page displayed on the display of the information processing device 10, the reception unit 11 is notified of content generation request information related to the design of the next process, and the process of Figure 2 begins to be executed when the reception unit 11 receives the above generation request information.

[0022] In response to receiving the creation request information, the reception unit 11 receives, along with the (1) creation request information, (2) information about the conditions of the building and (3) information about the sketch images created in each step of the design process up to the current step (step S1). Note that the (2) information about the conditions of the building is not required as the information to be received, and predetermined information or information acquired in advance may be used. In this case, if there are deficiencies or missing information in the received (2) information about the conditions of the building and (3) information about the sketch images created in each step of the design process up to the current step, the reception unit 11 may supplement the missing or missing information in the (2) information about the conditions of the building and the (3) information about the sketch images by searching the in-house DB 20 or an external server (not shown) using keywords included in the (1) content creation request information.

[0023] Next, the determination unit 12 determines an architect who meets the architectural conditions based on information related to the architectural conditions (e.g., at least one of the aforementioned (a) design experience according to the intended use of the building, (b) reputation regarding cost consideration, (c) track record or evaluation of designs that take the surrounding environment into consideration, or (d) design award history) (step S2). The information on which the determination is based (e.g., the information (a) to (d) above) is not only obtained from the reception unit 11, but also by searching the in-house database 20 or an external server (not shown) using keywords related to the required information. The determination unit 12 may also determine multiple architects who meet the architectural conditions, and in this case, determine the ratio of each of the multiple architects according to their degree of suitability for the conditions. For example, architect A may be assigned 70% and architect B may be assigned 30%.

[0024] Next, the output unit 13 outputs an input sentence (an instruction sentence to the LLM 30) to the prompt for instructing the creation of content related to the design of the next process (here, content including image files and a description of the concept for the image files) based on the information on the building conditions received in step S1, information on the sketch images of each process up to the current process, and information on the architect determined in step S2 (step S3). Note that the "information on the building conditions" is not essential as the basic information; information on the architect determined based on the "information on the building conditions" and information on the sketch images of each process up to the current process may also be used as the basic information. The input sentence to the prompt may include, for example, information on the role, task, and conditions, as well as the shape, pattern, color (e.g., red, blue, white, etc.) of the building, its size, display location in the virtual space, and display timing. The "size" may, for example, represent the width, depth, and height of the building, its size along the X, Y, and Z axes in a three-dimensional coordinate system in the virtual space, or its size relative to existing buildings. For example, an input sentence containing multiple items such as role, task, and condition, as shown in Figure 4, might look like this: "Role: You are Architect A. Task: Based on the sketch images entered up to the current process, generate an image file and concept explanation for the design of the next process, taking into account the following conditions. Conditions: - The building is a public housing complex of approximately 10 stories. - The surrounding area is an environment with many housing complexes. - The building should have excellent design and functionality."

[0025] 4, the output unit 13 may include information indicating the "degree" of the conditions for content generation in the input sentence for the prompt. As described above, if the determination unit 12 determines that architect A is 70% and architect B is 30% as architects who meet the architectural conditions, the output unit 13 includes information indicating the degree of the architects, such as "architect A is 70% and architect B is 30%," in the input sentence. This makes it possible to instruct content generation based on a complex architectural style, such as using architect A's architectural style as a base and incorporating some of architect B's architectural style, as if it were thought up by a human being.

[0026] Subsequently, the LLM 30 outputs an image file related to the design of the next process and a description of the concept of the image file as the generated content, and the output unit 13 acquires and outputs the content (step S4). As an example of the output content, FIG. 3(b) shows an example of an image file (sketch image) related to the design of the next process. The sketch image of FIG. 3(b) is an image generated and output by the LLM 30 based on the sketch image of the current process shown in FIG. 3(a), and the bold lines in FIG. 3(b) indicate the added portion. The sketch image of the current process in FIG. 3(a) shows a design concept in which a portion of the building protrudes horizontally from the side wall of the building. An example of the description of the concept for the sketch image of FIG. 3(b) is, "By adding a portion that protrudes horizontally from the portion that protrudes horizontally from the side wall of the building, we have further evolved the concept of effective use of three-dimensional space." Such a description of the concept may further include comments regarding the building's components, area, cost, etc.

[0027] In this way, by utilizing the generative AI model (LLM30), a user can easily obtain a highly accurate sketch image based on the architect's style that matches the architectural requirements. By repeating the process of obtaining the sketch image for the next step in this manner, the remaining design steps can be smoothly carried out, and an image such as the image shown in FIG. 5 can be obtained as a sketch image generated through all steps. FIG. 5 shows a diagram in which multiple horizontally protruding portions are provided from the side wall (hatched portion) of a building. This also contributes to the preservation of the architectural design styles of various architects, and related information can be saved so that the architectural designs of various architects can be reproduced. For example, related information can be saved so that architectural designs by architects who were not highly regarded during their lifetime but became highly regarded after their death can be reproduced.

[0028] The following configuration (FIG. 6) using a learning model is also possible. That is, the output unit 13 shown in FIG. 6 transmits (i) "information related to sketch images (image files for the current process and image files up to the previous process, and text information recorded at each process (e.g., designer's notes, requests received from the building client, etc.))" received by the receiving unit 11 and (ii) "content (image files related to the design of the next process and explanatory text for the image files)" output from the LLM 30 to the in-house server 20A, and performs supervised machine learning in an in-house system running on the in-house server 20A, using the above (i) as an explanatory variable and the above (ii) as a target variable, thereby generating the learning model 21. This creates a mechanism in which the above (ii) is output from the learning model 21 in response to the above (i) being input to the learning model 21. In response to inputting the above (i) at the time of generating a new prompt into the learning model 21, the output unit 13 acquires the above (ii) from the learning model 21 and includes the acquired (ii) as reference information in the input sentence for the prompt. In this case, it is expected that more appropriate content can be acquired from the LLM 30 by effectively utilizing the vast amount of performance data in which the above (ii) was output from the above (i) in past processing.

[0029] (Modification of System 1) System 1 is not limited to the configurations shown in Figures 1 and 6, and may have a configuration in which LLM 30 is implemented inside information processing device 10, as shown in Figure 7. This configuration can be realized by installing an application that executes the functions of LLM 30 in information processing device 10. Furthermore, although Figures 1 and 6 show examples in which in-house DB 20 is implemented outside information processing device 10 (for example, on a network), in-house DB 20 may also be implemented inside information processing device 10.

[0030] The gist of the present disclosure lies in the following [1] to [6]. [1] An information processing device comprising: a receiving unit that receives at least information requesting the generation of content related to the design of a step next to a current step for which design has been completed among a plurality of steps related to architectural design, and information related to sketch images created for each step up to the current step in the design steps; a determining unit that determines an architect who meets information related to the conditions of the building based on the information about the conditions; and an output unit that outputs an input sentence to a prompt for instructing the generation of content related to the design of the next step based on at least the information about the determined architect and the information about the sketch images for each step up to the current step. [2] The information processing device described in [1], wherein the information related to the conditions of the building includes at least one of: the use of the building to be built, the specifications of the building, information about costs, information about the location and surrounding environment, or information about the client of the building. [3] The information processing device according to [1] or [2], wherein the determination unit determines the architect who meets the conditions based on at least one of: experience in designing according to the use of the building; reputation for consideration of cost; track record or evaluation of designs that take the surrounding environment into consideration; or history of design awards. [4] The information processing device according to any one of [1] to [3], wherein the output unit includes information indicating the level of the conditions for generating the content in an input sentence to the prompt. [5] The information processing device according to any one of [1] to [4], wherein the output unit outputs an input sentence to the prompt for instructing the generation of the content including an image file related to the design of the next process and an explanatory text about the concept of the image file. [6] The information processing device according to [5], wherein the output unit receives and outputs the content including an image file related to the design of the next process and an explanatory text about the concept of the image file as a generation result output from a generative AI model in response to input of the input sentence to the prompt.[7] An information processing method comprising the steps of: an information processing device receiving, at least, request information for generating content related to the design of a process next to a current process that has been completed among a plurality of processes related to architectural design, and information related to sketch images created at each process up to the current process in the design process; a step by the information processing device determining an architect who meets the conditions based on information related to the architectural conditions; and a step by the information processing device outputting an input sentence to a prompt for instructing the generation of content related to the design of the next process based on at least the information related to the determined architect and the information related to the sketch images at each process up to the current process.

[0031] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 8), etc.] The block diagrams used in the description of the above embodiments show functional blocks. 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 a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may be realized by combining the single device or multiple devices with software.

[0032] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0033] For example, an information processing device according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 8 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0034] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0035] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0036] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0037] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. While the various processes have been described 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 by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0038] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0039] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0040] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0041] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0042] 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 be configured using a single bus, or may be configured using different buses between each device.

[0043] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0044] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0045] Each aspect / embodiment described in the present disclosure may be implemented using any of the following standards: LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal number)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.17 (WiMAX (registered trademark)), IEEE 802.19 (WiMAX (registered trademark)), IEEE 802.20 (WiMAX (registered trademark)), IEEE 802.21 (Wi-Fi (registered trademark)), IEEE 802.22 (WiMAX (registered trademark)), IEEE 802.23 (WiMAX (registered trademark)), IEEE 802.24 (WiMAX (registered trademark)), IEEE 802.25 (WiMAX (registered trademark)), IEEE 802.26 (WiMAX (registered trademark)), IEEE 802.27 (WiMAX (registered trademark)), IEEE 802.28 (WiMAX (registered trademark)), IEEE 802.29 (WiMAX (registered trademark)), IEEE 802.30 (WiMAX (registered trademark)), IEEE 802.31 (Wi-Fi (registered trademark)), IEEE 802.32 (WiMAX (registered trademark)), IEEE 802.33 (WiMAX (registered trademark)), IEEE 802.34 ( The present invention may be applied to at least one of systems using 802.20, Ultra-Wideband (UWB), Bluetooth, or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. It may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0046] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0047] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0048] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0049] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0050] Although the present disclosure has been described in detail above, it is 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 spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0051] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0052] Software, instructions, information, etc. may also be transmitted or received over 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, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0053] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0054] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0055] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0056] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0057] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0058] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0059] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0060] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0061] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0062] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0063] In the present 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 "coupled" may also be interpreted in the same way as "different."

[0064] 1...system, 10...information processing device, 11...reception unit, 12...decision unit, 13...output unit, 20...in-house DB, 20A...in-house server, 30...LLM, 30A...external server, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An information processing device comprising: a reception unit that receives at least information requesting the generation of content related to the design of the next step after a current step that has been completed in multiple steps related to architectural design, and information related to sketch images created in each step up to the current step in the design process; a determination unit that determines an architect who meets the conditions based on information related to the architectural conditions; and an output unit that outputs input text to a prompt to instruct the generation of content related to the design of the next step based on at least information related to the determined architect and information related to the sketch images of each step up to the current step.

2. The information processing device of claim 1, wherein the information regarding the conditions of the building includes at least one of the following: the use of the building to be built, the specifications of the building, information regarding costs, information regarding the location and surrounding environment, or information regarding the person requesting the building.

3. The information processing device of claim 1, wherein the determination unit determines the architect who meets the conditions based on at least one of the following: experience in designing according to the use of the building; reputation for consideration of costs; track record or evaluation of designs that take the surrounding environment into consideration; or history of winning design awards.

4. The information processing device according to claim 1, wherein the output unit includes information indicating a degree of a condition for generating the content in an input sentence for the prompt.

5. The information processing device according to claim 1, wherein the output unit outputs an input sentence to the prompt for instructing the generation of an image file relating to the design of the next process and the content including an explanatory text of the concept of the image file.

6. The information processing device according to claim 5, wherein the output unit receives and outputs the content including an image file relating to the design of the next process and an explanatory text of the concept of the image file as a generation result output from the generative AI model in response to input of the input sentence to the prompt.

7. An information processing method comprising the steps of: an information processing device receiving at least information requesting the generation of content related to the design of a process next to a current process that has been completed in a plurality of processes related to architectural design, and information related to sketch images created in each process up to the current process in the design process; a step by the information processing device determining an architect who meets the conditions based on information related to the architectural conditions; and a step by the information processing device outputting an input sentence to a prompt to instruct the generation of content related to the design of the next process based on at least the information related to the determined architect and the information related to the sketch images in each process up to the current process.