Data processing device, data processing method and data processing program

Abstract

To provide a data processing device, a data processing method and a program capable of reducing a work burden for creating a drawing.SOLUTION: A data processing device includes: a receiving unit 292 that accepts, from a user terminal operated by a user, a source drawing that is a source for drawing creation; a variable obtaining unit 294 that obtains, from an AI-OCR model, variable data by inputting the source drawing in the AI-OCR model that has learnt drawings created in past as learning data; and an obtaining unit 296 which accepts, from the user terminal, a prompt that instructs the creation of a new drawing, inputs, to a generative AI model 58A, the prompt together with the source drawing and the variable data, and obtains code information from the output by the generative AI model.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the conventional technology can respond to dialogue using a language model, it cannot create drawings, and there is room for improvement. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device that includes: a reception unit that receives an original drawing that is the basis for drawing; a variable acquisition unit that inputs the original drawing into a learning model that has been trained using drawings created in the past, and acquires variable data necessary for drawing a new drawing that includes newly installed equipment from the output of the learning model; and an acquisition unit that inputs instruction information that instructs the creation of the new drawing, together with the original drawing and the variable data, into a generative AI model that has been trained using public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0006] A second aspect of the technology disclosed herein is a data processing device that includes: a reception unit that receives an original drawing that is the basis for drawing and instruction information that instructs the creation of a new drawing that includes newly installed equipment; and an acquisition unit that inputs the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0007] A third aspect of the technology disclosed herein is a data processing method that receives an original drawing that is the basis for drawing, inputs the original drawing into a learning model that has been trained using drawings created in the past, obtains variable data necessary for drawing a new drawing that includes newly installed equipment from the output of the learning model, inputs instruction information that instructs the creation of the new drawing together with the original drawing and the variable data into a generative AI model that has been trained using public data, and executes a process of obtaining at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0008] A fourth aspect of the technology disclosed herein is a data processing method in which a computer receives an original drawing that serves as the basis for drawing and instruction information that instructs the creation of a new drawing that includes newly installed equipment, inputs the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and executes a process of obtaining at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0009] A fifth aspect of the technology disclosed herein is a data processing program for causing a computer to execute a process of accepting an original drawing that is the basis for drawing, inputting the original drawing into a learning model that has been trained using drawings created in the past, obtaining variable data necessary for drawing a new drawing that includes newly installed equipment from the output of the learning model, inputting instruction information that instructs the creation of the new drawing together with the original drawing and the variable data into a generative AI model that has been trained using public data, and obtaining at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0010] A sixth aspect of the technology of the present disclosure is a data processing program for causing a computer to execute a process of receiving an original drawing that serves as the basis for drawing and instruction information that instructs the creation of a new drawing that includes newly installed equipment, inputting the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and obtaining at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Figure 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a user terminal. [Figure 3] FIG. 1 is a diagram showing an example of a plan view illustrating the positional relationship between an existing antenna and a new antenna. [Figure 4] FIG. 10 is a diagram showing an example of a side view illustrating the positional relationship between an existing antenna and a new antenna. [Figure 5] FIG. 10 is a diagram for explaining the processing of a specific processing unit. [Figure 6] FIG. 1 is a diagram illustrating an example of an AI-OCR model. [Figure 7] 2 is a block diagram illustrating a schematic functional configuration of a specific processing unit of the data processing device. FIG. [Figure 8]10 is a flowchart illustrating an example of an operation of a specific process by a data processing device. [Figure 9] 10A and 10B are diagrams for explaining the processing of a specific processing unit according to a modified example. [Figure 10] FIG. 10 is a block diagram illustrating a schematic functional configuration of a specific processing unit of a data processing device according to a modified example. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), or an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0020] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a user terminal 14. An example of the data processing device 12 is a server. An example of the user terminal 14 is a personal computer or a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0021] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0022] The user terminal 14 includes a computer 36, a reception device 38, an output device 40, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38 and the output device 40 are also connected to the bus 52.

[0023] The reception device 38 is equipped with a keyboard, a mouse, etc., and receives user input. The reception device 38 may also receive user input by touch of an indicator (for example, a pen or a finger) by detecting contact with the touch panel, or may receive user input by voice by detecting the user's voice by a microphone. The control unit 46A transmits data indicating the received user input to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0024] The output device 40 includes a display 40A and a speaker 40B, and presents data to a person by outputting the data in a form of expression that can be perceived by the person (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46.

[0025] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0026] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminal 14.

[0027] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0028] Storage 32 stores a generation AI model 58A and an AI-OCR (Optical Character Recognition / Reader) model 58B. Generation AI model 58A and AI-OCR model 58B are used by specific processing unit 290. Note that, although this embodiment shows an example in which generation AI model 58A and AI-OCR model 58B are stored in storage 32 of the same data processing device 12, they may also be stored in different devices and executed by different devices.

[0029] The generative AI model 58A is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58A is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58A, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58A performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0030] AI-OCR model 58B is a learning model that uses previously created drawings related to the construction of mobile phone base stations as training data, extracts predetermined specific words representing equipment, such as "antenna" and "sector," and figures representing equipment, such as specific equipment icons, from the drawings using OCR and image recognition technology, and obtains the coordinates of the extracted equipment. In other words, by inputting a drawing containing equipment into AI-OCR model 58B, AI-OCR model 58B can obtain coordinates representing the location of the equipment in the drawing. For example, one example of coordinates obtained by AI-OCR model 58B is the latitude and longitude of the four corners of an antenna in the drawing.

[0031] In the user terminal 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0032] Incidentally, when constructing base station equipment such as mobile phone antennas, there are cases where multiple operators' equipment is installed on the same building or tower. In such cases, a co-location consultation is held between the operators who install their equipment on the same building or tower, based on a gentleman's agreement, to discuss whether there will be any radio wave interference between them. Co-location consultations are held when multiple operators install their equipment on the same building or tower, based on a gentleman's agreement, to discuss whether there will be any radio wave interference between them. In addition, there are cases where a company adds its own equipment to a building or tower that already has its own equipment installed. In such cases, no consultation is held between the operators, but it is necessary to check whether there will be any radio wave interference between the existing equipment and the newly installed equipment.

[0033] In co-location negotiations, it is necessary to create a consultation drawing, but if there are many pieces of equipment to be discussed, the amount of equipment and information that needs to be included on the drawing increases, making the drawing cumbersome. In addition, since it is necessary to comply with many drawing creation rules, creating the drawing becomes a tedious task. Drawings are not only created when conducting negotiations between businesses, but also when adding company facilities to check whether there is any radio wave interference between existing and new facilities.

[0034] For example, when installing a new antenna on the roof of a building where another operator's antenna is already installed, it is necessary to prepare a drawing (including dotted lines, etc.) as a consultation drawing that includes the negotiation information showing the relative positions of the existing antenna 70 and the new antenna 72, as shown in Figures 3 and 4. In other words, it is necessary to prepare a drawing of the existing facility to which the negotiation information, such as the dotted lines in Figures 3 and 4, has been added as a consultation drawing.

[0035] Furthermore, when constructing new equipment such as antennas other than those on the consultation drawings, it is necessary to create new drawings that add the new equipment to the drawings of the construction location, and it is desirable to reduce the work involved in creating drawings. For example, as shown in Figure 4, when constructing a new antenna 72 on an existing building 74, it is necessary to create a drawing that adds the new antenna 72 as shown in Figure 4 to the original drawing that includes the existing building 74 and the existing antenna 70 (a drawing in which the new antenna 72 does not exist compared to Figure 4).

[0036] Therefore, the data processing device 12 according to this embodiment accepts an original drawing that will be used as the basis for drawing, inputs the original drawing into a learning model trained using previously created drawings, and obtains variable data necessary for drawing a new drawing including the newly installed equipment from the output of the learning model. Then, along with the original drawing and variable data, instruction information for instructing the creation of a new drawing is input into a generative AI model trained using public data, and processing is performed to obtain at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model 58A. This facilitates the creation of new drawings and reduces the work required for drawing creation. The following describes the case where code information for creating a new drawing is generated by the generative AI model 58A. As an example, AutoLISP code for AutoCAD (Computer Aided Design) can be used as the generated code information, but code information from other drawing creation software can also be used.

[0037] Next, the processing of the identification processing unit 290 when the data processing device 12 performs identification processing to generate code information for creating a new drawing including new equipment such as an antenna from an original drawing will be described. Fig. 5 is a diagram for explaining the processing of the identification processing unit 290.

[0038] First, in the identification process of this embodiment, as shown in Fig. 5, an original drawing 76 that is the basis for drawing is received from a user and input to the AI-OCR model 58B. The original drawing 76 may be, for example, a drawing of a building where new equipment is to be constructed. The original drawing 76 may also include existing equipment such as an existing antenna 70.

[0039] The AI-OCR model 58B extracts predetermined specific words representing equipment, such as "antenna" or "sector," and figures representing equipment, such as specific equipment icons, from the drawing, and acquires the coordinates of the extracted equipment (coordinates such as latitude and longitude of a location required for drawing) as variable data. For example, as shown in FIG. 6, the AI-OCR model 58B detects an antenna by object detection, as indicated by the dotted line, and extracts "antenna," which corresponds to the antenna, as an example of a specific word by AI-OCR. The coordinates of the equipment at the extracted location are then acquired as variable data. Note that FIG. 6 is a diagram for explaining an example of the AI-OCR model 58B.

[0040] 5, the user generates a prompt 78 that instructs the creation of a new drawing including variable data and the original drawing as instruction information to be input to the generative AI model 58A. For example, the acquired variable data is used to generate a prompt 78 that instructs the creation of code information for creating a drawing with the new equipment added, along with the location where the new equipment will be added. Alternatively, the acquired variable data is used to generate a prompt 78 that instructs the creation of code information for creating a drawing with added consultation information indicating the positional relationship between the existing equipment and the new equipment. Then, by inputting the generated prompt 78 together with the original drawing 76 and the variable data into the generative AI model 58A, the generative AI model 58A generates code information (e.g., AutoLISP code).

[0041] Then, by inputting the generated code information into drawing creation software such as AutoCAD, it becomes possible to create a new drawing 80 including the new equipment.

[0042] Next, a description will be given of the specific processing unit 290 of the data processing device 12. Fig. 7 is a block diagram showing a schematic functional configuration of the specific processing unit 290 of the data processing device 12.

[0043] As shown in FIG. 5, the identification processing unit 290 includes a receiving unit 292, a variable acquiring unit 294, an acquiring unit 296, and an output unit 298.

[0044] The reception unit 292 receives the original drawing 76 that is the basis for drawing from the user terminal 14 operated by the user. For example, the user operates the user terminal 14 to specify the original drawing 76 of the location where new equipment is to be installed (for example, a building 74, etc.) and transmits it to the data processing device 12, whereby the reception unit 292 receives the original drawing 76.

[0045] The variable acquisition unit 294 acquires variable data from the AI-OCR model 58B by inputting the original drawing 76 accepted by the acceptance unit 292 into the AI-OCR model 58B, which has been trained using drawings created in the past (for example, drawings used at the time of construction of a mobile phone base station or drawings used in consultations on the co-location of mobile phone base station construction, etc.) as learning data.

[0046] The acquisition unit 296 receives from the user terminal 14 a prompt 78 instructing the creation of a new drawing 80 generated by the user operating the user terminal 14, and inputs the received prompt 78 together with the original drawing 76 and variable data to the generative AI model 58A. The acquisition unit 296 then acquires the code information generated by the generative AI model 58A. Note that the acquisition unit 296 may input the generated code information into drawing creation software such as AutoCAD to further acquire the new drawing 80 created by the drawing creation software.

[0047] The output unit 298 transmits the results of the specified processing to the user terminal 14. When the user terminal 14 receives code information as a result of the specified processing, the desired drawing can be obtained by inputting the code information into drawing creation software. When the user terminal 14 receives code information as a result of the specified processing, the drawing can be modified by checking the drawing that was created based on the code information and then modifying the code information. On the other hand, when the user receives a drawing as a result of the specified processing, the desired drawing can be obtained without operating the drawing software.

[0048] Next, the operation of the data processing system 10 will be described.

[0049] An example of the flow of the identification process will be described with reference to Fig. 8. The flow of the identification process shown in Fig. 8 is an example of a "data processing method" according to the technology of the present disclosure.

[0050] In step S100, the reception unit 292 receives the original drawing 76 that is the basis for drawing, and the process proceeds to step S102. That is, the user operates the user terminal 14 to designate the original drawing 76 of the location where the new equipment is to be installed (e.g., the building 74, etc.), and transmits the original drawing 76 to the data processing device 12, whereby the reception unit 292 receives the original drawing 76 from the user terminal 14.

[0051] In step S102, the variable acquisition unit 294 inputs the original drawing 76 to the AI-OCR model 58B, and the process proceeds to step S104. That is, the original drawing 76 received by the reception unit 292 is input to the AI-OCR model 58B that has been trained using previously created drawings as training data.

[0052] In step S104, the variable acquisition unit 294 acquires the coordinates of the locations required for drawing as variable data from the AI-OCR model 58B, and the process proceeds to step S106. That is, the variable acquisition unit 294 acquires the variable data output from the AI-OCR model 58B.

[0053] In step S106, the acquisition unit 296 determines whether or not it has received the prompt 78. This determination determines whether or not it has received, from the user terminal 14, the prompt 78 instructing the creation of a new drawing 80 that has been generated by the user operating the user terminal 14. The process waits until the determination is affirmative, and then proceeds to step S108.

[0054] In step S108, the acquisition unit 296 inputs the received prompt 78 together with the original drawing 76 and the variable data into the generative AI model 58A, and the process proceeds to step S110.

[0055] In step S110, the acquisition unit 296 acquires the code information generated by the generative AI model 58A, and the process proceeds to step S112.

[0056] In step S112, the acquisition unit 296 inputs the code information generated by the generation AI model 58A into the drawing software, and the process proceeds to step S114.

[0057] In step S114, the acquisition unit 296 determines whether or not the drawing result has been output from the drawing software, waits until the determination is affirmative, and then proceeds to step S116.

[0058] In step S116, the output unit 298 outputs the drawing result to the user terminal 14, thereby completing the series of identification processes. Note that in step S116, the code information may also be output to the user terminal 14 together with the new drawing 80 as the drawing result. Also, steps S112 to S114 may be deleted, and the code information may be output to the user terminal in step S116.

[0059] In this way, the data processing device 12 according to this embodiment performs specific processing, making it possible to easily create drawings for newly installed equipment and consultation drawings, thereby reducing the work involved in creating drawings.

[0060] In the above embodiment, AI-OCR model 58B and generative AI model 58A are configured to be provided in a single data processing device 12, but they may also be provided in different devices. For example, by providing AI-OCR model 58B in a company's own device and using a general-purpose generative AI model 58A provided by another company, desired drawings can be created without transmitting confidential drawings required for training AI-OCR model 58B to an external party, thereby preventing information leaks.

[0061] In the above embodiment, the acquisition of variable data by AI-OCR model 58B and the generation of at least one of code information and drawings by generation AI model 58A are performed separately, but the present invention is not limited to this. For example, as shown in a modified example of Fig. 9, past drawings, etc. may be registered in generation AI model 58A in advance, and generation AI model 58A may learn using previously created drawings and public data, thereby giving generation AI model 58A the functionality of AI-OCR model 58B.

[0062] When the function of AI-OCR model 58B is provided to generation AI model 58A, specific processing unit 290 includes a receiving unit 293, an acquiring unit 295, and an output unit 298, as shown in FIG.

[0063] The receiving unit 293 receives an original drawing 76 that serves as the basis for drawing and a prompt 78 as instruction information instructing the creation of a new drawing 80 that includes the newly installed equipment. The acquiring unit 295 inputs the original drawing 76 and the prompt 78 into a generative AI model 58A that has been trained using previously created drawings and public data, and acquires at least one of code information for creating the new drawing 80 and the new drawing from the output of the generative AI model 58A. Then, the output unit 298 transmits the results of the identification process to the user terminal 14, as in the above embodiment. As a result, by inputting the original drawing 76 and the prompt 78 requesting drawing into the generative AI model 58A, at least one of code information representing the desired new drawing 80 and the new drawing 80 can be obtained.

[0064] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0065] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0066] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0067] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0068] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0069] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0070] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0071] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0072] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0073] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0074] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0075] The following additional notes are provided regarding the above-described embodiments.

[0076] <Appendix 1> a reception unit that receives a source drawing that is the basis for drawing; a variable acquisition unit that inputs the original drawing into a learning model that has been trained using drawings created in the past, and acquires variable data necessary for drawing a new drawing including the newly installed equipment from the output of the learning model; an acquisition unit that inputs instruction information for instructing the creation of the new drawing, together with the original drawing and the variable data, into a generative AI model trained using public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model; 2. A data processing device comprising:

[0077] <Appendix 2> a reception unit that receives an original drawing that is the basis for drawing and instruction information that instructs the creation of a new drawing that includes the newly installed equipment; an acquisition unit that inputs the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model; 2. A data processing device comprising:

[0078] <Appendix 3> The data processing device according to claim 1 or 2, wherein the acquisition unit, when acquiring the code information from the generative AI model, inputs the code information into drawing creation software to acquire the new drawing.

[0079] <Appendix 4> A data processing device described in any one of Appendices 1 to 3, wherein the acquisition unit acquires at least one of a consultation drawing to which consultation information between the existing equipment and the new equipment has been added and code information for creating the consultation drawing.

[0080] <Appendix 5> The computer We accept the original drawings that will be used as the basis for the drawing. The original drawing is input into a learning model that has been trained using drawings created in the past, and variable data necessary for drawing a new drawing including the newly installed equipment is obtained from the output of the learning model; A data processing method in which instruction information for creating the new drawing, together with the original drawing and the variable data, is input into a generative AI model trained using public data, and a process is performed to obtain at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0081] <Appendix 6> The computer An original drawing that is the basis for the drawing and instruction information for instructing the creation of a new drawing including the newly installed equipment are received; A data processing method in which the original drawing and the instruction information are input into a generative AI model that has been trained using previously created drawings and public data, and at least one of the code information for creating the new drawing and the new drawing is obtained from the output of the generative AI model.

[0082] <Appendix 7> On the computer, We accept the original drawings that will be used as the basis for the drawing. The original drawing is input into a learning model that has been trained using drawings created in the past, and variable data necessary for drawing a new drawing including the newly installed equipment is obtained from the output of the learning model; A data processing program for inputting instruction information for creating the new drawing, together with the original drawing and the variable data, into a generative AI model trained using public data, and executing a process for obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

[0083] <Appendix 8> On the computer, An original drawing that is the basis for the drawing and instruction information for instructing the creation of a new drawing including the newly installed equipment are received; A data processing program for inputting the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and executing a process of obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model. [Explanation of symbols]

[0084] 10 Data Processing System 12 Data Processing Device 14 User terminal 56 Specific Processing Program 58A Generative AI Model 58B AI-OCR model 70 Existing antenna 72 New antenna 74 Building 76 Original Drawings 78 prompts 80 New Drawings 290 Special Processing Department 292, 293 Reception 294 Variable Acquisition Section 295, 296 Acquisition Department 298 Output Section< / url:>

Claims

1. a reception unit that receives a source drawing that is the basis for drawing; a variable acquisition unit that inputs the original drawing into a learning model that has been trained using drawings created in the past, and acquires variable data necessary for drawing a new drawing including the newly installed equipment from the output of the learning model; an acquisition unit that inputs instruction information for instructing the creation of the new drawing, together with the original drawing and the variable data, into a generative AI model trained using public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model; 2. A data processing device comprising:

2. a reception unit that receives an original drawing that is the basis for drawing and instruction information that instructs the creation of a new drawing that includes the newly installed equipment; an acquisition unit that inputs the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and acquires at least one of code information for creating the new drawing and the new drawing from the output of the generative AI model; 2. A data processing device comprising:

3. The data processing device according to claim 1 , wherein when the acquisition unit acquires the code information from the generative AI model, the acquisition unit inputs the code information into drawing creation software to acquire the new drawing.

4. The data processing device according to claim 1 , wherein the acquisition unit acquires at least one of a consultation drawing to which consultation information between the existing facility and the new facility has been added and code information for creating the consultation drawing.

5. The computer We accept the original drawings that will be used as the basis for the drawing. The original drawing is input into a learning model that has been trained using drawings created in the past, and variable data necessary for drawing a new drawing including the newly installed equipment is obtained from the output of the learning model; A data processing method that inputs instruction information for creating the new drawing, together with the original drawing and the variable data, into a generative AI model trained using public data, and executes a process of obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

6. The computer An original drawing that is the basis for the drawing and instruction information for instructing the creation of a new drawing including the newly installed equipment are received; A data processing method that inputs the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and performs a process of obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

7. On the computer, We accept the original drawings that will be used as the basis for the drawing. The original drawing is input into a learning model that has been trained using drawings created in the past, and variable data necessary for drawing a new drawing including the newly installed equipment is obtained from the output of the learning model; A data processing program for inputting instruction information for creating the new drawing, together with the original drawing and the variable data, into a generative AI model trained using public data, and executing a process for obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

8. On the computer, An original drawing that is the basis for the drawing and instruction information for instructing the creation of a new drawing including the newly installed equipment are received; A data processing program for inputting the original drawing and the instruction information into a generative AI model that has been trained using previously created drawings and public data, and executing a process for obtaining at least one of the code information for creating the new drawing and the new drawing from the output of the generative AI model.

Images