Drawing processing method and drawing processing apparatus

Abstract

Provided are a drawing processing method and a drawing processing apparatus that enable easy and accurate extraction of dimensions from a drawing by utilizing generative AI. 【Solution means】The method is such that the drawing processing apparatus 3 receives drawing information including drawing data related to a processed product from the terminal device 4, and based on the drawing information, generates first prompt information for instructing the generative artificial intelligence model 20 to output first response information, which is all the dimensions described in the drawing data, while referring to first dimension extraction information. Based on the first response information, second prompt information is generated for instructing the generative artificial intelligence model 20 to output second response information, which is the maximum dimension described in the drawing data, while referring to second dimension extraction information regarding maximum dimension extraction of the drawing. By inputting the second prompt information into the generative artificial intelligence model, display screen information including the second response information output from the generative artificial intelligence model 20 is transmitted to the terminal device 4.

Description

Technical Field

[0001] The present invention relates to a drawing processing method and a drawing processing apparatus.

Background Art

[0002] In drawings handled in various fields such as machinery, architecture, civil engineering, electricity, and apparel, for example, in addition to lines (outline lines, dimension lines, etc.) for representing shapes and structures, various types of information are described in characters. Since the characters described in the drawings are important information for understanding the contents of the drawings, methods for utilizing these information have been developed. For example, Patent Document 1 discloses a drawing management method in which drawing data including raster data is vectorized, and character recognition is performed on a region specified based on dimension lines included in the vector data to recognize dimension values within a figure.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the drawing management method disclosed in Patent Document 1, since a rule-based approach is mainly used in vectorization, detection of dimension lines, and character recognition, it has low flexibility for special drawing descriptions, and misrecognition of characters and dimensions is likely to occur.

[0005] On the other hand, in recent years, generative artificial intelligence models called generative AI and generative AI have been utilized for various purposes and applications.

[0006] The present invention has been made in view of the above problems, and an object thereof is to provide a drawing processing method and a drawing processing apparatus that enable easy and accurate extraction of dimensions from drawings by utilizing generative AI.

Means for Solving the Problem

[0007] To achieve the above object, a drawing processing method according to an aspect of the present invention includes: a drawing reception process for receiving drawing information including drawing data related to a processed product; a first prompt generation process for generating first prompt information for instructing a generative artificial intelligence model to output first response information, which is all dimensions described in the drawing data, based on the drawing information; a first response providing process for providing the first response information output from the generative artificial intelligence model by inputting the first prompt information into the generative artificial intelligence model; a second prompt generation process for generating second prompt information for instructing a generative artificial intelligence model to output second response information, which is the maximum dimension described in the drawing data, based on the first response information; a second response providing process for providing the second response information output from the generative artificial intelligence model by inputting the second prompt information into the generative artificial intelligence model.

Advantages of the Invention

[0008] According to the drawing processing method according to an aspect of the present invention, by utilizing generative AI, dimensions can be easily and accurately extracted from a drawing.

[0009] Problems, configurations, and effects other than the above will be clarified in the embodiments for carrying out the invention described later.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8A

Figure 8B

Figure 8C

Embodiments for Carrying Out the Invention

[0011] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. In the following, the scope necessary for explaining to achieve the object of the present invention is schematically shown, and mainly the scope necessary for explaining the corresponding part of the present invention will be described, and the parts where the explanation is omitted shall be based on the known technology.

[0012] (Configuration of the Drawing Management System 1) FIG. 1 is an overall view showing an example of the drawing management system 1. The drawing management system 1 functions as a system for managing drawing data D10 including drawing elements related to processed products.

[0013] The drawing data D10 processed by the drawing management system 1 records, as digital data, arbitrary drawings such as mechanical drawings like assembly drawings and part drawings, architectural drawings, electrical circuit drawings, pneumatic circuit drawings, hydraulic circuit drawings, apparel drawings, etc. At that time, the drawing data D10 may be vector-formatted data or raster-formatted data. For example, the drawing data D10 may be CAD data (an example of vector format) output by various CAD software, or image data (an example of raster format) output by reading a drawing printed on paper media with a scanner or the like. Note that the drawing data D10 may be drawn using any projection method and may also be a three-dimensional drawing.

[0014] The drawing management system 1 includes, as its main components, a generative AI device 2, a drawing processing device 3 that operates in cooperation with the generative AI device 2, a terminal device 4 used by a user, and a database device 5 that stores various types of information. Each of the devices 2 to 5 is configured by, for example, a general-purpose or dedicated computer (see FIG. 6 described later), and is connected to a wired or wireless network 6 so as to be able to transmit and receive various types of data to and from each other. Note that the number of each of the devices 2 to 5 and the connection configuration of the network 6 are not limited to the example in FIG. 1 and may be changed as appropriate.

[0015] The generative AI device 2 is configured by, for example, a server-type computer or a cloud-type computer. The generative AI device 2 includes, for example, a generative artificial intelligence model 20 called generative AI or generative AI. The generative artificial intelligence model 20 generates response information D5 in response to an instruction given by prompt information D4.

[0016] Hereinafter, the prompt information D4 refers to either the first prompt information D4A or the second prompt information D4B. Also, the response information D5 refers to either the first response information D5A or the second response information D5B. The first response information D5A is information on all dimensions described in the drawing data D10, and the first prompt information D4A is information for instructing the generative artificial intelligence model to output the first response information D5A. The second response information D5B is information on the maximum dimension described in the drawing data D10, and the second prompt information D4B is information for instructing the generative artificial intelligence model to output the second response information D5B.

[0017] The generative artificial intelligence model 20 is a trained model constructed using a vast learning dataset and deep learning techniques, and a base model (e.g., a large language model, etc.) or a multimodal model, etc. is used. Note that the generative artificial intelligence model 20 may use one provided as a service by an external contractor, and in that case, the generative AI device 2 may be omitted from the components of the drawing management system 1.

[0018] The drawing processing device 3 is composed of, for example, a server-type computer or a cloud-type computer. When the drawing processing device 3 receives the drawing information D1 including the drawing data D10 from the terminal device 4, it generates the prompt information D4 for the generative artificial intelligence model 20 and transmits it to the generative AI device 2. Also, when the drawing processing device 3 receives the response information D5 from the generative AI device 2 by the generative artificial intelligence model 20, it provides the response information D5 to the terminal device 4.

[0019] The terminal device 4 is composed of, for example, a stationary computer or a portable computer. The terminal device 4 is used by various users such as processors. The terminal device 4 has programs such as applications and browsers installed, accepts various input operations, and outputs various information via a display screen and sound. The terminal device 4 displays a display screen for accepting an input operation for inputting the drawing information D1 or outputting the response information D5, etc., and transmits and receives various data such as the drawing information D1 and the response information D5 to and from the drawing processing device 3.

[0020] The database device 5 is composed of, for example, a server-type computer or a cloud-type computer. The database device 5 includes a technical information management database 50 that manages the first dimension extraction information D2A related to the dimension extraction of the drawing and the second dimension extraction information D2B related to the maximum dimension extraction of the drawing. The technical information management database 50 is accessible from each of the devices 2 to 4 and is referred to, for example, when the generative artificial intelligence model 20 generates the response information D5. Also, the technical information management database 50 is subjected to editing operations such as addition, deletion, and modification via the drawing processing device 3 and the terminal device 4.

[0021] FIG. 2 is a diagram showing an example of the drawing data D10. The drawing area 10 of the drawing data D10 corresponds to the entire area of the paper when the drawing data D10 is printed on paper media. In the drawing area 10 of the drawing data D10, for example, a shape area 11, a title block 12, a header column 13, a footer column 14, and a memo area 15 are respectively arranged as drawing elements. Note that drawing elements other than the above may be arranged in the drawing area 10.

[0022] The shape area 11 is an area where the shape and dimensions of an assembled product or component are described by lines, characters (including symbols), figures, etc. In the shape area 11, as shape lines that define the shape and structure of the assembled product or component, for example, outline lines, dimension lines, hidden lines, center lines, imaginary lines, etc. are described. Also, in the shape area 11, characters indicating dimensions, tolerances, part numbers, etc. are described. The shape area 11 is given an attribute called a drawing feature quantity, and vector-form data representing the features of the shape area 11 as a fixed-length numerical array is obtained as an attribute value by feature recognition processing. Note that the shape area 11 is not limited to any one of the six views by the orthographic projection method. For example, it may represent other types of drawings such as sectional views, perspective views, and exploded views. Also, in the example of FIG. 2, the number of shape areas 11 is two, but it may be one, or three or more.

[0023] The title block 12 is a type of table included in the drawing data D10. The table has grid lines formed by combining vertical and horizontal lines, and boxes 120 separated by the grid lines. Each box 120 is given an attribute of the characters described within the box 120, and the characters described within the box 120 are obtained as an attribute value by character recognition processing. Examples of the attributes of each box 120 included in the title block 12 are, as shown in FIG. 2, for example, company name, drafter, drafting method, scale, quantity, material, part name, part number, etc. The title block 12 may be treated as one drawing element as a whole, or each of the multiple boxes 120 included in the title block 12 may be treated as one drawing element. Note that the type of table included in the drawing data D10 is not limited to the title block 12. For example, it may be other types of tables such as a parts list. Also, the arrangement and number of the boxes 120 that make up the table may be appropriately changed according to the type of the table, and the attributes defined for each box 120 are not limited to the above examples.

[0024] The header column 13 is an area arranged on the upper side of the paper surface, and any information regarding the drawing data D10 is described therein. The header column 13 is given the attribute of "header", and the characters described in the header column 13 are acquired as attribute values by character recognition processing. In the example of FIG. 2, although information on the fax transmission side is described in the header column 13, it is not limited thereto. Also, in the example of FIG. 2, there is one header column 13, but there may be two or more.

[0025] The footer column 14 is an area arranged on the lower side of the paper surface, and any information regarding the drawing data D10 is described therein. The footer column 14 is given the attribute of "footer", and the characters described in the footer column 14 are acquired as attribute values by character recognition processing. In the example of FIG. 2, although information on the fax reception side is described in the footer column 14, it is not limited thereto. Also, in the example of FIG. 2, there is one footer column 14, but there may be two or more.

[0026] The memo area 15 is an area where any handwritten characters are arranged. The memo area 15 is given the attribute of "handwritten memo", and the handwritten characters are acquired as attribute values by character recognition processing. Note that in the example of FIG. 2, there are two memo areas 15, but there may be one, or three or more.

[0027] FIG. 3 is a data configuration diagram showing an example of the technical information management database 50. In the technical information management database 50, as technical information D2 which is information referred to when generating the prompt information D4, the first dimension extraction information D2A and the second dimension extraction information D2B are stored.

[0028] The first dimension extraction information D2A includes information regarding the dimension extraction of the drawing. As information regarding the dimension extraction of the drawing, it may be an example in which all dimensions of an existing drawing and the drawing are extracted, or may be general knowledge regarding dimensions described in general drawings or know-how regarding drawing descriptions for each customer.

[0029] The second dimension extraction information D2B includes information regarding the extraction of the maximum dimension of the drawing. As information regarding the extraction of the maximum dimension of the drawing, it may be an example of extracting the maximum dimension described in the existing drawing and the said drawing, or may be general knowledge regarding the maximum dimension described in a general drawing, know-how regarding the drawing description for each customer, or the like.

[0030] (Configuration of the drawing processing apparatus 3) FIG. 4 is a block diagram showing an example of the drawing processing apparatus 3. FIG. 5 is a functional explanatory diagram showing an example of the drawing processing apparatus 3.

[0031] The drawing processing apparatus 3 includes a control unit 30 configured by a processor or the like, a storage unit 31 configured by an HDD, an SSD, a memory, or the like, a communication unit 32 which is a communication interface with the network 6, an input unit 33 configured by a keyboard, a mouse, or the like, and a display unit 34 configured by a display or the like. Note that the input unit 33 and the display unit 34 may be omitted.

[0032] The storage unit 31 stores the prompt syntax data 310 and the information processing program 311, and also stores an operating system, other programs, various data, and the like.

[0033] The prompt syntax data 310 is used when generating the prompt information D4 from the drawing information D1, and includes a plurality of syntaxes. Each syntax specifies the technical information D2 to be referred to when generating the response information D5, or specifies the task imposed on the generative artificial intelligence model 20.

[0034] The control unit 30 functions as a drawing reception unit 300, a prompt generation unit 301, and a response providing unit 302 by executing the information processing program 311 stored in the storage unit 31. Each part 300 to 302 of the control unit 30 transmits display information for causing the terminal device 4 to display various display screens to the terminal device 4, and functions as a user interface with the user by receiving various input operations via the display screens.

[0035] The drawing reception unit 300 performs a drawing reception process of receiving drawing information D1 including drawing data D10 related to a processed product.

[0036] The drawing information D1 may include text data in which a sentence representing information related to the drawing from the user is recorded together with the drawing data D10. The drawing data D10 may be input by a file in which the drawing data D10 is recorded in an arbitrary data format, or may be input by a reference file name for referring to the file in which the drawing data D10 is recorded.

[0037] The prompt generation unit 301 performs a prompt generation process of generating prompt information D4 for instructing the generative artificial intelligence model 20 to output response information D5 while referring to the technical information D2 based on the drawing information D1. For example, the prompt generation unit 301 performs natural language processing on the sentence (text data) representing the information related to the drawing in the drawing information D1, and generates the prompt information D4 according to the type of the drawing data D10 and the like. At this time, the prompt generation unit 301 refers to the prompt syntax data 310 stored in the storage unit 31, selects a syntax suitable for the type of the drawing and the like, and fits the type of the technical information D2 and the content of the drawing data D10 to the syntax to generate the prompt information D4.

[0038] The response providing unit 302 performs a response providing process of providing the response information D5 output from the generative artificial intelligence model 20 by inputting the prompt information D4 to the generative artificial intelligence model 20.

[0039] The prompt generation unit 301 and the answer providing unit 302 perform the prompt generation process and the answer providing process twice. When a plurality of types of technical information D2 (D2A and D2B) are stored in the technical information management database 50, as shown in the example of FIG. 5, in the first prompt generation process, which is the first prompt generation process, based on the drawing information D1, a first prompt information D4A is generated that gives an instruction to output a first answer information D5A while referring to the first dimension extraction information D2A. In the second prompt generation process, which is the second prompt generation process, based on the drawing information D1 and the first answer information D5A output from the generative artificial intelligence model 20 in the first answer providing process, which is the first answer providing process, a second prompt information D4B is generated that gives an instruction to output a second answer information D5B while referring to the second dimension extraction information D2B.

[0040] (Hardware configuration of each device) FIG. 6 is a hardware configuration diagram showing an example of a computer 900 that constitutes each device. Each device 2 to 5 in the drawing management system 1 is constituted by a general-purpose or dedicated computer 900.

[0041] As shown in FIG. 6, the main components of the computer 900 include a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be appropriately omitted according to the application for which the computer 900 is used.

[0042] The processor 912 is composed of one or more arithmetic processing units (such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), DSP (Digital Signal Processor), GPU (Graphics Processing Unit), NPU (Neural Processing Unit), etc.) and operates as a control unit that oversees the entire computer 900. The memory 914 stores various data and programs 930 and is composed of, for example, a volatile memory (such as DRAM, SRAM, etc.) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0043] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc. and functions as an input unit. The output device 917 is composed of, for example, a sound (voice) output device, a vibration device, etc. and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, an electronic paper, a projector, etc. and functions as an output unit. The input device 916 and the display device 918 may be integrally configured, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD, etc. and functions as a storage unit. The storage device 920 stores various data necessary for the execution of the operating system and the program 930.

[0044] The communication I / F unit 922 is connected, either wired or wirelessly, to a network 940 such as the Internet or an intranet (which may be the same as the network 6 in FIG. 1), and functions as a communication unit that transmits and receives data to and from other computers according to a predetermined communication standard. The external device I / F unit 924 is connected, either wired or wirelessly, to an external device 950 such as a camera, printer, scanner, or reader / writer, and functions as a communication unit that transmits and receives data to and from the external device 950 according to a predetermined communication standard. The I / O device I / F unit 926 is connected to an I / O device 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I / O device 960. The media input / output unit 928 is composed of, for example, drive devices such as a DVD drive and a CD drive, a memory card slot, and a USB connector, and reads and writes data to a media (non-volatile storage medium) 970 such as a DVD, CD, memory card, or USB memory.

[0045] In the computer 900 having the above configuration, the processor 912 calls and executes the program 930 stored in the storage device 920 in the memory 914, and controls each part of the computer 900 via the bus 910. Note that the program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded in the media 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the network 940 through the communication I / F unit 922. Also, the computer 900 may implement various functions realized when the processor 912 executes the program 930 using hardware such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0046] The computer 900 is composed of, for example, a stationary computer or a portable computer, and is an electronic device in any form. The computer 900 may be a client-type computer, a server-type computer or a cloud-type computer, or may be an embedded computer called, for example, a control panel, a controller (including a microcomputer, a programmable logic controller, a sequencer, etc.).

[0047] (Operation of the drawing management system 1) Hereinafter, a series of operations by the drawing management system 1 will be described. Also, the drawing data D10 will be described as including three drawings, a plan view, a front view, and a side view, as one or more specific perspective views of a drawing of a processed product seen from a predetermined direction. The series of operations is executed by the cooperation of each part 300-302 of the drawing processing device 3 (each process of the drawing processing method executed by the information processing program 311), the generative AI device 2, the terminal device 4, and the database device 5.

[0048] FIG. 7 is a flowchart showing an example of the operation of the drawing management system 1. Hereinafter, it will be described on the assumption that the first dimension extraction information D2A and the second dimension extraction information D2B are registered in the technical information management database 50.

[0049] First, at step S100, the terminal device 4 receives, as a user input operation on, for example, the display screen shown in FIG. 8A described later, the drawing data D10 related to the processed product, and transmits the drawing information D1 based on the input operation to the drawing processing device 3.

[0050] FIG. 8A is a screen configuration diagram showing an example of the display screen 11A for inputting the drawing information D1. The display screen 11A includes a text input area 110 for inputting text, a file attachment button 110A for attaching a file, and an input confirmation button 110B for transmitting the text input in the text input area 110 and the file attached by the file attachment button 110A to the drawing processing device 3.

[0051] When the user attaches a file containing drawing data D10 using the file attachment button 110A on the display screen 11A and presses the input confirmation button 110B, drawing information D1 is transmitted to the drawing processing device 3 based on the input operation on the display screen 11A.

[0052] Next, in step S110 (drawing reception process), the drawing reception unit 300 of the drawing processing device 3 receives the drawing information D1 transmitted in step S100, thereby accepting the drawing information D1 including the drawing data D10.

[0053] Next, in step S200 (first prompt generation process), the prompt generation unit 301 generates first prompt information D4A that instructs the generative artificial intelligence model 20 to output the first response information D5A while referring to the first dimension extraction information D2A based on the drawing information D1 received in step S110.

[0054] Next, in step S210 (first response provision process), the response provision unit 302 inputs the first prompt information D4A generated in step S200 into the generative artificial intelligence model 20, and generates the first response information D5A as the output result from the generative artificial intelligence model 20.

[0055] Next, in step S220 (first response provision process), the response provision unit 302 transmits display screen information for displaying the first response information D5A generated in step S210 to the terminal device 4 that is the source of the drawing information D1. At this time, the display screen information also includes the first prompt information D4A generated in step S200.

[0056] Next, in step S230, when the terminal device 4 receives the display screen information transmitted in step S220, it displays a display screen 11B including the first prompt information D4A and the first response information D5A based on the display screen information.

[0057] FIG. 8B is a screen configuration diagram showing an example of a display screen 11B including first prompt information D4A and first response information D5A. The display screen 11B includes an input display area 111 for displaying drawing information D1 and text input in the text input area 110, a prompt display area 112A for displaying the first prompt information D4A, and a response display area 113A for displaying the first response information D5A.

[0058] In the example of FIG. 8B, the first prompt information D4A is illustrated as an instruction to the generative artificial intelligence model 20 to extract all dimensions described in the drawing data D10 input as an attached file from the drawing information D1 in accordance with the first dimension extraction information D2A. Here, the first prompt information D4A is described in a human-readable multi-purpose data serialization language called the YAML format, and includes an instruction to extract the part shape of the drawing data D10 and an instruction to extract each dimension in each specific perspective view of the plan view, front view, and side view. However, the first prompt information D4A is not limited to these description methods and contents, and may have other description methods and contents. As a result of the instruction by the first prompt information D4A, the first response information D5A is illustrated as a case where the part shape described in the drawing data D10 and all dimensions in each specific perspective view are output in the JSON format. Note that the display screen 11B may include buttons for proceeding to the subsequent step S300 and buttons for modifying the first prompt information D4A and returning to step S210.

[0059] Next, in step S300 (second prompt generation process), the prompt generation unit 301 generates second prompt information D4B for instructing the generative artificial intelligence model 20 to output a second response information D5B while referring to the second dimension extraction information D2B based on the drawing information D1 received in step S110 and the first response information D5A generated in step S200.

[0060] Next, in step S310 (second response providing process), the response providing unit 302 inputs the second prompt information D4B generated in step S300 into the generative artificial intelligence model 20, and generates second response information D5B as an output result from the generative artificial intelligence model 20.

[0061] Next, in step S320 (second response providing process), the response providing unit 302 transmits display screen information for displaying the second response information D5B generated in step S310 to the terminal device 4 which is the transmission source of the drawing information D1. At this time, the display screen information also includes the second prompt information D4B generated in step S300.

[0062] Next, in step S330, when the terminal device 4 receives the display screen information transmitted in step S320, it displays a display screen 11C including the second prompt information D4B and the second response information D5B based on the display screen information.

[0063] FIG. 8C is a screen configuration diagram showing an example of a display screen 11C including the second prompt information D4B and the second response information D5B. The display screen 11C includes a prompt display area 112B for displaying the second prompt information D4B and a response display area 113B for displaying the second response information D5B.

[0064] In the example of FIG. 8C, there is an illustration of a case where the second prompt information D4B instructs the generative artificial intelligence model 20 to extract the maximum dimension described in the drawing data D10 with reference to the second dimension extraction information D2B based on the drawing information D1 and the first response information D5A. Here, the second prompt information D4B is described in the YAML format and includes an instruction to extract individual dimensions for each part shape. However, the second prompt information D4B is not limited to these description methods and contents, and other description methods and contents may be used. As a result of the instruction by the second prompt information D4B, there is an illustration of a case where the second response information D5B outputs the maximum dimension described in the drawing data D10 in the JSON format. Note that the display screen 11C may be provided with buttons for proceeding to the subsequent step S400 and buttons for modifying the first prompt information D4A or the second prompt information D4B and returning to steps S210 and S310.

[0065] By performing the above series of processes, the second response information D5B for the drawing information D1 is provided to the user. Note that when the user inputs a new drawing, the above series of processes are similarly performed.

[0066] As described above, according to the drawing processing apparatus 3 and the drawing processing method according to the present embodiment, the prompt information D4 generated based on the drawing information D1 including the drawing data D10 is repeatedly input to the generative artificial intelligence model 20, and the response information D5 generated by referring to the technical information D2 by the generative artificial intelligence model 20 is repeatedly generated. Therefore, it is possible to easily and accurately extract dimensions from the user's drawing.

[0067] Also, as a plurality of types of technical information D2 referred to each time the prompt generation process and the answer provision process are repeatedly performed, they are referred to in the order of the first dimension extraction information D2A and the second dimension extraction information D2B. Therefore, the answer information D5 is gradually concretized, such as the first answer information D5A regarding the dimension extraction of the drawing and the second answer information D5B taking into account the information regarding the maximum dimension extraction of the drawing based on the first answer information D5A. As a result, since two technical viewpoints are effectively reflected in the answer information D5, it is possible to generate more appropriate answer information D5 compared to referring to various technical information D2 at once and generating the answer information D5.

[0068] (Other embodiments) The present invention is not limited to the above-described embodiments, and various modifications can be made and implemented without departing from the gist of the present invention. And all of them are included in the technical idea of the present invention.

[0069] In the above embodiment, the functions of each part provided in the drawing processing device 3 have been described for the case where they are realized by one device, but the functions of each part may be realized by a plurality of devices by being distributed among the plurality of devices. Also, the control unit of the terminal device 4 or the control unit of the database device 5 may function as the drawing processing device 3 by executing the information processing program 311.

[0070] In the above embodiment, the case where the database device 5 includes the technical information management database 50 has been described, but a part or all of the technical information management database 50 may be stored in an external device (which may be plural) connectable to the network 6 or an arbitrary storage medium. Also, the technical information management database 50 may be stored in the storage unit 31 of the drawing processing device 3.

[0071] In the above embodiment, the case where the drawing processing apparatus 3 operates according to the flowchart shown in FIG. 7 has been described. However, the execution order of each step may be appropriately changed, some steps may be omitted, or other steps may be added. For example, when the prompt generation unit 301 generates the prompt information D4 in the prompt generation process (steps S200 and S300), the prompt information D4 may be provided to the terminal device 4, and an input operation of a user for changing the prompt information D4 may be received via the display screen of the terminal device 4, and a step of changing the prompt information D4 may be added.

[0072] In the above embodiment, the case where the generative artificial intelligence model 20 refers to the technical information D2 indicated by the prompt information D4 among the plurality of types of technical information D2 stored in the technical information management database 50 when the prompt information D4 is input and generates the response information D5 has been described. In contrast, the generative artificial intelligence model 20 may use a learned model in which a plurality of types of technical information D2 are systematically incorporated as part of the learning dataset. In that case, the generative artificial intelligence model 20 may generate the response information D5 by referring to the technical information D2 incorporated into the generative artificial intelligence model 20 based on the instruction of the prompt information D4.

[0073] In the above embodiment, the case where the terminal device 4 receives the drawing data D10 related to the processed product as a user input operation on the display screen 11A shown in FIG. 8A and transmits the drawing information D1 based on the input operation to the drawing processing apparatus 3 has been described. However, the user may input supplementary information of the drawing data D10 or other information significant for dimension extraction as text in the text input area 110 of the display screen 11A shown in FIG. 8A, and by attaching a file including the drawing data D10 and pressing the input confirmation button 110B, the drawing information D1 may be transmitted to the drawing processing apparatus 3 based on the input operation on the display screen 11A.

[0074] In the above-described embodiment, the case where the prompt information D4 generated based on the drawing information D1 including the drawing data D10 is repeatedly input to the generative artificial intelligence model 20, and the response information D5 generated by referring to the technical information D2 by the generative artificial intelligence model 20 is repeatedly generated has been described. On the other hand, without referring to the technical information D2, the prompt information D4 generated based on the drawing information D1 including the drawing data D10 may be repeatedly input to the generative artificial intelligence model 20, and the response information D5 may be repeatedly generated. Further, in each of the first prompt generation process and the second prompt generation process, whether to refer to the technical information D2 (D2A and D2B) may be selectable.

[0075] In the above-described embodiment, the case where the first prompt information D4A includes an instruction to extract the component shape of the drawing data D10 and an instruction to extract each dimension in each specific perspective view of the plan view, front view, and side view has been described. However, the instruction to extract the dimension for each component shape or specific perspective view may be omitted, and an instruction for extracting other information may be included.

[0076] In the above embodiment, the prompt generation unit 301 and the answer providing unit 302 have been described for the case of performing the prompt generation process and the answer providing process twice. In contrast, when the drawing data D10 describes the incidental information regarding the processed product, after the prompt generation unit 301 and the answer providing unit 302 perform the prompt generation process and the answer providing process twice to provide the second answer information D5B, they may further perform the prompt generation process (the third prompt generation process) and the answer providing process (the third answer providing process) once again to provide the third answer information D5C, which is the incidental information described in the drawing data D10. Here, the third prompt information D4C generated in the third prompt generation process is information for instructing the generative artificial intelligence model 20 to output the third answer information D5C based on the second answer information D5B. Also, in the third prompt generation process, the third prompt information D4C may be generated while referring to the third extraction information D2C regarding the extraction of the incidental information of the drawing stored in the technical information management database 50 as the technical information D2. The third extraction information D2C may be, for example, an example of extracting the existing drawing and the incidental information described in the drawing, or general knowledge regarding the incidental information described in general drawings, know-how regarding the drawing description for each customer, etc., and is not limited thereto. Furthermore, whether to refer to the technical information D2 (D2A to D2C) in each of the first to third prompt generation processes may be selective. Note that an example of the incidental information includes, but is not limited to, the shape category of the processed product, geometric tolerance, material, hardness, processing quantity, drawing number, customer name, delivery date, etc., and may also be tabular information, remarks, handwritten information, etc.

Explanation of Signs

[0077] 1…Drawing management system, 2…Generative AI device, 3…Drawing processing device, 4…Terminal device, 5…Database device, 10…Drawing area, 11…Shape area, 12…Title block, 13…Header column, 14…Footer column, 15…Memo area, 20…Generative artificial intelligence model, 30…Control unit, 31…Storage unit, 32…Communication unit, 33…Input unit, 34…Display unit, 50…Technical information management database, 300…Drawing reception section, 301…Prompt generation section, 302…Answer providing section, 310…Prompt syntax data, 311…Information processing program

Claims

1. A drawing processing method for processing drawing data relating to a processed product by a computer, comprising the steps of: a drawing reception process for receiving drawing information including the drawing data; a first prompt generation process for generating first prompt information for instructing a generative artificial intelligence model to output first answer information, which is all dimensions described in the drawing data, based on the drawing information; a first answer providing process for providing the first answer information output from the generative artificial intelligence model by inputting the first prompt information to the generative artificial intelligence model; a second prompt generation process for generating second prompt information for instructing a generative artificial intelligence model to output second answer information, the second answer information being a maximum dimension described in the drawing data, based on the first answer information; a second answer providing process for providing the second answer information output from the generative artificial intelligence model by inputting the second prompt information to the generative artificial intelligence model; How to process drawings.

2. The first prompt generation process includes: generating the first prompt information while referring to first dimension extraction information related to dimension extraction of the drawing; The drawing processing method according to claim 1 .

3. The second prompt generation process includes: generating second prompt information with reference to second dimension extraction information relating to maximum dimension extraction of the drawing; The drawing processing method according to claim 1 .

4. The first prompt generation process includes: Generate first prompt information by referring to first dimension extraction information related to dimension extraction of the drawing; The second prompt generation process includes: generating second prompt information with reference to second dimension extraction information relating to maximum dimension extraction of the drawing; The drawing processing method according to claim 1 .

5. The drawing data is one or more specific viewpoint views, which are drawings of the workpiece from a predetermined direction; The first response information is All dimensions described in the specific viewpoint views in each of the specific viewpoint views, 5. A method for processing drawings according to claim 1.

6. The first response information is Furthermore, the part shapes of all parts described in the drawing data are included, The drawing processing method according to claim 5.

7. The specific viewpoint view is At least one of a plan view, a front view, and a side view is included; 7. A method for processing drawings according to claim 6.

8. The drawing data includes supplementary information regarding the processed product, a third prompt generation process for generating third prompt information for instructing a generative artificial intelligence model to output third answer information, which is the auxiliary information described in the drawing data, based on the second answer information; a third answer providing process for providing the third answer information output from the generative artificial intelligence model by inputting the third prompt information to the generative artificial intelligence model; 5. A method for processing drawings according to claim 1.

9. The third prompt generation process includes: generating third prompt information by referring to third extraction information related to extraction of supplementary information of the drawing; The drawing processing method according to claim 8.

10. The supplementary information is At least one of the shape category, geometric tolerance, material, hardness, processing quantity, drawing number, customer name, and delivery date of the processed product is included. The drawing processing method according to claim 8.

11. A drawing processing device that processes drawing data related to a processed product by a computer, a drawing receiving unit that receives drawing information including the drawing data; a first prompt generating unit that generates first prompt information for instructing a generative artificial intelligence model to output first answer information, which is all dimensions described in the drawing data, based on the drawing information; a first answer providing unit that provides the first answer information output from the generative artificial intelligence model by inputting the first prompt information to the generative artificial intelligence model; a second prompt generating unit that generates second prompt information for instructing a generative artificial intelligence model to output second answer information, the second answer information being a maximum dimension described in the drawing data, based on the first answer information; a second answer providing unit that provides the second answer information output from the generative artificial intelligence model by inputting the second prompt information to the generative artificial intelligence model, Drawing processing equipment.

Images