Design Support System

Abstract

Provided is a design support system suitable for grasping a plurality of continuously edited elements and their editing order. 【Solution means】 The drawing creation support device 100 inputs a request including an element ID that has been created or edited and a user ID of a target user, and including a generation request for generating element order information conforming to the target user, into the AI model 50, and obtains the element order information output from the AI model 50 for the request. Thereby, it is possible to grasp a plurality of edited elements that are continuously edited and their editing order. Since the estimated element order information conforms to the target user, it is suitable for the target user.

Description

Technical Field

[0001] The present invention relates to a system for assisting design, and more particularly to a design support system suitable for grasping a plurality of continuously edited elements and their editing order.

Background Art

[0002] Conventionally, as a technique for assisting design using AI (Artificial Intelligence), for example, the technique described in Patent Document 1 is known.

[0003] The technique described in Patent Document 1 assigns a reward R to a combination of a state S determined depending on the execution of a design activity and an action A that is an activity selectable under the state, and constructs a learned model by maximizing the value. Then, using the learned model, the action to be taken next from the current state is inferred.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In architectural design, it is sometimes necessary to continuously edit a plurality of related elements for a certain unit. For example, in the design of a toilet, the design of a toilet bowl and a washbasin are carried out continuously. However, in the technique described in Patent Document 1, since the action to be taken next from the current state is inferred, there is a problem that a plurality of continuously edited elements and their editing order cannot be grasped.

[0006] Therefore, the present invention has been made paying attention to such unsolved problems of the prior art, and an object thereof is to provide a design support system suitable for grasping a plurality of continuously edited elements and their editing order.

Means for Solving the Problems

[0007] 〔Invention 1〕 In order to achieve the above object, the design support system of Invention 1 includes an element information acquisition means for acquiring element information regarding created or edited elements in design information, a user information acquisition means for acquiring user information regarding a target user, and including the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, an input means for inputting a request including element order information regarding a plurality of elements continuously edited next to the element related to the element information and their editing order (hereinafter, the "plurality of elements and their editing order" is referred to as "element order") and including a request for generating the element order information conforming to the target user to an AI model, and an acquisition means for acquiring the element order information output from the AI model for the request.

[0008] With such a configuration, element information is acquired by the element information acquisition means. Also, user information is acquired by the user information acquisition means. Then, by the input means, a request including the acquired element information and user information and including a request for generating element order information is input to the AI model, and by the acquisition means, the element order information output from the AI model for the request is acquired.

[0009] Here, as the input means, for example, directly inputting a request to the AI model or indirectly inputting it to the AI model via processing, functions, devices, networks or other means is included. The same applies to the design support system of Invention 8 below.

[0010] In addition, as the acquisition means, for example, it includes directly acquiring the output information of the AI model, or indirectly acquiring the output information of the AI model through processing, functions, devices, networks, or other means. The same applies to the design support system of Invention 8 below.

[0011] In addition, as the generation request, for example, it includes those that explicitly request the generation of element order information or those that indirectly request the generation of element order information. Explicit requests include, for example, requests such as "Please generate element order information." Indirect requests include, for example, in order to request the generation of response information to questions regarding element order, making a question regarding element order the generation request. This is because in the AI model, when a question regarding element order is input as a prompt, the response information is generated. The same applies to the design support system of Invention 8 below.

[0012] In addition, the request or the information included therein can be configured in any form such as vector data, for example. The same applies to the design support system of Invention 8 below.

[0013] In addition, the element information acquisition means may, for example, input element information from an input device or the like, acquire or receive element information from an external terminal or the like, read out element information from a storage device, a storage medium, or the like, or generate or calculate element information through information processing or the like. Therefore, acquisition includes at least input, acquisition, reception, reading (including search), generation, and calculation. The same applies to the user information acquisition means, and the concept of acquisition is the same below.

[0014] In addition, the element information can be configured, for example, not only by the element itself, but also as information for identifying the element (e.g., link information such as name, number, ID, code, URL, etc.), or as feature information regarding the outline, statistical quantity, and other features of the element. Also, the element information can be configured, for example, as characters, numbers, figures, symbols, signs, images, sounds, or other information. Further, the element information can be configured as keywords related to the element (e.g., one or more keywords indicating a part of the name of the element). The same applies to the design support system of Invention 8 below.

[0015] In addition, the user information can be configured, for example, as information for identifying the user (e.g., link information such as name, number, ID, code, URL, etc.), or as feature information regarding the outline, statistical quantity, and other features of the user. Also, the user information can be configured, for example, as characters, numbers, figures, symbols, signs, images, sounds, or other information. Further, the user information can be configured as keywords related to the user (e.g., one or more keywords indicating a part of the name of the user). The same applies to the design support system of Invention 8 below.

[0016] In addition, the element order information can be configured, for example, not only by the element order itself, but also as information for identifying the element and the editing order (e.g., link information such as name, number, ID, code, URL, etc.), or as feature information regarding the outline, statistical quantity, and other features of the element and the editing order. Also, the element order information can be configured, for example, as characters, numbers, figures, symbols, signs, images, sounds, or other information. Further, the element order information can be configured as keywords related to the element and the editing order (e.g., one or more keywords indicating a part of the name of the element and the editing order). The same applies to the design support system of Invention 8 below.

[0017] Further, this system may be implemented as a single device, apparatus, terminal, or other device, or may be implemented as a network system in which a plurality of devices, apparatuses, terminals, or other devices are communicably connected. In the latter case, each component may belong to any of the plurality of devices as long as they are communicably connected to each other. The same applies to the design support system of Invention 8 below.

[0018] 〔Invention 2〕 Further, the design support system of Invention 2 includes a registration means in the design support system of Invention 1 for registering reference information including element information regarding the created or edited elements, element order information regarding the order of elements continuously edited next to the element, and user information regarding the user who edited the plurality of elements in a knowledge base that can be referred to by the AI model. The acquisition means acquires the element order information output from the AI model by referring to the reference information in the knowledge base in response to the request.

[0019] With such a configuration, the registration means registers reference information including element information, element order information, and user information in the knowledge base. Then, the acquisition means acquires the element order information output from the AI model in response to the request. At this time, the AI model refers to the reference information in the knowledge base.

[0020] Here, the knowledge base stores the reference information by any means and at any time. It may store the reference information in advance, or may be configured to store the reference information from an external input or the like during the operation of this system without storing the reference information in advance.

[0021] 〔Invention 3〕 Further, the design support system of Invention 3 includes, in the design support system of Invention 2, the registration means for registering reference information including the element information, element order information regarding the element order, the user information, and an evaluation value regarding the editing of the plurality of elements in the knowledge base.

[0022]

[0023] With such a configuration, the registration means registers the first reference information and the second reference information in the knowledge base. Then, the index information acquisition means acquires the index information, and the input means inputs a request including a request to refer to either the first reference information or the second reference information in the knowledge base based on the acquired index information to the AI model.

[0024]

[0025] With such a configuration, the input means inputs a request including a request to generate element order information including element information, user information, and reference information to the AI model, and the acquisition means acquires the element order information output from the AI model in response to the request.

[0026] ​​​

[0027] 〔Invention 7〕Furthermore, the design support system of Invention 7, in the design support system of Invention 6, comprises index information acquisition means for acquiring index information regarding a first index indicating an index of the value of the evaluation value or a second index different from the first index, and the input means, based on the index information acquired by the index information acquisition means, inputs the request including any one of the first reference information including the element information, the element order information, the user information, and the evaluation value based on the first index, and the second reference information including the element information, the element order information, the user information, and the evaluation value based on the second index into the AI model.

[0028] With such a configuration, index information is acquired by the index information acquisition means, and based on the acquired index information, a request including either the first reference information or the second reference information is input into the AI model by the input means.

[0029] 〔Invention 8〕Furthermore, the design support system of Invention 8 comprises element order information acquisition means for acquiring element order information regarding a plurality of continuously edited elements and their editing order (hereinafter, the "plurality of elements and their editing order" is referred to as "element order"), the element order information being such that the elements or the editing order are different; user information acquisition means for acquiring user information regarding a target user; input means for inputting into the AI model a request including the plurality of element order information acquired by the element order information acquisition means and the user information acquired by the user information acquisition means, the request including a request for generating, from among the plurality of element order information, the one that conforms to the target user; and acquisition means for acquiring the element order information output from the AI model in response to the request.

[0030] With such a configuration, a plurality of element order information is acquired by the element order information acquisition means. Also, user information is acquired by the user information acquisition means. Then, by the input means, a request including the acquired plurality of element order information and user information and including a request to generate element order information is input to the AI model, and by the acquisition means, the element order information output from the AI model for the request is acquired.

[0031] 〔Invention 9〕 Further, the design support system of Invention 9 is the design support system of Invention 8, and includes a registration means for registering reference information including element order information regarding the successively edited element order and user information regarding the user who edited the plurality of elements in a knowledge base that can be referred to by the AI model. The acquisition means acquires the element order information output from the AI model with reference to the reference information in the knowledge base for the request.

[0032] With such a configuration, reference information including element order information and user information is registered in the knowledge base by the registration means. Then, by the acquisition means, the element order information output from the AI model for the request is acquired. At this time, the reference information in the knowledge base is referred to by the AI model.

[0033] 〔Invention 10〕 Further, the design support system of Invention 10 is the design support system of Invention 9, and the registration means registers reference information including the element order information regarding the element order, the user information, and an evaluation value regarding the editing of the plurality of elements in the knowledge base.

[0034] [[Inventive Concept 11]] Further, the design support system according to Inventive Concept 11 includes, in the design support system according to Inventive Concept 10, an index information acquisition unit that acquires index information regarding a first index indicating the value of the evaluation value or a second index different from the first index, and the registration unit registers, in the knowledge base, first reference information including the element order information, the user information, and the evaluation value based on the first index, and second reference information including the element order information, the user information, and the evaluation value based on the second index. The input unit inputs, to the AI model, the request including a request to refer to either the first reference information or the second reference information in the knowledge base based on the index information acquired by the index information acquisition unit.

[0035] With such a configuration, the registration unit registers the first reference information and the second reference information in the knowledge base. Then, the index information acquisition unit acquires the index information, and the input unit inputs, to the AI model, a request including a request to refer to either the first reference information or the second reference information in the knowledge base based on the acquired index information.

[0036] [[Inventive Concept 12]] Further, the design support system according to Inventive Concept 12 includes, in the design support system according to Inventive Concept 8, the request including reference information including element order information regarding an element order edited continuously and user information regarding a user who edited the plurality of elements.

[0037] With such a configuration, the input unit inputs, to the AI model, a request including a request to generate element order information including user information and the reference information, and the acquisition unit acquires the element order information output from the AI model in response to the request.

[0038] [[Inventive Concept 13]] Further, the design support system according to Inventive Concept 13 includes, in the design support system according to Inventive Concept 12, the request including reference information including the element order information regarding the element order, the user information, and an evaluation value regarding the editing of the plurality of elements.

[0039] [[Invention 14]] Further, in the design support system of Invention 14, in the design support system of Invention 13, the design support system includes index information acquisition means for acquiring index information regarding a first index indicating the value index of the evaluation value or a second index different from the first index, and the input means is based on the index information acquired by the index information acquisition means, the element order information, the user information, and the first reference information including the evaluation value based on the first index, and any of the second reference information including the evaluation value based on the element order information, the user information, and the second index. The request including is input to the AI model.

[0040] With such a configuration, the index information acquisition means acquires the index information, and the input means inputs a request including either the first reference information or the second reference information to the AI model based on the acquired index information.

[0041] [[Invention 15]] Further, in the design support system of Invention 15, in any one of the design support systems of Inventions 1 to 3, 5, 6, 8 to 10, 12, and 13, the plurality of elements are elements that require human judgment for their setting or change, and the setting or change affects other elements.

[0042] [[Invention 16]] Further, in the design support system of Invention 16, in the design support system of Invention 1, the design information is design information for performing the design of a building. [[Advantages of the Invention]]

[0043] As described above, according to the design support systems of Inventions 1, 2, 5, 8, 9, or 12, it is possible to grasp a plurality of continuously edited elements and their editing order. The estimated element order information is suitable for the target user because it is adapted to the target user.

[0044] Furthermore, according to the design support systems of Inventions 3, 6, 10, or 13, it is possible to grasp the element order with a high evaluation value.

[0045] Furthermore, according to the design support system of Invention 4, 7, 11, or 14, it is possible to grasp the element order based on the higher evaluation value of the first index or the second index.

[0046] Furthermore, according to the design support system of Invention 15, it is possible to grasp the element order considering the relationship between the elements that require human judgment for their setting or change and the other elements affected by the setting or change.

Brief Description of the Drawings

[0047]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Mode for Carrying Out the Invention

[0048] 〔First Embodiment〕 Hereinafter, a first embodiment of the present invention will be described. FIGS. 1 to 9 are diagrams showing this embodiment.

[0049] 〔Configuration of the Present Embodiment〕 First, the configuration of the present embodiment will be described. FIG. 1 is a diagram showing the hardware configuration of the drawing creation support device 100.

[0050] As shown in FIG. 1, the drawing creation support device 100 includes a CPU (Central Processing Unit) 30 that controls operations and the entire system based on a control program, a ROM (Read Only Memory) 32 that stores in advance the control program of the CPU 30 and the like in a predetermined area, a RAM (Random Access Memory) 34 that stores data read from the ROM 32 and the like and operation results necessary in the operation process of the CPU 30, and an I / F (InterFace) 38 that mediates data input / output to and from an external device. These are connected to each other via a bus 39, which is a signal line for transferring data, so that data can be exchanged between them.

[0051] Connected to the I / F 38 as external devices are an input device 40 composed of a keyboard, a mouse, etc. that can input data as a human interface, a storage device 42 that stores data, tables, etc. as files, and a display device 44 that displays a screen based on an image signal.

[0052] Installed in the storage device 42 are CAD (Computer Aided Design) software and BIM (Building Information Modeling) software (hereinafter collectively referred to as "CAD software"). CAD software is software that supports the creation of drawings according to the operations of a designer. When the startup of CAD software is requested, the CPU 30 starts the program for CAD software stored in a predetermined area of the ROM 32 and executes processing according to that program. The designer can start the CAD software and create a dimensioned drawing, a detailed plan drawing, and other architectural drawings.

[0053] Next, the data structure of the storage device 42 will be described. The storage device 42 stores CAD data of dimensioned drawings, detailed plan drawings, and other architectural drawings.

[0054] FIG. 2 is a diagram showing the structure of the CAD data of a dimensioned drawing. The CAD data of the floor plan drawing is data that constitutes a drawing that details the cross-section of a building, and is configured as data including one or more elements that can be created or edited (hereinafter referred to as "editable elements"). The CAD data of the floor plan drawing is created by a designer using CAD software. The designer creates the floor plan drawing by creating, setting, changing, or deleting (hereinafter referred to as "editing") editable elements in the CAD software. In the example of Figure 2, each editable element of the floor, wall, and ceiling in the area labeled "Inner Corridor" and each editable element of the floor, wall, and ceiling in the area labeled "Vestibule" are arranged respectively.

[0055] The same applies to the CAD data of the detailed floor plan and other architectural drawings, which are configured as data including one or more editable elements.

[0056] The storage device 42 stores edit history data indicating the history of editing the editable elements for each CAD data. The final editing result related to the edit history data is reflected in the CAD data.

[0057] Figure 3 is a diagram showing the structure of the edit history data. As shown in Figure 3, the edit history data includes, for each editable element that has been edited, element information 400 regarding the editable element, a user ID 402 for identifying the user (hereinafter referred to as the "editing user") who edited the editable element, and the edit time 404 required for editing the editable element, in the order of editing. The element information 400 includes an element ID for identifying the editable element, the area targeted for editing of the editable element, and the editable element. The edit time 404 can be calculated, for example, by subtracting the edit start time from the edit end time.

[0058] In the example of FIG. 3, as the first related group, it shows that the editing elements of the toilet, "toilet bowl", "wash basin counter", "mirror", "towel rack", are continuously edited in that order. Element IDs "52", "53", "54", "55" are assigned to these editing elements, and the editing times respectively require 35, 38, 70, 94 minutes. These editing elements are being edited by the user with user ID "001".

[0059] Also, as the second related group, it shows that the editing elements of the toilet, "ventilator", "lighting", "storage", "electrical outlet", are continuously edited in that order. Element IDs "56", "57", "58", "59" are assigned to these editing elements, and the editing times respectively require 94, 48, 42, 74 minutes. These editing elements are being edited by the user with user ID "001".

[0060] Also, as the third related group, it shows that the editing elements of the closet, "shelf board", "hanger pipe", "drawer", "basket", are continuously edited in that order. Element IDs "60", "61", "62", "63" are assigned to these editing elements, and the editing times respectively require 96, 74, 84, 22 minutes. These editing elements are being edited by the user with user ID "002".

[0061] Also, as the fourth related group, it shows that the editing elements of the kitchen, "floor material", "wall material", "counter", "sink", are continuously edited in that order. Element IDs "64", "65", "66", "67" are assigned to these editing elements, and the editing times respectively require 42, 44, 35, 32 minutes. These editing elements are being edited by the user with user ID "003".

[0062] The editing history data is used for creating learning data, and thus a large number of editing history data created in the past are stored in the storage device 42.

[0063] 〔Operation of this Embodiment〕 Next, the operation of this embodiment will be described. 〔Learning Data Generation Process〕 FIG. 4 is a flowchart showing the learning data generation process.

[0064] The learning data generation process is a process for generating learning data. When executed in the CPU 30, as shown in FIG. 4, the process proceeds to step S100.

[0065] In step S100, unprocessed edit history data is acquired from the storage device 42, the process proceeds to step S102, "2" is set to the variable n, and the process proceeds to step S104.

[0066] In steps S104 to S110, from the edit history data acquired in step S100, the element ID of the created or edited edit element (hereinafter abbreviated as "created or edited element ID"), the n edited elements (the number indicated by the value of the variable n) that are continuously edited next to the edit element and their edit order, the user ID of the editing user, and the edit time are acquired. Hereinafter, a plurality of edit elements and their edit order may be referred to as "element order". The element order is acquired with the same user ID as a unit. Taking FIG. 3 as an example, the case where the value of the variable n is "2" will be described. In the edit history data of FIG. 3, each row is arranged in the edit order.

[0067] When the second row is targeted, the element IDs "01" to "51" of the edit elements before this are acquired as the created or edited element ID. Since the value of the variable n is "2", "toilet" and "washbasin counter" are acquired as the edit elements, "001" is acquired as the user ID, and "35" and "38" are acquired as the edit times, respectively.

[0068] When the third row is targeted, the element IDs "01" to "52" of the edit elements before this are acquired as the created or edited element ID. Since the value of the variable n is "2", "washbasin counter" and "mirror" are acquired as the edit elements, "001" is acquired as the user ID, and "38" and "70" are acquired as the edit times, respectively.

[0069] Next, proceed to step S112, and calculate the evaluation value by multiplying the sum of the editing times obtained in step S110 by "-1". In the example of the second line above, since the editing times "35" and "38" are obtained, the evaluation value is calculated as (35 + 38) × -1 = -73. The reason for multiplying by "-1" is to set a higher evaluation value for shorter editing times.

[0070] Next, proceed to step S114, associate the element ID, element order, user ID obtained in steps S104 to S110, and the evaluation value calculated in step S112, and register them in the learning data. Then, proceed to step S116, add "1" to the value of variable n, and proceed to step S118.

[0071] In step S118, determine whether the value of variable n is greater than "4". If it is determined that it is "4" or less (NO), proceed to step S104. Then, repeat the processing of steps S104 to S116 until the value of variable n becomes "4".

[0072] Taking Figure 3 as an example, the processing of steps S104 to S112 will be described for the case where the value of variable n is "3".

[0073] For the second line, the element IDs "01" to "51" of the previous edited element are obtained as the created or edited element ID. Since the value of variable n is "3", "toilet", "washbasin counter", and "mirror" are obtained as the edited elements, "001" is obtained as the user ID, and "35", "38", and "70" are obtained as the editing times respectively. The evaluation value is calculated as (35 + 38 + 70) × -1 = -143.

[0074] For the third line, the element IDs "01" to "52" of the previous edited element are obtained as the created or edited element ID. Since the value of variable n is "3", "washbasin counter", "mirror", and "towel rack" are obtained as the edited elements, "001" is obtained as the user ID, and "38", "70", and "94" are obtained as the editing times respectively. The evaluation value is calculated as (38 + 70 + 94) × -1 = -202.

[0075] Also, taking FIG. 3 as an example, the processing of steps S104 to S112 will be described for the case where the value of the variable n is "4".

[0076] When the second line is targeted, the element IDs "01" to "51" of the editing elements before this are acquired as the created or edited element IDs. Since the value of the variable n is "4", "toilet", "washstand counter", "mirror", and "towel rack" are acquired as the editing elements, "001" is acquired as the user ID, and "35", "38", "70", and "94" are acquired as the editing times. The evaluation value is calculated as (35 + 38 + 70 + 94) × -1 = -237.

[0077] When the third line is targeted, the element IDs "01" to "52" of the editing elements before this are acquired as the created or edited element IDs. Since the value of the variable n is "4", "washstand counter", "mirror", "towel rack", and "ventilator" are acquired as the editing elements, "001" is acquired as the user ID, and "38", "70", "94", and "94" are acquired as the editing times. The evaluation value is calculated as (38 + 70 + 94 + 94) × -1 = -296.

[0078] On the other hand, in step S118, when it is determined that the value of the variable n is greater than "4" (YES), the process proceeds to step S120 to determine whether the processing of steps S100 to S118 has been completed for all the editing history data. When it is determined that the processing has been completed for all the editing history data (YES), the process proceeds to step S122.

[0079] In step S122, the learning data in which the element ID and other information are registered in step S114 is stored in the storage device 42.

[0080] FIG. 5 is a diagram showing the structure of the learning data. As shown in FIG. 5, the learning data includes, for each row, an element ID 410 that has been created or edited, element order information 412, a user ID 414, and an evaluation value 416. The element order information 412 includes the area to be edited and the element order of the edited element.

[0081] The second row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the first row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The third row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the second row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The fourth row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the third row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. Also, the sixth row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the fifth row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The seventh row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the sixth row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The eighth row of FIG. 5 shows two edited elements that are continuously edited after the edited element in the seventh row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value.

[0082] Also, the tenth row of FIG. 5 shows three edited elements that are continuously edited after the edited element in the first row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The eleventh row of FIG. 5 shows three edited elements that are continuously edited after the edited element in the second row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. Also, the thirteenth row of FIG. 5 shows three edited elements that are continuously edited after the edited element in the fifth row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value. The fourteenth row of FIG. 5 shows three edited elements that are continuously edited after the edited element in the sixth row of FIG. 3, their editing order, the user ID of the editing user, and the evaluation value.

[0083] Also, the 16th line of FIG. 5 shows four editing elements that are edited consecutively after the editing element on the 1st line of FIG. 3, the editing order thereof, the user ID of the editing user, and the evaluation value. The 18th line of FIG. 5 shows four editing elements that are edited consecutively after the editing element on the 5th line of FIG. 3, the editing order thereof, the user ID of the editing user, and the evaluation value.

[0084] 〔Trained Model Generation Process〕 FIG. 6 is a flowchart showing the trained model generation process.

[0085] FIG. 7 is a block diagram showing the steps of generating and using a trained model. The trained model generation process is a process executed to generate a trained model. When executed in the CPU 30, as shown in FIG. 6, it proceeds to step S200 and executes the learning data analysis process. In the learning data analysis process, the learning data is read from the storage device 42, and the created or edited element ID 410, element order information 412, user ID 414, and evaluation value 416 are extracted from the read learning data.

[0086] Next, it proceeds to step S202. In step S202, as shown in FIG. 7, a learning data set is generated based on the information extracted in step S200, and then it proceeds to step S204. The generated learning data set is input to the learning program, and a trained model is generated by the learning program. The learning program includes pre-learning parameters and hyperparameters, performs learning based on the input learning data set and hyperparameters, and updates the pre-learning parameters. As a learning method, for example, reinforcement learning (e.g., supervised reinforcement learning, imitation learning) can be adopted. In reinforcement learning, for a combination of a created or edited element ID, element order information regarding a plurality of editing elements that are edited consecutively after the editing element, and the user ID, an evaluation value regarding the editing of the plurality of editing elements is given, and learning is performed so that the evaluation value becomes maximum. Then, a trained model is output as the learning result.

[0087] The learned model is trained so that the evaluation value 416 is maximized based on the created or edited element ID 410, element order information 412, user ID 414, and evaluation value 416. The learned model includes learned parameters obtained by updating pre-learning parameters through learning and an inference program. The inference program inputs the created or edited element ID and the user ID of the user currently being edited (hereinafter referred to as the "target user"), and based on the learned parameters, estimates the element order information that matches the target user from the input element ID and user ID, and outputs the estimated element order information. Note that the relationship between the input element ID and user ID and the output element order information is determined by the learning of AI, so although it shows a tendency similar to the content of past learning data, there is ambiguity and it does not necessarily match exactly. However, this ambiguity can be reduced by the amount of learning data and learning accuracy.

[0088] Next, the process proceeds to step S206, where the learned model generated in step S204 is stored in the storage device 42, and a series of processes is terminated.

[0089] 〔Element Order Information Estimation Process〕 FIG. 8 is a flowchart showing the element order information estimation process.

[0090] The element order information estimation process is a process executed in response to a request from the target user. When executed in the CPU 30, as shown in FIG. 8, first, the process proceeds to step S300.

[0091] In step S300, the user ID of the target user is acquired, the process proceeds to step S302, the created or edited element ID is acquired from the CAD data currently being edited, and the process proceeds to step S304.

[0092] In step S304, using the learned model of the storage device 42, from the element ID and user ID obtained in steps S300 and S302, element order information that conforms to the target user and that has different edited elements or editing orders among a plurality of element order information is estimated. The estimation is performed by inputting the element ID and user ID into the learned model and obtaining the element order information output from the learned model. For the learned model, it is also possible to obtain a plurality of outputs from one input, or to obtain a plurality of outputs by repeating one input and one output a plurality of times.

[0093] Next, proceed to step S306, and based on the plurality of element order information estimated in step S304, display any one of the plurality of element orders on the display device 44 according to any one of the plurality of display rules. Which display rule to use may be set by the target user, for example, or may be set by a predetermined algorithm.

[0094] The first display rule is to display the element order with the largest number of edited elements among the plurality of estimated element orders.

[0095] The second display rule is to display the element order having a related group among the plurality of estimated element orders. For example, as the plurality of element orders estimated from the current editing state, there are (1) A, B, (2) A, B, C, (3) A, B, C, D, (4) A, B, C, D, E, (5) A, B, C, D, E, F, and if A to D among them are a related group, according to the second display rule, any one of (3) to (5) is displayed. The determination of whether it is a related group can be performed, for example, by specifying those in which the number of occurrences in the learning data of two or more edited elements and their editing orders among A to F is equal to or more than a predetermined value. The same applies to the third and fourth display rules below.

[0096] The third display rule is to display the element order that is the same as the relevant group among the plurality of presumed element orders. For example, when the plurality of element orders presumed from the current editing state are the above (1) to (5), according to the third display rule, (3) is displayed.

[0097] The fourth display rule is to display the part with the relevant group from the element order including the relevant group and other editing elements among the plurality of presumed element orders. For example, when the plurality of element orders presumed from the current editing state are the above (1), (2), (5), according to the fourth display rule, A to D are displayed from (5).

[0098] Next, proceed to step S308. When the target user creates or edits an editing element based on the displayed element order, obtain the created or edited element ID including the element ID of the editing element from the CAD data being currently edited, and proceed to step S310.

[0099] In step S310, based on the element order displayed in steps S306 and S316 and the element ID obtained in step S308, determine whether the editing element created or edited by the target user is different from the editing element or editing order displayed in steps S306 and S316. If it is determined that the editing result is different from the estimation result (YES), proceed to step S312.

[0100] In step S312, change the display rule used for display in steps S306 and S316. For example, change it to an optimal display rule so that the editing result matches the estimation result. The timing of changing the display rule does not have to be for each creation or edit, and it can also be for multiple creations or edits.

[0101] Next, proceed to step S314. Similar to the process of step S304, use the learned model of the storage device 42 to estimate a plurality of element order information from the element ID and user ID obtained in steps S300 and S308, and proceed to step S316.

[0102] In step S316, similar to the process of step S306, any one of the plurality of element orders is displayed on the display device 44 based on the plurality of element order information estimated in step S314, and the process proceeds to step S318.

[0103] In step S318, it is determined whether the editing by the target user has been completed. If it is determined that the editing has been completed (YES), the series of processes is terminated.

[0104] On the other hand, if it is determined in step S318 that the editing by the target user has not been completed (NO), the process proceeds to step S308.

[0105] On the other hand, if it is determined in step S310 that the editing result does not match the estimation result (NO), the process proceeds to step S314.

[0106] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0107] FIG. 9 is a schematic diagram assuming the piano to be carried in. When the designer wants to install a piano with a width of 120 [mm] in the floor plan of Figure 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying the piano in, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it becomes necessary to edit other editing elements of the toilet as well. Therefore, when the designer requests an estimation of the order of elements to be edited for the toilet after changing the width of the toilet, through steps S300 to S306, the created or edited element IDs and user IDs are obtained, and the element order is estimated and displayed from the obtained element IDs and user IDs. For example, when the element order information on the 16th line of Figure 5 is estimated, "toilet → washbasin counter → mirror → towel rack" is displayed. When these editing elements are already included in the CAD data as shown in Figure 9, for example, these editing elements are highlighted (for example, displayed in a specific color or pattern) and connected with arrows or the like to display the editing order. When not included in the CAD data, for example, these editing elements are ghost displayed (for example, the ghost image of the editing element is displayed in wireframe) and connected with arrows or the like to display the editing order.

[0108] Then, when the designer creates or edits the editing element "toilet" based on the estimated and displayed element order, through steps S308 to S316, the next element order is estimated and displayed. When the designer's editing result is different from the estimated result, the display rule is changed through step S312.

[0109] 〔Effects of this Embodiment〕 Next, the effects of this embodiment will be described. In this embodiment, the created or edited element IDs and the user ID of the target user are obtained, and using the learned model, element order information suitable for the target user is estimated from the obtained element IDs and user ID.

[0110] Thereby, it is possible to grasp a plurality of editing elements that are continuously edited and their editing order. The estimated element order information is suitable for the target user because it is suitable for the target user.

[0111] Furthermore, in the present embodiment, a plurality of element order information with different editing elements or editing orders is estimated, and any one of the plurality of element orders is displayed based on the estimated plurality of element order information.

[0112] As a result, it is possible to grasp a plurality of candidates for a plurality of editing elements that are continuously edited and their editing order.

[0113] Furthermore, in the present embodiment, the element order with the largest number of editing elements among the estimated plurality of element orders is displayed.

[0114] As a result, the designer can perform editing while imagining a large editing unit. Furthermore, in the present embodiment, an element order with an appearance frequency in the learning data equal to or greater than a predetermined value is specified as a related group, and an element order having a related group among the estimated plurality of element orders is displayed.

[0115] As a result, the designer can perform editing while imagining a related group.

[0116] Furthermore, in the present embodiment, an element order with an appearance frequency in the learning data equal to or greater than a predetermined value is specified as a related group, and an element order identical to the related group among the estimated plurality of element orders is displayed.

[0117] As a result, the designer can perform editing while imagining a related group.

[0118] Furthermore, in the present embodiment, an element order with an appearance frequency in the learning data equal to or greater than a predetermined value is specified as a related group, and a part with a related group is displayed from an element order including the related group and other editing elements among the estimated plurality of element orders.

[0119] As a result, the designer can perform editing while imagining a related group.

[0120] Furthermore, in the present embodiment, based on the displayed element order, the created or edited element IDs including the element IDs of the edited elements created or edited by the target user are acquired, and using the learned model, from the acquired element IDs and user ID, the element order information suitable for the target user is estimated.

[0121] As a result, since the element order is estimated and displayed for the result of creation or editing based on the displayed element order, it is possible to grasp a plurality of edited elements that are continuously edited and their editing order.

[0122] Furthermore, in the present embodiment, based on the displayed element order, the created or edited element IDs including the element IDs of the edited elements created or edited by the target user are acquired, and the display rule is changed based on the displayed element order and the acquired element IDs.

[0123] As a result, the display rule can be changed according to the display result of the element order and the result of subsequent creation or editing.

[0124] Furthermore, in the present embodiment, the learned model is learned based on learning data including the created or edited element IDs, the element order information regarding a plurality of edited elements continuously edited after the edited element and their editing order, the user ID of the editing user, and the evaluation value regarding the editing of the plurality of edited elements so that the evaluation value is maximized.

[0125] As a result, it is possible to grasp the element order with a high evaluation value. Furthermore, in the present embodiment, for the combination of the created or edited element IDs, the element order information regarding a plurality of edited elements continuously edited after the edited element and their editing order, and the user ID, an evaluation value regarding the editing of the plurality of edited elements is given, and a learned model is generated by performing learning so that the evaluation value is maximized.

[0126] As a result, a learned model with the element order having a high evaluation value can be obtained. 〔Second Embodiment〕 Next, a second embodiment of the present invention will be described. FIGS. 10 to 12 are diagrams showing this embodiment. In addition, FIGS. 3, 5, 6, and 9 are incorporated.

[0127] This embodiment is different from the above-described first embodiment in that estimation is performed using a first learned model and a second learned model that have been learned respectively with evaluation values based on different indices. Hereinafter, only the parts different from the above-described first embodiment will be described, and the overlapping parts will be omitted from the description.

[0128] 〔Configuration of this Embodiment〕 First, the configuration of this embodiment will be described. FIG. 10 is a diagram showing the structure of the edit history data.

[0129] The storage device 42 stores the edit history data of FIG. 10 in addition to the edit history data of FIG. 3 for each CAD data.

[0130] As shown in FIG. 10, the edit history data includes, for each edited edit element, element information 420 regarding the edit element, the user ID 422 of the editing user, and the number of edit items required for the edit of the edit element, in the edit order.

[0131] In the example of FIG. 10, as a first related group, it shows that the edit elements of the toilet, "toilet bowl", "washbasin counter", "mirror", and "towel rack" are continuously edited in that order. Element IDs "52", "53", "54", and "55" are assigned to these edit elements, and the number of edit items is 8, 5, 6, and 9 respectively. These edit elements are being edited by a user with the user ID "001".

[0132] Also, as a second related group, it shows that the editing elements of the toilet, "ventilation fan", "lighting", "storage", and "outlet", are continuously edited in that order. Element IDs "56", "57", "58", and "59" are assigned to these editing elements, and the number of editing items is 3, 7, 8, and 6 respectively. These editing elements are being edited by the user with user ID "001".

[0133] Also, as a third related group, it shows that the editing elements of the closet, "shelf board", "hanger pipe", "drawer", and "basket", are continuously edited in that order. Element IDs "60", "61", "62", and "63" are assigned to these editing elements, and the number of editing items is 8, 7, 2, and 4 respectively. These editing elements are being edited by the user with user ID "002".

[0134] Also, as a fourth related group, it shows that the editing elements of the kitchen, "floor material", "wall material", "counter", and "sink", are continuously edited in that order. Element IDs "64", "65", "66", and "67" are assigned to these editing elements, and the number of editing items is 7, 4, 3, and 8 respectively. These editing elements are being edited by the user with user ID "003".

[0135] 〔Operation of this Embodiment〕 Next, the operation of this embodiment will be described. 〔Learning Data Generation Process〕 In the learning data generation process, similar to the generation of the learning data in FIG. 5, learning data is generated based on the editing history data in FIG. 10.

[0136] FIG. 11 is a diagram showing the structure of the learning data. As shown in FIG. 11, the learning data includes, for each row, the created or edited element ID 430, the element order information 432, the user ID 434, and the evaluation value 436.

[0137] The second row of FIG. 11 shows two editing elements edited consecutively after the editing element in the first row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The third row of FIG. 11 shows two editing elements edited consecutively after the editing element in the second row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The fourth row of FIG. 11 shows two editing elements edited consecutively after the editing element in the third row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. Also, the sixth row of FIG. 11 shows two editing elements edited consecutively after the editing element in the fifth row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The seventh row of FIG. 11 shows two editing elements edited consecutively after the editing element in the sixth row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The eighth row of FIG. 11 shows two editing elements edited consecutively after the editing element in the seventh row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value.

[0138] Also, the tenth row of FIG. 11 shows three editing elements edited consecutively after the editing element in the first row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The eleventh row of FIG. 11 shows three editing elements edited consecutively after the editing element in the second row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. Also, the thirteenth row of FIG. 11 shows three editing elements edited consecutively after the editing element in the fifth row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The fourteenth row of FIG. 11 shows three editing elements edited consecutively after the editing element in the sixth row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value.

[0139] Also, the sixteenth row of FIG. 11 shows four editing elements edited consecutively after the editing element in the first row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value. The eighteenth row of FIG. 11 shows four editing elements edited consecutively after the editing element in the fifth row of FIG. 10, their editing order, the user ID of the editing user, and the evaluation value.

[0140] 〔Trained Model Generation Process〕 In the trained model generation process, through steps S200 to S204, learning is performed based on the learning data in FIG. 5 to generate a first trained model. The first trained model is the same as the trained model in the above first embodiment.

[0141] In the trained model generation process, through steps S200 to S204, similar to the generation of the first trained model, learning is performed based on the learning data in FIG. 11 to generate a second trained model. The second trained model is learned so that the evaluation value 436 is maximized based on the created or edited element ID 430, element order information 432, user ID 434, and evaluation value 436.

[0142] Then, it proceeds to step S206, stores the first trained model and the second trained model generated in step S204 in the storage device 42, and ends a series of processes.

[0143] 〔Element Order Information Estimation Process〕 FIG. 12 is a flowchart showing the element order information estimation process.

[0144] The element order information estimation process is a process executed in response to a request from a target user. When executed in the CPU 30, as shown in FIG. 12, first, it proceeds to step S330.

[0145] In step S330, index information regarding a first index "editing time" or a second index "number of editing items", which indicates an index of the value of the evaluation value, is acquired. Then, it proceeds to step S332. If the index related to the acquired index information is the first index, the first trained model is selected. If the index related to the acquired index information is the second index, the second trained model is selected.

[0146] Next, it proceeds to step S334 to acquire the user ID of the target user, then proceeds to step S336 to acquire the created or edited element ID from the CAD data being edited, and then proceeds to step S338.

[0147] In step S338, using the learned model selected in step S332 (hereinafter referred to as the "selected learned model") from among the first learned model and the second learned model of the storage device 42, a plurality of element order information is estimated from the element ID and the user ID acquired in steps S334 and S336. The estimation method is the same as the process of step S304 in the first embodiment above.

[0148] Next, the process proceeds to step S340. Similar to the process of step S306, based on the plurality of element order information estimated in step S338, any one of the plurality of element orders is displayed on the display device 44, and the process proceeds to step S342.

[0149] In step S342, when the target user creates or edits an editing element based on the displayed element order, the created or edited element ID including the element ID of the editing element is acquired from the CAD data being currently edited, and the process proceeds to step S344.

[0150] In step S344, based on the element order displayed in steps S340 and S350 and the element ID acquired in step S342, it is determined whether the editing element created or edited by the target user is different from the editing element or the editing order displayed in steps S340 and S350. If it is determined that the editing result is different from the estimation result (YES), the process proceeds to step S346.

[0151] In step S346, similar to the process of step S312, the display rule used for display in steps S340 and S350 is changed, and the process proceeds to step S348.

[0152] In step S348, similar to the process of step S338, using the selected learned model, a plurality of element order information is estimated from the element ID and the user ID acquired in steps S334 and S342, and the process proceeds to step S350.

[0153] In step S350, similar to the process of step S340, based on the plurality of element order information estimated in step S348, any one of the plurality of element orders is displayed on the display device 44, and the process proceeds to step S352.

[0154] In step S352, it is determined whether the editing by the target user has been completed. If it is determined that the editing has been completed (YES), the series of processes is terminated.

[0155] On the other hand, if it is determined in step S352 that the editing by the target user has not been completed (NO), the process proceeds to step S342.

[0156] On the other hand, if it is determined in step S344 that the editing result does not match the estimation result (NO), the process proceeds to step S348.

[0157] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0158] When the designer wants to install a piano with a width of 120 [mm] in the plan view of FIG. 9 in the CAD software, in order to prevent interference between the piano and the toilet wall when carrying in the piano, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it becomes necessary to edit other editing elements of the toilet as well. Therefore, after changing the width of the toilet, the designer requests an estimation of the order of elements to be edited for the toilet. At this time, if the designer wants to obtain an element order that shortens the editing time and selects "editing time" as an index, through steps S330 to S332, the first learned model is selected. Then, through steps S334 to S340, the created or edited element IDs and user IDs are obtained, and the element order is estimated and displayed from the obtained element IDs and user IDs by the first learned model.

[0159] On the other hand, when the designer wants to obtain an element order in which the number of editing items decreases, if the designer selects "the number of editing items" as an index, through steps S330 to S332, a second learned model is selected. Then, through steps S334 to S340, the created or edited element ID and user ID are obtained, and the element order is estimated and displayed from the obtained element ID and user ID by the second learned model.

[0160] 〔Effects of this embodiment〕 Next, the effects of this embodiment will be described. In this embodiment, index information regarding the first index or the second index is obtained, either the first learned model or the second learned model is selected based on the obtained index information, the created or edited element ID and user ID are obtained, and a plurality of element order information is estimated from the obtained element ID and user ID using the selected learned model.

[0161] Thereby, it is possible to grasp the element order with a high evaluation value based on the first index or the second index.

[0162] 〔Third Embodiment〕 Next, a third embodiment of the present invention will be described. FIGS. 13 to 14 are diagrams showing this embodiment. In addition, FIGS. 3, 5, 6, and 9 are incorporated.

[0163] This embodiment is different from the above-described first embodiment in that element order information suitable for the target user is estimated using the second learned model from the plurality of element order information estimated by the first learned model. Hereinafter, only the parts different from the above-described first embodiment will be described, and the description of the overlapping parts will be omitted.

[0164] 〔Operation of this embodiment〕 First, the operation of this embodiment will be described. 〔Learning data generation process〕 In the learning data generation process, learning data is generated based on the editing history data in FIG. 3 in the same manner as the generation of the learning data in FIG. 5.

[0165] FIG. 13 is a diagram showing the structure of learning data. As shown in FIG. 13, the learning data includes, for each row, element order information 440, user ID 442, and evaluation value 444. It is different from the learning data in FIG. 5 in that it does not have the created or edited element ID 410. The learning data in FIG. 13 can be configured, for example, (1) by deleting the element ID 410 from the learning data in FIG. 5, (2) by generating it by a generation method different from that of the learning data in FIG. 5 based on the edit history data in FIG. 3, or (3) by being based on data other than the edit history data in FIG. 3, etc., and can be configured independently of the content of the learning data in FIG. 5. The evaluation value 444 is calculated based on the editing time required for editing the edited element, similar to the first embodiment. The higher the evaluation value 444, the higher the possibility that the user with the user ID 442 selects the element order.

[0166] 〔Trained model generation process〕 Prepare general-purpose learning data with the user ID 414 deleted from the learning data in FIG. 5. In the trained model generation process, through steps S200 to S204, similar to the generation of the trained model in the first embodiment, learning is performed based on the general-purpose learning data to generate a first trained model. The first trained model is learned so that the evaluation value 416 is maximized based on the created or edited element ID 410, element order information 412, and evaluation value 416.

[0167] In the trained model generation process, through steps S200 to S204, similar to the generation of the trained model in the first embodiment, learning is performed based on the learning data in FIG. 13 to generate a second trained model. The second trained model is learned so that the evaluation value 444 is maximized based on the element order information 440, user ID 442, and evaluation value 444.

[0168] Then, it proceeds to step S206, stores the first trained model and the second trained model generated in step S204 in the storage device 42, and ends a series of processes.

[0169] 〔Element Order Information Estimation Process〕 FIG. 14 is a flowchart showing the element order information estimation process.

[0170] The element order information estimation process is a process executed in response to a request from a target user. When executed in the CPU 30, as shown in FIG. 14, first, the process proceeds to step S360.

[0171] In step S360, the user ID of the target user is acquired, and the process proceeds to step S362 to acquire the created or edited element IDs from the CAD data being currently edited, and then the process proceeds to step S364.

[0172] In step S364, using the first learned model in the storage device 42, a plurality of element order information is estimated from the element IDs acquired in step S362. The estimation method is the same as the process of step S304 in the above first embodiment.

[0173] Next, the process proceeds to step S366, and using the second learned model in the storage device 42, among the plurality of element order information estimated in step S364 and the user ID acquired in step S360, the one that matches the target user is estimated. The estimation is performed by inputting the plurality of element order information and the user ID into the second learned model and acquiring the element order information output from the second learned model.

[0174] Next, the process proceeds to step S368, and based on the element order information estimated in step S366, the element order is displayed on the display device 44. Then the process proceeds to step S370 to determine whether the editing by the target user has ended. If it is determined that the editing has ended (YES), the series of processes is terminated.

[0175] On the other hand, if it is determined in step S370 that the editing by the target user has not ended (NO), the process proceeds to step S362.

[0176] 〔When assuming the piano is to be carried in〕 Next, the operation when assuming the piano is to be carried in will be described.

[0177] When the designer wants to install a piano with a width of 120 [mm] in the floor plan of FIG. 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying in the piano, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it becomes necessary to edit other editing elements of the toilet as well. Therefore, after the designer changes the width of the toilet and requests an estimation of the order of elements to be edited for the toilet, through steps S360 to S364, the created or edited element IDs and user IDs are obtained, and from the obtained element IDs, a plurality of element order information is estimated by the first pre-trained model. Then, through steps S366 to S368, based on the plurality of estimated element order information and the obtained user ID, the element order is estimated and displayed by the second pre-trained model. That is, in step S364, a plurality of candidates for the element order are estimated, and in step S366, those that match the target user among the candidates are narrowed down.

[0178] Then, when the designer creates or edits the editing element "toilet bowl" based on the estimated and displayed element order, through steps S362 to S368, the next element order is estimated and displayed.

[0179] 〔Effect of this embodiment〕 Next, the effect of this embodiment will be described. In this embodiment, a plurality of element order information and the user ID of the target user are obtained, and using the second pre-trained model, element order information that matches the target user is estimated from the obtained plurality of element order information and user ID.

[0180] Thereby, it is possible to grasp a plurality of editing elements that are continuously edited and their editing order. The estimated element order information is suitable for the target user because it matches the target user.

[0181] 〔Fourth Embodiment〕 Next, a fourth embodiment of the present invention will be described. FIGS. 15 to 16 are diagrams showing this embodiment. In addition, FIGS. 6, 9, 11, and 13 are incorporated by reference.

[0182] This embodiment is different from the above-described third embodiment in that estimation is performed using a second learned model and a third learned model that have been learned respectively with evaluation values based on different indicators. Hereinafter, only the parts different from the above-described third embodiment will be described, and the overlapping parts will be omitted.

[0183] 〔Operation of this Embodiment〕 First, the operation of this embodiment will be described. 〔Learning Data Generation Process〕 In the learning data generation process, learning data is generated based on the edit history data in FIG. 10 in the same manner as the generation of the learning data in FIG. 11.

[0184] FIG. 15 is a diagram showing the structure of the learning data. As shown in FIG. 15, the learning data includes, for each row, element order information 450, user ID 452, and evaluation value 454. It is different from the learning data in FIG. 11 in that it does not have the created or edited element ID 430. The learning data in FIG. 15 can be configured independently of the learning data in FIG. 11, for example, (1) by deleting the element ID 430 from the learning data in FIG. 11, (2) by generating it by a generation method different from that of the learning data in FIG. 11 based on the edit history data in FIG. 10, or (3) based on data other than the edit history data in FIG. 10. The evaluation value 454 is calculated based on the number of edit items required for the edit of the edited element, in the same manner as in the second embodiment above. The higher the evaluation value 454, the higher the possibility that the user with the user ID 452 will select the element order.

[0185] 〔Learned Model Generation Process〕 In the trained model generation process, through steps S200 to S204, similar to the generation of the trained model in the first embodiment, a third trained model is generated by performing learning based on the learning data in FIG. 15. The third trained model is learned so that the evaluation value 454 is maximized based on the element order information 450, the user ID 452, and the evaluation value 454.

[0186] Then, it proceeds to step S206, stores the third trained model generated in step S204 in the storage device 42, and ends the series of processes.

[0187] 〔Element order information estimation process〕 FIG. 16 is a flowchart showing the element order information estimation process.

[0188] The element order information estimation process is a process executed in response to a request from the target user. When executed in the CPU 30, as shown in FIG. 16, first, it proceeds to step S380.

[0189] In step S380, index information regarding the first index "editing time" or the second index "number of editing items", which indicates the index of the value of the evaluation value, is acquired, and it proceeds to step S382. If the index related to the acquired index information is the first index, the second trained model is selected, and if the index related to the acquired index information is the second index, the third trained model is selected.

[0190] Next, it proceeds to step S384 to acquire the user ID of the target user, proceeds to step S386 to acquire the created or edited element ID from the CAD data being currently edited, and proceeds to step S388.

[0191] In step S388, using the first trained model in the storage device 42, a plurality of element order information is estimated from the element ID acquired in step S386. The estimation method is the same as the process of step S364 in the third embodiment.

[0192] Next, proceed to step S390, and use the learned model selected in step S382 (hereinafter referred to as the "selected learned model") from among the second and third learned models in the storage device 42 to estimate, from the plurality of element order information estimated in step S388 and the user ID acquired in step S384, the element order information that matches the target user among them. The estimation method is the same as the process of step S366 in the above-described third embodiment.

[0193] Next, proceed to step S392, display the element order on the display device 44 based on the element order information estimated in step S390, proceed to step S394, determine whether the editing by the target user has ended, and if it is determined that the editing has ended (YES), end the series of processes.

[0194] On the other hand, if it is determined in step S394 that the editing by the target user has not ended (NO), proceed to step S386.

[0195] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0196] When a designer wants to install a piano with a width of 120 [mm] in the layout diagram of Figure 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying the piano in, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it is also necessary to edit other editing elements of the toilet. Therefore, after changing the width of the toilet, the designer requests an estimation of the order of elements to be edited for the toilet. At this time, if the designer wants to obtain an element order that shortens the editing time, when selecting "editing time" as an index, through steps S380 - S382, the second pre-trained model is selected. Then, through steps S384 - S388, the created or edited element IDs and user IDs are obtained, and from the obtained element IDs, a plurality of element order information is estimated by the first pre-trained model. And through steps S390 - S392, from the plurality of estimated element order information and the obtained user ID, the element order is estimated and displayed by the second pre-trained model.

[0197] On the contrary, if the designer wants to obtain an element order that reduces the number of editing items, when selecting "number of editing items" as an index, through steps S380 - S382, the third pre-trained model is selected. And through steps S390 - S392, from the plurality of estimated element order information and the obtained user ID, the element order is estimated and displayed by the third pre-trained model.

[0198] 〔Effects of this Embodiment〕 Next, the effects of this embodiment will be described. In this embodiment, index information regarding the first index or the second index is acquired, either the second pre-trained model or the third pre-trained model is selected based on the acquired index information, a plurality of element order information and user IDs are acquired, and using the selected pre-trained model, from the acquired plurality of element order information and user IDs, element order information suitable for the target user is estimated.

[0199] Thereby, it is possible to grasp the element order with a high evaluation value based on the first index or the second index.

[0200] 〔Fifth Embodiment〕 Next, a fifth embodiment of the present invention will be described. FIGS. 17 to 20 are diagrams showing this embodiment. In addition, FIGS. 5 and 9 are incorporated by reference.

[0201] This embodiment is different from the above-described first embodiment in that a Large Language Model is used. Hereinafter, only the parts different from the first embodiment will be described, and the overlapping parts will be omitted.

[0202] 〔Configuration of This Embodiment〕 First, the configuration of this embodiment will be described. FIG. 17 is a block diagram showing the configuration of a network system according to this embodiment.

[0203] As shown in FIG. 17, a drawing creation support device 100 and a generation AI server 120 that generates response information by an AI (Artificial Intelligence) model in response to a request are communicably connected to the Internet 199.

[0204] 〔Generation AI Server 120〕 Next, the configuration of the generation AI server 120 will be described. The generation AI server 120 has a hardware configuration similar to that of a general computer in which a CPU, ROM, RAM, I / F, etc. are bus-connected, and is configured as, for example, a cloud server, similar to the drawing creation support device 100.

[0205] FIG. 18 is a functional block diagram of the generation AI server 120. As shown in FIG. 18, the generation AI server 120 includes a plurality of AI models 50, an AI model control unit 52 that controls the AI models 50, and a knowledge base 54 that registers data referred to by the AI models 50 for inference.

[0206] The AI model 50 is an AI model trained on a large-scale dataset and is a highly versatile model capable of handling various tasks. As the AI model 50, for example, a large language model can be adopted. A large language model is a deep learning model that pre-learns from vast amounts of data a language model called one that models human spoken language by its occurrence probability. When a prompt is input, the large language model statistically infers the generation probability of the next word from the text contained in the input prompt and outputs the inference result. As the large language model, for example, known technologies described on the Internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be adopted. More specifically, for example, Titan Text G1 - Express, Titan Text G1 - Lite, Titan Image Generator G1, Titan Embeddings G1 - Text, Titan Embeddings Text V2, Titan Multimodal Embeddings G1, Claude, Claude Instant, Claude 3 Sonnet, Claude 3 Haiku, Claude 3 Opus, Jurassic-2 Mid, Jurassic-2 Ultra, Command, Command Light, Command R, Command R+, Embed English, Embed Multilingual, Llama 2 Chat 13B, Llama 2 Chat 70B, Llama 2 13B, Llama 2 70B, Llama 3 8b Instruct, Llama 3 70b Instruct, Mistral 7B Instruct, Mixtral 8X7B Instruct, Mistral Large, Stable Diffusion XL can be adopted.

[0207] The AI model control unit 52 selects, in response to a selection request from the request processing unit 58, one to be used for inference from among the plurality of AI models 50. Also, when a reference request is input from the request processing unit 58, the selected AI model 50 (hereinafter referred to as the "selected AI model") is made to refer to the data in the knowledge base 54 in response to the input reference request. Further, when a prompt is input from the request processing unit 58, the input prompt is input to the selected AI model. Then, when an execution request is input from the request processing unit 58, inference is executed on the selected AI model in response to the input execution request, an inference result is obtained from the selected AI model, and the obtained inference result is output to the request processing unit 58.

[0208] The knowledge base 54 can register learning data. The registered information in the knowledge base 54 is in a data format (for example, vector data) that can be referred to by the AI model 50.

[0209] The generation AI server 120 further includes a request reception unit 56 that receives requests, a request processing unit 58 that processes the requests received by the request reception unit 56, and a response information transmission unit 60 that transmits response information for the requests received by the request reception unit 56 to the drawing creation support apparatus 100.

[0210] The request reception unit 56 receives, from the drawing creation support apparatus 100, a request for generating response information, and outputs the received request to the request processing unit 58. The request includes (1) an element ID that has been created or edited, (2) a user ID, (3) a generation request for generating a plurality of editing elements to be continuously edited next to the created or edited editing element and element order information (element order information suitable for the target user) regarding the editing order thereof, (4) a selection request for selecting the AI model 50, and (5) a reference request for referring to the learning data in the knowledge base 54. (4) and (5) are not essential and are additionally included.

[0211] When the request received by the request processing unit 58 includes a selection request or a reference request, the request processing unit 58 outputs the selection request or the reference request to the AI model control unit 52. Also, based on the request received by the request receiving unit 56, a prompt for instructing the AI model 50 is generated. As the prompt, for example, based on the created or edited element ID and user ID, a plurality of edited elements to be continuously edited after the created or edited edited element and element order information (element order information suitable for the target user) regarding the editing order thereof, which have an evaluation value equal to or greater than a predetermined value, are generated and the content of requesting the AI model 50 to do so. Then, the generated prompt and execution request are output to the AI model control unit 52, and when an inference result is input from the AI model control unit 52 for the execution request, the input inference result is output to the response information transmission unit 60.

[0212] The response information transmission unit 60 transmits response information including the inference result input from the request processing unit 58 to the drawing creation support device 100.

[0213] The generation AI server 120 further includes a request receiving unit 62 that receives a request and a learning data registration unit 64 that registers learning data in the knowledge base 54.

[0214] The request receiving unit 62 receives a request for registering learning data from the drawing creation support device 100 and outputs the received request to the learning data registration unit 64. The request includes (1) learning data.

[0215] The learning data registration unit 64 stores the learning data included in the request received by the request reception unit 62 in a storage (not shown) and converts it into a data format (e.g., vector data) that can be referenced by the AI model 50. The vector data can be generated by a technique (embedding) that converts data including characters, images, voices, etc. into numerical vectors. Then, the converted learning data is registered in the knowledge base 54. The AI model control unit 52 causes the selection AI model to refer to the learning data in response to a reference request from the request processing unit 58.

[0216] [Operation of this Embodiment] Next, the operation of this embodiment will be described. [Learning Data Registration Process] FIG. 19 is a flowchart showing the learning data registration process.

[0217] The learning data registration process is a process executed in response to a request from a target user. When executed by the CPU 30, as shown in FIG. 19, first, it proceeds to step S400.

[0218] In step S400, the learning data in FIG. 5 is acquired from the storage device 42, and the process proceeds to step S402.

[0219] In step S402, a request for registering the learning data is transmitted to the generation AI server 120. The request includes (1) the learning data acquired in step S400.

[0220] When the process of step S402 ends, the series of processes ends. [Element Order Information Acquisition Process] FIG. 20 is a flowchart showing the element order information acquisition process.

[0221] The element order information acquisition process is a process executed in response to a request from a target user. When executed by the CPU 30, as shown in FIG. 20, first, it proceeds to step S500.

[0222] In step S500, the user ID of the target user is acquired, and the process proceeds to step S502, where the created or edited element ID is acquired from the CAD data being currently edited, and then the process proceeds to step S504.

[0223] In step S504, a request for generating response information based on the element ID and user ID acquired in steps S500 and S502 is generated and sent to the generation AI server 120. The request includes: (1) the element ID acquired in step S502, (2) the user ID acquired in step S500, (3) element order information regarding a plurality of editing elements to be continuously edited next to the created or edited editing element and their editing order (element order information conforming to the target user), where a generation request for generating a plurality of element order information with different editing elements or editing orders, (4) a selection request for selecting a predetermined AI model 50, and (5) a reference request for referring to the learning data of the knowledge base 54.

[0224] Next, the process proceeds to step S506, where response information is received from the generation AI server 120, and then the process proceeds to step S508. Similar to the process of step S306, any one of the plurality of element orders is displayed on the display device 44 based on the plurality of element order information included in the received response information, and then the process proceeds to step S510.

[0225] In step S510, when the target user creates or edits an editing element based on the displayed element order, the created or edited element ID including the element ID of the editing element is acquired from the CAD data being currently edited, and the process proceeds to step S512.

[0226] In step S512, it is determined whether the editing element created or edited by the target user is different from the editing element or editing order displayed in steps S508 and S520 based on the element order displayed in steps S508 and S520 and the element ID acquired in step S510. If it is determined that the editing result is different from the inference result (YES), the process proceeds to step S514.

[0227] In step S514, similar to the process of step S312, the display rules used for display in steps S508 and S520 are changed, and the process proceeds to step S516.

[0228] In step S516, similar to the process of step S504, a request for generating response information based on the element ID and user ID obtained in steps S500 and S510 is generated and sent to the generation AI server 120, and the process proceeds to step S518.

[0229] In step S518, similar to the process of step S506, response information is received from the generation AI server 120, and the process proceeds to step S520. Similar to the process of step S306, any one of the multiple element orders is displayed on the display device 44 based on the multiple element order information included in the received response information, and the process proceeds to step S522.

[0230] In step S522, it is determined whether the editing by the target user has been completed. If it is determined that the editing has been completed (YES), the series of processes is terminated.

[0231] On the other hand, if it is determined in step S522 that the editing by the target user has not been completed (NO), the process proceeds to step S510.

[0232] On the other hand, if it is determined in step S512 that the editing result does not match the inference result (NO), the process proceeds to step S516.

[0233] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0234] When the designer wants to install a piano with a width of 120 [mm] in the layout diagram of Figure 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying the piano in, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it is also necessary to edit other editing elements of the toilet. Therefore, after the designer changes the width of the toilet and requests an inference of the order of elements to be edited for the toilet, through steps S500 to S508, the created or edited element IDs and user IDs are obtained, and the element order is inferred and displayed from the obtained element IDs and user IDs. In the inference, the learning data of the knowledge base 54 is referred to by the selected AI model. The method of displaying the element order is the same as that in the first embodiment above.

[0235] Then, when the designer creates or edits the editing element "toilet bowl" based on the inferred and displayed element order, through steps S510 to S520, the next element order is inferred and displayed. If the designer's editing result is different from the inference result, the display rule is changed through step S514.

[0236] 〔Effects of this embodiment〕 Next, the effects of this embodiment will be described. In this embodiment, a request including the created or edited element IDs and the user ID of the target user and including a generation request for generating element order information suitable for the target user is input to the AI model 50, and the element order information output from the AI model 50 is obtained for the request.

[0237] Thereby, it is possible to grasp a plurality of editing elements that are continuously edited and their editing order. The inferred element order information is suitable for the target user because it is suitable for the target user.

[0238] Furthermore, in the present embodiment, a request including a generation request for generating a plurality of element order information with different editing elements or editing orders is input to the AI model 50, a plurality of element order information output from the AI model 50 is acquired for the request, and any one of the plurality of element orders is displayed based on the acquired plurality of element order information.

[0239] Thereby, it is possible to grasp a plurality of candidates for a plurality of editing elements that are continuously edited and their editing order.

[0240] Furthermore, in the present embodiment, learning data including the created or edited element ID, element order information regarding a plurality of editing elements that are continuously edited next to the editing element and their editing order, the user ID of the editing user, and an evaluation value regarding the editing of the plurality of editing elements is registered in the knowledge base 54, and for the request, the plurality of element order information output from the AI model 50 is acquired by referring to the learning data of the knowledge base 54.

[0241] Thereby, it is possible to grasp an element order with a high evaluation value. Furthermore, in the present embodiment, a created or edited element ID including the element ID of the editing element created or edited by the target user based on the displayed element order is acquired, a request including a generation request for generating element order information suitable for the target user including the acquired element ID and user ID is input to the AI model 50, and the element order information output from the AI model 50 is acquired for the request.

[0242] Thereby, since the element order is inferred and displayed for the result of creation or editing based on the displayed element order, it is possible to grasp a plurality of editing elements that are continuously edited and their editing order. The inferred element order information is suitable for the target user because it is suitable for the target user.

[0243] Furthermore, in the present embodiment, based on the displayed element order, the created or edited element IDs including the element IDs of the edited elements created or edited by the target user are obtained, and a request including the obtained element IDs and user IDs and including a generation request for generating a plurality of element order information with different edited elements or editing orders is input to the AI model 50. For the request, a plurality of element order information output from the AI model 50 is obtained, and any one of the plurality of element orders is displayed based on the obtained plurality of element order information.

[0244] As a result, based on the displayed element order, a plurality of element orders are inferred and displayed for the result of creation or editing, so that a plurality of candidates for a plurality of edited elements edited continuously and their editing orders can be grasped.

[0245] In the present embodiment, step S402 corresponds to the registration means of Invention 2 or 3, step S500 corresponds to the user information acquisition means of Invention 1, steps S502 and S510 correspond to the element information acquisition means of Invention 1, and steps S504 and S516 correspond to the input means of Invention 1. Also, steps S506 and S518 correspond to the acquisition means of Invention 1 or 2, the CAD data corresponds to the design information of Invention 16, the created or edited element IDs correspond to the element information of Inventions 1 to 3, and the user ID corresponds to the user information of Inventions 1 to 3.

[0246] 〔Sixth Embodiment〕 Next, a sixth embodiment of the present invention will be described. FIG. 21 is a diagram showing the present embodiment. In addition, FIGS. 5, 9, 11, and 19 are incorporated.

[0247] This embodiment is different from the above-described second and fifth embodiments in that the AI model 50 is made to refer to first learning data including an evaluation value based on a first index or second learning data including an evaluation value based on a second index. Hereinafter, only the parts different from the above-described second and fifth embodiments will be described, and the description of the overlapping parts will be omitted.

[0248] 〔Operation of the Present Embodiment〕 Next, the operation of this embodiment will be described. 〔Learning data registration process〕 In the learning data registration process, through steps S400 to S402, the learning data in FIG. 5 and the learning data in FIG. 11 are acquired from the storage device 42, and a request for registering the learning data is generated and sent to the generation AI server 120. The request includes (1) the learning data in FIG. 5 as the first learning data and (2) the learning data in FIG. 11 as the second learning data.

[0249] 〔Element order information acquisition process〕 FIG. 21 is a flowchart showing the element order information acquisition process.

[0250] The element order information acquisition process is a process executed in response to a request from a target user. When executed by the CPU 30, as shown in FIG. 21, first, the process proceeds to step S530.

[0251] In step S530, index information regarding the first index "editing time" or the second index "number of editing items", which indicates an index of the value of the evaluation value, is acquired. Then, the process proceeds to step S532 to acquire the user ID of the target user, and then proceeds to step S534 to acquire the element IDs that have been created or edited from the CAD data currently being edited, and then proceeds to step S536.

[0252] In step S536, a request for generating response information is generated based on the index information, element ID, and user ID obtained in steps S530, S532, and S534, and is sent to the generation AI server 120. The request includes: (1) the element ID obtained in step S534, (2) the user ID obtained in step S532, (3) element order information (element order information conforming to the target user) regarding a plurality of editing elements that are successively edited after the created or edited editing element and their editing order, a generation request for generating a plurality of element order information with different editing elements or editing orders, (4) a selection request for selecting a predetermined AI model 50, and (5) a reference request for referring to the first learning data of the knowledge base 54 when the index related to the index information obtained in step S530 is the first index, or a reference request for referring to the second learning data of the knowledge base 54 when the index related to the index information obtained in step S530 is the second index.

[0253] Next, it proceeds to step S538, receives response information from the generation AI server 120, proceeds to step S540, and based on the plurality of element order information included in the received response information, in the same manner as the process of step S306, displays any of the plurality of element orders on the display device 44, and proceeds to step S542.

[0254] In step S542, when the target user creates or edits an editing element based on the displayed element order, the created or edited element ID including the element ID of the editing element is obtained from the CAD data being currently edited, and it proceeds to step S544.

[0255] In step S544, based on the element order displayed in steps S540 and S552 and the element ID obtained in step S542, it is determined whether the editing element created or edited by the target user is different from the editing element or editing order displayed in steps S540 and S552. If it is determined that the editing result is different from the inference result (YES), it proceeds to step S546.

[0256] In step S546, similar to the process of step S312, the display rules used for display in steps S540 and S552 are changed, and the process proceeds to step S548.

[0257] In step S548, similar to the process of step S536, a request for generating response information based on the index information, element ID, and user ID obtained in steps S530, S532, and S542 is generated and sent to the generation AI server 120, and the process proceeds to step S550.

[0258] In step S550, similar to the process of step S538, response information is received from the generation AI server 120, and the process proceeds to step S552. Similar to the process of step S306, one of the plurality of element orders is displayed on the display device 44 based on the plurality of element order information included in the received response information, and the process proceeds to step S554.

[0259] In step S554, it is determined whether the editing by the target user has been completed. If it is determined that the editing has been completed (YES), the series of processes is terminated.

[0260] On the other hand, if it is determined in step S554 that the editing by the target user has not been completed (NO), the process proceeds to step S542.

[0261] On the other hand, if it is determined in step S544 that the editing result does not match the inference result (NO), the process proceeds to step S548.

[0262] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0263] When a designer wants to install a piano with a width of 120 [mm] in the layout diagram of Figure 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying the piano in, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it is also necessary to edit other editing elements of the toilet. Therefore, after the designer changes the width of the toilet, an inference of the order of elements to be edited for the toilet is requested. At this time, if the designer wants to obtain the element order that shortens the editing time, when the designer selects "editing time" as an index, through steps S530~S540, the created or edited element IDs and user IDs are obtained, and the element order is inferred and displayed from the obtained element IDs and user IDs. In the inference, the first learning data of the knowledge base 54 is referred to by the selected AI model.

[0264] On the contrary, if the designer wants to obtain the element order that reduces the number of editing items, when the designer selects "number of editing items" as an index, through steps S530~S540, the created or edited element IDs and user IDs are obtained, and the element order is inferred and displayed from the obtained element IDs and user IDs. In the inference, the second learning data of the knowledge base 54 is referred to by the selected AI model.

[0265] [[Effect of the present embodiment]] Next, the effect of the present embodiment will be described. In the present embodiment, the first learning data including the evaluation value based on the first index and the second learning data including the evaluation value based on the second index are registered in the knowledge base 54, the index information regarding the first index or the second index is obtained, and based on the obtained index information, a request including a request to refer to either the first learning data or the second learning data of the knowledge base 54 is input to the AI model 50.

[0266] Thereby, it is possible to grasp the element order with a high evaluation value based on the first index or the second index.

[0267] In the present embodiment, step S402 corresponds to the registration means of Invention 4, step S530 corresponds to the index information acquisition means of Invention 4, and steps S536 and S548 correspond to the input means of Invention 4.

[0268] 〔Seventh Embodiment〕 Next, a seventh embodiment of the present invention will be described. FIG. 22 is a diagram showing this embodiment. In addition, FIGS. 9, 13, and 19 are incorporated by reference.

[0269] This embodiment is different from the above-described fifth embodiment in that the AI model 50 is caused to generate element order information suitable for the target user from a plurality of pieces of element order information acquired from the AI model 50. Hereinafter, only the parts different from the above-described fifth embodiment will be described, and the overlapping parts will be omitted from the description.

[0270] 〔Operation of this Embodiment〕 Next, the operation of this embodiment will be described. 〔Learning Data Registration Process〕 In the learning data registration process, through steps S400 to S402, the general-purpose learning data in the above-described third embodiment and the learning data in FIG. 13 are acquired from the storage device 42, and a request for registering the learning data is transmitted to the AI server 120 that generates the request. The request includes (1) the general-purpose learning data as the first learning data and (2) the learning data in FIG. 13 as the second learning data.

[0271] 〔Element Order Information Acquisition Process〕 FIG. 22 is a flowchart showing the element order information acquisition process.

[0272] The element order information acquisition process is a process executed in response to a request from the target user. When executed in the CPU 30, as shown in FIG. 22, first, the process proceeds to step S560.

[0273] In step S560, the user ID of the target user is acquired, and the process proceeds to step S562, where the created or edited element IDs are acquired from the CAD data being currently edited, and then the process proceeds to step S564.

[0274] In step S564, a request for generating response information based on the element IDs acquired in step S562 is generated and sent to the generation AI server 120. The request includes: (1) the element IDs acquired in step S562; (2) element order information regarding a plurality of editing elements to be edited successively after the created or edited editing element and their editing order, and a generation request for generating a plurality of element order information with different editing elements or editing orders; (3) a selection request for selecting a predetermined AI model 50; and (4) a reference request for referring to the first learning data of the knowledge base 54.

[0275] Next, the process proceeds to step S566, where response information is received from the generation AI server 120, and then the process proceeds to step S568.

[0276] In step S568, a request for generating response information based on the plurality of element order information included in the response information received in step S566 and the user ID acquired in step S560 is generated and sent to the generation AI server 120. The request includes: (1) the plurality of element order information included in the response information received in step S566; (2) the user ID acquired in step S560; (3) a generation request for selecting or generating element order information suitable for the target user; (4) a selection request for selecting a predetermined AI model 50; and (5) a reference request for referring to the second learning data of the knowledge base 54.

[0277] Next, the process proceeds to step S570, where response information is received from the generation AI server 120, then the process proceeds to step S572, where the element order is displayed on the display device 44 based on the element order information included in the received response information, and then the process proceeds to step S574.

[0278] In step S574, it is determined whether the editing by the target user has been completed. If it is determined that the editing has been completed (YES), a series of processes are terminated.

[0279] On the other hand, if it is determined in step S574 that the editing by the target user has not been completed (NO), the process proceeds to step S562.

[0280] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0281] When the designer wants to install a piano with a width of 120 [mm] in the floor plan of FIG. 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying in the piano, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it becomes necessary to edit other editing elements of the toilet as well. Therefore, after the designer changes the width of the toilet and requests an inference of the order of elements to be edited for the toilet, through steps S560 to S566, the created or edited element IDs and user IDs are obtained, and a plurality of element order information is inferred from the obtained element IDs. In the inference, the first learning data of the knowledge base 54 is referred to by the selection AI model. Then, through steps S568 to S572, the element order is inferred and displayed from the inferred plurality of element order information and the obtained user ID. That is, in steps S564 and S566, a plurality of candidates for the element order are inferred, and in steps S568 and S570, those candidates that match the target user are narrowed down.

[0282] Then, when the designer creates or edits the editing element "toilet bowl" based on the inferred and displayed element order, through steps S562 to S572, the next element order is inferred and displayed.

[0283] 〔Effects of the present embodiment〕 Next, the effects of the present embodiment will be described. In the present embodiment, a request including a plurality of element order information and the user ID of a target user and including a generation request for selecting or generating element order information suitable for the target user is input to the AI model 50, and the element order information output from the AI model 50 is acquired for the request.

[0284] Thereby, it is possible to grasp a plurality of editing elements that are continuously edited and the editing order thereof. Since the inferred element order information is suitable for the target user, it is suitable for the target user.

[0285] In the present embodiment, step S402 corresponds to the registration means of Invention 9 or 10, step S560 corresponds to the user information acquisition means of Invention 8, step S562 corresponds to the element order information acquisition means of Invention 8, and step S568 corresponds to the input means of Invention 8. Further, step S570 corresponds to the acquisition means of Invention 8 or 9, and the user ID corresponds to the user information of Inventions 8 to 10.

[0286] 〔Eighth Embodiment〕 Next, an eighth embodiment of the present invention will be described. FIG. 23 is a diagram showing the present embodiment. In addition, FIGS. 9, 13, 15, and 19 are incorporated.

[0287] This embodiment is different from the above-described seventh embodiment in that the AI model 50 is made to refer to second learning data including an evaluation value based on a first index or third learning data including an evaluation value based on a second index. Hereinafter, only the parts different from the above-described seventh embodiment will be described, and the description of the overlapping parts will be omitted.

[0288] 〔Operation of the Present Embodiment〕 Next, the operation of the present embodiment will be described. 〔Learning Data Registration Process〕 In the learning data registration process, through steps S400 to S402, the general-purpose learning data, the learning data in FIG. 13, and the learning data in FIG. 15 in the above-described third embodiment are acquired from the storage device 42, and a request for registering the learning data is generated and sent to the generation AI server 120. The request includes (1) the general-purpose learning data as the first learning data, (2) the learning data in FIG. 13 as the second learning data, and (3) the learning data in FIG. 15 as the third learning data.

[0289] 〔Element order information acquisition process〕 FIG. 23 is a flowchart showing the element order information acquisition process.

[0290] The element order information acquisition process is a process executed in response to a request from a target user. When executed in the CPU 30, as shown in FIG. 23, first, it proceeds to step S580.

[0291] In step S580, index information regarding the first index "editing time" or the second index "number of editing items", which indicates an index of the value of the evaluation value, is acquired, and it proceeds to step S582 to acquire the user ID of the target user, and then proceeds to step S584 to acquire the element ID of the created or edited elements from the CAD data being currently edited, and then proceeds to step S586.

[0292] In step S586, a request for generating response information is generated based on the element ID acquired in step S584 and sent to the generation AI server 120. The request includes (1) the element ID acquired in step S584, (2) element order information regarding a plurality of editing elements that are continuously edited next to the created or edited editing elements and their editing order, and a generation request for generating a plurality of element order information with different editing elements or editing orders, (3) a selection request for selecting a predetermined AI model 50, and (4) a reference request for referring to the first learning data of the knowledge base 54.

[0293] Next, it proceeds to step S588 to receive response information from the generation AI server 120, and then proceeds to step S590.

[0294] In step S590, a request for generating response information is sent to the generation AI server 120 based on the plurality of element order information included in the response information received in step S588 and the user ID obtained in step S582. The request includes: (1) the plurality of element order information included in the response information received in step S588, (2) the user ID obtained in step S582, (3) a generation request for selecting or generating element order information that matches the target user, (4) a selection request for selecting a predetermined AI model 50, and (5) a reference request for referring to the second learning data of the knowledge base 54 when the index related to the index information obtained in step S580 is the first index, or a reference request for referring to the third learning data of the knowledge base 54 when the index related to the index information obtained in step S580 is the second index.

[0295] Next, it proceeds to step S592 to receive response information from the generation AI server 120, then proceeds to step S594 to display the element order on the display device 44 based on the element order information included in the received response information, and then proceeds to step S596.

[0296] In step S596, it is determined whether the editing by the target user has ended. If it is determined that the editing has ended (YES), the series of processes is terminated.

[0297] On the other hand, if it is determined in step S596 that the editing by the target user has not ended (NO), it proceeds to step S584.

[0298] 〔When assuming the piano to be carried in〕 Next, the operation when assuming the piano to be carried in will be described.

[0299] When a designer wants to install a piano with a width of 120 [mm] in the floor plan of Figure 9 in CAD software, in order to prevent interference between the piano and the toilet wall when carrying the piano in, it is necessary to shorten the width of the toilet. However, when changing the width of the toilet, it is also necessary to edit other editing elements of the toilet. Therefore, after changing the width of the toilet, the designer requests an inference of the order of elements to be edited for the toilet. At this time, if the designer wants to obtain an element order that shortens the editing time, when selecting "editing time" as an index, through steps S580 to S588, the created or edited element IDs and user IDs are obtained, and a plurality of element order information is inferred from the obtained element IDs. In the inference, the first learning data of the knowledge base 54 is referred to by the selected AI model. Then, through steps S590 to S592, the element order is inferred and displayed from the inferred plurality of element order information and the obtained user ID. In the inference, the second learning data of the knowledge base 54 is referred to by the selected AI model.

[0300] On the contrary, if the designer wants to obtain an element order that reduces the number of editing items, when selecting "the number of editing items" as an index, through steps S580 to S592, the element order is inferred and displayed from the inferred plurality of element order information and the obtained user ID. In the inference, the third learning data of the knowledge base 54 is referred to by the selected AI model.

[0301] 〔Effects of the Present Embodiment〕 Next, the effects of the present embodiment will be described. In the present embodiment, the second learning data including the evaluation value based on the first index and the third learning data including the evaluation value based on the second index are registered in the knowledge base 54, the index information regarding the first index or the second index is obtained, and based on the obtained index information, a request including a request to refer to either the second learning data or the third learning data of the knowledge base 54 is input to the AI model 50.

[0302] Thereby, it is possible to grasp the element order with a high evaluation value based on the first index or the second index.

[0303] In this embodiment, step S402 corresponds to the registration means of Invention 11, step S580 corresponds to the index information acquisition means of Invention 11, and step S590 corresponds to the input means of Invention 11.

[0304] [Modification Example] In addition, in the above-described first and second embodiments and their modification examples, although a plurality of element order information is estimated in steps S304 and S338, the present invention is not limited to this, and one element order information can be estimated.

[0305] Further, in the above-described fifth and sixth embodiments and their modification examples, although a generation request for generating a plurality of element order information is included in the request in steps S504 and S536, the present invention is not limited to this, and a generation request for generating one element order information can be included in the request.

[0306] In addition, in the above-described third and fourth embodiments and their modification examples, although the first learned model is generated based on general-purpose learning data, the present invention is not limited to this, and the first learned model can be generated based on general-purpose learning data obtained by deleting user ID434 from the learning data of FIG. 11, the learning data of FIG. 5, or the learning data of FIG. 11.

[0307] Further, in the above-described seventh and eighth embodiments and their modification examples, although the general-purpose learning data is referred to by the AI model 50 for the request in step S586, the present invention is not limited to this, and (1) a configuration in which general-purpose learning data obtained by deleting user ID434 from the learning data of FIG. 11, the learning data of FIG. 5, or the learning data of FIG. 11 is referred to, or (2) a configuration in which the learning data is not referred to can be adopted.

[0308] In addition, in the above-described third and fourth embodiments and their modification examples, although a plurality of element order information is obtained from the first learned model, the present invention is not limited to this, and a plurality of element order information can be obtained from the storage device 42 or any other device, any node, or any process.

[0309] Also, in the above-described seventh and eighth embodiments and their modifications, a plurality of element order information is obtained from the generation AI server 120. However, the present invention is not limited to this, and a plurality of element order information can be obtained from the storage device 42 or any other device, any node, or any process.

[0310] Also, in the above-described fourth embodiment and its modification, in step S388, a plurality of element order information is estimated from the element ID using the first learned model of the storage device 42. However, the present invention is not limited to this, and the following configuration can be adopted.

[0311] Prepare first general-purpose learning data obtained by deleting the user ID 414 from the learning data in FIG. 5, and second general-purpose learning data obtained by deleting the user ID 434 from the learning data in FIG. 11.

[0312] In steps S200 to S204, a first learned model is generated by performing learning based on the first general-purpose learning data. Also, a fourth learned model is generated by performing learning based on the second general-purpose learning data.

[0313] Then, in step S388, when the index related to the index information obtained in step S380 is the first index, the first learned model is selected. When the index related to the index information obtained in step S380 is the second index, the fourth learned model is selected, and a plurality of element order information is estimated from the element ID using the selected learned model.

[0314] Also, in the above-described eighth embodiment and its modification, in response to the request in step S586, the first learning data of the knowledge base 54 is referred to by the AI model 50. However, the present invention is not limited to this, and the following configuration can be adopted.

[0315] Prepare first general-purpose learning data obtained by deleting the user ID 414 from the learning data in FIG. 5, and second general-purpose learning data obtained by deleting the user ID 434 from the learning data in FIG. 11.

[0316] In steps S400 to S402, the first general learning data, the second general learning data, the learning data in FIG. 13, and the learning data in FIG. 15 are acquired from the storage device 42, and a request for registering the learning data is generated and sent to the generation AI server 120. The request includes (1) the first general learning data as the first learning data, (2) the learning data in FIG. 13 as the second learning data, (3) the learning data in FIG. 15 as the third learning data, and (4) the second general learning data as the fourth learning data.

[0317] Then, in step S586, a request for generating response information based on the element ID is generated and sent to the generation AI server 120. The request includes (1) the element ID, (2) a generation request for generating a plurality of element order information, (3) a selection request for the AI model 50, and (4) a reference request for referring to the first learning data of the knowledge base 54 when the index related to the index information acquired in step S580 is the first index, or a reference request for referring to the fourth learning data of the knowledge base 54 when the index related to the index information acquired in step S580 is the second index.

[0318] Also, in the first, second, fifth, and sixth embodiments and their modifications, the first to fourth display rules are adopted, but the present invention is not limited to this. For example, display rules such as displaying the elements with the fewest number of editing elements, displaying elements in a predetermined order or more, in a predetermined order or less, or in a predetermined order, or any other arbitrary display rules can be adopted.

[0319] Also, in the first, second, fifth, and sixth embodiments and their modifications, the element order is displayed according to any one of a plurality of display rules, but the present invention is not limited to this. Without providing a plurality of display rules, the element order can be displayed according to a predetermined display rule.

[0320] Also, in the first to eighth embodiments and their modifications, one element order is displayed, but the present invention is not limited to this. A plurality of element orders can be displayed.

[0321] In addition, in the first, second, fifth, and sixth embodiments and their modifications described above, the display rules are changed. However, the present invention is not limited to this, and a configuration that does not change the display rules can also be adopted.

[0322] In addition, in the first to fourth embodiments and their modifications described above, the estimation and display are repeated multiple times. However, the present invention is not limited to this, and a configuration that performs the estimation and display only once can also be adopted. The same applies to the fifth to eighth embodiments and their modifications.

[0323] In addition, in the first to fourth embodiments and their modifications described above, reinforcement learning is adopted as the learning method. However, the present invention is not limited to this, and supervised learning, semi-supervised learning, unsupervised learning, deep learning, or any other learning method can be adopted.

[0324] In addition, in the first to eighth embodiments and their modifications described above, the learning data is configured to include the user ID and the evaluation value. However, the present invention is not limited to this, and it can be configured without including one or both of the user ID or the evaluation value.

[0325] In addition, in the first to eighth embodiments and their modifications described above, the edit history data and the learning data are configured to include the user ID. However, the present invention is not limited to this, and it can be configured to include identification information other than the user ID, or feature information regarding the user's profile, statistical quantities, or other features. The same applies to the element ID.

[0326] In addition, in the second embodiment and its modification described above, the first learned model and the second learned model can be configured as one learned model.

[0327] In addition, in the fourth embodiment and its modification described above, the second learned model and the third learned model can be configured as one learned model, and the first learned model and the fourth learned model can be configured as one learned model.

[0328] Also, in the fifth to eighth embodiments and their modified examples described above, the AI model 50 can be configured as the learned model in the first to fourth embodiments and their modified examples.

[0329] Also, in the first, second, fifth, and sixth embodiments and their modified examples described above, the order of elements with a predetermined or more number of occurrences in the learning data was specified. However, the present invention is not limited to this, and the order of elements with a predetermined or more number of occurrences in the edit history data can be specified.

[0330] Also, in the first to eighth embodiments and their modified examples described above, a maximum of four edit elements and their edit order were handled. However, the present invention is not limited to this, and five or more edit elements and their edit order can be handled. The number of edit elements only needs to be plural, and there is no need to limit the number. Also, the number of edit elements can be independently set for the learning data in FIGS. 5, 11, 13, and 15.

[0331] Also, in the first to eighth embodiments and their modified examples described above, all combinations of 2 to 4 edit elements were obtained from the edit history data for the element order, and learning data was generated. However, the present invention is not limited to this, and the order of elements with a predetermined or more number of occurrences in the edit history data can be obtained from the edit history data, and learning data can be generated. In this case, a learned model obtained by learning a plurality of edit history data may be used to estimate the element order with a high appearance frequency. Thereby, the element order with a high appearance frequency in the edit history data can be learned or inferred.

[0332] Also, in the first to eighth embodiments and their modified examples described above, the edit history data was configured as data separate from the CAD data. However, the present invention is not limited to this, and it can be configured integrally included in the CAD data.

[0333] In addition, in the fifth to eighth embodiments and their modifications described above, although the learning data of the knowledge base 54 is referred to by the AI model 50, the present invention is not limited to this, and the learning data to be referred to by the knowledge base 54 can be included in the request. As a result, it can be applied even to a configuration that does not include the knowledge base 54. Specifically, for example, the following configuration can be adopted.

[0334] 〔Invention A1〕Element information acquisition means for acquiring element information regarding created or edited elements in design information, User information acquisition means for acquiring user information regarding a target user, Input means for inputting a request including the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, and including element order information regarding a plurality of elements continuously edited next to the element related to the element information and their editing order (hereinafter, in Inventions A1 to A3, "a plurality of elements and their editing order" is referred to as "element order") to the AI model, the request including a request for generating the element order information suitable for the target user, Acquisition means for acquiring the element order information output from the AI model in response to the request, The request includes reference information including element information regarding created or edited elements, element order information regarding the element order continuously edited next to the element, and user information regarding the user who edited the plurality of elements.

[0335] As a result, it is possible to grasp a plurality of continuously edited elements and their editing order. Since the estimated element order information is suitable for the target user, it is suitable for the target user.

[0336] 〔Invention A2〕In Invention A1, The request includes reference information including the element information, the element order information regarding the element order, the user information, and an evaluation value regarding the editing of the plurality of elements.

[0337] Accordingly, it is possible to grasp the order of elements with high evaluation values. As a modification of the fifth embodiment, embodiments of inventions A1 and A2 will be described. In step S504, a request for generating response information is sent to the generation AI server 120. The request includes (1) the element ID obtained in step S502, (2) the user ID obtained in step S500, (3) generation requirements for generating a plurality of editing elements to be edited continuously next to the created or edited editing element and element order information regarding the editing order thereof (element order information conforming to the target user), where a plurality of element order information with different editing elements or editing orders is generated, (4) a selection requirement for selecting a predetermined AI model 50, and (5) the learning data obtained in step S400.

[0338] 〔Invention A3〕 In Invention A2, it includes index information acquisition means for acquiring first index information indicating an index of the value of the evaluation value or second index information different from the first index, based on the index information acquired by the index information acquisition means, the input means inputs the request including any one of the first reference information including the element information, the element order information, the user information, and the evaluation value based on the first index, and the second reference information including the element information, the element order information, the user information, and the evaluation value based on the second index into the AI model.

[0339] Accordingly, it is possible to grasp the order of elements with high evaluation values based on the first index or the second index.

[0340] As a modification of the sixth embodiment described above, an embodiment of Invention A3 will be described. In step S536, a request for generating response information is sent to the generation AI server 120. The request includes: (1) the element ID obtained in step S534, (2) the user ID obtained in step S532, (3) generation requirements for a plurality of editing elements to be successively edited after the created or edited editing element and element order information regarding the editing order thereof (element order information conforming to the target user), for generating a plurality of element order information with different editing elements or editing orders, (4) a selection request for selecting a predetermined AI model 50, and (5) the second learning data obtained in step S400 when the index related to the index information obtained in step S530 is the first index, or the third learning data obtained in step S400 when the index related to the index information obtained in step S530 is the second index.

[0341] In this case, step S530 corresponds to the index information acquisition means of Invention 7, and step S536 corresponds to the input means of Invention 7.

[0342] 〔Invention A4〕 Element order information regarding a plurality of successively edited elements and their editing order (hereinafter, in Inventions A4 to A6, the "plurality of elements and their editing order" is referred to as "element order"), including element order information acquisition means for acquiring a plurality of the element order information with different elements or editing orders, user information acquisition means for acquiring user information regarding the target user, input means for inputting a request including the plurality of element order information obtained by the element order information acquisition means and the user information obtained by the user information acquisition means, and including a request for generating the element order information conforming to the target user among the plurality of element order information, into an AI model, acquisition means for acquiring the element order information output from the AI model in response to the request. The request includes reference information including element order information regarding the element order and user information regarding the user who edited the plurality of elements.

[0343] As a result, it is possible to grasp a plurality of continuously edited elements and their editing order. Since the estimated element order information is adapted to the target user, it is suitable for the target user.

[0344] 〔Invention A5〕 In Invention A4, The request includes reference information including element order information regarding the element order, the user information, and an evaluation value regarding the editing of the plurality of elements.

[0345] As a result, it is possible to grasp an element order with a high evaluation value. As a modification of the seventh embodiment, embodiments of Inventions A4 and A5 will be described. In step S568, a request for generating response information is transmitted to the generation AI server 120. The request includes (1) a plurality of element order information included in the response information received in step S566, (2) the user ID acquired in step S560, (3) a generation request for selecting or generating element order information adapted to the target user, (4) a selection request for selecting a predetermined AI model 50, and (5) the second learning data acquired in step S400.

[0346] 〔Invention A6〕 In Invention A5, It includes index information acquisition means for acquiring index information regarding a first index indicating a value index of the evaluation value or a second index different from the first index, Based on the index information acquired by the index information acquisition means, the input means inputs the request including any one of the first reference information including the element order information, the user information, and the evaluation value based on the first index, and the second reference information including the element order information, the user information, and the evaluation value based on the second index into the AI model.

[0347] As a result, it is possible to grasp an element order with a high evaluation value based on the first index or the second index.

[0348] As a modification of the eighth embodiment described above, the embodiment of Invention A3 will be described. In step S590, a request for generating response information is sent to the generation AI server 120. The request includes (1) a plurality of element order information included in the response information received in step S588, (2) the user ID acquired in step S582, (3) a generation request for selecting or generating element order information suitable for the target user, (4) a selection request for selecting a predetermined AI model 50, and (5) the second learning data acquired in step S400 when the index related to the index information acquired in step S580 is the first index, or the third learning data acquired in step S400 when the index related to the index information acquired in step S580 is the second index.

[0349] In this case, step S580 corresponds to the index information acquisition means of Invention 14, and step S590 corresponds to the input means of Invention 14.

[0350] 〔Invention A7〕 In Invention A1, A2, A4 or A5, the plurality of elements are elements that require human judgment for their setting or change, and are elements that affect the setting or change of other elements.

[0351] 〔Invention A8〕 In Inventions A1 to A3, the design information is design information for performing the design of a building.

[0352] Also, in the fifth to eighth embodiments and their modifications described above, the information in the knowledge base 54 is referred to by the AI model 50. However, the present invention is not limited to this, and information to be referred to by the knowledge base 54 (for example, the learning data in FIG. 5 or FIG. 11) can be acquired by Web search or the like, and the search result can be referred to by the AI model 50 for inference. This configuration can be realized by, for example, RAG (Retrieval Augmented Generation).

[0353] Also, in the above-described first to eighth embodiments and their modifications, although the learned model or the AI model 50 is used, the present invention is not limited thereto, and for example, the following configuration can be adopted.

[0354] 〔Invention B1〕Element information acquisition means for acquiring element information regarding created or edited elements in design information, User information acquisition means for acquiring user information regarding a target user, Element order information regarding a plurality of elements to be continuously edited after the created or edited element and their editing order (hereinafter, in Inventions B1 to B4, the "plurality of elements and their editing order" is referred to as "element order") is retrieved from storage means that stores the element order information in association with the element information regarding the created or edited element and the user information regarding the user who edited the plurality of elements, and search means for searching for the element order information corresponding to the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means.

[0355] Thereby, it is possible to grasp a plurality of elements to be continuously edited and their editing order. The estimated element order information is suitable for the target user because it is suitable for the target user.

[0356] 〔Invention B2〕In Invention B1, the storage means stores the element order information regarding the element order in association with the element information, the user information, and an evaluation value regarding the editing of the plurality of elements, the search means searches for the element order information corresponding to the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, and having an evaluation value equal to or more than a predetermined value.

[0357] Thereby, it is possible to grasp an element order with a high evaluation value. As a modification of the first embodiment described above, embodiments of inventions B1 and B2 will be described. The storage device 42 stores an element order information table having the same data structure as the learning data in FIG. 5. In step S304, a plurality of pieces of element order information corresponding to the element ID and the user ID acquired in steps S300 and S302 and having an evaluation value equal to or higher than a predetermined value are retrieved from the element order information table. In step S314, a plurality of pieces of element order information corresponding to the element ID and the user ID acquired in steps S300 and S308 and having an evaluation value equal to or higher than a predetermined value are retrieved from the element order information table.

[0358] 〔Invention B3〕 In invention B2, the storage means includes first storage means for storing the element order information in association with the evaluation value based on a first index indicating an index of the value of the element information, the user information, and the evaluation value, and second storage means for storing the element order information in association with the evaluation value based on a second index different from the first index of the element information, the user information, and the first index, index information acquisition means for acquiring index information regarding the first index or the second index, and storage means selection means for selecting either the first storage means or the second storage means based on the index information acquired by the index information acquisition means, the retrieval means retrieves the element order information from the storage means selected by the storage means selection means.

[0359] Thereby, it is possible to grasp the element order having a high evaluation value based on the first index or the second index.

[0360] A modification of the second embodiment described above will be described as an embodiment of Invention B3. The storage device 42 stores a first element order information table having the same data structure as the learning data in FIG. 5 and a second element order information table having the same data structure as the learning data in FIG. 11. In step S332, if the index related to the index information acquired in step S330 is the first index, the first element order information table is selected, and if the index related to the acquired index information is the second index, the second element order information table is selected. In step S338, a plurality of element order information corresponding to the element ID and user ID acquired in steps S334 and S336 and having an evaluation value equal to or higher than a predetermined value is retrieved from the element order information table selected in step S332. In step S348, a plurality of element order information corresponding to the element ID and user ID acquired in steps S334 and S342 and having an evaluation value equal to or higher than a predetermined value is retrieved from the element order information table selected in step S332.

[0361] 〔Invention B4〕 In Invention B2, the storage means stores the element order information in association with the element information, the user information, the evaluation value, and index information indicating an index of the value of the evaluation value, the index information being a first index or a second index different from the first index, includes index information acquisition means for acquiring index information regarding the first index or the second index, the search means searches for the element order information corresponding to the element information acquired by the element information acquisition means, the user information acquired by the user information acquisition means, and the index information acquired by the index information acquisition means.

[0362] Thereby, it is possible to grasp the element order having a high evaluation value based on the first index or the second index.

[0363] As a modification of the second embodiment described above, the embodiment of Invention B4 will be described. The storage device 42 stores, for each row, an element order information table in which element IDs 430, element order information 432, user IDs 434, evaluation values 436, and index information regarding the first index or the second index that have been created or edited are registered. In step S338, a plurality of element order information corresponding to the element ID, user ID, and index information obtained in steps S330, S334, and S336 and having an evaluation value equal to or greater than a predetermined value are retrieved from the element order information table. In step S348, a plurality of element order information corresponding to the element ID, user ID, and index information obtained in steps S330, S334, and S342 and having an evaluation value equal to or greater than a predetermined value are retrieved from the element order information table.

[0364] 〔Invention B5〕Element order information regarding a plurality of continuously edited elements and their editing order (hereinafter, in Inventions B5 to B8, the "plurality of elements and their editing order" is referred to as "element order"), and element order information acquisition means for acquiring a plurality of the element order information in which the elements or the editing order are different, user information acquisition means for acquiring user information regarding a target user, search means for searching, from storage means for storing the element order information regarding the element order in association with user information regarding the user who edited the plurality of elements, any one of the plurality of element order information acquired by the element order information acquisition means and the element order information corresponding to the user information acquired by the user information acquisition means.

[0365] Thereby, it is possible to grasp a plurality of continuously edited elements and their editing order. The estimated element order information is suitable for the target user because it conforms to the target user.

[0366] 〔Invention B6〕In Invention B5, the storage means stores the element order information regarding the element order in association with the user information and an evaluation value regarding the editing of the plurality of elements, The search means searches for any one of the plurality of element order information obtained by the element order information acquisition means and the element order information corresponding to the user information obtained by the user information acquisition means, and having an evaluation value equal to or greater than a predetermined value.

[0367] Thereby, it is possible to grasp an element order with a high evaluation value. As a modification of the above-described third embodiment, embodiments of inventions B5 and B6 will be described. The storage device 42 stores an element order information table having a data structure similar to the learning data in FIG. 13. In step S366, any one of the plurality of element order information estimated in step S364 and the element order information corresponding to the user ID obtained in step S360 and having an evaluation value equal to or greater than a predetermined value is searched from the element order information table.

[0368] 〔Invention B7〕 In Invention B6, the storage means includes first storage means for storing the element order information in association with the evaluation value based on a first index indicating an index of the value of the user information and the evaluation value, and second storage means for storing the element order information in association with the evaluation value based on a second index different from the user information and the first index, index information acquisition means for acquiring index information regarding the first index or the second index, and storage means selection means for selecting either the first storage means or the second storage means based on the index information acquired by the index information acquisition means, wherein the search means searches for the element order information from the storage means selected by the storage means selection means.

[0369] Thereby, it is possible to grasp an element order with a high evaluation value based on the first index or the second index.

[0370] A modification of the above-described fourth embodiment, the embodiment of Invention B7, will be described. The storage device 42 stores a first element order information table having the same data structure as the learning data in FIG. 13 and a second element order information table having the same data structure as the learning data in FIG. 15. In step S382, if the index related to the index information acquired in step S380 is the first index, the first element order information table is selected; if the index related to the acquired index information is the second index, the second element order information table is selected. In step S390, among the plurality of element order information estimated in step S388 and the element order information corresponding to the user ID acquired in step S384 and having an evaluation value equal to or higher than a predetermined value, a search is made from the element order information table selected in step S382.

[0371] 〔Invention B8〕 In Invention B6, the storage means stores the element order information in association with the user information, the evaluation value, and index information indicating an index of the value of the evaluation value, the index information being a first index or a second index different from the first index, includes index information acquisition means for acquiring index information regarding the first index or the second index, the search means searches for any of the plurality of element order information acquired by the element order information acquisition means, the user information acquired by the user information acquisition means, and the element order information corresponding to the index information acquired by the index information acquisition means.

[0372] Thereby, it is possible to grasp the element order having a high evaluation value based on the first index or the second index.

[0373] A modification of the fourth embodiment described above will be explained as an embodiment of Invention B8. The storage device 42 stores, for each row, an element order information table in which element order information, user ID, evaluation value, and index information regarding the first index or the second index are registered. In step S390, among the plurality of pieces of element order information estimated in step S388, or a plurality of pieces of element order information corresponding to the user ID and index information acquired in steps S380 and S384 and having an evaluation value equal to or higher than a predetermined value are retrieved from the element order information table.

[0374] 〔Invention B9〕 In Invention B1, B2, B5, or B6, the plurality of elements are elements that require human judgment for their setting or change, and are elements that affect other elements when the setting or change is made.

[0375] 〔Invention B10〕 In Invention B1, the design information is design information for performing architectural design.

[0376] Also, in Inventions B1 to B10 and their modifications, as for storing the element order information in association with the element information and the like, for example, (1) directly associating and storing by registering the element order information and the element information and the like in the same record, (2) providing a table for registering the element order information and the intermediate information in association with each other and a table for registering the element information and the like and the intermediate information in association with each other, and storing through one or a plurality of pieces of information in the middle is included. That is, any data structure can be adopted as long as the element order information can be traced from the element information and the like. Note that the element order information may be stored in the storage means in association with the element information and the like, and it is not always necessary to store the element information and the like in the storage means.

[0377] In addition, in Inventions B1 to B10 and their modified examples, the storage means stores the element order information by any means and at any time. The element order information may be stored in advance, or may be configured to store the element order information by an external input or the like during the operation of the drawing creation support apparatus 100 without storing the element order information in advance.

[0378] In addition, in the fifth to eighth embodiments and their modified examples, as the prompt, for example, based on the created or edited element IDs, the AI model 50 is required to generate element order information regarding a plurality of editing elements that are continuously edited next to the created or edited editing element and their editing order, and having an evaluation value equal to or greater than a predetermined value. However, the present invention is not limited to this, and the content required for the AI model 50 may be to generate element order information regarding a plurality of editing elements that are continuously edited next to the created or edited editing element and their editing order.

[0379] In addition, in the fifth to eighth embodiments and their modified examples, the learning data of FIG. 5 or FIG. 11 is registered in the knowledge base 54. However, the present invention is not limited to this, and (1) editing history data, (2) element information regarding the created or edited element, and reference information including element order information regarding a plurality of elements that are continuously edited next to the element and their editing order, or (3) element information regarding the created or edited element, element order information regarding a plurality of elements that are continuously edited next to the element and their editing order, and reference information including an evaluation value regarding the editing of the plurality of elements can be registered in the knowledge base 54. The reference information in (2) or (3) may include element order information estimated using the learned model in the first to fourth embodiments and their modified examples.

[0380] In addition, in the fifth to eighth embodiments and their modified examples, vector data is registered in the knowledge base 54. However, the present invention is not limited to this, and data in any format can be registered.

[0381] In addition, in the above-described first to eighth embodiments and their modified examples, a configuration including any one of the estimation process using a learned model, the acquisition process from the AI model 50, and the search process using a table is adopted. However, the present invention is not limited thereto, and a configuration including a plurality of these processes can be adopted. Specifically, for example, the following configurations can be adopted.

[0382] The first configuration is a configuration in which the process of step S304 or the process of step S314 is performed by any one of the estimation process, the acquisition process, and the search process. For the second and subsequent processes of step S314, the process can be the same as or different from the process of step S304 or the first process of step S314.

[0383] The second configuration is a configuration in which the process of step S338 or the process of step S348 is performed by any one of the estimation process, the acquisition process, and the search process. For the second and subsequent processes of step S348, the process can be the same as or different from the process of step S338 or the first process of step S348.

[0384] The third configuration is a configuration in which the processes of steps S504 and S506 or the processes of steps S516 and S518 are performed by any one of the estimation process, the acquisition process, and the search process. For the second and subsequent processes of steps S516 and S518, the process can be the same as or different from the processes of steps S504 and S506 or the first processes of steps S516 and S518.

[0385] The fourth configuration is a configuration in which the processes of steps S536 and S538 or the processes of steps S548 and S550 are performed by any one of the estimation process, the acquisition process, and the search process. For the second and subsequent processes of steps S548 and S550, the process can be the same as or different from the processes of steps S536 and S538 or the first processes of steps S548 and S550.

[0386] The fifth configuration is a configuration that controls which process to prioritize. For example, (1) a configuration that prioritizes the process with the lowest current load among multiple processes, (2) a configuration that prioritizes the process with a high adoption rate (referring to the number of times of adoption, ratio, or other degrees of adoption) by the target user among multiple processes, and (3) a configuration that prioritizes the process with a high usage rate (referring to the number of times of use, ratio, or other degrees of use) by the target user among multiple processes can be adopted.

[0387] Also, in the above-described first to eighth embodiments and their modified examples, a plurality of editing elements and their editing order were learned or inferred. However, this is not the only case. The "plurality of editing elements" to be learned or inferred can be editing element A that requires human judgment for its setting or change, and can be an editing element that affects the setting or change of other editing element B. Thereby, the element order considering the relationship between editing element A and editing element B can be grasped. For editing elements that do not require human judgment, for example, since editing can be automated by the technology of Japanese Patent No. 7341580, the editing work can be made more efficient by targeting editing elements that are difficult to automate.

[0388] Also, in the above-described first to fourth embodiments and their modified examples, it was realized as a single device. However, this is not the only case, and it can also be realized as a network system. As an example of a network system, part or all of the functions of the drawing creation support device 100 can be configured as a virtual server on a server that provides cloud computing services.

[0389] Also, in the above-described fifth to eighth embodiments and their modified examples, the generation AI server 120 integrally constitutes each function including the AI model 50, the AI model control unit 52, the knowledge base 54, the request reception unit 56, the request processing unit 58, the response information transmission unit 60, the request reception unit 62, and the learning data registration unit 64. However, this is not the only case, and some functions can be configured by another server or the like.

[0390] Also, in the fifth to eighth embodiments and their modifications described above, although it is realized as a network system, it is not limited to this, and it can be realized as a single device or application.

[0391] Further, in the fifth to eighth embodiments and their modifications described above, the case where it is applied to a network system composed of the Internet 199 has been described. However, it is not limited to this, and for example, it may be applied to a so-called intranet that communicates in the same manner as the Internet 199. Of course, it is not limited to a network that communicates in the same manner as the Internet 199, and it can be applied to a network of any communication method.

[0392] Also, in the first to eighth embodiments and their modifications described above, the drawing creation support device 100 is configured to use the storage device 42. However, it is not limited to this, and it can also be configured to use an external storage device such as a database server.

[0393] Also, in the first to eighth embodiments and their modifications described above, when executing the processes shown in the flowcharts of FIGS. 4, 6, 8, 12, 14, 16, 19 to 23, the case where a program pre-stored in the ROM 32 is executed has been described. However, it is not limited to this, and the program may be read from a storage medium storing the program showing these procedures into the RAM 34 and executed.

[0394] Here, the storage medium is a semiconductor storage medium such as RAM and ROM, a magnetic storage type storage medium such as FD and HD, an optical reading type storage medium such as CD, CDV, LD, and DVD, and a magnetic storage type / optical reading type storage medium such as MO. Regardless of the reading method such as electronic, magnetic, or optical, any storage medium that can be read by a computer is included.

[0395] Also, the first to eighth embodiments and their modifications can be applied to each other. Moreover, the present invention is applicable not only to the above-described first to eighth embodiments and their modifications, but also to other cases without departing from the gist of the present invention. For example, the present invention can be applied to cases where design is widely carried out, such as automobile design, mechanical design, circuit design, and the like.

Explanation of Signs

[0396] 100... Drawing creation support device, 30... CPU, 32... ROM, 34... RAM, 38... I / F, 39... Bus, 40... Input device, 42... Storage device, 44... Display device, 120... Generation AI server, 50... AI model, 52... AI model control unit, 54... Knowledge base, 56, 62... Request reception unit, 58... Request processing unit, 60... Response information transmission unit, 64... Learning data registration unit, 199... Internet, 400, 420... Element information, 402, 414, 422, 434, 442, 452... User ID, 404... Editing time, 424... Number of editing items, 410, 430... Element ID, 412, 432, 440, 450... Element order information, 416, 436, 444, 454... Evaluation value

Claims

1. An element information acquisition means for acquiring element information relating to an element that has been created or edited in the design information; A user information acquisition means for acquiring user information regarding a target user; an input means for inputting a request to an AI model, the request including a request to generate element order information suitable for the target user, the element order information including the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, the element order information including a request to generate element order information suitable for the target user, the element order information including a request to generate element order information suitable for the target user, the element order information including a request to generate element order information suitable for the target user, and an input means for inputting a request to generate element order information suitable for the target user, the element order information including ... A design support system comprising: an acquisition means for acquiring the element order information output from the AI ​​model in response to the request.

2. In claim 1, A registration means for registering reference information including element information on an element that has been created or edited, element order information on an order of elements that have been edited consecutively after the element, and user information on a user who has edited the plurality of elements, in a knowledge base that can be referenced by the AI ​​model; A design support system characterized in that the acquisition means acquires the element order information output from the AI ​​model by referring to reference information in the knowledge base in response to the request.

3. In claim 2, The design support system is characterized in that the registration means registers, in the knowledge base, reference information including the element information, element order information relating to the element order, the user information, and an evaluation value relating to editing of the plurality of elements.

4. In claim 3, An index information acquisition means for acquiring index information relating to a first index indicating an index of the value of the evaluation value or a second index different from the first index, the registration means registers, in the knowledge base, first reference information including the element information, the element order information, the user information, and the evaluation value based on the first index, and second reference information including the element information, the element order information, the user information, and the evaluation value based on the second index; A design support system characterized in that the input means inputs the request, including a request to refer to either the first reference information or the second reference information of the knowledge base, to the AI ​​model based on the index information acquired by the index information acquisition means.

5. In claim 1, A design support system characterized in that the request includes reference information including element information regarding an element that has already been created or edited, element order information regarding the order of elements that have been edited consecutively after the element, and user information regarding a user who edited the multiple elements.

6. In claim 5, A design support system, wherein the request includes the element information, element order information relating to the element order, the user information, and reference information including an evaluation value relating to editing of the plurality of elements.

7. In claim 6, An index information acquisition means for acquiring index information relating to a first index indicating an index of the value of the evaluation value or a second index different from the first index, The design support system is characterized in that the input means inputs the request to the AI ​​model based on the index information acquired by the index information acquisition means, the request including either first reference information including the element information, the element order information, the user information, and the evaluation value based on the first index, or second reference information including the element information, the element order information, the user information, and the evaluation value based on the second index.

8. an element order information acquiring means for acquiring element order information relating to a plurality of elements that have been successively edited and their order of editing (hereinafter, "a plurality of elements and their order of editing" will be referred to as "element order"), the element order information being a plurality of pieces of element order information having different elements or different order of editing; A user information acquisition means for acquiring user information regarding a target user; an input means for inputting a request including a plurality of pieces of element order information acquired by the element order information acquisition means and user information acquired by the user information acquisition means, the request including a request to generate one of the plurality of pieces of element order information suitable for the target user, into an AI model; A design support system comprising: an acquisition means for acquiring the element order information output from the AI ​​model in response to the request.

9. In claim 8, A registration means for registering reference information including element order information on an element order that has been successively edited and user information on a user who has edited the plurality of elements in a knowledge base that can be referenced by the AI ​​model, A design support system characterized in that the acquisition means acquires the element order information output from the AI ​​model by referring to reference information in the knowledge base in response to the request.

10. In claim 9, The design support system is characterized in that the registration means registers, in the knowledge base, element order information relating to the element order, the user information, and reference information including an evaluation value relating to editing of the plurality of elements.

11. In claim 10, An index information acquisition means for acquiring index information relating to a first index indicating an index of the value of the evaluation value or a second index different from the first index, the registration means registers, in the knowledge base, first reference information including the element order information, the user information, and the evaluation value based on the first index, and second reference information including the element order information, the user information, and the evaluation value based on the second index; A design support system characterized in that the input means inputs the request, including a request to refer to either the first reference information or the second reference information of the knowledge base, to the AI ​​model based on the index information acquired by the index information acquisition means.

12. In claim 8, A design support system, wherein the request includes reference information including element order information relating to an order of consecutively edited elements and user information relating to a user who edited the plurality of elements.

13. In claim 12, The design support system according to the present invention, wherein the request includes element order information regarding the element order, the user information, and reference information including an evaluation value regarding editing of the plurality of elements.

14. In claim 13, An index information acquisition means for acquiring index information relating to a first index indicating an index of the value of the evaluation value or a second index different from the first index, The design support system is characterized in that the input means inputs the request to the AI ​​model based on the index information acquired by the index information acquisition means, the request including either the element order information, first reference information including the user information and the evaluation value based on the first index, or second reference information including the element order information, the user information and the evaluation value based on the second index.

15. In any one of claims 1 to 3, 5, 6, 8 to 10, 12 and 13, A design support system, wherein the plurality of elements are elements whose setting or change requires human judgment and whose setting or change has an effect on other elements.

16. In claim 1, A design support system, wherein the design information is design information for designing a building.

Images