Design support system, learning data generation system, and trained model generation system

Abstract

To provide a design support system suitable for grasping a plurality of elements to be edited successively and the order of editing them. [Solution] A drawing creation support device 100 acquires the IDs of created or edited elements and the user ID of a target user, and estimates element order information suitable for the target user from the acquired element IDs and user IDs using a trained model trained based on training data including the created or edited element IDs, the user ID of the editing user, and element order information related to multiple edited elements edited consecutively after the edited element and their edit order. This makes it possible to grasp the multiple edited elements that are edited consecutively and their edit order. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

Description

[Technical Field]

[0001] The present invention relates to a design support system, and more particularly to a design support system, a training data generation system, and a trained model generation system that are suitable for grasping multiple elements that are edited in succession and the order in which they are edited. [Background technology]

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

[0003] The technology described in Patent Document 1 assigns a reward R to the combination of a state S, which is determined depending on whether or not a design activity has been performed, and an action A, which is an activity that can be selected under the state, and builds a trained model by maximizing the value.The trained model is then used to infer the next action to be taken from the current state. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-56238 Summary of the Invention [Problem to be solved by the invention]

[0005] In architectural design, multiple related elements of a unit may be edited consecutively. For example, when designing a toilet, the toilet bowl and hand basin are designed consecutively. However, the technology described in Patent Document 1 infers the next action to be taken from the current state, which poses a problem in that it is not possible to grasp the multiple elements that are edited consecutively and the order in which they are edited.

[0006] Therefore, the present invention has been made with a focus on the unresolved issues of the conventional technology, and aims to provide a design support system, a training data generation system, and a trained model generation system that are suitable for grasping multiple elements that are edited in succession and the order in which they are edited. [Means for solving the problem]

[0007] [Invention 1] In order to achieve the above object, the design support system of Invention 1 comprises: 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; and estimation means for estimating element order information suitable for the target user from the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, using a trained model trained based on training data including element information regarding the created or edited element, element order information regarding multiple elements edited in succession after the created or edited element and the order of editing them (hereinafter, "multiple elements and the order of editing them" will be referred to as "element order"), and user information regarding the user who edited the multiple elements.

[0008] With this configuration, the element information acquisition means acquires element information. Also, the user information acquisition means acquires user information. Then, the estimation means estimates element order information suitable for the target user from the acquired element information and user information using the trained model.

[0009] Here, the trained model may be one that has been trained based on training data that includes at least element information, element order information, and user information, and may also be one that has been trained based on training data that includes element information, element order information, user information, and other information.

[0010] Furthermore, 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 element information from a storage device or storage medium or the like, or generate or calculate element information by information processing or the like. Therefore, acquisition includes at least input, acquisition, reception, reading (including search), generation, and calculation. The same applies to user information acquisition means, and the same concept of acquisition applies hereinafter.

[0011] Furthermore, the element information may be configured, for example, as the element itself, or as information for identifying the element (for example, link information such as a name, number, ID, code, or URL), or as feature information relating to an outline, statistics, or other features of the element. The element information may be configured, for example, as characters, numbers, figures, codes, symbols, images, sounds, or other information. The element information may also be configured as keywords relating to the element (for example, one or more keywords indicating part of the name of the element). The same applies hereinafter to the trained model generation system of Invention 10.

[0012] Furthermore, the user information can be configured, for example, as information for identifying the user (for example, link information such as a name, number, ID, code, or URL), or as feature information relating to the user's summary, statistics, or other characteristics. The user information can be configured, for example, as characters, numbers, figures, codes, symbols, images, sounds, or other information. The user information can also be configured as keywords relating to the user (for example, one or more keywords indicating part of the user's name). The same applies to the design support system of Invention 4, the training data generation system of Invention 9, and the trained model generation system of Invention 10.

[0013] Furthermore, the element order information may be configured, for example, as the element order itself, or as information for identifying the elements and the editing order (e.g., link information such as a name, number, ID, code, or URL), or as feature information relating to an overview, statistics, or other features of the elements and the editing order. The element order information may be configured, for example, as characters, numbers, figures, codes, symbols, images, sounds, or other information. The element order information may also be configured as keywords relating to the elements and the editing order (e.g., one or more keywords indicating part of the name of the elements and the editing order). The same applies to the design support system of Invention 4, the training data generation system of Invention 9, and the trained model generation system of Invention 10.

[0014] Furthermore, this system may be realized as a single device, apparatus, terminal, or other device, or as a network system in which multiple devices, apparatus, terminals, or other devices are communicatively connected. In the latter case, each component may belong to any of the multiple devices as long as they are communicatively connected. The same applies to the design support system of Invention 4, the training data generation system of Invention 9, and the trained model generation system of Invention 10.

[0015] [Invention 2] Furthermore, the design support system of Invention 2 is the design support system of Invention 1, in which the trained model is trained to maximize the evaluation value based on training data including the element information, element order information regarding the element order, the user information, and an evaluation value regarding editing of the plurality of elements.

[0016] Here, the trained model may be one that has been trained based on training data that includes at least element information, element order information, user information, and an evaluation value, and may also be one that has been trained based on training data that includes element information, element order information, user information, an evaluation value, and other information. The same applies hereinafter to the trained model generation system of Invention 10.

[0017] [Invention 3] Furthermore, the design support system of Invention 3 is the design support system of Invention 2, wherein the trained model is a first trained model trained to maximize an evaluation value based on training data including the element information, the element order information, the user information, and the evaluation value based on a first index indicating an index of value of the evaluation value, and a second trained model trained to maximize an evaluation value based on training data including the element information, the element order information, the user information, and the evaluation value based on a second index different from the first index. The The system includes two trained models, and is equipped with an index information acquisition means that acquires index information regarding the first index or the second index, and a trained model selection means that selects either the first trained model or the second trained model based on the index information acquired by the index information acquisition means, and the estimation means estimates the element order information using the trained model selected by the trained model selection means.

[0018] With this configuration, the index information acquisition means acquires index information, the trained model selection means selects a trained model based on the acquired index information, and the estimation means estimates element order information using the selected trained model.

[0019] Here, the first trained model may be one that has been trained based on training data that includes at least element information, element order information, user information, and an evaluation value based on the first index, and may also be one that has been trained based on training data that includes element information, element order information, user information, an evaluation value based on the first index, and other information.

[0020] Furthermore, the second trained model may be one that has been trained based on training data that includes at least element information, element order information, user information, and an evaluation value based on the second index, and may also be one that has been trained based on training data that includes element information, element order information, user information, an evaluation value based on the second index, and other information.

[0021] [Invention 4] Furthermore, the design support system of Invention 4 comprises: element order information acquisition means for acquiring a plurality of pieces of element order information relating to a plurality of elements that have been edited consecutively and the order in which they are edited (hereinafter, "a plurality of elements and the order in which they are edited" will be referred to as "element order"), the plurality of pieces of element order information being different in elements or edit orders; user information acquisition means for acquiring user information relating to a target user; and estimation means for estimating, from the plurality of pieces of element order information acquired by the element order information acquisition means and the user information acquired by the user information acquisition means, which piece of the plurality of pieces of element order information is suitable for the target user, using a trained model trained based on training data including the element order information relating to the element order and user information relating to the user who edited the plurality of elements.

[0022] With this configuration, the element order information acquisition means acquires a plurality of pieces of element order information. Furthermore, the user information acquisition means acquires user information. Then, the estimation means estimates, using the trained model, one of the plurality of pieces of element order information that is suitable for the target user, based on the acquired plurality of pieces of element order information and the user information.

[0023] Here, the trained model may be one that has been trained based on training data that includes at least element order information and user information, and may also be one that has been trained based on training data that includes element order information, user information, and other information.

[0024] [Invention 5] Furthermore, the design support system of Invention 5 is the design support system of Invention 4, in which the trained model is trained to maximize the evaluation value based on training data including element order information regarding the element order, the user information, and an evaluation value regarding editing of the plurality of elements.

[0025] Here, the trained model may be one that has been trained based on training data that includes at least element order information, user information, and evaluation values, and may also be one that has been trained based on training data that includes element order information, user information, evaluation values, and other information.

[0026] [Invention 6] Furthermore, the design support system of Invention 6 is the design support system of Invention 5, wherein the trained model is a first trained model trained to maximize an evaluation value based on training data including the element order information, the user information, and the evaluation value based on a first index indicating an index of value of the evaluation value, and a second trained model trained to maximize an evaluation value based on training data including the element order information, the user information, and the evaluation value based on a second index different from the first index. The The system includes two trained models, and is equipped with an index information acquisition means that acquires index information regarding the first index or the second index, and a trained model selection means that selects either the first trained model or the second trained model based on the index information acquired by the index information acquisition means, and the estimation means estimates the element order information using the trained model selected by the trained model selection means.

[0027] With this configuration, the index information acquisition means acquires index information, the trained model selection means selects a trained model based on the acquired index information, and the estimation means estimates element order information using the selected trained model.

[0028] Here, the first trained model may be one that has been trained based on training data that includes at least element order information, user information, and an evaluation value based on the first index, and may also be one that has been trained based on training data that includes element order information, user information, an evaluation value based on the first index, and other information.

[0029] Furthermore, the second trained model may be one that has been trained based on training data that includes at least element order information, user information, and an evaluation value based on the second index, and may also be one that has been trained based on training data that includes element order information, user information, an evaluation value based on the second index, and other information.

[0030] [Invention 7] Furthermore, the design support system of Invention 7 is a design support system of any one of Inventions 1, 2, 4 and 5, in which the multiple elements are elements that require human judgment for setting or changing, and the setting or change affects other elements.

[0031] [Invention 8] Furthermore, in the design support system of Invention 8, in the design support system of Invention 1, the design information is design information for designing a building.

[0032] [Invention 9] Meanwhile, in order to achieve the above object, a training data generation system of Invention 9 includes an acquisition means for acquiring, from editing history data including a plurality of elements that have been edited consecutively and the editing order thereof (hereinafter, "a plurality of elements and the editing order thereof" will be referred to as "element order"), an element order that appears a predetermined number of times in the editing history data, and a generation means for generating training data including element order information regarding the element order acquired by the acquisition means and user information regarding the user who edited the plurality of elements.

[0033] With this configuration, the acquisition means acquires element orders that appear a predetermined number of times or more from the editing history data, and the generation means generates learning data that includes element order information and user information related to the acquired element orders.

[0034] [Invention 10] Meanwhile, in order to achieve the above object, the trained model generation system of Invention 10 assigns an evaluation value for the editing of the multiple elements to a combination of element information about an element that has already been created or edited, element order information about multiple elements that have been edited consecutively after the element in question and their editing order (hereinafter, "multiple elements and their editing order" will be referred to as "element order"), and user information about the user who edited the multiple elements, and generates a trained model by performing training so as to maximize the evaluation value.

[0035] With this configuration, an evaluation value is assigned to the combination of element information, element order information, and user information, and a trained model is generated by performing learning so as to maximize the evaluation value. [Effects of the Invention]

[0036] As described above, the design support system of the inventions 1 and 4 can grasp multiple elements that are edited consecutively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0037] Furthermore, according to the design support system of the second or fifth invention, it is possible to grasp the order of elements with high evaluation values.

[0038] Furthermore, according to the design support system of the third or sixth invention, it is possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0039] Furthermore, according to the design support system of Invention 7, it is possible to grasp the element order taking into consideration the relationship between elements whose setting or change requires human judgment and other elements that are affected by the setting or change.

[0040] On the other hand, according to the learning data generation system of Invention 9, it is possible to learn the element order that appears frequently in the editing history data.

[0041] On the other hand, according to the trained model generation system of Invention 10, a trained model can be obtained that provides an element order with a high evaluation value. [Brief explanation of the drawings]

[0042] [Figure 1] 1 is a diagram illustrating a hardware configuration of a drawing creation support device 100. FIG. [Figure 2] FIG. 10 is a diagram showing the structure of CAD data for a plan view. [Figure 3] FIG. 10 is a diagram showing the structure of edit history data. [Figure 4] 10 is a flowchart showing a learning data generation process. [Figure 5] FIG. 2 is a diagram illustrating a structure of learning data. [Figure 6] 10 is a flowchart illustrating a trained model generation process. [Figure 7] FIG. 1 is a block diagram showing the process of generating and using a trained model. [Figure 8] 10 is a flowchart showing an element order information estimation process. [Figure 9] This is a plan showing the expected delivery of a piano. [Figure 10] FIG. 10 is a diagram showing the structure of edit history data. [Figure 11] FIG. 2 is a diagram illustrating a structure of learning data. [Figure 12] 10 is a flowchart showing an element order information estimation process. [Figure 13] FIG. 2 is a diagram illustrating a structure of learning data. [Figure 14] 10 is a flowchart showing an element order information estimation process. [Figure 15] FIG. 2 is a diagram illustrating a structure of learning data. [Figure 16] 10 is a flowchart showing an element order information estimation process. [Figure 17] 1 is a block diagram showing a configuration of a network system according to an embodiment of the present invention; [Figure 18] FIG. 1 is a functional block diagram of a generation AI server 120. [Figure 19] 10 is a flowchart showing a learning data registration process. [Figure 20] 10 is a flowchart showing an element order information acquisition process. [Figure 21] 10 is a flowchart showing an element order information acquisition process. [Figure 22] 10 is a flowchart showing an element order information acquisition process. [Figure 23] 10 is a flowchart showing an element order information acquisition process. DETAILED DESCRIPTION OF THE INVENTION

[0043] [First embodiment] A first embodiment of the present invention will be described below, with Figs. 1 to 9 showing the present embodiment.

[0044] [Configuration of this embodiment] First, the configuration of this embodiment will be described. FIG. 1 is a diagram showing the hardware configuration of a drawing creation support device 100. As shown in FIG.

[0045] As shown in FIG. 1, the drawing creation support device 100 is composed of a CPU (Central Processing Unit) 30 that controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 that stores the control program and the like for the CPU 30 in advance in a predetermined area, a RAM (Random Access Memory) 34 that stores data read from the ROM 32 and the calculation results required in the calculation process of the CPU 30, and an I / F (Interface) 38 that mediates the input and output of data to and from external devices, and these are connected to each other and capable of sending and receiving data by a bus 39, which is a signal line for transferring data.

[0046] The I / F 38 is connected to external devices such as an input device 40 consisting of a keyboard, 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.

[0047] CAD (Computer Aided Design) software and BIM (Building Information Modeling) software (hereinafter collectively referred to as "CAD software") are installed in the storage device 42. CAD software is software that assists designers in creating drawings in response to their operations. When a request is made to start the CAD software, the CPU 30 starts a program for the CAD software stored in a predetermined area of ​​the ROM 32 and executes processing in accordance with the program. The designer can start the CAD software to create plan drawings, detailed floor plans, and other architectural drawings.

[0048] Next, the data structure of the storage device 42 will be described. The storage device 42 stores CAD data of architectural drawings such as plan drawings, detailed floor plans, and the like.

[0049] FIG. 2 is a diagram showing the structure of CAD data for a plan view. As shown in Figure 2, CAD data for a plan is data that constitutes a detailed drawing of the cross section of a building, and is configured as data that includes one or more elements that can be created or edited (hereinafter referred to as "edit elements"). CAD data for a plan is created by a designer using CAD software. A designer creates a plan by creating, setting, changing, or deleting (hereinafter referred to as "editing") edit elements in the CAD software. In the example of Figure 2, the edit elements for the floor, wall, and ceiling of the area labeled "internal corridor" are arranged, and the edit elements for the floor, wall, and ceiling of the area labeled "windbreak room" are arranged.

[0050] The same is true for CAD data of detailed floor plans and other architectural drawings, which are structured as data including one or more editing elements.

[0051] The storage device 42 stores, for each CAD data, edit history data that indicates the history of editing of edit elements. The CAD data reflects the final edit results related to the edit history data.

[0052] FIG. 3 is a diagram showing the structure of the edit history data. 3, the editing history data includes, for each edited element, element information 400 about the edited element, a user ID 402 for identifying the user who edited the edited element (hereinafter referred to as the "editing user"), and editing time 404 required to edit the edited element, in the order of editing. The element information 400 includes the element ID for identifying the edited element, the area that was the target of editing of the edited element, and the edited element. The editing time 404 can be calculated, for example, by subtracting the editing start time from the editing end time.

[0053] The example in Figure 3 shows that the first related group of toilet edit elements, "toilet bowl," "hand wash counter," "mirror," and "towel rack," were edited consecutively in that order. These edit elements were assigned element IDs "52," "53," "54," and "55," and the edit times were 35, 38, 70, and 94 minutes, respectively. These edit elements were edited by the user with user ID "001."

[0054] The second related group shows that the edit elements of the toilet, "exhaust fan," "lighting," "storage," and "outlet," were edited consecutively in that order. These edit elements were assigned element IDs "56," "57," "58," and "59," and the edit times were 94, 48, 42, and 74 minutes, respectively. These edit elements were edited by the user with user ID "001."

[0055] Additionally, the third related group shows that the closet edit elements "shelf," "clothing rail," "drawer," and "basket" were edited consecutively in that order. These edit elements were assigned element IDs "60," "61," "62," and "63," and the edit times were 96, 74, 84, and 22 minutes, respectively. These edit elements were edited by the user with user ID "002."

[0056] Additionally, the fourth related group shows that the kitchen edit elements "flooring," "wall material," "counter," and "sink" were edited consecutively in that order. These edit elements were assigned element IDs "64," "65," "66," and "67," and the edit times were 42, 44, 35, and 32 minutes, respectively. These edit elements were edited by the user with user ID "003."

[0057] The editing history data is used to create learning data, and therefore the storage device 42 stores a large number of pieces of editing history data that have been created in the past.

[0058] [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.

[0059] The learning data generation process is a process for generating learning data, and when executed by the CPU 30, the process proceeds to step S100 as shown in FIG.

[0060] In step S100, unprocessed editing history data is obtained from the storage device 42, and the process proceeds to step S102, where the variable n is set to "2", and the process proceeds to step S104.

[0061] In steps S104 to S110, the element ID of the edited element that has been created or edited (hereinafter abbreviated as "created or edited element ID"), the n edited elements (the number indicated by the value of variable n) that were edited consecutively after that edited element and their edit order, the user ID of the editing user, and their edit time are obtained from the edit history data obtained in step S100. Hereinafter, multiple edited elements and their edit order may be referred to as the "element order." The element order is obtained in units of the same user ID. Using Figure 3 as an example, a case where the value of variable n is "2" will be described. In the edit history data in Figure 3, the rows are arranged in the order of edits.

[0062] When the second row is targeted, the element IDs of the previously edited elements, "01" to "51", are acquired as the created or edited element IDs. Because the value of variable n is "2", the edited elements are "toilet" and "hand wash counter", the user ID is "001", and the edited times are "35" and "38".

[0063] When the third row is targeted, the element IDs of the previous edited elements, "01" to "52", are acquired as created or edited element IDs. Because the value of variable n is "2", the edited elements are "hand washing counter" and "mirror", the user ID is "001", and the edited times are "38" and "70".

[0064] Next, the process proceeds to step S112, where the sum of the editing times acquired in step S110 is multiplied by "-1" to calculate an evaluation value. In the example of the second line above, the editing times "35" and "38" are acquired, so the evaluation value is calculated as (35 + 38) x -1 = -73. The reason for multiplying by "-1" is to set a higher evaluation value the shorter the editing time.

[0065] Next, the process proceeds to step S114, where the element ID, element order, and user ID obtained in steps S104 to S110, and the evaluation value calculated in step S112 are associated and registered in the learning data, the process proceeds to step S116, where "1" is added to the value of variable n, and the process proceeds to step S118.

[0066] In step S118, it is determined whether the value of variable n is greater than "4", and if it is determined that the value is less than or equal to "4" (NO), the process proceeds to step S104. Then, the processes of steps S104 to S116 are repeatedly executed until the value of variable n becomes "4".

[0067] Using 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 "3."

[0068] When the second row is targeted, the element IDs of the previously edited elements, "01" to "51," are obtained as the created or edited element IDs. Since the value of variable n is "3," the edited elements are "toilet," "hand wash counter," and "mirror," the user ID is "001," and the edit times are "35," "38," and "70." The evaluation value is calculated as (35 + 38 + 70) x -1 = -143.

[0069] When the third row is targeted, the element IDs of the previously edited elements, "01" to "52," are obtained as the created or edited element IDs. Since the value of variable n is "3," the edited elements are "hand washing counter," "mirror," and "towel rack," the user ID is "001," and the edit times are "38," "70," and "94." The evaluation value is calculated as (38 + 70 + 94) x -1 = -202.

[0070] Also, using 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."

[0071] When the second row is targeted, the element IDs of the previously edited elements, "01" to "51," are obtained as the created or edited element IDs. Since the value of variable n is "4," the edited elements are "toilet," "hand wash counter," "mirror," and "towel rack," the user ID is "001," and the edit times are "35," "38," "70," and "94." The evaluation value is calculated as (35 + 38 + 70 + 94) x -1 = -237.

[0072] When the third row is targeted, the element IDs of the previously edited elements, "01" to "52," are obtained as the created or edited element IDs. Since the value of variable n is "4," the edited elements are "hand washing counter," "mirror," "towel rack," and "exhaust fan," the user ID is "001," and the edit times are "38," "70," "94," and "94." The evaluation value is calculated as (38 + 70 + 94 + 94) x -1 = -296.

[0073] On the other hand, if it is determined in step S118 that the value of variable n is greater than "4" (YES), the process proceeds to step S120 to determine whether processing of steps S100 to S118 has been completed for all editing history data, and if it is determined that processing has been completed for all editing history data (YES), the process proceeds to step S122.

[0074] In step S122, the learning data in which the element IDs and other information have been registered in step S114 is stored in the storage device .

[0075] FIG. 5 is a diagram illustrating the structure of the learning data. 5, each row of the learning data includes a created or edited element ID 410, element order information 412, a user ID 414, and an evaluation value 416. The element order information 412 includes the area to be edited for the edit element and the element order.

[0076] The second line of Figure 5 shows the two edited elements that were edited consecutively after the edited element in the first line of Figure 3, their edit order, the user ID and evaluation value of the editing user, the third line of Figure 5 shows the two edited elements that were edited consecutively after the edited element in the second line of Figure 3, their edit order, the user ID and evaluation value of the editing user, and the fourth line of Figure 5 shows the two edited elements that were edited consecutively after the edited element in the third line of Figure 3, their edit order, the user ID and evaluation value of the editing user. In addition, the sixth line of Figure 5 shows the two edited elements that were edited consecutively after the edited element on the fifth line of Figure 3, their edit order, the user ID and evaluation value of the editing user, the seventh line of Figure 5 shows the two edited elements that were edited consecutively after the edited element on the sixth line of Figure 3, their edit order, the user ID and evaluation value of the editing user, and the eighth line of Figure 5 shows the two edited elements that were edited consecutively after the edited element on the seventh line of Figure 3, their edit order, the user ID and evaluation value of the editing user.

[0077] 5 shows the three edited elements edited in succession after the edited element on the first line of Fig. 3, their edit order, the user ID of the editing user, and the evaluation value. Line 11 of Fig. 5 shows the three edited elements edited in succession after the edited element on the second line of Fig. 3, their edit order, the user ID of the editing user, and the evaluation value. Line 13 of Fig. 5 shows the three edited elements edited in succession after the edited element on the fifth line of Fig. 3, their edit order, the user ID of the editing user, and the evaluation value. Line 14 of Fig. 5 shows the three edited elements edited in succession after the edited element on the sixth line of Fig. 3, their edit order, the user ID of the editing user, and the evaluation value.

[0078] Furthermore, line 16 of Figure 5 shows the four edited elements that were edited consecutively after the edited element on line 1 of Figure 3, their edit order, the user ID and evaluation value of the editing user, and line 18 of Figure 5 shows the four edited elements that were edited consecutively after the edited element on line 5 of Figure 3, their edit order, the user ID and evaluation value of the editing user.

[0079] [Trained model generation process] FIG. 6 is a flowchart showing the trained model generation process.

[0080] FIG. 7 is a block diagram showing the process of generating and using a trained model. The trained model generation process is a process executed to generate a trained model, and when executed by the CPU 30, the process proceeds to step S200 to execute a training data analysis process, as shown in Fig. 6. In the training data analysis process, training data is read from the storage device 42, and created or edited element IDs 410, element order information 412, user IDs 414, and evaluation values ​​416 are extracted from the read training data.

[0081] Next, the process proceeds to step S202. In step S202, as shown in FIG. 7, a training dataset is generated based on the information extracted in step S200. The process proceeds to step S204, where the generated training dataset is input to a training program, and a trained model is generated by the training program. The training program includes pre-training parameters and hyperparameters, and performs training based on the input training dataset and hyperparameters to update the pre-training parameters. As a training method, for example, reinforcement learning (e.g., supervised reinforcement learning, imitation learning) can be adopted. In reinforcement learning, an evaluation value related to the editing of the multiple edited elements is assigned to a combination of an already created or edited element ID, multiple edited elements edited consecutively after the edited element, element order information related to the edit order, and a user ID, and training is performed to maximize the evaluation value. The trained model is then output as the training result.

[0082] The trained model is trained based on created or edited element IDs 410, element order information 412, user IDs 414, and evaluation values ​​416 so as to maximize the evaluation value 416. The trained model includes trained parameters in which pre-trained parameters have been updated through training, and an inference program. The inference program inputs created or edited element IDs and the user ID of the user currently editing (hereinafter referred to as the "target user"), estimates element order information suitable for the target user from the input element IDs and user ID based on the trained parameters, and outputs the estimated element order information. Note that the relationship between the input element IDs and user ID and the output element order information is determined by AI training, and therefore, although it shows a similar tendency to the content of past training data, there is ambiguity in that it does not necessarily match exactly. However, this ambiguity can be reduced by adjusting the amount of training data and the training accuracy.

[0083] Next, the process proceeds to step S206, where the trained model generated in step S204 is stored in the storage device 42, and the series of processes ends.

[0084] [Element order information estimation process] FIG. 8 is a flowchart showing the element order information estimation process.

[0085] The element order information estimation process is a process that is executed in response to a request from a target user, and when executed by the CPU 30, the process first proceeds to step S300 as shown in FIG.

[0086] In step S300, the user ID of the target user is acquired, and the process proceeds to step S302, where the created or edited element ID is acquired from the CAD data currently being edited, and the process proceeds to step S304.

[0087] In step S304, using the trained model in the storage device 42, multiple pieces of element order information suitable for the target user, which have different edit elements or edit orders, are estimated from the element IDs and user IDs acquired in steps S300 and S302. The estimation is performed by inputting the element IDs and user ID into the trained model and acquiring element order information output from the trained model. The trained model may be configured to acquire multiple outputs from a single input, or multiple outputs may be acquired by repeating a single input and a single output multiple times.

[0088] Next, the process proceeds to step S306, where one of the plurality of element orders is displayed on the display device 44 according to one of the plurality of display rules based on the plurality of element order information estimated in step S304. Which display rule is to be used may be set by the target user, or may be set according to a predetermined algorithm, for example.

[0089] The first display rule is to display the element order with the largest number of edit elements among the multiple estimated element orders.

[0090] The second display rule is to display an element order that has a related grouping among the multiple estimated element orders. For example, if the multiple element orders estimated from the current editing state are (1) A, B, (2) A, B, C, (3) A, B, C, D, (4) A, B, C, D, E, and (5) A, B, C, D, E, F, and A to D are a related grouping among them, according to the second display rule, one of (3) to (5) is displayed. Whether or not a grouping is related can be determined by, for example, identifying two or more edited elements and their edit orders among A to F that appear more than a predetermined number of times in the learning data. The same applies to the third and fourth display rules below.

[0091] The third display rule is to display the same element order as a related group of the estimated element orders. For example, if the element orders estimated from the current editing state are (1) to (5) above, the third display rule displays (3).

[0092] The fourth display rule is to display related groups among the estimated element sequences and related groups from the element sequence including other edited elements. For example, if the element sequence estimated from the current edit state is (1), (2), and (5) above, according to the fourth display rule, A to D are displayed from (5).

[0093] Next, proceed to step S308, and if the target user creates or edits an edit element based on the displayed element order, obtain the created or edited element ID including the element ID of the edit element from the CAD data currently being edited, and proceed to step S310.

[0094] In step S310, based on the element order displayed in steps S306 and S316 and the element ID acquired in step S308, it is determined whether the edited elements created or edited by the target user differ from the edited elements or edit order displayed in steps S306 and S316, and if it is determined that the edited result differs from the estimated result (YES), the process proceeds to step S312.

[0095] In step S312, the display rules used for display in steps S306 and S316 are changed. For example, the display rules are changed to the most appropriate ones so that the edited results match the estimated results. The timing for changing the display rules does not have to be every time one creation or edit is made, but may be every time multiple creations or edits are made.

[0096] Next, the process proceeds to step S314, where, similar to the processing of step S304, multiple element order information is estimated from the element IDs and user IDs obtained in steps S300 and S308 using the trained model in the storage device 42, and the process proceeds to step S316.

[0097] In step S316, similar to the process in step S306, 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.

[0098] In step S318, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0099] On the other hand, if it is determined in step S318 that the editing by the target user has not finished (NO), the process proceeds to step S308.

[0100] On the other hand, if it is determined in step S310 that the edited result matches the estimated result (NO), the process proceeds to step S314.

[0101] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0102] Figure 9 is a plan showing how a piano will be brought in. If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when the piano is delivered. However, changing the toilet width also requires editing other editable elements of the toilet. Therefore, after changing the toilet width, the designer requests estimation of the element order to be edited for the toilet. Steps S300 to S306 are then executed to acquire the created or edited element IDs and user IDs, and the element order is estimated and displayed based on the acquired element IDs and user IDs. For example, if the element order information in line 16 of FIG. 5 is estimated, "toilet bowl → hand washing counter → mirror → towel rack" is displayed. As shown in FIG. 9, if these editable elements are already included in the CAD data, for example, these editable elements are highlighted (e.g., displayed with a specific color or pattern) and the edit order is displayed by connecting them with arrows or the like. If they are not included in the CAD data, for example, these editable elements are displayed as ghosts (e.g., ghost images of the editable elements are displayed in wireframe) and the edit order is displayed by connecting them with arrows or the like.

[0103] Then, when the designer creates or edits the edit element "toilet" based on the estimated and displayed element order, the next element order is estimated and displayed through steps S308 to S316. If the designer's editing result differs from the estimated result, the display rules are changed through step S312.

[0104] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, the created or edited element ID and the user ID of the target user are obtained, and element order information suitable for the target user is estimated from the obtained element ID and user ID using a trained model.

[0105] This makes it possible to grasp a plurality of edited elements that are edited successively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0106] Furthermore, in this embodiment, a plurality of pieces of element order information with different edit elements or edit orders are estimated, and one of a plurality of element orders is displayed based on the estimated plurality of pieces of element order information.

[0107] This makes it possible to grasp a plurality of edit elements to be edited successively and a plurality of candidates for the order of editing.

[0108] Furthermore, in this embodiment, the element order with the largest number of edited elements among the plurality of estimated element orders is displayed.

[0109] This allows the designer to carry out editing while imagining large editing units. Furthermore, in this embodiment, element orders that appear a predetermined number of times or more in the training data are identified as related groups, and element orders that have related groups among the multiple estimated element orders are displayed.

[0110] This allows the designer to carry out editing while imagining related groups.

[0111] Furthermore, in this embodiment, an element order that appears a predetermined number of times or more in the training data is identified as a related group, and an element order that is the same as the related group among the multiple estimated element orders is displayed.

[0112] This allows the designer to carry out editing while imagining related groups.

[0113] Furthermore, in this embodiment, element sequences that appear a predetermined number of times or more in the training data are identified as related groups, and from among the multiple estimated element sequences, related groups and element sequences that include other edited elements are displayed, which are related groups.

[0114] This allows the designer to carry out editing while imagining related groups.

[0115] Furthermore, in this embodiment, created or edited element IDs including the element IDs of edited elements created or edited by the target user are obtained based on the displayed element order, and element order information suitable for the target user is estimated from the obtained element IDs and user ID using a trained model.

[0116] As a result, the element order is estimated and displayed for the results of creation or editing based on the displayed element order, so that it is possible to grasp the multiple edit elements that are edited consecutively and their edit order.

[0117] Furthermore, in this embodiment, created or edited element IDs including the element IDs of edited elements created or edited by the target user are obtained based on the displayed element order, and the display rules are changed based on the displayed element order and the obtained element IDs.

[0118] This allows the display rules to be changed depending on the display result of the element order and the result of subsequent creation or editing.

[0119] Furthermore, in this embodiment, the trained model is trained to maximize the evaluation value based on learning data including the ID of an element that has been created or edited, multiple edited elements that have been edited consecutively after that edited element and element order information regarding the order of editing, the user ID of the editing user, and evaluation values ​​regarding the editing of the multiple edited elements.

[0120] This allows the order of elements with high evaluation values ​​to be understood. Furthermore, in this embodiment, an evaluation value related to the editing of the multiple edited elements is assigned to a combination of an already created or edited element ID, multiple edited elements edited consecutively after that edited element and element order information related to the order of editing, and a user ID, and a trained model is generated by performing training so as to maximize the evaluation value.

[0121] This makes it possible to obtain a trained model that produces an element order with a high evaluation value. In this embodiment, step S300 corresponds to the user information acquisition means of invention 1, steps S302 and S308 correspond to the element information acquisition means of invention 1, steps S304 and S314 correspond to the estimation means of invention 1, and CAD data corresponds to the design information of invention 8. In addition, the created or edited element ID corresponds to the element information of invention 1, 2 or 10, and the user ID corresponds to the user information of invention 1, 2, 9 or 10.

[0122] Second Embodiment Next, a second embodiment of the present invention will be described. Figures 10 to 12 show this embodiment. Figures 3, 5, 6 and 9 are also used.

[0123] This embodiment differs from the first embodiment in that estimation is performed using a first trained model and a second trained model that have been trained using evaluation values ​​based on different indices. Only the differences from the first embodiment will be described below, and descriptions of overlapping parts will be omitted.

[0124] [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.

[0125] 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.

[0126] As shown in FIG. 10, the editing history data includes, for each edited element, element information 420 about that edited element, the user ID 422 of the editing user, and the number of edited items 424 required to edit that edited element, in the order of editing.

[0127] The example in Figure 10 shows that the first related group is made up of the toilet edit elements "toilet bowl," "hand wash counter," "mirror," and "towel rack," which are edited consecutively in that order. These edit elements are assigned element IDs "52," "53," "54," and "55," and the number of edited items is 8, 5, 6, and 9, respectively. These edit elements were edited by the user with user ID "001."

[0128] Additionally, the second related group shows that the edit elements of the toilet, "exhaust fan," "lighting," "storage," and "outlet," have been edited consecutively in that order. These edit elements have been assigned element IDs "56," "57," "58," and "59," and the number of edited items is 3, 7, 8, and 6, respectively. These edit elements were edited by the user with user ID "001."

[0129] Additionally, the third related group shows that the closet edit elements "shelf," "hanger rail," "drawer," and "basket" have been edited consecutively in that order. These edit elements have been assigned element IDs "60," "61," "62," and "63," and the number of edited items is 8, 7, 2, and 4, respectively. These edit elements were edited by the user with user ID "002."

[0130] Additionally, the fourth related group shows that the kitchen edit elements "flooring," "wall material," "counter," and "sink" have been edited consecutively in that order. These edit elements have been assigned element IDs "64," "65," "66," and "67," and the number of edited items is 7, 4, 3, and 8, respectively. These edit elements were edited by the user with user ID "003."

[0131] [Operation of this embodiment] Next, 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 of FIG. 10, similarly to the generation of learning data of FIG.

[0132] FIG. 11 is a diagram showing the structure of the learning data. As shown in FIG. 11, each line of the learning data includes an element ID 430 that has been created or edited, element order information 432, a user ID 434, and an evaluation value 436.

[0133] The second line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the first line of Figure 10, their edit order, the user ID and evaluation value of the editing user, the third line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the second line of Figure 10, their edit order, the user ID and evaluation value of the editing user, and the fourth line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the third line of Figure 10, their edit order, the user ID and evaluation value of the editing user. In addition, the sixth line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the fifth line of Figure 10, their edit order, the user ID and evaluation value of the editing user, the seventh line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the sixth line of Figure 10, their edit order, the user ID and evaluation value of the editing user, and the eighth line of Figure 11 shows the two edited elements that were edited consecutively after the edited element on the seventh line of Figure 10, their edit order, the user ID and evaluation value of the editing user.

[0134] 11 shows the three edited elements edited in succession after the edited element on the first line of Fig. 10, their edit order, the user ID of the editing user, and the evaluation value. Line 11 of Fig. 11 shows the three edited elements edited in succession after the edited element on the second line of Fig. 10, their edit order, the user ID of the editing user, and the evaluation value. Line 13 of Fig. 11 shows the three edited elements edited in succession after the edited element on the fifth line of Fig. 10, their edit order, the user ID of the editing user, and the evaluation value. Line 14 of Fig. 11 shows the three edited elements edited in succession after the edited element on the sixth line of Fig. 10, their edit order, the user ID of the editing user, and the evaluation value.

[0135] In addition, line 16 of Figure 11 shows the four edited elements that were edited consecutively after the edited element on line 1 of Figure 10, their edit order, the user ID and evaluation value of the editing user, and line 18 of Figure 11 shows the four edited elements that were edited consecutively after the edited element on line 5 of Figure 10, their edit order, the user ID and evaluation value of the editing user.

[0136] [Trained model generation process] In the trained model generation process, steps S200 to S204 are performed to generate a first trained model by performing training based on the training data in Fig. 5. The first trained model is the same as the trained model in the first embodiment.

[0137] In the trained model generation process, steps S200 to S204 are performed, and a second trained model is generated by performing training based on the training data in Fig. 11, similar to the generation of the first trained model. The second trained model is trained based on the created or edited element ID 430, element order information 432, user ID 434, and evaluation value 436 so as to maximize the evaluation value 436.

[0138] Then, the process proceeds to step S206, where the first trained model and the second trained model generated in step S204 are stored in the storage device 42, and the series of processes is terminated.

[0139] [Element order information estimation process] FIG. 12 is a flowchart showing the element order information estimation process.

[0140] The element order information estimation process is a process that is executed in response to a request from a target user, and when executed by the CPU 30, first, the process proceeds to step S330 as shown in FIG.

[0141] In step S330, index information regarding the first index "editing time" or the second index "number of edited items", which indicate an index of the value of the evaluation value, is acquired, and the process proceeds to step S332, where if the index related to the acquired index information is the first index, the first trained model is selected, and if the index related to the acquired index information is the second index, the second trained model is selected.

[0142] Next, the process proceeds to step S334, where the user ID of the target user is acquired, and then to step S336, where the created or edited element ID is acquired from the CAD data currently being edited, and then to step S338.

[0143] In step S338, the trained model selected in step S332 from the first trained model and the second trained model in the storage device 42 (hereinafter referred to as the "selected trained model") is used to estimate multiple pieces of element order information from the element IDs and user IDs acquired in steps S334 and S336. The estimation method is the same as the processing in step S304 in the first embodiment described above.

[0144] Next, the process proceeds to step S340, where 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 S338, similar to the process of step S306, and the process proceeds to step S342.

[0145] In step S342, if the target user creates or edits an edit element based on the displayed element order, the created or edited element ID including the element ID of the edit element is obtained from the CAD data currently being edited, and the process proceeds to step S344.

[0146] In step S344, based on the element order displayed in steps S340 and S350 and the element ID obtained in step S342, it is determined whether the edited elements created or edited by the target user differ from the edited elements or edit order displayed in steps S340 and S350, and if it is determined that the edited result differs from the estimated result (YES), the process proceeds to step S346.

[0147] In step S346, similar to the process in step S312, the display rules used for display in steps S340 and S350 are changed, and the process proceeds to step S348.

[0148] In step S348, similar to the processing in step S338, the selected trained model is used to estimate multiple pieces of element order information from the element IDs and user IDs acquired in steps S334 and S342, and the process proceeds to step S350.

[0149] In step S350, similar to the process in step S340, one of the plurality of element orders is displayed on display device 44 based on the plurality of element order information estimated in step S348, and the process proceeds to step S352.

[0150] In step S352, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0151] On the other hand, if it is determined in step S352 that the editing by the target user has not finished (NO), the process proceeds to step S342.

[0152] On the other hand, if it is determined in step S344 that the edited result matches the estimated result (NO), the process proceeds to step S348.

[0153] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0154] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when bringing the piano in. However, changing the width of the toilet will require editing of other elements of the toilet as well. Therefore, after changing the width of the toilet, the designer requests an estimation of the element order to be edited for the toilet. At this time, if the designer wants to obtain an element order that shortens the editing time, the designer selects "editing time" as the indicator, and the first trained model is selected through steps S330 to S332. Then, through steps S334 to S340, the created or edited element IDs and user IDs are acquired, and the element order is estimated and displayed using the first trained model from the acquired element IDs and user IDs.

[0155] On the other hand, if an element order that reduces the number of edited items is desired, the designer selects "number of edited items" as the index, and the second trained model is selected through steps S330 to S332. Then, through steps S334 to S340, created or edited element IDs and user IDs are acquired, and the element order is estimated and displayed from the acquired element IDs and user IDs by the second trained model.

[0156] [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 first trained model or the second trained model is selected based on the acquired index information, created or edited element IDs and user IDs are acquired, and multiple element order information is estimated from the acquired element IDs and user IDs using the selected trained model.

[0157] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0158] In this embodiment, step S330 corresponds to the index information acquisition means of invention 3, step S332 corresponds to the model selection means of invention 3, and steps S338 and S348 correspond to the estimation means of invention 3.

[0159] Third Embodiment Next, a third embodiment of the present invention will be described. Figures 13 and 14 show this embodiment. Figures 3, 5, 6 and 9 are also used.

[0160] This embodiment differs from the first embodiment in that a second trained model is used to estimate element order information suitable for a target user from a plurality of pieces of element order information estimated by a first trained model. Only the differences from the first embodiment will be described below, and descriptions of overlapping parts will be omitted.

[0161] [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 of FIG. 3, similar to the generation of learning data of FIG.

[0162] FIG. 13 is a diagram illustrating the structure of the learning data. As shown in FIG. 13 , the learning data includes element order information 440, a user ID 442, and an evaluation value 444 for each row. The learning data in FIG. 13 differs from the learning data in FIG. 5 in that it does not include the created or edited element ID 410. The learning data in FIG. 13 can be configured independently of the learning data in FIG. 5 , for example, by (1) deleting the element ID 410 from the learning data in FIG. 5 , (2) generating the learning data based on the editing history data in FIG. 3 but using a different generation method than the learning data in FIG. 5 , or (3) using data other than the editing history data in FIG. 3 . The evaluation value 444 is calculated based on the editing time required to edit the edit elements, as in the first embodiment. A higher evaluation value 444 indicates an element order that is more likely to be selected by a user with user ID 442.

[0163] [Trained model generation process] Generic training data is prepared by deleting the user ID 414 from the training data in Figure 5. In the trained model generation process, steps S200 to S204 are performed, and a first trained model is generated by performing training based on the generic training data, similar to the generation of the trained model in the first embodiment. The first trained model is trained based on the created or edited element ID 410, element order information 412, and evaluation value 416 so as to maximize the evaluation value 416.

[0164] In the trained model generation process, steps S200 to S204 are performed, and a second trained model is generated by performing training based on the training data in Fig. 13, similar to the generation of the trained model in the first embodiment. The second trained model is trained based on the element order information 440, the user ID 442, and the evaluation value 444 so that the evaluation value 444 is maximized.

[0165] Then, the process proceeds to step S206, where the first trained model and the second trained model generated in step S204 are stored in the storage device 42, and the series of processes is terminated.

[0166] [Element order information estimation process] FIG. 14 is a flowchart showing the element order information estimation process.

[0167] The element order information estimation process is a process that is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S360 as shown in FIG.

[0168] In step S360, the user ID of the target user is acquired, and the process proceeds to step S362, where the created or edited element ID is acquired from the CAD data currently being edited, and the process proceeds to step S364.

[0169] In step S364, a plurality of pieces of element order information are estimated from the element IDs acquired in step S362 using the first trained model in the storage device 42. The estimation method is the same as the process in step S304 in the first embodiment.

[0170] Next, the process proceeds to step S366, where, using the second trained model in the storage device 42, it estimates, from the multiple pieces of element order information estimated in step S364 and the user ID acquired in step S360, which of the pieces of element order information is suitable for the target user. The estimation is performed by inputting the multiple pieces of element order information and the user ID into the second trained model and acquiring the element order information output from the second trained model.

[0171] Next, the process proceeds to step S368, where the element order is displayed on the display device 44 based on the element order information estimated in step S366, and the process proceeds to step S370, where it is determined whether editing by the target user has finished, and if it is determined that editing has finished (YES), the process ends.

[0172] On the other hand, if it is determined in step S370 that the editing by the target user has not finished (NO), the process proceeds to step S362.

[0173] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0174] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when the piano is delivered. However, changing the width of the toilet also requires editing other elements of the toilet. Therefore, after changing the width of the toilet, the designer requests estimation of the element order to be edited for the toilet. In steps S360 to S364, created or edited element IDs and user IDs are acquired, and multiple pieces of element order information are estimated from the acquired element IDs using the first trained model. Then, in steps S366 to S368, the second trained model estimates and displays the element order based on the estimated multiple pieces of element order information and the acquired user ID. That is, in step S364, multiple candidate element orders are estimated, and in step S366, the candidates are narrowed down to those that suit the target user.

[0175] Then, when the designer creates or edits the edit element "toilet" based on the element order that has been estimated and displayed, the next element order is estimated and displayed through steps S362 to S368.

[0176] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, multiple pieces of element order information and the user ID of the target user are obtained, and using the second trained model, element order information suitable for the target user is estimated from the multiple pieces of element order information and user ID obtained.

[0177] This makes it possible to grasp a plurality of edited elements that are edited successively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0178] In this embodiment, step S360 corresponds to the user information acquisition means of invention 4, step S362 corresponds to the element order information acquisition means of invention 4, step S366 corresponds to the estimation means of invention 4, and the user ID corresponds to the user information of invention 4 or 5.

[0179] [Fourth embodiment] Next, a fourth embodiment of the present invention will be described. Figures 15 and 16 are diagrams showing this embodiment. Figures 6, 9, 11, and 13 are also used.

[0180] This embodiment differs from the third embodiment in that estimation is performed using a second trained model and a third trained model that have been trained using evaluation values ​​based on different indices. Only the differences from the third embodiment will be described below, and descriptions of overlapping parts will be omitted.

[0181] [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 of FIG. 10, similar to the generation of learning data of FIG.

[0182] FIG. 15 is a diagram illustrating the structure of the learning data. As shown in FIG. 15 , the learning data includes element order information 450, a user ID 452, and an evaluation value 454 for each row. The learning data in FIG. 15 differs from the learning data in FIG. 11 in that it does not include the created or edited element ID 430. The learning data in FIG. 15 can be configured independently of the learning data in FIG. 11 by, for example, (1) deleting the element ID 430 from the learning data in FIG. 11 , (2) generating the learning data based on the editing history data in FIG. 10 but using a different generation method than the learning data in FIG. 11 , or (3) using data other than the editing history data in FIG. 10 . The evaluation value 454 is calculated based on the number of edited items required to edit the edit element, as in the second embodiment. A higher evaluation value 454 indicates an element order that is more likely to be selected by the user with user ID 452.

[0183] [Trained model generation process] In the trained model generation process, steps S200 to S204 are performed, and a third trained model is generated by performing training based on the training data in Fig. 15, similar to the generation of the trained model in the first embodiment. The third trained model is trained based on the element order information 450, the user ID 452, and the evaluation value 454 so as to maximize the evaluation value 454.

[0184] Then, the process proceeds to step S206, where the third trained model generated in step S204 is stored in the storage device 42, and the series of processes ends.

[0185] [Element order information estimation process] FIG. 16 is a flowchart showing the element order information estimation process.

[0186] The element order information estimation process is a process that is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S380 as shown in FIG.

[0187] In step S380, index information regarding the first index "editing time" or the second index "number of edited items", which indicate an index of the value of the evaluation value, is obtained, and the process proceeds to step S382, where if the index related to the obtained index information is the first index, the second trained model is selected, and if the index related to the obtained index information is the second index, the third trained model is selected.

[0188] Next, the process proceeds to step S384 to acquire the user ID of the target user, then proceeds to step S386 to acquire the created or edited element ID from the CAD data currently being edited, and then proceeds to step S388.

[0189] In step S388, a plurality of pieces of element order information are estimated from the element IDs acquired in step S386 using the first trained model in the storage device 42. The estimation method is the same as the process in step S364 in the third embodiment.

[0190] Next, the process proceeds to step S390, where the trained model selected in step S382 from the second trained model and the third trained model in the storage device 42 (hereinafter referred to as the "selected trained model") is used to estimate, from the multiple pieces of element order information estimated in step S388 and the user ID acquired in step S384, which of the pieces of element order information is suitable for the target user. The estimation method is the same as the processing in step S366 in the third embodiment described above.

[0191] Next, the process proceeds to step S392, where the element order is displayed on the display device 44 based on the element order information estimated in step S390, and the process proceeds to step S394, where it is determined whether editing by the target user has finished, and if it is determined that editing has finished (YES), the process ends.

[0192] On the other hand, if it is determined in step S394 that the editing by the target user has not finished (NO), the process proceeds to step S386.

[0193] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0194] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when the piano is delivered. However, changing the width of the toilet also requires editing other elements of the toilet. Therefore, after changing the width of the toilet, the designer requests estimation of the element order to be edited for the toilet. To obtain an element order that shortens the editing time, the designer selects "editing time" as the indicator. Then, steps S380 to S382 select the second trained model. Next, steps S384 to S388 acquire the created or edited element IDs and user IDs, and the first trained model estimates multiple element order information from the acquired element IDs. Then, steps S390 to S392 acquire the element order from the estimated multiple element order information and the acquired user ID, and the second trained model displays the element order.

[0195] On the other hand, if an element order that reduces the number of edit items is desired, the designer selects "number of edit items" as the index, and the third trained model is selected through steps S380 to S382. Then, through steps S390 to S392, the third trained model estimates and displays the element order from the estimated multiple element order information and the acquired user ID.

[0196] [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 trained model or the third trained model is selected based on the acquired index information, multiple pieces of element order information and a user ID are acquired, and element order information suitable for the target user is estimated from the acquired multiple pieces of element order information and the user ID using the selected trained model.

[0197] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0198] In this embodiment, step S380 corresponds to the index information acquisition means of invention 6, step S382 corresponds to the model selection means of invention 6, and step S390 corresponds to the estimation means of invention 6.

[0199] Fifth Embodiment Next, a fifth embodiment of the present invention will be described. Figures 17 to 20 show this embodiment. Figures 5 and 9 are also used.

[0200] This embodiment differs from the first embodiment in that a large language model is used. Only the differences from the first embodiment will be described below, and descriptions of overlapping parts will be omitted.

[0201] [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.

[0202] As shown in FIG. 17, the drawing creation support device 100 and a generation AI server 120 that generates answer information in response to a request using an AI (Artificial Intelligence) model are connected to the Internet 199 so as to be able to communicate with each other.

[0203] [Generation AI Server 120] Next, the configuration of the generation AI server 120 will be described. Like the drawing creation support device 100, 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 connected by a bus, and is configured as, for example, a cloud server.

[0204] FIG. 18 is a functional block diagram of the generation AI server 120. As shown in Figure 18, the generation AI server 120 is configured to have multiple AI models 50, an AI model control unit 52 that controls the AI ​​models 50, and a knowledge base 54 that registers data that the AI ​​models 50 refer to for inference.

[0205] The AI ​​model 50 is an AI model trained on a large data set and is a highly versatile model capable of performing a variety of tasks. For example, a large-scale language model can be used as the AI ​​model 50. A large-scale language model is a deep learning model that pre-trains a language model, which models human-spoken language based on its occurrence probability, from a massive amount of data. When a prompt is input, the large-scale language model statistically infers the probability of generating the next word from the sentence included in the input prompt and outputs the inference result. For example, publicly known technologies described on the internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be used as the large-scale language model. 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, and Stable Diffusion XL can be adopted.

[0206] The AI ​​model control unit 52 selects one of the multiple AI models 50 to be used for inference in response to a selection request from the request processing unit 58. Furthermore, when a reference request is input from the request processing unit 58, the AI ​​model control unit 52 causes the selected AI model 50 (hereinafter referred to as the "selected AI model") to refer to the data in the knowledge base 54 in response to the input reference request. Furthermore, 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, the AI ​​model control unit 52 causes the selected AI model to execute inference in response to the input execution request, obtains an inference result from the selected AI model, and outputs the obtained inference result to the request processing unit 58.

[0207] Learning data can be registered in the knowledge base 54. Information registered in the knowledge base 54 is in a data format (for example, vector data) that can be referenced by the AI ​​model 50.

[0208] The generation AI server 120 is further configured to include a request receiving unit 56 that receives requests, a request processing unit 58 that processes the requests received by the request receiving unit 56, and an answer information sending unit 60 that sends answer information to the request received by the request receiving unit 56 to the drawing creation support device 100.

[0209] The request receiving unit 56 receives a request for generating answer information from the drawing creation support device 100 and outputs the received request to the request processing unit 58. The request includes (1) an element ID that has already been created or edited, (2) a user ID, (3) a generation request to generate multiple edit elements to be edited consecutively after the edit element that has already been created or edited and element order information regarding the edit order (element order information suitable for the target user), (4) a selection request to select an AI model 50, and (5) a reference request to reference learning data in the knowledge base 54. (4) and (5) are not essential and are included additionally.

[0210] When the request received by the request receiving unit 56 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. Furthermore, based on the request received by the request receiving unit 56, the request processing unit 58 generates a prompt that instructs the AI ​​model 50. The prompt, for example, requests the AI ​​model 50 to generate, based on the created or edited element ID and the user ID, multiple edited elements to be edited consecutively after the created or edited edited element and element order information regarding the edit order (element order information suitable for the target user), which has an evaluation value equal to or greater than a predetermined value. The generated prompt and execution request are then output to the AI ​​model control unit 52. When an inference result is input from the AI ​​model control unit 52 in response to the execution request, the request processing unit 58 outputs the input inference result to the answer information sending unit 60.

[0211] The answer information sending unit 60 sends the answer information including the inference result input from the request processing unit 58 to the drawing creation support device 100.

[0212] The generation AI server 120 further includes a request receiving unit 62 that receives requests, and a learning data registration unit 64 that registers learning data in the knowledge base 54.

[0213] The request receiving unit 62 receives a request for registering learning data from the drawing production support device 100, and outputs the received request to the learning data registration unit 64. The request includes (1) learning data.

[0214] The learning data registration unit 64 stores the learning data included in the request received by the request receiving unit 62 in storage (not shown) and converts it into a data format (e.g., vector data) that can be referenced by the AI ​​model 50. Vector data can be generated by a technique (embedding) that converts data including characters, images, audio, etc. into a numerical vector. The converted learning data is then registered in the knowledge base 54. In response to a reference request from the request processing unit 58, the AI ​​model control unit 52 causes the selected AI model to reference the learning data.

[0215] [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.

[0216] The learning data registration process is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S400 as shown in FIG.

[0217] In step S400, the learning data of FIG. 5 is acquired from the storage device 42, and the process proceeds to step S402.

[0218] In step S402, a request for registering the learning data is sent to the generation AI server 120. The request includes (1) the learning data acquired in step S400.

[0219] 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.

[0220] The element order information acquisition process is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S500 as shown in FIG.

[0221] 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 currently being edited, and the process proceeds to step S504.

[0222] In step S504, a request for generating answer information based on the element ID and user ID acquired in steps S500 and S502 is 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) a generation request to generate multiple element order information regarding multiple edit elements to be edited consecutively after an edit element that has already been created or edited and their edit order (element order information suitable for the target user), where the edit elements or edit orders are different, (4) a selection request to select a specific AI model 50, and (5) a reference request to reference learning data in the knowledge base 54.

[0223] Next, the process proceeds to step S506, where answer information is received from the generation AI server 120, and the process proceeds to step S508, where, similar to the processing of step S306, one of the multiple element orders is displayed on the display device 44 based on the multiple element order information contained in the received answer information, and the process proceeds to step S510.

[0224] In step S510, if the target user creates or edits an edit element based on the displayed element order, the created or edited element ID including the element ID of the edit element is obtained from the CAD data currently being edited, and the process proceeds to step S512.

[0225] In step S512, based on the element order displayed in steps S508 and S520 and the element ID obtained in step S510, it is determined whether the edited elements created or edited by the target user differ from the edited elements or edit order displayed in steps S508 and S520, and if it is determined that the edited result differs from the inference result (YES), proceed to step S514.

[0226] In step S514, similar to the process in step S312, the display rules used for display in steps S508 and S520 are changed, and the process proceeds to step S516.

[0227] In step S516, similar to the process in step S504, a request for generating answer information based on the element ID and user ID acquired in steps S500 and S510 is sent to the generation AI server 120, and the process proceeds to step S518.

[0228] In step S518, similar to the processing in step S506, answer information is received from the generation AI server 120, and the process proceeds to step S520, where, similar to the processing in step S306, one of multiple element orders is displayed on the display device 44 based on the multiple element order information contained in the received answer information, and the process proceeds to step S522.

[0229] In step S522, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0230] On the other hand, if it is determined in step S522 that the editing by the target user has not finished (NO), the process proceeds to step S510.

[0231] On the other hand, if it is determined in step S512 that the edited result matches the inference result (NO), the process proceeds to step S516.

[0232] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0233] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent interference between the piano and the toilet wall when bringing the piano in. However, changing the width of the toilet will require editing of other toilet elements as well. Therefore, after changing the width of the toilet, the designer requests inference of the element order to be edited for the toilet. Steps S500 to S508 are then performed to acquire created or edited element IDs and user IDs, and the element order is inferred and displayed from the acquired element IDs and user IDs. During the inference, the selection AI model references the learning data in the knowledge base 54. The method for displaying the element order is the same as in the first embodiment.

[0234] Then, when the designer creates or edits the edit element "toilet" based on the inferred and displayed element order, the next element order is inferred and displayed through steps S510 to S520. If the designer's editing result and the inferred result differ, the display rules are changed through step S514.

[0235] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, a request including a created or edited element ID and the user ID of the target user, and a generation request to generate 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 in response to the request is obtained.

[0236] This allows the user to grasp the multiple edited elements that are edited consecutively and the order in which they are edited. The inferred element order information is suitable for the target user and is therefore suitable for the target user.

[0237] Furthermore, in this embodiment, a request including a generation request to generate multiple pieces of element order information with different editing elements or editing orders is input to the AI ​​model 50, and multiple pieces of element order information output from the AI ​​model 50 are obtained in response to the request, and one of the multiple element orders is displayed based on the obtained multiple pieces of element order information.

[0238] This makes it possible to grasp a plurality of edit elements to be edited successively and a plurality of candidates for the order of editing.

[0239] Furthermore, in this embodiment, learning data including the ID of an element that has already been created or edited, multiple edited elements that have been edited consecutively after that edited element and element order information regarding the order of editing, the user ID of the editing user, and evaluation values ​​regarding the editing of the multiple edited elements is registered in the knowledge base 54, and in response to a request, the learning data in the knowledge base 54 is referenced to obtain multiple element order information output from the AI ​​model 50.

[0240] This allows the order of elements with high evaluation values ​​to be understood. Furthermore, in this embodiment, created or edited element IDs including the element IDs of edited elements created or edited by the target user are obtained based on the displayed element order, and a request including the obtained element IDs and user ID and a generation request to generate element order information suitable for the target user is input to the AI ​​model 50, and element order information output from the AI ​​model 50 in response to the request is obtained.

[0241] This allows the user to understand the order of elements that are edited consecutively and their order of editing, since the order of elements is inferred and displayed for the results of creation or editing based on the displayed order of elements. The inferred order of elements is suitable for the target user, and is therefore suitable for the target user.

[0242] Furthermore, in this embodiment, created or edited element IDs including the element IDs of edited elements created or edited by the target user are obtained based on the displayed element order, and a request including the obtained element ID and user ID and a generation request to generate multiple element order information with different edit elements or edit orders is input to the AI ​​model 50, and multiple element order information output from the AI ​​model 50 is obtained in response to the request, and one of the multiple element orders is displayed based on the obtained multiple element order information.

[0243] As a result, a plurality of element orders are inferred and displayed for the results of creation or editing based on the displayed element order, so that a plurality of candidates for the plurality of editing elements to be edited successively and the editing order can be grasped.

[0244] Sixth Embodiment Next, a sixth embodiment of the present invention will be described. Fig. 21 shows this embodiment. In addition, Fig. 5, Fig. 9, Fig. 11 and Fig. 19 are also used.

[0245] This embodiment differs from the second and fifth embodiments in that the AI ​​model 50 refers to first learning data including evaluation values ​​based on the first index or second learning data including evaluation values ​​based on the second index. Only the differences from the second and fifth embodiments will be described below, and overlapping portions will not be described.

[0246] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data registration process] In the learning data registration process, steps S400 to S402 are performed to obtain the learning data of Figure 5 and the learning data of Figure 11 from the storage device 42, and a request for registration of the learning data is sent to the generation AI server 120. The request includes (1) the learning data of Figure 5 as the first learning data, and (2) the learning data of Figure 11 as the second learning data.

[0247] [Element order information acquisition process] FIG. 21 is a flowchart showing the element order information acquisition process.

[0248] The element order information acquisition process is executed in response to a request from a target user, and when executed by the CPU 30, the process first proceeds to step S530 as shown in FIG.

[0249] In step S530, index information regarding the first index "editing time" or the second index "number of edited items", which indicate an index of the value of the evaluation value, is obtained, and the process proceeds to step S532 to obtain the user ID of the target user, and the process proceeds to step S534 to obtain the element IDs that have been created or edited from the CAD data currently being edited, and the process proceeds to step S536.

[0250] In step S536, a request for generating answer information is sent to the generation AI server 120 based on the index information, element ID, and user ID acquired in steps S530, S532, and S534. The request includes (1) the element ID acquired in step S534, (2) the user ID acquired in step S532, (3) element order information (element order information suitable for the target user) relating to multiple edited elements to be edited consecutively after the edited element that has already been created or edited, and the order in which they are edited, where the multiple edited elements or edit orders are different, (4) a selection request for selecting a predetermined AI model 50, and (5) a reference request for referencing first learning data in the knowledge base 54 if the index related to the index information acquired in step S530 is the first index, or a reference request for referencing second learning data in the knowledge base 54 if the index related to the index information acquired in step S530 is the second index.

[0251] Next, the process proceeds to step S538, where answer information is received from the generation AI server 120, and the process proceeds to step S540, where, similar to the processing of step S306, one of the multiple element orders is displayed on the display device 44 based on the multiple element order information contained in the received answer information, and the process proceeds to step S542.

[0252] In step S542, if the target user creates or edits an edit element based on the displayed element order, the created or edited element ID including the element ID of the edit element is obtained from the CAD data currently being edited, and the process proceeds to step S544.

[0253] In step S544, based on the element order displayed in steps S540 and S552 and the element ID acquired in step S542, it is determined whether the edited elements created or edited by the target user differ from the edited elements or edit order displayed in steps S540 and S552, and if it is determined that the edited result differs from the inference result (YES), the process proceeds to step S546.

[0254] In step S546, similar to the process in step S312, the display rules used for display in steps S540 and S552 are changed, and the process proceeds to step S548.

[0255] In step S548, similar to the processing in step S536, a request to generate answer information based on the index information, element ID, and user ID obtained in steps S530, S532, and S542 is sent to the generation AI server 120, and the process proceeds to step S550.

[0256] In step S550, similar to the processing in step S538, answer information is received from the generation AI server 120, and the process proceeds to step S552, where, similar to the processing in step S306, one of multiple element orders is displayed on the display device 44 based on the multiple element order information contained in the received answer information, and the process proceeds to step S554.

[0257] In step S554, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0258] On the other hand, if it is determined in step S554 that the editing by the target user has not finished (NO), the process proceeds to step S542.

[0259] On the other hand, if it is determined in step S544 that the edited result matches the inference result (NO), the process proceeds to step S548.

[0260] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0261] If a designer wants to install a piano with a width of 120 mm in the plan view of Figure 9 in CAD software, he or she needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when bringing the piano in. However, changing the width of the toilet will require editing of other elements of the toilet as well. Therefore, after changing the width of the toilet, the designer requests inference of the element order to be edited for the toilet. To obtain an element order that shortens the editing time, the designer selects "editing time" as the indicator. Then, through steps S530 to S540, the created or edited element IDs and user IDs are acquired, and the element order is inferred and displayed from the acquired element IDs and user IDs. During inference, the selection AI model references the first learning data in the knowledge base 54.

[0262] On the other hand, if an element order that reduces the number of edit items is desired, the designer selects "number of edit items" as the index, and steps S530 to S540 are performed to acquire created or edited element IDs and user IDs, and the element order is inferred and displayed from the acquired element IDs and user IDs. In the inference, the selected AI model refers to the second learning data in the knowledge base 54.

[0263] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, first learning data including an evaluation value based on the first index and second learning data including an evaluation value based on the second index are registered in the knowledge base 54, index information regarding the first index or the second index is obtained, and a request including a request to refer to either the first learning data or the second learning data in the knowledge base 54 based on the obtained index information is input to the AI ​​model 50.

[0264] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0265] Seventh Embodiment Next, a seventh embodiment of the present invention will be described. Fig. 22 shows this embodiment. Figs. 9, 13 and 19 are also used.

[0266] This embodiment differs from the fifth embodiment in that the AI ​​model 50 generates element order information suitable for the target user from a plurality of pieces of element order information acquired from the AI ​​model 50. Only the differences from the fifth embodiment will be described below, and explanations of overlapping parts will be omitted.

[0267] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data registration process] In the training data registration process, steps S400 to S402 are performed to acquire the general-purpose training data in the third embodiment and the training data of FIG. 13 from the storage device 42, and a request for registration of the training data is sent to the generation AI server 120. The request includes (1) the general-purpose training data as the first training data and (2) the training data of FIG. 13 as the second training data.

[0268] [Element order information acquisition process] FIG. 22 is a flowchart showing the element order information acquisition process.

[0269] The element order information acquisition process is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S560 as shown in FIG.

[0270] 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 ID is acquired from the CAD data currently being edited, and the process proceeds to step S564.

[0271] In step S564, a request for generating answer information based on the element ID acquired in step S562 is sent to the generation AI server 120. The request includes (1) the element ID acquired in step S562, (2) a generation request to generate element order information relating to multiple edited elements to be edited consecutively after an edited element that has already been created or edited and their edit order, where the edited elements or edit orders are different, (3) a selection request to select a predetermined AI model 50, and (4) a reference request to reference the first learning data in the knowledge base 54.

[0272] Next, the process proceeds to step S566, where answer information is received from the generation AI server 120, and the process proceeds to step S568.

[0273] In step S568, a request for generating answer information is sent to the generation AI server 120 based on the multiple element order information included in the answer information received in step S566 and the user ID acquired in step S560. The request includes (1) the multiple element order information included in the answer information received in step S566, (2) the user ID acquired in step S560, (3) a generation request to select or generate element order information suitable for the target user, (4) a selection request to select a predetermined AI model 50, and (5) a reference request to reference the second learning data in the knowledge base 54.

[0274] Next, proceed to step S570 to receive answer information from the generation AI server 120, proceed to step S572 to display the element order on the display device 44 based on the element order information contained in the received answer information, and proceed to step S574.

[0275] In step S574, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0276] On the other hand, if it is determined in step S574 that the editing by the target user has not finished (NO), the process proceeds to step S562.

[0277] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0278] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when the piano is delivered. However, changing the width of the toilet also requires editing other elements of the toilet. Therefore, after changing the width of the toilet, the designer requests inference of the element order to be edited for the toilet. In steps S560 to S566, created or edited element IDs and user IDs are acquired, and multiple element order information is inferred from the acquired element IDs. In the inference, the selection AI model references the first learning data in the knowledge base 54. Then, in steps S568 to S572, the element order is inferred and displayed from the inferred multiple element order information and the acquired user ID. That is, in steps S564 and S566, multiple candidate element orders are inferred, and in steps S568 and S570, the candidates are narrowed down to those suitable for the target user.

[0279] Then, when the designer creates or edits the edit element "toilet bowl" based on the element order that has been inferred and displayed, the next element order is inferred and displayed through steps S562 to S572.

[0280] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, a request including a plurality of element order information and the user ID of the target user, and including a generation request to select or generate 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 in response to the request is obtained.

[0281] This allows the user to grasp the multiple edited elements that are edited consecutively and the order in which they are edited. The inferred element order information is suitable for the target user and is therefore suitable for the target user.

[0282] Eighth Embodiment Next, an eighth embodiment of the present invention will be described. Fig. 23 shows this embodiment. In addition, Figs. 9, 13, 15 and 19 are also used.

[0283] This embodiment differs from the seventh embodiment in that the AI ​​model 50 refers to second learning data including an evaluation value based on the first index or third learning data including an evaluation value based on the second index. Only the differences from the seventh embodiment will be described below, and overlapping portions will not be described.

[0284] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data registration process] In the training data registration process, steps S400 to S402 are performed to acquire the general-purpose training data in the third embodiment, the training data in FIG. 13, and the training data in FIG. 15 from the storage device 42, and a request for registration of the training data is sent to the generation AI server 120. The request includes (1) the general-purpose training data as the first training data, (2) the training data in FIG. 13 as the second training data, and (3) the training data in FIG. 15 as the third training data.

[0285] [Element order information acquisition process] FIG. 23 is a flowchart showing the element order information acquisition process.

[0286] The element order information acquisition process is executed in response to a request from a target user, and when executed by CPU 30, first, the process proceeds to step S580 as shown in FIG.

[0287] In step S580, index information regarding the first index "editing time" or the second index "number of edited items", which indicate an index of the value of the evaluation value, is obtained, and the process proceeds to step S582 to obtain the user ID of the target user, and the process proceeds to step S584 to obtain the element IDs that have been created or edited from the CAD data currently being edited, and the process proceeds to step S586.

[0288] In step S586, a request for generating answer information based on the element ID acquired in step S584 is sent to the generation AI server 120. The request includes (1) the element ID acquired in step S584, (2) a generation request to generate element order information relating to multiple edited elements to be edited consecutively after an edited element that has already been created or edited and their edit order, where the edited elements or edit orders are different, (3) a selection request to select a predetermined AI model 50, and (4) a reference request to reference the first learning data in the knowledge base 54.

[0289] Next, the process proceeds to step S588, where answer information is received from the generation AI server 120, and the process proceeds to step S590.

[0290] In step S590, a request for generating answer information is sent to the generation AI server 120 based on the multiple pieces of element order information included in the answer information received in step S588 and the user ID acquired in step S582. The request includes (1) the multiple pieces of element order information included in the answer information received in step S588, (2) the user ID acquired in step S582, (3) a generation request to select or generate element order information suitable for the target user, (4) a selection request to select a predetermined AI model 50, and (5) a reference request to reference second learning data in the knowledge base 54 if the index related to the index information acquired in step S580 is the first index, or a reference request to reference third learning data in the knowledge base 54 if the index related to the index information acquired in step S580 is the second index.

[0291] Next, proceed to step S592 to receive answer information from the generation AI server 120, proceed to step S594 to display the element order on the display device 44 based on the element order information contained in the received answer information, and proceed to step S596.

[0292] In step S596, it is determined whether or not the editing by the target user has finished, and if it is determined that the editing has finished (YES), the series of processes is ended.

[0293] On the other hand, if it is determined in step S596 that the editing by the target user has not finished (NO), the process proceeds to step S584.

[0294] [When considering bringing in a piano] Next, the operation when a piano is brought in will be described.

[0295] If a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the designer needs to shorten the width of the toilet to prevent the piano from interfering with the toilet wall when the piano is delivered. However, changing the width of the toilet also requires editing other elements of the toilet. Therefore, the designer requests inference of the element order to be edited for the toilet after changing the width of the toilet. To obtain an element order that shortens the editing time, the designer selects "editing time" as an indicator. Then, through steps S580 to S588, created or edited element IDs and user IDs are acquired, and multiple pieces of element order information are inferred from the acquired element IDs. In the inference, the selection AI model references the first learning data in the knowledge base 54. Then, through steps S590 to S592, the element order is inferred and displayed based on the inferred multiple pieces of element order information and the acquired user ID. In the inference, the selection AI model references the second learning data in the knowledge base 54.

[0296] On the other hand, if an element order that reduces the number of edit items is desired, the designer selects "number of edit items" as an index, and the element order is inferred and displayed from the inferred multiple element order information and the acquired user ID through steps S580 to S592. In the inference, the selected AI model refers to the third learning data in the knowledge base 54.

[0297] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, second learning data including an evaluation value based on the first index and third learning data including an evaluation value based on the second index are registered in the knowledge base 54, index information regarding the first index or the second index is obtained, and a request including a request to refer to either the second learning data or the third learning data in the knowledge base 54 based on the obtained index information is input to the AI ​​model 50.

[0298] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0299] [Modification] In the first and second embodiments and their modifications, a plurality of pieces of element order information are estimated in steps S304 and S338, but the present invention is not limited to this and it is also possible to estimate one piece of element order information.

[0300] Furthermore, in the above fifth and sixth embodiments and their variations, in steps S504 and S536, a generation request for generating multiple pieces of element order information is included in the request, but this is not limited to this, and a generation request for generating one piece of element order information can also be included in the request.

[0301] Furthermore, in the third and fourth embodiments and their variations, the first trained model is generated based on general-purpose training data. However, the first trained model can be generated based on general-purpose training data obtained by deleting the user ID 434 from the training data of FIG. 11, the training data of FIG. 5, or the training data of FIG. 11.

[0302] Furthermore, in the seventh and eighth embodiments and their variations, the AI ​​model 50 references the general-purpose learning data in response to the request in step S586. However, this is not limited to this. Alternatively, it may reference (1) the general-purpose learning data in which the user ID 434 has been deleted from the learning data of FIG. 11, the learning data of FIG. 5, or the learning data of FIG. 11, or (2) the learning data is not referenced.

[0303] Furthermore, in the above third and fourth embodiments and their variations, multiple pieces of element order information are obtained from the first trained model, but this is not limited to this, and multiple pieces of element order information can be obtained from the memory device 42 or any other device, any node, or any process.

[0304] Furthermore, in the above seventh and eighth embodiments and their variations, multiple element order information was obtained from the generation AI server 120, but this is not limited to this, and multiple element order information can be obtained from the memory device 42 or any other device, any node, or any process.

[0305] Furthermore, in the above fourth embodiment and its variant, in step S388, multiple pieces of element order information are estimated from the element ID using the first trained model in the storage device 42, but this is not limited to this, and the following configuration can also be adopted.

[0306] First general-purpose learning data is prepared by deleting the user ID 414 from the learning data of FIG. 5, and second general-purpose learning data is prepared by deleting the user ID 434 from the learning data of FIG.

[0307] In steps S200 to S204, a first trained model is generated by training based on the first general-purpose training data, and a fourth trained model is generated by training based on the second general-purpose training data.

[0308] Then, in step S388, if the index related to the index information acquired in step S380 is the first index, a first trained model is selected, and if the index related to the index information acquired in step S380 is the second index, a fourth trained model is selected, and multiple element order information is estimated from the element ID using the selected trained model.

[0309] Furthermore, in the eighth embodiment and its variants, the AI ​​model 50 is made to refer to the first learning data in the knowledge base 54 in response to the request in step S586, but this is not limited to this, and the following configuration can also be adopted.

[0310] First general-purpose learning data is prepared by deleting the user ID 414 from the learning data of FIG. 5, and second general-purpose learning data is prepared by deleting the user ID 434 from the learning data of FIG.

[0311] In steps S400 to S402, the first general-purpose learning data, the second general-purpose learning data, the learning data of Figure 13, and the learning data of Figure 15 are obtained from the storage device 42, and a request for registering the learning data is sent to the generation AI server 120. The request includes (1) the first general-purpose learning data as the first learning data, (2) the learning data of Figure 13 as the second learning data, (3) the learning data of Figure 15 as the third learning data, and (4) the second general-purpose learning data as the fourth learning data.

[0312] Then, in step S586, a request for generating answer information based on the element ID is sent to the generation AI server 120. The request includes (1) the element ID, (2) a generation request to generate multiple pieces of element order information, (3) a request to select an AI model 50, and (4) a reference request to reference the first learning data in the knowledge base 54 if the index related to the index information acquired in step S580 is the first index, or a reference request to reference the fourth learning data in the knowledge base 54 if the index related to the index information acquired in step S580 is the second index.

[0313] Furthermore, in the first, second, fifth and sixth embodiments and their variations, display rules 1 to 4 were adopted, but this is not limiting, and any other display rule can be adopted, for example, a display rule that displays the fewest number of editing elements, an element order above a predetermined number, below a predetermined number, or a predetermined order.

[0314] Furthermore, in the above first, second, fifth and sixth embodiments and their variations, the element order is displayed according to one of a plurality of display rules, but this is not limited to this, and the element order can be displayed according to a predetermined display rule without providing a plurality of display rules.

[0315] Furthermore, in the first to eighth embodiments and their modifications, one element order is displayed, but the present invention is not limited to this and multiple element orders can be displayed.

[0316] Furthermore, in the first, second, fifth and sixth embodiments and their modifications, the display rules are changed, but the present invention is not limited to this, and a configuration in which the display rules are not changed can also be adopted.

[0317] In addition, in the first to fourth embodiments and their modifications, estimation and display are repeated multiple times, but this is not limiting, and a configuration in which estimation and display are performed only once can be adopted. The same applies to the fifth to eighth embodiments and their modifications.

[0318] Furthermore, in the above first to fourth embodiments and their variations, reinforcement learning is adopted as the learning method, but this is not limited to this, and any learning method such as supervised learning, semi-supervised learning, unsupervised learning, deep learning, or the like can be adopted.

[0319] Furthermore, in the above first to eighth embodiments and their modifications, the learning data includes a user ID and an evaluation value, but this is not limited to this, and the learning data may be configured without including either or both of the user ID and the evaluation value.

[0320] In the first to eighth embodiments and their modifications, the edit history data and the learning data include the user ID, but are not limited to this and may include identification information other than the user ID, or feature information related to the user's profile, statistics, or other features. The same applies to the element ID.

[0321] Furthermore, in the second embodiment and its modified example, the first trained model and the second trained model can be configured as one trained model.

[0322] Furthermore, in the above-described fourth embodiment and its variant examples, the second trained model and the third trained model can be configured as one trained model, and the first trained model and the fourth trained model can be configured as one trained model.

[0323] In the fifth to eighth embodiments and their modifications, the AI ​​model 50 can be configured as the trained model in the first to fourth embodiments and their modifications.

[0324] Furthermore, in the first, second, fifth and sixth embodiments and their modifications, an element order that appears a predetermined number of times or more in the learning data is identified. However, this is not limited to this, and an element order that appears a predetermined number of times or more in the editing history data can also be identified.

[0325] Furthermore, in the first to eighth embodiments and their modifications, a maximum of four editing elements and their editing orders are handled, but this is not limiting, and five or more editing elements and their editing orders can be handled. There is no need to limit the number of editing elements as long as there are multiple editing elements. Furthermore, the number of editing elements can be set independently for each of the learning data in Figures 5, 11, 13, and 15.

[0326] Furthermore, in the above-described first to eighth embodiments and their modifications, all combinations of element orders with two to four edited elements are obtained from the edit history data to generate learning data, but this is not limiting. It is also possible to obtain element orders that appear a predetermined number of times or more in the edit history data from the edit history data to generate learning data. In this case, an element order with a high frequency of appearance may be estimated using a trained model trained on multiple edit history data. This allows the element order with a high frequency of appearance in the edit history data to be learned or inferred.

[0327] Furthermore, in the first to eighth embodiments and their modifications, the edit history data is configured as data separate from the CAD data, but this is not limiting, and the edit history data can be configured as an integral part of the CAD data.

[0328] Furthermore, in the fifth to eighth embodiments and their modifications, the AI ​​model 50 is made to refer to the learning data in the knowledge base 54, but this is not limiting, and the learning data to be referred to in the knowledge base 54 can be included in the request. This makes it possible to apply the present invention to a configuration that does not include the knowledge base 54. Specifically, for example, the following configuration can be adopted.

[0329] [Invention A1] An element information acquisition means for acquiring element information relating to created or edited elements in design information; user information acquisition means for acquiring user information relating to 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, and the element order information relating to a plurality of elements to be edited successively after the element related to the element information and the order of editing the plurality of elements (hereinafter, in Inventions A1 to A3, "a plurality of elements and the order of editing the plurality of elements" will be referred to as "element order"); an 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 about an element that has been created or edited, element order information about the order of elements that have been edited next to the element, and user information about the user who edited the multiple elements.

[0330] This allows the user to grasp the plurality of elements that are edited consecutively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0331] [Invention A2] In Invention A1, The request includes the element information, element order information regarding the element order, the user information, and reference information including an evaluation value regarding editing of the plurality of elements.

[0332] This allows the order of elements with high evaluation values ​​to be understood. The following describes embodiments of inventions A1 and A2 as variations of the fifth embodiment. In step S504, a request for generating answer information is 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) a generation request for generating a plurality of element order information related to multiple edited elements to be edited consecutively after an edited element that has already been created or edited and the order of the edited elements (element order information suitable for the target user), where the edited elements or the order of the edited elements are different, (4) a selection request for selecting a predetermined AI model 50, and (5) the learning data acquired in step S400.

[0333] [Invention A3] In Invention A2, 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 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.

[0334] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0335] An embodiment of invention A3 will be described as a variation of the sixth embodiment. In step S536, a request for generating answer information is sent to the generation AI server 120. The request includes: (1) the element ID acquired in step S534; (2) the user ID acquired in step S532; (3) a generation request for generating a plurality of element order information pieces related to multiple edited elements to be edited consecutively after the edited element that has already been created or edited and the order of the edited elements (element order information suitable for the target user), where the edited elements or the order of the edited elements are different; (4) a selection request for selecting a predetermined AI model 50; and (5) the second learning data acquired in step S400 if the index related to the index information acquired in step S530 is the first index; or the third learning data acquired in step S400 if the index related to the index information acquired in step S530 is the second index.

[0336] [Invention A4] An element order information acquisition means for acquiring element order information relating to a plurality of elements that have been edited consecutively and their edit order (hereinafter, in Inventions A4 to A6, "a plurality of elements and their edit order" will be referred to as "element order"), the element order information being different in elements or edit order; user information acquisition means for acquiring user information relating to a target user; an input means for inputting a request to an AI model, the 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, and a request to generate one of the plurality of pieces of element order information that is suitable for the target user; an acquisition means for acquiring the element order information output from the AI ​​model in response to the request, The request includes element order information regarding the element order and reference information including user information regarding the user who edited the plurality of elements.

[0337] This allows the user to grasp the plurality of elements that are edited consecutively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0338] [Invention A5] In Invention A4, 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.

[0339] This allows the order of elements with high evaluation values ​​to be understood. As a modification of the seventh embodiment, embodiments A4 and A5 will be described. In step S568, a request for generating answer information is sent to the generation AI server 120. The request includes (1) multiple pieces of element order information included in the answer information received in step S566, (2) the user ID acquired in step S560, (3) a generation request to select or generate element order information suitable for the target user, (4) a selection request to select a predetermined AI model 50, and (5) the second learning data acquired in step S400.

[0340] [Invention A6] In Invention A5, 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 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 order information, 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.

[0341] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0342] An embodiment of invention A3 will be described as a variation of the eighth embodiment. In step S590, a request for generating answer information is sent to the generation AI server 120. The request includes (1) multiple pieces of element order information included in the answer information received in step S588, (2) the user ID acquired in step S582, (3) a generation request to select or generate element order information suitable for the target user, (4) a selection request to select a predetermined AI model 50, and (5) the second learning data acquired in step S400 if the index related to the index information acquired in step S580 is the first index, or the third learning data acquired in step S400 if the index related to the index information acquired in step S580 is the second index.

[0343] [Invention A7] In Invention A1, A2, A4 or A5, The plurality of elements are elements that require human judgment to set or change, and the setting or change affects other elements.

[0344] [Invention A8] In Inventions A1 to A3, The design information is information for designing a building.

[0345] Furthermore, in the fifth to eighth embodiments and their modifications, the AI ​​model 50 references information in the knowledge base 54, but the present invention is not limited to this. Information to be referenced in the knowledge base 54 (for example, the learning data in FIG. 5 or FIG. 11) can be obtained by a web search or the like, and the search results can be referenced by the AI ​​model 50 to perform inference. This configuration can be realized, for example, by RAG (Retrieval Augmented Generation).

[0346] Furthermore, in the first to eighth embodiments and their modifications, the trained model or AI model 50 is used, but the present invention is not limited to this, and for example, the following configuration can be adopted.

[0347] [Invention B1] An element information acquisition means for acquiring element information relating to created or edited elements in design information; user information acquisition means for acquiring user information relating to a target user; The device is provided with a search means for searching, from a storage means for storing element order information relating to a plurality of elements to be edited successively after an element that has already been created or edited and the order in which they are edited (hereinafter, in Inventions B1 to B4, "a plurality of elements and the order in which they are edited" will be referred to as "element order") in association with the element information relating to the created or edited elements and user information relating to the user who edited the plurality of elements, 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.

[0348] This allows the user to grasp the plurality of elements that are edited consecutively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0349] [Invention B2] In Invention B1, the storage means stores element order information relating to the element order in association with the element information, the user information, and an evaluation value relating to 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 for the evaluation value being equal to or greater than a predetermined value.

[0350] This allows the order of elements with high evaluation values ​​to be understood. As modifications of the first embodiment, embodiments B1 and B2 will be described. Storage device 42 stores an element order information table having a data structure similar to that of the training data in Fig. 5. In step S304, the element order information table is searched for a plurality of pieces of element order information corresponding to the element IDs and user IDs acquired in steps S300 and S302, and having evaluation values ​​equal to or greater than a predetermined value. In step S314, the element order information table is searched for a plurality of pieces of element order information corresponding to the element IDs and user IDs acquired in steps S300 and S308, and having evaluation values ​​equal to or greater than a predetermined value.

[0351] [Invention B3] In Invention B2, the storage means includes a first storage means for storing the element order information in association with the element information, the user information, and the evaluation value based on a first index indicating an index of value of the evaluation value, and a second storage means for storing the element order information in association with the element information, the user information, and the evaluation value based on a second index different from the first index; index information acquisition means for acquiring index information relating to the first index or the second index; a 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.

[0352] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0353] An embodiment of Invention B3 will be described as a variation of the second embodiment. The storage device 42 stores a first element order information table having a data structure similar to that of the learning data in FIG. 5 and a second element order information table having a data structure similar to that of 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. If the index related to the acquired index information is the second index, the second element order information table is selected. In step S338, the element order information table selected in step S332 is searched for multiple pieces of element order information corresponding to the element IDs and user IDs acquired in steps S334 and S336 and having evaluation values ​​equal to or greater than a predetermined value. In step S348, the element order information table selected in step S332 is searched for multiple pieces of element order information corresponding to the element IDs and user IDs acquired in steps S334 and S342 and having evaluation values ​​equal to or greater than a predetermined value.

[0354] [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 relating to a first index indicating an index of value of the evaluation value or a second index different from the first index; index information acquisition means for acquiring index information relating to 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.

[0355] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0356] An embodiment of Invention B4 will be described as a variation of the second embodiment. The storage device 42 stores an element order information table in which, for each row, created or edited element IDs 430, element order information 432, user IDs 434, evaluation values ​​436, and index information related to the first or second index are registered. In step S338, the element order information table is searched for a plurality of pieces of element order information corresponding to the element IDs, user IDs, and index information acquired in steps S330, S334, and S336, and having an evaluation value equal to or greater than a predetermined value. In step S348, the element order information table is searched for a plurality of pieces of element order information corresponding to the element IDs, user IDs, and index information acquired in steps S330, S334, and S342, and having an evaluation value equal to or greater than a predetermined value.

[0357] [Invention B5] An element order information acquisition means for acquiring element order information relating to a plurality of elements that have been edited consecutively and their edit order (hereinafter, in Inventions B5 to B8, "a plurality of elements and their edit order" will be referred to as "element order"), the element order information being different in elements or edit order; user information acquisition means for acquiring user information relating to a target user; The device is provided with a search means for searching, from a storage means for storing element order information relating to the element order in association with user information relating to the user who edited the plurality of elements, for the element order information corresponding to any one of the plurality of pieces of element order information acquired by the element order information acquisition means and the user information acquired by the user information acquisition means.

[0358] This allows the user to grasp the plurality of elements that are edited consecutively and the order in which they are edited. The estimated element order information is suitable for the target user and is therefore suitable for the target user.

[0359] [Invention B6] In Invention B5, the storage means stores element order information relating to the element order in association with the user information and an evaluation value relating to editing of the plurality of elements; The search means searches for element order information corresponding to any one of the plurality of pieces of element order information acquired by the element order information acquisition means and the user information acquired by the user information acquisition means, and having an evaluation value equal to or greater than a predetermined value.

[0360] This allows the order of elements with high evaluation values ​​to be understood. As modifications of the third embodiment, embodiments B5 and B6 will be described. The storage device 42 stores an element order information table having a data structure similar to that of the learning data shown in Fig. 13. In step S366, the element order information table is searched for element order information that corresponds to any one of the plurality of element order information estimated in step S364 and the user ID acquired in step S360 and has an evaluation value equal to or greater than a predetermined value.

[0361] [Invention B7] In Invention B6, the storage means includes a first storage means for storing the element order information in association with the user information and the evaluation value based on a first index indicating an index of value of the evaluation value, and a second storage means for storing the element order information in association with the user information and the evaluation value based on a second index different from the first index; index information acquisition means for acquiring index information relating to the first index or the second index; a 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.

[0362] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0363] An embodiment of Invention B7 will be described as a modification of the fourth embodiment. Storage device 42 stores a first element order information table having a data structure similar to that of the learning data in FIG. 13 and a second element order information table having a data structure similar to that of 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, element order information corresponding to any one of the plurality of element order information estimated in step S388 and the user ID acquired in step S384 and having an evaluation value equal to or greater than a predetermined value is searched for from the element order information table selected in step S382.

[0364] [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 relating to a first index indicating an index of value of the evaluation value or a second index different from the first index; index information acquisition means for acquiring index information relating to the first index or the second index; The search means searches for element order information corresponding to 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 index information acquired by the index information acquisition means.

[0365] This makes it possible to grasp the order of elements with high evaluation values ​​based on the first index or the second index.

[0366] An embodiment of Invention B8 will be described as a modification of the fourth embodiment. Storage device 42 stores an element order information table in which, for each row, element order information, a user ID, an evaluation value, and index information relating to the first index or the second index are registered. In step S390, the element order information table is searched for multiple pieces of element order information that correspond to any of the multiple pieces of element order information estimated in step S388 and the user ID and index information acquired in steps S380 and S384 and have an evaluation value equal to or greater than a predetermined value.

[0367] [Invention B9] In Invention B1, B2, B5 or B6, The plurality of elements are elements that require human judgment to set or change, and the setting or change affects other elements.

[0368] [Invention B10] In Invention B1, The design information is information for designing a building.

[0369] Furthermore, in inventions B1 to B10 and their variations, storing element order information in association with element information, etc. includes, for example, (1) storing element order information and element information, etc. in the same record in a direct association manner, or (2) storing element order information via one or more intermediate pieces of information, such as providing a table in which element order information and intermediate information are associated and registered, and another table in which element information, etc. and intermediate information are associated and registered. In other words, any data structure can be adopted as long as it is possible to trace element order information from element information, etc. Note that element order information may be stored in a storage means in association with element information, etc., and it is not necessarily required that element information, etc., be stored in the storage means.

[0370] Furthermore, in inventions B1 to B10 and their variations, the storage means stores the element order information by any means and at any time, and may store the element order information in advance, or may store the element order information by external input or the like during operation of the drawing creation support device 100 without storing the element order information in advance.

[0371] Furthermore, in the fifth to eighth embodiments and their variations, the prompt is, for example, a request to the AI ​​model 50 to generate, based on the created or edited element ID, a plurality of edited elements to be edited successively after the created or edited edited element and element order information relating to the edit order, which has an evaluation value of a predetermined value or more. However, the prompt is not limited to this, and the prompt can be a request to the AI ​​model 50 to generate a plurality of edited elements to be edited successively after the created or edited edited element and element order information relating to the edit order.

[0372] 5 or 11 is registered in the knowledge base 54 in the fifth to eighth embodiments and their modifications. However, the present invention is not limited to this. (1) Edit history data, (2) Reference information including element information on an element that has already been created or edited, and element order information on multiple elements to be edited in succession after the element and the order in which they are edited, or (3) Reference information including element information on an element that has already been created or edited, element order information on multiple elements to be edited in succession after the element and the order in which they are edited, and evaluation values ​​related to the editing of the multiple elements, may be registered in the knowledge base 54. The reference information of (2) or (3) may include element order information estimated using the trained model in the first to fourth embodiments and their modifications.

[0373] Furthermore, in the fifth to eighth embodiments and their modifications, vector data is registered in the knowledge base 54, but this is not limiting and data in any format can be registered.

[0374] Furthermore, in the first to eighth embodiments and their modifications, a configuration including any one of an estimation process using a trained model, an acquisition process from the AI ​​model 50, and a search process using a table is employed, but the present invention is not limited to this, and a configuration including two or more of these processes may be employed. Specifically, for example, the following configuration may be employed.

[0375] In the first configuration, the process of step S304 or the process of step S314 is performed by any one of estimation process, acquisition process, and search process. The process of step S314 from the second time onwards can be performed by the same or different process as the process of step S304 or the first time.

[0376] In the second configuration, the process of step S338 or the process of step S348 is performed by any one of estimation process, acquisition process, and search process. The process of step S348 from the second time onwards can be performed by the same or different process as the process of step S338 or the first time.

[0377] In the third configuration, the processing of steps S504 and S506 or the processing of steps S516 and S518 is performed by any of estimation processing, acquisition processing, and search processing. The second and subsequent processing of steps S516 and S518 can be performed by the same or different processing as the processing of steps S504 and S506 or the first processing of steps S516 and S518.

[0378] In the fourth configuration, the processing of steps S536 and S538 or the processing of steps S548 and S550 is performed by any of estimation processing, acquisition processing, and search processing. The second and subsequent processing of steps S548 and S550 can be performed by the same or different processing as the first processing of steps S536 and S538 or steps S548 and S550.

[0379] The fifth configuration is a configuration for controlling which process is given priority. For example, (1) a configuration for giving priority to a process with a low current load among multiple processes, (2) a configuration for giving priority to a process whose results have been adopted by the target user to a high degree (referring to the number of times, percentage, or other degree of adoption) among multiple processes, or (3) a configuration for giving priority to a process whose results have been used by the target user to a high degree (referring to the number of times, percentage, or other degree of use) among multiple processes can be adopted.

[0380] Furthermore, in the first to eighth embodiments and their modifications, multiple edit elements and their edit order are learned or inferred, but this is not limiting. The "multiple edit elements" to be learned or inferred can be edit element A, the setting or change of which requires human judgment, and the setting or change of which affects another edit element B. This makes it possible to grasp the element order taking into account the relationship between edit element A and edit element B. For edit elements that do not require human judgment, editing can be automated using the technology of Japanese Patent No. 7341580, for example. Therefore, by targeting edit elements that are difficult to automate, the editing work can be made more efficient.

[0381] In the first to fourth embodiments and their modifications, the device is implemented as a single device, but the present invention is not limited to this and can also be implemented as a network system. As an example of a network system, some 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.

[0382] Furthermore, in the above fifth to eighth embodiments and their variations, the generation AI server 120 is configured as an integrated unit that includes the functions of the AI ​​model 50, AI model control unit 52, knowledge base 54, request receiving unit 56, request processing unit 58, answer information sending unit 60, request receiving unit 62, and learning data registration unit 64, but this is not limited to this, and some functions can be configured on a separate server, etc.

[0383] Furthermore, in the fifth to eighth embodiments and their modifications, the system is realized as a network system, but the present invention is not limited to this and can be realized as a single device or application.

[0384] Furthermore, in the fifth to eighth embodiments and their modifications, the case where the present invention is applied to a network system consisting of the Internet 199 has been described, but the present invention is not limited to this, and may be applied to, for example, a so-called intranet that communicates in the same manner as the Internet 199. Of course, the present invention is not limited to a network that communicates in the same manner as the Internet 199, and may be applied to a network of any communication method.

[0385] Furthermore, in the above first to eighth embodiments and their variations, the drawing creation support device 100 is configured to use a storage device 42, but this is not limited to this, and it can also be configured to use an external storage device such as a database server.

[0386] Furthermore, in the above first to eighth embodiments and their variations, when executing the processes shown in the flowcharts of Figures 4, 6, 8, 12, 14, 16, and 19 to 23, we have described the case where a program pre-stored in ROM 32 is executed, but this is not limited to this, and the program showing these procedures may be read into RAM 34 from a storage medium on which the program is stored and executed.

[0387] Here, storage media refers to semiconductor storage media such as RAM and ROM, magnetic storage media such as FD and HD, optically readable storage media such as CD, CDV, LD and DVD, and magnetic storage / optically readable storage media such as MO, and includes all storage media that can be read by a computer, regardless of the reading method (electronic, magnetic, optical, etc.).

[0388] Moreover, the first to eighth embodiments and their modifications can be applied to each other. Furthermore, the present invention is not limited to the first to eighth embodiments and their modifications, but can also be applied to other cases without departing from the spirit of the present invention. For example, the present invention can be applied to a wide range of design cases, such as automobile design, machine design, and circuit design. [Explanation of symbols]

[0389] 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 receiving unit, 58...request processing unit, 60...answer information sending 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 edited 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 created or edited elements in the design information; user information acquisition means for acquiring user information relating to a target user; a means for estimating element order information suitable for a target user from the element information acquired by the element information acquisition means and the user information acquired by the user information acquisition means, using a trained model trained based on training data including element information on an element that has already been created or edited, element order information on multiple elements that have been edited in succession after the element and the order in which they are edited (hereinafter, "multiple elements and their edit order" will be referred to as "element order"), and user information on a user who edited the multiple elements.

2. In claim 1, A design support system characterized in that the trained model is trained to maximize the evaluation value based on learning data including the element information, element order information regarding the element order, the user information, and an evaluation value regarding editing of the plurality of elements.

3. In claim 2, The trained model includes: a first trained model trained to maximize an evaluation value based on training data including the element information, the element order information, the user information, and an evaluation value based on a first index indicating an index of value of the evaluation value; and a second trained model trained to maximize an evaluation value based on training data including the element information, the element order information, the user information, and an evaluation value based on a second index different from the first index, index information acquisition means for acquiring index information relating to the first index or the second index; a trained model selection means for selecting either the first trained model or the second trained model based on the index information acquired by the index information acquisition means; A design support system characterized in that the estimation means estimates the element order information using the trained model selected by the trained model selection means.

4. an element order information acquiring means for acquiring element order information relating to a plurality of elements that have been edited consecutively and their edit order (hereinafter, "a plurality of elements and their edit order" will be referred to as "element order"), the element order information being a plurality of pieces of element order information that are different in elements or edit order; user information acquisition means for acquiring user information relating to a target user; and an estimation means for estimating, using a trained model trained on the basis of training data including element order information regarding the element order and user information regarding the user who edited the plurality of elements, which of the plurality of pieces of element order information is suitable for the target user, from the plurality of pieces of element order information acquired by the element order information acquisition means and the user information acquired by the user information acquisition means.

5. In claim 4, A design support system characterized in that the trained model is trained to maximize the evaluation value based on learning data including element order information regarding the element order, the user information, and an evaluation value regarding editing of the plurality of elements.

6. In claim 5, The trained model includes: a first trained model trained to maximize an evaluation value based on training data including the element order information, the user information, and an evaluation value based on a first index indicating an index of value of the evaluation value; and a second trained model trained to maximize an evaluation value based on training data including the element order information, the user information, and an evaluation value based on a second index different from the first index, index information acquisition means for acquiring index information relating to the first index or the second index; a trained model selection means for selecting either the first trained model or the second trained model based on the index information acquired by the index information acquisition means; A design support system characterized in that the estimation means estimates the element order information using the trained model selected by the trained model selection means.

7. In any one of claims 1, 2, 4 and 5, A design support system characterized in that the plurality of elements are elements whose setting or change requires human judgment and whose setting or change has an effect on other elements.

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

9. an acquisition means for acquiring, from edit history data including a plurality of elements that have been edited consecutively and their edit order (hereinafter, "a plurality of elements and their edit order" will be referred to as "element order"), an element order that appears a predetermined number of times or more in the edit history data; a generation means for generating learning data including element order information regarding the element order acquired by the acquisition means and user information regarding the user who edited the plurality of elements.

10. A trained model generation system characterized by generating a trained model by performing training based on training data to which an evaluation value is assigned regarding the editing of a plurality of elements, for a combination of element information regarding an element that has been created or edited, element order information regarding multiple elements that have been edited consecutively after the element in question and the order in which they are edited (hereinafter, "multiple elements and their edit order" will be referred to as "element order"), and user information regarding the user who edited the multiple elements, so that the evaluation value is maximized.

Images