Design Support System

Abstract

A design support system is provided that is suitable for grasping a plurality of elements to be edited in succession and the order of editing. SOLUTION: A drawing creation support device 100 inputs a request including a created or edited element ID and a request to generate multiple edit elements edited in succession after the edit element and edit order information related to the edit order, and obtains information output from the AI ​​model 50 in response to the request. This makes it possible to obtain multiple edit elements edited in succession after a created or edited edit element and edit order information related to the edit order, thereby making it possible to grasp multiple edit elements that are edited in succession and their edit order.

Description

[Technical field]

[0001] The present invention relates to a design support system, and more particularly to a design support system suitable for grasping a plurality of elements to be edited in succession and the order of editing them. [Background technology]

[0002] 2. Description of the Related Art Conventionally, as a technique for supporting design using AI (Artificial Intelligence), for example, the technique described in Patent Document 1 is known.

[0003] The technology described in Patent Document 1 assigns a reward R to a 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] 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 in succession. For example, when designing a toilet, the toilet bowl and hand washing basin are designed in succession. However, the technology described in Patent Document 1 has the problem that it is not possible to grasp multiple elements that are edited in succession and the order of editing, because the technology infers the next action to be taken from the current state.

[0006] Therefore, the present invention has been made in consideration of the unresolved problems of the conventional technology, and has an object to provide a design support system 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 an input means for inputting a request to the AI ​​model, the request including element information relating to an element that has been created or edited in design information, and including a request to generate editing order information relating to a plurality of elements to be edited successively after the element in question and the editing order thereof, and an acquisition means for acquiring information output from the AI ​​model in response to the request.

[0008] With this configuration, the input means inputs a request including element information and a request to generate editing order information to the AI ​​model, and the acquisition means acquires information output from the AI ​​model in response to the request.

[0009] Here, the input means includes, for example, directly inputting a request to the AI ​​model, or indirectly inputting the request to the AI ​​model via a process, function, device, network, or other means.

[0010] In addition, the acquisition means includes, for example, directly acquiring the output information of the AI ​​model, or indirectly acquiring the output information of the AI ​​model via processing, function, device, network, or other means.

[0011] Furthermore, the request to generate edit order information includes, for example, a request to generate answer information to a question regarding a plurality of elements and their edit order.

[0012] Furthermore, the generation request includes, for example, an explicit request to generate editing order information, or an indirect request to generate editing order information. An explicit request includes, for example, a request such as "Please generate editing order information." An indirect request includes, for example, a generation request including a question regarding multiple elements and their editing order to request the generation of answer information to a question regarding multiple elements and their editing order. This is because, in an AI model, the answer information is generated by inputting a question regarding multiple elements and their editing order as a prompt.

[0013] Furthermore, the element information and the request may be configured in any format, such as vector data.

[0014] Furthermore, element information can be, for example, configured as the element itself, or as information for identifying the element (for example, name, number, ID, code, link information such as URL), or as feature information related to an outline, statistics, or other features of the element. Furthermore, element information can be, for example, configured as characters, numbers, figures, codes, symbols, images, sounds, and other information. Furthermore, element information can be configured as keywords related to the element (for example, one or more keywords indicating part of the name of the element).

[0015] The editing sequence information may be configured, for example, as a plurality of elements and their editing sequence itself, or as information for identifying the elements and the editing sequence (for example, link information such as a name, number, ID, code, URL, etc.), or as feature information relating to an overview, statistics, and other features of the elements and the editing sequence. The editing sequence information may be configured, for example, as characters, numbers, figures, codes, symbols, images, sounds, and other information. The editing sequence information may be configured as keywords relating to the elements and the editing sequence (for example, one or more keywords indicating part of the name of the elements and the editing sequence).

[0016] The system may be realized as a single device, equipment, terminal, or other device, or as a network system in which multiple devices, equipment, terminals, or other devices are communicatively connected. In the latter case, each component may belong to any one of the multiple devices as long as they are communicatively connected to each other.

[0017] [Invention 2] Furthermore, the design support system of Invention 2, in the design support system of Invention 1, comprises a registration means for registering, in a knowledge base that can be referenced by the AI ​​model, reference information including element information on an element that has already been created or edited, as well as reference information on a plurality of elements to be edited successively after the element and the order in which they are edited, and the acquisition means acquires, in response to the request, information output from the AI ​​model by referring to the reference information in the knowledge base.

[0018] With this configuration, the registration unit registers the reference information in the knowledge base. Then, the acquisition unit acquires information output from the AI ​​model in response to the request. At this time, the AI ​​model refers to the reference information in the knowledge base.

[0019] Here, the knowledge base stores reference information by any means and at any time, and may store reference information in advance, or may store reference information by external input or the like while the system is operating, without storing reference information in advance.

[0020] [Invention 3] Furthermore, the design support system of Invention 3 is the design support system of Invention 2, wherein the registration means registers in the knowledge base reference information including element information on an element that has already been created or edited, editing order information on a plurality of elements to be edited successively after the element and the editing order thereof, and evaluation values ​​related to the editing of the plurality of elements.

[0021] [Invention 4] Furthermore, the design support system of Invention 4 is the design support system of Invention 3, wherein the registration means registers, in the knowledge base, first reference information including the element information, the editing order information, and the evaluation value based on a first index indicating an index of a value of the evaluation value, and second reference information including the element information, the editing order information, and the evaluation value based on a second index different from the first index, and is provided with index information acquisition means for acquiring index information regarding the first index or the second index, and the input means inputs, to the AI ​​model, the request including a request to refer to either the first reference information or the second reference information of the knowledge base based on the index information acquired by the index information acquisition means.

[0022] With this configuration, the registration means registers the first reference information and the second reference information in the knowledge base. Then, the index information acquisition means acquires index information, and the input means inputs a request including a request to refer to either the first reference information or the second reference information in the knowledge base based on the acquired index information to the AI ​​model.

[0023] Here, the index information acquisition means may, for example, input index information from an input device or the like, acquire or receive index information from an external terminal or the like, read index information from a storage device or storage medium or the like, or generate or calculate index information by information processing or the like. Therefore, acquisition includes at least input, acquisition, reception, reading (including search), generation and calculation. The same applies below to the design support system of Invention 7.

[0024] [Invention 5] Furthermore, in the design support system of Invention 5, in the design support system of Invention 1, the request includes element information relating to an element that has already been created or edited, as well as reference information including editing order information relating to a plurality of elements to be edited successively after the element in question and the editing order thereof.

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

[0026] [Invention 6] Furthermore, in the design support system of Invention 6, in the design support system of Invention 5, the request includes reference information including element information on an element that has already been created or edited, editing order information on a plurality of elements to be edited successively after the element and the editing order thereof, and evaluation values ​​related to the editing of the plurality of elements.

[0027] [Invention 7] Furthermore, the design support system of Invention 7, in the design support system of Invention 6, further comprises 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, and 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 editing order information, and the evaluation value based on the first index, or second reference information including the element information, the editing order information, and the evaluation value based on the second index.

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

[0029] [Invention 8] Furthermore, the design support system of Invention 8, in the design support system of any one of Inventions 1 to 7, further comprises an identification means for identifying, as a related group, the plurality of elements and their editing order that appear a predetermined number of times in the design information, and the request includes a request to generate the editing order information regarding the plurality of elements and their editing order as the related group identified by the identification means.

[0030] With this configuration, the identification means identifies multiple elements and their editing order that have a predetermined number of occurrences or more as a related group, and the input means inputs a request to the AI ​​model, the request including a request to generate editing order information regarding the multiple elements and their editing order as the identified related group.

[0031] [Invention 9] Furthermore, the design support system of Invention 9 is a design support system of any one of Inventions 1 to 7, wherein the plurality of elements are elements whose setting or changing requires human judgment, and the setting or changing of the elements has an effect on other elements.

[0032] [Invention 10] Furthermore, the design support system of invention 10 is the design support system of any one of inventions 1 to 7, wherein the design information is design information for designing a building. Effect of the Invention

[0033] As described above, according to the design support system of Invention 1, it is possible to obtain editing order information regarding a plurality of elements to be edited in succession after an element that has already been created or edited and the editing order of those elements, so that it is possible to grasp a plurality of elements to be edited in succession and the editing order of those elements.

[0034] Furthermore, according to the design support system of the third or sixth aspect, it is possible to obtain multiple elements with high evaluation values ​​and editing order information regarding the editing order thereof.

[0035] Furthermore, according to the design support system of the fourth or seventh aspect, it is possible to obtain a plurality of elements having high evaluation values ​​based on the first index or the second index and editing order information relating to the editing order thereof.

[0036] Furthermore, according to the design support system of Invention 8, editing can be performed while imagining related groups.

[0037] Furthermore, according to the design support system of Invention 9, it is possible to obtain editing order information regarding a plurality of elements and their editing order, taking into consideration the relationship between elements whose setting or changing requires human judgment and other elements affected by the setting or changing of the elements. [Brief description of the drawings]

[0038] [Figure 1] FIG. 1 is a diagram illustrating a hardware configuration of a drawing creation support device 100. [Diagram 2] FIG. 13 is a diagram showing the structure of CAD data for a plan view. [Diagram 3] FIG. 4 is a diagram showing a structure of edit history data. [Figure 4] 13 is a flowchart showing a learning data generation process. [Diagram 5] FIG. 2 is a diagram showing a structure of learning data. [Figure 6] 13 is a flowchart showing 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] 13 is a flowchart showing an editing order information estimation process. [Figure 9] This is a plan showing the expected delivery of a piano. [Figure 10] FIG. 4 is a diagram showing a structure of edit history data. [Figure 11] FIG. 2 is a diagram showing a structure of learning data. [Figure 12] 13 is a flowchart showing an editing order information estimation process. [Figure 13] 1 is a block diagram showing a configuration of a network system according to an embodiment of the present invention; [Figure 14] FIG. 1 is a functional block diagram of a generation AI server 120. [Figure 15] 13 is a flowchart showing a learning data registration process. [Figure 16] 13 is a flowchart showing an editing order information acquisition process. [Figure 17] 13 is a flowchart showing an editing order information acquisition process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0039] First Embodiment A first embodiment of the present invention will be described below. Figures 1 to 9 are diagrams showing this embodiment.

[0040] [Configuration of this embodiment] First, the configuration of this embodiment will be described. FIG. 1 is a diagram showing a hardware configuration of a drawing production support device 100. As shown in FIG.

[0041] As shown in FIG. 1, the drawing creation support device 100 is composed of a CPU (Central Processing Unit) 30 which controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 which stores the control program and the like for the CPU 30 in advance in a specified area, a RAM (Random Access Memory) 34 for storing data read from the ROM 32 etc. and calculation results required in the calculation process of the CPU 30, and an I / F (InterFace) 38 which mediates the input and output of data to and from external devices. 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.

[0042] Connected to the I / F 38 as external devices are an input device 40 consisting of a keyboard, mouse, etc. capable of inputting data as a human interface, a storage device 42 which stores data, tables, etc. as files, and a display device 44 which displays a screen based on an image signal.

[0043] 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 in the creation of drawings in response to operations by a designer. When a request is made to start the CAD software, the CPU 30 starts a program for the CAD software stored in a specified area of ​​the ROM 32, and executes processing according to the program. The designer can start the CAD software to create plan drawings, detailed floor plans, and other architectural drawings.

[0044] 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.

[0045] FIG. 2 is a diagram showing the structure of CAD data of a plan view. As shown in Figure 2, CAD data for a rectangular plan is data constituting a detailed drawing of the cross section of a building, and is configured as data including one or more createable or editable elements (hereinafter referred to as "edit elements"). CAD data for a rectangular plan is created by a designer using CAD software. A designer creates a rectangular 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 of the floor, wall and ceiling of the area labeled "internal corridor" are arranged, and the edit elements of the floor, wall and ceiling of the area labeled "windbreak room" are arranged.

[0046] The same is true for CAD data of floor plan details and other architectural drawings, which are structured as data including one or more editing elements.

[0047] The storage device 42 stores, for each CAD data, editing history data indicating the history of editing of the editing elements. The CAD data reflects the final editing results related to the editing history data.

[0048] 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 related to the edited element and editing time 402 required to edit the edited element in the order of editing. The element information 400 includes an element ID for identifying the edited element, an area that is the subject of editing of the edited element, and the edited element itself. The editing time 402 can be calculated, for example, by subtracting the editing start time from the editing end time.

[0049] In the example of Figure 3, the first related group shows that the edit elements of the toilet, "toilet bowl," "washing 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.

[0050] In addition, the second related group shows that the edit elements of the toilet, "exhaust fan," "lighting," "storage," and "outlet," are edited consecutively in that order. These edit elements are assigned element IDs "56," "57," "58," and "59," and the edit times were 94, 48, 42, and 74 minutes, respectively.

[0051] The third related group shows that the closet edit elements "shelf", "hanging 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.

[0052] The fourth related group shows that the kitchen editing elements "floor material," "wall material," "counter," and "sink" were edited consecutively in that order. These editing elements were assigned element IDs "64," "65," "66," and "67," and took 42, 44, 35, and 32 minutes to edit, respectively.

[0053] The editing history data is used to create learning data, and therefore a large number of pieces of editing history data created in the past are stored in the storage device 42.

[0054] [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.

[0055] 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.

[0056] In step S100, unprocessed editing history data is obtained from storage device 42, and the process proceeds to step S102, where variable n is set to "2", and the process proceeds to step S104.

[0057] In steps S104 to S108, the element ID of the edited element that has been created or edited, the n edited elements (the number indicated by the value of variable n) that were edited consecutively after that edited element, their edit order, and their edit time are obtained from the edit history data obtained in step S100. Taking Fig. 3 as an example, a case where the value of variable n is "2" will be described. In the edit history data in Fig. 3, the rows are arranged in the order of editing.

[0058] When the second row is targeted, the element IDs of the previous edited elements, "01" to "51", are obtained as the created or edited element IDs. Because the value of the variable n is "2", "toilet" and "washbasin counter" are obtained as the edited elements, and "35" and "38" are obtained as the edit times.

[0059] When the third row is targeted, the element IDs of the previous edited elements, "01" to "52", are obtained as the created or edited element IDs. Because the value of the variable n is "2", "hand washing counter" and "mirror" are obtained as the edited elements, and "38" and "70" are obtained as the edit times.

[0060] Next, the process proceeds to step S110, where the evaluation value is calculated by multiplying the sum of the editing times obtained in step S108 by "-1". In the example of the second line above, the editing times "35" and "38" are obtained, so the evaluation value is calculated as (35+38)×-1=-73. The reason for multiplying by "-1" is to set a higher evaluation value for shorter editing times.

[0061] Next, the process proceeds to step S112, where the element IDs, edited elements and their edit order obtained in steps S104 to S108, and the evaluation values ​​calculated in step S110 are associated with each other and registered in the learning data, the process proceeds to step S114, where "1" is added to the value of variable n, and the process proceeds to step S116.

[0062] In step S116, it is determined whether the value of the 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 S114 are repeatedly executed until the value of the variable n becomes "4".

[0063] Using FIG. 3 as an example, the process of steps S104 to S110 will be described for the case where the value of the variable n is "3."

[0064] When the second row is targeted, the element IDs of the previous edited elements, "01" to "51", are obtained as the created or edited element IDs. Because the value of variable n is "3", the edited elements obtained are "toilet", "washing counter", and "mirror", and the edit times obtained are "35", "38", and "70". The evaluation value is calculated as (35 + 38 + 70) x -1 = -143.

[0065] When the third row is targeted, the element IDs of the previous edited elements, "01" to "52", are obtained as the created or edited element IDs. Because the value of the variable n is "3", the edited elements obtained are "hand washing counter", "mirror", and "towel rack", and the edit times obtained are "38", "70", and "94". The evaluation value is calculated as (38 + 70 + 94) x -1 = -202.

[0066] Moreover, the process of steps S104 to S110 will be described for the case where the value of the variable n is "4" using FIG. 3 as an example.

[0067] When the second row is targeted, the element IDs of the previous edited elements, "01" to "51", are obtained as the created or edited element IDs. Because the value of variable n is "4", the edited elements obtained are "toilet", "washing counter", "mirror", and "towel rack", and the edit times obtained are "35", "38", "70", and "94". The evaluation value is calculated as (35 + 38 + 70 + 94) x -1 = -237.

[0068] When the third row is targeted, the element IDs of the previous edited elements, "01" to "52", are obtained as the created or edited element IDs. Because the value of the variable n is "4", the edited elements obtained are "hand washing counter", "mirror", "towel rack", and "exhaust fan", and the edit times obtained are "38", "70", "94", and "94". The evaluation value is calculated as (38 + 70 + 94 + 94) x -1 = -296.

[0069] On the other hand, if it is determined in step S116 that the value of variable n is greater than "4" (YES), the process proceeds to step S118 to determine whether or not the processing of steps S100 to S116 has been completed for all of the editing history data, and if it is determined that the processing has been completed for all of the editing history data (YES), the process proceeds to step S120.

[0070] In step S120, the learning data in which the element IDs and other information have been registered in step S112 is stored in the storage device .

[0071] FIG. 5 is a diagram showing the structure of the learning data. 5, each line of the learning data includes an already created or edited element ID 410, edit order information 412, and an evaluation value 414. The edit order information 412 includes an area to be edited by the edit element, the edit element, and the edit order.

[0072] The second line of Fig. 5 shows two edit elements edited in succession after the edit element in the first line of Fig. 3, their edit order, and evaluation value, the third line of Fig. 5 shows two edit elements edited in succession after the edit element in the second line of Fig. 3, their edit order, and evaluation value, the fourth line of Fig. 5 shows two edit elements edited in succession after the edit element in the third line of Fig. 3, their edit order, and evaluation value, the sixth line of Fig. 5 shows two edit elements edited in succession after the edit element in the fifth line of Fig. 3, their edit order, and evaluation value, the seventh line of Fig. 5 shows two edit elements edited in succession after the edit element in the sixth line of Fig. 3, their edit order, and evaluation value, the eighth line of Fig. 5 shows two edit elements edited in succession after the edit element in the seventh line of Fig. 3, their edit order, and evaluation value,

[0073] Also, the 10th line of Fig. 5 shows three edit elements edited in succession after the edit element on the 1st line of Fig. 3, their edit order, and evaluation value, and the 11th line of Fig. 5 shows three edit elements edited in succession after the edit element on the 2nd line of Fig. 3, their edit order, and evaluation value, respectively. Also, the 13th line of Fig. 5 shows three edit elements edited in succession after the edit element on the 5th line of Fig. 3, their edit order, and evaluation value, and the 14th line of Fig. 5 shows three edit elements edited in succession after the edit element on the 6th line of Fig. 3, their edit order, and evaluation value, respectively.

[0074] In addition, line 16 of Figure 5 shows the four edit elements edited consecutively after the edit element on line 1 of Figure 3, their edit order, and evaluation value, and line 18 of Figure 5 shows the four edit elements edited consecutively after the edit element on line 5 of Figure 3, their edit order, and evaluation value.

[0075] [Trained model generation process] FIG. 6 is a flowchart showing the trained model generation process.

[0076] 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 trained data analysis process, as shown in Fig. 6. In the trained data analysis process, the trained data is read from the storage device 42, and created or edited element IDs 410, editing order information 412, and evaluation values ​​414 are extracted from the read trained data.

[0077] Next, the process proceeds to step S202. In step S202, as shown in FIG. 7, a learning data set is generated based on the information extracted in step S200, and the process proceeds to step S204, where the generated learning data set is input to a learning program, and a trained model is generated by the learning program. The learning program includes pre-learning parameters and hyperparameters, and performs learning based on the input learning data set and hyperparameters to update the pre-learning parameters. For example, reinforcement learning can be adopted as a learning method. In reinforcement learning, an evaluation value related to the editing of the multiple edit elements is given to a combination of an already created or edited element ID, a plurality of edit elements edited consecutively after the edit element, and editing order information related to the editing order, and learning is performed so that the evaluation value is maximized. Then, the trained model is output as a learning result.

[0078] The trained model is trained based on created or edited element IDs 410, editing order information 412, and evaluation value 414 so that evaluation value 414 is maximized. The trained model includes trained parameters in which pre-trained parameters have been updated by training, and an inference program. The inference program inputs created or edited element IDs, estimates editing order information from the input created or edited element IDs based on the trained parameters, and outputs the estimated editing order information. Note that the relationship between the input element IDs and the output editing order information is determined by AI training, and therefore, although it shows a similar tendency to the contents of past training data, there is ambiguity that does not necessarily match exactly. However, this ambiguity can be reduced by the amount of training data and the training accuracy.

[0079] 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 is terminated.

[0080] [Editing Order Information Estimation Processing] FIG. 8 is a flowchart showing the editing order information estimation process.

[0081] The edit order information estimation process is executed in response to a request from a designer or other user, and when executed by the CPU 30, first the process proceeds to step S300 as shown in FIG.

[0082] In step S300, an element ID that has been created or edited is obtained from the CAD data currently being edited, and the process proceeds to step S302.

[0083] In step S302, editing order information is estimated from the created or edited element IDs acquired in step S300, using the trained model in the storage device 42. The estimation is performed by inputting the created or edited element IDs to the trained model and acquiring the editing order information output from the trained model.

[0084] Here, a Monte Carlo tree search method or the like can be used to estimate edit elements with a larger number of edit elements and a higher degree of accuracy, as well as their edit order. In the example of Fig. 3, priority is given to estimating three edit elements rather than two, and four edit elements rather than three, as well as their edit order. This allows the designer to perform editing while imagining larger edit units.

[0085] Also, rather than prioritizing the longest, it is possible to estimate the edit elements and their edit order as a related group. For example, it is possible to estimate A, B, C, D, E, F, G, and H as the edit elements to be edited next in succession from the current edit state, and if A to D and E to H are related groups, A to D are estimated instead of A to H. Whether or not they are related groups can be determined by, for example, identifying two or more edit elements and their edit orders among A to H that have a predetermined number of occurrences or more in the learning data. This allows the designer to perform editing while imagining related groups.

[0086] Next, the process proceeds to step S304, where the editing order information estimated by the trained model is displayed on the display device 44, and the series of processes is terminated.

[0087] [When considering bringing in a piano] Next, an operation will be described assuming that a piano is brought in.

[0088] FIG. 9 is a plan illustrating the delivery of a piano. When a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in CAD software, the width of the toilet needs to be shortened to prevent interference between the piano and the toilet wall when the piano is brought in. However, if the width of the toilet is changed, other editing elements of the toilet also need to be edited. Therefore, when the designer requests estimation of the editing elements to be edited for the toilet and their editing order after changing the width of the toilet, the created or edited element IDs are acquired from the CAD data currently being edited through steps S300 to S304, and the editing order information is estimated and displayed from the acquired created or edited element IDs. For example, when the editing order information of the 16th line in FIG. 5 is estimated, "toilet bowl → hand washing counter → mirror → towel rack" is displayed. If these editing elements are already included in the CAD data as shown in FIG. 9, for example, these editing elements are highlighted (for example, displayed with a specific color or pattern) and the editing order is displayed by connecting them with arrows or the like.

[0089] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, a created or edited element ID is obtained, and editing order information is estimated from the obtained created or edited element ID using a trained model trained based on training data including the created or edited element ID, as well as multiple edit elements edited in succession after the edited element and editing order information relating to the editing order.

[0090] This makes it possible to obtain multiple editing elements to be edited in succession after an editing element that has already been created or edited, and editing order information regarding the editing order, so that the multiple editing elements to be edited in succession and the editing order can be grasped.

[0091] Furthermore, in this embodiment, the trained model is trained to maximize the evaluation value based on learning data including a created or edited element ID, multiple edit elements edited consecutively after the edit element and editing order information regarding the editing order of the multiple edit elements, and evaluation values ​​regarding the editing of the multiple edit elements.

[0092] This makes it possible to obtain multiple editing elements with high evaluation values ​​and editing order information relating to the editing order of the editing elements.

[0093] Furthermore, in this embodiment, multiple edit elements and their edit orders that appear a predetermined number of times or more are identified as a related group, and edit order information regarding the multiple edit elements and their edit orders as the identified related group is estimated.

[0094] This allows you to edit while imagining related groups. Furthermore, in this embodiment, an evaluation value related to the editing of a plurality of edited elements is assigned to a combination of an already created or edited element ID, a plurality of edited elements edited in succession after the edited element, and edit order information related to the edit order of the plurality of edited elements, and a trained model is generated by performing training so as to maximize the evaluation value.

[0095] This makes it possible to obtain a trained model that provides multiple editing elements with high evaluation values ​​and editing order information regarding their editing order.

[0096] Second Embodiment Next, a second embodiment of the present invention will be described. Figures 10 to 12 are diagrams showing this embodiment. Figures 3, 5 and 9 are also used.

[0097] 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. Hereinafter, only the parts that differ from the first embodiment will be described, and a description of the overlapping parts will be omitted.

[0098] [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.

[0099] 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.

[0100] As shown in FIG. 10, the edit history data includes, for each edit element, element information 404 relating to the edit element and the number of edit items 406 required to edit the edit element, in the order of editing.

[0101] In the example of Figure 10, the first related group shows that the edit elements of the toilet, "toilet bowl," "washing counter," "mirror," and "towel rack," are edited consecutively in that order. These edit elements are assigned element IDs "52," "53," "54," and "55," and the number of edit items is 8, 5, 6, and 9, respectively.

[0102] Also, as a second related group, the edit elements of the toilet, "exhaust fan," "lighting," "storage," and "outlet," are edited consecutively in that order. These edit elements are assigned element IDs "56," "57," "58," and "59," and the number of edit items is 3, 7, 8, and 6, respectively.

[0103] Also, as a third related group, the edit elements of the closet, "shelf," "hanging rail," "drawer," and "basket," are shown to have been edited consecutively in that order. These edit elements are assigned element IDs "60," "61," "62," and "63," and the number of edit items is 8, 7, 2, and 4, respectively.

[0104] Also, as the fourth related group, the kitchen edit elements "floor material," "wall material," "counter," and "sink" are edited consecutively in that order. These edit elements are assigned element IDs "64," "65," "66," and "67," and the number of edit items is 7, 4, 3, and 8, respectively.

[0105] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data generation process] In the learning data generation process, similarly to the generation of the learning data in FIG. 5, learning data is generated based on the editing history data in FIG.

[0106] FIG. 11 is a diagram showing the structure of the learning data. As shown in FIG. 11, the learning data includes, for each line, an element ID 410 that has been created or edited, editing order information 412, and an evaluation value 414.

[0107] The second line of Fig. 11 shows two edit elements edited in succession after the edit element in the first line of Fig. 10, their edit order, and evaluation value, the third line of Fig. 11 shows two edit elements edited in succession after the edit element in the second line of Fig. 10, their edit order, and evaluation value, the fourth line of Fig. 11 shows two edit elements edited in succession after the edit element in the third line of Fig. 10, their edit order, and evaluation value, the sixth line of Fig. 11 shows two edit elements edited in succession after the edit element in the fifth line of Fig. 10, their edit order, and evaluation value, the seventh line of Fig. 11 shows two edit elements edited in succession after the edit element in the sixth line of Fig. 10, their edit order, and evaluation value, the eighth line of Fig. 11 shows two edit elements edited in succession after the edit element in the seventh line of Fig. 10, their edit order, and evaluation value, respectively.

[0108] 11 shows three edit elements edited in succession after the edit element on the first line of Fig. 10, their edit order, and evaluation value, while the 11th line of Fig. 11 shows three edit elements edited in succession after the edit element on the second line of Fig. 10, their edit order, and evaluation value, while the 13th line of Fig. 11 shows three edit elements edited in succession after the edit element on the fifth line of Fig. 10, their edit order, and evaluation value, while the 14th line of Fig. 11 shows three edit elements edited in succession after the edit element on the sixth line of Fig. 10, their edit order, and evaluation value, respectively.

[0109] In addition, line 16 of Figure 11 shows the four edit elements that are edited consecutively after the edit element on line 1 of Figure 10, their edit order, and their evaluation value, and line 18 of Figure 11 shows the four edit elements that are edited consecutively after the edit element on line 5 of Figure 10, their edit order, and their evaluation value.

[0110] [Trained model generation process] In the trained model generation process, through steps S200 to S204, a first trained model is generated by performing learning based on the learning data in Fig. 5. The first trained model is similar to the trained model in the above-described first embodiment.

[0111] In the trained model generation process, after steps S200 to S204, a second trained model is generated by performing learning based on the learning 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 IDs 416, the editing order information 418, and the evaluation value 420 so as to maximize the evaluation value 420.

[0112] 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.

[0113] [Editing Order Information Estimation Processing] FIG. 12 is a flowchart showing the editing order information estimation process.

[0114] The edit order information estimation process is executed in response to a request from a designer or other user, and when executed by the CPU 30, the process first proceeds to step S310 as shown in FIG.

[0115] In step S310, index information regarding the first index "editing time" or the second index "number of edited items" indicating an index of the value of the evaluation value is obtained, and the process proceeds to step S312, where if the index related to the obtained index information is the first index, the first trained model is selected, and if the index related to the obtained index information is the second index, the second trained model is selected.

[0116] Next, the process proceeds to step S314, where the created or edited element ID is obtained from the CAD data currently being edited, and the process proceeds to step S316.

[0117] In step S316, editing order information is estimated from the created or edited element IDs acquired in step S314 using the learned model selected in step S312 from the first learned model and the second learned model in the storage device 42 (hereinafter referred to as the "selected learned model"). The estimation method is the same as the process in step S302 in the first embodiment.

[0118] Next, the process proceeds to step S318, where the editing order information estimated by the selected trained model is displayed on the display device 44, and the series of processes is terminated.

[0119] [When considering bringing in a piano] Next, an operation will be described assuming that a piano is brought in.

[0120] When the designer wants to install a piano with a width of 120 [mm] in the plan view of FIG. 9 in the CAD software, the width of the toilet needs to be shortened to prevent interference between the piano and the toilet wall when the piano is brought in. However, when the width of the toilet is changed, other editing elements of the toilet also need to be edited. Therefore, the designer requests estimation of the editing elements to be edited for the toilet and their editing order after changing the width of the toilet. At this time, if the designer wants to obtain the editing elements and their editing order that shorten the editing time, the designer selects "editing time" as an index, and the first trained model is selected through steps S310 to S312. Then, through steps S314 to S318, the created or edited element ID is acquired from the CAD data currently being edited, and the first trained model estimates and displays the editing order information from the acquired created or edited element ID.

[0121] On the other hand, if it is desired to obtain edit elements and their edit order that reduce the number of edit items, the designer selects "number of edit items" as an index, and the second trained model is selected through steps S310 to S312. Then, through steps S314 to S318, created or edited element IDs are acquired from the CAD data currently being edited, and the second trained model estimates and displays edit order information from the acquired created or edited element IDs.

[0122] [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 are acquired, and editing order information is estimated from the acquired created or edited element IDs using the selected trained model.

[0123] This makes it possible to obtain a plurality of edit elements having high evaluation values ​​based on the first index or the second index and edit order information relating to the edit order thereof.

[0124] Third embodiment Next, a third embodiment of the present invention will be described. Figures 13 to 16 are diagrams showing this embodiment. Figures 3, 5 and 9 are also used.

[0125] This embodiment differs from the first embodiment in that a large language model is used. Hereinafter, only the differences from the first embodiment will be described, and the description of the overlapping parts will be omitted.

[0126] [Configuration of this embodiment] First, the configuration of this embodiment will be described. FIG. 13 is a block diagram showing a configuration of a network system according to this embodiment.

[0127] As shown in FIG. 13, the drawing creation support device 100 and a generation AI server 120 that generates answer information by an AI (Artificial Intelligence) model in response to a request are connected to the Internet 199 so as to be able to communicate with each other.

[0128] [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 via a bus, and is configured as, for example, a cloud server.

[0129] FIG. 14 is a functional block diagram of the generation AI server 120. As shown in FIG. 14, the generation AI server 120 is configured to include a plurality of AI models 50, an AI model control unit 52 that controls the AI ​​models 50, and a knowledge base 54 that registers data that the AI ​​models 50 refer to for inference.

[0130] The AI ​​model 50 is an AI model trained on a large data set, and is a highly versatile model capable of performing various tasks. For example, a large-scale language model can be adopted as the AI ​​model 50. The large-scale language model is a deep learning model that pre-learns from a huge amount of data what is called a language model that models human spoken words based on their occurrence probability. When a prompt is input, the large-scale language model statistically infers the generation probability of the next word from the sentence included in the input prompt, and outputs the inference result. For example, the publicly known technology described in the Internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be adopted 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.

[0131] The AI ​​model control unit 52 selects one to be used for inference from among multiple AI models 50 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, it 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, it inputs the input prompt to the selected AI model. Then, when an execution request is input from the request processing unit 58, it 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.

[0132] 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.

[0133] The generation AI server 120 is further configured to have 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.

[0134] 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 already created or edited element ID, (2) a generation request for generating multiple edit elements to be edited consecutively after the already created or edited edit element and edit order information regarding the edit order, (3) a selection request for selecting the AI ​​model 50, and (4) a reference request for referencing the learning data in the knowledge base 54. (3) and (4) are not essential but are included additionally.

[0135] 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. In addition, 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. For example, the prompt is a request to the AI ​​model 50 to generate, based on the created or edited element ID, a plurality of edit elements to be edited consecutively next to the created or edited edit element and edit order information regarding the edit order, which has an evaluation value of a predetermined value or more. Then, the generated prompt and execution request are output to the AI ​​model control unit 52, and when an inference result is input from the AI ​​model control unit 52 in response to the execution request, the inference result is output to the answer information sending unit 60.

[0136] The answer information sending unit 60 sends answer information including the inference result input from the request processing unit 58 to the drawing creation support apparatus 100 .

[0137] The generation AI server 120 further includes a request receiving unit 62 that receives requests, and a learning data registration unit 64 that registers the learning data in the knowledge base 54.

[0138] 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.

[0139] The learning data registration unit 64 stores the learning data included in the request received by the request receiving unit 62 in a storage (not shown) and converts it into a data format (e.g., vector data) that can be referenced by the AI ​​model 50. The vector data can be generated by a technique (embedding) for converting data including characters, images, sounds, etc. into a numerical vector. Then, the converted learning data is 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 refer to the learning data.

[0140] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data registration process] FIG. 15 is a flowchart showing the learning data registration process.

[0141] The learning data registration process is executed in response to a request from a designer or other user, and when executed by CPU 30, first, the process proceeds to step S400 as shown in FIG.

[0142] In step S400, the learning data in FIG. 5 is obtained from the storage device 42, and the process proceeds to step S402.

[0143] 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.

[0144] When the process of step S402 ends, the series of processes ends. [Editing Order Information Acquisition Process] FIG. 16 is a flowchart showing the edit order information acquisition process.

[0145] The edit order information acquisition process is executed in response to a request from a designer or other user, and when executed by the CPU 30, first the process proceeds to step S500 as shown in FIG.

[0146] In step S500, an element ID that has been created or edited is obtained from the CAD data currently being edited, and the process proceeds to step S502.

[0147] In step S502, a request for generating answer information is sent to the generation AI server 120. The request includes (1) the created or edited element ID acquired in step S500, (2) a generation request for generating multiple edit elements to be edited consecutively after the created or edited edit element and edit order information regarding the edit order, (3) a selection request for selecting a specific AI model 50, and (4) a reference request for referencing the learning data in the knowledge base 54.

[0148] Here, a generation request can be included to generate edit elements with a larger number of edit elements and high accuracy, and edit sequence information related to the edit sequence. In the example of Fig. 3, priority is given to generating edit elements with three rather than two, and edit sequence information related to four rather than three, and so on, related to the edit sequence. This allows the designer to perform editing while imagining larger edit units.

[0149] Also, instead of prioritizing the longest length, a generation request for generating edit sequence information regarding edit elements and their edit order as a related group can be included. For example, if the AI ​​model 50 can infer A, B, C, D, E, F, G, and H as edit elements to be edited next in succession from the current edit state, and A to D and E to H are related groups, respectively, a request is made to generate edit sequence information regarding A to D, not edit sequence information regarding A to H. Whether or not a group is related can be determined by, for example, identifying two or more edit elements among A to H and their edit orders that have a predetermined number of occurrences or more in the learning data. This allows the designer to perform editing while imagining related groups.

[0150] Next, the process proceeds to step S504, where answer information is received from the generation AI server 120, and the process proceeds to step S506, where the editing order information included in the received answer information is displayed on the display device 44, and the series of processes is terminated.

[0151] [When considering bringing in a piano] Next, an operation will be described assuming that a piano is brought in.

[0152] When a designer wants to install a piano with a width of 120 mm in the plan view of FIG. 9 in the CAD software, the width of the toilet needs to be shortened to prevent interference between the piano and the toilet wall when the piano is brought in. However, if the width of the toilet is changed, other editing elements of the toilet also need to be edited. Therefore, when the designer requests inference of the editing elements to be edited for the toilet and their editing order after changing the width of the toilet, the created or edited element IDs are acquired from the CAD data currently being edited through steps S500 to S506, and the editing order information is inferred and displayed from the acquired created or edited element IDs. In the inference, the learning data of the knowledge base 54 is referenced by the selection AI model.

[0153] [Effects of this embodiment] Next, the effects of this embodiment will be described. In this embodiment, a request including an element ID that has already been created or edited and a request to generate editing order information regarding a plurality of editing elements that have been edited consecutively after the edit element and their editing order is input to the AI ​​model 50, and information output from the AI ​​model 50 in response to the request is obtained.

[0154] This makes it possible to obtain multiple editing elements to be edited in succession after an editing element that has already been created or edited, and editing order information regarding the editing order, so that the multiple editing elements to be edited in succession and the editing order can be grasped.

[0155] Furthermore, in this embodiment, learning data including an already created or edited element ID, multiple edit elements edited consecutively after that edit element and editing order information regarding the editing order of the multiple edit elements, and evaluation values ​​regarding the editing of the multiple edit elements are registered in the knowledge base 54, and in response to a request, information output from the AI ​​model 50 is obtained by referring to the learning data in the knowledge base 54.

[0156] This makes it possible to obtain multiple editing elements with high evaluation values ​​and editing order information relating to the editing order of the editing elements.

[0157] Furthermore, in this embodiment, multiple editing elements and their editing orders that occur a predetermined number of times or more are identified as a related group, and a request including a request to generate editing order information regarding the multiple editing elements and their editing order as the identified related group is input to the AI ​​model 50.

[0158] This allows you to edit while imagining related groups. In this embodiment, step S402 corresponds to the registration means of invention 2 or 3, step S502 corresponds to the input means of invention 1 or the specification means of invention 8, step S504 corresponds to the acquisition means of invention 1 or 2, and the CAD data corresponds to the design information of invention 8 or 10. In addition, the created or edited element ID corresponds to the element information of inventions 1 to 3, and the learning data corresponds to the reference information of invention 2 or 3.

[0159] [Fourth embodiment] Next, a fourth embodiment of the present invention will be described. Fig. 17 is a diagram showing this embodiment. Figs. 5, 9, 11, and 15 are also used.

[0160] This embodiment differs from the second and third embodiments in that the AI ​​model 50 refers to first learning data including an evaluation value based on a first index or second learning data including an evaluation value based on a second index. Hereinafter, only the parts that differ from the second and third embodiments will be described, and a description of the overlapping parts will be omitted.

[0161] [Operation of this embodiment] Next, the operation of this embodiment will be described. [Learning data registration process] The learning data registration process is executed in response to a request from a designer or other user, and when executed by CPU 30, first, the process proceeds to step S400 as shown in FIG.

[0162] In step S400, the learning data in FIG. 5 and the learning data in FIG. 11 are obtained from the storage device 42, and the process proceeds to step S402.

[0163] 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 of Fig. 5 acquired in step S400 as the first learning data, and (2) the learning data of Fig. 11 acquired in step S400 as the second learning data.

[0164] When the process of step S402 ends, the series of processes ends. [Editing Order Information Acquisition Process] FIG. 17 is a flowchart showing the edit order information acquisition process.

[0165] The edit order information acquisition process is executed in response to a request from a designer or other user, and when executed by the CPU 30, the process first proceeds to step S510 as shown in FIG.

[0166] In step S510, index information regarding the first index "editing time" or the second index "number of edited items", which indicate indicators of the value of the evaluation value, is obtained, and then the process proceeds to step S512 to obtain the created or edited element ID from the CAD data currently being edited, and the process proceeds to step S514.

[0167] In step S514, a request for generating answer information is sent to the generation AI server 120. The request includes (1) the created or edited element ID acquired in step S512, (2) a generation request for generating multiple edit elements to be edited consecutively after the created or edited edit element and edit order information related to the edit order, (3) a selection request for selecting a predetermined AI model 50, and (4) a reference request for referencing the first learning data in the knowledge base 54 if the index related to the index information acquired in step S510 is the first index, or a reference request for referencing the second learning data in the knowledge base 54 if the index related to the index information acquired in step S510 is the second index.

[0168] Next, the process proceeds to step S516, where answer information is received from the generation AI server 120, and the process proceeds to step S518, where the editing order information included in the received answer information is displayed on the display device 44, and the series of processes is terminated.

[0169] [When considering bringing in a piano] Next, an operation will be described assuming that a piano is brought in.

[0170] When a designer wants to install a piano with a width of 120 [mm] in the plan of FIG. 9 in the CAD software, the width of the toilet needs to be shortened to prevent interference between the piano and the wall of the toilet when the piano is brought in. However, when the width of the toilet is changed, other editing elements of the toilet also need to be edited. Therefore, the designer requests an estimation of the editing elements to be edited for the toilet and their editing order after changing the width of the toilet. At this time, if the designer wants to obtain the editing elements and their editing order that shorten the editing time, the designer selects "editing time" as an index, and through steps S510 to S518, the created or edited element IDs are obtained from the CAD data currently being edited, and the editing order information is inferred and displayed from the obtained created or edited element IDs. In the inference, the first learning data of the knowledge base 54 is referenced by the selected AI model.

[0171] On the other hand, when it is desired to obtain edit elements and their edit order that reduce the number of edit items, the designer selects "number of edit items" as an index, and through steps S510 to S518, created or edited element IDs are obtained from the CAD data currently being edited, and edit order information is inferred and displayed from the obtained created or edited element IDs. In the inference, the second learning data in the knowledge base 54 is referenced by the selected AI model.

[0172] [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.

[0173] This makes it possible to obtain a plurality of edit elements having high evaluation values ​​based on the first index or the second index and edit order information relating to the edit order thereof.

[0174] In this embodiment, step S510 corresponds to the index information acquiring means of invention 4, step S514 corresponds to the input means of invention 1 or 4 or the identifying means of invention 8, step S516 corresponds to the acquiring means of invention 1 or 2, and the first learning data corresponds to the first reference information of invention 4. Also, the second learning data corresponds to the second reference information of invention 4.

[0175] [Modifications] In the above first to fourth embodiments and their variations, reinforcement learning is adopted as the learning method, but the present invention is not limited to this, and any other learning method such as supervised learning, semi-supervised learning, unsupervised learning, deep learning, or the like can be adopted.

[0176] In the first to fourth embodiments and their modifications, the learning data includes an already created or edited element ID, multiple edit elements edited in succession after the edit element and editing order information related to the editing order, and evaluation values ​​related to the editing of the multiple edit elements, but is not limited to this and may be configured without including evaluation values. In this case, the learning data includes an already created or edited element ID, multiple edit elements edited in succession after the edit element and editing order information related to the editing order.

[0177] In addition, in the above first and second embodiments and their variations, the trained model used is one that has been trained based on created or edited element IDs, editing order information, and evaluation values, but this is not limited to the above, and it is also possible to use one that has been trained based on created or edited element IDs and editing order information.

[0178] In addition, in the above-described second embodiment and its modified example, the first trained model and the second trained model can be configured as one trained model.

[0179] In addition, in the third and fourth embodiments and their modifications, the AI ​​model 50 can be configured as the trained model in the first and second embodiments and their modifications.

[0180] In addition, in the above first to fourth embodiments and their variations, multiple editing elements and their editing orders that appear a predetermined number of times or more in the learning data are identified. However, this is not limited to this, and it is also possible to identify elements that appear a predetermined number of times or more in the editing history data.

[0181] In the above first to fourth embodiments and their modifications, a maximum of four editing elements and their editing orders are handled, but the present invention is not limited to this, 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.

[0182] In the above first to fourth embodiments and their modifications, all combinations of two to four edit elements are obtained from the edit history data for the multiple edit elements and their edit order to generate learning data, but this is not limiting. It is also possible to obtain multiple edit elements and their edit order that have a predetermined number of occurrences or more in the edit history data from the edit history data to generate learning data. In this case, multiple edit elements and their edit order that appear frequently may be estimated using a trained model that has trained multiple edit history data. This allows multiple edit elements and their edit order that appear frequently in the edit history data to be learned or inferred.

[0183] Furthermore, in the above first to fourth embodiments and their modifications, the edit history data is configured as data separate from the CAD data, but the present invention is not limited to this, and the edit history data can be configured as an integrated part included in the CAD data.

[0184] In the above third and fourth embodiments and their modifications, the learning data in the knowledge base 54 is referred to by the AI ​​model 50, 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.

[0185] [Invention A1] An input means for inputting a request including element information on an element that has been created or edited in design information and a request for generating editing order information on a plurality of elements to be edited successively after the element and the editing order thereof, into the AI ​​model; and acquiring information output from the AI ​​model in response to the request; The request includes element information relating to an element that has been created or edited, and reference information including editing order information relating to a number of elements to be edited successively after the element and the order in which they are edited.

[0186] This makes it possible to obtain editing order information regarding a plurality of elements to be edited successively after an element that has already been created or edited and the editing order thereof, so that it is possible to grasp a plurality of elements to be edited successively and the editing order thereof.

[0187] [Invention A2] In Invention A1, The request includes element information on an already created or edited element, editing order information on a plurality of elements to be edited successively after the element and the editing order thereof, and reference information including evaluation values ​​related to the editing of the plurality of elements.

[0188] This makes it possible to obtain multiple elements with high evaluation values ​​and editing order information regarding the editing order of the elements.

[0189] As a modification of the third embodiment, embodiments of inventions A1 and A2 will be described. In step S502, a request for generating answer information is sent to the generation AI server 120. The request includes (1) the created or edited element ID acquired in step S500, (2) a generation request for generating multiple edit elements to be edited in succession after the created or edited edit element and edit order information regarding the edit order, (3) a selection request for selecting a predetermined AI model 50, and (4) the learning data acquired in step S400.

[0190] [Invention A3] In Invention A2, An index information acquisition means for acquiring index information on 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 editing order information, and the evaluation value based on the first index, or second reference information including the element information, the editing order information, and the evaluation value based on the second index.

[0191] This makes it possible to obtain a plurality of elements having high evaluation values ​​based on the first index or the second index and edit order information relating to the edit order of the elements.

[0192] An embodiment of the invention A3 will be described as a modification of the above fourth embodiment. In step S514, a request for generating answer information is sent to the generation AI server 120. The request includes (1) the created or edited element ID acquired in step S512, (2) a generation request for generating multiple edit elements to be edited next to the created or edited edit element and edit order information related to the edit order, (3) a selection request for selecting a predetermined AI model 50, and (4) the first learning data acquired in step S400 if the index related to the index information acquired in step S510 is the first index, or the second learning data acquired in step S400 if the index related to the index information acquired in step S510 is the second index.

[0193] [Invention A4] In Inventions A1 to A3, a specifying means for specifying, as a related group, those elements and their editing sequences that appear a predetermined number of times in the design information, The request includes a request to generate the edit order information regarding the elements and their edit order as a related group identified by the identification means.

[0194] [Invention A5] In Inventions A1 to A3, The multiple elements are elements that require human judgment to set or change, and the setting or change has an effect on other elements.

[0195] [Invention A6] In Inventions A1 to A3, The design information is information for designing a building.

[0196] In the third and fourth embodiments and their modifications, the AI ​​model 50 refers to the information in the knowledge base 54, but the present invention is not limited to this. Information to be referred to 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 referred to by the AI ​​model 50 to perform inference. This configuration can be realized, for example, by RAG (Retrieval Augmented Generation).

[0197] Furthermore, in the above first to fourth 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 may be adopted.

[0198] [Invention B1] An element information acquisition means for acquiring element information relating to an element that has been created or edited in design information; The system further includes a search means for searching for edit order information corresponding to the element information acquired by the element information acquisition means from a storage means for storing edit order information relating to a plurality of elements to be edited successively after an already created or edited element and the edit order thereof in association with element information relating to the already created or edited elements.

[0199] This makes it possible to obtain editing order information regarding a plurality of elements to be edited successively after an element that has already been created or edited and the editing order thereof, so that it is possible to grasp a plurality of elements to be edited successively and the editing order thereof.

[0200] [Invention B2] In Invention B1, the storage means stores editing order information relating to a plurality of elements to be edited successively after an already created or edited element and an editing order thereof in association with element information relating to the already created or edited elements and evaluation values ​​relating to editing of the plurality of elements; The search means searches for the edit sequence information corresponding to the element information acquired by the element information acquisition means and having the evaluation value equal to or greater than a predetermined value.

[0201] This makes it possible to obtain multiple elements with high evaluation values ​​and editing order information regarding the editing order of the elements.

[0202] As a modification of the first embodiment, embodiments of inventions B1 and B2 will be described. The storage device 42 stores an edit order information table having a data structure similar to that of the learning data in Fig. 5. In step S302, the edit order information table is searched for edit order information corresponding to the created or edited element ID acquired in step S300 and having an evaluation value equal to or greater than a predetermined value.

[0203] [Invention B3] In Invention B2, the storage means includes a first storage means for storing the edit order information in association with the element 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 edit order information in association with the element information and the evaluation value based on a second index different from the first index; An 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 edit sequence information from the storage means selected by the storage means selection means.

[0204] This makes it possible to obtain a plurality of elements having high evaluation values ​​based on the first index or the second index and edit order information relating to the edit order of the elements.

[0205] An embodiment of the invention B3 will be described as a modification of the second embodiment. The storage device 42 stores a first edit order information table having a data structure similar to that of the learning data in FIG. 5, and a second edit order information table having a data structure similar to that of the learning data in FIG. 11. In step S312, if the index related to the index information acquired in step S310 is the first index, the first edit order information table is selected, and if the index related to the acquired index information is the second index, the second edit order information table is selected. In step S316, edit order information corresponding to the created or edited element ID acquired in step S314 and having an evaluation value equal to or greater than a predetermined value is searched for in the edit order information table selected in step S312.

[0206] [Invention B4] In Invention B2, the storage means stores the element information, the editing order information, the evaluation value based on a first index indicating an index of a value of the evaluation value, and index information related to the first index in association with each other, and also stores the element information, the editing order information, the evaluation value based on a second index different from the first index, and index information related to the second index in association with each other; An index information acquisition means for acquiring index information relating to the first index or the second index, The search means searches for the edit sequence information corresponding to the element information acquired by the element information acquisition means and the index information acquired by the index information acquisition means, and the evaluation value being equal to or greater than a predetermined value.

[0207] This makes it possible to obtain a plurality of elements having high evaluation values ​​based on the first index or the second index and edit order information relating to the edit order of the elements.

[0208] An embodiment of the invention B4 will be described as a modification of the second embodiment. The storage device 42 stores an edit order information table in which, for each row, (1) created or edited element ID 410, edit order information 412, evaluation value 414, and index information related to the first index, or (2) created or edited element ID 416, edit order information 418, evaluation value 420, and index information related to the second index are registered. In step S316, edit order information corresponding to the created or edited element ID acquired in step S314 and the index information acquired in step S310 and having an evaluation value equal to or greater than a predetermined value is searched for in the edit order information table.

[0209] [Invention B5] In Inventions B1 to B4, a specifying means for specifying, as a related group, those elements and their editing sequences that appear a predetermined number of times in the design information, The search means searches for the plurality of elements as the related group identified by the identification means and the edit order information relating to the edit order of the elements.

[0210] This allows you to edit while imagining related groups. [Invention B6] In Inventions B1 to B4, The multiple elements are elements that require human judgment to set or change, and the setting or change has an effect on other elements.

[0211] [Invention B7] In Inventions B1 to B4, The design information is information for designing a building.

[0212] In addition, in the inventions B1 to B7 and their variations, storing the edit order information in association with the element information, etc. includes, for example, (1) storing the edit order information and the element information, etc. in a direct association, such as by registering them in the same record, and (2) storing via one or more pieces of intermediate information, such as by providing a table for registering the edit order information and intermediate information in association with each other, and a table for registering the element information, etc. and the intermediate information in association with each other. In other words, any data structure can be adopted as long as the edit order information can be traced from the element information, etc. Note that it is sufficient that the edit order information is stored in the storage means in association with the element information, etc., and it is not necessarily required to store the element information, etc. in the storage means.

[0213] Furthermore, in inventions B1 to B7 and their variations, the storage means stores the editing sequence information by any means and at any time, and may store the editing sequence information in advance, or may store the editing sequence information by external input or the like during operation of the drawing creation support device 100 without storing the editing sequence information in advance.

[0214] Furthermore, in the third and fourth 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 edit elements to be edited in succession after a created or edited edit element and edit sequence information regarding the edit order thereof, the plurality of edit elements having an evaluation value equal to or greater than a predetermined value. However, without being limited to this, the prompt may be a request to the AI ​​model 50 to generate a plurality of edit elements to be edited in succession after a created or edited edit element and edit sequence information regarding the edit order thereof.

[0215] 5 or 11 is registered in the knowledge base 54 in the third and fourth 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 edit order information on a plurality of elements to be edited in succession after the element and the edit order thereof, or (3) Reference information including element information on an element that has already been created or edited, edit order information on a plurality of elements to be edited in succession after the element and the edit order thereof, and evaluation values ​​related to the editing of the plurality of elements may be registered in the knowledge base 54. The reference information of (2) or (3) may include edit order information estimated using the trained model in the first and second embodiments and their modifications.

[0216] Furthermore, in the third and fourth embodiments and their modifications, vector data is registered in the knowledge base 54, but the present invention is not limited to this and data in any format can be registered.

[0217] In the first to fourth 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 adopted, but the present invention is not limited to this, and a configuration including a plurality of these processes can be adopted. In this case, it is possible to control which process is to be performed with priority. For example, it is possible to adopt a configuration in which (1) a process with a low current load is performed with priority among the plurality of processes, (2) a process with a high degree of adoption (referring to the number of times of adoption, the percentage, or other degree) by the designer is performed with priority among the plurality of processes. It is also possible to adopt a configuration in which (3) a process with a high degree of use (referring to the number of times of use, the percentage, or other degree) by the designer is performed with priority among the plurality of processes.

[0218] Furthermore, in the above first to fourth embodiments and their modified examples, multiple edit elements and their edit order are learned or inferred, but the present invention is not limited to this. The "multiple edit elements" to be learned or inferred can be edit element A, which requires human judgment for its setting or change, and whose setting or change affects another edit element B. This makes it possible to obtain edit order information regarding multiple edit elements and their edit 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, so that editing work can be made more efficient by targeting edit elements that are difficult to automate.

[0219] In the first and second embodiments and their modifications, the device is realized as a single device, but the present invention is not limited to this, and may be realized as a network system. As an example of a network system, a part or all of the functions of the drawing creation support device 100 may be configured as a virtual server on a server that provides a cloud computing service.

[0220] Furthermore, in the above third and fourth embodiments and their variations, the generation AI server 120 is configured as an integrated unit that includes the functions of the AI ​​model 50, the AI ​​model control unit 52, the knowledge base 54, the request receiving unit 56, the request processing unit 58, the answer information sending unit 60, the request receiving unit 62, and the learning data registration unit 64, but this is not limited to the above, and some of the functions may be configured as separate servers, etc.

[0221] Furthermore, in the third and fourth embodiments and the modifications thereof, the system is realized as a network system, but the present invention is not limited to this and may be realized as a single device or application.

[0222] In addition, in the above third and fourth 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.

[0223] Furthermore, in the above first to fourth embodiments and their variations, the drawing creation support device 100 is configured to use the storage device 42, but is not limited to this and can also be configured to use an external storage device such as a database server.

[0224] In addition, in the above first to fourth embodiments and their variations, when executing the processes shown in the flowcharts of Figures 4, 6, 8, 12, 15, 16 and 17, a program pre-stored in ROM 32 is executed. However, this is not limited to the above, and the program showing these procedures may be read into RAM 34 from a storage medium on which the program is stored and executed.

[0225] Here, storage media refers to semiconductor storage media such as RAM and ROM, magnetic storage type storage media such as FD and HD, optically readable storage media such as CD, CDV, LD and DVD, and magnetic storage type / optically readable storage media such as MO, and includes any storage medium that can be read by a computer, regardless of the reading method (electronic, magnetic, optical, etc.).

[0226] Moreover, the above first to fourth embodiments and their modifications can be applied to each other. Furthermore, the present invention is not limited to the first to fourth embodiments and their modifications, but may be applied to other cases without departing from the spirit of the present invention. For example, the present invention may be applied to a wide range of design cases, such as automobile design, machine design, and circuit design. [Explanation of symbols]

[0227] 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...request receiving unit, 58...request processing unit, 60...answer information transmitting unit, 62...request receiving unit, 64...learning data registration unit, 199...Internet, 400, 404...element information, 402...editing time, 406...number of edited items, 410, 416...element ID, 412, 418...editing order information, 414, 420...evaluation value

Claims

1. An input means for inputting a request including element information on an already created or edited element in the design information and a request for generating editing order information on a plurality of elements to be edited successively after the element and an editing order thereof, into the AI ​​model; A design support system comprising: an acquisition means for acquiring information output from the AI ​​model in response to the request.

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

3. In claim 2, The design support system is characterized in that the registration means registers in the knowledge base reference information including element information on an element that has been created or edited, editing order information on a plurality of elements to be edited in succession after the element and the editing order thereof, and evaluation values ​​related to the editing of the plurality of elements.

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

5. In claim 1, A design support system characterized in that the request includes element information relating to an element that has already been created or edited, and reference information including editing order information relating to a plurality of elements to be edited successively after the element and the editing order thereof.

6. In claim 5, A design support system characterized in that the request includes element information regarding an element that has already been created or edited, editing order information regarding a plurality of elements to be edited successively after the element and the editing order thereof, and reference information including evaluation values ​​regarding the editing of the plurality of elements.

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

8. In any one of claims 1 to 7, a specifying means for specifying, as a group of related elements, elements and their editing sequences that appear in the design information a predetermined number of times or more; The design support system according to claim 1, wherein the request includes a request to generate the edit sequence information regarding the plurality of elements as a related group identified by the identifying means and an edit sequence thereof.

9. In any one of claims 1 to 7, A design support system, wherein the plurality of elements are elements whose setting or change requires human judgment and whose setting or change has an effect on other elements.

10. In any one of claims 1 to 7, A design support system, wherein the design information is design information for designing a building.

Images