WO2023218503A1

WO2023218503A1 - Icon placement system, icon placement method, and program

Info

Publication number: WO2023218503A1
Application number: PCT/JP2022/019663
Authority: WO
Inventors: 隆也駒井
Original assignee: スパイダープラス株式会社
Priority date: 2022-05-09
Filing date: 2022-05-09
Publication date: 2023-11-16
Also published as: JPWO2023218503A1; JP7159513B1

Abstract

[Problem] To attain an improvement in work efficiency by creating associations between plan data and detail drawing data for building structural drawings. [Solution] Provided is an icon placement system for placing icons on plans of a building structural drawing, wherein the system acquires annotation data in which first icons associated with signs applied to plans have been pre-placed, learns the association between the plans and the first icons by using the acquired annotation data as training data, generates a trained model on the basis of the learning result, and places second icons based on the generated trained model in a new plan.

Description

Icon placement system, icon placement method and program

The present invention relates to a technique effective for arranging icons on a floor plan of a building structure drawing.

In recent years, the use of ICT (Information and Communication Technology), which focuses on converting building structures into data, has been attracting attention.
For example, in Patent Document 1, a building structure drawing created for a single building is composed of parts, so that even a person who is inexperienced in drawing can draw a floor plan, foundation plan, foundation plan, floor plan, etc. without contradiction. A building structure drawing creation system that can create building structure drawings is disclosed.
In addition, in Patent Document 2, the interior is displayed in a three-dimensional virtual space on the terminal where the owner views the building structure diagram of the house, and the viewpoint position and line of sight direction can be switched and displayed on the owner's terminal. A possible home design system is disclosed.

Japanese Patent Application Publication No. 2018-206017 Japanese Patent Application Publication No. 2020-086809

A building structure diagram requires many floor plans and their detailed drawings (miniature drawings, etc.), but it is necessary to associate these drawings with icons and the like. This association was performed manually by associating the data of the outline drawing with the data of the detailed drawing, which was inefficient.
Therefore, there is a need for a technology that automatically associates the floor plan data with detailed drawing data in a building structural drawing.
However, in the systems described in Patent Documents 1 and 2, it was not possible to automatically associate the floor plan data and detailed drawing data in the building structural drawing.
Therefore, the present inventor focused on a mechanism for automatically associating floor plan data and detailed drawing data in a building structural drawing.

The present invention provides an icon placement system, an icon placement method, and a program that make it possible to improve work efficiency by automatically arranging and associating icons with floor plan data in building structure drawings. With the goal.

The present invention is an icon arrangement system for arranging icons on a blueprint of a building structure drawing,
an acquisition unit that acquires annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance;
a learning unit that learns by associating the foreword and the first icon with the acquired annotation data as training data;
a model generation unit that generates a trained model based on the learning results;
a placement unit that places a second icon based on the generated trained model on the new sketch;
An icon arrangement system is provided.

According to the present invention, an icon placement system for arranging icons on a blueprint of a building structure diagram acquires annotation data in which a first icon associated with a code attached to the blueprint is arranged in advance. Using the annotation data obtained as training data, the foreground map and the first icon are learned in association with each other, a learned model is generated based on the learning result, and the generated learning model is applied to the new foreground map. A second icon is placed based on the completed model.

Although the present invention is in the category of systems, similar actions and effects can be achieved even in methods and programs.

According to the present invention, it is possible to improve work efficiency.

1 is a diagram illustrating an overview of an icon placement system 1. FIG. 1 is a diagram showing a functional configuration of an icon placement system 1. FIG. 2 is a diagram showing a flowchart of learning processing executed by the icon arrangement system 1. FIG. FIG. 2 is a diagram schematically showing an example of a map in which the learning terminal 20 has arranged first icons. 3 is a diagram showing a flowchart of placement processing executed by the icon placement system 1. FIG. FIG. 3 is a diagram schematically showing an example of a layout in which second icons are arranged by the computer 10. FIG. 3 is a diagram showing a flowchart of relearning processing executed by the icon placement system 1. FIG. 3 is a diagram showing a flowchart of a change process executed by the icon placement system 1. FIG.

Hereinafter, modes for carrying out the present invention (hereinafter referred to as embodiments) will be described in detail with reference to the accompanying drawings. In the subsequent figures, the same numbers or symbols are given to the same elements throughout the description of the embodiments.

[Overview of icon placement system 1]
FIG. 1 is a schematic diagram for explaining an overview of an icon placement system 1. As shown in FIG.
In the icon placement system 1, a computer 10 having a server function realizes a process of placing icons on a blueprint of a building structure diagram.

The terminals and devices that make up the icon arrangement system 1 will be explained.
The icon arrangement system 1 may be any system as long as it includes a computer 10 having at least a server function. This computer 10 may be realized by, for example, one computer, or may be realized by a plurality of computers such as a cloud computer.
In this specification, a cloud computer refers to one that uses any computer in a scalable manner to perform a certain function, or one that includes multiple functional modules to realize a certain system, and whose functions can be freely combined. It can be anything.
In this specification, the icon arrangement system 1 includes a computer 10, a learning terminal 20 for setting annotation data for learning, and a worker terminal 30 managed by a worker working at a construction site.
The terminals, devices, etc. that make up the icon arrangement system 1 are merely examples, and the number, types, and functions of each terminal other than the computer 10 can be changed as appropriate.

An overview of the processing steps when the icon placement system 1 arranges icons on the blueprint of the building structure drawing will be explained.

The computer 10 acquires annotation data in which a first icon associated with a code attached to the blueprint is arranged in advance (step S1).
The computer 10 acquires annotation data from the learning terminal 20.
The learning terminal 20 receives input from an administrator or the like who manages the learning terminal 20, and places a first icon corresponding to a code attached to the blueprint on the blueprint. The learning terminal 20 transmits the map on which the first icon is arranged to the computer 10 as annotation data.
The computer 10 receives this annotation data and obtains annotation data in which the first icons associated with the symbols attached to the diagram are arranged in advance.

The computer 10 learns the map and the first icon in association with each other using the acquired annotation data as teacher data (step S2).
Learning methods include, for example, machine learning using supervised learning, unsupervised learning, reinforcement learning, etc., deep learning using convolutional neural networks, recurrent neural networks, long/short-term memory, etc., and the computer 10 stores annotation data. Supervised learning is performed using the teacher data to learn the map and the first icon in association with each other.

The computer 10 generates a learned model based on the learning results (step S3).
The computer 10 generates a trained model using general algorithms used for machine learning such as linear regression, random forest, decision tree, and k-nearest neighbor method.

The computer 10 places a second icon based on the generated trained model on the new sketch (step S4).
The computer 10 acquires a new blueprint from the worker terminal 30 or the like, and arranges a second icon based on the generated learned model on the new blueprint.

The above is an overview of the icon arrangement system 1.
According to the present icon arrangement system 1, it is possible to improve work efficiency.

[Device configuration]
FIG. 2 is a block diagram showing the configuration of the icon placement system 1. As shown in FIG. The icon placement system 1 is a system for arranging icons on a blueprint of a building structure diagram, and is composed of at least a computer 10. In this embodiment, the icon arrangement system 1 further includes a learning terminal 20 for setting annotation data for learning, and a worker terminal 30 managed by a worker working at a construction site.
The icon arrangement system 1 is a system in which a computer 10, a learning terminal 20, and a worker terminal 30 are connected to enable data communication via a network 5 such as a public line network.
Note that the terminals, devices, etc. that make up the icon arrangement system 1 are merely examples, and the number, types, and functions of each terminal other than the computer 10 can be changed as appropriate.

The computer 10 has a server function, and may be implemented by, for example, one computer or multiple computers such as a cloud computer.
The computer 10 includes a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc. as a control unit, and a communication unit. as a connection with other terminals, devices, etc. It includes a device for enabling communication, an acquisition unit 11 that acquires annotation data in which a first icon associated with a code attached to a diagram is arranged in advance, and the like.
The computer 10 includes a data storage section such as a hard disk, a semiconductor memory, a storage medium, a memory card, etc. as a storage section.
The computer 10 includes, as a processing unit, various devices that execute various processes, a learning unit 12 that learns by associating a foreshadowing diagram with a first icon using annotation data as teacher data, and a learned model based on learning results. The present invention includes a model generation unit 13 that generates a model, an arrangement unit 14 that arranges a second icon based on the generated trained model on a new sketch, and the like.

In the computer 10, by reading a predetermined program, the control section cooperates with the communication section to realize an annotation data acquisition module, a map acquisition module, a map output module, and a change reception module.
Further, in the computer 10, the control section reads a predetermined program, thereby realizing a learned model storage module in cooperation with the storage section.
In addition, in the computer 10, the control unit reads a predetermined program to cooperate with the processing unit to generate a first identification module, a learning module, a learned model generation module, a second identification module, a placement module, and an assignment module. Realize.

Each of the learning terminal 20 and the worker terminal 30 is, for example, a mobile terminal such as a mobile phone, a smartphone, or a tablet terminal, or a terminal such as a personal computer.
Each of the learning terminal 20 and the worker terminal 30 is equipped with a CPU, GPU, RAM, ROM, etc. as a terminal control unit, and is equipped with a device etc. for enabling communication with other terminals, devices, etc. as a communication unit. The input/output unit includes a device for inputting/outputting various information.

Hereinafter, each process executed by the icon arrangement system 1 will be explained together with the processes executed by each of the modules described above.
In this specification, each module may execute its processing content as its own function, or may execute it via a predetermined application.

[Learning process executed by computer 10]
The learning process executed by the computer 10 will be explained based on FIG. 3. This figure is a diagram showing a flowchart of the learning process executed by the computer 10. This learning process includes an acquisition process (step S1) of acquiring annotation data in which the first icon associated with the code attached to the foreground map is arranged in advance; The following are details of the learning process (step S2) in which the first icon is learned in association with the first icon, and the model generation process (step S3) in which a trained model is generated based on the learning results.

The annotation data acquisition module acquires annotation data in which the first icon associated with the code attached to the blueprint is arranged (step S10).
The code attached to the diagram is, for example, a predetermined character string consisting of any one or a combination of numbers, letters, symbols, etc. Furthermore, this code indicates structural members of a building such as beams, columns, walls, foundations, and floors. The first icon is, for example, a pin, mark, character string, or symbol.
The learning terminal 20 receives input from an administrator or the like who manages the learning terminal 20, and places a first icon on the blueprint. The learning terminal 20 receives an input from the administrator or the like about the placement of the first icon desired by the administrator for the code attached to the blueprint. The learning terminal 20 places this first icon at the location where the input is received (see FIG. 4).
The foreground map in which the first icons are arranged will be explained based on FIG. 4. This figure is a diagram schematically showing an example of a map in which the learning terminal 20 has arranged the first icons.
The learning terminal 20 receives an input for selection of a desired first icon 41 by the administrator from a list 42 of a plurality of first icons 41 . In this figure, the first icon 41 is a part of the character string of the name of a structural member (column, beam, floor, wall, base, pile, etc.) surrounded by a square. The learning terminal 20 accepts input to the reference numeral 43 attached to the diagram 40 . The learning terminal 20 arranges the first icon 41 whose selection has been accepted near the code 43 (for example, within a predetermined range from the code 43 and around the code 43). Here, the learning terminal 20 associates this code 43 with the first icon 41.
The learning terminal 20 transmits the map 40 on which the first icon 41 is arranged to the computer 10 as annotation data.
The annotation data acquisition module receives the blueprint 40 on which the first icon 41 is arranged, and acquires annotation data on which the first icon associated with the code attached to the blueprint is arranged.

Note that the map on which the learning terminal 20 arranges the first icon may be one that the learning terminal 20 obtains from another computer or the like, or may be one that is photographed by the learning terminal 20 with its own photographing device. The information may be stored in advance, or may be obtained by other methods.
Moreover, the number of first icons arranged by the learning terminal 20 may be one or more for one map.
In addition, the learning terminal 20 displays the first icon with a different attention level depending on the type of blueprint and predetermined conditions (for example, the content of the construction site, the orderer, the contractor, the worker, the structure), etc. You can also place it. Changing the degree of attention is intended to, for example, change the size, color classification, or highlight display.
Furthermore, the type of the first icon is not limited to the example described above.

Returning to FIG. 3, the continuation of the learning process will be explained.
The first identification module identifies each structure included in the acquired annotation data (step S11).
The first identification module analyzes the acquired annotation data and identifies each structure included in the map. The first identification module identifies the code attached to the floor plan and identifies the type of each structure (for example, a column, a beam, a floor, a wall, a base, and a pile) included in the floor plan. The first identification module may perform this identification by referring to a database or the like in which codes and types of structures are associated in advance. In the diagram 40 in FIG. 4 described above, the first identification module identifies the code 43 and identifies the type of structure corresponding to the code 43. The first identification module identifies C1 as the reference numeral 43, and identifies a column as the type of structure corresponding to C1.
The first identification module identifies the code of this structure and its type, and identifies each structure included in the acquired annotation data.

The learning module uses the acquired annotation data as teacher data to learn the map and the first icon in association with each other (step S12).
As described above, the learning module executes machine learning using supervised learning, unsupervised learning, reinforcement learning, etc., and deep learning using convolutional neural networks, recurrent neural networks, long/short-term memory, etc. as learning methods. In this embodiment, the learning method executed by the learning module will be described using machine learning using supervised learning as an example, as described above.
The learning module uses the code and type of the structure included in the identified blueprint and the first icon as training data, and learns by associating the blueprint in this annotation data with the first icon.

The trained model generation module generates a trained model based on the learning results (step S13).
The trained model generation module generates this trained model using general algorithms used in machine learning such as linear regression, random forest, decision tree, and k-nearest neighbor method. The algorithm used by the trained model generation module is not particularly limited, and any suitable algorithm may be used as appropriate.

The trained model storage module stores the generated trained model (step S14).

The above is the learning process.
The computer 10 uses the learned model created by the learning process to execute the process described below.

[Placement processing executed by computer 10]
The arrangement process executed by the computer 10 will be explained based on FIG. 5. This figure is a diagram showing a flowchart of the arrangement processing executed by the computer 10. This arrangement processing is the details of the arrangement processing (step S4) of arranging the second icon based on the generated trained model on the new background map described above.
This placement process is a process that uses the trained model created by the learning process described above.

The blueprint acquisition module acquires a new blueprint (step S20).
The blueprint acquisition module acquires a new blueprint for arranging icons from the worker terminal 30.
The worker terminal 30 transmits to the computer 10 a plan stored in advance by itself, a plan photographed by its own photographing device, or a plan obtained from another computer or the like.
The blueprint acquisition module acquires a new blueprint by receiving this blueprint.
Note that the map acquisition module may acquire this map from a terminal other than the worker terminal 30, may use a map stored in advance by itself, or may use other methods. You may also obtain a foreground map.

The second identification module identifies each structure included in the acquired new map (step S21).
The second identification module data-analyzes the acquired new map and identifies each structure included in the map. The second identification module identifies the code attached to the floor plan and identifies the type of each structure (eg, column, beam, floor, wall, base, pile) included in the floor plan. The second identification module may perform this identification by referring to a database or the like in which codes and types of structures are associated in advance. A second identification module identifies details of all structures included in the acquired plan.
The second identification module identifies each structure and identifies each structure included in the obtained new map.

The placement module places a second icon based on the generated trained model on the new sketch (step S22).
The second icon is, for example, a pin, mark, character string, or symbol.
The placement module refers to the learned model, identifies a second icon to be placed on the blueprint based on the code and type of the structure included in the identified blueprint, and places the identified second icon on the blueprint. (See Figure 6).
Based on FIG. 6, a background map in which the second icon is placed by the placement module will be described. This figure is a diagram schematically showing an example of a layout in which the second icon is arranged by the arrangement module.
The placement module specifies a second icon 51 to be placed on this plan based on the code and type of the structure included in the plan 50 and the learned model, and places the specified second icon 51 with this code. Place nearby. In this figure, the second icon 51 is placed over the symbol. Further, the second icon 51, like the first icon 41 described above, is a part of the character string of the name of a structural member (column, beam, floor, wall, base, pile, etc.) enclosed in a square. . By arranging the second icon 51 on the map 50, the arrangement module associates the second icon 51 with the code and type of the structure in which the second icon 51 is arranged.

Note that the placement module may place only one second icon or a plurality of second icons for one foreground.
In addition, the placement module arranges second icons with different attention levels depending on the type of blueprint and predetermined conditions (for example, contents of the construction site, orderer, contractor, worker, structure), etc. It's okay. Similar to the example described above, changing the degree of attention is intended to, for example, change the size, color classification, or highlight display.
Further, when the layout module outputs the blueprint on which the second icon is arranged to the worker terminal 30, the arrangement module may arrange the second icon in a freely movable format according to input from the worker. . In this case, the placement module may arrange the placed second icon in a movable format while extending the leader line from the original position of the second icon so that the corresponding part on the map can be identified. .
Further, the type of the second icon is not limited to the example described above.

Returning to FIG. 5, the continuation of the placement process will be explained.
The adding module adds metadata to the second icon (step S23).
The adding module adds a detailed diagram (miniature diagram) corresponding to the code of the identified structure, progress management information, etc. to the placed second icon as metadata.
Note that the provision module may provide metadata that includes data other than the above-mentioned example (for example, creation date and time, operator name).

The blueprint output module outputs a blueprint on which the second icon is arranged (step S24).
The blueprint output module transmits the blueprint on which the second icon is arranged to the worker terminal 30.
The worker terminal 30 receives this blueprint and displays it on its own display unit or the like.
The blueprint output module outputs the blueprint with the second icons arranged by displaying the blueprint with the second icons arranged on the worker terminal 30.
Note that the worker terminal 30 may also display metadata attached to the second icon by accepting an input for the second icon in the displayed map.
Further, the worker terminal 30 may be able to move the position of the second icon on the displayed plan by accepting an input for the second icon on the screen. In this case, the worker terminal 30 may move the position of the second icon while extending the leader line from the original position of the second icon so that the corresponding part on the sketch can be identified.

The above is the arrangement process.

[Relearning process executed by computer 10]
The relearning process executed by the computer 10 will be described based on FIG. 7. This figure is a flowchart of the relearning process executed by the computer 10.
This relearning process is a process that uses the learned model created by the above-described learning process and the foreground map in which the second icon is placed by the placement process.
Note that detailed explanations of processes similar to those described above will be omitted.

The learning module uses the foreground map in which the second icon is arranged as teacher data and learns the foreground map and the second icon in association with each other (step S30).
The learning method in this process may be the same as the learning method in the learning process described above.
The learning module uses the code of the structure included in the identified foreground map, its type, and the second icon as training data, and learns the foreground map and the second icon in association with each other.

The trained model generation module updates the generated trained model based on the learning results (step S31).
The learned model generation module updates the learned model generated and stored by the above-described learning process using the current learning results.

The trained model storage module stores the updated trained model (step S32).

The above is the relearning process.
When the computer 10 executes the placement process next time, it executes the process using the learned model updated by the relearning process.
The icon placement system 1 updates the learned model through the relearning process every time the placement process is executed, so the more times the process is performed, the more accurate the placement of the second icons can be.

[Change process executed by computer 10]
The change processing executed by the computer 10 will be described based on FIG. 8. This figure is a flowchart of the change processing executed by the computer 10.
This change process is a process that uses the foreground map in which the second icon has been placed by the above-described placement process, and this foreshadow map output to the worker terminal 30.
Note that detailed explanations of processes similar to those described above will be omitted.

The change reception module receives input of changes to the second icon (step S40).
The worker terminal 30 receives an input for changing the blueprint on which the second icon displayed on itself is arranged by the above-described arrangement process. The contents of the changes that the worker terminal 30 accepts input are changes to the second icon and changes to metadata. The worker terminal 30 receives input for changing the type, degree of attention, number, etc. of the second icon. Further, the worker terminal 30 receives an input for changing the metadata attached to the second icon.
The worker terminal 30 transmits the input change details to the computer 10.
The change reception module receives the change contents and accepts input of changes to the second icon.
The change reception module may not accept input for changes for a predetermined period of time (for example, after a predetermined period of time has elapsed after the output of the blueprint with the second icon placed) or an input from the worker terminal 30 indicating that no changes are required. If this is the case, for example, the change processing is ended without executing the subsequent processing.

Note that the worker terminal 30 may be one that accepts input of this change to the blueprint that is the source of the blueprint on which the second icon is placed. In this case, if the worker terminal 30 owns this blueprint, it accepts the arrangement of the second icon and the input of metadata for the blueprint it owns. If the worker terminal 30 does not own this blueprint, it acquires this blueprint from another computer, etc., and accepts input of the arrangement of the second icon and metadata for the acquired blueprint. . The worker terminal 30 transmits to the computer 10 the blueprint in which the arrangement of the second icon and the input of metadata are accepted. The change reception module may receive this blueprint and accept input of changes to the second icon.

The arrangement module re-arranges the second icon based on the received change (step S41).
The placement module changes the second icon originally placed on the blueprint and places a new second icon based on the received change content.

Note that when receiving an input from the worker terminal 30 to change the plan that is the source of the plan in which the second icon is placed, the placement module changes the second icon All you have to do is place the .

The adding module adds metadata again based on the received change content (step S42).
The adding module changes the metadata originally added to the second icon based on the received change content and adds it as new metadata.

The blueprint output module outputs a blueprint in which the changed second icon is arranged (step S43).
The process in step S43 is similar to the process in step S24 described above.

The above is the change process.

Although each of the above-mentioned processes is described as a separate process, the computer 10 can also be configured to execute a part or all of the above-mentioned processes in combination. Further, the computer 10 can also be configured to execute each process at a timing other than the timing described above.

The means and functions described above are realized by a computer (including a CPU, an information processing device, and various terminals) reading and executing a predetermined program. For example, the program may be provided from a computer via a network (SaaS: Software as a Service) or in a cloud service. Further, the program may be provided in a form recorded on a computer-readable recording medium. In this case, the computer reads the program from the recording medium, transfers it to an internal recording device or an external recording device, records it, and executes it. Alternatively, the program may be recorded in advance on a recording device (recording medium) and provided to the computer from the recording device via a communication line.

Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments described above. Furthermore, the effects described in the embodiments of the present invention are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. isn't it.

(1) An icon placement system that places icons on a blueprint of a building structure drawing,
An acquisition unit (for example, acquisition unit 11, annotation data acquisition module) and
a learning unit (for example, a learning unit 12, a learning module) that learns by associating the foreword and the first icon with the acquired annotation data as training data;
A model generation unit (for example, model generation unit 13, trained model generation module) that generates a trained model based on the learning results;
an arrangement unit (e.g., arrangement unit 14, arrangement module) that arranges a second icon (e.g., pin, mark, character string, symbol) based on the generated trained model on a new plan;
An icon placement system with.

According to the invention (1), it is possible to improve work efficiency.

(2) The code is a predetermined string of characters (for example, a string of numbers, letters, symbols, etc., or a combination of them);
The icon arrangement system described in (1).

According to the invention (2), it is possible to improve work efficiency.

(3) The code indicates a structural member of the building (e.g. beam, column, wall, foundation, floor),
The icon arrangement system described in (1).

According to the invention (3), it is possible to improve work efficiency.

(4) The learning unit associates the new foreground with the second icon and re-learns the new foreground with the second icon placed thereon as new teacher data.
The icon arrangement system described in (1).

According to the invention (4), it is possible to improve the accuracy of learning.

(5) The arrangement section changes the degree of attention of the second icon and arranges it.
The icon arrangement system described in (1).

According to the invention (5), it is possible to improve work efficiency.

(6) an adding unit (for example, an adding module) that adds metadata to the second icon;
The icon arrangement system according to (1), further comprising:

According to the invention (6), it is possible to improve work efficiency.

(7) The placement unit movably places the placed second icon while extending a leader line so that the corresponding part on the sketch map can be identified.
The icon arrangement system described in (1).

According to the invention (7), it is possible to improve work efficiency.

(8) An icon placement method executed by a computer for placing icons on a blueprint of a building structure drawing,
a step of acquiring annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance (for example, step S10);
a step (for example, step S12) of learning an association between the foreground map and the first icon using the acquired annotation data as training data;
a step of generating a trained model based on the learning results (for example, step S13);
a step of arranging a second icon based on the generated trained model on the new plan (for example, step S22);
An icon arrangement method comprising:

(9) In the computer that places the icon on the blueprint of the building structure drawing,
acquiring annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance (for example, step S10);
a step of learning by associating the foreground map with the first icon using the acquired annotation data as training data (for example, step S13);
a step of generating a trained model based on the learning results (for example, step S13);
a step of arranging a second icon based on the generated learned model on the new sketch (for example, step S22);
A computer readable program for executing.

1 Icon arrangement system 5 Network 10 Computer 11 Acquisition unit 12 Learning unit 13 Model generation unit 14 Arrangement unit 20 Learning terminal 30

Worker terminal

40, 50 Foreground map 41 First icon 42 List 43 Code 51 Second icon

Claims

An icon placement system that places icons on a blueprint of a building structure drawing,
an acquisition unit that acquires annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance;
a learning unit that learns by associating the foreword and the first icon with the acquired annotation data as training data;
a model generation unit that generates a trained model based on the learning results;
a placement unit that places a second icon based on the generated trained model on the new sketch;
An icon placement system with.
the code is a predetermined character string;
The icon arrangement system according to claim 1.
The code indicates a structural member of the building,
The icon arrangement system according to claim 1.
The learning unit associates the new foreground with the second icon and re-learns the new foreground with the second icon as new teacher data.
The icon arrangement system according to claim 1.
The placement unit changes the degree of attention of the second icon and arranges it.
The icon arrangement system according to claim 1.
an adding unit that adds metadata to the second icon;
The icon arrangement system according to claim 1, further comprising:.
The arrangement section movably arranges the arranged second icon while extending a leader line so that the corresponding part on the diagram can be identified.
The icon arrangement system according to claim 1.
An icon placement method executed by a computer for placing icons on a blueprint of a building structure drawing, the method comprising:
acquiring annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance;
a step of learning by associating the foreword and the first icon with the acquired annotation data as training data;
a step of generating a trained model based on the learning results;
arranging a second icon based on the generated trained model on the new plan;
An icon arrangement method comprising:
On the computer that places the icon on the blueprint of the building structure drawing,
acquiring annotation data in which a first icon associated with a code attached to the foreground map is arranged in advance;
learning by associating the foreword and the first icon with the acquired annotation data as training data;
generating a trained model based on the learning results;
arranging a second icon based on the generated trained model on the new plan;
A computer readable program for executing.