JP2023082281A - Design support system, information processing device, design support method and program - Google Patents

Abstract

To easily acquire information necessary for design.SOLUTION: A design support system includes: a database 20 in which a plurality of items showing quality of a structure and design information for designing the structure are correlated to each other and stored for each structure; and an information processing device 10 which receives as input, the plurality of items on the basis of operation received from the outside, and on the basis of the plurality of received items, retrieves design information from the database 20, outputs the retrieved design information, compares the plurality of received items with the plurality of items stored in the database 20, and retrieves design information associated with items in accordance with the number of the items coincident with each other from the database 20.SELECTED DRAWING: Figure 1

Description

The present invention relates to a design support system, an information processing apparatus, a design support method, and a program.

When designing a structure, if a similar design has been done in the past, it is efficient to design with reference to the information on the past design. As a technique for acquiring information about past designs, for example, a technique for storing and visualizing improvement points and side effects caused by past design changes in association with each other has been considered (see, for example, Patent Document 1). .).

JP 2020-95377 A

When the amount of information about past designs is enormous, it is not easy to obtain desired information from it. In addition, in the technique as described in Patent Document 1, only the relationship between the points improved by the design change and the side effects is visualized. Therefore, the desired information cannot be obtained in the initial design. Thus, there is a problem that information necessary for design cannot be easily obtained.

An object of the present invention is to provide a design support system, an information processing apparatus, a design support method, and a program that can easily obtain information necessary for design.

The design support system of the present invention is
a database that stores a plurality of items indicating properties of a structure and design information for designing the structure in association with each structure;
an input unit for inputting the plurality of items based on an operation received from the outside;
a search unit for searching the design information from the database based on the plurality of items input by the input unit;
an output unit for outputting the design information searched by the search unit,
The search unit compares a plurality of items input by the input unit with a plurality of items stored in the database, and retrieves design information associated with the items according to the number of matching items. Search from database.

Further, the information processing device of the present invention is
an input unit for inputting a plurality of items indicating properties of a structure based on an operation received from the outside;
A search for searching the design information from a database that stores the plurality of items and design information for designing the structure in association with each of the structures based on the plurality of items input by the input unit. Department and
an output unit for outputting the design information searched by the search unit,
The search unit compares a plurality of items input by the input unit with a plurality of items stored in the database, and retrieves design information associated with the items according to the number of matching items. Search from database.

Further, the design support method of the present invention includes:
a process of obtaining a plurality of items indicating properties of the structure;
The acquired plurality of items are compared with the plurality of items associated in the database with the design information for designing the structure for each of the structures, and according to the number of items that match each other, the a process of retrieving design information associated with the item from the database;
and outputting the retrieved design information.

Further, the program of the present invention is
A program for a computer to execute,
to the computer,
a procedure for obtaining a plurality of items indicating properties of the structure;
The acquired plurality of items are compared with the design information for designing the structure for each of the structures and the plurality of items associated in the database, and the item is determined according to the number of items that match each other. a procedure of searching the database for design information associated with
and a step of outputting the retrieved design information.

In the present invention, information necessary for design can be easily obtained.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows 1st Embodiment of the design support system of this invention. 2 is a diagram showing an example of correspondence between a plurality of items stored in the database shown in FIG. 1 and design information; FIG. 2 is a diagram showing an example of correspondence between work information and support information stored in the database shown in FIG. 1; FIG. FIG. 2 is a diagram showing an example of correspondence between indication information and answer information stored in the database shown in FIG. 1; FIG. 2 is a diagram showing an example of the internal configuration of the information processing apparatus shown in FIG. 1; FIG. 6 is a diagram showing an example of inputs and outputs of a first learning model included in the learning models shown in FIG. 5; FIG. 6 is a diagram showing an example of inputs and outputs of a second learning model included in the learning model shown in FIG. 5; FIG. 2 is a flow chart for explaining an example of a process of acquiring design information in a design support method in the design support system shown in FIG. 1; 4 is a flowchart for explaining an example of a process of acquiring support information in the design support method in the design support system shown in FIG. 1; 4 is a flow chart for explaining an example of processing for acquiring answer information in the design support method in the design support system shown in FIG. 1; It is a figure which shows 2nd Embodiment of the design support system of this invention. 12 is a diagram showing an example of the internal configuration of the information processing apparatus shown in FIG. 11; FIG. 12 is a flowchart for explaining an example of a process of performing reinforcement learning using evaluation information in the design support method in the design support system shown in FIG. 11;

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.
(First embodiment)

FIG. 1 is a diagram showing the first embodiment of the design support system of the present invention. The control system in this embodiment has an information processing device 10 and a database 20, as shown in FIG. The information processing device 10 and the database 20 may be directly connected to each other, or may be communicatively connected to each other via a communication network.

The database 20 stores a plurality of items indicating properties of a structure and design information for designing the structure in association with each structure. Further, the database 20 associates and stores work information indicating work performed in the stage of designing a structure and support information for supporting the work indicated by the work information. In addition, the database 20 associates and stores indication information pointed out to the design information and reply information indicating a reply to the indication information. The database 20 may be provided within the information processing device 10 . Each piece of information stored in the database 20 is written in advance from the outside. Each piece of information stored in database 20 can be changed externally.

FIG. 2 is a diagram showing an example of correspondence between a plurality of items stored in the database 20 shown in FIG. 1 and design information. In the database 20 shown in FIG. 1, as shown in FIG. 2, a plurality of items indicating building outlines, a plurality of items indicating structural outlines, drawings, and calculation sheets correspond to each property that is a structure. It is stored with These pieces of information are information registered based on past performance. A property ID, which is identification information unique to the property, is assigned to each property. Items of building outline and structural outline include, for example, information indicating the structure such as wooden construction and reinforcing bars, the number of floors of the structure, shape (design), location, area, purpose, strength, seismic isolation device and vibration damping. This information indicates the properties of the structure, such as the presence or absence of equipment, the materials that make up the structure, the size and quantity of materials, the drainage structure, and the safety performance. Drawings and calculation sheets are design information for designing structures. The drawing is a design drawing of the structure. The design document is information indicating the design schedule, the number of days actually taken to construct the structure, the number of man-hours, the cost, and the like. The database 20 may store electronic files of drawings and calculations, or may store information indicating storage locations where electronic files of drawings and calculations are stored.

FIG. 3 is a diagram showing an example of correspondence between work information and support information stored in the database 20 shown in FIG. As shown in FIG. 3, the database 20 shown in FIG. 1 stores work information, design review minutes, defect information, and checklist items in association with each other. These pieces of information are information registered based on past performance. The design review minutes, defect information, and checklist are support information for supporting the work indicated by the work information, and are examples of the support information. The work information is information indicating each work performed at each stage of the design of the structure. The design review minutes indicate the minutes created when a review meeting was held for the work indicated by the work information. The design review minutes may store an electronic file of the minutes of the design review, or may store information indicating the storage location where the electronic file of the minutes of the design review is stored. The contents described in the minutes may be the same as the contents described in general minutes. The contents described in the minutes may be, for example, the date and place at which the review was held, the names of the participants in the review, and the contents of the proceedings. The defect information is information indicating the content of the defect that occurred when the work indicated by the work information was performed. The defect information is, for example, information indicating a shortage of parts, a delay in the schedule, a shortage of personnel, a mismatch of parts, and the like. The checklist items indicate items to be confirmed when performing the work indicated by the work information.

FIG. 4 is a diagram showing an example of correspondence between pointing information and answer information stored in the database 20 shown in FIG. As shown in FIG. 4, the database 20 shown in FIG. 1 stores pointing information, answers, and answer materials in association with each other. These pieces of information are information registered based on past performance. The indication information is information indicating the content pointed out by a specialized examination agency. The reply and reply materials are reply information for replying to an indication from a specialized reviewing agency, and are an example of reply information. The reply is information indicating the content of the reply to the reviewing organization in response to the indicated information. The answer material indicates the material attached to the answer. Answers and answer materials may store electronic files of the answers and answer materials, or may store information indicating the storage location where the electronic files of the answers and answer materials are stored.

The information processing device 10 is a device that inputs information based on an operation received from the outside, performs predetermined processing, and outputs the result. The information processing device 10 is, for example, a device having means for inputting and outputting information, such as a PC (Personal Computer), a tablet terminal, and a smart phone. FIG. 5 is a diagram showing an example of the internal configuration of the information processing apparatus 10 shown in FIG. 1. As shown in FIG. The information processing apparatus 10 shown in FIG. 1 includes an input unit 110, a learning model generation unit 120, a learning model 130, an inference unit 140, a search unit 150, and an output unit 160, as shown in FIG. . Note that FIG. 5 shows only main components related to the present embodiment among the components included in the information processing apparatus 10 shown in FIG.

Input unit 110 inputs information based on an operation received from the outside. The input unit 110 is, for example, a keyboard, mouse, touch pad, touch panel, or the like. The input unit 110 inputs a plurality of items described above. At this time, the input unit 110 inputs a plurality of items according to a screen that prompts the user to select one of a plurality of options for each item. For example, when a plurality of options are displayed using a pull-down menu for each of a plurality of items, the input unit 110 inputs the selected information based on the operation of selecting one of the options. Also, the input unit 110 can input general text information. Textual information is written information.

The learning model generation unit 120 performs machine learning on work information corresponding to text information to generate a first learning model. The learning model generation unit 120 also performs machine learning on the indication information corresponding to the text information to generate a second learning model. The first learning model and the second learning model are included in learning model 130 shown in FIG.

FIG. 6 is a diagram showing an example of inputs and outputs of the first learning model included in learning model 130 shown in FIG. A first learning model included in the learning model 130 shown in FIG. 5 is a learning model 131 that outputs work information when text information is input, as shown in FIG. In the learning phase of the learning model 131, the learning model generation unit 120 generates teacher data that associates externally input text information with work information. The work information is work information stored in the database 20 . The learning model generation unit 120 performs machine learning using the generated teacher data to generate a learning model 131 that outputs work information according to various text information. The text information input by the worker through the input unit 110 as work information does not always match the work information stored in the database 20 completely. Therefore, it is necessary to determine which of the pieces of work information stored in the database 20 corresponds to the text information that the worker inputs via the input unit 110 as work information. Therefore, a mechanism is provided to acquire work information stored in the database 20 from text information input via the input unit 110 using the learning model 131 . As a method of learning work information in the learning model 131, a general method for generating a learning model may be used.

FIG. 7 is a diagram showing an example of inputs and outputs of the second learning model included in learning model 130 shown in FIG. A second learning model included in the learning model 130 shown in FIG. 5 is a learning model 132 that outputs indication information when text information is input, as shown in FIG. In the learning phase of the learning model 132, the learning model generation unit 120 generates teacher data that associates externally input text information with indication information. The indicated information is indicated information stored in the database 20 . The learning model generation unit 120 performs machine learning using the generated teacher data to generate a learning model 132 that outputs indication information corresponding to various text information. The text information input by the operator as indication information through the input unit 110 does not always match exactly with the indication information stored in the database 20 . Therefore, it is necessary to determine which piece of indication information stored in the database 20 corresponds to the text information that the operator inputs as indication information via the input unit 110 . Therefore, a mechanism is provided for acquiring indication information stored in the database 20 from text information input via the input unit 110 using the learning model 132 . As a method of learning work information in the learning model 132, a general method for generating a learning model may be used.

The inference unit 140 acquires work information from the learning model 131 by inputting the text information input by the input unit 110 to the learning model 131 included in the learning model 130 . The inference unit 140 outputs the acquired work information to the search unit 150 . Also, the inference unit 140 inputs the text information input by the input unit 110 to the learning model 132 included in the learning model 130 , thereby acquiring indication information from the learning model 132 . The inference unit 140 outputs the acquired pointing information to the search unit 150 .

The search unit 150 searches the database 20 for design information based on a plurality of items input by the input unit 110 . Specifically, the search unit 150 compares a plurality of items input by the input unit 110 with a plurality of items stored in the database 20, and, depending on the number of items that match each other, matches the matching items. The attached design information is read from the database. For example, the search unit 150 retrieves design information associated with items in which the number of matching items between the items input by the input unit 110 and the items stored in the database 20 exceeds a predetermined threshold. It may be read from the database 20 . Further, the search unit 150 may read from the database 20 the design information that has the largest number of matching items between the items input by the input unit 110 and the items stored in the database 20 . The search unit 150 outputs the design information read from the database 20 to the output unit 160 .

Also, the search unit 150 searches the database 20 for support information based on the work information output from the inference unit 140 . Specifically, the search unit 150 uses the work information output from the inference unit 140 as a search key, and reads from the database 20 the support information associated with the work information in the database 20 . The search unit 150 outputs the support information read from the database 20 to the output unit 160 . Also, the search unit 150 searches the database 20 for answer information based on the indicated information output from the inference unit 140 . Specifically, the search unit 150 uses the indication information output from the inference unit 140 as a search key, and reads from the database 20 the answer information associated with the indication information in the database 20 . The search unit 150 outputs the answer information read from the database 20 to the output unit 160 .

The output section 160 outputs the design information output from the search section 150 . At this time, the output unit 160 may output the design information in descending order of the number of matching items between the items input by the input unit 110 and the items stored in the database 20 . Also, the output unit 160 outputs the support information output from the search unit 150 . Furthermore, the output section 160 outputs the answer information output from the search section 150 . The output mode of the output section 160 may be a mode in which information to be output is stored in a storage section (not shown), or a mode in which information to be output is displayed on a display section (not shown).

A design support method in the design support system shown in FIG. 1 will be described below. FIG. 8 is a flowchart for explaining an example of a process for acquiring design information in the design support method in the design support system shown in FIG.

First, the display unit (not shown) provided in the information processing apparatus 10 displays a display prompting the worker to input items of building outline and structure outline (step S1). At this time, the display unit displays a form for inputting the items of building outline and structure outline. This form may display a plurality of options for each item as described above using a pull-down menu. After that, when the worker performs an operation for inputting the items of the building outline and the structure outline according to the display on the display unit, the items are input (obtained) based on the operation received by the input unit 110 (step S2).

Then, the search unit 150 compares the items input by the input unit 110 with the items stored in the database 20 (step S3). Based on the result of the comparison, the search unit 150 searches the database for the design information associated with the matching items according to the number of matching items (step S4). Subsequently, the output unit 160 outputs the design information read by the search unit 150 (step S5).

FIG. 9 is a flow chart for explaining an example of a process of acquiring support information in the design support method in the design support system shown in FIG.

When the worker performs an operation of inputting text information indicating work information to the input unit 110, the input unit 110 inputs (obtains) the text information (step S11). Then, the inference unit 140 inputs the text information input by the input unit 110 to the learning model 131 included in the learning model 130 (step S12). Then, the inference unit 140 acquires work information from the learning model 131 (step S13).

Subsequently, the search unit 150 uses the work information acquired by the inference unit 140 as a search key to search the database 20 for support information associated with the work information (step S14). The search unit 150 reads out the searched support information from the database 20 . The output unit 160 outputs the support information read by the search unit 150 (step S15).

In step S5, the worker prepares documents to be submitted to the examination agency using the drawing information and calculation sheet information included in the design information output by the output unit 160. FIG. The worker submits the prepared document to the examination agency. During the examination period, the documents submitted by the workers are examined, and the workers are notified of the indicated matters (indicated information) indicating the matters that need to be pointed out.

FIG. 10 is a flow chart for explaining an example of processing for acquiring answer information in the design support method in the design support system shown in FIG.

When the operator performs an operation of inputting text information indicating indication information to the input unit 110, the input unit 110 inputs (obtains) the text information (step S21). Then, the inference unit 140 inputs the text information input by the input unit 110 to the learning model 132 included in the learning model 130 (step S22). Then, the inference unit 140 acquires indication information from the learning model 131 (step S23).

Subsequently, the search unit 150 searches the database 20 for answer information associated with the indication information using the indication information acquired by the inference unit 140 as a search key (step S24). The search unit 150 reads out the searched answer information from the database 20 . The output unit 160 outputs the answer information read by the search unit 150 (step S25).

In steps S5, S15, and S25, the output unit 160 may display the design information, support information, and answer information on a predetermined screen. By doing so, it is possible to assist the work of the worker who has confirmed the display.

It should be noted that each correspondence (correspondence of design information, correspondence of support information, and correspondence of answer information) stored in the database 20 may be associated with each other. In this case, it is preferable to link the properties using the property ID. Specifically, the database 20 assigns a property ID to each of the correspondence between work information and support information as shown in FIG. 3 and the correspondence between indication information and answer information as shown in FIG. They may be stored in association with each other. By specifying and inputting a property ID when inputting text information, it is possible to acquire support information and reply information specifying a property. Also, when a property ID is entered when text information is entered, and if support information and answer information have already been obtained for a design to which the same property ID has been assigned, these information may not be obtained. . In this case, the search unit 150 may not acquire information from the database 20, and even if the search unit 150 acquires information, the output unit 160 may not output the information. This makes it possible to avoid obtaining redundant information.

Also, when a worker uses this design support system, it may be possible to designate a worker ID uniquely assigned to the worker. In this case, when a worker enters multiple items to acquire design information, when entering text information to acquire support information, and when entering text information to acquire answer information, , the worker ID may be input and the information processing apparatus 10 may store the input worker ID as a history. By storing the worker ID, acquisition of design information, acquisition of support information, and acquisition of answer information performed by the worker can be associated with each worker. Thereby, for example, it is possible to identify which answer information the input for obtaining the support information is based on.

Thus, in this embodiment, the past design information, support information and answer information are registered in the database 20, and the design information, support information and answer information registered in the database 20 are used for the structure to be designed. The information processing apparatus 10 acquires the design information, the support information, and the answer information of the similar property from among them. This makes it possible to easily obtain information necessary for design. In order to search for design information of similar properties, the information processing device 10 displays options for the building outline and structural outline, and compares the contents selected from the displayed options with the contents stored in the database 20. to determine similar properties. This makes it possible to easily determine similar properties. Furthermore, the information processing apparatus 10 generates a learning model 130 that outputs work information and indication information by inputting text information, and stores the text information input based on the operation performed by the worker in the learning model 130. Input to obtain work information and indication information from the learning model 130 . As a result, even if the text information input by the input unit 110 does not completely match the work information and indication information stored in the database 20, the database 20 can associate the text information with the task information and indication information. Stored support information and answer information can be obtained.
(Second embodiment)

FIG. 11 is a diagram showing a second embodiment of the design support system of the present invention. The control system in this embodiment has an information processing device 11 and a database 20, as shown in FIG. The information processing device 11 and the database 20 may be directly connected to each other, or may be communicatively connected to each other via a communication network. The database 20 is the same as in the first embodiment.

FIG. 12 is a diagram showing an example of the internal configuration of the information processing device 11 shown in FIG. 11. As shown in FIG. The information processing apparatus 11 shown in FIG. 11 has an input unit 110, a learning model generation unit 121, a learning model 130, an inference unit 140, a search unit 150, and an output unit 160, as shown in FIG. . Note that FIG. 12 shows only main components related to this embodiment among the components provided in the information processing apparatus 11 shown in FIG. 11 . Input unit 110, learning model 130, inference unit 140, retrieval unit 150, and output unit 160 are the same as in the first embodiment.

In addition to the functions provided by the learning model generation unit 120 in the first embodiment, the learning model generation unit 121 uses the evaluation information input by the input unit 110 to perform reinforcement learning on the work information corresponding to the text information. Equipped with a function to perform The evaluation information is information indicating the result of evaluation by the worker as to whether or not the support information output by the output unit 160 is desired information for the worker. The evaluation information is input to the input unit 110 by the operator who has confirmed the support information output by the output unit 160 . The evaluation information may be information indicating the level of evaluation, or may be information indicating suitability. A method of reinforcement learning performed by the learning model generation unit 121 may be the same as a general reinforcement learning method. For example, if the evaluation information indicates a good level of evaluation for the support information, the learning model generation unit 121 may widen the range of the text information for outputting the support information. Further, for example, if the evaluation information indicates a poor level of evaluation of the support information, the learning model generation unit 121 converts the text information input when outputting the support information into may be excluded from the text information.

Processing for performing reinforcement learning using evaluation information among the design support methods in the design support system shown in FIG. 11 will be described below. FIG. 13 is a flow chart for explaining an example of a process of performing reinforcement learning using evaluation information in the design support method in the design support system shown in FIG. In the following description, an example in which the output unit 160 has an information display function will be described.

After the output unit 160 outputs the support information, the output unit 160 displays a form for inputting an evaluation (step S31). The display mode of this form is to prompt the input of evaluation information indicating the evaluation, and it is sufficient if the evaluation information can be input, and the details are not particularly defined. For example, the form may display a predetermined frame in which text can be entered, or may display a selectable evaluation level. When the input unit 110 inputs (acquires) the evaluation information according to the operator's operation (step S32), the learning model generation unit 121 uses the input evaluation information to generate work information corresponding to the text information of the learning model 131. Reinforcement learning is performed (step S33).

Thus, in this embodiment, the past design information, support information and answer information are registered in the database 20, and the design information, support information and answer information registered in the database 20 are used for the structure to be designed. The information processing apparatus 11 acquires the design information, support information, and answer information of the similar property from among them. This makes it possible to easily obtain information necessary for design. In order to search for design information of similar properties, the information processing device 11 displays options for the building outline and the structure outline, and compares the contents selected from the displayed options with the contents stored in the database 20. to determine similar properties. This makes it possible to easily determine similar objects. Furthermore, the information processing apparatus 11 generates a learning model 130 that outputs work information and indication information by inputting text information, and stores the text information input based on the operation performed by the worker in the learning model 130. Input to obtain work information and indication information from the learning model 130 . As a result, even if the text information input by the input unit 110 does not completely match the work information and indication information stored in the database 20, the database 20 can associate the text information with the task information and indication information. Stored support information and answer information can be obtained. Furthermore, the learning model 131 that outputs the support information is strengthened using the evaluation information about the output support information. Thereby, more desired support information can be acquired.

As described above, each function (process) is assigned to each component, but this assignment is not limited to the above. Moreover, the configurations of the constituent elements are also only examples, and are not limited to these. Moreover, what combined each embodiment may be used.

The processing performed by each of the information processing apparatuses 10 and 11 may be performed by a logic circuit manufactured according to the purpose. Further, a computer program (hereinafter referred to as a program) describing processing contents as a procedure is recorded in a recording medium readable by each of the information processing apparatuses 10 and 11, and the program recorded in the recording medium is transferred to the information processing apparatus 10. , 11 and executed. Recording media readable by each of the information processing apparatuses 10 and 11 include magneto-optical discs, DVDs (Digital Versatile Discs), CDs (Compact Discs), Blu-ray (registered trademark) Discs, and USB (Universal Serial Bus) memories. In addition to removable recording media such as the above, memories such as ROM (Read Only Memory) and RAM (Random Access Memory) built into each of the information processing apparatuses 10 and 11, HDD (Hard Disc Drive), SSD (Solid State Drive) ) etc. The program recorded on this recording medium is read by the CPU provided in each of the information processing apparatuses 10 and 11, and the same processing as described above is performed under the control of the CPU. Here, the CPU operates as a computer that executes a program read from a recording medium on which the program is recorded.

10, 11 information processing device 20 database 110 input unit 120, 121 learning model generation unit 130 to 132 learning model 140 inference unit 150 search unit 160 output unit

Claims (18)

a database that stores a plurality of items indicating properties of a structure and design information for designing the structure in association with each structure;
an input unit for inputting the plurality of items based on an operation received from the outside;
a search unit for searching the design information from the database based on the plurality of items input by the input unit;
an output unit for outputting the design information searched by the search unit,
The search unit compares a plurality of items input by the input unit with a plurality of items stored in the database, and retrieves design information associated with the items according to the number of matching items. A design support system that searches from a database. 2. The design support system according to claim 1, wherein said search unit searches said database for design information associated with items whose number of matching items exceeds a predetermined threshold. 3. The design support system according to claim 1, wherein said output unit outputs said design information in descending order of the number of matching items. 4. The design support system according to any one of claims 1 to 3, wherein said search unit searches for drawing information and calculation sheet information included in said design information from said database. a learning model generation unit that generates a first learning model by performing machine learning on work information corresponding to text information and indicating work performed in the design stage of the structure;
an inference unit that acquires the work information from the first learning model by inputting the text information input by the input unit into the first learning model;
the database associates and stores the work information and support information for supporting the work indicated by the work information;
the search unit searches the database for the support information based on the work information acquired by the inference unit;
5. The design support system according to claim 1, wherein said output unit outputs said support information searched by said search unit. 6. The design support according to claim 5, wherein said learning model generation unit performs machine learning on said work information corresponding to said text information using evaluation information input by said input unit and indicating evaluation of said support information. system. The learning model generation unit performs machine learning on indication information pointed out to the design information corresponding to the text information to generate a second learning model,
The inference unit acquires the indication information from the second learning model by inputting the text information input by the input unit into the second learning model,
the database associates and stores the indication information and answer information indicating an answer to the indication information;
the search unit searches the database for the answer information based on the indication information acquired by the inference unit;
7. The design support system according to claim 5, wherein said output unit outputs said answer information searched by said search unit. 8. The design support system according to claim 1, wherein said output unit stores said output information in a storage unit. 9. The design support system according to claim 1, wherein said output unit causes a display unit to display said information to be output. an input unit for inputting a plurality of items indicating properties of a structure based on an operation received from the outside;
A search for searching the design information from a database that stores the plurality of items and design information for designing the structure in association with each of the structures based on the plurality of items input by the input unit. Department and
an output unit for outputting the design information searched by the search unit,
The search unit compares a plurality of items input by the input unit with a plurality of items stored in the database, and retrieves design information associated with the items according to the number of matching items. An information processing device that searches from a database. a learning model generation unit that generates a first learning model by performing machine learning on work information corresponding to text information and indicating work performed in the design stage of the structure;
an inference unit that acquires the work information from the first learning model by inputting the text information input by the input unit into the first learning model;
Based on the work information acquired by the inference unit, the search unit searches the database for support information for assisting the work indicated by the work information, which is associated with the work information in the database. death,
The information processing apparatus according to claim 10, wherein said output unit outputs said support information searched by said search unit. The learning model generation unit performs machine learning on indication information pointed out to the design information corresponding to the text information to generate a second learning model,
The inference unit acquires the indication information from the second learning model by inputting the text information input by the input unit into the second learning model,
based on the indication information acquired by the inference unit, searching the database for answer information indicating an answer to the indication information, which is associated with the indication information in the database;
12. The information processing apparatus according to claim 11, wherein said output unit outputs said answer information searched by said search unit. a process of obtaining a plurality of items indicating properties of the structure;
The acquired plurality of items are compared with the plurality of items associated in the database with the design information for designing the structure for each of the structures, and according to the number of items that match each other, the a process of retrieving design information associated with the item from the database;
and outputting the searched design information. A process of performing machine learning on work information corresponding to text information and indicating work performed in the design stage of the structure to generate a first learning model;
a process of obtaining the text information;
a process of acquiring the work information from the first learning model by inputting the acquired text information into the first learning model;
a process of searching the database for support information for supporting the work indicated by the work information, which is associated with the work information in the database, based on the acquired work information;
14. The design support method according to claim 13, further comprising outputting said searched support information. a process of performing machine learning on indication information pointed out to the design information corresponding to the text information to generate a second learning model;
a process of acquiring the indication information from the second learning model by inputting the acquired text information into the second learning model;
a process of searching the database for response information indicating an answer to the pointed out information, which is associated with the pointed out information in the database, based on the acquired pointed out information;
15. The design support method according to claim 14, further comprising outputting said retrieved answer information. to the computer,
a procedure for obtaining a plurality of items indicating properties of the structure;
The acquired plurality of items are compared with the design information for designing the structure for each of the structures and the plurality of items associated in the database, and the item is determined according to the number of items that match each other. a procedure of searching the database for design information associated with
A program for executing a procedure for outputting the searched design information. a procedure of performing machine learning on work information corresponding to text information and indicating work performed in the design stage of the structure to generate a first learning model;
a procedure for obtaining the text information;
a step of acquiring the work information from the first learning model by inputting the acquired text information into the first learning model;
a procedure of searching the database for support information for supporting the work indicated by the work information, which is associated with the work information in the database, based on the acquired work information;
17. The program according to claim 16, for executing a procedure of outputting said retrieved support information. a procedure of performing machine learning on indication information pointed out to the design information corresponding to the text information to generate a second learning model;
a step of acquiring the indication information from the second learning model by inputting the acquired text information into the second learning model;
a procedure of searching the database for answer information indicating an answer to the indicated information, which is associated with the indicated information in the database, based on the obtained indicated information;
18. The program according to claim 17, for executing a step of outputting said retrieved answer information.

Images