JP2021022330A - Sheet metal processing estimate creation support device and sheet metal processing estimate creation support method - Google Patents

Abstract

To reduce labor required to create estimates for sheet metal processing.SOLUTION: In a sheet metal processing estimate creation support device 1, a database 11 has associated and stored existing drawing data on sheet metal processing and estimate data. A new drawing data input reception unit 13 receives an input of new drawing data related to sheet metal processing. A search unit 14 searches the existing drawing data stored in the database 11 for existing drawing data similar to the new drawing data by a similar determination model M2 generated by machine learning in advance. A selection input reception unit 15 receives an input to select the retrieved existing drawing data. An estimate data output unit 16 outputs estimate data stored in the database 11 in association with the selected existing drawing data. The estimate data on sheet metal processing made in the past can be referred to more easily and labor required to create estimate for sheet metal processing can be reduced.SELECTED DRAWING: Figure 1

Description

The present invention relates to a sheet metal processing estimate creation support device and a sheet metal processing estimate creation support method.

Generally, a sheet metal processing company is given a drawing of a product and is requested by an orderer to submit a quotation. For example, Patent Document 1 discloses a technique for simulating product manufacturing and creating an estimate when an order for manufacturing a product for sheet metal processing is received. In the technique of Patent Document 1, when the ordering party requests the contractor for a quotation for manufacturing the product, the contractor creates a three-dimensional figure from the three-dimensional view of the product. The three-dimensional figure is divided into a plurality of parts so that the processing can be performed properly.

A development drawing of each part is created. Material costs, blank processing costs, etc. are calculated from the development drawing. The process of making a hole is determined from each development drawing. The processing cost for making a hole is calculated from the process for making a hole. The bending process is determined from each developed view. The bending processing cost is calculated from the bending process. Parts are assembled and products are manufactured. Welding costs, painting costs, assembly costs, etc. are calculated from the product. An estimate is created from the costs calculated as described above.

JP-A-2002-203007

By the way, in the above technique, drawings are referred to for each process of making a hole, a process of bending, a process of assembling parts, and the like, and a cost is calculated for each process. Therefore, there is a drawback that it takes time to create an estimate. It is also conceivable to refer to the data of the estimation of sheet metal processing performed in the past and create an estimate according to the order for manufacturing a new sheet metal processing product. However, it is difficult to search the enormous amount of data of sheet metal processing performed in the past in response to an order for manufacturing a new sheet metal processing product, and at present, estimates are created based on human memory and experience. Therefore, there is a drawback that labor is required to create an estimate for sheet metal processing.

Therefore, an object of the present invention is to provide a sheet metal processing estimate creation support device and a sheet metal processing estimate creation support method capable of reducing the labor required for creating a sheet metal processing estimate.

The present invention is a database in which existing drawing data related to sheet metal processing and estimation data related to estimation of sheet metal processing based on existing drawing data are stored in association with each other, and a new drawing data input receiving unit that accepts input of new drawing data related to sheet metal processing. Search for existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit by the similarity determination model generated in advance by machine learning from the existing drawing data stored in the database. The unit, the selection input reception unit that accepts the input to select the existing drawing data searched by the search unit, and the estimate stored in the database associated with the existing drawing data selected by the input received by the selection input reception unit. It is a sheet metal processing estimate creation support device equipped with an estimate data output unit that outputs data.

According to this configuration, in the sheet metal processing estimate creation support device, the existing drawing data and the estimate data related to the sheet metal processing are associated and stored in the database. The new drawing data input receiving unit accepts the input of new drawing data related to sheet metal processing. The search unit searches the existing drawing data stored in the database for existing drawing data similar to the new drawing data by the similarity determination model generated in advance by machine learning. The selection input reception unit accepts input for selecting existing drawing data searched by the search unit. The quotation data output unit outputs the quotation data stored in the database in association with the selected existing drawing data. As a result, the existing drawing data similar to the new drawing data is searched by inputting the new drawing data, and the estimation data associated with the existing drawing data selected from the searched existing drawing data is output. It is possible to more easily refer to the estimated data of the sheet metal processing, and it is possible to reduce the labor required to create the estimate of the sheet metal processing.

In this case, the similarity determination model is trained by using the new drawing data related to the input received by the new drawing data input reception unit and the existing drawing data selected by the input received by the selection input reception unit as teachers. It is preferable to further provide a model training unit.

According to this configuration, the similarity determination model training unit trains the new drawing data related to the input received by the new drawing data input receiving unit and the existing drawing data selected by the input received by the selective input receiving unit. Therefore, since the similarity determination model is trained, the accuracy of searching the existing drawing data similar to the new drawing data can be improved by the trained similarity determination model.

In addition, the database stores attribute data related to sheet metal processing attributes based on existing drawing data, existing drawing data, and estimation data in association with each other, and inputs attribute data related to sheet metal processing attributes based on new drawing data. The search unit is further provided with an attribute data input receiving unit that accepts, and the search unit uses a similarity determination model to create new drawing data from existing drawing data stored in the database associated with the attribute data related to the input received by the attribute data input receiving unit. It is preferable to search for existing drawing data similar to the new drawing data related to the input received by the input receiving unit.

According to this configuration, the database stores the attribute data related to the attributes of sheet metal processing based on the existing drawing data, the existing drawing data, and the estimation data in association with each other. The attribute data input receiving unit accepts the input of attribute data related to the attributes of sheet metal processing using new drawing data. The search unit relates to the input received by the new drawing data input reception unit based on the similarity determination model from the existing drawing data stored in the database associated with the attribute data related to the input received by the attribute data input reception unit. Search for existing drawing data that is similar to the new drawing data. That is, the search unit searches the existing drawing data similar to the new drawing data from the existing drawing data limited by the attribute data. Therefore, it is possible to reduce the labor for the search unit to search the existing drawing data similar to the new drawing data from the existing drawing data.

In this case, the search unit has a plurality of similarity determination models generated in advance for each attribute data, and the existing drawing data stored in the database in association with the attribute data related to the input received by the attribute data input receiving unit. Searches for existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit by the similarity determination model generated for the attribute data related to the input received by the attribute data input receiving unit. Is preferable.

According to this configuration, the search unit has a plurality of similarity determination models generated in advance for each attribute data. The search unit generated the attribute data related to the input received by the attribute data input receiving unit from the existing drawing data stored in the database associated with the attribute data related to the input received by the attribute data input receiving unit. Existing drawing data similar to the new drawing data is searched by the similarity judgment model, that is, the similarity judgment model specialized for each attribute data. Therefore, it is possible to improve the accuracy of the search unit to search the existing drawing data similar to the new drawing data from the existing drawing data, as compared with the case where many attribute data are searched by the general similarity determination model. ..

Further, in the present invention, the new drawing data input receiving unit of the sheet metal processing estimate creation support device receives the input of new drawing data related to sheet metal processing, and the search unit of the sheet metal processing estimate creation support device has a new drawing data input receiving process. New by the similarity judgment model generated in advance by machine learning from the existing drawing data stored in the database in which the existing drawing data related to sheet metal processing and the estimated data related to the estimation of sheet metal processing based on the existing drawing data are associated and stored. The search process for searching existing drawing data similar to the new drawing data related to the input received in the drawing data input reception process, and the existing drawing data searched by the selection input reception unit of the sheet metal processing estimate creation support device in the search process. The selection input reception process that accepts the input to select is and the estimate data output unit of the sheet metal processing estimate creation support device are stored in the database in association with the existing drawing data selected by the input received in the selection input reception process. This is a sheet metal processing estimate creation support method including an estimate data output process for outputting estimate data.

In this case, the similarity determination model training unit of the sheet metal processing estimate creation support device has the new drawing data related to the input received in the new drawing data input reception process and the existing drawing selected by the input received in the selection input reception process. It is preferable to provide a similarity determination model training step for training the similarity determination model using the data as a teacher.

Further, in the database, attribute data related to the attributes of sheet metal processing based on existing drawing data, existing drawing data, and estimation data are stored in association with each other, and the attribute data input reception unit of the sheet metal processing estimation creation support device is used. It further includes an attribute data input reception process that accepts the input of attribute data related to the attributes of sheet metal processing using new drawing data. In the search process, the search unit is associated with the attribute data related to the input received in the attribute data input reception process. From the existing drawing data stored in the database, it is preferable to search the existing drawing data similar to the new drawing data related to the input received in the new drawing data input receiving process by the similarity determination model.

In this case, the search unit has a plurality of similarity determination models generated in advance for each attribute data, and in the search process, the search unit is associated with the attribute data related to the input received in the attribute data input reception process. From the existing drawing data stored in the database, the similarity judgment model generated for the attribute data related to the input received in the attribute data input receiving process is used to convert the new drawing data related to the input received by the new drawing data input receiving unit. It is preferable to search for similar existing drawing data.

According to the sheet metal processing estimate creation support device and the sheet metal processing estimate creation support method of the present invention, it is possible to reduce the labor required for creating an estimate for sheet metal processing.

It is a block diagram which shows the sheet metal processing estimate making support apparatus of embodiment. It is a figure which shows the example of the existing drawing data, the attribute data, the estimation data and the similarity determination model which are associated with a database and stored. It is a figure which shows the similarity determination model schematically. It is a flowchart which shows the process of the sheet metal processing estimate making support method of embodiment. It is a figure which shows the example of the display screen of the attribute data input reception process. It is a figure which shows the example of the display screen of the new drawing data input reception process. It is a figure which shows the example of the display screen after a search process. It is a figure which shows the example of the display screen of the selection input acceptance process. It is a figure which shows the example of the display screen of the estimate data output process.

Hereinafter, the sheet metal processing estimate creation support device and the sheet metal processing estimate creation support method according to the embodiment of the present invention will be described with reference to the drawings. As shown in FIG. 1, the sheet metal processing estimate creation support device 1 according to the present embodiment includes a database 11, an attribute data input reception unit 12, a new drawing data input reception unit 13, a search unit 14, a selection input reception unit 15, and an estimate. A data output unit 16 and a similarity determination model training unit 17 are provided. The sheet metal processing estimate creation support device 1 of the present embodiment is, for example, when there is a request to create an estimate when sheet metal processing is executed according to new drawing data related to sheet metal processing in the sheet metal processing estimation business. Support the preparation of the quotation so as to reduce the labor required to prepare the quotation.

The sheet metal processing estimate creation support device 1 is, for example, a computer device such as a personal computer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk, a liquid crystal display, and the like. In the sheet metal processing estimate creation support device 1, the program stored in the ROM is loaded into the RAM and executed by the CPU to execute the operations of each part such as the search unit 14. The sheet metal processing estimate creation support device 1 may be composed of a plurality of computer devices and storage devices. For example, the database 11, the attribute data input reception unit 12, the new drawing data input reception unit 13, the search unit 14, the selection input reception unit 15, the estimation data output unit 16, and the similarity judgment model training unit 17 are separate hard disks and personal computers, respectively. It may be composed of a computer device such as a computer.

The database 11 is a storage device such as a hard disk. As shown in FIG. 2, the database 11 stores the existing drawing data related to sheet metal processing, the attribute data related to the attributes of sheet metal processing based on the existing drawing data, and the estimated data related to the estimation of sheet metal processing based on the existing drawing data in association with each other. Has been done. In the example of FIG. 2, in addition to the existing drawing data, attribute data, and estimation data, a similarity determination model described later is associated and stored.

The existing drawing data is, for example, data of a drawing for which an estimate has been created when a request for creation of an estimate is made when sheet metal processing is executed according to the existing drawing data in the past. The attributes of the attribute data are, for example, the person in charge of sheet metal processing based on the existing drawing data, the machine name of the sheet metal processing, the type of 5/6 axis CAM (computer aided manufacturing), the type of bend machine, the material, and the sheet. Plate thickness, material size, part size, update date (update date of any of existing drawing data, attribute data and estimate data), creation date (creation date of any of existing drawing data, attribute data and estimate data) and Presence / absence of processing process (presence / absence of punching / bending / welding). The quotation data is, for example, the quotation data when there is a request to create a quotation when sheet metal processing is executed according to the existing drawing data in the past and the quotation is created. In the example of FIG. 2, existing drawing data having the same attributes other than the update date and the creation date are shown.

The attribute data input receiving unit 12 receives input of attribute data related to the attributes of sheet metal processing based on new drawing data. The attribute data received by the attribute data input receiving unit 12 does not necessarily have to be data related to all attributes of sheet metal processing using new drawing data, and may be, for example, data related to some attributes of sheet metal processing using new drawing data. ..

The new drawing data input receiving unit 13 receives input of new drawing data related to sheet metal processing. The new drawing data is, for example, drawing data when a request is made to create an estimate when sheet metal processing is executed according to new drawing data related to sheet metal processing in the sheet metal processing estimation business.

The search unit 14 uses the similarity determination model M1, the similarity determination model M2, the similarity determination model M3 to the similarity determination model Mn, which are generated in advance by machine learning from the existing drawing data stored in the database 11 (n is a natural number of 4 or more). ), Search for existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit 13. The search unit 14 uses the similarity determination models M1, M2, M3 to Mn to obtain new drawing data from the existing drawing data stored in the database 11 in association with the attribute data related to the input received by the attribute data input receiving unit 12. The existing drawing data similar to the new drawing data related to the input received by the input receiving unit 13 is searched.

The search unit 14 has a plurality of similarity determination models M1, M2, M3 to Mn generated in advance for each attribute data, and is associated with the attribute data related to the input received by the attribute data input receiving unit 12 and is associated with the database 11. Is received by the new drawing data input receiving unit 13 by the similarity determination models M1, M2, M3 to Mn generated for the attribute data related to the input received by the attribute data input receiving unit 12 from the existing drawing data stored in. Search for existing drawing data similar to the new drawing data related to the input.

The similarity determination models M1, M2, M3 to Mn are information used for classifying images of existing drawing data stored in the database 11 in association with attribute data corresponding to the similarity determination models M1, M2, M3 to Mn. .. For example, the similarity determination model M2 for attribute data relating to the attributes of machine name: XXX, material: AL-N2 (aluminum nitride), plate thickness: 1.5 mm, material size: 1524 mm × 3048 mm, and component size: 442 mm × 228 mm is Classification (similarity determination) is performed such as whether or not the parts shown in the image of the drawing data are rectangular parts and whether or not they are L-shaped parts. In the present embodiment, the classification destination (rectangular parts, L-shaped parts, etc. in the above example) is referred to as a category. For example, category C1 is a classification of rectangular parts, and category C2 is a classification of L-shaped parts.

The similarity determination models M1, M2, M3 to Mn input information based on the image of the drawing data, and output information indicating the category in which the image is classified. For example, the similarity determination models M1, M2, M3 to Mn output scores (similarity) for each category. The higher the score, the more likely the image is to fall into that category.

The similarity determination models M1, M2, M3 to Mn are configured to include a neural network. For example, the similarity determination models M1, M2, M3 to Mn are models using deep learning. As shown in FIG. 3, the similarity determination models M1, M2, M3 to Mn are composed of a plurality of neurons (nodes) included in any of the input layer (first layer) L1, the intermediate layer L2, and the output layer L3, respectively. ing. Intermediate layer L2 contains neurons of multiple layers.

Input based on the image P of the drawing data is performed on each of the plurality of neurons included in the input layer L1. The information input to the neurons of the input layer L1 is generated as follows, for example. First, the image P is divided into a certain number of regions A. For example, the vertical and horizontal directions of the image P are divided into preset numbers at equal intervals, and the image P is divided into rectangular areas A of the same size generated by the division. Information (vector) input to the neuron of the input layer L1 is generated from the pixel values of the pixels of each of the rectangular regions A. For example, the average value and the maximum value of the pixel values in the region A are used as information to be input to the neurons of the input layer L1.

While the information input to the input layer L1 is transmitted to the deeper layers, the features are extracted in each layer. That is, the neurons in each layer form a filter of a certain size, and the information is slid to extract a plurality of features for each filter. The information (numerical value) output from each of the plurality of neurons included in the output layer L3 indicates the score of each category.

Label information, which is information indicating the characteristics of a plurality of learning images and the learning images, is input to the search unit 14, machine learning is performed using the input learning images and label information, and similarity determination is performed. Models M1, M2, M3 to Mn are generated. The label information is information indicating the category of the learning image. That is, the learning image and the label information of the learning image are teachers of machine learning.

The learning image and label information are prepared by the administrator of the sheet metal processing estimate creation support device 1 or the like, and are input to the search unit 14. For example, when an image showing an L-shaped component is prepared as a learning image, the label information of the learning image is information indicating category C2 of the L-shaped component. In the search unit 14, deep learning is performed using the learning image and the label information corresponding to the learning image, and similarity determination models M1, M2, M3 to Mn for each attribute data are generated. Since the similarity determination models M1, M2, M3 to Mn generated by the search unit 14 are used for the search of existing drawing data by the search unit 14, the similarity determination models M1, M2, M3 to Mn of the search unit 14 The generation is performed prior to the search of the existing drawing data by the search unit 14.

The search unit 14 performs the above processing on the image P of the new drawing data related to the input received by the new drawing data input receiving unit 13, and outputs the score of each category. For example, the search unit 14 outputs the category with the highest score of the image P of the new drawing data in the order of the highest score of the existing drawing data stored in the database 11 in the category.

The selection input reception unit 15 receives an input for selecting existing drawing data searched by the search unit. The estimate data output unit 16 outputs the estimate data stored in the database 11 in association with the existing drawing data selected by the input received by the selection input reception unit 15.

The similarity determination model training unit 17 is similar to the new drawing data related to the input received by the new drawing data input receiving unit 13 and the existing drawing data selected by the input received by the selective input receiving unit 15 as a teacher. The determination models M1, M2, M3 to Mn are trained. The training of the similarity determination models M1, M2, M3 to Mn by the similarity determination model training unit 17 is performed, for example, by selecting an image of new drawing data related to the input received by the new drawing data input reception unit 13 as a learning image. Generation of similarity determination models M1, M2, M3 to Mn in the search unit 14 except that the label information indicating the category of the existing drawing data selected by the input received by the input reception unit 15 is a machine learning teacher. It is done in the same way as.

Hereinafter, the sheet metal processing estimate creation support method by the sheet metal processing estimate creation support device of the present embodiment will be described. As shown in FIG. 4, the attribute data input receiving step 12 of the sheet metal processing estimate creation support device 1 receives the input of the attribute data related to the sheet metal processing attribute by the new drawing data is executed (S1). ..

As shown in FIG. 5, in the attribute data input reception process, the attribute item input reception frame 101, the attribute content input reception frame 102, and the attribute content input reception frame 102 are displayed on the display screen 100 of the liquid crystal display of the personal computer or the like constituting the sheet metal processing estimate creation support device 1. The new drawing data input reception frame 103 is displayed. In the attribute item input reception frame 101, the item of the attribute of sheet metal processing such as the material size and the material as described above is designated. The attribute content input reception frame 102 specifies the content of the sheet metal processing attribute specified in the attribute item input reception frame 101. On the display screen 100, the attribute item input reception frame 101 and the attribute content input reception frame 102 can be deleted or added. In the example of FIG. 5, input of material size: 1524 mm × 3048 mm and material: AL-N2 is accepted as attribute data. The new drawing data input receiving frame 103 is a frame used for inputting new drawing data in the new drawing data input receiving process.

As shown in FIG. 4, the new drawing data input receiving unit 13 of the sheet metal processing estimate creation support device 1 executes a new drawing data input receiving step of receiving input of new drawing data related to sheet metal processing (S2). As shown in FIG. 6, in the new drawing data input receiving process, the new drawing data file is dragged and dropped from the new drawing data window 104 showing the new drawing data file to the new drawing data input receiving frame 103. By doing so, the input of new drawing data is accepted. The reception of input of new drawing data may be executed by a method other than dragging and dropping to the new drawing data input receiving frame 103, such as directly opening the file displayed in the new drawing data window 104. ..

As shown in FIG. 4, the search unit 14 of the sheet metal processing estimate creation support device 1 stores in the database 11 in which the existing drawing data related to sheet metal processing and the estimation data related to the estimation of sheet metal processing based on the existing drawing data are associated and stored. Existing drawing data similar to the new drawing data related to the input received in the new drawing data input receiving step 13 by the similarity determination models M1, M2, M3 to Mn previously generated by machine learning from the stored existing drawing data. A search process for searching for is performed (S3).

In the search step, in the search step, the search unit 14 uses the existing drawing data stored in the database 11 in association with the attribute data related to the input received in the attribute data input receiving step to determine the similarity determination models M1, M2, M3. ~ Mn searches for existing drawing data similar to the new drawing data related to the input received in the new drawing data input receiving process. That is, the search unit 14 does not search all the existing drawing data stored in the database 11, but searches a part of the existing drawing data corresponding to the attribute data related to the input received in the attribute data input receiving process. To do.

In the search process, the search unit 14 relates to the input received in the attribute data input receiving process from the existing drawing data stored in the database 11 associated with the attribute data related to the input received in the attribute data input receiving process. The similarity determination models M1, M2, M3 to Mn generated for the attribute data are used to search for existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit 13. For example, as in the example of FIG. 5, when the input of the material size: 1524 mm × 3048 mm and the material: AL-N2 is accepted as the attribute data, the search is executed by the similarity determination model M2 generated for the attribute data. Will be done.

The search unit 14 performs the above processing on the image P of the new drawing data by the similarity determination model M2 generated for the attribute data related to the input received in the attribute data input receiving process, and outputs the score of each category. To do. The search unit 14 describes the category of the highest score of the image P of the new drawing data in the existing drawing data stored in the database 11 in association with the attribute data related to the input received in the attribute data input receiving process. The highest score is output as a similar order.

As shown in FIG. 7, after the search step, the thumbnail of the drawing of the new drawing data and the attribute data related to the attribute of sheet metal processing by the new drawing data are displayed on the new drawing data display frame 105 of the display screen 100. Further, in the search result display frame 106 of the display screen 100, a thumbnail of the drawing of the existing drawing data, attribute data related to the attribute of sheet metal processing by the existing drawing data, and estimation data stored in association with the existing drawing data. Are displayed in a similar order.

As shown in FIG. 4, the selection input reception step 15 of the sheet metal processing estimate creation support device 1 receives the input for selecting the existing drawing data searched in the search process (S4). As shown in FIG. 8, in the selection input receiving process, for example, the existing drawing data that the user considers to be most similar is selected from the existing drawing data displayed in the search result display frame 106 in the order of similarity.

As shown in FIG. 4, the quotation data output unit 16 of the sheet metal processing quotation creation support device 1 is associated with the existing drawing data selected by the input received in the selection input reception process, and is stored in the database 11. The estimate data output process for outputting the above is executed (S5). As shown in FIG. 9, in the estimation data output process, the estimation data output frame 107 is provided with the thumbnail of the drawing of the new drawing data displayed in the new drawing data display frame 105 and the attribute data related to the attributes of sheet metal processing by the new drawing data. , The thumbnail of the drawing of the existing drawing data selected by the input received in the selection input receiving process, the attribute data related to the attribute of sheet metal processing by the existing drawing data, and the estimation data stored in association with the existing drawing data. Is displayed.

The quotation data output by the quotation data output process is used, for example, to create a quotation for sheet metal processing using new drawing data by an arbitrary quotation creation program installed in a personal computer or the like constituting the sheet metal processing quotation creation support device 1. It is possible to do. After creating the sheet metal processing estimate based on the new drawing data, the new drawing data is stored in the database 11 as existing drawing data by associating the attribute data related to the sheet metal processing attributes based on the existing drawing data, the existing drawing data, and the estimation data. Will be remembered.

As shown in FIG. 4, the similarity determination model training unit of the sheet metal processing estimate creation support device 1 uses the new drawing data related to the input received in the new drawing data input receiving process and the input received in the selective input receiving process. A similarity determination model training step of training the similarity determination model is executed using the selected existing drawing data as a teacher (S6).

In the present embodiment, in the sheet metal processing estimate creation support device 1, the database 11 stores existing drawing data and estimate data related to sheet metal processing in association with each other. The new drawing data input receiving unit 13 receives input of new drawing data related to sheet metal processing. The search unit 14 searches the existing drawing data stored in the database 11 for existing drawing data similar to the new drawing data by the similarity determination models M1, M2, M3 to Mn generated in advance by machine learning. The selection input reception unit 15 accepts the input for selecting the existing drawing data searched by the search unit 14. The quotation data output unit 16 outputs the quotation data stored in the database 11 in association with the selected existing drawing data. As a result, the existing drawing data similar to the new drawing data is searched by inputting the new drawing data, and the estimation data associated with the existing drawing data selected from the searched existing drawing data is output. It is possible to more easily refer to the estimated data of the sheet metal processing, and it is possible to reduce the labor required to create the estimate of the sheet metal processing.

In other words, as in the past, in response to an order for manufacturing a new sheet metal processing product, it is possible to make an estimate by relying on human memory and experience while referring to the huge amount of data on sheet metal processing performed in the past. However, there is a drawback that a great deal of labor is required and the estimated amount of money also varies. On the other hand, in the present embodiment, the existing drawing data similar to the new drawing data is searched by inputting the new drawing data, and the estimation data associated with the existing drawing data is output. Therefore, the labor required to create the estimation for sheet metal processing. Is significantly reduced. Further, since the existing drawing data similar to the new drawing data is searched with the accuracy within a certain range, the accuracy of the estimated amount can be improved.

Further, in the present embodiment, the similarity determination model training unit 17 selects new drawing data related to the input received by the new drawing data input receiving unit 13 and the existing drawing selected by the input received by the selective input receiving unit 15. Since the similarity determination models M1, M2, M3 to Mn are trained using the data as a teacher, the trained similarity determination models M1, M2, M3 to Mn search for existing drawing data similar to the new drawing data. The accuracy can be improved.

Further, in the present embodiment, the database 11 stores the attribute data relating to the attributes of sheet metal processing based on the existing drawing data, the existing drawing data, and the estimation data in association with each other. The attribute data input receiving unit 12 accepts the input of attribute data related to the attributes of sheet metal processing using new drawing data. The search unit 14 uses the similarity determination models M1, M2, M3 to Mn to obtain new drawing data from the existing drawing data stored in the database 11 in association with the attribute data related to the input received by the attribute data input receiving unit 12. The existing drawing data similar to the new drawing data related to the input received by the input receiving unit 13 is searched. That is, the search unit 14 searches for existing drawing data similar to the new drawing data from the existing drawing data limited by the attribute data. Therefore, it is possible to reduce the effort of the search unit 14 to search the existing drawing data similar to the new drawing data from the existing drawing data.

In particular, when the search unit 14 searches for existing drawing data similar to the new drawing data using the similarity determination models M1, M2, M3 to Mn, the search unit 14 makes it relatively easy to determine the similarity regarding the shape of the object. However, it is difficult to determine the similarity of the size and material of the object. Therefore, the accuracy of the search can be improved by searching the existing drawing data similar to the new drawing data from the existing drawing data whose size and material are limited by the attribute data.

Further, according to the present embodiment, the search unit 14 has a plurality of similarity determination models M1, M2, M3 to Mn generated in advance for each attribute data. From the existing drawing data stored in the database 11 associated with the attribute data related to the input received by the attribute data input receiving unit 12 by the search unit 14, the attribute data related to the input received by the attribute data input receiving unit 12 Existing drawing data similar to the new drawing data is searched by the similarity determination models M1, M2, M3 to Mn generated for, that is, the similarity determination models M1, M2, M3 to Mn specialized for each attribute data. Therefore, it is possible to improve the accuracy of the search unit to search the existing drawing data similar to the new drawing data from the existing drawing data, as compared with the case where many attribute data are searched by the general similarity determination model. ..

It should be noted that the present invention is not limited to the above-described embodiment, and it goes without saying that various modifications can be made without departing from the gist of the embodiment of the present invention.

1 ... Sheet metal processing estimate creation support device, 11 ... Database, 12 ... Attribute data input reception unit, 13 ... New drawing data input reception unit, 14 ... Search unit, 15 ... Selective input reception unit, 16 ... Estimate data output unit, 17 ... Similarity judgment model training department, 100 ... Display screen, 101 ... Attribute item input reception frame, 102 ... Attribute content input reception frame, 103 ... New drawing data input reception frame, 104 ... New drawing data window, 105 ... New drawing data display Frame, 106 ... Search result display frame, 107 ... Estimated data output frame, M1, M2, M3, Mn ... Similarity judgment model, P ... Image, A ... Area, L1 ... Input layer, L2 ... Intermediate layer, L3 ... Output layer , C1, C2 ... Category.

Claims (8)

A database in which existing drawing data related to sheet metal processing and estimation data related to estimation of sheet metal processing based on the existing drawing data are associated and stored.
A new drawing data input reception unit that accepts input of new drawing data related to sheet metal processing,
From the existing drawing data stored in the database, the existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit is obtained by the similarity determination model generated in advance by machine learning. Search section to search and
A selection input reception unit that accepts input for selecting the existing drawing data searched by the search unit, and
An estimate data output unit that outputs the estimate data stored in the database in association with the existing drawing data selected by the input received by the selection input reception unit.
Sheet metal processing estimate creation support device equipped with. The similarity determination model is trained using the new drawing data related to the input received by the new drawing data input receiving unit and the existing drawing data selected by the input received by the selection input receiving unit as teachers. The sheet metal processing estimate creation support device according to claim 1, further comprising a similarity determination model training unit. In the database, attribute data relating to sheet metal processing attributes based on the existing drawing data, the existing drawing data, and the estimation data are stored in association with each other.
Further provided with an attribute data input receiving unit for receiving the input of the attribute data regarding the attributes of sheet metal processing based on the new drawing data.
The search unit uses the similarity determination model to obtain the new drawing data input receiving unit from the existing drawing data stored in the database in association with the attribute data related to the input received by the attribute data input receiving unit. The sheet metal processing estimate creation support device according to claim 1 or 2, which searches the existing drawing data similar to the new drawing data related to the input received by. The search unit
It has a plurality of the similarity determination models generated in advance for each of the attribute data.
Generated from the existing drawing data associated with the attribute data related to the input received by the attribute data input receiving unit and stored in the database, the attribute data related to the input received by the attribute data input receiving unit is generated. The sheet metal processing estimate creation support device according to claim 3, wherein the existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit is searched by the similarity determination model. The new drawing data input reception process of the sheet metal processing estimate creation support device accepts the input of new drawing data related to sheet metal processing, and the new drawing data input reception process.
From the existing drawing data stored in the database in which the search unit of the sheet metal processing estimation creation support device stores the existing drawing data related to sheet metal processing and the estimation data related to the estimation of sheet metal processing based on the existing drawing data in association with each other. , A search step of searching the existing drawing data similar to the new drawing data related to the input received in the new drawing data input receiving step by the similarity determination model generated in advance by machine learning.
A selection input reception process in which the selection input reception unit of the sheet metal processing estimate creation support device accepts an input for selecting the existing drawing data searched in the search process.
The quotation data output unit of the sheet metal processing quotation creation support device outputs the quotation data stored in the database in association with the existing drawing data selected by the input received in the selection input reception process. Output process and
Sheet metal processing estimate creation support method equipped with. The similarity determination model training unit of the sheet metal processing estimate creation support device is selected by the new drawing data related to the input received in the new drawing data input reception process and the input received in the selection input reception process. The sheet metal processing estimate creation support method according to claim 5, further comprising a similarity determination model training step of training the similarity determination model using existing drawing data as a teacher. In the database, attribute data relating to sheet metal processing attributes based on the existing drawing data, the existing drawing data, and the estimation data are stored in association with each other.
The attribute data input receiving unit of the sheet metal processing estimate creation support device further includes an attribute data input receiving process for receiving the input of the attribute data related to the sheet metal processing attribute based on the new drawing data.
In the search step, the search unit uses the similarity determination model to generate the new data from the existing drawing data stored in the database in association with the attribute data related to the input received in the attribute data input receiving step. The sheet metal processing estimate creation support method according to claim 5 or 6, wherein the existing drawing data similar to the new drawing data related to the input received in the drawing data input receiving process is searched. The search unit has a plurality of the similarity determination models generated in advance for each of the attribute data.
In the search step, the search unit receives the existing drawing data associated with the attribute data related to the input received in the attribute data input receiving step and stored in the database in the attribute data input receiving step. 7. The existing drawing data similar to the new drawing data related to the input received by the new drawing data input receiving unit is searched by the similarity determination model generated for the attribute data related to the input. The sheet metal processing estimate creation support method described in.

Images