Manufacturing support system and manufacturing support method

Abstract

To enable a wide variety of data to be utilized for support of design.SOLUTION: A production support system includes: an accumulated database which stores three-dimensional design information including a plurality of partial structures with attentional information given to at least one thereof; an input unit which receives data operation of a user onto the three-dimensional design information; a data conversion unit which converts information on the partial structures into graph data; an extraction unit which extracts the attentional information corresponding to the graph data to be input; and a proposition unit which inputs a selected structure to the extraction unit, the selected structure being a partial structure selected on the basis of input to the input unit by the user, and proposes to the user to give an attentional information candidate which is the attentional information extracted by the extraction unit to the selected structure.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a manufacturing support system and a manufacturing support method. [Background technology]

[0002] At product production sites, there is a huge amount of information related to each process of product design, process design, procurement, manufacturing, inspection, operation and maintenance, and this information is communicated between each process at the production site. It is expected that such information will be utilized to improve business efficiency and prevent product defects.

[0003] The issues in the information management process at production sites are broadly divided into information accumulation, search, and utilization, and are described below.

[0004] The information accumulation process requires the accumulation of a huge amount of information from the entire production process. The challenge with this process is that the amount of information between processes requires a large amount of work for the person in charge to input information, making it easy for errors to occur in the input information. Furthermore, since errors in the input information spread to related processes, it is a highly important challenge to improve the efficiency of information input by the person in charge and reduce information deficiencies. Here, processing instruction information and inspection information are examples of input information. At the current site where processing instructions and inspection work are performed, the input information is carefully checked by increasing the number of people in charge and the amount of work in order to prevent information errors. However, this careful checking work creates a new challenge of increasing labor costs, and there is a demand for improving the accuracy and efficiency of information input work.

[0005] In the information retrieval process, it is necessary to instantly retrieve desired information from accumulated information. However, because the information accumulated at product production sites is diverse, there is no common standard for comparing data when searching for information, and it is not easy to retrieve information for various purposes.

[0006] In the information utilization process, it is necessary to prevent accidents and improve the efficiency of the entire information management process by utilizing past information. However, there is a problem that the utilization of information has not progressed much because data collection in a data format suitable for information utilization has not progressed. For example, in the process design process, there are many similar cases in the past for processing instructions on drawings, and it is possible to improve efficiency by utilizing similar information, but currently the person in charge inputs the processing instructions while checking them as needed. Therefore, if the system can appropriately judge similar cases and complement the work, it is expected that the work of the person in charge to input processing instructions can be simplified.

[0007] There are systems that can prevent human error and improve work efficiency by streamlining the information management process at product production sites; these are called Product Life Management (PLM) tools. Current PLM tools manage information by linking the information to be managed to the 3D-CAD information of the 3D design drawings that are the basis of the product. However, there is no mechanism for realizing data search and utilization of generic information linked to product design drawings, so it is not easy to utilize similar data from other products or past cases, and the scope of application of the information management process is severely limited, which is a problem. Due to these issues, the current situation is that there has been little progress in streamlining information management processes that utilize similar data.

[0008] Patent Document 1 discloses an invention of a device that manages information on welding conditions. In detail, the welding control device includes a drawing storage unit that receives and stores drawing data of a processing target including one or more welds, a welding condition database that stores welding conditions previously determined for each combination of multiple types of welded members and multiple types of base materials, a welded portion extraction unit, and a welding condition generation unit, in which the drawing data in the drawing storage unit includes data indicating the type of welded members constituting the welds of the processing target and data indicating the type of base material, the welded portion extraction unit extracts data indicating the type of welded members and data indicating the type of base material for each of the one or more welds from the drawing data, and the welding condition generation unit determines, for each of the one or more welds, welding conditions corresponding to the combination of the type of welded members and the type of base material read by the welded portion extraction unit by referring to information stored in the welding condition database. [Prior art documents] [Patent documents]

[0009] [Patent Document 1] JP 2020-182973 A Summary of the Invention [Problem to be solved by the invention]

[0010] In the device described in Patent Document 1, the target structure is limited to the welded part. In addition, as the feature for identifying the welding information, a specific set of feature, i.e., the type of the welded member and the base material and the plate thickness, which are acquired in advance, is used for identifying the information. The technical problem of Patent Document 1 is that since it is a system for identifying the desired welding conditions using a specific set of feature, the use is severely limited. For example, the identification rule cannot be changed in response to the following changes (1)-(3): (1) change in the object of information management, (2) expansion of the identification range of the welding conditions, (3) introduction of a new feature. In addition, in the method described in Patent Document 1, when it becomes necessary to change the identification rule due to a change in the number of identification objects or the nature of the acquired data, the data format of the feature must be redefined each time. In particular, with regard to (1) change in the object of information management, the information of the product production process includes not only welding information, but also the material and shape of the screw, jig information, sintering processing information, adhesion information, friction stir welding information, inspection information, past defects, etc. In the information management method (information identification method) based on the data of a specific feature element as in Patent Document 1, a wide variety of information of the product production process cannot be managed. Therefore, there is a problem in that the application of the information management system is severely limited. [Means for solving the problem]

[0011] A manufacturing support system according to a first aspect of the present invention comprises an accumulation database storing three-dimensional design information including a plurality of partial structures, at least one of the plurality of partial structures being assigned attention information, an input unit that accepts data operations by a user on the three-dimensional design information, a data conversion unit that converts information of the partial structures into graph data, an extraction unit that extracts attention information corresponding to the input graph data, and a suggestion unit that inputs a selected structure, which is a partial structure selected based on an input by the user to the input unit, to the extraction unit and suggests to the user that a candidate attention information, which is the attention information extracted by the extraction unit, be assigned to the selected structure. A manufacturing support method according to a second aspect of the present invention is a manufacturing support method executed by a computer having a database storing three-dimensional design information including a plurality of substructures, at least one of which has been assigned attention information, and includes an input step of accepting data operations performed by a user on the three-dimensional design information, a data conversion step of converting the information of the substructures into graph data, an extraction step of determining a similarity between the plurality of substructures based on the graph data, and a proposal step of inputting a selected structure, which is a substructure selected based on an input by the user in the input step, into the extraction step, and proposing to the user that a candidate attention information, which is the attention information extracted by the extraction step, be assigned to the selected structure. Effect of the Invention

[0012] According to the present invention, by using graph data, it is possible to utilize a variety of data for design support. [Brief description of the drawings]

[0013] [Figure 1] Conceptual diagram showing the effects of the manufacturing support system [Diagram 2] Manufacturing support system hardware configuration diagram [Diagram 3] FIG. 1 shows information stored in a storage unit. [Figure 4] Welding model set configuration diagram [Diagram 5] Diagram showing the information contained in a model set [Figure 6] Functional block diagram of the manufacturing support system [Figure 7] A diagram showing the correspondence between three-dimensional structures and graph data [Figure 8] Flowchart showing the process of the model set generation unit [Figure 9] Flowchart showing the process of the model set generation unit [Figure 10] FIG. 1 is a diagram for explaining an example of a subgraph extraction process performed by a subset generation unit. [Figure 11]Conceptual diagram of common subset for welding [Figure 12] Conceptual diagram showing the process of the subset generation unit [Figure 13] Diagram explaining the prediction model [Figure 14] Diagram explaining the search model [Figure 15] Diagram explaining the search model [Figure 16] A diagram explaining the first method of the input assistance function [Figure 17] A diagram explaining the second method of the input assistance function [Figure 18] Diagram explaining the proposed changes feature [Figure 19] Diagram explaining the inspection assistance function DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] --First embodiment-- Hereinafter, a first embodiment of a manufacturing support system S will be described with reference to FIGS.

[0015] (System Configuration) FIG. 1 is a conceptual diagram showing the effect of the manufacturing support system S. When the process of completing a product is roughly divided into three steps, namely, design, manufacturing, and inspection, the manufacturing support system S supports the design process and the inspection process. In the design process, the manufacturing support system S helps reduce the input burden on the designer and prevent mistakes, and in the inspection process, it helps prevent inspection omissions. In the design process, the manufacturing support system S displays candidates for input information on a liquid crystal display D1 used by a designer U1, for example. A computer P1 that outputs images to the liquid crystal display D1 has a configuration corresponding to a known CAD engine C, and a configuration corresponding to the manufacturing support system S according to the present invention.

[0016] The manufacturing support system S may function as a part of the CAD engine C, or may function as an add-on to the CAD engine C. The manufacturing support system S operates in cooperation with the CAD engine C, and an input operation by the designer U1 to the computer P1 is input to both the manufacturing support system S and the CAD engine C. However, the manufacturing support system S may accept the input operation by the designer U1 and provide the necessary information to the CAD engine C, or the CAD engine C may accept the input operation by the designer U1 and provide the necessary information to the manufacturing support system S.

[0017] During the inspection process, the manufacturing support system S displays, for example, a warning regarding the inspection on a head-up display D2 or liquid crystal display D3 worn by an inspector U2. A computer P2 that outputs images to the head-up display D2 or liquid crystal display D3 has a configuration corresponding to a known CAD engine C, and a configuration corresponding to the manufacturing support system S according to the present invention. However, it is preferable to use wireless communication for the connection between the computer P2 and the head-up display D2. In the following, the designer U1 and the inspector U2 are collectively referred to as "users".

[0018] (Hardware configuration) Fig. 2 is a hardware configuration diagram of the manufacturing support system S. The computer P1 and the computer P2 described in Fig. 1 are equipped with the hardware described below. The manufacturing support system S is equipped with a CPU 41 which is a central processing unit, a ROM 42 which is a read-only storage device, a RAM 43 which is a readable and writable storage device, an input / output device 44 which is a user interface, a communication device 45, and a storage unit 46.

[0019] The CPU 41 loads a program stored in the ROM 42 into the RAM 43 and executes it to perform various calculations, which will be described later. The manufacturing support system S may be realized by a field programmable gate array (FPGA), which is a rewritable logic circuit, or an application specific integrated circuit (ASIC), which is an integrated circuit for a specific application, instead of the combination of the CPU 41, the ROM 42, and the RAM 43. Furthermore, the calculation unit may be realized by a combination of different configurations, for example, a combination of the CPU 41, the ROM 42, the RAM 43, and an FPGA, instead of the combination of the CPU 41, the ROM 42, and the RAM 43.

[0020] The input / output device 44 is an input / output interface for information with an input device operated by a user and an image display device viewed by a user. The input / output device 44 includes an input interface for receiving information from a mouse or a keyboard, and an output interface for outputting image information to the liquid crystal display D1, the head-up display D2, and the liquid crystal display D3. The input / output device 44 may be a device that supports wireless communication. The communication device 45 is a communication interface that can communicate with other devices. The storage unit 46 is a non-volatile storage device, such as a hard disk drive or a semiconductor memory. Below, an overview of the data configuration and the functional configuration will be described, followed by a detailed description.

[0021] (Data Composition) 3 is a diagram showing information stored in the storage unit 46. The storage unit 46 stores a design accumulation database (hereinafter referred to as a "design accumulation DB") 20, a total attention information graph database (hereinafter referred to as a "total attention information graph DB") 20G, and a model set 200. The total attention information graph DB 20G is a collective term for a welding graph database (hereinafter referred to as a "welding graph DB") 21G, an adhesive graph database (hereinafter referred to as a "adhesive graph DB") 22G, a screw graph database (hereinafter referred to as a "screw graph DB") 23G, and an attention graph database (hereinafter referred to as an "attention graph DB") 24G.

[0022] The model set 200 is a collective term for a welding model set 201, an adhesive model set 202, a screw model set 203, and a caution model set 204.

[0023] The design accumulation DB20 stores information on past 3D-CAD designs made by the designer and information on 3D-CAD currently being designed. The past 3D-CAD information may be configured to be selectable, for example, it may include only past 3D-CAD information for products on the same production line, or it may include only past 3D-CAD information for products with the same design rules. Structure information, which is information on each structure in the 3D-CAD, includes shape information and attachment information. Shape information is information that can specify the shape of an object in a three-dimensional space, and the method of expressing the information is not particularly limited.

[0024] Here, shape information is divided into (1) shape information of a structure that can be converted into a graph shape (hereinafter, simply referred to as "shape information of a structure") and (2) shape auxiliary information of a structure that cannot be converted into a graph shape (hereinafter, simply referred to as "shape auxiliary information"). The former (1) "shape information of a structure" is information that is expressed by the relationship between nodes and edges, which is a graph shape, after conversion to graph data. The latter (2) shape auxiliary information is information that is converted into numerical values ​​or digit vectors that nodes and edges hold after conversion to graph data. Details will be described later in the (Graph Data) section, but the former (1) "shape information of a structure" is information that expresses the connections between the faces and edges of the structure, among the shape information of the structure, and the latter (2) "shape auxiliary information" is information that expresses the properties of the faces and edges. Therefore, the latter (2) "shape auxiliary information" includes information such as the length of an edge, the curvature of an edge, the area of ​​a face, and the angle between faces.

[0025] It can also be said that information on multiple substructures, which are parts of a structure, is stored in the design accumulation DB 20. For example, a structure is one product or part, and a substructure is one part or a part of a part. However, a substructure may be a part of multiple parts or multiple parts themselves.

[0026] The attached information is classified into component information and attention information. Attention information is information that the manufacturing support system S supports in attaching information, and includes, for example, information about the connection between parts. The attached information can be applied as long as it is information linked to a structure on 3D-CAD. Information about the connection between parts is information about welding, adhesives, screws, jigs, joints, brazing, solder, hinges, springs, sealing materials, etc., used at the connection points between parts. The component information mainly includes information about materials (hereinafter referred to as "material information"). The material information can include the material type and name, the elastic constant, which is a mechanical characteristic, various physical properties such as yield stress, tensile strength, and elongation related to the stress-strain curve, thermal conductivity, melting point, etc. In addition, as material information, for example, safety factors of various measured values ​​defined at the time of design can also be treated as part of the component information, and there are no particular restrictions on setting the information as long as it is linked to a partial structure of the design drawing in the previous process of attaching information.

[0027] In this embodiment, the type of connection points between parts is called a "connection type." There are no limitations on the connection types, and they can include, for example, connection methods that will be newly used in the future. In this embodiment, for the sake of simplicity, there are three connection types: welding, adhesion, and screws, and information related to welding included in the additional information is called "welding information," information related to adhesion included in the additional information is called "adhesion information," and information related to screws included in the additional information is called "screw information."

[0028] The welding information may include the whole or part of the welding procedure specification (hereinafter referred to as WPS) that shows the welding information to the welding operator. The WPS includes the joint structure, shape, base material, welding material, welding conditions (welding type, current, voltage, welding speed, number of welding layers, etc.), heat treatment, etc. The welding information may also include information on the performance test record (Process Qualification Record) that supports the WPS. In addition, the process parameters of the welding robot may be used as one type of welding information linked to the structure. This is particularly effective in sites where the automation of construction work using welding robots has progressed. The adhesive information includes information on the adhesive material, whether or not forced drying is performed, the drying time, and the amount of adhesive to be applied. The screw information includes information on the base material of the screw, the surface treatment of the screw, the diameter and length of the pilot hole that forms the female screw, and the pitch of the screw.

[0029] Furthermore, in this embodiment, information used to call attention in the inspection process is included in the assigned information as attention information. That is, the assigned information in this embodiment includes connection information and attention information. Therefore, the assigned information includes welding information, adhesive information, screw information, and attention information. Hereinafter, the welding information, adhesive information, screw information, and attention information are collectively referred to as "attention information."

[0030] The total attention information graph DB20G is obtained by converting into graph data the structural information, that is, the shape information and the attached information, of the articles contained in the design accumulation DB 20. The graph data will be described in detail later.

[0031] The welding model set 201 includes a plurality of combinations of any welding information included in the design accumulation DB 20, graph data obtained by converting nearby structure information to which the welding information is added, and a welding search model or a welding prediction model. The bonding model set 202 includes a plurality of combinations of any bonding information included in the design accumulation DB 20, graph data obtained by converting nearby structure information to which the bonding information is added, and a bonding search model or a bonding prediction model. The screw model set 203 includes a plurality of combinations of any screw information included in the design accumulation DB 20, graph data showing the shape of the neighborhood to which the screw information is added, and a screw search model or a screw prediction model. The attention model set 204 includes a plurality of combinations of any attention information included in the design accumulation DB 20, graph data showing the shape of the neighborhood to which the attention information is added, and an attention search model or an attention prediction model.

[0032] Since the welding model set 201, the adhesive model set 202, the screw model set 203, and the caution model set 204 have the same configuration, the welding model set 201 will be described in detail later as a representative of these four.

[0033] FIG. 4 is a configuration diagram of a welding model set 201. The welding model set 201 includes a first welding model set 201-1, a second welding model set 201-2, a third welding model set 201-3, and the like. As shown in the lower part of FIG. 4, the configuration of each model set is classified into two types. The first type is shown in the lower left of FIG. 4, and includes a welding search model 171, a welding common subset 211, and a welding search subset 221. The second type is shown in the lower right of FIG. 4, and includes a welding prediction model 161 and a welding common subset 211.

[0034] The common subset 210 is used to create and update both the welding retrieval model 171 and the welding prediction model 161. The retrieval subset 220 is not included in the second type because it is used for the welding retrieval model 171 but not for the welding prediction model 161. However, since the common subset 210 and the retrieval subset 220 are created separately according to their respective purposes, the data in the two sets may overlap.

[0035] FIG. 5 is a diagram showing information included in the model set 200. Although the configuration of the welding model set 201 has been described in FIG. 4, the adhesive model set 202, the screw model set 203, and the attention model set 204 have the same configuration. Therefore, it can be said that the model set 200 includes the information shown in FIG. 5. The common subset 210 is a collective term for the welding common subset 211, the adhesive common subset 212, the screw common subset 213, and the attention common subset 214. The common subset 210 is used for optimization and verification evaluation of the prediction model and the search model. The common subset 210 is used for machine learning as described later, so it can also be called a "dataset". The search subset 220 is a collective term for the welding search subset 221, the adhesive search subset 222, the screw search subset 223, and the attention search subset 224. The search subset 220 is a database that is a search target of the search model as described later.

[0036] The welding common subset 211 and the welding search subset 221 include a portion of the welding model set 201. Specifically, the welding common subset 211 and the welding search subset 221 include several sets of combinations of welding information and graph data included in the welding model set 201. Which sets are included will be described later. The bonding common subset 212 and the bonding search subset 222 include a portion of the bonding model set 202. Specifically, the bonding common subset 212 and the bonding search subset 222 include several sets of combinations of bonding information and graph data included in the bonding model set 202. Which sets are included will be described later.

[0037] The screw common subset 213 and the screw search subset 223 include a part of the screw model set 203. Specifically, the screw common subset 213 and the screw search subset 223 include several combinations of screw information and graph data included in the screw model set 203. Which combinations are included will be described later. The attention common subset 214 and the attention search subset 224 include a part of the attention model set 204. Specifically, the attention common subset 214 and the attention search subset 224 include several combinations of attention information and graph data included in the attention model set 204. Which combinations are included will be described later.

[0038] The relationship between the welding common subset 211 and the welding search subset 221 and the welding model set 201 is the same as the relationship between the bonding common subset 212 and the bonding search subset 222 and the bonding model set 202, the relationship between the screw common subset 213 and the screw search subset 223 and the screw model set 203, and the relationship between the attention common subset 214 and the attention search subset 224 and the attention model set 204. Therefore, in the following, the relationship between the welding common subset 211 and the welding search subset 221 and the welding model set 201 will be described in detail as a representative of these.

[0039] (Functional configuration) FIG. 6 is a diagram showing the functions of the manufacturing support system S as functional blocks. Each function shown in FIG. 6 is realized by a combination of a CPU 41, a ROM 42, and a RAM 43. The manufacturing support system S includes, as its functions, a model set generation unit 12, a subset generation unit 13, an input unit 14, an extraction unit 15, a prediction model 16, a search model 17, a proposal unit 18, and a model update unit 19. The prediction model 16 is a collective term for a welding prediction model 161, a bonding prediction model 162, a screw prediction model 163, and an attention prediction model 164. The search model 17 is a collective term for a welding search model 171, a bonding search model 172, a screw search model 173, and an attention search model 174.

[0040] The model set generation unit 12 generates a model set 200 using information stored in the design accumulation DB 20. The model set generation unit 12 operates the subset generation unit 13 as necessary. As described later, the design accumulation DB 20 is updated based on a user operation. When the design accumulation DB 20 is updated, or when an update is instructed from the input unit 14 at the discretion of the user, the model set generation unit 12 can update the model set 200 and a series of databases, prediction models 16, and search models 17 linked to the model set 200 as necessary.

[0041] A specific procedure for creating the model set 200 will be described. First, the model set generation unit 12 converts the structural information of the article contained in the design accumulation DB 20 into graph data to be described later, and creates the total attention information graph DB 20G. Then, the model set generation unit 12 combines the graph data and the attached information contained in the total attention information graph DB 20G to generate the model set 200. At this time, depending on the type of attention information to be combined, it is determined which of the welding model set 201, the bonding model set 202, the screw model set 203, and the attention model set 204 to add. The model set generation unit 12 converts the structural information of the article into graph data, and therefore can also be called a "data conversion unit."

[0042] The subset generating unit 13 generates a common subset 210 and a search subset 220 using the model set 200. Specific correspondences in the operation of the subset generating unit 13 are shown below. The subset generating unit 13 generates a common subset 211 for welding and a search subset 221 for welding using the model set 201 for welding. The subset generating unit 13 generates a common subset 212 for bonding and a search subset 222 for bonding using the model set 202 for bonding. The subset generating unit 13 generates a common subset 213 for screws and a search subset 223 for screws using the model set 203 for screws. The subset generating unit 13 generates a common subset 214 for attention and a search subset 224 for attention using the model set 204 for attention. The subset generating unit 13 updates the common subset 210 and the search subset 220 when the model set 200 is updated or when an update is instructed from the input unit 14 at the discretion of the user.

[0043] The input unit 14 receives an input operation from the user using the input / output device 44, and outputs information on the input operation by the user to the suggestion unit 18.

[0044] The extraction unit 15 extracts attention information corresponding to the input structural information of the article. Hereinafter, the attention information extracted by the extraction unit 15 is referred to as "attention information candidate". Specifically, the extraction unit 15 first converts the input structural information of the article into graph data, inputs it to an appropriate type of prediction model 16 or retrieval model 17, and outputs the added information candidate output by the prediction model 16 or retrieval model 17. For example, when the type of attention information is "welding information", the extraction unit 15 inputs the graph data to the welding prediction model 161 or welding retrieval model 171.

[0045] The prediction model 16 calculates and outputs one or more pieces of attention information corresponding to the input graph data. The search model 17 searches for one or more pieces of graph data similar to the input graph data from the search subset 220, and outputs attachment information corresponding to the similar graph data. Specifically, the welding search model 171 uses the welding search subset 221 for search, the bonding search model 172 uses the bonding search subset 222 for search, the screw search model 173 uses the screw search subset 223 for search, and the attention search model 174 uses the attention search subset 224 for search.

[0046] The suggestion unit 18 specifies the selected structure based on the input to the input unit 14 by the user, inputs the selected structure to the extraction unit 15, and suggests to the user that the candidate attention information, which is the attention information extracted by the extraction unit 15, be assigned to the selected structure. In this embodiment, the partial structure selected based on the input to the input unit 14 by the user is called a "selected structure". The selected structure is a partial structure selected by the user, or a partial structure similar to the partial structure selected by the user. The suggestion unit 18 may determine which of the partial structure selected by the user and the partial structure similar to the partial structure selected by the user should be the selected structure according to the operation mode of the manufacturing support system S, or may determine which of the above should be the selected structure according to the size of the area specified by the user to extract the selected structure. The suggestion unit 18 also updates the design accumulation DB 20 based on the user's response when the suggestion unit 18 suggests the candidate attention information to the user.

[0047] The model update unit 19 updates the prediction model 16 and the search model 17 by referring to the search subset 220. Specifically, the model update unit 19 updates the prediction model 161 for welding and the search model 171 for welding by referring to the search subset 221 for welding. The model update unit 19 updates the prediction model 162 for bonding and the search model 172 for bonding by referring to the search subset 222 for adhesive. The model update unit 19 updates the prediction model 163 for screws and the search model 173 for screws by referring to the search subset 223 for screws. The model update unit 19 updates the attention prediction model 164 and the attention search model 174 by referring to the attention search subset 224. Note that in this embodiment, the model update unit 19 updates the prediction model 16 and the search model 17, but the data scientist may update the prediction model 16 and the search model 17.

[0048] (Graph data) Before describing the welding model set 201 and the like, graph data will be described. In this embodiment, graph data is used to abstract parts to which additional information is added and handle them in a common format. The graph data can represent shape information indicating connections between physical lines and faces that are components of a structure in a graph form. In addition, shape auxiliary information and additional information of a structure, which are pieces of shape information that cannot be represented in a graph form, can be held on a graph in the form of a feature vector.

[0049] Figure 7 is a diagram showing the correspondence between three-dimensional structures and graph data. The upper part of Figure 7 is a diagram showing the three-dimensional structure as a Boundary Representation (Brep). In Brep, an object in three-dimensional space is represented using physical vertices, which are the vertices of the three-dimensional structure, physical edges formed by the physical vertices, physical surfaces formed by the physical edges, and solids, which are solid 3D structures surrounded by physical surfaces. Furthermore, an object made up of one or more solids is considered a part, and a collection of parts makes up a single product.

[0050] As shown in the lower part of Fig. 7, graph data is a data structure composed of vertices V called nodes and lines E that show connections between the vertices called edges. In this embodiment, the vertices and edges on the 3D-CAD are called "physical vertices" and "physical edges", and the vertices and edges of the graph structure are called "nodes" and "edges". In addition, each node and each edge can hold multiple feature amounts in vector format. The vector is used as a feature amount vector to express the features of each node and each edge.

[0051] The correspondence between the components of the Brep structure and the components of the graph data can be, for example, with physical planes as nodes and physical edges as edges. The physical planes V701-V706 shown in the upper part of Fig. 7 correspond to the nodes V701-V706 of the graph structure shown in the lower part of Fig. 7. Similarly, each physical edge of the three-dimensional structure corresponds to an edge E707-E718.

[0052] The edge E of the graph data can hold auxiliary shape information such as the length of the edge, the curvature of the edge, and the angle between the faces sharing the edge, and the node V can hold auxiliary shape information such as the area of ​​the face and the curvature of the face. These pieces of information are held as feature quantities of each component of the vector. Such vectors are called feature quantity vectors. When the auxiliary shape information is not a constant value on the physical edge or surface corresponding to the edge E or node V, the average or variance, which is a characteristic of the distribution of values ​​indicating this information, can be held in the feature quantity vector. In addition, when converting the information on the components constituting the article, which is one of the additional information, into graph data, it is desirable to hold material information such as the material type and its physical properties as the feature quantity vector of the node or edge. Converting into graph data including the component information is particularly effective when treating the joining conditions as the information of interest, because the joining conditions depend on the material properties and material type.

[0053] The handling of categorical variables in this embodiment will be described. A categorical variable refers to a variable of information that cannot be directly expressed by a numerical value, such as a material type. When handling a variable of information that cannot be directly expressed by a numerical value, it is necessary to perform a quantification process of the categorical variable as a preprocessing. For example, by performing a one-hot encoding process using a material type as an example of a categorical variable, the categorical variable of each data can be converted into a vector notation. The vector obtained after the quantification process of the categorical variable indicates the material type of each data by making a specific vector component corresponding to a certain material type 1 and the remaining vector components 0, and can be held as a part of the feature vector of the node or edge. However, in the one-hot encoding process, if the dimension of the feature vector finally obtained becomes too large, the accuracy of prediction and search may decrease. In such a case, it is desirable to perform label encoding, which is an operation that directly converts each categorical variable into a numerical value. There is no particular restriction on the method of converting the categorical variable as long as it is within the range of the notation method that can be held in the feature vector format for the node or edge, and a general conversion method can be used instead.

[0054] As an example of secondarily generated features, consider the features of a structure joined at the interface (physical surface) of different materials. Faces and edges shared by two structures are at the boundary between structures with different types of material information, and therefore cannot be defined by the features of a single type of material. Therefore, the average, variance, etc. of the features of both materials between the interface can be stored as secondarily generated features in the components of vectors of nodes and edges. In addition, the values ​​of each component of the feature vectors stored in nodes and edges are generally graph data containing features obtained secondarily by performing standardization processing on the model set 200.

[0055] (Model set generation part) 8 and 9 are flowcharts showing the processing of the model set generation unit 12. As described below, the model set generation unit 12 generates a welding model set 201, a bonding model set 202, a screw model set 203, and a notice model set 204 using the attached information included in the design accumulation DB 20 and the total attention information graph DB 20G.

[0056] First, in step S301, the model set generation unit 12 determines target attention information (hereinafter referred to as "target attention information"). Since a model set corresponding to the target attention information determined here is generated, in order to generate all four, namely, the welding model set 201, the adhesive model set 202, the screw model set 203, and the caution model set 204, the processing from step S302 onwards is executed four times while changing the attention information in step S301. Here, the explanation will be continued taking as a representative example the case where "welding information" is determined as the target attention information in step S301.

[0057] In the next step S302, the model set generation unit 12 generates a database (graph DB) including graph data corresponding to the target attention information determined in step S301, based on the design accumulation DB 20. For example, when the target attention information is "welding information", a welding graph DB 21G is generated. Each graph DB has different information in the nodes and edges of the graph data. Of all the structure information, only the structure information to which each target attention information is added is converted into graph data and converted into each database 21G to 24G.

[0058] In step S303, the model set generation unit 12 selects a model optimization method. Specifically, the model set generation unit 12 selects a machine learning method, whether to create a search model or a prediction model, and the like. This selection is made, for example, in an order designated in advance by the user. In this case, the options for the first execution of step S303, the options for the second execution after returning from step S309, and the like are designated in advance by the user. In the following step S304, the model set generation unit 12 selects one from the graph extraction algorithm candidates. The selection here may be made in an order designated in advance by the user, or may be made randomly. However, when returning from step S308 and executing step S304, an algorithm that has not been selected so far is selected.

[0059] In the following step S305, the model set generation unit 12 generates a model set according to the extraction algorithm selected in step S304. In the following step S306, the model set generation unit 12 extracts a common subset for optimizing a prediction model and a search model using the model set generated in step S305.

[0060] In the next step S307, the model set generation unit 12 optimizes the model using the common subset and verifies the prediction accuracy. A test data set (not shown) is used to verify the prediction accuracy. The test data set is data in the same input / output format as the common subset, and is a collection of data that is not included in the common subset, even though it is created in the same flow as the common subset. In the next step S308, the model set generation unit 12 judges whether or not to end the consideration of the extraction algorithm candidates. If the model set generation unit 12 judges that the consideration can be ended, the process proceeds to step S309, and if the model set generation unit 12 judges that the consideration should be continued, the process returns to step S304.

[0061] In step S309, the model set generation unit 12 judges whether the prediction accuracy of the generated model is sufficient. In this step, the calculation speed may be further evaluated to judge whether the performance of the prediction model is sufficient. If the model set generation unit 12 judges that the prediction accuracy is sufficient, it proceeds to step S310 in FIG. 9 via circled A, and if it judges that the prediction accuracy is insufficient, it returns to step S303. In the operation of step S309, the candidate models obtained by executing the operations from S303 to S308 with various parameters may be evaluated collectively in S309 to select the best prediction model. In step S310, the model set generation unit 12 judges whether the generated model is a search model, and if it is judged to be a search model, it proceeds to step S311, and if it is judged to be not a search model, i.e., a prediction model, it proceeds to step S312.

[0062] In step S311, the model set generation unit 12 selects a search subset to be searched by the search model, and proceeds to step S312. In this case, the model set generation unit 12 selects a search model set based on the search speed and search accuracy for a test data set configured in the same format as the model set. In step S312, the model set generation unit 12 selects a model, an extraction algorithm, a model set, and each subset for the selected attention information. In the following step S313, the model set generation unit 12 determines whether or not model creation and updating for other attention information is necessary. If it is determined that it is necessary, the process returns to step S301 via circled B, and if it is determined that it is unnecessary, the process shown in FIG. 8 and FIG. 9 is terminated.

[0063] (Subset generation part) Fig. 10 is a diagram illustrating an example of a subgraph extraction process by subset generation unit 13. The graph data shown in the upper part of Fig. 10 shows graph data of parts A and B that are joined by welding, where nodes correspond to physical faces of the 3D structure and edges correspond to physical sides of the 3D structure. Parts A and B are joined by edge E indicated by welding lines 801 and 802. Here, it is assumed that information on weld line 801 is the attention information selected in step S302.

[0064] In this case, in the second proximity extraction algorithm, which is an example of an extraction algorithm, the graph data including the nodes adjacent to the adjacent node of the position related to the attention information selected in step S302 via edges, i.e., the second proximity nodes, are extracted as subgraph data. This extraction process results in the subgraph data shown in the lower part of Fig. 10. In addition, the feature vector F V,total Or F E,total Some dimensional elements of F V,partial ,F E,partialHere, the graph data including the second nearest neighbor nodes is extracted as subgraph data, but it may be expanded to a third nearest neighbor extraction algorithm that includes adjacent nodes in the subgraph data. This may be further expanded to adopt an nth nearest neighbor extraction algorithm expressed using a natural number n. Similarly, a partial feature vector including the natural number n and m elements of a part of the dimension of the feature vector is selected. The selection of the nth nearest neighbor and the combination of the number of m elements and the element type is determined by trial and error from the evaluation of the prediction accuracy according to the process of the flowcharts shown in Figures 8 and 9. For example, as the degree of freedom of the model created for the common subset increases with the increase of n and m, the prediction accuracy for the test data will not improve with the increase of n and m at a certain point. Therefore, as an example of a method for determining the upper limit of the natural n and m to be considered, a method of stopping the consideration of higher n and m is effective.

[0065] In addition, when the information of interest is linked to a solid rather than a physical edge, an algorithm may be adopted that extracts a graph structure including the nearest edge and face of the solid up to the n-th nearest node. This concludes the description of the subgraph data extraction algorithm.

[0066] FIG. 11 is a conceptual diagram of the common subset for welding 211. The common subset for welding 211 includes a plurality of data (j). "j" is an index indicating the data in the common subset for welding 211. Data (j) 1004A is converted from original data (j) 1000. The original data includes structure information (j) that is the source of input information to the prediction model 16, and welding information (j) that corresponds to output information to the prediction model 16. The graph data (j) 1005 obtained by the processing of step S305 and the vector t, which is a vector for identifying the welding information and is obtained by one-hot encoding processing from the welding information, are j (1006) is obtained.

[0067] The subset generation unit 13 generates a common subset 210 and a search subset 220 from each model set. Specifically, the subset generation unit 13 uses a welding model set 201 to generate a welding common subset 211 and a welding search subset 221. The subset generation unit 13 uses a bonding model set 202 to generate a bonding common subset 212 and a bonding search subset 222. The subset generation unit 13 uses a screw model set 203 to generate a screw common subset 213 and a screw search subset 223. The subset generation unit 13 uses an attention model set 204 to generate an attention common subset 214 and an attention search subset 224.

[0068] A method for creating a welding common subset 211 and a welding search subset 221 will be described using the welding model set 201 as an example. The subset generation unit 13 extracts, from the attention information paired with the graph data included in the welding model set 201, a plurality of pairs of graph data and attention information included in the welding common subset and the welding search subset for each subset.

[0069] This extraction process can be considered as a sampling process of the data included in the model set. After pointing out the necessity of a sampling method for creating a common subset for welding and a search subset and the problems to be solved, an example of a sampling method will be explained using Fig. 12.

[0070] First, the sampling method will be described using a common subset used for optimizing a predictive model as an example. The common subset is used for learning when optimizing a predictive model using a machine learning method. Therefore, if sampling when creating a common subset is biased toward specific data, problems may occur in which the prediction accuracy of the predictive model for new data decreases or the prediction accuracy of each class is biased. In order to prevent these problems, it is necessary to correct the bias in the learning data by creating a common subset using an appropriate sampling process. Here, the classification result of the attention information is called label data, and the type of label data is called a class. The attention information obtained at the product production site often has biased numbers of data for each class and their distribution, even within the same product.

[0071] Therefore, sampling can cause the following two problems that need to be solved. Problem (1): With general random sampling, label data belonging to a specific class is excessively sampled, resulting in the generation of a predictive model that prioritizes the predictive accuracy of classes with a large amount of data at the expense of the predictive accuracy of classes with a small amount of data. Problem (2): By repeatedly sampling homogeneous data excessively, not only does the predictive accuracy not improve, but the computational costs of learning also increase. One example of a solution to these problems is to perform random sampling for each class so that the number of data for each class is roughly the same.

[0072] The effect of sampling is explained using the upper diagram in Figure 12. The upper diagram shows a schematic of the distribution of subgraph data of the model set in the data space, with the differences in each figure indicating the difference in the class of attention information corresponding to the subgraph data. In particular, the data of the class indicated by the triangle is much more abundant than the other classes, and problem (1) occurs when all the data indicated by the triangles is used. Therefore, only sampled data, i.e., extracted data, is used. This reduces the amount of data and at the same time avoids unnecessarily increasing the computational costs of learning, addressing problem (2).

[0073] Here is an example of a solution using another sampling method. In the solution of using only the extracted data mentioned above, the bias of the predictive model may become large due to the bias of random sampling for each class. Therefore, it is also effective to combine the sampling method for each class mentioned above with ensemble learning. Another solution is to create multiple predictive models using multiple common subsets obtained by multiple samplings, and then treat the average of the prediction results of each predictive model as the output of a new predictive model.

[0074] The purpose of the sampling method described above is to reduce the learning cost of the predictive model and improve the prediction accuracy for unknown data. Therefore, as long as a common subset that corrects the bias of the dataset and satisfies the desired evaluation indexes of computational cost and prediction accuracy is sampled, it can be substituted with a general sampling method. Note that although the predictive model has been described as a classification model, a common subset can also be extracted using a similar sampling method for regression models. Furthermore, when using a common subset to optimize a search model, a common subset can also be extracted using a similar sampling method.

[0075] Next, the necessity of a specific sampling process in creating a search subset and the problem to be solved are described, and an example of a sampling method as a solution is given. As with the creation of a common subset, the search subset needs to reduce the computational cost of the search model and the bias in search accuracy for unknown data of each class. In addition, since the search model is greatly related to the speed at which information is presented to the user by the suggestion unit 18, the number of data in the search subset to be searched needs to be carefully selected in order to maintain a sufficient search speed. Therefore, in addition to the problem related to the bias of problem data when creating a common subset, a unique problem may also occur when creating a search subset. Since data is searched and acquired according to the similarity of graph data in the subset during a search, there is a problem that the search results are significantly affected by outliers in the search subset. To solve this problem, it is necessary to remove the outliers by sampling. For example, an example of a sampling method is given in the reference [DL Wilson, IEEE Trans. Syst. Man. Cybern. SMC-2, 408 (1972).]. By using such a method, outlier data of different classes of peripheral data can be excluded from sampling.

[0076] An example of sampling to remove outliers will be explained using the lower diagram in Fig. 12. In Fig. 12, it is preferable to remove outlier data 1201, indicated by triangles in the rectangular class area, and data indicated by reference symbol 1202 that is mixed near the boundaries of the class areas. This makes it possible to stabilize search results. The method in the above-mentioned reference is a method for removing outlier data.

[0077] Although the sampling process for removing outliers in the above-mentioned reference requires the distance between data in the feature vector space, it is generally difficult to define the distance between graph data in the feature space. Furthermore, it is more desirable to use the sampling method mentioned in the common subset in combination to correct the bias in the number of data between classes. Therefore, it is desirable to use it in combination with the method of embedding graph data in the feature vector space, which will be described later in the retrieval model section. This embedding method allows the graph data to be sampled based on the obtained distance in the feature space.

[0078] Appropriate sampling is evaluated based on the search response speed and search accuracy for the search subset by the search model. As long as this evaluation is satisfied, there are no particular limitations on the sampling method, and multiple combinations may be used. As an example of a sampling method, a method of removing data of different classes that are close to each other is also effective (see Ivan Tomek. Two modifications of cnn. IEEE Trans. Systems, Man and Cybernetics, 6:769-772, 1976.). This method is particularly effective when removing data where data of different classes is mixed at the boundaries of each class, as shown by reference numeral 1202 in FIG. 12.

[0079] The subset generation unit 13 obtains a common subset for welding 211 by using the above-mentioned sampling method for the common subset based on the welding information paired with each piece of graph data. The subset generation unit 13 obtains a search subset for welding 221 by using the above-mentioned sampling method for the search subset based on the welding information paired with each piece of graph data.

[0080] A set of attention information paired with graph data obtained according to the sampling process of the subset generation unit 13 may be included in both the common subset and the search subset, or may be included in only one of the subsets.

[0081] (Prediction model) FIG. 13 is a diagram for explaining the prediction model 16. Input data 903 to the prediction model 16 is information created from structure information (i) 901 in FIG. 13. Here, i is an index for distinguishing each piece of structure information. In FIG. 13, as an example, the information of interest is shown as welding information, and structure information (i) 901 is shown as a structure near a weld line. Here, since the structure information (i) cannot be directly input to the prediction model 16, it is converted into sub-graph data (i) 903. The process of converting this structure information into sub-graph data is as described above. The sub-graph data 903 is obtained according to the extraction algorithm selected by the process shown in the flowcharts of FIG. 8 and FIG. 9.

[0082] The prediction model 16 receives subgraph data (i) 903 as a direct input and obtains output information 905. The information obtained as a direct output from the prediction model 16 is an output vector t i It is 906. i Each component of t indicates the probability of assigning each candidate attention information 907-909 to structure information (i). i The sum of the components of is 1. As shown in Fig. 13, each component, component 1, component 2, component 3, ... indicates the probability of assigning candidate welding information (1), candidate welding information (2), candidate welding information (3) ..., respectively. In the example of Fig. 10, since component 3 has the highest probability, welding information (3) (907) is proposed as the information to be assigned to structure information (i) from the output result of prediction model 16.

[0083] Output vector t i In displaying attention information using t iCandidates for attention information are listed in order of the highest probability indicated by each component of . Also, attention information with the highest attachment probability may be provisionally attached to the structure information as attention information 910. Note that here, the prediction model 16 is a classifier that estimates appropriate attachment information from a group of attachment information candidates when structure information is input. However, the prediction model 16 is not limited to a classifier, and a regression model that predicts attention information in the form of a numerical value or a numerical vector may be used as the prediction model 16. However, the prediction model 16 is characterized in that it receives graph data converted from structure information as an input, and the output of the prediction model 16 indicates information to be attached to the structure.

[0084] A machine learning method for creating the prediction model 16 will be described. The machine learning method used in the present invention can create a prediction model 16 such as a classifier using graph data as input. For example, among the methods using graph data as input, it is desirable to use a method classified as a GNN (Graph Neural Network) that can create a prediction model 16 with high generalization performance. Among them, it is desirable to use a GCN (Graph Convolutional Network) that reflects local information around the nodes of the graph data in the prediction model 16. Each process in the GNN, including the propagation process, sampling process, and pooling process, may be examined by trial and error for the common subset 210, and there is no particular restriction as long as a process with high prediction accuracy is selected.

[0085] Cross entropy error is often used as a loss function in optimizing the classification model (a type of prediction model 16) illustrated in Fig. 10, but there are no particular limitations as long as it is possible to optimize which candidate of attention information is desirable for the input of structure information with respect to the common subset 210. Similarly, if the prediction model 16 is a regression model, a general loss function such as a sum of squares error is used, but is not limited to this. Other than GNN, as an example of a machine learning method that uses graph data as input, a graph kernel that defines the similarity between graph data may be used.

[0086] Types of graph kernels include the random walk kernel [H. Kashima, K. Tsuda, and A. Inokuchi, in Proc. Twent. Int. Conf. Int. Conf. Mach. Learn. (AAAI Press, 2003), pp. 321-328.], the shortest kernel [KM Borgwardt and H.-P. Kriegel, in Proc. Fifth IEEE Int. Conf. Data Min. (IEEE Computer Society, USA, 2005), pp. 74-81.], and the subgraph matching kernel [N. Kriege and P. Mutzel, in Proc. 29th Int. Conference Int. Conf. Mach. Learn. (Omnipress, Madison, WI, USA, 2012), pp. 291-298.]. Machine learning methods that can be used in combination with the graph kernel include SVM (Support Vector Machine), kernel perceptron, Gaussian Process, linear discriminant analysis, etc., but there are no particular restrictions as long as the algorithm is used in combination with the kernel method to create a predictive model16.

[0087] However, a drawback of using the graph kernel to create the prediction model 16 is that the calculation cost of the graph kernel can become a bottleneck when creating and using the prediction model 16. Therefore, although it is necessary to implement some ingenuity in the kernel calculation, such as limiting the amount of learning data used, the graph kernel may be used to create the prediction model 16 as long as the prediction model 16 can achieve a calculation speed that does not cause dissatisfaction in use by users.

[0088] (Search model) 14 and 15 are diagrams for explaining the search model 17. Input data 1103 to the search model 17 is subgraph data (i) 1103 based on structure information (i) 1102. Here, i is an index for distinguishing each piece of structure information. The structure information (i) is converted into subgraph data (i) 1103 and then input to the search model 17. The series of processes for creating the subgraph data (i) 1103 shown here is the same as the example of the prediction model 16 shown using FIG. 13, and a search model is obtained by optimizing the model for the input / output results for the common subset 210.

[0089] The purpose of the search model 17 is to identify subgraph data similar to the subgraph data (i) that is a search query from among the graph data (j) included in the database 1105. Here, the subgraph data (j) is data converted from the structure information (j) like the subgraph data (i). j is an index that identifies the subgraph data (j) and the original structure information (j) in the database, and is included in the search subset 220.

[0090] The search model 17 calculates a similarity S between the graph data (i) 1105 to be compared and each graph data (j) in the search subset 220. ij As shown in 1107A, 1108A, and 1109A of FIG. 14, the similarities calculated for the subgraph data (1), the subgraph data (2), and the subgraph data (j) are calculated as similarity S i1 , similarity S i2 ,..., similarity S ij Also, attention (1) 1107B, attention information (2) 1108B, . . . , attention information (j) 1109B are associated with each graph data in advance.

[0091] The extraction unit 15 extracts the similarity S ij Using the evaluation index, sub-graph data (j) 1109A having a high similarity to the sub-graph data (i) is extracted. In the example shown in FIG. 14 and FIG. 15, attention information (j) 1109B of original information (j) linked to the sub-graph data (j) has a similarity Sij It was extracted because it has a large similarity S ij Since the structure information (i) and the structure information (j) are similar through the calculation result, the attention information (j) 1109B is linked to the structure information (i) to estimate the attention information (i) 1200. By the operation using the search model 17 shown here, the attention information (i) 1200 to be linked to the structure information 1103 of the input data (i) 1103 is obtained. In addition, the similarity S i1 By obtaining multiple pieces of promising information of interest (j) from similar data (j) with high similarity in descending order, these pieces of information can be treated as candidates for information to be added to the structure information (i).

[0092] 14, for the sake of abstraction, the description is given using the search model 17 and the search subset 220, but in practice, a specific search model 17 and a search subset 220 are used according to the attention information. For example, when welding information is the attention information, the search model 171 for welding and the search subset 221 for welding are used.

[0093] The following points should be noted when calculating similarity using the search model 17. In theory, it is possible to calculate similarity for all data in the model set, but in actual operation, it is necessary to calculate similarity S for all the large amount of data in the model set. ij It is difficult to perform the calculation of the above in a desired amount of time. Therefore, as will be explained next, it is desirable to adopt a method for lowering the calculation cost and reducing the time required for search processing based on similarity calculation.

[0094] For example, the calculation cost can be reduced by calculating the similarity of the data set (j) of the model set only for the search subset obtained by sampling the model set based on the attention information. As another method, the search subset can be divided into hierarchical groups, and the similarity S can be calculated for the representative data of each group for each hierarchy. ijBy calculating the similarity S of the graph data, it is possible to link the representative structural information (j) of the group to which the data belongs with the same attention information. In this latter method, similarity calculations are performed for each layer, like a decision tree, so the number of similarity calculations can be reduced. ij As long as the search method is characterized by using the above as an evaluation index, various known search algorithms can be used.

[0095] A method for creating the search model 17 will be described from two perspectives: the common subset 210 and the machine learning method. The search model 17 is generated by calculating the similarity S between the subgraph data (i) of the input structure information (i) and the subgraph data of the search target structure information (j). ij is a similarity S that indicates high similarity when each piece of attention information is the same in the data set (j) and low similarity when they are different. ij It is desirable that the evaluation index is S that meets the requirements. ij In order to create a search model 17 that performs the calculation of similarity, a common subset 210 can be used in advance to optimize a similarity calculation method so that data can be distinguished for each attention information label. The optimization method follows the machine learning method described below. Here, the common subset 210 is composed of a set of subgraph data (j) and the corresponding attention information (j), and has the same format as the set of data (j) used to optimize the prediction model 16.

[0096] A method for creating a search model 17 that performs similarity calculations according to each machine learning method will be described. The machine learning method uses graph data as input and calculates the similarity S ijIt is necessary to be able to evaluate the above, and it is preferable to determine the distance using a graph kernel or a graph neural network (GNN). When using a graph kernel, the distance between graph data (i) and graph data (j) can be calculated from the definition of the graph kernel function. This calculated value is treated as the similarity between graph data (i) and graph data (j), and the closer the distance, the higher the similarity is treated. Although the similarity between two graph data can be directly calculated using the graph kernel, the distance in a secondary feature vector space obtained by clustering or dimensional reduction using the search subset 220 and a kernel function may also be calculated as the similarity. The secondary feature can be created by using the clustering or dimensional reduction method of a general kernel method in the same way.

[0097] The definition of distance can be cosine distance, Mahalanobis distance, Euclidean distance, Hausdorff distance, etc. in feature space, but there are no particular restrictions as long as the desired information can be added by using it as a similarity measure. However, one thing to note about calculations using graph kernels is that the information to be extracted from graph data changes depending on the attention information (label data) added to the graph data, so the graph kernel must be designed depending on the type of attention information. Therefore, it is not easy to extract information from graph data in a general purpose manner, and there is a drawback in that the kernel must be redesigned to improve the prediction model and search model.

[0098] On the other hand, when using GNN, which is a method suitable for constructing a model with high generalization performance, a search model 17 for calculating similarity is constructed. To optimize the search model, a method for calculating similarity between graph data can be optimized through a process of optimizing the parameters of the GNN using the data set (j) of the subgraph data of the common subset 210 and the attention information so as to increase the discrimination accuracy of the subgraph data of the common subset 210 as the attention information. For this reason, it is particularly desirable to use the GNN in the method for creating the search model 17.

[0099] Among the search model creation methods using GNNs, for example, a model for calculating the similarity between graph data can be created by using the method described in the literature "P. Riba, A. Fischer, J. Llados, and A. Fornns, in 2018 24th Int. Conf. Pattern Recognit. (2018), pp. 2239-2244." In this case, the similarity scale can be optimized by calculating subgraph data to which label data of the search subset 220 is assigned as a high similarity, and calculating subgraph data to which different label data is assigned as a low similarity (search model 17).

[0100] In addition, the method of the literature "Y. Li, C. Gu, T. Dullien, O. Vinyals, and P. Kohli, CoRR abs / 1904.12787, (2019)" makes it possible to embed graph data of the same label data at a close distance in the feature vector space through optimization based on label data. In addition, the similarity between graph data can be determined based on the distance in this feature vector space. As in the literature, the search model 17 that calculates the similarity can be optimized using a loss function based on the label data of the common subset 210 by comparing the similarity between graphs between two bodies and three bodies. Here, too, the similarity calculation method (search model 17) is optimized so that graph data with common attention information (label data) have high similarity and graph data with different attachment information have low similarity.

[0101] The method described in the aforementioned document can map graph data to a general feature vector space based on optimization for the common subset 210. This has the advantage that the search model can be used in combination with a general search algorithm that targets feature vectors corresponding to each graph data. Furthermore, the method described in the aforementioned document can be used in combination with a clustering process that groups feature vector data and a general sampling method that focuses on the data distribution in the feature vector space, so that the search subset 220 to be searched can be easily created by acquiring the search subset 220 using each of the aforementioned methods as appropriate.

[0102] The machine learning technique for creating the search model 17 is to calculate the similarity S between the subgraph data (i) and the subgraph data (j) in the search subset 220, which is the database to be searched. ij However, the machine learning method for creating the search model 17 is preferably one that can optimize the method of calculating the similarity according to the common subset 210.

[0103] The prediction model 16 and the search model 17 are distinguished based on their intended use. The prediction model 16 is created using the common subset 210, and therefore has a prior understanding of candidates (label data) of attention information, and is desirable when assigning any of a limited range of label data to new structure information (i). This is because the prediction model 16 predicts attention information to be assigned to the input graph data (i) from the label data in the range previously learned.

[0104] On the other hand, the search model 17 learns the similarity of the graph data by the common subset 210, and calculates the similarity S ijcan be obtained. At this time, the retrieval model 17 can calculate the similarity even for the label data of attention information that is not included in the common subset 210 during learning. Therefore, when the range of candidates for attention information cannot be determined in advance, such as when the label data of new attention information is updated in the database to be searched, linking of the attached information by the retrieval model 17 is effective.

[0105] (Example of operation) The manufacturing support system S has two input assistance functions, a change suggestion function, and an inspection assistance function. These functions are executed when the user specifies each function. However, each function may be executed without the user specifying it by setting conditions in advance. Each function will be described below in order with reference to Figs. 16 to 19.

[0106] The designer U1 assigns welding information to the welding lines that indicate the positions to be welded in the 3D-CAD structure. Although the welding lines on the 3D-CAD are generally expressed by sketch lines (one-dimensional lines that are structural components) or parts (3D structure), the present system can be applied as long as the welding lines are expressed as structural components. However, it is preferable that the method of expressing the structure be unified for each site where information management is performed. Here, an example of setting welding information between a circular metal plate 101 and a square metal plate 102 will be described with reference to Figs. 16 and 17. If the designer U1 assigns information without using the present system, it is necessary to manually input all the information on the welding lines 103 to 106 on the top surface of the square metal plate 102.

[0107] In this embodiment, the system complements the input work of the added information, thereby reducing the workload of the designer U1. Two complementing methods will be described. In the first method, welding information that has already been input as welding information for a selected location is also added to other locations on the same 3D-CAD file. In the second method, welding information that has not been input in the selected range is estimated and added. The following process is provided as a function of the 3D-CAD software or an add-on function.

[0108] FIG. 16 is a diagram for explaining a first method of the input assistance function. In the first method, four steps, steps 1-1 to 1-4, which will be described below, are executed in order. First, in step 1-1, the input unit 14 accepts an input operation by the designer U1, that is, a selection operation of the welding line 103 for which welding information has been input. However, multiple welds may be selected in this step. In the next step 1-2, the input unit 14 accepts an input of a range in which a target to which welding information is to be assigned exists from the designer U1. In FIG. 16, the selection range 305 selected by the designer U1 is shown by a rectangular parallelepiped drawn with dashed lines. When the designer U1 selects the selection range 305, the proposing unit 18 extracts the welding lines included in the selection range 305.

[0109] If the structural element of the 3D-CAD has information indicating the weld line as the target to which attention information should be added, the proposing unit 18 sets the weld lines 104, 105, and 106 as the selected structure selected based on the user's input based on this information. If the structural element of the 3D-CAD does not have information distinguishing the weld lines, the proposing unit 18 obtains the weld lines 104, 105, and 106 by extracting a structure similar to the weld part selected in step 1-1 based on the similarity of the graph data using the search model 17. The proposing unit 18 extracts welding information corresponding to the weld lines 104, 105, and 106 using the extracting unit 15. At this time, the extracting unit 15 uses the predictive model 16 or the search model 17 specified by the designer U1 or preset in advance.

[0110] In the following step 1-3, the suggestion unit 18 displays on a screen that the welding information of the welding line selected in step 1-1 will be added to the welding line extracted by the extraction unit 15 in step 1-2. In FIG. 16, the welding line to which the welding information is to be added is shown by a dashed ellipse. Here, an exclamation mark displayed next to the welding line indicates that information has been added to the welding line, and a dashed speech bubble indicates that the welding information has not yet been finalized. The suggestion unit 18 accepts approval or correction by the designer U1. If approved, the suggestion unit 18 finalizes the addition of the welding information to the extracted welding line, and if corrected, the suggestion unit 18 adds the corrected welding information.

[0111] The above process determines the information to be added as shown in steps 1-4. Regardless of whether the welding information is corrected or not, once it is determined, it is reflected in the design accumulation DB20. The total attention information graph DB20G and each model set and subset are updated as appropriate according to a criterion predetermined by the user or when the user determines that the performance of the prediction model and the search model needs to be improved. The timing of the update may be, for example, every time a predetermined time has passed, or when the number of data items with corrections to the user-added information by the designer U1 reaches a certain level. Here, data that has been corrected from the attention information proposed by the user or the proposal unit 18 indicates that there is room for improvement in the proposal on the system side, and is important data that should be learned preferentially by the model in order to improve the performance of each prediction and search model as each model set and subset are updated. Therefore, it is desirable for the data reflected in the design accumulation DB20 to hold information on whether or not the correction has been made.

[0112] FIG. 17 is a diagram for explaining a second method of the input assistance function. In the second method, four steps, steps 2-1 to 2-4, which will be described below, are executed in order. First, in step 2-1, the input unit 14 accepts a designation from the designer U1 as to whether to use the prediction model 16 or the search model 17. However, step 2-1 may be omitted by completing the designation in step 2-1 in advance. The designation by the designer U1 in step 2-1 may be made by selecting an option displayed on the screen, or by inputting a predetermined key from the keyboard.

[0113] In the next step 2-2, the input unit 14 accepts an input of a range in which the target to which welding information is to be assigned exists from the designer U1. In FIG. 17, the range specified by the designer U1 is indicated by a dashed line as a specified range 301. In the next step 2-3, the suggestion unit 18 first extracts welding lines from the specified range 301. The suggestion unit 18 then calculates welding information candidates for each welding line using the prediction model 16 or the search model 17 specified by the designer U1 in step 2-1. The suggestion unit 18 then displays the calculated welding information candidates and waits for the designer U1 to make a selection. Note that in FIG. 17, for convenience of drawing, candidates are displayed only for the welding line 106, but in reality, candidates are displayed for all welding lines.

[0114] At this time, the proposing unit 18 visually displays the corresponding probability. For example, the proposing unit 18 may arrange the welding information from top to bottom in order of the probability, or may display the welding information with a higher probability larger. The proposing unit 18 may also output the welding information with the highest probability as the first candidate. The "first candidate" is, for example, a candidate selected by default, and is a candidate that the designer U1 can select with the least operation. Note that although the table format is shown in FIG. 17, it is also possible to handle json or xml formats, which are highly flexible data structures, and the data may be displayed in a general tree format using a data structure visualization method. When the designer U1 selects the welding information for all the welding lines, the process proceeds to step 2-4, and all the welding information is confirmed. The confirmed welding information is reflected in the design accumulation DB20, and is also reflected in the all-attention information graph DB20G, the model set, and the subset.

[0115] Fig. 18 is a diagram for explaining the change suggestion function. In the change suggestion function, the following four steps, Step 3-1 to Step 3-4, are executed in order. Steps 3-1 and 3-2 are the same as Steps 2-1 and 2-2 described above, and therefore will not be described. However, in this example, some welding information has already been added to the weld lines 103 to 106.

[0116] In step 3-3, the suggestion unit 18 first extracts welding lines from the specified range 301. Next, the extraction unit 15 calculates welding information candidates for each welding line using the prediction model 16 or the search model 17 specified by the designer U1 in step 2-1. Unlike step 2-3, the welding information candidate calculated here is only one with the highest probability. Then, the suggestion unit 18 calculates the difference between the calculated welding information candidate and the welding information already assigned for each extracted welding line, and displays it on the screen as a change proposal 501. In FIG. 18, two exclamation marks are added to the welding lines that include the change proposal 501.

[0117] The change proposal 501 is preferably designed to allow the user to check information before and after the change to the welding information. However, there are no particular limitations as long as the information allows the user to check the reason why the welding information needs to be rechecked. The designer U1 judges whether the change proposal 501 is appropriate or not, and inputs the judgment result to the input unit 14. At this time, the designer U1 may input other correct values ​​that are not written in the change proposal 501. In step 3-4, the proposing unit 18 confirms each of the attached information based on the input by the designer U1 in step 3-3. The confirmed welding information is reflected in the design accumulation DB20, and is also reflected in the total attention information graph DB20G, the model set, and the subset.

[0118] The change suggestion function described above has the effect of prompting the process designer to recheck the welding information in light of past similar cases when the process designer adds welding information to the weld line, thereby preventing the occurrence of errors when inputting the welding information. In order to show the necessity of a system that realizes this effect, the issues at product production sites are shown. Even if the welding information seems to have been properly specified in the upstream process of process design, it is often found that the construction conditions are difficult to implement in the manufacturing process. For example, it may become clear at the construction stage that it is difficult to perform construction that satisfies the torch angle in the welding information due to a problem in the product structure.

[0119] When such a problem occurs, the manufacturing process manager or the person in charge may decide and implement alternative operation conditions. However, there is a problem in that the data of the operation conditions is not managed in a manner that allows the process designer to improve the process condition instructions in the future. Therefore, the change suggestion function in this embodiment can provide the process designer with an awareness by linking data indicating the change in the process conditions to the target structure, thereby preventing the occurrence of errors when inputting the process conditions.

[0120] FIG. 19 is a diagram for explaining the inspection assistance function. Here, caution information is mainly used. The inspection assistance function executes the following four steps, steps 4-1 to 4-4, in order. When the inspector U2 uses the liquid crystal display D3, the image information shown in FIG. 19 is displayed as is. When the inspector U2 uses the head-up display D2, the image information shown in FIG. 19 may be displayed transparently, or the image information shown in FIG. 19 excluding the component shapes may be displayed.

[0121] First, in step 4-1, the suggestion unit 18 uses the CAD engine C to output image information of the structural information of the inspection point of the product targeted by the inspector U2 from the same viewpoint as the inspector U2. In the next step 4-2, the weld lines to which the information of the inspection items is linked and check boxes for managing the progress of the inspection are further displayed. Specifically, the weld lines 103-106 in the figure are marked with check boxes indicating the status of the end of the welding inspection, and the exclamation marks next to the check boxes are icons for displaying details of the information to be inspected. In step 4-2, none of the check boxes are checked. For example, in a case where the weld line 106 is similar to a structure near the weld line and there was an oversight during the weld line inspection, the weld line is displayed in a different manner from the others, such as an exclamation mark 401, to draw attention.

[0122] When the inspection is completed, the inspector U2 checks the checkbox to manage the progress. In step 4-3, the inspection of the weld line 103 and the weld line 105 is completed. In addition, the inspector U2 can check detailed information to be inspected as shown by the reference numeral 403 by selecting the exclamation mark icon. Furthermore, an item that was overlooked in the past inspection may be displayed in a different manner from the others to further draw attention. For example, in the example shown in step 4-3, the item "number of welding layers" is underlined to draw attention. In step 4-4, if the attention information given to the weld line is inappropriate, the suggestion unit 18 accepts the correction of the attention information from the inspector U2. The attention information corrected by the inspector U2 is reflected in the design accumulation DB 20.

[0123] The inspection assistance function described above has the effect of raising the awareness of inspector U2 by displaying information related to defects or information input errors that have occurred in structure information similar to the target structure, and thus preventing the occurrence of similar defects or information input errors. The current issue with inspector U2 is that in order to prevent overlooking an inspection, multiple inspectors inspect the same inspection points multiple times. This increases the amount of work required, and there is a demand for both reducing the amount of work required and preventing overlooking an inspection.

[0124] In general, oversights during inspections are influenced by on-site conditions and human cognitive tendencies, and it is believed that there is a probabilistic bias in places where oversights are likely to occur. When considering accidents caused by inadequate inspections, as mentioned in Heinrich's rule of thumb, which is an empirical rule for workplace accidents, it is said that behind one serious accident, there are 29 minor accidents and 300 abnormalities. Similarly to this rule, behind the occurrence of serious oversights that occur during duplicate inspections, there are many minor oversights. Therefore, this function is useful as it prevents inspectors from oversights by linking inspection information that has been overlooked in the past to similar target structures and alerting users.

[0125] In order to handle a state in which no attention information is added in the prediction model 16 or the search model 17, the information that there is no attention information (label data) is treated as one type of label data during the system processing of FIG. 19, or the addition probability or similarity S, which is a criterion for acquiring candidates for added information, is used. ij The target structure information (i) is linked to the target structure information (i) only when the common subset 210 exceeds a certain threshold. The threshold is also determined based on an evaluation index for the accuracy of linking the target structure information (i) using the common subset 210.

[0126] According to the above-described first embodiment, the following advantageous effects can be obtained. (1) The manufacturing support system S includes a design accumulation DB 20 that stores three-dimensional design information including a plurality of partial structures, at least one of which is assigned with attention information, an input unit 14 that accepts a user's data operation on the three-dimensional design information, a model set generation unit 12 that converts the information of the partial structures into graph data, an extraction unit 15 that extracts attention information corresponding to the input graph data, and a suggestion unit 18 that inputs a selected structure, which is a partial structure selected based on an input by the user to the input unit 14, to the extraction unit 15 and suggests to the user that the attention information candidate, which is the attention information extracted by the extraction unit 15, be assigned to the selected structure. Therefore, it can be used to support design, not only for welding information, but also for various data to be linked to structures that constitute a product.

[0127] (2) The proposing unit 18 sets, as a selected structure, a partial structure including a part selected by the user via the input unit 14. Therefore, the manufacturing support system S can propose candidates for attention information to be assigned to the partial structure selected by the user.

[0128] (3) The proposing unit 18 sets as a selected structure a partial structure similar to a partial structure including a part selected by the user via the input unit 14. Therefore, the manufacturing support system S can propose candidates for attention information to be assigned to other partial structures similar to the partial structure selected by the user.

[0129] (4) The manufacturing support system S includes a prediction model 16 that identifies and outputs candidates for attention information corresponding to the input graph data of a selected structure based on prior learning. The extraction unit 15 outputs the candidates for attention information output by the prediction model 16.

[0130] (5) The extraction unit 15 calculates the likelihood information for each of the multiple candidates of attention information. The extraction unit outputs the candidate of attention information with the highest likelihood as the first candidate among the multiple candidates of attention information output by the prediction model 16. Therefore, the manufacturing support system S can prioritize the multiple candidates of attention information and present them to the user.

[0131] (6) The manufacturing support system S includes a common subset 210 including a plurality of combinations of graph data and attention information, and a search model 17 that searches the common subset 210 for similar graph data, which is graph data similar to the graph data of a selected structure, and outputs the attention information combined with the similar graph data. The extraction unit 15 outputs the attention information output by the search model 17.

[0132] (7) The search model 17 calculates the likelihood information for each of the multiple candidates of attention information. The extraction unit 15 outputs the candidate of attention information with the highest likelihood as the first candidate among the multiple candidates of attention information output by the prediction model. Therefore, the manufacturing support system S can prioritize the multiple candidates of attention information and present them to the user.

[0133] (8) The proposing unit 18 updates the design accumulation DB 20 by recording the user's response to the proposal in the design accumulation DB 20. The manufacturing support system S includes a model updating unit 19 having a function of updating parameters of the search model by using the design accumulation DB 20 updated by the proposing unit 18.

[0134] (9) The proposing unit 18 updates the design accumulation DB 20 by recording the user's response to the proposal in the design accumulation DB 20. The manufacturing support system S includes a model updating unit 19 having a function of updating parameters of the prediction model using the design accumulation DB 20 updated by the proposing unit 18.

[0135] (10) The attention information includes at least one of construction conditions, inspection information, welding construction defects, information related to accident cases, and jig information regarding the welding of the partial structure to which the attention information is attached.

[0136] (11) The attention information includes at least one of information relating to the fastening of the partial structure to which the attention information is attached using a screw, information on the screw hole corresponding to the screw, information on the type of screw, inspection information, construction defects, and information relating to accident cases.

[0137] (12) The attention information includes at least one of information related to the adhesion of the partial structure to which the attention information is attached, information on the adhesive used for adhesion, inspection information, defects, and information related to accident cases.

[0138] As described in this embodiment, constructing a system that collects and manages data in a common format is highly compatible with information addition using machine learning, and data scientists can use the collected database to continuously improve the prediction model 16 and the search model 17. The subgraph data that is the input of the prediction model 16 and the search model 17 is obtained by partially extracting the feature vectors and graph data held by the nodes and edges of the graph data, and this extraction method also follows the state of the updated database, making it easy for data scientists to improve it based on the evaluation results of the prediction accuracy of the information of interest.

[0139] The manufacturing support system S manages the accumulation, search, and utilization of data at production and development sites. The manufacturing support system S converts structural information on 3D-CAD, which is the product design drawing, into graph data, and uses it as data in a common format for accumulation, search, and utilization. As a result, the manufacturing support system S promotes the reuse of data that has not been utilized until now by horizontally deploying past cases and similar cases, and achieves the search and prediction of a wide range of information to be added to structures based on data. In this way, the manufacturing support system S improves work efficiency by supporting users' awareness to prevent human error and complementing the user's information assignment work.

[0140] Furthermore, by adding data obtained by having the user feed back the success or failure of the information of interest in the structure information to the database, it is possible to continuously improve the prediction model 16 and the search model 17. At this time, the newly created prediction model 16 and search model 17 also use graph data as input, and the prediction model 16 and search model 17 can be updated.

[0141] As described above, the predictive model 16 and the search model 17 can be continuously updated, and a general-purpose predictive model 16 and search model 17 can be generated in response to changes in the search subset 220 due to the following two points: (1) the data within the system is unified into graph data, which is a flexible and general-purpose data format, and (2) a method similar to GNN is used to input graph data to the predictive model 16 and the search model 17 and generate a model with high generalization performance for a variety of input data.

[0142] In the above-described embodiment, the configuration of the functional blocks is merely an example. Some functional configurations shown as separate functional blocks may be integrated, or a configuration shown in one functional block diagram may be divided into two or more functions. In addition, a part of the function of each functional block may be provided in another functional block. The present invention is not limited to the contents of the above-described embodiment. Other aspects conceivable within the scope of the technical idea of ​​the present invention are also included in the scope of the present invention. [Explanation of symbols]

[0143] 12…Model set generation section 13...Subset generation section 14...Input section 15...Extraction part 16…Prediction model 17…Search Model 18…Proposal Department 19…Model Update Section 20...Design accumulation database 20G…All hot topics graph database 200…Model set 210…Common subset 220…Search subset

Claims

1. an accumulation database for storing three-dimensional design information including a plurality of partial structures, at least one of the plurality of partial structures being assigned attention information; an input unit that accepts data operations by a user on the three-dimensional design information; a data conversion unit that converts information about the partial structure into graph data; an extraction unit that extracts information of interest corresponding to the input graph data; a proposal unit that inputs a selected structure, which is the partial structure selected based on an input by the user to the input unit, to the extraction unit, and proposes to the user that candidate attention information, which is the attention information extracted by the extraction unit, be assigned to the selected structure.

2. 2. The manufacturing support system according to claim 1, The proposal unit sets the partial structure including the part selected by the user via the input unit as the selected structure, in this manufacturing support system.

3. 2. The manufacturing support system according to claim 1, The suggestion unit sets the partial structure similar to the partial structure including a portion selected by the user via the input unit as the selected structure, in this manufacturing support system.

4. 2. The manufacturing support system according to claim 1, The method further includes a prediction model that identifies and outputs candidates for the attention information corresponding to the input graph data of the selected structure based on prior learning, The extraction unit outputs candidates for the attention information output by the prediction model.

5. The manufacturing support system according to claim 4, The prediction model further calculates likelihood information for each of the plurality of candidates for the attention information, The extraction unit outputs, as a first candidate, the candidate for attention information with the highest likelihood from among the multiple candidates for attention information output by the predictive model.

6. 2. The manufacturing support system according to claim 1, a search database including a plurality of combinations of the graph data and the attention information; a search model that searches the search database for similar graph data that is similar to the graph data of the selected structure, and outputs the attention information that is combined with the similar graph data; The extraction unit outputs the attention information output by the search model.

7. 7. The manufacturing support system according to claim 6, The search model further calculates likelihood information for each of the plurality of candidates of the attention information, The extraction unit outputs, as a first candidate, the candidate of interest information having the highest likelihood from among the multiple candidates of interest information output by the search model.

8. The manufacturing support system according to claim 4, The input unit updates the accumulation database by recording a response of the user to the suggestion by the suggestion unit in the accumulation database; The manufacturing support system further comprises a model updating unit having a function of updating parameters of the prediction model using the accumulated database updated by the input unit.

9. 7. The manufacturing support system according to claim 6, The input unit updates the accumulation database by recording a response of the user to the suggestion by the suggestion unit in the accumulation database; The manufacturing support system further comprises a model update unit having a function of updating parameters of the search model using the accumulation database updated by the input unit.

10. 2. The manufacturing support system according to claim 1, A manufacturing support system, wherein the attention information includes at least one of construction conditions, inspection information, welding construction defects, information related to accident cases, and jig information regarding the welding of the partial structure to which the attention information is attached.

11. 2. The manufacturing support system according to claim 1, A manufacturing support system in which the attention information includes at least one of information regarding the fastening of the partial structure to which the attention information is attached using a screw, information regarding the screw hole corresponding to the screw, information regarding the type of the screw, inspection information, construction defects, and information regarding accident cases.

12. 2. The manufacturing support system according to claim 1, A manufacturing support system, wherein the attention information includes at least one of information relating to the adhesive used for bonding, inspection information, defects, and accident cases, regarding the bonding of the partial structure to which the attention information is attached.

13. A manufacturing support method executed by a computer having a database storing three-dimensional design information including a plurality of partial structures, at least one of the plurality of partial structures being assigned attention information, the method comprising: an input step of accepting a user's data operation for the three-dimensional design information; a data conversion step of converting information of the partial structure into graph data; an extraction step of determining a similarity between the plurality of partial structures based on the graph data; a proposal step of inputting a selected structure, which is the partial structure selected based on the user's input in the input step, into the extraction step, and proposing to the user that candidate attention information, which is the attention information extracted by the extraction step, be assigned to the selected structure.

Images