Map image generating device, control method, and program

Abstract

A map image generation device (2000) acquires material specification information (10) that represents the material specification of a material (60) and property information (20) that represents the property information of a deliverable (70). The map image generation device (2000) generates a self-organizing map (30) using the property information (20). Each node of the self-organizing map (30) is assigned a property vector that indicates a value regarding a position in the map space and a physical quantity of each of multiple kinds of properties of the deliverable (70). The map image generation device (2000) assigns, using the material specification information (10), a specification vector to each node of the self-organizing map (30), that indicates a value regarding the material specification. The map image generation device (2000) generates a map image (40) on the basis of the assignment of the specification vector to each node. In the map image (40), the nodes are clustered or colored on the basis of the specification vector.

Description

[Technical field]

[0001] The present disclosure relates to techniques for providing information related to product development. [Background technology]

[0002] In product development, it is useful to understand the relationship between materials and the end product. Therefore, a system that supports understanding of the relationship between materials and the end product has been developed. For example, Patent Document 1 discloses a system that uses a self-organizing map to support understanding of the causal relationship between design values ​​and physical property values ​​of a tire. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-148988 A Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, a self-organizing map is used to identify which of multiple design variables of a tire is an important factor. Therefore, it is not envisioned to use the self-organizing map for any other purpose. The present disclosure has been made in consideration of such problems, and an object of the present disclosure is to provide a new technology that provides information useful for product development. [Means for solving the problem]

[0005] The map image generating device of the present disclosure has an acquisition unit that acquires, for each of multiple patterns of materials that can be used in a target process, material specification information that represents the material specifications of the material and physical property information that indicates physical property quantities for each of multiple physical properties of a product that can be generated in the process using the material, a self-organizing map generation unit that uses the physical property information to generate a self-organizing map in which each node is assigned a position in a map space and a physical property vector that indicates a value related to the physical property quantities for each of multiple types of physical properties of the product, and a map image generation unit that generates a map image representing each of the nodes arranged in the map space. The map image generation unit uses the material parameter information to assign a parameter vector indicating a value related to a material parameter to each of the nodes, and performs one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the parameter vector to each of the nodes.

[0006] The control method of the present disclosure is executed by a computer and includes an acquisition step of acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material, a self-organizing map generation step of generating, using the physical property information, a self-organizing map in which a position in a map space and a physical property vector that indicates a value related to each of a plurality of types of physical property of the product are assigned to each node, and a map image generation step of generating a map image that indicates each of the nodes arranged in the map space. In the map image generation step, a parameter vector indicating a value related to the material parameter is assigned to each node using the material parameter information, and based on the assignment of the parameter vector to each node, one or both of clustering and coloring of each node are performed in the map image.

[0007] The non-transitory computer-readable medium of the present disclosure stores a program that causes a computer to execute the control method of the present disclosure. Effect of the Invention

[0008] According to the present disclosure, a new technology is provided that provides information useful for product development. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a diagram illustrating an example of an outline of the operation of the map image generating device of the first embodiment. [Diagram 2] 1 is a block diagram illustrating an example of a functional configuration of a map image generating device according to a first embodiment. [Diagram 3] FIG. 2 is a block diagram illustrating a hardware configuration of a computer that realizes the map image generating device. [Figure 4] 4 is a flowchart illustrating a flow of processing executed by the map image generating device of the first embodiment. [Diagram 5] FIG. 11 is a diagram illustrating an example of material specification information in a table format. [Figure 6] FIG. 2 is a diagram illustrating an example of physical property information in a table format. [Figure 7] FIG. 13 is a diagram illustrating, in table form, an example of the configuration of a self-organizing map in which a specification vector is assigned to each node. [Figure 8] FIG. 13 is a diagram illustrating an example map image in which nodes are clustered. [Figure 9] 11 is a flowchart illustrating an example of the flow of a process for assigning colors to nodes. [Figure 10] FIG. 13 is a diagram illustrating an example of a map image colored based on specification vectors. [Figure 11] FIG. 13 is a diagram illustrating an example of a map image including a target display. [Figure 12] FIG. 13 is a diagram illustrating a case in which material specifications are displayed in the target display. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are given the same reference numerals, and duplicated explanations will be omitted as necessary for clarity of explanation. Furthermore, unless otherwise specified, predetermined information such as a predetermined value or a threshold value is stored in advance in a storage device accessible from a device that uses the information.

[0011] [Embodiment 1] <Summary> Fig. 1 is a diagram illustrating an example of an outline of the operation of the map image generating device 2000 of the embodiment 1. Here, Fig. 1 is a diagram for facilitating understanding of the outline of the map image generating device 2000, and the operation of the map image generating device 2000 is not limited to that shown in Fig. 1.

[0012] The map image generating device 2000 generates a map image 40 for a deliverable 70 that can be generated in a specific process (hereinafter, a target process) of product development. The map image 40 is an image that expresses the correspondence between the distribution of material specifications of materials used in generating the deliverable 70 and the distribution of physical properties of the deliverable 70.

[0013] The deliverable 70 is what is predicted to be produced or what has actually been produced by processing the material 60 in the production process of the target process. The material 60 is a material used to produce the deliverable 70. Various patterns of the material 60 can be used in the target process. The physical properties of the deliverable 70 can vary depending on the material 60 used.

[0014] A pattern of the material 60 is specified by the material specifications. In other words, materials 60 having different material specifications are treated as materials 60 having different patterns. On the other hand, materials 60 having the same material specifications are treated as materials 60 having the same pattern.

[0015] The material specifications are expressed by, for example, the type of material, the type of substances constituting the material, the blending ratio of each substance, and the type of processing performed to create the material. Examples of the type of material include carbon fiber reinforced plastic and stainless steel. For example, assume that the material 60 is carbon fiber reinforced plastic. In this case, the material specifications of the material 60 include the type of each of one or more carbon fibers constituting the material 60 (such as polyacrylonitrile fiber or carbonized cellulose fiber), the type of each of one or more resins constituting the material 60 (such as epoxy or polyether terephthalate), and the blending ratio of those substances. The material specifications may further include the type of fiber directional polymerization method, the type of compression bonding method, and the resin composition.

[0016] In order to generate such a map image 40, the map image generating device 2000 acquires, for each of the multiple patterns of materials 60 (in other words, for the materials 60 specified by each of the multiple patterns of material specifications), material specification information 10 indicating the material specifications of the materials 60 and physical property information 20 indicating the physical properties of a product 70 that can be generated in a target process using the materials 60. The physical property information 20 indicates the physical property quantities of each of multiple types of physical properties for the product 70. The types of physical properties are, for example, flame retardancy, heat resistance, elastic modulus, toughness, etc.

[0017] The map image generating device 2000 uses the physical property information 20 to generate a self-organizing map 30 that represents the distribution of the physical properties of the deliverable 70. The self-organizing map 30 has a plurality of nodes arranged in an m-dimensional map space. Here, m is set to 2 or 3 so that a map image 40 can be generated from the self-organizing map 30. For example, the nodes can be expressed as squares of a grid or as lattices on a grid.

[0018] Multidimensional data (hereinafter, physical property vector) that represents the magnitude of each of a plurality of types of physical properties is assigned to each node of the self-organizing map 30. For example, assume that four types of physical properties, namely flame retardancy, heat resistance, elastic modulus, and toughness, are used. In this case, the physical property vector is four-dimensional data that represents the magnitude of each of the physical property quantities of these four types of physical properties. Hereinafter, the number of dimensions of the physical property vector is set to n, where n>m. That is, in the self-organizing map 30, the space of the physical property vector is a high-dimensional space, and the map space is a low-dimensional space.

[0019] The physical property information 20 indicates physical property quantities for n or more types of physical properties. The map image generating device 2000 performs learning of the self-organizing map 30 using the physical property quantities for the n types of physical properties indicated by the physical property information 20, and generates the self-organizing map 30 by determining the physical property vectors to be assigned to each node.

[0020] Furthermore, the map image generating device 2000 assigns each piece of material specification information 10 to any one of the nodes of the self-organizing map 30. Specifically, the map image generating device 2000 assigns multidimensional data (hereinafter, specification vectors) representing the values ​​of each of a plurality of types of parameters (hereinafter, specification parameters) indicated by the material specification information 10 to the nodes. Here, the specification vector obtained from the material specification information 10 is assigned to a node having a physical property vector most similar to n-dimensional data obtained from the physical property information 20 corresponding to the material specification information 10 (physical property information 20 representing the physical property of the product 70 generated by using the material 60 specified by the material specification information 10). As a result, each pair of the material specification information 10 and the physical property information 20 acquired by the map image generating device 2000 is associated with any one of the nodes of the self-organizing map 30. That is, in the self-organizing map 30, the material specification is associated with the physical property of the product 70.

[0021] The map image generating device 2000 generates a map image 40 based on the association between the nodes and the specification vectors in the self-organizing map 30. The map image 40 represents the arrangement of each node in an m-dimensional space. Furthermore, each node in the map image 40 is 1) clustered based on the association between the nodes and the specification vectors, or 2) colored based on the association between the nodes and the specification vectors.

[0022] <Example of action and effect> In product development, in order to generate a product with desired physical properties, a search is sometimes made for materials capable of generating such a product. One method for achieving such a search is to perform a simulation of the generation of the product while changing the material specifications in various ways, or to experimentally generate the product. Furthermore, a method is also conceivable in which a reverse analysis is performed to predict material specifications from desired physical properties by utilizing the correspondence between the material specifications and the physical properties of the product accumulated through such simulations or experimental generation of the product (the correspondence between the material specification information 10 and the physical property information 20 in this disclosure).

[0023] In this regard, the map image generating device 2000 generates a self-organizing map 30 using physical property vectors obtained from each of the multiple physical property information 20, and assigns a property vector representing a material property to each node of the self-organizing map 30. Then, the map image generating device 2000 performs one or both of clustering and coloring of the nodes based on the assignment of the material property to each node. As a result, the distribution of the material property can be grasped on the self-organizing map representing the distribution of the physical property. In other words, by using the map image 40, the corresponding relationship between the distribution of the physical property and the distribution of the material property can be grasped. Therefore, the map image 40 can be used for the above-mentioned inverse analysis.

[0024] For example, suppose that among the nodes shown in the map image 40, there is a node that represents physical properties close to those desired by the user of the map image generating device 2000. In this case, it can be said that there is a high probability that a product 70 having the desired physical properties can be generated by using a material 60 specified by the material specifications represented by that node, or a material 60 specified by material specifications close to those of the node.

[0025] In this regard, in the map image 40, clustering and coloring based on the property vectors are further performed on the self-organizing map 30 generated based on the property vectors. Therefore, it can be said that both the property and the material property are similar to each other in nodes classified into the same cluster or nodes assigned similar colors. Therefore, for example, the user of the map image generating device 2000 starts from a node that represents a property close to the desired property, and searches for materials in the vicinity of the material property represented by the starting node (each node included in the same cluster as the node, or each node with a similar color to the node). This allows an efficient (less time and cost) search for materials capable of generating the product 70 having the desired property.

[0026] The map image generating device 2000 of this embodiment will be described in more detail below.

[0027] <Example of functional configuration> FIG. 2 is a block diagram illustrating a functional configuration of the map image generating device 2000 of the first embodiment. The map image generating device 2000 includes an acquisition unit 2020, a self-organizing map generating unit 2040, and a map image generating unit 2060. The acquisition unit 2020 acquires material specification information 10 and physical property information 20 for each of a plurality of patterns of materials 60. The self-organizing map generating unit 2040 generates a self-organizing map 30 using the physical property information 20. The map image generating unit 2060 assigns a specification vector obtained from each material specification information 10 to each node of the self-organizing map 30. Furthermore, the map image generating unit 2060 generates a map image 40 representing the arrangement of the nodes in the map space of the self-organizing map 30. In the map image 40, the nodes are clustered or colored based on the specification vector assigned to the node.

[0028] <Example of hardware configuration> Each functional component of the map image generating device 2000 may be realized by hardware that realizes each functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a further explanation is given of the case where each functional component of the map image generating device 2000 is realized by a combination of hardware and software.

[0029] 3 is a block diagram illustrating an example of a hardware configuration of a computer 500 that realizes the map image generating device 2000. The computer 500 is any computer. For example, the computer 500 is a stationary computer such as a server machine or a PC (Personal Computer). In addition, for example, the computer 500 is a portable computer such as a smartphone or a tablet terminal. The computer 500 may be a dedicated computer designed to realize the map image generating device 2000, or may be a general-purpose computer.

[0030] For example, by installing a specific application on the computer 500, each function of the map image generating device 2000 is realized by the computer 500. The application is configured with a program for realizing each functional component of the map image generating device 2000. The method of acquiring the program is arbitrary. For example, the program can be acquired from a storage medium (such as a DVD disk or USB memory) on which the program is stored. Alternatively, the program can be acquired by downloading the program from a server device that manages the storage device on which the program is stored.

[0031] The computer 500 has a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface 510, and a network interface 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and other components to each other is not limited to a bus connection.

[0032] The processor 504 is a processor such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 506 is a main storage device realized using a random access memory (RAM) or the like. The storage device 508 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, or a read only memory (ROM) or the like.

[0033] The input / output interface 510 is an interface for connecting the computer 500 to an input / output device. For example, the input / output interface 510 is connected to an input device such as a keyboard and an output device such as a display device.

[0034] The network interface 512 is an interface for connecting the computer 500 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0035] The storage device 508 stores a program (a program that realizes the above-mentioned application) that realizes each functional component of the map image generating device 2000. The processor 504 reads this program into the memory 506 and executes it to realize each functional component of the map image generating device 2000.

[0036] The map image generating device 2000 may be realized by one computer 500, or may be realized by multiple computers 500. In the latter case, the configurations of the computers 500 do not need to be the same, and can be different from each other.

[0037] <Processing flow> FIG. 4 is a flowchart illustrating a process flow executed by the map image generating device 2000 of the first embodiment. The acquiring unit 2020 acquires material specification information 10 and physical property information 20 for each of a plurality of materials 60 that can be used in the target process (S102). The self-organizing map generating unit 2040 generates a self-organizing map 30 using the physical property information 20 (S104). The map image generating unit 2060 assigns a specification vector obtained from each material specification information 10 to any node of the self-organizing map 30 (S106). The map image generating unit 2060 generates a map image 40 from the self-organizing map 30 based on the assignment of the specification vector to the node (S108).

[0038] <Acquisition of material specification information 10 and physical property information 20: S102> The acquisition unit 2020 acquires, for each of a plurality of patterns of materials 60 that can be used in a target process, material specification information 10 that indicates the material specifications of the material 60, and physical property information 20 about a product 70 that can be generated using the material 60 (S102). FIG. 5 is a diagram illustrating an example of the material specification information 10 in a table format. The table 100 in FIG. 5 has columns of material identification information 102 and material specifications 104. The material identification information 102 indicates identification information assigned to the material 60. The material specifications 104 indicate the specifications of the material 60.

[0039] 5, the material specification information 10 is represented by one record in a table 100. That is, the material specification information 10 associates identification information of a material 60 with the material specifications of the material 60 having that identification information.

[0040] Fig. 6 is a diagram illustrating an example of the physical property information 20 in table format. The table 200 in Fig. 6 has columns of deliverable identification information 202 and physical properties 204. The deliverable identification information 202 indicates identification information of the deliverable 70. The physical properties 204 indicate the physical properties of the deliverable 70. In the table 200, the physical properties of the deliverable 70 are represented by indicating, for each physical property, a correspondence of "label indicating the type of physical property: physical property amount of that physical property."

[0041] 6, the physical property information 20 is represented by one record in a table 200. That is, the physical property information 20 associates identification information of a deliverable 70 with the physical property of the deliverable 70 having that identification information.

[0042] The acquisition unit 2020 acquires a plurality of pairs of the material specification information 10 and the physical property information 20. There are various methods for the acquisition unit 2020 to acquire the pairs of the material specification information 10 and the physical property information 20. For example, the pairs of the material specification information 10 and the physical property information 20 are stored in advance in an arbitrary storage device accessible from the map image generating device 2000. The acquisition unit 2020 acquires the pairs of the material specification information 10 and the physical property information 20 by accessing this storage device. Alternatively, for example, the acquisition unit 2020 may acquire the pairs of the material specification information 10 and the physical property information 20 by accepting a user input for inputting the pairs of the material specification information 10 and the physical property information 20. Alternatively, for example, the acquisition unit 2020 may acquire the pairs of the material specification information 10 and the physical property information 20 by receiving the pairs of the material specification information 10 and the physical property information 20 transmitted from another device.

[0043] Here, there are various methods for generating a pair of the material specification information 10 and the physical property information 20. For example, the pair of the material specification information 10 and the physical property information 20 is generated by simulating the generation of the product 70. Specifically, by inputting specific material specifications and executing a simulation, the physical property information 20 indicating the predicted values ​​of the physical property quantities of each physical property of the product 70 is generated. Then, a pair of the generated physical property information 20 and the material specification information 10 indicating the material specifications inputted as input is obtained. Here, existing technology can be used to realize a simulation in which material specifications are acquired as input, and prediction data of the physical properties of a product generated in a specific process using the material for a material specified by the material specifications is outputted.

[0044] Alternatively, for example, a pair of the material specification information 10 and the physical property information 20 may be generated by actually generating a product 70. Specifically, the product 70 is experimentally generated by using a material 60 represented by specific material specifications in a target process. Furthermore, the physical property amount of each physical property is measured for the generated product 70, thereby generating the physical property information 20. As a result, a pair of the generated physical property information 20 and the material specification information 10 representing the used material 60 is obtained.

[0045] The physical property information 20 acquired by the acquisition unit 2020 may include information having different data expression methods. For example, different labels may be used for essentially the same physical property. Also, physical property quantities of the same physical property may be expressed in different units. In such a case, it is preferable for the acquisition unit 2020 to unify the data expression methods by unifying the labels or converting the units. It is considered that such a situation in which the data expression methods of the physical property information 20 differ from each other may occur, for example, when acquiring both the physical property information 20 generated by using a simulation and the physical property information 20 generated by actually generating the deliverable 70. It is preferable that such unification of the data expression methods is also performed for the material specification information 10.

[0046] <Generation of self-organizing map 30: S104> The self-organizing map generating unit 2040 generates a self-organizing map 30 by using the physical property information 20 (S104). The self-organizing map 30 has a plurality of nodes arranged in an m-dimensional map space (m=2 or m=3). The number of dimensions of the map space, either two or three, may be determined in advance or may be specified by the user. An n-dimensional physical property vector is assigned to each node of the self-organizing map 30.

[0047] The allocation of physical property vectors to each node is performed by learning the self-organizing map 30. The self-organizing map 30 can be learned by inputting n-dimensional training data to be used for learning to the self-organizing map 30. Here, an existing method can be used as a specific method for learning the self-organizing map using the training data.

[0048] For example, the self-organizing map generating unit 2040 initializes the self-organizing map 30 by an arbitrary method. For example, the method of initialization may be a method of initializing the physical property vector of each node to a random value. The self-organizing map generating unit 2040 generates a plurality of n-dimensional physical property vectors by extracting the physical property amount of each of the n types of physical properties from each of the acquired plurality of pieces of physical property information 20. The self-organizing map generating unit 2040 generates the self-organizing map 30 by learning the self-organizing map 30 by treating each of the plurality of physical property vectors as training data. As a result, the physical property vector of each node of the self-organizing map 30 becomes n-dimensional data indicating the value of each of the physical property amounts of the n types of physical properties.

[0049] The n-dimensional data obtained from the physical property information 20 may directly represent the physical property quantities of the n types of physical properties represented by the physical property information 20, or may represent values ​​obtained by converting each physical property quantity in a predetermined method (e.g., normalization, standardization, etc.).

[0050] Here, the number of physical properties indicated by the physical property information 20 may be greater than n. In this case, a part of the data indicated by the physical property information 20 is used to generate the self-organizing map 30. Here, which type of physical property is to be used to generate the self-organizing map 30 among the physical properties indicated by the physical property information 20 may be determined in advance or may be specified by the user.

[0051] <Assignment of characteristic vectors: S106> In order to generate a map image 40 from the self-organizing map 30, the map image generator 2060 assigns a specification vector to each node of the self-organizing map 30 by using the material specification information 10 (S106). Here, the specification vector obtained from the material specification information 10 may indicate values ​​for all parameters indicated by the material specification information 10, or may indicate values ​​for some of the parameters. In other words, if the number of dimensions of the specification vector is k, the value of k may be the same as the number of parameters indicated by the material specification information 10, or may be smaller than the number of parameters indicated by the material specification information 10.

[0052] For example, suppose that the material specification information 10 indicates both parameters that take continuous values ​​(e.g., the compounding ratio of materials) and parameters that do not take continuous values ​​(e.g., the type of processing, etc.). In this case, the specification vector is generated by the parameters that take continuous values.

[0053] Incidentally, which parameters among those indicated by the material characteristic information 10 are used to generate the characteristic vector may be determined in advance or may be designated by the user. Also, the characteristic vector may directly indicate the values ​​of the parameters indicated by the material characteristic information 10, or may indicate values ​​obtained by converting the values ​​of the parameters by a predetermined method (for example, by performing normalization or standardization).

[0054] To determine the allocation of the specification vectors to each node, for example, the map image generating unit 2060 assigns each piece of material specification information 10 to a node. The physical property information 20 corresponding to the material specification information 10 is used to assign the material specification information 10 to the node. In other words, the map image generating unit 2060 identifies a node having a physical property vector that is most similar to a physical property vector obtained from the physical property information 20 corresponding to the material specification information 10. The map image generating unit 2060 assigns the material specification information 10 to the identified node. The map image generating unit 2060 assigns the specification vector obtained from the material specification information 10 to the node to which the material specification information 10 is assigned.

[0055] Here, as a result of the above process, there may be nodes to which the material specification information 10 is not assigned. Therefore, for example, the map image generating unit 2060 estimates the specification vectors to be assigned to the nodes to which the material specification information 10 is not assigned. That is, the map image generating unit 2060 estimates the distribution of the specification vectors based on the specification vectors of each node to which the material specification information 10 is assigned and the arrangement of these nodes in the map space. Then, the map image generating unit 2060 assigns specification vectors to the nodes to which the material specification information 10 is not assigned, using the estimated distribution.

[0056] There are various methods for estimating the distribution of the specification vectors. For example, the map image generating unit 2060 estimates the distribution of the specification vectors by any interpolation process such as linear interpolation or spline interpolation. Alternatively, for example, the map image generating unit 2060 may estimate the distribution of the specification vectors by sparse estimation. Note that when estimating the distribution of the specification vectors, Bayesian estimation may be further applied to improve the estimation accuracy.

[0057] Here, by further searching for materials (i.e., simulation, etc.) and increasing the number of pairs of material specification information 10 and physical property information 20 used by the map image generating device 2000, the number of nodes to which the material specification information 10 is assigned can be increased. As a result, the number of data points obtained by actual measurement can be increased in the distribution of material specifications, so that the distribution of specification vectors can be estimated with higher accuracy. In this case, it is preferable to select the material specifications to be the target of simulation, etc. by using Bayesian optimization. Specifically, for the physical properties of the product 70 generated from a material 60 having certain material specifications, a predicted value and its probability (prediction error) can be obtained by prediction using Bayesian estimation. Using this predicted value and error, the data point to be measured next (i.e., the material specifications to be the target of simulation, etc.) can be specified. According to this method, a material that can obtain a product 70 with better physical properties can be searched for with fewer trials.

[0058] Fig. 7 is a diagram illustrating, in table form, an example of the configuration of a self-organizing map 30 in which a property vector is assigned to each node. The table 300 in Fig. 7 has four columns: position 302, physical property vector 304, material identification information 306, and property vector 308. The table 300 has one record for each node.

[0059] Position 302 indicates the coordinates of the node on the m-dimensional map space. In the example of FIG. 7, m=2, and x and y coordinates are assigned to the node. Physical property vector 304 indicates an n-dimensional physical property vector assigned to the node. In the example of FIG. 7, n=4. Material identification information 306 indicates, for a node to which material property information 10 is assigned, the identification information of the material 60 indicated by the material property information 10 assigned to that node. In the record of a node to which material property information 10 is not assigned, material identification information 306 indicates "-". Property vector 308 indicates a k-dimensional property vector assigned to the node. In the example of FIG. 7, k=3.

[0060] <Generation of map image 40: S108> The map image generating unit 2060 generates a map image 40 by using the specification vectors assigned to the nodes (S108). The map image 40 is an image that represents the arrangement of each node in the map space of the self-organizing map 30. In addition, in the map image 40, the nodes are subjected to either or both of clustering and coloring based on the specification vectors. Below, the clustering and coloring based on the specification vectors will each be described.

[0061] <<Clustering based on characteristic vectors>> The map image generating unit 2060 performs clustering of the nodes based on the specification vectors assigned to each node. Here, existing technology can be used for clustering the nodes based on the vectors associated with each of the multiple nodes. For example, the map image generating unit 2060 performs clustering of the nodes using a clustering algorithm such as the k-means method. The number of clusters to be generated may be set as a fixed number, may be specified by the user, or may be calculated as a result of executing a clustering algorithm.

[0062] When clustering based on the specification vectors is performed, the map image generating unit 2060 includes, in the map image 40, an indication that enables each of the multiple clusters generated by the clustering to be identified. For example, the map image 40 is configured to show the boundary line of each cluster.

[0063] Fig. 8 is a diagram illustrating a map image 40 in which nodes are clustered. In Fig. 8, each square in a two-dimensional grid represents a node. The map image 40 in Fig. 8 has seven clusters. The clusters are separated by borders that are thicker than the borders of the nodes.

[0064] The display that makes the clusters identifiable is not limited to the borders. For example, the map image generating unit 2060 may assign a unique color or pattern to each of the multiple clusters, and assign the color or pattern assigned to each cluster to each node included in the cluster.

[0065] <<Coloring based on property vectors>> The map image generating unit 2060 colors each node based on the specification vector of the node. For example, the map image generating unit 2060 determines the magnitude of the components of one or more reference colors (e.g., three primary colors) that make up the color to be assigned to the node based on the value of any element of the specification vector (i.e., specification parameter). Hereinafter, the color to be assigned to a node is referred to as the assigned color. Below, a specific example of a method of assigning colors to nodes will be described.

[0066] FIG. 9 is a flowchart illustrating the flow of a process for assigning colors to nodes. S202 to S212 constitute a loop process L1. The loop process L1 is executed once for each node included in the self-organizing map 30. In S202, the map image generating unit 2060 determines whether or not the loop process L1 has been executed for all nodes. If the loop process L1 has already been executed for all nodes, the process in FIG. 9 ends. On the other hand, if there are nodes that have not yet been the target of the loop process L1, the map image generating unit 2060 selects one node from among them. The node selected here is denoted as node i.

[0067] S204 to S208 constitute a loop process L2. The loop process L2 is executed once for each type of specification parameter used to determine the assigned colors. In S204, the map image generating unit 2060 judges whether or not the loop process L2 has been executed for all types of specification parameters used to determine the assigned colors. If the loop process L2 has already been executed for all types of specification parameters used to determine the assigned colors, the process of FIG. 9 proceeds to S210. On the other hand, if there is a specification parameter that has not yet been the target of the loop process L2 among the specification parameters used to determine the assigned colors, the map image generating unit 2060 selects one specification parameter from among them. The specification parameter selected here is referred to as the jth specification parameter.

[0068] In S206, the map image generating unit 2060 determines the magnitude of the jth reference color component in the assigned color of node i based on the value indicated by the specification vector of node i for the jth specification parameter. For example, the magnitude of the jth reference color component in the assigned color of node i is calculated by a conversion formula determined based on the numerical range of values ​​indicated by the specification vector for the jth specification parameter and the numerical range of the magnitude of each reference color component. This conversion formula is expressed, for example, by the following formula (1).

number

[0069] Here, in the conversion formula expressed by formula (1), the larger the value indicated by the specification vector for the jth specification parameter, the larger the component of the jth reference color. In other words, the magnitude of the component of the jth reference color monotonically increases with respect to the value indicated by the specification vector for the jth specification parameter. However, the magnitude of the component of the jth reference color does not necessarily have to monotonically increase with respect to the value indicated by the specification vector for the jth specification parameter. For example, the smaller the value indicated by the specification vector for the jth specification parameter, the larger the value set for the component of the jth reference color.

[0070] S208 is the end of the loop process L2, so the process in FIG.

[0071] S210 is executed after the loop process L2 for one node i is repeated. Therefore, before executing S210, the magnitude of each reference color component is determined for the assigned color of node i. Therefore, in S210, the map image generating unit 2060 assigns a color specified by the magnitude of each determined reference color component to node i. For example, red, green, and blue are used as the first to third reference colors, respectively. In this case, the assigned color of node i is (R, G, B) = (f(x[i, 1]), f(x[i, 2]), f(x[i, 3])).

[0072] S212 is the end of the loop process L1, so the process in FIG.

[0073] Based on the color allocation to the nodes determined in this manner, the map image generation unit 2060 generates the map image 40. Specifically, the map image generation unit 2060 generates the map image 40 by expressing each node arranged on the map space in the assigned color of that node.

[0074] For example, suppose the arrangement of nodes is represented using grids. In this case, the map image 40 is an image including grids in which each grid is represented (e.g., filled) in the color assigned to the node corresponding to that grid. FIG. 10 is a diagram illustrating a map image 40 colored based on the specification vectors. In the map image 40 of FIG. 10, the color of the grid corresponding to each node is set to the assigned color of that node. For convenience of illustration, differences in color are represented by differences in the density of the diagonal lines.

[0075] The method of expressing the arrangement of nodes is not limited to the method of using a grid. For example, the arrangement of nodes may be expressed using a grid. In this case, for example, the map image 40 becomes an image of a grid in which an area within a predetermined range around each grid point (for example, a circle of a predetermined radius centered on the grid point) is expressed in the assigned color of the node corresponding to the grid point.

[0076] <Display that allows you to grasp desired physical properties> The map image generating device 2000 may obtain target information, which is information that represents desired physical properties of the resultant product 70, and include in the map image 40 a display that represents a node that corresponds to the desired physical properties. Hereinafter, this display will be referred to as a target display. If a node that corresponds to a desired physical property can be displayed on the map image 40, it will be easier for a user of the map image generating device 2000 to search for a material 60 that can generate a resultant product 70 having desired physical properties. A specific description will be given below.

[0077] First, the map image generating device 2000 acquires target information. For example, the target information is input by a user of the map image generating device 2000. Here, the acquisition of the target information may be performed before the map image 40 is generated, or may be performed after the map image 40 is generated. In the latter case, for example, the map image generating device 2000 acquires the target information after outputting the map image 40 that does not include a target display, and updates the map image 40 so that the target display is included.

[0078] The map image generating device 2000 generates a physical property vector from the target information. The method of generating a physical property vector from the target information is similar to the method of generating a physical property vector from the physical property information 20.

[0079] The map image generating device 2000 identifies a node having a physical property vector that has the highest similarity to the physical property vector obtained from the target information from among the nodes of the self-organizing map 30. The map image generating device 2000 then includes in the map image 40 a target indication indicating that this node is a node corresponding to the desired physical property.

[0080] 11 is a diagram illustrating a map image 40 including a target display. In FIG. 11, the target display is designated by reference numeral 42.

[0081] It can be said that the node to which the target indicator 42 is attached represents the property closest to the desired property among the distribution of the property represented by the self-organizing map 30. Therefore, it can be said that the specification vector assigned to this node represents the material property that is most likely to be capable of generating the resultant product 70 having the desired property among the distribution of the material properties represented by the self-organizing map 30. From this, by viewing the map image 40 including the target indicator 42, the user of the map image generating device 2000 can grasp the material property that is most likely to be capable of generating the resultant product 70 having the desired property from the specification vector of the node to which the target indicator 42 is attached.

[0082] For example, the user searches for a material 60 capable of generating a product 70 having desired physical properties, starting from the material specifications represented by the specification vector of the node to which the target indicator 42 is attached. That is, the user executes a simulation and actually generates the product 70 using the material specifications represented by the specification vector of the node to which the target indicator 42 is attached, or one or more patterns of material specifications close to the material specifications. Then, the user specifies the material specifications capable of generating the product 70 having desired physical properties based on the results of the simulation and the generation of the product 70. According to this method, the material specifications to be the starting point of the search can be easily specified by using the map image 40, so that the time and cost required for the search can be reduced compared to the case where the map image 40 is not used.

[0083] Here, it is preferable to specify the range of material search (material specifications close to the material specifications represented by the specification vector of the node to which the target indicator 42 is attached) and the order of material search based on the cluster and coloring of the nodes. For example, the user searches for materials in a cluster including the node to which the target indicator 42 is attached. In the example of FIG. 11, the node to which the target indicator 42 is displayed is included in the cluster at the top right. Thus, the user searches for materials in this cluster. Alternatively, for example, the user searches for materials in the order of nodes having colors that are most similar to the color of the node to which the target indicator 42 is attached.

[0084] The target display 42 may not only be a mark for simply identifying a node, but may also include other information. For example, the target display 42 may include material specifications represented by the corresponding node. Fig. 12 is a diagram illustrating a case in which material specifications are displayed in the target display 42. In Fig. 12, the target display 42 represents the blending ratio of physical properties A, B, and C.

[0085] As described above, the value indicated by the specification vector may be the value of the parameter of the material specification converted by a method such as normalization. In such a case, it is preferable that the value included in the target display 42 is not the value indicated by the specification vector itself, but the value converted into the value of the parameter of the material specification.

[0086] <Map image 40 output> The map image generating device 2000 outputs the generated map image 40. The map image 40 may be output in any manner. For example, the map image generating device 2000 stores the map image 40 in any storage device accessible from the map image generating device 2000. As another example, the map image generating device 2000 displays the map image 40 on any display device controllable by the map image generating device 2000. As another example, the map image generating device 2000 transmits the map image 40 to any device communicably connected to the map image generating device 2000.

[0087] When the map image 40 is displayed on a display device, the screen preferably has a function of further displaying information about each node. The information about the node is, for example, a physical property vector or a specification vector assigned to the node. For example, when the user selects a specific node (for example, by hovering the mouse over the node), information about the node is displayed. Note that, when the values ​​of the physical property vector or specification vector assigned to the node have been transformed by normalization or the like, it is preferable to perform an inverse transformation to return them to parameter values ​​of the physical property amount or material specification before displaying them on the screen.

[0088] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0089] In the above example, the program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable medium includes various types of tangible storage media. Examples of the non-transitory computer readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs, CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable medium include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable medium can supply the program to the computer via a wired communication path such as an electric wire or optical fiber, or via a wireless communication path.

[0090] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) an acquisition means for acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material, and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating means for generating a self-organizing map in which a position in a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating means for generating a map image representing each of the nodes arranged on the map space, The map image generating means includes: using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A map image generating device that performs one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the specification vectors to the nodes. (Appendix 2) The map image generating means includes: identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; A map image generating device as described in Appendix 1, which calculates the specification vectors to be assigned to the nodes other than each of the identified nodes by performing an interpolation process based on the arrangement of each of the identified nodes in the map space and the specification vectors assigned to each of the identified nodes. (Appendix 3) The map image generating means includes: clustering the nodes based on the assignment of the characteristic vectors to the nodes; 3. The map image generating device according to claim 1 or 2, wherein the map image includes an indication that enables each cluster to be distinguished from the others. (Appendix 4) In the map image, the color of each of the nodes is determined by the magnitude of one or more reference color components that make up the color of the node; A map image generating device described in any one of Appendix 1 to 3, wherein the map image generating means determines the magnitude of each of the reference color components in the color to be assigned to the node using a value indicated by the parameter corresponding to the reference color in the specification vector assigned to the node. (Appendix 5) The map image generating means includes: obtaining target information representative of desired properties of the product; A map image generating device as described in any one of Appendix 1 to 4, wherein the map image includes a target indication that can identify the node to which the physical property vector that is assigned is most similar to the physical property vector obtained from the target information. (Appendix 6) The map image generating device according to claim 5, wherein the map image generating means includes in the target display a material property represented by the property vector assigned to the node corresponding to the target display. (Appendix 7) 1. A computer-implemented control method comprising: an acquisition step of acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating step of generating a self-organizing map in which a position on a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating step of generating a map image representing each of the nodes arranged on the map space, In the map image generating step, using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A control method comprising: performing one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the specification vectors to the nodes. (Appendix 8) In the map image generating step, identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; The control method described in Appendix 7, wherein the characteristic vectors to be assigned to the nodes other than each of the identified nodes are calculated by performing an interpolation process based on the arrangement of each of the identified nodes in the map space and the characteristic vectors assigned to each of the identified nodes. (Appendix 9) In the map image generating step, clustering the nodes based on the assignment of the characteristic vectors to the nodes; 9. The control method of claim 7 or 8, wherein the map image includes an indication that enables each cluster to be distinguished from the others. (Appendix 10) In the map image, the color of each of the nodes is determined by the magnitude of one or more reference color components that make up the color of the node; A control method described in any one of Appendix 7 to 9, wherein in the map image generation step, the magnitude of each of the reference color components in the color to be assigned to the node is determined using a value indicated by the specification vector assigned to that node for a parameter corresponding to that reference color. (Appendix 11) In the map image generating step, obtaining target information representative of desired properties of the product; A control method according to any one of appendices 7 to 10, further comprising including in the map image a target indication capable of identifying the node to which the physical property vector most similar to the physical property vector obtained from the target information is assigned. (Appendix 12) 12. The control method according to claim 11, wherein in the map image generating step, material properties represented by the property vector assigned to the node corresponding to the target display are included in the target display. (Appendix 13) On the computer, an acquisition step of acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating step of generating a self-organizing map in which a position on a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating step of generating a map image representing each of the nodes arranged in the map space; In the map image generating step, using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A non-transitory computer-readable medium that clusters and / or colors each of the nodes in the map image based on the assignment of the feature vectors to the nodes. (Appendix 14) In the map image generating step, identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; The non-transitory computer-readable medium of claim 13, further comprising: performing an interpolation process based on the location of each of the identified nodes in the map space and the characteristic vectors assigned to each of the identified nodes to calculate the characteristic vectors to be assigned to the nodes other than each of the identified nodes. (Appendix 15) In the map image generating step, clustering the nodes based on the assignment of the characteristic vectors to the nodes; 15. The non-transitory computer-readable medium of claim 13 or 14, wherein the map image includes an indication that each cluster is distinguishable from the other clusters. (Appendix 16) In the map image, the color of each of the nodes is determined by the magnitude of one or more reference color components that make up the color of the node; A non-transitory computer-readable medium according to any one of appendixes 13 to 15, wherein in the map image generation step, the magnitude of each of the reference color components in the color assigned to the node is determined using the value indicated by the characteristic vector assigned to that node for the parameter corresponding to that reference color. (Appendix 17) In the map image generating step, obtaining target information representative of desired properties of the product; 17. The non-transitory computer-readable medium of any one of claims 13 to 16, further comprising a target representation in the map image that identifies the node to which the physical property vector is assigned that is most similar to a physical property vector obtained from the target information. (Appendix 18) 18. The non-transitory computer-readable medium of claim 17, wherein in the map image generation step, material properties represented by the property vector assigned to the node corresponding to the target representation are included in the target representation.

[0091] This application claims priority to Japanese Patent Application No. 2021-044486, filed on March 18, 2021, the disclosure of which is incorporated herein in its entirety.

[0092] 10 Material specifications 20 Physical properties information 30 Self-Organizing Maps 40 Map Images 42 Target Display 60 materials 70 Deliverables 100 Tables 102 Material Identification Information 104 Material specifications 200 Tables 202 Product Identification Information 204 Physical Properties 300 Tables 302 position 304 Physical Property Vectors 306 Material Identification Information 308 Parameter Vector 500 Computers 502 Bus 504 Processor 506 Memory 508 Storage Devices 510 Input / Output Interface 512 Network Interface 2000 Map image generator 2020 Acquisition Department 2040 Self-organizing map generator 2060 Map image generator

Claims

1. an acquisition means for acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material, and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating means for generating a self-organizing map in which a position in a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating means for generating a map image representing each of the nodes arranged on the map space, The map image generating means includes: using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A map image generating device that performs one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the specification vectors to the nodes.

2. The map image generating means includes: identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; The map image generating device of claim 1, wherein the characteristic vectors to be assigned to the nodes other than each of the identified nodes are calculated by performing an interpolation process based on the arrangement of each of the identified nodes in the map space and the characteristic vectors assigned to each of the identified nodes.

3. The map image generating means includes: clustering the nodes based on the assignment of the characteristic vectors to the nodes; The map image generating device according to claim 1 or 2, wherein the map image includes an indication that enables each cluster to be distinguished from the others.

4. In the map image, the color of each of the nodes is determined by the magnitude of one or more reference color components that constitute the color of the node; A map image generating device according to any one of claims 1 to 3, wherein the map image generating means determines the magnitude of each of the reference color components in the color to be assigned to the node using a value indicated by the specification vector assigned to the node for a parameter corresponding to that reference color.

5. The map image generating means includes: obtaining target information representative of desired properties of the product; A map image generating device according to claim 1 , wherein the map image includes a target indication capable of identifying the node to which the physical property vector most similar to the physical property vector obtained from the target information is assigned.

6. 6. The map image generating device according to claim 5, wherein said map image generating means includes, in said target representation, material properties represented by said property vectors assigned to said nodes corresponding to said target representations.

7. 1. A computer-implemented control method comprising: an acquisition step of acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating step of generating a self-organizing map in which a position on a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating step of generating a map image representing each of the nodes arranged on the map space, In the map image generating step, using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A control method comprising: performing one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the specification vectors to the nodes.

8. In the map image generating step, identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; The control method according to claim 7, further comprising: calculating the characteristic vectors to be assigned to the nodes other than each of the identified nodes by performing an interpolation process based on the arrangement of each of the identified nodes in the map space and the characteristic vectors assigned to each of the identified nodes.

9. On the computer, an acquisition step of acquiring, for each of a plurality of patterns of materials that can be used in a target process, material specification information that indicates material specifications of the material and physical property information that indicates physical property quantities for each of a plurality of physical properties of a product that can be generated in the process using the material; a self-organizing map generating step of generating a self-organizing map in which a position on a map space and a physical property vector indicating a value related to each of a plurality of types of physical properties of the deliverable are assigned to each node using the physical property information; a map image generating step of generating a map image representing each of the nodes arranged in the map space; In the map image generating step, using each of the material property information, assigning a property vector indicating a value related to the material property to each of the nodes; A program that performs one or both of clustering and coloring of each of the nodes in the map image based on the assignment of the specification vectors to the nodes.

10. In the map image generating step, identifying the node to which the physical property vector most similar to the physical property vector obtained from the physical property information corresponding to each of the plurality of material specification information is assigned; The program according to claim 9, further comprising: calculating the characteristic vectors to be assigned to the nodes other than each of the identified nodes by performing an interpolation process based on the arrangement of each of the identified nodes in the map space and the characteristic vectors assigned to each of the identified nodes.

Images