Map generation device, map generation method, and program

Abstract

This map generation device (2000) acquires material specification information (10) and physical property information (20) in a plurality. The material specification information (10) indicates a material specification. The physical property information (20) indicates a physical quantity for each of a plurality of physical properties of a deliverable (70), which can be produced in the material specification indicated in the corresponding material specification information (10). The map generation device (2000) performs clustering of the plurality of physical property information (20) and extracts some of the physical property information (20) from each cluster. The map generation device (2000) generates a self-organizing map (30) by using the extracted physical property information (20). A physical property vector, which indicates a value pertaining to the physical quantity of each of a plurality of types of physical property of the deliverable (70), is allocated to each of a plurality of nodes on a map space of the self-organizing map (30). The map generation device (2000) allocates the material specification information (10) corresponding to the physical property information (20) extracted from a cluster to any one of the nodes on the self-organizing map (30).

Description

Technical Field

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

Background Art

[0002] In product development, it is useful to understand the relationship between materials and products. Therefore, a system for assisting in understanding the relationship between materials and products has been developed. For example, Patent Document 1 discloses a system that uses a self-organizing map to assist in understanding the causal relationship between the design values and physical property values of tires.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In Patent Document 1, a self-organizing map is used to identify which of the multiple design variables of a tire is an important factor. Therefore, it is not assumed to use the self-organizing map for other purposes. The present disclosure is in view 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 Problems

[0005] The map generation device of the present disclosure acquires a plurality of material specification information indicating material specifications, and for each of the material specification information, acquires property information indicating the amount of each of a plurality of physical properties of a product that can be produced with the material specifications indicated by the material specification information; a clustering execution means for clustering the plurality of property information; from each of the plurality of clusters generated by the clustering, extracting some of the property information among the plurality of property information included in the cluster, and using the extracted property information, generating a self-organizing map in which a property vector indicating a value related to the amount of each of the plurality of physical properties of the product is assigned to each node in the map space; and an assignment means for assigning the material specification information corresponding to the extracted property information to any one of the nodes.

[0006] The map generation method of the present disclosure is executed by a computer. The map generation method includes: an acquisition step of acquiring a plurality of material specification information indicating material specifications, and for each of the material specification information, acquiring property information indicating the amount of each of a plurality of physical properties of a product that can be produced with the material specifications indicated by the material specification information; a clustering execution step of clustering the plurality of property information; a generation step of extracting some of the property information among the plurality of property information included in each of the plurality of clusters generated by the clustering, and using the extracted property information, generating a self-organizing map in which a property vector indicating a value related to the amount of each of the plurality of physical properties of the product is assigned to each node in the map space; and an assignment step of assigning the material specification information corresponding to the extracted property information to any one of the nodes.

[0007] The non-transitory computer-readable medium of the present disclosure stores a program for causing a computer to execute the map generation method of the present disclosure.

Advantages of the Invention

[0008] According to the present disclosure, a new technology for providing information useful for product development is provided.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted as necessary for clarity of explanation. Also, unless otherwise specified, information such as predetermined values and threshold values that are predetermined is stored in advance in a storage device or the like accessible from the device that uses the information.

[0011] [Embodiment 1] <Overview> FIG. 1 is a diagram illustrating an overview of the operation of the map generation device 2000 according to Embodiment 1. Here, FIG. 1 is a diagram for facilitating the understanding of the overview of the map generation device 2000, and the operation of the map generation device 2000 is not limited to that shown in FIG. 1.

[0012] The map generation device 2000 generates a self-organizing map 30 representing the distribution of physical properties of the various products 70 that can be generated in a specific process (hereinafter referred to as the target process) of product development. The product 70 is predicted to be generated by processing the material 60 in the generation process of the target process, or is actually generated. The material 60 is a material used for generating the product 70. In the target process, various patterns of the material 60 can be used. The physical properties of the product 70 may vary depending on the material 60 used.

[0013] One pattern of the material 60 is specified by the material specifications. In other words, materials 60 with different material specifications are treated as different patterns of the material 60. On the other hand, materials 60 with the same material specifications are treated as the same pattern of the material 60.

[0014] The material specifications are represented by, for example, the type of material, the type of substance 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 one or more carbon fibers (such as polyacrylonitrile fiber and cellulose carbonized fiber) constituting the material 60, the type of each one or more resins (such as epoxy and polyether terephthalate) constituting the material 60, and the blending ratio of these substances. Further, the material specifications may further include the type of fiber orientation polymerization method, the type of crimping method, and the resin composition.

[0015] Note that the target process may be a single process or a combination of a plurality of consecutive processes. In this case, the product 70 can be a product generated by processing the material 60 through these plurality of consecutive processes. For example, assume that the target process is a combination of process P1 and process P2. In this case, the product 70 can be obtained by processing the material 60 in the generation process of process P1 and then processing the product of process P1 in the generation process of process P2.

[0016] The self-organizing map 30 has a plurality of nodes arranged on an m-dimensional map space. Here, in order to be able to visually represent (for example, in an image) the map space, m is set to 2 or 3. In the visually represented map space, each node is represented by, for example, a cell in a grid or a lattice on a grid.

[0017] To each node of the self-organizing map 30, multi-dimensional data (hereinafter referred to as physical property vector) representing the magnitude of the physical property amount of each of a plurality of types of physical properties is assigned. 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 4-dimensional data representing the magnitude of the physical property amount of each of these four types of physical properties. Hereinafter, the number of dimensions of the physical property vector is denoted as n. Here, 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.

[0018] To generate such a self-organizing map 30, the map generation device 2000 obtains, for each of a plurality of patterns of materials 60 (in other words, for the materials 60 specified by each of the material specifications of the plurality of patterns), material specification information 10 representing the material specifications of the material 60 and property information 20 corresponding to the material specification information 10. That is, the map generation device 2000 obtains a plurality of pairs of material specification information 10 and property information 20. The property information 20 corresponding to the material specification information 10 indicates the amount of each of a plurality of types of physical properties of the product 70 that can be generated in the target process using the material 60 of the material specifications represented by the material specification information 10. The types of physical properties are, for example, flame retardancy, heat resistance, elastic modulus, or toughness. Note that the number of types of physical properties indicated by the property information 20 is equal to or greater than the dimension number n of the physical property vector.

[0019] The map generation device 2000 performs clustering on the plurality of obtained property information 20 based on the amount of physical properties indicated by each property information 20. As a result, a plurality of clusters of the property information 20 are generated.

[0020] The map generation device 2000 extracts a part of the plurality of property information 20 included in each cluster from each cluster. Each piece of property information extracted here is referred to as "target property information". Then, the map generation device 2000 generates the self-organizing map 30 by training the self-organizing map 30 using the amount of physical properties indicated by each target property information and determining the physical property vector to be assigned to each node. Therefore, the map generation device 2000 generates the self-organizing map 30 using only a part of the obtained property information 20, not all of the property information 20. And the property information 20 used for the generation of the self-organizing map 30 is determined based on the result of clustering.

[0021] Furthermore, the map generation device 2000 assigns the material specifications information 10 corresponding to each object property information to any node of the self-organizing map 30. Specifically, the map generation device 2000 assigns the material specifications information 10 corresponding to the object property information to the node having the physical property vector most similar to the n-dimensional data obtained from the object property information. As a result, each pair of object property information and material specifications information 10 is associated with any node of the self-organizing map 30. That is, in the self-organizing map 30, the material specifications and the physical properties of the product 70 are associated with each other.

[0022] <An example of the operation and effect> In product development, in order to produce a product having desired physical properties, it may be necessary to search for materials that can produce such a product. As one method of realizing such a search, there is a method of simulating the production of a product while variously changing the material specifications, or experimentally producing a product. Furthermore, an inverse analysis method of predicting material specifications from preferable physical properties by using the correspondence relationship between the material specifications and the physical properties of the product (the correspondence relationship between the material specifications information 10 and the object property information 20 in the present disclosure) accumulated through such simulations and experimental production of the product is also conceivable.

[0023] In this regard, the map generation device 2000 generates a self-organizing map 30 by using physical property vectors obtained from each of a plurality of object property information 20, and assigns material specifications information 10 representing material specifications to each node of the self-organizing map 30. By using such a self-organizing map 30, the distribution of material specifications can be grasped on the self-organizing map representing the distribution of physical properties. That is, by using the self-organizing map 30, the correspondence relationship between the distribution of physical properties and the distribution of material specifications can be grasped. Therefore, the self-organizing map 30 can be used for the above-described inverse analysis.

[0024] In addition, when performing simulations or the like while varying various material specifications, there may be a bias in the physical properties of the resulting products. For example, even if simulations or the like are performed while randomly changing the pattern of material specifications so as to be uniformly distributed, the physical properties of the products do not necessarily follow a uniform distribution. Therefore, among the plurality of pieces of physical property information 20 obtained by simulations or the like, there may be many pieces of physical property information 20 that exhibit similar physical properties to each other.

[0025] When there are many pieces of physical property information 20 that exhibit similar physical properties to each other, if a self-organizing map 30 is generated using all the pieces of physical property information 20, in the self-organizing map 30, the influence of the physical properties indicated by these many pieces of physical property information 20 that are similar to each other will become strong. Therefore, there is a possibility that the distribution of material specifications and physical properties cannot be accurately represented by the self-organizing map 30.

[0026] In this regard, the map generation device 2000 clusters the plurality of pieces of physical property information 20 obtained, extracts some pieces of physical property information 20 from each cluster, and generates a self-organizing map 30. In this way, by extracting and using representative pieces of physical property information 20 from each cluster, it is possible to reduce the bias in the distribution of physical properties for the pieces of physical property information 20 used in the generation of the self-organizing map 30. Therefore, an accurate self-organizing map 30 can be generated.

[0027] Generating a self-organizing map 30 using representative pieces of physical property information 20 is particularly useful in cases where the target process is a combination of multiple processes. For example, assume that the target process consists of two processes: a first process of producing plastic from a plastic material and a second process of producing a propeller from the plastic produced in the first process. In this case, the material specification information 10 indicates information regarding the plastic material, information regarding the structure of the plastic, and information regarding the manufacturing method of the plastic, etc. And the physical property information 20 indicates information regarding the physical properties of the propeller produced in the second process.

[0028] Here, in order to be able to generate a propeller having desired properties, it is preferable to be able to grasp appropriate material specifications in the first step so that an appropriate plastic for the propeller can be generated. Thus, for example, the person in charge of the first step performs simulations of the first step and the second step while varying the material specifications (such as the plastic material and manufacturing method) as the input of the first step. As a result, a self-organizing map 30 is generated that associates the distribution of the plastic material specifications (input of the first step) with the distribution of the physical properties of the propeller (output of the second step).

[0029] At this time, as described above, it is preferable to generate the self-organizing map 30 using a representative part of the physical property information 20 instead of all the physical property information 20 obtained by simulations or the like. Here, as one method of selecting the physical property information 20 to be used for generating the self-organizing map 30, a method of manual selection by the person in charge of the first step can be considered. However, the person in charge of the first step may not have sufficient knowledge about the second step necessary to make this selection appropriately. For example, when the first step and the second step are carried out by different companies, the knowledge about the second step held by the company carrying out the second step may not be provided to the company carrying out the first step. Therefore, it is considered difficult for the person in charge of the first step to manually select the physical property information 20 to be used for generating the self-organizing map 30.

[0030] In this regard, according to the map generation device 2000, the physical property information 20 to be used for generating the self-organizing map 30 is automatically selected based on the result of clustering the physical property information 20. Therefore, even when the person in charge of the step of inputting the material specification information 10 does not have sufficient knowledge about the subsequent steps, a highly accurate self-organizing map 30 can be generated using a plurality of physical property information 20 with less bias.

[0031] Hereinafter, the map generation device 2000 of the present embodiment will be described in more detail.

[0032] <Example of functional configuration> FIG. 2 is a block diagram illustrating the functional configuration of the map generation device 2000 according to Embodiment 1. The map generation device 2000 includes an acquisition unit 2020, a clustering execution unit 2040, a generation unit 2060, and an allocation unit 2080. The acquisition unit 2020 acquires material specification information 10 and object property information 20 for each of a plurality of patterns of materials 60. The clustering execution unit 2040 performs clustering of the object property information 20. The generation unit 2060 generates a self-organizing map 30 using the target object property information. The target object property information is the object property information 20 extracted from each cluster. A part of the plurality of object property information 20 included in the cluster is extracted from each cluster. The allocation unit 2080 allocates the material specification information 10 corresponding to each target object property information to any node of the self-organizing map 30.

[0033] <Example of Hardware Configuration> Each functional component of the map generation device 2000 may be realized by hardware (e.g., a hard-wired electronic circuit, etc.) that realizes each functional component, 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.). Hereinafter, the case where each functional component of the map generation device 2000 is realized by a combination of hardware and software will be further described.

[0034] FIG. 3 is a block diagram illustrating the hardware configuration of a computer 1000 that realizes the map generation device 2000 according to Embodiment 1. The computer 1000 is an arbitrary computer. For example, the computer 1000 is a stationary computer such as a PC (Personal Computer) or a server machine. In addition, for example, the computer 1000 is a portable computer such as a smartphone or a tablet terminal. The computer 1000 may be a dedicated computer designed to realize the map generation device 2000, or may be a general-purpose computer.

[0035] For example, by installing a predetermined application on the computer 1000, each function of the map generation device 2000 is realized on the computer 1000. The above application is composed of a program for realizing each functional component of the map generation device 2000. Note that the method for obtaining the above program is arbitrary. For example, the program can be obtained from a storage medium (such as a DVD disc or a USB memory) in which the program is stored. In addition, for example, the program can be obtained by downloading the program from a server device that manages the storage device in which the program is stored.

[0036] The computer 1000 has a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. The bus 1020 is a data transmission path for the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 to transmit and receive data to and from each other. However, the method of connecting the processor 1040 and the like to each other is not limited to bus connection.

[0037] The processor 1040 is various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array). The memory 1060 is a main storage device realized using a RAM (Random Access Memory) or the like. The storage device 1080 is an auxiliary storage device realized using a hard disk, an SSD (Solid State Drive), a memory card, or a ROM (Read Only Memory) or the like.

[0038] The input / output interface 1100 is an interface for connecting the computer 1000 and the input / output device. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 1100.

[0039] The network interface 1120 is an interface for connecting the computer 1000 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0040] The storage device 1080 stores a program (a program for realizing the above-described application) for realizing each functional component of the map generation device 2000. The processor 1040 reads this program into the memory 1060 and executes it, thereby realizing each functional component of the map generation device 2000.

[0041] The map generation device 2000 may be realized by one computer 1000 or by a plurality of computers 1000. In the latter case, the configurations of the respective computers 1000 do not have to be the same and can be different from each other.

[0042] <Flow of processing> FIG. 4 is a flowchart exemplifying the flow of processing executed by the map generation device 2000 according to Embodiment 1. The acquisition unit 2020 acquires the material specifications information 10 and the physical property information 20 for each of a plurality of patterns of the material 60 (S102). The clustering execution unit 2040 performs clustering on the physical property information 20 to generate a plurality of clusters (S104). The generation unit 2060 extracts target physical property information from each cluster (S106). The generation unit 2060 generates a self-organizing map 30 using the target physical property information (S108). The allocation unit 2080 allocates the material specifications information 10 corresponding to the target physical property information to any node of the self-organizing map 30 (S110).

[0043] <Acquisition of Material Specifications Information 10 and Physical Property Information 20: S102> The acquisition unit 2020 acquires material specifications information 10 representing the material specifications of each of a plurality of patterns of materials 60 that can be used in the target process, and physical property information 20 regarding the product 70 that can be generated using the material 60 (S102). FIG. 5 is a diagram illustrating the material specifications 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 the identification information assigned to the material 60. The material specifications 104 indicate the specifications of the material 60.

[0044] In FIG. 5, the material specifications information 10 is represented by one record in the table 100. That is, the material specifications information 10 associates the identification information of the material 60 with the material specifications of the material 60 having the identification information.

[0045] FIG. 6 is a diagram illustrating the physical property information 20 in a table format. The table 200 in FIG. 6 has columns of product identification information 202 and physical properties 204. The product identification information 202 indicates the identification information of the product 70. The physical properties 204 indicate the physical properties of the product 70. In the table 200, the physical properties of the product 70 are represented by showing the association of "label representing the type of physical property: physical property amount of the physical property" for each physical property.

[0046] In FIG. 6, the physical property information 20 is represented by one record in the table 200. That is, the physical property information 20 associates the identification information of the product 70 with the physical properties of the product 70 having the identification information.

[0047] The acquisition unit 2020 acquires a plurality of pairs of material specifications information 10 and physical property information 20. There are various methods for the acquisition unit 2020 to acquire the pair of material specifications information 10 and physical property information 20. For example, the pair of material specifications information 10 and physical property information 20 is stored in advance in an arbitrary storage device accessible from the map generation device 2000. The acquisition unit 2020 accesses this storage device to acquire the pair of material specifications information 10 and physical property information 20. Additionally, for example, the acquisition unit 2020 may acquire the pair of material specifications information 10 and physical property information 20 by receiving a user input for inputting the pair of material specifications information 10 and physical property information 20. Additionally, for example, the acquisition unit 2020 may acquire the pair of material specifications information 10 and physical property information 20 by receiving the pair of material specifications information 10 and physical property information 20 transmitted from another device.

[0048] Here, there are various methods for generating the pair of material specifications information 10 and physical property information 20. For example, the pair of material specifications information 10 and physical property information 20 is generated by performing a simulation of the generation of the product 70. Specifically, by inputting specific material specifications as input and executing the simulation, physical property information 20 indicating predicted values of the physical property amounts of each physical property for the product 70 is generated. Then, a pair of the generated physical property information 20 and the material specifications information 10 indicating the material specifications given as input is obtained. Here, for the technology that acquires material specifications as input and outputs prediction data of the physical properties of the product generated in a specific process using the material specified by the material specifications, existing technologies can be utilized.

[0049] Additionally, for example, the pair of material specifications information 10 and physical property information 20 may be generated by actually performing the generation of the product 70. Specifically, by using the material 60 represented by specific material specifications in the target process, the product 70 is experimentally generated. Further, for the generated product 70, physical property information 20 is generated by measuring the physical property amounts of each physical property. As a result, a pair of the generated physical property information 20 and the material specifications information 10 representing the used material 60 is obtained.

[0050] Note that the physical property information 20 acquired by the acquisition unit 2020 may include those with different data representation methods. For example, it is conceivable that different labels are used for essentially the same physical properties. Also, it is conceivable that the physical property amounts of the same physical property are represented in different units. In such a case, it is preferable for the acquisition unit 2020 to unify the data representation method by performing label unification, unit conversion, etc. Such a situation where the data representation methods of the physical property information 20 are different from each other may occur, for example, when acquiring both the physical property information 20 generated using simulation and the physical property information 20 generated by actually producing the product 70. Note that it is preferable to perform the unification of such data representation methods in the same way for the material specifications information 10.

[0051] <Clustering of Physical Property Information 20: S104> The clustering execution unit 2040 performs clustering of the physical property information 20 (S104). Specifically, the clustering execution unit 2040 performs clustering of the physical property information 20 by clustering the physical property vectors obtained from each of the plurality of physical property information 20 acquired by the acquisition unit 2020.

[0052] For example, the clustering execution unit 2040 performs clustering of the physical property vectors by using various clustering algorithms such as the k-means method. At this time, it is preferable for the clustering execution unit 2040 to perform dimensionality reduction on the physical property vectors and perform clustering using the physical property vectors after dimensionality reduction. By performing dimensionality reduction in this way, it is possible to prevent the self-organizing map 30 from being strongly affected by those physical properties when the physical property information 20 includes a plurality of highly correlated physical properties. Note that as the method of dimensionality reduction, various methods such as a method using a neural network and a method using principal component analysis can be used.

[0053] As described above, the physical property vector is n-dimensional data representing the magnitudes of the physical property amounts of each of the n types of physical properties. The physical property vector may directly indicate the physical property amounts of each of the n types of physical properties indicated by the physical property information 20, or may indicate values obtained by converting each physical property amount by a predetermined method (for example, normalization, standardization, etc.).

[0054] Here, the number of physical properties indicated by the physical property information 20 may be more than n. In this case, a part of the data indicated by the physical property information 20 is represented by the physical property vector. Here, regarding which types of physical properties among the physical properties indicated by the physical property information 20 are to be represented by the physical property vector (in other words, which types of physical properties are to be used for generating the self-organizing map 30), it may be determined in advance or may be specified by the user.

[0055] <Extraction of target physical property information: S106> The generation unit 2060 extracts target physical property information from each cluster (S106). Here, there are various methods for extracting target physical property information from a cluster. For example, the clustering execution unit 2040 randomly extracts a predetermined number of pieces of physical property information 20 from each cluster and uses the extracted physical property information 20 as the target physical property information.

[0056] The number of pieces of target physical property information extracted from a cluster may be different for each cluster. For example, the clustering execution unit 2040 determines, for each cluster, the number of pieces of target physical property information to be extracted from that cluster based on the size of that cluster. Here, the larger the size of the cluster, the more pieces of target physical property information are extracted from the cluster.

[0057] For example, the clustering execution unit 2040 calculates a statistical value (for example, an average value) of the sizes of all the clusters as a reference value for the size. Then, the clustering execution unit 2040 calculates the ratio of the size of each cluster to the reference value, and sets the value obtained by multiplying that ratio by a predetermined reference number as the number of pieces of target physical property information to be extracted from that cluster. It is assumed that an arbitrary value is set in advance for the reference number.

[0058] Here, the method for determining the size of the cluster is arbitrary. For example, the size of the cluster can be determined by the number of piece property information 20 included in the cluster. Additionally, for example, the size of the cluster may be determined by the magnitude of the variation of the property vectors obtained from each piece of piece property information 20 included in the cluster.

[0059] <Self-organizing map 30 generation: S108> The generation unit 2060 generates a self-organizing map 30 using each piece of target piece property information (S108). The self-organizing map 30 has a plurality of nodes arranged on an m-dimensional map space (m = 2 or m = 3). Whether to adopt two dimensions or three dimensions as the number of dimensions of the map space may be predetermined or specified by the user. An n-dimensional property vector is assigned to each node of the self-organizing map 30.

[0060] FIG. 7 is a diagram illustrating the configuration of the self-organizing map 30 in tabular form. The table 300 has two columns, namely the node 302 and the property vector 304. Each record in the table 300 represents that the property vector shown in the property vector 304 of that record is assigned to the node specified by the node 302 of that record. In FIG. 7, the node 302 indicates the coordinates of the node on the map space.

[0061] The assignment of the property vector to each node is performed by training the self-organizing map 30. The training of the self-organizing map 30 can be performed by inputting the n-dimensional training data used for training into the self-organizing map 30. Here, existing methods can be used as the specific method for training the self-organizing map using the training data.

[0062] For example, the generation unit 2060 initializes the self-organizing map 30 in an arbitrary manner. As an initialization method, for example, a method of initializing the physical property vectors of each node to random values can be adopted. The generation unit 2060 obtains a plurality of physical property vectors by obtaining the physical property vectors from each of the plurality of object property information. The generation unit 2060 generates the self-organizing map 30 by performing training of the self-organizing map 30 using each of these plurality of physical property vectors as training data. As a result, the physical property vectors corresponding to each node of the self-organizing map 30 become n-dimensional data indicating values for each of the physical property amounts of n types of physical properties.

[0063] <Assignment of the material specifications information 10: S110> The assignment unit 2080 assigns the material specifications information 10 corresponding to the object property information to any one node of the self-organizing map 30 for each object property information (S110). Specifically, the assignment unit 2080 performs the following processing for each object property information. First, the assignment unit 2080 identifies a node having the physical property vector most similar to the physical property vector obtained from the object property information from among the nodes of the self-organizing map 30. Then, the assignment unit 2080 assigns the material specifications information 10 corresponding to the object property information to the identified node.

[0064] The degree of similarity between physical property vectors can be determined based on, for example, the distance between physical property vectors. Thus, for example, the assignment unit 2080 calculates the distance between the physical property vector obtained from the object property information and the physical property vectors of each node of the self-organizing map 30. Then, the node with the smallest calculated distance is identified as the node having the physical property vector closest to the physical property vector obtained from the object property information.

[0065] FIG. 8 is a diagram illustrating the configuration of the self-organizing map 30 to which the material specifications information 10 is assigned. The table 300 in FIG. 8 is different from the table 300 in FIG. 7 in that it has a column of material identification information 306. The record indicating the node to which the material specifications information 10 is assigned shows the material specifications information indicated by the material specifications information 10 in the material identification information 306. On the other hand, in the record indicating the node to which the material specifications information 10 is not assigned, the material identification information 306 is blank.

[0066] <Output of Results> The map generation device 2000 outputs information (hereinafter referred to as output information) representing the self-organizing map 30 to which the material specifications information 10 is assigned to the nodes in an arbitrary manner. Hereinafter, the functional component of the map generation device 2000 that generates and outputs the output information is referred to as an output unit.

[0067] For example, the output unit stores the output information in an arbitrary storage unit. In addition, for example, the output unit causes the display device to display the output information by outputting the output information to the display device. In addition, for example, the output unit transmits the output information to an arbitrary other device.

[0068] <Example of Output Information> For example, the output information includes an image (hereinafter referred to as a map image) that visually represents the self-organizing map 30. The map image is an image representing the correspondence between the distribution of material specifications and the distribution of physical properties.

[0069] FIG. 9 is a diagram illustrating the map image. In FIG. 9, the map image 40 visually represents the map space of the self-organizing map 30. A material specification display 42 representing part or all of the material specifications information 10 is superimposed on the node to which the material specifications information 10 is assigned.

[0070] The nodes of the map image 40 are divided into clusters based on the physical property vectors. The thick frames of the map image 40 represent the boundaries of the clusters. In order to divide the nodes into clusters, the map generation device 2000 performs clustering on the physical property vectors corresponding to each node of the self-organizing map 30. By dividing the physical property vectors into clusters in this way, the nodes corresponding to the physical property vectors can also be divided into clusters. Note that the method of clustering the physical property vectors is as described above.

[0071] Each node of the map image 40 may be colored based on the physical property vector. Here, various existing methods can be used as the method of performing coloring according to the data associated with each node of the self-organizing map.

[0072] As described above, the present invention has been described with reference to the embodiments. However, the present invention is not limited to the above embodiments. Various changes 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.

[0073] In the above example, when the program is loaded into a computer, it includes a set of instructions (or software code) for causing the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted on a transient computer-readable medium or a communication medium. By way of example and not limitation, the transient computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0074] Some or all of the above embodiments may be described as follows, but are not limited thereto. (Appendix 1) An acquisition means for acquiring a plurality of material parameter information indicating material parameters, and for each of the material parameter information, acquiring property information indicating the amount of physical properties for each of a plurality of physical properties of a product that can be generated with the material parameters indicated by the material parameter information; A clustering execution means for clustering the plurality of property information; From each of the plurality of clusters generated by the clustering, extracting some of the property information among the plurality of property information included in the cluster, and using the extracted property information, generating a self-organizing map in which a property vector indicating a value related to the amount of each of the plurality of physical properties of the product is assigned to each node on the map space; An assignment means for assigning the material parameter information corresponding to the extracted property information to any one of the nodes, a map generation device having the assignment means. (Supplementary Note 2) The clustering execution means is the map generation device according to Supplementary Note 1, which clusters the physical property information by clustering the physical property vectors obtained from each of the plurality of pieces of physical property information. (Supplementary Note 3) The clustering execution means is the map generation device according to Supplementary Note 2, which performs dimensionality reduction on the physical property vectors obtained from each piece of physical property information, and clusters the physical property vectors after the dimensionality reduction is performed. (Supplementary Note 4) The allocation means is the map generation device according to any one of Supplementary Notes 1 to 3, which specifies, for each of the extracted pieces of physical property information, the node to which the physical property vector similar to the physical property vector obtained from the physical property information is associated, and allocates the material specifications information corresponding to the physical property information to the specified node. (Supplementary Note 5) The physical property information corresponding to the material specifications information indicates information regarding the physical properties of the product that can be generated by using, as the material for the second step after the first step, the product that can be generated in the first step by using the material specifications shown in the material specifications information. The map generation device according to any one of Supplementary Notes 1 to 3. (Supplementary Note 6) The map generation device according to any one of Supplementary Notes 1 to 3, further comprising output means for outputting an image representing each node of the self-organizing map and information regarding the material specifications indicated by the material specifications information associated with the node. (Supplementary Note 7) An acquisition step of acquiring a plurality of pieces of material specifications information indicating material specifications, and further acquiring, for each piece of material specifications information, physical property information indicating the amount of physical properties for each of a plurality of physical properties of the product that can be generated by the material specifications shown in the material specifications information; A clustering execution step of clustering the plurality of pieces of physical property information; A generation step of extracting a part of the physical property information from each of the plurality of clusters generated by the clustering, and using the extracted physical property information to generate a self-organizing map in which a physical property vector indicating a value related to the physical property amount of each of the plurality of physical properties of the product is assigned to each node on the map space; An assignment step of assigning the material specification information corresponding to the extracted physical property information to any one of the nodes, a map generation method executed by a computer. (Appendix 8) The map generation method according to Appendix 7, wherein in the clustering execution step, the physical property information is clustered by clustering the physical property vectors obtained from each of the plurality of physical property information. (Appendix 9) The map generation method according to Appendix 8, wherein in the clustering execution step, dimensionality reduction is performed on the physical property vectors obtained from each of the physical property information, and the physical property vectors after the dimensionality reduction are clustered. (Appendix 10) In the assignment step, for each of the extracted physical property information, a node associated with a physical property vector similar to the physical property vector obtained from the physical property information is specified, and the material specification information corresponding to the physical property information is assigned to the specified node. The map generation method according to any one of Appendices 7 to 9. (Appendix 11) The physical property information corresponding to the material specification information indicates information related to the physical properties of a product that can be generated by using, as a material in a second step subsequent to the first step, a product that can be generated in a first step by using the material specifications shown in the material specification information. The map generation method according to any one of Appendices 7 to 9. (Appendix 12) An output unit that outputs an image representing each node of the self-organizing map and information related to the material specifications indicated by the material specification information associated with the node. The map generation method according to any one of Appendices 7 to 9. (Appendix 13) An acquisition step of acquiring a plurality of material specification information indicating material specifications, and for each of the material specification information, acquiring property information indicating the amount of properties for each of a plurality of physical properties of a product that can be generated with the material specifications indicated by the material specification information; A clustering execution step of clustering a plurality of the property information; From each of the plurality of clusters generated by the clustering, extracting a part of the property information among the plurality of property information included in the cluster, and using the extracted property information, generating a self-organizing map in which a property vector indicating a value related to the amount of each of a plurality of physical properties of the product is assigned to each node on the map space; An assignment step of assigning the material specification information corresponding to the extracted property information to any one of the nodes, a non-transitory computer-readable medium storing a program for causing a computer to execute. (Appendix 14) The computer-readable medium according to Appendix 13, wherein in the clustering execution step, the property information is clustered by clustering the property vectors obtained from each of the plurality of property information. (Appendix 15) The computer-readable medium according to Appendix 14, wherein in the clustering execution step, dimensionality reduction is performed on the property vectors obtained from each of the property information, and the property vectors after the dimensionality reduction are clustered. (Appendix 16) In the assignment step, for each of the extracted property information, identifying the node to which a property vector similar to the property vector obtained from the property information is associated, and assigning the material specification information corresponding to the property information to the identified node, the computer-readable medium according to any one of Appendices 13 to 15. (Appendix 17) The physical property information corresponding to the material specification information indicates information regarding the physical properties of a product that can be generated by using, as a material for a second process subsequent to the first process, a product that can be generated in the first process by using the material specifications indicated in the material specification information. A computer-readable medium according to any one of Appendices 13 to 15. (Appendix 18) A computer-readable medium according to any one of Appendices 13 to 15, having an output unit that outputs an image representing each of the nodes of the self-organizing map and information regarding the material specifications indicated by the material specification information associated with the nodes.

Explanation of Signs

[0075] 10 Material specification information 20 Physical property information 30 Self-organizing map 40 Map image 42 Material specification display 60 Material 70 Product 100 Table 102 Material identification information 104 Material specifications 200 Table 202 Product identification information 204 Physical properties 300 Table 302 Node 304 Physical property vector 306 Material identification information 1000 Computer 1020 Bus 1040 Processor 1060 Memory 1080 Storage device 1100 Input / output interface 1120 Network interface 2000 Map generation device 2020 Acquisition unit 2040 Clustering execution unit 2060 Generation unit 2080 Allocation unit

Claims

1. An acquisition means for acquiring a plurality of material parameter information indicating material parameters, and for each of the material parameter information, acquiring property information indicating the amount of each of a plurality of physical properties of a product that can be generated using the material parameters indicated by the material parameter information; A clustering execution means for clustering the plurality of property information; A generation means for extracting a part of the property information from among the plurality of property information included in each cluster generated by the clustering, and generating a self-organizing map in which a property vector indicating a value related to the amount of each of a plurality of physical properties of the product is assigned to each node on a map space using the extracted property information; An assignment means for assigning the material parameter information corresponding to the extracted property information to any one of the nodes, the map generation device having the assignment means.

2. The clustering execution means clusters the property information by clustering the property vectors obtained from each of the plurality of property information. The map generation device according to claim 1.

3. The clustering execution means performs dimensionality reduction on the property vector obtained from each property information, and clusters the property vector after the dimensionality reduction. The map generation device according to claim 2.

4. The assignment means identifies, for each of the extracted property information, the node to which a property vector similar to the property vector obtained from the property information is associated, and assigns the material parameter information corresponding to the property information to the identified node. The map generation device according to any one of claims 1 to 3.

5. The property information corresponding to the material parameter information indicates information regarding the physical properties of a product that can be generated by using, as a material in a second step subsequent to the first step, a product that can be generated in a first step using the material parameters indicated by the material parameter information. The map generation device according to any one of claims 1 to 3.

6. The map generation device according to any one of claims 1 to 3, further comprising an output means for outputting an image representing each node of the self-organizing map and information regarding the material parameters indicated by the material parameter information associated with the node.

7. An acquisition step of acquiring a plurality of material specification information indicating material specifications, and for each of the material specification information, acquiring property information indicating the amount of properties for each of a plurality of physical properties of a product that can be produced with the material specifications indicated by the material specification information; A clustering execution step of clustering the plurality of property information; A generation step of extracting a part of the property information among the plurality of property information included in each of the plurality of clusters generated by the clustering, and using the extracted property information to generate a self-organizing map in which a property vector indicating a value related to the amount of each of the plurality of physical properties of the product is assigned to each node on the map space; An assignment step of assigning the material specification information corresponding to the extracted property information to any one of the nodes, a map generation method executed by a computer.

8. The map generation method according to claim 7, wherein in the clustering execution step, the property information is clustered by clustering the property vectors obtained from each of the plurality of property information.

9. An acquisition step of acquiring a plurality of material specification information indicating material specifications, and for each of the material specification information, acquiring property information indicating the amount of properties for each of a plurality of physical properties of a product that can be produced with the material specifications indicated by the material specification information; A clustering execution step of clustering the plurality of property information; A generation step of extracting a part of the property information among the plurality of property information included in each of the plurality of clusters generated by the clustering, and using the extracted property information to generate a self-organizing map in which a property vector indicating a value related to the amount of each of the plurality of physical properties of the product is assigned to each node on the map space; A program for causing a computer to execute an assignment step of assigning the material specification information corresponding to the extracted property information to any one of the nodes.

10. The program according to claim 9, wherein in the clustering execution step, the property information is clustered by clustering the property vectors obtained from each of the plurality of property information.

Images