公开(公告)号：EP4310718A1

公开(公告)日：2024-01-24

申请号：EP22770967.2

申请日：2022-02-14

申请人： NEC Corporation ,  Tohoku University

发明人： KUWAMORI Naoki ,  MUSA Akihiro ,  TAKIGAWA Yohei ,  KAZAMA Yuka ,  SATOU Yoshihiko ,  KOBAYASHI Hiroaki ,  KIKUGAWA Gota ,  OKABE Tomonaga ,  KOMATSU Kazuhiko

IPC分类号： G06F30/27 ,  G06F30/12

摘要： A singular material detection apparatus (2000) acquires, for each of a plurality of materials (60), material specification information (10) representing material specifications of the material (60) and physical property information (20) indicating physical properties of a product (70) that can be generated by using the material (60). The singular material detection apparatus (2000) generates a self-organizing map (30) by using the physical property information (20). The singular material detection apparatus (2000) assigns each of pieces of material specification information (10) to one of nodes based on the physical property information (20) corresponding to that piece of the material specification information (10). Then, the singular material detection apparatus (2000) detects, from among the nodes to which the pieces of material specification information (10) are assigned, a singular node located at a singular position in a map space.

公开(公告)号：EP4310715A1

公开(公告)日：2024-01-24

申请号：EP22770968.0

申请日：2022-02-14

申请人： NEC Corporation ,  Tohoku University

发明人： KUWAMORI Naoki ,  MUSA Akihiro ,  TAKIGAWA Yohei ,  KAZAMA Yuka ,  SATOU Yoshihiko ,  KOBAYASHI Hiroaki ,  KIKUGAWA Gota ,  OKABE Tomonaga ,  KOMATSU Kazuhiko

IPC分类号： G06F30/12 ,  G06F30/27

摘要： A physical property map image generation apparatus (2000) acquires, for each of a plurality of patterns of a material (60), physical property information (20) indicating a physical property quantity for each of a plurality of physical properties of a product (70). The physical property map image generation apparatus (2000) generates, by using the physical property information (20), a self-organizing map (30). A position in a map space and a physical property vector indicating a value related to a physical property quantity for each of a plurality of types of physical properties of the product (70) are assigned to each of nodes on the self-organizing map (30). The physical property map image generation apparatus (2000) generates a physical property map image (40) from the self-organizing map (30). On the physical property map image 40, each of the nodes arranged in the map space is represented by a color assigned to that node. For each of the nodes, each of two or three base color components of a color assigned to the node is determined based on a value that a physical property vector assigned to that node indicates for a physical property corresponding to that base color.

公开(公告)号：EP4310714A1

公开(公告)日：2024-01-24

申请号：EP22770966.4

申请日：2022-02-14

申请人： NEC Corporation ,  Tohoku University

发明人： KUWAMORI Naoki ,  MUSA Akihiro ,  TAKIGAWA Yohei ,  KAZAMA Yuka ,  SATOU Yoshihiko ,  KOBAYASHI Hiroaki ,  KIKUGAWA Gota ,  OKABE Tomonaga ,  KOMATSU Kazuhiko

IPC分类号： G06F30/10 ,  G06F30/27

摘要： A map image generation apparatus (2000) acquires material specification information (10) representing a material specification of a material (60) and physical property information (20) representing a physical property of a product (70). The map image generation apparatus (2000) generates a self-organizing map (30) by using the physical property information (20). A position in a map space, and a physical property vector indicating, for each of a plurality of types of physical properties of the product (70), a value related to a physical property quantity of the physical property are assigned to each of nodes on the self-organizing map (30). The map image generation apparatus (2000) assigns, by using the material specification information (10), a specification vector indicating a value related to the material specification to each of the nodes on the self-organizing map (30). The map image generation apparatus (2000) generates a map image (40) based on an assignment of the specification vectors to the respective nodes. On the map image (40), the nodes are clustered or colored based on the specification vectors.