EP4775075A1

EP4775075A1 - Footwear component design device and footwear component design method

Info

Publication number: EP4775075A1
Application number: EP24874422.9A
Authority: EP
Inventors: Genki HATANO; Masanori Sakaguchi; Shingo Takashima; Yuta Kawai
Original assignee: Asics Corp
Current assignee: Asics Corp
Priority date: 2023-10-03
Filing date: 2024-09-06
Publication date: 2026-07-15
Also published as: CN121941430A; JP2025062881A; WO2025074810A1

Abstract

In a footwear component design device 250, a measurement data acquirer 212 acquires measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject. A model determining unit 222 determines, among multiple three-dimensional homologous models 104, a three-dimensional homologous model 104 similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the multiple three-dimensional homologous models. A basic design determining unit 232 determines basic design data corresponding to the three-dimensional homologous model 104 determined, among multiple basic design data. A design processing unit 234 generates footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.

Description

TECHNICAL FIELD

The present disclosure relates to a footwear component design device and a footwear component design method. In particular, the present disclosure relates to a design technology for sock liners.

BACKGROUND ART

It is preferable to prepare many types of shoe and sock liner size variations for various foot shapes and sizes. However, since increasing the size variations entails an increase in manufacturing costs and the risk of holding a large stock, many shoe manufacturers mainly prepare size variations that are in high demand.
There is a known technology of selecting a type of shoe that fits a foot shape, based on three-dimensional data obtained by measuring the foot shape three-dimensionally (see Patent Literature 1, for example). In Patent Literature 1, from the three-dimensional foot shape data, feature data of a two-dimensional shape is generated for each of the toe portion, central portion, and heel portion. Similarly, feature data for each portion is also generated for lasts. The feature data of a large number of lasts are collected and clustered, and each cluster is stored with a code assigned thereto. The relationship between the feature data of a foot shape and the feature data of a last that fits the foot shape is learned with a neural network, and a rule is defined such that the feature data of a last is obtained from the feature data of a foot shape.
Meanwhile, in recent years, products that can be customized and personalized by consumers have been increasing in line with diversifying preferences (see Patent Literatures 2-4, for example). Also, there is a known method for manufacturing products with greater design flexibility using additive manufacturing, also known as 3D printing (see Patent Literatures 5-7, for example).

RELATED-ART LITERATURE

PATENT LITERATURE

Patent Literature 1: Japanese Unexamined Patent Application Publication No. 2000-90272
Patent Literature 2: Japanese Unexamined Patent Application Publication No. 2022-60213
Patent Literature 3: Japanese Unexamined Patent Application Publication No. 2023-71642
Patent Literature 4: Japanese Translation of PCT International Application Publication No. 2023-523141
Patent Literature 5: Japanese Translation of PCT International Application Publication No. 2018-501865
Patent Literature 6: Japanese Translation of PCT International Application Publication No. 2017-522917
Patent Literature 7: Japanese Unexamined Patent Application Publication No. 2020-163154

SUMMARY OF INVENTION

TECHNICAL PROBLEM

Even if the flexibility in product design is increased by additive manufacturing, some designs may result in shapes that are difficult to manufacture in the first place, or shapes that are not normal for products. To avoid such designs, it is important to confirm the design validity in advance, but there is a risk that the design flexibility may be restricted to ensure the design validity. There is also a risk that adaptability for customization and personalization may be compromised.
The present disclosure has been made in view of such a situation, and a purpose thereof is to provide a technology for achieving both high design flexibility and design validity for footwear components.

SOLUTION TO PROBLEM

To solve the problem above, a footwear component design device according to one embodiment of the present disclosure includes: a model storage unit that stores, in advance, a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot; a design storage unit that stores a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models; a measurement data acquirer that acquires measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject; a model determining unit that determines, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models; a basic design determining unit that determines basic design data corresponding to the three-dimensional homologous model determined, among the plurality of basic design data; and a design processing unit that generates footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.
Another embodiment of the present disclosure is a footwear component design method. This method includes: reading a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot; acquiring measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject; determining, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models; determining basic design data corresponding to the three-dimensional homologous model determined, among a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models; and generating footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.
Optional combinations of the aforementioned constituting elements, and methods, devices, programs, transitory or non-transitory recording media storing programs, systems, and the like among which constituting elements or expressions in the present disclosure are mutually replaced are also effective as embodiments of the present disclosure.

ADVANTAGEOUS EFFECTS OF INVENTION

The present disclosure can achieve both high design flexibility and design validity for footwear components.

BRIEF DESCRIPTION OF DRAWINGS

[Fig. 1] Fig. 1 is a diagram that illustrates a basic configuration of a footwear component design system.
[Fig. 2] Fig. 2 is a functional block diagram that shows each configuration in a footwear component design device.
[Fig. 3] Fig. 3 is a diagram that shows an example of a three-dimensional homologous model.
[Fig. 4] Fig. 4 is an upper perspective view that shows an external view of a sock liner manufactured by three-dimensional additive manufacturing.
[Fig. 5] Fig. 5 is a lower perspective view that shows an external view of a sock liner manufactured by three-dimensional additive manufacturing.
[Fig. 6] Fig. 6 is a diagram that shows a sock liner with no three-dimensional decoration added.
[Fig. 7] Fig. 7 is a diagram that shows a sock liner with a three-dimensional decoration of text added to a side surface.
[Fig. 8] Fig. 8 is a diagram that shows a sock liner with three-dimensional decorations of marks added to a side surface and a lower surface.
[Fig. 9] Fig. 9 is a diagram that schematically shows a slice section image in sock liner design data.
[Fig. 10] Fig. 10 is a functional block diagram that shows each configuration in a shape analysis device.
[Fig. 11] Fig. 11 is a diagram that shows the relationships between the distributions of foot lengths and ball girths of women and men and the JIS in Japan.
[Fig. 12] Fig. 12 is a diagram that shows a difference between a general cluster analysis method and a new cluster analysis method.
[Fig. 13] Fig. 13 is a diagram that shows a method in which different cluster analysis methods for an upper layer and a lower layer are combined.
[Fig. 14] Fig. 14 is a diagram that shows the Euclidean distance and the cosine similarity between points.
[Fig. 15] Fig. 15 is a diagram that shows the relationships between corresponding points in two foot shape models.
[Fig. 16] Fig. 16 is a diagram that shows comparisons between foot shape models using the Euclidean distance and the cosine similarity.
[Fig. 17] Fig. 17 is a diagram that shows differences in classification result between cluster analysis based on the cosine similarity and cluster analysis based on the Euclidean distance.
[Fig. 18] Fig. 18 is a diagram that shows a classification result of the cluster analysis based on the cosine similarity.
[Fig. 19] Fig. 19 is a diagram that shows regression lines of the foot length and ball girth of top three clusters and also shows results of principal component analysis of the top three clusters.
[Fig. 20] Fig. 20 is a diagram that shows results of principal component analysis for a cluster.

DESCRIPTION OF EMBODIMENTS

In the following, the present disclosure will be described based on a preferred embodiment with reference to each drawing. In the embodiment and modifications, like reference characters denote like or corresponding constituting elements, and the repetitive description will be omitted as appropriate.
In the present embodiment, footwear or a footwear component customized for each wearer or intending purchaser is provided. For example, not only is footwear or a footwear component most suitable for the wearer's foot size and foot shape designed, but also the preferences of an intending purchaser are further reflected in the design and decoration. This enables designing of unique footwear or footwear components in which the individual differences and preferences of each wearer or intending purchaser are reflected.
Besides shoes that cover the entire foot, such as sports shoes, and shoes that do not cover the entire foot, such as sandals, "footwear" as used herein includes socks, sock shoes, which are shoes integrated with socks, and tights. Also, the "footwear" includes not only footwear of which the entirety can be customized, but also footwear of which a footwear component, as part of the footwear, can be customized. A footwear component in the present embodiment is a sock liner (also generally referred to as an "insole") that is inserted inside footwear and placed over an inner sole. In the following, the present embodiment describes an example of designing a sock liner as a footwear component. However, as a modification, the technology may be applied to an example of designing a footwear component other than a sock liner, such as a sole and an upper, or an example of designing the entirety of footwear such as a sandal.
The present embodiment employs three-dimensional additive manufacturing (also referred to as "additive manufacturing", "3D printing", or the like), which is different from the conventional manufacturing method of mass-producing and selling footwear or a footwear component of the same standard. A sock liner as the footwear component in the present embodiment is formed by three-dimensional lattice structures.
When designing a sock liner customized for each intending purchaser, the method of designing from scratch for each order requires a large amount of time. In addition, in the designing performed for each order, it is difficult to check in advance whether the manufacturing process is valid in actual manufacturing or whether a shape in the design is manufacturable. In this way, in the customization of footwear, it is necessary to ensure both high design flexibility and design validity.
Therefore, in the present embodiment, a large number of basic design data of basic design to which customization is assumed to be added are prepared. Then, the design validity within the customizable range of these basic design data is confirmed in advance to achieve both design flexibility and design validity.
A large number of basic design data are designed as follows. That is, three-dimensional shapes of feet of a large number of measurement subjects are measured and accumulated as foot shape data, which are then classified in advance into multiple clusters using a cluster analysis method described later. Also, by designing lasts or sock liners based on the classified multiple clusters, shape variations of footwear products can be provided based on standards different from conventional standards, and footwear or footwear components that fit many people's feet can be provided. Further, demand for each shape in the shape variations is forecasted based on a foot shape distribution.
A three-dimensional shape of a foot of an intending purchaser of a sock liner, regarded as a measurement subject, is measured to acquire foot shape measurement data. The foot shape measurement data of the measurement subject are three-dimensional point cloud data indicating anatomical features corresponding to a three-dimensional homologous model of the foot shape including at least the sole and a foot side surface of the measurement subject. The three-dimensional homologous model is a model that specifies a coordinate group of anatomical features of an average foot in three-dimensional space, in which a predetermined number, e.g., 295, of contour points are specified.
The similarity between the foot shape measurement data of the measurement subject and a large number of foot shape models classified by cluster analysis is evaluated, and design data corresponding to a three-dimensional homologous model similar to the foot shape of the subject is used as basic design data. To the basic design data, an individual transformation specified based on the subject's wishes is added to generate footwear component design data. Individual transformations include a transformation according to the intending purchaser's preference regarding the arch height, and transformations of adding text that is input freely as the intending purchaser likes and adding patterns or other design decorations. By three-dimensional additive manufacturing based on the footwear component design data thus generated, a sock liner with three-dimensional lattice structures is manufactured.
In the following, a footwear component design system 200 operated by a footwear manufacturer will be described first, and a shape analysis system for classifying a large number of foot shape models or basic design data by cluster analysis will be described.
Fig. 1 illustrates a basic configuration of the footwear component design system 200. The footwear component design system 200 includes a measurement device 15, such as a three-dimensional foot shape measuring device 18 and an information terminal 16, and a footwear component design device 250. When the three-dimensional foot shape measuring device 18 is used as the measurement device 15, a foot shape of a measurement subject 10 is scanned using the three-dimensional foot shape measuring device 18. When the information terminal 16 is used as the measurement device 15, an image of a foot of the measurement subject 10 is captured using a camera function of the information terminal 16.
Opportunities to acquire the foot shape measurement data include the case where persons considering the purchase of sock liners are selected as measurement subjects 10, and the case where a large number of subjects are selected as measurement subjects 10 for the purpose of acquiring foot shape data. The persons considering the purchase of sock liners include, for example, persons who are considering the purchase of sock liners at footwear stores, and persons who wish to purchase sock liners through online sales. A large number of subjects are subjects when the purpose is to acquire foot shape measurement data of various sizes or shapes regardless of gender or age, at the stage of generating the basic design data of footwear or a footwear component.
When the three-dimensional foot shape measuring device 18 is used as the measurement device 15, the three-dimensional foot shape measuring device 18 acquires three-dimensional point cloud data related to a foot shape of a measurement subject 10 by laser measurement. The "foot shape" as used herein is a three-dimensional model that virtually reproduces a three-dimensional shape of a foot of the measurement subject 10. The three-dimensional foot shape measuring device 18 transmits the three-dimensional point cloud data of the foot shape to the footwear component design device 250. The "footwear component design device" in the claims may mean the entire footwear component design system 200 or may mean the footwear component design device 250. Also, in the present embodiment, since many of the characteristic functions included in the "footwear component design device" in the claims are implemented such as to be included in the footwear component design device 250, the footwear component design device 250 substantially corresponds to the "footwear component design device".
When the information terminal 16 is used as the measurement device 15, the measurement subject 10 captures and acquires an image of his or her own foot using a camera built into the information terminal 16, such as his or her cellular phone terminal. For example, in the method of capturing an image of the entire foot from directly above the foot, it is difficult to capture the contour shape of the entire foot in a single image because, even though the heel is to be fully captured, the ankle will appear in the image. Therefore, the measurement subject 10 captures multiple images from multiple angles such as to acquire images at least capturing the contours of the toe and the heel and the contours of the left and right sides from a forefoot portion to a midfoot portion. The measurement subject 10 may place his or her foot on a dedicated measurement mat 12 and capture images of his or her own foot using the camera function of the information terminal 16 and a foot shape acquisition application. The information terminal 16 transmits the multiple images capturing the foot to the footwear component design device 250.
When the information terminal 16 has a three-dimensional scanner function using a technology such as LiDAR (Light Detection And Ranging), scanning may be performed around the foot to acquire the three-dimensional point cloud data of the foot shape. Even if the information terminal 16 does not have the three-dimensional scanner function with LiDAR or the like, the three-dimensional point cloud data of the foot shape may be acquired through image synthesis processing such as photogrammetry. In these cases, the information terminal 16 transmits the three-dimensional point cloud data of the foot shape to the footwear component design device 250.
The footwear component design device 250 is a server computer connected to multiple three-dimensional foot shape measuring devices 18 and information terminals 16 via a network line, such as the Internet or a LAN (Local Area Network), and a communication means, such as wireless communication. The footwear component design device 250 may be constituted by a single server computer or may be constituted by a combination of multiple server computers.
Fig. 2 is a functional block diagram that shows each configuration in the footwear component design device 250. The footwear component design device 250 may be implemented by various hardware configurations and software configurations. With regard to the footwear component design device 250, Fig. 2 shows functional blocks implemented by coordination of various hardware configurations and software configurations. Therefore, it will be understood by those skilled in the art that these functional blocks may be implemented in a variety of forms by hardware only, software only, or a combination thereof. The footwear component design device 250 is constituted by a combination of hardware, e.g., a microprocessor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), memory, display, and communication module. The footwear component design device 250 may be a server computer constructed and managed by a footwear manufacturer or a footwear store.
On the footwear component design device 250, a program having the following functions runs. The footwear component design device 250 includes, as its functions, a communication unit 210, a measurement data acquirer 212, a model conversion unit 214, an individual information acquirer 216, a footwear information acquirer 218, a model storage unit 220, a model determining unit 222, a design storage unit 230, a basic design determining unit 232, a design processing unit 234, and an output unit 236. The communication unit 210 of the footwear component design device 250 is connected to a three-dimensional foot shape measuring device 18 and an information terminal 16 via a network.
The measurement data acquirer 212 acquires three-dimensional point cloud data of a foot shape of a measurement subject 10 from the three-dimensional foot shape measuring device 18 or acquires a captured image of a foot of a measurement subject 10 from the information terminal 16, via the communication unit 210.
When acquiring the three-dimensional point cloud data from the three-dimensional foot shape measuring device 18, the measurement data acquirer 212 converts the three-dimensional point cloud data to three-dimensional point cloud data indicating anatomical features corresponding to a three-dimensional homologous model to acquire measurement data of a three-dimensional coordinate group. The conversion of the three-dimensional point cloud data is performed by the model conversion unit 214.
When acquiring multiple foot images of the measurement subject 10 from the information terminal 16, the measurement data acquirer 212 generates three-dimensional point cloud data indicating anatomical features corresponding to a three-dimensional homologous model based on the multiple foot images to acquire measurement data of a three-dimensional coordinate group. The generation of three-dimensional point cloud data based on the multiple foot images and conversion to three-dimensional point cloud data indicating anatomical features corresponding to a three-dimensional homologous model are performed by the model conversion unit 214.
Thus, even when the measurement data acquirer 212 acquires measurement data using various types of foot shape measurement devices as the measurement device 15, the measurement data is converted into three-dimensional point cloud data corresponding to a three-dimensional homologous model by the model conversion unit 214. This can generalize the measurement data into a data format that can be easily used. Meanwhile, in a modification, the measurement data to be acquired by the measurement data acquirer 212 may be converted into three-dimensional point cloud data corresponding to a foot shape three-dimensional homologous model in advance by the three-dimensional foot shape measuring device 18 or the information terminal 16.
The model storage unit 220 stores, in advance, multiple three-dimensional models for multiple foot shapes with a three-dimensional coordinate group indicating anatomical features of a foot. A three-dimensional model of a foot shape stored in the model storage unit 220 is, for example, a three-dimensional homologous model in which a coordinate group of points indicating anatomical features of an average foot in three-dimensional space is defined. A foot shape three-dimensional homologous model is a model with which multiple foot shapes having various sizes and shapes are each represented by a polyhedron anatomically defined by the same topological structure with the same number of points. The points representing anatomical features of an average foot are obtained in advance based on foot samples obtained from a large number of subjects. The three-dimensional models in modifications may be various other models created in accordance with the same anatomical criteria, such as a three-dimensional shape model in a spherical coordinate system, and a model obtained by modifying a template foot shape generated by a three-dimensional CAD system, based on anatomical landmarks.
Fig. 3 shows an example of a three-dimensional homologous model. A three-dimensional homologous model 104 of a foot shape is constituted by a point cloud representing anatomical features of a foot. The three-dimensional homologous model 104 does not necessarily faithfully reproduce the foot shape, especially the shape near the toes, of the measurement subject 10 and is intentionally deformed so as to be easily compared with other foot shapes or three-dimensional homologous models. More specifically, the three-dimensional homologous model 104 does not have complete similarity to the actual foot shape or foot contour of the measurement subject 10 and has a shape such that convex hull processing has been performed particularly on the contour of the toes. Also, by detecting multiple characteristic points included in the foot contour of the three-dimensional homologous model 104 and using each point as a reference, the length of each part, such as the foot length, ball girth, instep girth, short heel girth, and heel width, can be measured. Since the methods for measuring the length of each part is known, the description thereof will be omitted.
The description now returns to Fig. 2. The model storage unit 220 stores multiple three-dimensional homologous models 104 classified into multiple clusters in an upper layer by cluster analysis based on cosine similarity. The cluster analysis based on cosine similarity is cluster analysis based on cosine similarity between position vectors from a predetermined reference point to the respective points in the three-dimensional homologous models 104. The model storage unit 220 also stores multiple three-dimensional homologous models 104 further classified into multiple more detailed clusters in a lower layer by cluster analysis different from that in the upper layer. The cluster analysis in the lower layer is cluster analysis based on principal component analysis performed on each cluster in the upper layer, of which results are dimensionally reduced to the second and the subsequent principal components excluding the first principal component.
The model determining unit 222 evaluates the similarity in coordinates between the three-dimensional coordinate group in the measurement data acquired by the measurement data acquirer 212 and the three-dimensional coordinate groups in multiple three-dimensional homologous models 104. Based on the similarity in coordinates, the model determining unit 222 determines, among the multiple three-dimensional homologous models 104 in the model storage unit 220, a three-dimensional homologous model 104 similar to the foot shape of the measurement subject 10. More specifically, the model determining unit 222 first acquires a position vector from a predetermined reference point to each point in the multiple three-dimensional homologous models 104 stored in the model storage unit 220. Subsequently, the model determining unit 222 acquires a position vector from a predetermined reference point to each point in the three-dimensional homologous model in the measurement data. Based on the distance between corresponding points or the similarity between corresponding position vectors in three-dimensional homologous models, a three-dimensional homologous model 104 similar to the foot shape of the measurement subject 10 is determined from among the multiple three-dimensional homologous models 104 in the model storage unit 220.
The distance between points may be the Euclidean distance, and the similarity between position vectors may be the cosine similarity, for example. The model determining unit 222 combines the selection result for a similar three-dimensional homologous model based on the Euclidean distance and the selection result for a similar three-dimensional homologous model based on the cosine similarity and determines therebetween the three-dimensional homologous model that is most similar to the foot shape of the measurement subject 10. It is assumed here that about 6,000 foot shape three-dimensional homologous models are stored in the model storage unit 220. In such a case, even if the model determining unit 222 determines the most similar three-dimensional homologous model by calculating the similarity with all the three-dimensional homologous models, it can be determined in about 10 seconds of calculation, so that a foot shape can be extracted in a very short time. The Euclidean distance and the cosine similarity will be described later.
The model determining unit 222 scales the three-dimensional homologous model thus determined to various sizes based on the foot length of the measurement subject 10 and calculates the similarity between each of the scaled models and the foot shape three-dimensional homologous model of the measurement subject 10. Based on the similarity of each scaled model, the model determining unit 222 determines the scale of the three-dimensional homologous model with the highest similarity.
The footwear information acquirer 218 acquires footwear information indicating the type of a shoe specified by the subject. More specifically, an intending purchaser of a sock liner enters, as footwear information, information such as the product model and size of the shoe into which the sock liner is to be inserted, and the footwear information acquirer 218 acquires the footwear information. The information thus acquired by the footwear information acquirer 218 is transmitted to the basic design determining unit 232. The information such as the product model and size of the shoe is referred to when basic design data is selected, as will be described later.
In a modification, when an intending purchaser of a sock liner does not enter the information such as the product model and size of the shoe, basic design data of standard design may be selected regardless of the product model and size of the shoe. Alternatively, on the premise that the intending purchasers of sock liners do not enter the information such as the product models and sizes of the shoes, basic design data of standard design may be selected regardless of the product model and size of the shoe.
The individual information acquirer 216 acquires individual information that designates an individual transformation specified as a transformation of the basic design of a sock liner based on the intending purchaser's wishes. The "individual transformation" as used herein means a change in function or design for customization based on the intending purchaser's preferences. For example, individual transformations include transformations related to preferences for the height and hardness of the arch support, and transformations related to decorative preferences.
For example, it is assumed here that the arch height rate in the basic design data is a predetermined value in 60-70%. An intending purchaser can select the arch height rate from among "high", "standard", and "low" based on his or her own preference. When the individual information acquirer 216 acquires individual information indicating "high" for the arch height rate, the basic design data is modified so that the arch height rate is a predetermined value in 70-80%. When the individual information acquirer 216 acquires individual information indicating "low" for the arch height rate, the basic design data is modified so that the arch height rate is a predetermined value in 50-60%. The numerical range of the arch height rate is only an example and may be a different numerical range.
An intending purchaser can select the hardness of a sock liner 300 from among "hard", "standard", and "soft" based on his or her own preference. When the individual information acquirer 216 acquires individual information indicating "hard" or "soft" for the hardness, the density of the three-dimensional lattice structures may be partially changed, or the material of the sock liner 300 may be changed. Besides the hardness, the material of the sock liner 300 may be selectable according to preference, and the method for surface treatment, such as embossing, gloss finishing, or matte finishing, may also be selectable according to preference. Furthermore, the type and form of a reinforcing member attached to the sock liner 300 may also be selectable according to preference.
As the transformations related to decorative preferences of an intending purchaser, letters, symbols, marks, and patterns can be specified, and a decoration (hereinafter, referred to as a "three-dimensional decoration") that stereoscopically forms at least one of the letters, symbols, marks, and patterns thus specified may be added to at least one of the side surface, lower surface, and top surface of the sock liner 300. The intending purchaser can enter any text within a predetermined maximum number of characters, and the text thus entered is converted into design data of a three-dimensional decoration and synthesized into the basic design data. The individual information acquirer 216 stores a list of terms as prohibited terms that are considered inappropriate from a legal perspective or in terms of public order and morals. If the text entered by the intending purchaser contains a prohibited term, the conversion into a three-dimensional decoration will be restricted. Meanwhile, discriminatory terms, prohibited terms, inappropriate terms, and terms that evoke such terms are created one after another. In order to automatically eliminate these terms, judgment may be made not only by referring to a glossary stored in advance in the form of a list, but also through a learning model, generative AI (Artificial Intelligence), an API (Application Programming Interface), and the like, which are updated as needed. Besides text, the intending purchaser can also select another element, such as a single letter of the alphabet, a symbol, mark, or pattern, and add it as a three-dimensional decoration. In a modification, as a decoration other than a three-dimensional decoration, the surface color or the type of surface pattern of the sock liner 300 may be selectable according to preference. Also, a drawing hand-drawn by the intending purchaser or a simple drawing created by the intending purchaser may be input as the original drawing of a three-dimensional decoration and added as the three-dimensional decoration. A randomly generated pattern or character string may be set and added as a three-dimensional decoration. Information indicating the date when the design of the sock liner 300 was created, information indicating a location, and a two-dimensional code or barcode indicating such information may be set and added as a three-dimensional decoration. The intending purchaser may specify such details of a decoration by allowing another person to select the details through a predetermined online service. The serial number or individual identification number of the sock liner 300 may be added as a three-dimensional decoration. Also, factors that affect the manufacturability in additive manufacturing may be considered to determine whether or not the three-dimensional decoration can be implemented. Furthermore, the shape of the three-dimensional decoration may be automatically modified so as to be manufacturable.
For a three-dimensional decoration of text, the font type, size, font thickness, underline, character enclosure, height of the three-dimensional shape, and the like may be specified according to preference. Each three-dimensional decoration in the present embodiment is configured in a convex three-dimensional shape; however, in a modification, the three-dimensional decoration may be configured in a concave three-dimensional shape, or the intending purchaser may select whether to configure the three-dimensional decoration in a convex or concave shape based on his or her preference.
The intending purchaser can specify the placement location of a three-dimensional decoration. The placement location of a three-dimensional decoration is at least one of the side surface, top surface, and lower surface around the sock liner 300. Information including the text of a three-dimensional decoration, i.e., the individual information indicating text, a mark, a pattern, and the like specified and the placement location, is transmitted to the design processing unit 234. The three-dimensional decorations and the placement locations thereof will be described later.
The basic design determining unit 232 determines basic design data corresponding to the three-dimensional homologous model 104 determined by the model determining unit 222, among multiple basic design data. When the basic design determining unit 232 also receives the footwear information from the footwear information acquirer 218, the basic design determining unit 232 determines the basic design data based on the three-dimensional homologous model 104 determined by the model determining unit 222 and the footwear information.
The design storage unit 230 stores multiple basic design data as three-dimensional design data used for additive manufacturing of a sock liner corresponding to the foot shape of each of the multiple three-dimensional homologous models 104 stored in the model storage unit 220. The multiple three-dimensional homologous models 104 are classified into multiple clusters, and the basic design data corresponding to these three-dimensional homologous models 104 are also substantially classified into multiple clusters. The multiple basic design data stored in the design storage unit 230 may correspond one-to-one to the multiple three-dimensional homologous models 104 classified into multiple clusters in the model storage unit 220, or the multiple basic design data may correspond many-to-one, one-to-many, or many-to-many to the multiple three-dimensional homologous models 104.
In the case of many-to-one correspondence, variations of basic design data are prepared so that one basic design data corresponds to multiple three-dimensional homologous models 104. For example, depending on the sock liner product model, the number of sock liner variations may desirably be reduced with respect to the number of foot shape variations, and in such a case, many-to-one can be employed. In the case of one-to-many correspondence, variations of basic design data are prepared so that multiple basic design data correspond to one three-dimensional homologous model 104. For example, multiple types of sock liner product models may be prepared for one foot shape. Also, when the shape of the lower surface of a sock liner differs according to the shape of the last of a shoe product model into which the sock liner is inserted, multiple basic design data for shoe product models may be prepared for one foot shape. Also, while one basic design data corresponds to multiple three-dimensional homologous models 104, such basic design data may be prepared for each sock liner product model or each shoe product model.
With regard to each of the multiple basic design data stored in the design storage unit 230, it is confirmed in advance that the design therein is valid, i.e., the manufacture by additive manufacturing is possible for the design. For each basic design data, it is also confirmed in advance that the design therein is valid even if an individual transformation is added thereto within a range that can be specified as individual information.
Based on the basic design data determined by the basic design determining unit 232, the design processing unit 234 generates sock liner design data as footwear component design data corresponding to the foot shape of the measurement subject 10. When the design processing unit 234 receives the individual information from the individual information acquirer 216, the design processing unit 234 generates the sock liner design data as footwear component design data in which an individual transformation is added to the basic design, based on the basic design data and the individual information. For example, upon receiving specified information regarding the arch height rate as the individual information, the design processing unit 234 generates the sock liner design data in which the top surface shape in the basic design data including the arch shape is transformed so that the specified arch height rate is achieved. For example, upon receiving specified information regarding the hardness as the individual information, the design processing unit 234 generates the sock liner design data in which part of the top surface shape in the basic design data is transformed so that the specified hardness is achieved. For example, upon receiving information including text as the individual information, the design processing unit 234 generates the sock liner design data in which a three-dimensional decoration that forms the specified text is added to the basic design, based on the basic design data and the individual information.
The present embodiment describes an example in which the basic design data is individually transformed based on the arch height rate specified by the individual information. In a modification, based on one basic design data, multiple basic design data with different arch height rates may be prepared in advance as design variations, and the design validity of each basic design data may be confirmed in advance.
Thus, both assurance of the design flexibility for a sock liner and assurance of the design validity for the sock liner can be achieved. Also, since sock liner design data based on design other than the basic design data stored in the design storage unit 230 and the designation of a three-dimensional decoration in a range that has not been checked in advance are excluded in advance, designing for which design validity has not been confirmed can be prevented. In particular, this can prevent manufacturing failures and defective products due to unexpected sock liner designing based on extremely non-standard foot shapes.
The output unit 236 transmits the sock liner design data generated by the design processing unit 234 to an additive manufacturing device 260 to allow the additive manufacturing device 260 to perform additive manufacturing of a sock liner 300 based on the sock liner design data. Also, the output unit 236 may display the sock liner design data on a display screen of the footwear component design device 250 or may transmit the sock liner design data to the information terminal 16 via the communication unit 210.
Fig. 4 is an upper perspective view that shows an external view of a sock liner manufactured by three-dimensional additive manufacturing. Fig. 5 is a lower perspective view that shows an external view of the sock liner manufactured by three-dimensional additive manufacturing. In Fig. 4, the left side corresponds to a toe side 308, and the right side corresponds to a heel side 309. In Fig. 5, the right side corresponds to the toe side 308, and the left side corresponds to the heel side 309. The sock liner 300 is manufactured by three-dimensional additive manufacturing of stereolithography. The material of the sock liner 300 is a material that can be formed by three-dimensional additive manufacturing of stereolithography. For example, a resin material or a rubber material suitable for maintaining flexibility, elasticity, and durability is preferable. When the sock liner 300 is made of resin, it can be, for example, a polyolefin resin, ethylene-vinyl acetate copolymer (EVA), a thermoplastic polyamide elastomer (TPA, TPAE), thermoplastic polyurethane (TPU), or a thermoplastic polyester elastomer (TPEE). When the sock liner 300 is made of rubber, it can be, for example, butadiene rubber (BR). As a modification, an upper layer part of the sock liner 300 may be mainly manufactured with resin or the like by additive manufacturing, and a lower layer part may be mass-produced with another lightweight material by injection molding using a mold, for example; then, the upper layer part and the lower layer part may be laminated to configure the sock liner 300.
A base layer part that appears on a lower surface 302 and a side surface 303 of the sock liner 300 is configured in the form of a three-dimensional mesh structure in which a three-dimensional lattice structure as a unit structure is repeatedly arranged. This unit structure is repeatedly arranged in three orthogonal directions of longitudinal, lateral, and vertical directions. The side surface 303 is scarcely provided on the toe side 308 and is provided from a midfoot portion to the heel side 309 in the form of a peripheral wall such that the edge of the lower surface 302 extends slightly diagonally upward to form a mortar-like shape. The side surface 303 has a larger area on a medial side 306 than on a lateral side 307 as a height is required for the arch support. The side surface 303 also has an area on the heel side 309, but it is greatly curved to follow the contour of the heel; accordingly, it is more difficult to add a three-dimensional decoration of text to the heel side 309 compared to the medial side 306 and the lateral side 307.
On a surface layer part that appears on a top surface 301 of the sock liner 300, a large number of holes are provided. For the curved shape on the top surface 301 of the sock liner 300, design corresponding to the foot shape is determined so that the curved shape fits the sole shape of the measurement subject 10. For the curved shape on the lower surface of the sock liner 300, design corresponding to a shoe specified by the measurement subject 10 is determined so that the curved shape fits the inner sole shape and the internal shape of the upper of the shoe into which the sock liner 300 is inserted. For example, design corresponding to a last of a shoe specified by the measurement subject 10 in the footwear information may be determined, design corresponding to the type of the specified shoe may be determined, and design corresponding to the foot length size or the foot width type of the specified shoe may be determined. In a modification, design of a standard shape may be determined for the lower surface shape of the sock liner 300, regardless of whether or not a shoe is specified in the footwear information. Also, according to the type of a shoe specified in the footwear information, a material suitable for the shoe type may be selected as the material of the sock liner 300.
Fig. 6 is a side view of the sock liner 300 with no three-dimensional decoration added. Fig. 7 is a side view of the sock liner 300 with a three-dimensional decoration of text added to the side surface. A text decoration 310 is a decoration that mainly forms text or a character string stereoscopically. Fig. 8 is a perspective view of the lower surface of the sock liner 300 with three-dimensional decorations of marks added to the side surface and the lower surface. Mark decorations 311 and 312 may be, for example, decorations that stereoscopically form marks such as logo marks or symbol marks of a footwear manufacturer.
The placement location of a three-dimensional decoration is at least one of the side surface 303 on the circumference, the top surface 301, and the lower surface 302 of the sock liner 300. However, since the sock liner 300 has a sheet-like shape, locations where three-dimensional decorations can be placed are limited. For example, on the side surface 303 on the circumference of the sock liner 300, since the edge extends, from the midfoot portion to the heel side 309, slightly upward to form a mortar-like shape that is relatively high and thick, the placement area can be secured in part of the side surface 303. More specifically, the medial side 306, the lateral side 307, and the heel side 309 of the side surface 303 can be selected in which the placement area can be secured. On the lower surface 302 of the sock liner 300, a heel part and a center part can be selected. The top surface 301 of the sock liner 300 can also be selected, but since the sole of the wearer is in direct contact therewith, an area that affects push-off may be avoided, or the thickness of the three-dimensional decoration may be limited. Alternatively, in the case of product specification in which fabric is applied to the top surface 301 of the sock liner 300, a decoration may be provided by printing the decoration such as text or a mark on the fabric.
Fig. 9 schematically shows a slice section image in the sock liner design data. A slice section image 320 in the sock liner design data is data of each cross section obtained by horizontally slicing the three-dimensional lattice structures into multiple layers when the sock liner 300 is placed horizontally. For example, when the DLP (Digital Light Processing) method is employed as the stereolithography, a cross-sectional pattern as shown in Fig. 9 is exposed for each layer and stacked. Each cross section is formed as a monochrome binary image as shown in Fig. 9, and irradiation portions 321 represented by white dots are irradiated with ultraviolet light and resin is laminated, and non-irradiation portions 322 represented by black dots are not irradiated with ultraviolet light. In this way, surface irradiation to the irradiation portions 321 is repeated based on the sock liner design data of each layer, thereby producing the sock liner 300 by additive manufacturing.
Thus, since the slice section image 320 is formed as a monochrome binary image, a monochrome binary image of the cross-section of only a three-dimensional decoration portion may be generated and overlayed on a monochrome binary image of the basic design portion, and the monochrome binary images may be combined to generate the slice section image 320 of the entire layer. Alternatively, to the basic design data as a three-dimensional model, partial numerical changes corresponding to the shape of a three-dimensional decoration may be added to generate the sock liner design data as an overall three-dimensional model including the three-dimensional decoration portion, and the slice section image 320 of each layer may be generated thereafter.
In the following, a shape analysis device 50 that classifies multiple three-dimensional homologous models 104 stored in the model storage unit 220 by cluster analysis will be described.
Fig. 10 is a functional block diagram that shows each configuration in the shape analysis device 50. The shape analysis device 50 may be implemented by various hardware configurations and software configurations. With regard to the shape analysis device 50, Fig. 10 shows functional blocks implemented by coordination of various hardware configurations and software configurations. Therefore, it will be understood by those skilled in the art that these functional blocks may be implemented in a variety of forms by hardware only, software only, or a combination thereof. The shape analysis device 50 is constituted by a combination of hardware, such as a microprocessor, memory, display, and communication module. The shape analysis device 50 may be a server computer constructed and managed by a shoe manufacturer. On the shape analysis device 50, a program having the following functions runs. The shape analysis device 50 includes, as its functions, a communication unit 19, a measurement data acquirer 20, a model generator 21, a model storage unit 22, an output unit 26, an analysis processing unit 30, and a statistical processing unit 35. The communication unit 19 of the shape analysis device 50 is connected to the three-dimensional foot shape measuring device 18 via a network. A measurement subject 10 scans his or her foot shape using the three-dimensional foot shape measuring device 18. For opportunities to acquire foot shape data, for example, a large number of subjects may be selected as measurement subjects 10 at the shoe design stage, for the purpose of acquiring foot shape data of various sizes or shapes regardless of gender or age.
The model storage unit 22 stores, in advance, multiple three-dimensional models for multiple body shapes with a three-dimensional coordinate group indicating anatomical features of at least part of a body. The body shape as used herein mainly means a foot shape. The three-dimensional model of a foot shape stored in the model storage unit 22 is, for example, a three-dimensional homologous model in which a coordinate group of points indicating anatomical features of an average foot in three-dimensional space is defined. A foot shape three-dimensional homologous model is a model with which multiple foot shapes having various sizes and shapes are each represented by a polyhedron anatomically defined by the same topological structure with the same number of points. The points representing anatomical features of an average foot are obtained in advance based on foot samples obtained from a large number of subjects. The three-dimensional models in modifications may be various other models created in accordance with the same anatomical criteria, such as a three-dimensional shape model in a spherical coordinate system, and a model obtained by modifying a template foot shape generated by a three-dimensional CAD system, based on anatomical landmarks.
The measurement data acquirer 20 acquires, as measurement data, a three-dimensional coordinate group indicating anatomical features corresponding to a three-dimensional homologous model of the foot shape of the measurement subject 10, from the three-dimensional foot shape measuring device 18 via the communication unit 19. The measurement data acquirer 20 may acquire measurement data from an external terminal 17 other than the three-dimensional foot shape measuring device 18 via the communication unit 19. The model generator 21 generates a foot shape three-dimensional homologous model based on the measurement data acquired by the measurement data acquirer 20 and stores the model as a new three-dimensional homologous model in the model storage unit 22. In this case, even when measurement data is acquired using various types of foot shape measurement devices as the three-dimensional foot shape measuring device 18 or external terminal 17, the measurement data is converted into a three-dimensional homologous model by the model generator 21. This can generalize the measurement data into a data format that can be easily used. Meanwhile, in a modification, the measurement data to be acquired by the measurement data acquirer 20 may be made into a foot shape three-dimensional homologous model format in advance by the three-dimensional foot shape measuring device 18 or external terminal 17. In such a case, the model generator 21 need not generate a foot shape three-dimensional homologous model based on the measurement data, and the measurement data may be stored as it is as a new three-dimensional homologous model in the model storage unit 22.
The analysis processing unit 30 includes a cluster analysis unit 31 and a principal component analysis unit 32. The cluster analysis unit 31 performs cluster analysis for an upper layer and a lower layer, which will be described later, on multiple three-dimensional homologous models stored in the model storage unit 22. The cluster analysis unit 31 performs a method in which different cluster analysis methods for the upper layer and lower layer are combined. The principal component analysis unit 32 performs principal component analysis, which will be described later, on multiple foot shape three-dimensional homologous models stored in the model storage unit 22. After performing the cluster analysis for the upper layer, the cluster analysis unit 31 performs the cluster analysis for the lower layer based on the result of the principal component analysis performed by the principal component analysis unit 32.
As the cluster analysis unit 31 performs the cluster analysis and the principal component analysis unit 32 performs the principal component analysis, information of each cluster is acquired as the classification results and output to the outside by the output unit 26. Based on the classification results of the cluster analysis, the analysis processing unit 30 divides the three-dimensional homologous models stored in the model storage unit 22 into multiple clusters.
The output unit 26 may display the classification results on a display screen of the shape analysis device 50 or an external terminal 17 or may transmit the classification results to an external terminal 17 via the communication unit 19. The output unit 26 outputs three-dimensional coordinate groups of three-dimensional homologous models of each cluster. The information of the classification results output by the output unit 26 may be used for designing of lasts or sock liners.
The statistical processing unit 35 performs demand forecasting for a last corresponding to each foot shape model based on the foot shape model distribution for each cluster. The result of the demand forecasting is output to the external terminal 17 by the output unit 26. Based on the result of the demand forecasting, the statistical processing unit 35 manages a database of lasts, footwear, or sock liners corresponding to the foot shape models in each cluster stored in the model storage unit 22.
Fig. 11 shows the relationships between the distributions of foot lengths and ball girths of women and men and the JIS in Japan. Shoe sizes in Japan are classified based on the foot length and the ball girth/foot width and standardized according to the Japanese Industrial Standards (JIS) as a standard specification. In this standard, sizes are defined separately for men, women, and children, taking into consideration the differences in physical size.
Fig. 11A shows the JIS for women and a distribution obtained from samples of a large number of adult women. Fig. 11B shows the JIS for men and a distribution obtained from samples of a large number of adult men. The JIS specifies the foot length in the range of 19.5 cm to 27.0 cm for women, whereas it specifies the foot length in the range of 20.0 cm to 30.0 cm for men. For the ball girth/foot width, shoe widths A-F for women and shoe widths A-G for men are defined for each foot length. However, the ranges are defined differently, such as the shoe width A for women is defined as 183 mm in ball girth and 76 mm in foot width, whereas the shoe width A for the foot length of 20.0 cm for men is defined as 189 mm in ball girth and 79 mm in foot width.
The multiple diagonal lines ascending to the right in Figs. 11A and 11B respectively indicate the relationships between the foot length [mm] and ball girth [mm] defined for the respective foot length sizes in the JIS. The multiple diagonal lines in Fig. 11A respectively indicate the shoe widths A-F for women from the bottom, and the multiple diagonal lines in Fig. 11B respectively indicate the shoe widths A-G for men from the bottom. The difference in ball girth between adjacent shoe widths is about 6 mm.
The distribution of the women's samples shown in Fig. 11A mostly lies within the range of the foot length and ball girth specified in the JIS, but there are some samples outside the range. Also, the distribution of the men's samples shown in Fig. 11B mostly lies within the range of the foot length and ball girth specified in the JIS, but there are some samples outside the range, as in the case of women's samples.
The bold diagonal line in each of Figs. 11A and 11B indicates a sample average for women or men. There is variance of ball girth of about ± 3-4 widths each above and below the average line for each foot length size. That is, even if the relationship between the foot length and ball girth is defined and provided as a standard, as shown in each of Figs. 11A and 11B, the variance or dispersion of the ball girth is actually large. Moreover, although the conventional shoe standards only define the relationships between the foot length and ball girth, the size and shape of a foot are determined further based on other parameters. Accordingly, even if only the foot length and the ball girth fit, the target shoes may not necessarily fit the subject's feet. In order to solve such a situation, a method described below is used to classify a group of foot shape models, measured three-dimensionally, by cluster analysis and to design size variations based on the classification.
Fig. 12 shows a difference between a general cluster analysis method and a new cluster analysis method. When a general cluster analysis method is used for clustering of a foot shape data group X, it is conceivable to perform cluster analysis based on the Euclidean distance. However, with this method, cluster classification is performed in a way that is greatly affected by the foot length size. Also, when the classification needs to be performed based on not only the foot length size but also differences in foot shape, it is conceivable to divide the data based on the foot length size and then perform cluster analysis for each foot length size. However, even with this method, it is expected that classification will be greatly affected by the foot length size and it will be difficult to make a difference from a conventional grading method in which classification is performed only based on multiple ball girth sizes for each foot length size. In addition, the number of classified clusters may vary depending on the size.
Therefore, the cluster analysis unit 31 in the present embodiment performs cluster analysis across all foot length sizes, as shown in Fig. 12. The foot shape data group X is configured such that a large cluster W, obtained by classification based on similarity in shape (i.e., shapes like similar figures) across foot length sizes, is multiplied by a small cluster H, obtained by classification based on detailed features. The next figure illustrates a hierarchical state of such clusters.
Fig. 13 shows a method in which different cluster analysis methods for an upper layer and a lower layer are combined. First, the foot shape data group X is classified, by cluster analysis based on the cosine similarity, into clusters 1 to n, which constitute a first layer 110 as the upper layer. The clusters 1 to n are each subdivided, by cluster analysis based on principal component analysis in which the results are dimensionally reduced to the second and the subsequent principal components excluding the first principal component, into clusters (1-1, 1-2, ..., 1-m, 2-1, 2-2, ..., 2-m, ..., n-1, n-2, ..., n-m), which constitute a second layer 112 as the lower layer. The cluster analysis method for each of the upper layer and lower layer will be described later.
Fig. 14 shows the Euclidean distance and the cosine similarity between points. Explanation will be given using an example in which there are four points of a first point 120, a second point 121, a third point 122, and a fourth point 123 in a vector space. A common method for measuring the proximity between two points is a method using distance called the Euclidean distance for judgment. The Euclidean distance is the linear distance between two points, and a smaller value thereof means that the two points are more similar. Meanwhile, the present embodiment mainly employs a method using similarity called the cosine similarity for judgment. The cosine similarity is the cosine value (cosθ) of an angle θ formed by position vectors of two points from the origin, and, when the angle θ is smaller, the cosine value becomes closer to 1, which means that the two points are more similar. In general, the cosine similarity is used in situations where the similarity between sentences is measured and is rarely used in situations where the similarity between shapes is measured.
The Euclidean distance (distance 124) from the first point 120 to the second point 121 is shorter than the Euclidean distance (distance 125) from the first point 120 to the third point 122. Therefore, the second point 121 is judged closer to the first point 120 than the third point 122 based on the Euclidean distance.
On the other hand, the angle θ2 between the position vectors of the first point 120 and the third point 122 from the origin is smaller than the angle θ1 between the position vectors of the first point 120 and the second point 121 from the origin, and the cosine value of the angle θ2 is closer to 1. Therefore, the third point 122 is judged closer to the first point 120 than the second point 121 based on the cosine similarity.
Further, the first point 120 and the fourth point 123 have almost the same position vectors from the origin and hence the angle θ is almost zero, so that the cosine similarity is almost 1. Therefore, the fourth point 123 is farther from the first point 120 than the second point 121 based on the Euclidean distance but is infinitely closer to the first point 120 based on the cosine similarity.
Fig. 15 shows the relationships between corresponding points in two foot shape models. The foot shape models are constituted by point clouds, and each point represents an anatomical feature in the foot shape. Since each foot shape model includes the same points of anatomical features, the similarity between the overall foot shape models is determined based on the similarity of the positional relationships between the points. When a relatively small foot shape model 130 and a relatively large foot shape model 131 are compared, the cosine similarity is calculated based on the angle between the position vectors, from the origin, of corresponding points in the clouds of a large number of points included in the respective foot shape models. In the side view of Fig. 15A, points 132 and 133, points 134 and 135, and points 136 and 137 correspond to each other; in the top view of Fig. 15B, points 138 and 139, points 140 and 141, and points 142 and 143 correspond to each other. In Fig. 15A, each of the angle between the position vectors of the points 132 and 133, the angle between the position vectors of the points 134 and 135, and the angle between the position vectors of the points 136 and 137 is almost zero. In Fig. 15B, each of the angle between the position vectors of the points 138 and 139, the angle between the position vectors of the points 140 and 141, and the angle between the position vectors of the points 142 and 143 is almost zero. Therefore, although they differ in size, the foot shape model 130 and the foot shape model 131 can be said to be almost similar figures.
Fig. 16 shows comparisons between foot shape models using the Euclidean distance and the cosine similarity. When foot shape models are closer in foot length size, the value of the Euclidean distance becomes smaller, so that the models are likely to be judged "similar". Conversely, foot shape models with a larger value of the Euclidean distance are likely to be judged "dissimilar". When foot shape models are closer to similar figures, the cosine similarity becomes closer to 1, so that the models are likely to be judged "similar". Conversely, when the cosine similarity is closer to 0, the models are likely to be judged "dissimilar".
In the example of Fig. 16A, the two foot shape models almost overlap. The Euclidean distance is relatively small, and the cosine similarity is almost 1. Therefore, based on either the Euclidean distance or the cosine similarity, the models are likely to be judged "similar".
In the example of Fig. 16B, on the other hand, the two foot shape models are clearly different in size. Since the Euclidean distance is relatively large, the models are likely to be judged "dissimilar" based on the Euclidean distance. Meanwhile, since the cosine similarity is almost 1, which is almost the same as in the example of Fig. 16A, the models are likely to be judged "similar" based on the cosine similarity. That is, when two foot shape models are compared, even when there is a large difference based on the Euclidean distance, there may be almost no difference based on the cosine similarity, indicating that the cosine similarity is not affected by size. The example of Fig. 16B shows that the two foot shape models are different in size but are similar such that they can be said to be almost similar figures.
Fig. 17 shows differences in classification result between the cluster analysis based on the cosine similarity and the cluster analysis based on the Euclidean distance. As the classification results of actual cluster analysis of the foot shape data group, hierarchical clusters based on the Euclidean distance are shown on the right, and the hierarchical clusters based on the cosine similarity are shown on the left.
In the cluster analysis based on the Euclidean distance, the foot length gradually increases from left to right in the subdivided clusters in the lowest layer, with the foot length size being smaller toward the left and being larger toward the right. This indicates that the influence of the foot length size is dominant in the cluster analysis based on the Euclidean distance. Also, in terms of sex, males gradually increases from left to right, with females increasing toward the left and males increasing toward the right. This is because women tend to have smaller foot lengths than men, and it can be seen, as a result, that the cluster analysis based on the Euclidean distance is also affected by sex.
Meanwhile, in the cluster analysis based on the cosine similarity, various foot lengths are randomly mixed from left to right in the subdivided clusters in the lowest layer, indicating that there is little influence by the foot length size. Similarly, sex is also randomly mixed, indicating that there is also little influence by sex.
Fig. 18 shows a classification result of the cluster analysis based on the cosine similarity. The samples for the cluster analysis were foot shape data of about 5,000 adult males and females. A hierarchical clustering method using the Ward's method based on the cosine similarity between points included in foot shape data was adopted.
The top three clusters (a first cluster 150, a second cluster 151, and a third cluster 152) are regarded as the upper layer. In each of the first cluster 150, second cluster 151, and third cluster 152, a foot shape based on the coordinates of each point obtained by normalizing the foot length size is defined as an average foot.
By superimposing the foot shape model of the average foot of each cluster, the characteristics of each cluster and the areas where such characteristics are likely to appear can be determined based on differences in partial shapes. For example, a characteristic may be found in a difference in instep height, such as, in a direction of instep height, the instep of the first cluster 150 is the lowest, the instep of the second cluster 151 is intermediate, and the instep of the third cluster 152 is the highest. For example, a characteristic may be found in a difference in first toe angle, such as, with regard to the angle of the first toe, the angle of the first cluster 150 extends toward the medial side the most, the angle of the second cluster 151 is intermediate, and the angle of the third cluster 152 is slightly inclined toward the second toe. For example, a characteristic may be found in the inclination around the ankle, such as, with regard to the inclination around the ankle, the inclination of the first cluster 150 is the largest on the medial side, the inclination of the second cluster 151 is intermediate, and the inclination of the third cluster 152 is the smallest.
Fig. 19 shows regression lines of the foot length and ball girth of top three clusters and also shows results of principal component analysis of the top three clusters. Fig. 19 shows the regression lines that respectively show the relationships between the foot length and the ball girth in the first cluster 150, second cluster 151, and third cluster 152, superimposed on graphs of the JIS similar to those in Fig. 11. It can be seen therein that although the regression lines are almost parallel to each other, the slopes thereof are significantly different from the slopes of the regression lines showing the relationships between the foot length and the ball girth in the JIS. Therefore, by designing last variations along the regression lines of the respective clusters, it is possible to design variations that are different from the conventional grading provided separately for men and women according to the JIS, i.e., variations separated based on foot shape characteristics other than the foot length size regardless of gender.
The principal component analysis unit 32 performs principal component analysis on the foot shape data in each cluster, calculates data obtained by adding a first principal component PC1, as the variance, to the average foot that is the center of gravity of each cluster, and plots the relationship between the foot length and the ball girth in the data on the graph of Fig. 19. The clusters have been obtained by primary clustering based on the cosine similarity and classified such that the influence of the foot length size can be ignored, but the data itself contains foot length information. Therefore, when the principal component analysis unit 32 performs the principal component analysis, a principal component greatly affected by the foot length is extracted as the first principal component PC1. However, since the data have been classified based on the cosine similarity into clusters having different average foot shapes as the large classifications in the upper layer, the classification based on principal components in the clustering for each cluster in the lower layer can be performed easily. In this regard, the plots with open circles in the graph, which indicate the relationship between the foot length and the ball girth in the data of the average foot + the first principal component PC1 for each cluster, are located almost along the regression line of each cluster, indicating that the results of the cluster analysis and the results of the principal component analysis are consistent.
Fig. 20 shows results of principal component analysis for a cluster. When the principal component analysis unit 32 performs principal component analysis on a cluster, it can be seen what parameter has a significant influence on the variance of the data included in the cluster. In Fig. 20, the first principal component PC1 is set on the vertical axis in the upper graphs, a second principal component PC2 is set on the vertical axis in the middle graphs, and a third principal component PC3 is set on the vertical axis in the lower graphs. Also, the foot length is set on the horizontal axis in the left graphs, and the ball girth is set on the horizontal axis in the right graphs. In each graph, the plot group enclosed by a line on the left side indicates females, and the plot group enclosed by a line on the right side indicates males.
As shown in the two upper graphs on the left and right sides, the first principal component PC1 is strongly correlated not only with the foot length but also with the ball girth. On the other hand, as shown in the middle and lower graphs, the regression lines therein are almost horizontal, so that it can be seen that the second principal component PC2 and the subsequent principal component are hardly affected by the foot length or ball girth. Utilizing such characteristics in the results of the principal component analysis, in the present embodiment, the first principal component PC1, which is affected by the foot length and ball girth, is excluded, and only the second principal component PC2 and the subsequent principal components, which are not affected by the foot length or ball girth, are used for sub-clustering. The utilization of such characteristics is considered to be convenient for construction of variations based on the clustering focusing on differences in shape of a detail, which are different from the conventional grading based on the size.
As shown in Fig. 13, the first layer 110 as the upper layer includes multiple clusters classified by cluster analysis performed by the cluster analysis unit 31 based on the cosine similarity. Each of the clusters classified in the first layer 110 is further classified into many more detailed clusters in the second layer 112 as the lower layer, by cluster analysis performed by the cluster analysis unit 31 based on the principal component analysis with the dimensional reduction to the second and the subsequent principal components. In the principal component analysis in that case, the results of the principal component analysis performed by the principal component analysis unit 32 are dimensionally reduced to the second and the subsequent principal components excluding the first principal component. In the cluster analysis for the second layer 112, hierarchical clustering with the Ward's method based on the Euclidean distance is used based on the second principal component PC2 and the subsequent principal components of which the cumulative contribution ratio is up to 99%.
A group of foot shape models classified into a large number of clusters based on detailed features can be used not only for designing of last and footwear variations, but also for designing of sock liners. For example, variations associated with the shape of a detail, which does not depend on the foot length and ball girth sizes, may be absorbed by design variations of sock liners, thereby reducing the number of variations to be absorbed in the designing of lasts and footwear. That is, by combining the last and footwear variations and the sock liner variations, the overall variations may be designed to cover the entire foot shape model group.
Also, a large number of foot shape models included in the foot shape model group may be allocated to size variations according to the JIS, based on which of the lasts of size variations designed according to the JIS the foot shape model fits.
Since the number of people of the foot shape data included in each cluster is different, the ratio of the number of people in each cluster to the entire foot shape data group, as the population, is also different. Meanwhile, when a group of foot shape data collected and accumulated for various purposes are held as a database besides the foot shape data group used for the cluster analysis in the first embodiment, the distribution for each foot length size with respect to the population can be calculated based on those data. Therefore, the statistical processing unit 35 can quantify the ratio of each combination of a cluster and a foot length by combining the ratio of the number of people in each cluster and the distribution for each foot length size. The ratio of each combination of a cluster and a foot length when the foot length sizes are divided in the range of 22 cm to 31 cm in increments of 1 cm is quantified.
When a variation of a combination pattern for the size and shape of a footwear product or sock liner product is designed based on the ratio of each combination of a cluster and a foot length, the statistical processing unit 35 can forecast demand for initial stock according to the ratio of each combination of a cluster and a foot length. In such a case, a combination pattern of a cluster and a foot length for which demand is expected to be extremely low can be excluded from the shoe product variations from the beginning. Besides forecasting demand for initial stock, the statistical processing unit 35 can also reflect a demand forecast in the production plan when the stock decreases due to actual sales. The statistical processing unit 35 may output information regarding the ratio of each combination of a cluster and a foot length, to the outside via the output unit 26.
The present disclosure has been described with reference to an embodiment. The embodiment is intended to be illustrative only, and it will be obvious to those skilled in the art that various modifications to a combination of constituting elements or processes could be developed and that such modifications also fall within the scope of the present disclosure. Also, when the embodiment set forth above is generalized, the following aspects are obtained.
The abovementioned embodiment describes an example in which the footwear component design system 200 is applied to customization of a sock liner and designing of a sock liner. In a modification, it may be applied to customization and designing of shoes that can be manufactured entirely, including the uppers, by additive manufacturing, such as sandals. Also, it may be applied to customization and designing of some footwear components, such as soles and uppers of shoes. Also, it may be applied to customization and designing of products other than footwear and footwear components, such as clothing made without sewing including gloves, hats, and garments, accessories including glasses, rings, necklaces, and earrings, wearable devices including headphones, hearing aids, and in-ear monitors, computer mice, mouthpieces, and bedding including pillows.

Aspect 1

A footwear component design device, including:

a model storage unit that stores, in advance, a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot;
a design storage unit that stores a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models;
a measurement data acquirer that acquires measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject;
a model determining unit that determines, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models;
a basic design determining unit that determines basic design data corresponding to the three-dimensional homologous model determined, among the plurality of basic design data; and
a design processing unit that generates footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.

Accordingly, in the footwear component design device according to Aspect 1, footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser can be designed. Since the basic design data is determined from multiple three-dimensional homologous models prepared in advance, the design validity can be assured. Therefore, both high design flexibility and design validity can be achieved for footwear or a footwear component.

Aspect 2

The footwear component design device according to Aspect 1, wherein the model determining unit acquires a position vector from a predetermined reference point to each point in the plurality of three-dimensional homologous models, also acquires a position vector from the predetermined reference point to each point in a three-dimensional homologous model in the measurement data, and determines, based on the distance between corresponding points or the similarity between corresponding position vectors in three-dimensional homologous models, a three-dimensional homologous model similar to a body shape of the subject, among the plurality of three-dimensional homologous models.
Accordingly, in the footwear component design device according to Aspect 2, size variations can be provided in a wider range to fit individual feet more precisely, compared to conventional size variations that are standardized based only on the foot length and the foot width. Therefore, footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser can be designed.

Aspect 3

The footwear component design device according to Aspect 1 or 2, wherein the model storage unit stores the plurality of three-dimensional homologous models that are classified into a plurality of clusters by cluster analysis based on cosine similarity between position vectors from a predetermined reference point to the respective points in the three-dimensional homologous models.
Accordingly, in the footwear component design device according to Aspect 3, classification can be performed based on similarity, which is not easily affected by size, and size variations can be provided to fit individual feet more precisely regardless of foot size. Therefore, footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser can be designed.

Aspect 4

The footwear component design device according to Aspect 3, wherein the model storage unit stores the plurality of three-dimensional homologous models that are classified into a plurality of clusters in an upper layer by cluster analysis based on cosine similarity and are further classified into a plurality of more detailed clusters in a lower layer by performing cluster analysis on each cluster in the upper layer based on principal component analysis of which results are dimensionally reduced to the second and the subsequent principal components excluding the first principal component.
Accordingly, in the footwear component design device according to Aspect 4, classification can be performed based on factors that are not easily affected by gender or size, and size variations can be provided to fit individual feet more precisely regardless of gender or size. Therefore, footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser can be designed.

Aspect 5

The footwear component design device according to any one of Aspects 1 through 4, further including an individual information acquirer that acquires individual information that designates an individual transformation specified as a transformation of basic design of the footwear component based on the subject's wishes,
wherein the design processing unit generates the footwear component design data in which the individual transformation is added to the basic design based on the basic design data and the individual information.
Accordingly, in the footwear component design device according to Aspect 5, not only can footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser be designed, but also the preferences of the intending purchaser can be further reflected in the design and decoration. Thus, unique footwear or footwear components in which individual differences and preferences are reflected can be custom-designed. Since the basic design data is determined from multiple three-dimensional homologous models prepared in advance, the design validity can be assured. Therefore, both high design flexibility and design validity can be achieved for footwear or a footwear component.

Aspect 6

The footwear component design device according to Aspect 5,

wherein the individual information acquirer acquires, as the individual information, information including text specified as a decoration shape to be added to an outer surface of the footwear component based on the subject's wishes, and
wherein the design processing unit generates the footwear component design data in which a decoration shape that forms the text specified is added to the basic design based on the basic design data and the individual information.

Accordingly, in the footwear component design device according to Aspect 6, not only can footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser be designed, but also the preferences of the intending purchaser can be further reflected in the design and decoration. Thus, unique footwear or footwear components in which individual differences and preferences are reflected can be custom-designed. Since the basic design data is determined from multiple three-dimensional homologous models prepared in advance, the design validity can be assured. Therefore, both high design flexibility and design validity can be achieved for footwear or a footwear component.

Aspect 7

The footwear component design device according to any one of Aspects 1 through 6, further including a footwear information acquirer that acquires footwear information indicating the type of footwear specified by the subject,

wherein the plurality of basic design data are designed to correspond to the shape of a last of at least one of a plurality of types of footwear, and
wherein the basic design determining unit determines the basic design data based on a three-dimensional homologous model similar to a foot shape of the subject and the footwear information.

Accordingly, in the footwear component design device according to Aspect 7, not only can a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser be designed, but also a footwear component of size and shape suitable for desired footwear of each wearer or intending purchaser can be designed.

Aspect 8

The footwear component design device according to any one of Aspects 1 through 7, wherein the footwear component is a sock liner of footwear.
Accordingly, in the footwear component design device according to Aspect 8, not only can a sock liner most suitable for the foot size and foot shape of each wearer or intending purchaser be designed, but also the preferences of the intending purchaser can be further reflected in the design and decoration. Thus, a unique sock liner in which individual differences and preferences are reflected can be custom-designed. Since the basic design data is determined from multiple three-dimensional homologous models prepared in advance, the design validity can be assured. Therefore, both high design flexibility and design validity can be achieved for a sock liner.

Aspect 9

A footwear component design method, including:

reading a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot;
acquiring measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject;
determining, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models;
determining basic design data corresponding to the three-dimensional homologous model determined, among a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models; and
generating footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.

Accordingly, in the footwear component design method according to Aspect 9, footwear or a footwear component most suitable for the foot size and foot shape of each wearer or intending purchaser can be designed. Since the basic design data is determined from multiple three-dimensional homologous models prepared in advance, the design validity can be assured. Therefore, both high design flexibility and design validity can be achieved for footwear or a footwear component.

INDUSTRIAL APPLICABILITY

The present disclosure relates to a footwear component design device and a footwear component design method.

REFERENCE SIGNS LIST

104 three-dimensional homologous model, 212 measurement data acquirer, 216 individual information acquirer, 218 footwear information acquirer, 220 model storage unit, 222 model determining unit, 230 design storage unit, 232 basic design determining unit, 234 design processing unit, 250 footwear component design device, 300 sock liner, 303 side surface

Claims

A footwear component design device, comprising:
a model storage unit that stores, in advance, a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot;

a design storage unit that stores a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models;

a measurement data acquirer that acquires measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject;

a model determining unit that determines, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models;

a basic design determining unit that determines basic design data corresponding to the three-dimensional homologous model determined, among the plurality of basic design data; and

a design processing unit that generates footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.
The footwear component design device according to Claim 1, wherein the model determining unit acquires a position vector from a predetermined reference point to each point in the plurality of three-dimensional homologous models, also acquires a position vector from the predetermined reference point to each point in a three-dimensional homologous model in the measurement data, and determines, based on the distance between corresponding points or the similarity between corresponding position vectors in three-dimensional homologous models, a three-dimensional homologous model similar to a body shape of the subject, among the plurality of three-dimensional homologous models.
The footwear component design device according to Claim 1 or 2, wherein the model storage unit stores the plurality of three-dimensional homologous models that are classified into a plurality of clusters by cluster analysis based on cosine similarity between position vectors from a predetermined reference point to the respective points in the three-dimensional homologous models.
The footwear component design device according to Claim 3, wherein the model storage unit stores the plurality of three-dimensional homologous models that are classified into a plurality of clusters in an upper layer by cluster analysis based on cosine similarity and are further classified into a plurality of more detailed clusters in a lower layer by performing cluster analysis on each cluster in the upper layer based on principal component analysis of which results are dimensionally reduced to the second and the subsequent principal components excluding the first principal component.
The footwear component design device according to any one of Claims 1 through 4, further comprising an individual information acquirer that acquires individual information that designates an individual transformation specified as a transformation of basic design of the footwear component based on the subject's wishes,
wherein the design processing unit generates the footwear component design data in which the individual transformation is added to the basic design based on the basic design data and the individual information.
The footwear component design device according to Claim 5,
wherein the individual information acquirer acquires, as the individual information, information including text specified as a decoration shape to be added to an outer surface of the footwear component based on the subject's wishes, and

wherein the design processing unit generates the footwear component design data in which a decoration shape that forms the text specified is added to the basic design based on the basic design data and the individual information.
The footwear component design device according to any one of Claims 1 through 6, further comprising a footwear information acquirer that acquires footwear information indicating the type of footwear specified by the subject,
wherein the plurality of basic design data are designed to correspond to the shape of a last of at least one of a plurality of types of footwear, and

wherein the basic design determining unit determines the basic design data based on a three-dimensional homologous model similar to a foot shape of the subject and the footwear information.
The footwear component design device according to any one of Claims 1 through 7, wherein the footwear component is a sock liner of footwear.
A footwear component design method, comprising:
reading a plurality of three-dimensional homologous models for a plurality of foot shapes with a three-dimensional coordinate group indicating an anatomical feature of a foot;

acquiring measurement data of a three-dimensional coordinate group indicating an anatomical feature corresponding to a three-dimensional homologous model of a foot shape at least including a sole and a foot side surface of a subject;

determining, among the plurality of three-dimensional homologous models, a three-dimensional homologous model similar to a foot shape of the subject by evaluating similarity in coordinates between a three-dimensional coordinate group in the measurement data and a three-dimensional coordinate group in each of the plurality of three-dimensional homologous models;

determining basic design data corresponding to the three-dimensional homologous model determined, among a plurality of basic design data as three-dimensional design data used for additive manufacturing of a footwear component corresponding to a foot shape of each of the plurality of three-dimensional homologous models; and

generating footwear component design data corresponding to a foot shape of the subject based on the basic design data determined.