Prediction device, prediction method, and prediction system

Abstract

To provide a technique capable of easily acquiring the shape of a subject's foot in an unloaded state, a prediction device (1), a prediction method, and a prediction system (100) that predict the shape of a subject's foot in an unloaded state include a communication device (16) that acquires subject data containing measurement data of the shape of a subject's foot in a loaded state; a storage (13) that stores first sample data in the loaded state and second sample data in the unloaded state calculated from measurement data of the shape of a plurality of sample feet in the same loaded state and the same unloaded state; and a processor (11) that predicts the shape of a subject's foot in the unloaded state, the processor (11) calculating a difference between the subject data and the first sample data and predicting the shape of a subject's foot in the unloaded state based on the difference and the second sample data.

Description

Technical Field

[0001] This disclosure relates to a prediction device, prediction method, and prediction system for predicting the shape of a subject's foot under no-load conditions. Background Technology

[0002] Custom-made shoes or insoles (insoles) that conform to the shape of an individual's foot are generally made based on the shape of the foot, especially the shape of the forefoot. The shape of the foot differs under load when the forefoot is bearing weight compared to when it is not. For example, the shape of the foot in an unloaded state does not deform due to load, so it is possible to make shoes or insoles that conform to the shape of the foot more closely than the shape of the foot under load.

[0003] One known method for measuring the shape of a foot under no-load conditions involves having the subject lie prone on a bed, wrapping a plaster cast around the subject's foot, and allowing plaster to flow into the cured cast to mold the foot's shape. However, this method requires an experienced technician, and the molding process can be time-consuming. Furthermore, it necessitates a molding bed and space for handling the plaster. Therefore, this method is difficult to implement in shops such as shoe stores.

[0004] Regarding this point, Japanese Patent No. 5717894 discloses a method for obtaining measurement data of the shape of the subject's foot standing on a transparent plate, i.e., pressure state data, and measurement data of the shape of the subject's foot gently touching the transparent plate, i.e., non-pressure state data, and making insoles based on the difference between the pressure state data and the non-pressure state data. Summary of the Invention

[0005] According to the method disclosed in Japanese Patent No. 5717894, insoles that conform to the shape of a subject's foot can be manufactured based on the shape of the subject's foot under both unloaded and loaded conditions. However, the method disclosed in Japanese Patent No. 5717894 requires measuring the shape of the subject's foot in a store under both unloaded and loaded conditions, which can easily lead to longer measurement times. Furthermore, in the method disclosed in Japanese Patent No. 5717894, the subject must ensure that their soles lightly contact the transparent plate to minimize the application of load to the soles, making it difficult to obtain accurate measurement data, and requiring skilled store clerks to perform the measurements.

[0006] This disclosure was made to solve this problem, and its purpose is to provide a technique that enables easy acquisition of the shape of a subject's foot under no-load conditions.

[0007] A prediction apparatus according to one aspect of this disclosure includes: an acquisition unit for acquiring subject data, the subject data including measurement data of the shape of the subject's feet under load; a storage unit for storing first sample data under load and second sample data under unload, calculated based on the same multiple sample foot shape measurement data under both load and unload conditions; and a prediction unit for predicting the shape of the subject's feet under unload conditions. The prediction unit calculates the difference between the subject data and the first sample data, and predicts the shape of the subject's feet under unload conditions based on the difference and the second sample data.

[0008] A prediction method according to one aspect of this disclosure includes the following steps: acquiring subject data, the subject data including measurement data of the shape of the subject's feet under load; storing first sample data under load and second sample data under unload, calculated from the same multiple sample foot shape measurement data under both load and unload conditions; and predicting the shape of the subject's feet under unload conditions. The prediction step includes the following steps: calculating the difference between the subject data and the first sample data; and predicting the shape of the subject's feet under unload conditions based on the difference and the second sample data.

[0009] A prediction system according to one aspect of this disclosure includes: a measuring device for measuring the shape of a subject's foot under load; and a prediction device for predicting the shape of the subject's foot under no-load. The prediction device includes: an acquisition unit for acquiring subject data from the measuring device, the subject data including measurement data of the subject's foot shape under load; a storage unit for storing first sample data under load and second sample data under no-load, calculated based on measurement data of the same multiple sample feet under both load and no-load conditions; and a prediction unit for predicting the shape of the subject's foot under no-load. The prediction unit calculates the difference between the subject data and the first sample data, and predicts the shape of the subject's foot under no-load based on the difference and the second sample data.

[0010] The descriptions and other objects, features, aspects, and advantages of this disclosure will become clear from the following detailed description relating to this disclosure, which will be understood in conjunction with the accompanying drawings. Attached Figure Description

[0011] Figure 1 This is a schematic diagram showing the structure of the prediction system in the implementation method.

[0012] Figure 2A as well as Figure 2B It is a diagram showing the shape of the foot under no-load and the shape of the foot under load.

[0013] Figures 3A to 3H It is a diagram used to illustrate the measurement of foot shape.

[0014] Figure 4 It is a diagram used to illustrate the curve of a foot.

[0015] Figure 5 It is a diagram showing the cross-section of the foot.

[0016] Figure 6 It is a diagram used to illustrate the shape data of the foot.

[0017] Figure 7 It is a diagram used to illustrate the common origin model.

[0018] Figure 8 This is a block diagram illustrating the structure of the prediction device in the implementation method.

[0019] Figure 9 This is a diagram illustrating an example of load profile data stored in the predictive device.

[0020] Figure 10 Figures (A) to (C) in the figure represent an example of obtaining load foot data.

[0021] Figure 11A as well as Figure 11B It is a diagram used to illustrate the leg length and orthogonal leg width of the reference.

[0022] Figure 12 This is a diagram illustrating an example of unloaded foot data stored in a predictive device.

[0023] Figure 13 Figures (A) to (C) in the figure represent an example of obtaining unloaded foot data.

[0024] Figure 14 This is a flowchart illustrating the prediction process performed by the prediction device in the implementation method.

[0025] Figure 15 It is a graph used to illustrate the calculation of the difference between the data of the subjects and the data of the first sample.

[0026] Figure 16 It is a graph used to illustrate changes in sample data based on differences.

[0027] Figure 17 This is an illustration of an example of how insoles are made.

[0028] Figures 18A-18CThis is a graph used to illustrate the changes in the second sample data based on the appearance of the foot arch. Detailed Implementation

[0029] The embodiments are described below based on the accompanying drawings. In the following description, the same symbols are used to refer to the same structures. Their names and functions are also the same. Therefore, detailed descriptions of them will not be repeated.

[0030] [Structure of the prediction system]

[0031] Figure 1 This is a schematic diagram illustrating the structure of the prediction system 100 according to the implementation method. In shoe stores and similar shops, custom-made shoes or insoles are manufactured to fit the shape of an individual's foot. Since the shape of the foot in an unloaded state does not deform under load, it is possible to manufacture shoes or insoles that conform to the shape of the foot even better than the shape of the foot under load.

[0032] For example, Figure 2A as well as Figure 2B This is a diagram showing the shape of the foot under no-load and under-load conditions. For example... Figure 2A As shown, the foot in a no-load state clearly shows the outline, the inner and outer contact lines, the transverse arch, the inner and outer arches, and the heel cup.

[0033] The outline of the foot is a line that represents its shape. The medial ground contact line is the line that appears on the inside of the foot, on the side of the big toe. The lateral ground contact line is the line that appears on the outside of the foot, on the side of the fifth toe. The medial arch is the arch that forms from the calcaneus to the first metatarsal bone. The lateral arch is the arch that forms from the calcaneus to the fifth metatarsal bone. The transverse arch is the arch that forms between the medial and lateral arches. The heel cup is the shape that appears at the back of the foot. These parts of the foot play a role in cushioning the impact of walking or improving balance when standing.

[0034] On the other hand, such as Figure 2B As shown, in the foot under load, the outline, inner ground contact line and outer ground contact line can be identified, but it is difficult to identify the transverse arch, inner arch, outer arch and heel cup.

[0035] Furthermore, in this disclosure, the term "load state" refers to a state that may affect the determination of the arch and heel cup of the foot, such as including... Figure 1 And the following Figure 10 As shown in (A), this refers to the state in which the subject's foot is in contact with the ground. On the other hand, in this disclosure, the term "no-load state" refers to a state that does not affect the determination of the arch of the foot and the heel cup, such as those described later. Figure 13As shown in (A), the subject's foot is not touching the ground. Alternatively, the "no-load state" can also be the state in which part of the subject's foot is in contact with the ground or some object, as long as it does not affect the determination of the arch of the foot and the heel cup.

[0036] Therefore, in order to manufacture shoes or insoles that conform to the shape of the foot, it is preferable to obtain the shape of the foot in a load-bearing state. However, when obtaining the shape of the foot in a load-bearing state in a shop, it is necessary to perform operations such as wrapping a plaster cast around the subject's foot and allowing plaster to flow into the cured plaster cast for injection molding, which can easily increase the measurement time and require skill from the measurer. Therefore, the prediction system 100 of the embodiment is configured to easily obtain the shape of the subject's foot in a load-bearing state.

[0037] like Figure 1 As shown, the prediction system 100 includes a measuring device 2 and a prediction device 1. Furthermore, the embodiment illustrates an example of using the prediction system 100 to generate data for making insoles, but the techniques disclosed herein can also be applied to examples of using the prediction system 100 to generate data for making custom shoes.

[0038] The measuring device 2 is, for example, a three-dimensional foot scanner using laser measurement, including a top plate 21 and a laser measuring unit 22 disposed in a manner that clamps the top plate. When the subject places their foot on the top plate 21 in a standing position, the subject's weight applies a load from the foot to the top plate 21. That is, the subject's foot is under load. While the subject's foot is under load, the measuring device 2 measures the shape of the foot by moving the laser measuring unit 22 from the toe to the heel. The measuring device 2 outputs the subject's data to the prediction device 1, the subject's data including measurement data (3D data) of the shape of the subject's foot acquired by the laser measuring unit 22. In addition, the subject's data only needs to include at least the measurement data of the shape of the foot acquired by the measuring device 2, but may also include other data (such as personal data such as the subject's gender or age).

[0039] The prediction device 1 acquires subject data from the measuring device 2 and predicts the shape of the subject's foot in an unloaded state based on the subject data. The prediction of the subject's foot shape in an unloaded state by the prediction device 1 will be described in detail later. The prediction device 1 outputs the predicted foot shape data in an unloaded state to a 3D printer 3 for manufacturing insoles, etc.

[0040] Thus, in the prediction system 100, the prediction device 1 can predict the shape of the subject's foot in the unloaded state based on the shape of the subject's foot in the loaded state obtained by the measuring device 2. Therefore, the user of the prediction system 100 can easily obtain the shape of the subject's foot in the unloaded state.

[0041] [Foot shape measurement items]

[0042] While referring to Figures 3A to 3H The description of the measurement device 2 is as follows: it measures the shape of the feet. Figures 3A to 3H This is a diagram used to illustrate measurement items for foot shape. For example... Figures 3A to 3H As shown, the measurement items for foot shape include foot length, foot circumference, orthogonal foot width, heel width, foot height, big toe angle, heel inclination angle, and arch height.

[0043] like Figure 3A As shown, foot length is the length from the back of the heel to the front of the longest toe. Figure 3B As shown, the foot circumference is the length around the foot measured from the back of the heel on the fifth toe side to a point A% of the foot length (e.g., the base of the fifth toe), and from the back of the heel on the big toe side to a point B% of the foot length (e.g., the base of the big toe). Figure 3C As shown, orthogonal foot width is the length in the width direction of the foot between the point on the fifth toe side (reaching C% of the foot length from the back of the heel, e.g., the base of the fifth toe) and the point on the big toe side (reaching D% of the foot length from the back of the heel, e.g., the base of the big toe). Furthermore, A through D are values ​​greater than 0, which can be predetermined according to specifications or arbitrarily set. Moreover, A can also be the same value as C, and B can also be the same value as D.

[0044] like Figure 3D As shown, heel width is the length in the width direction of the heel between the position on the fifth toe side (reaching E% of the foot length from the back of the heel) and the position on the big toe side (reaching E% of the foot length from the back of the heel). Figure 3E As shown, foot height is the height of the foot measured from the back of the heel to a point F% of the foot length. For example... Figure 3F As shown, the big toe side angle is the angle at which the big toe leans towards the fifth toe side. For example... Figure 3G As shown, the heel tilt angle is the angle at which the heel tilts relative to the direction perpendicular to the ground. Figure 3H As shown, arch height is the height from the ground to the navicular bone. Arch height can also be calculated using a formula based on foot length, foot circumference, heel width, foot height, big toe angle, and heel inclination angle. Furthermore, E and F are values ​​greater than 0, which can be predetermined according to specifications or can be set arbitrarily.

[0045] [Degree of flexion of the foot]

[0046] While referring to Figure 4 as well as Figure 5 On one hand, they explained the degree of bending of the foot. Figure 4 It is a diagram used to illustrate the curve of a foot. Figure 5 This is a diagram showing a cross-section of the foot. For example... Figure 4 As shown, the curve of the foot is defined within the range of the inner arch length corresponding to a length G% of the foot length originating from the back of the heel; it is a line indicating the degree of flexion of the foot. Furthermore, G is a value greater than 0, for example, a specified value set within the range of 70% to 75%. G can be predetermined according to specifications, or it can be set arbitrarily.

[0047] When the midpoint between the outline and the inner ground contact line is set as X, and the midpoint between the outline and the outer ground contact line is set as Y, the line passing through the midpoint Z between point X and point Y becomes a curve.

[0048] Figure 5 It shows Figure 4 The A-A' section of the foot is shown. Additionally, Figure 5 The image shows a cross-section of the foot taken under no-load conditions. (See figure.) Figure 5 As shown, when the line passing through the part of the foot in contact with the ground is set as the lowest line, the inner contact point can be represented by the intersection of line L, which passes through a height of H mm from the lowest line, and the inner shape of the foot. This inner contact point is set for each cross-section; therefore, the line connecting the multiple inner contact points set in each of the multiple cross-sections along the length of the foot... Figure 4 The inner contact lines shown are roughly consistent. Furthermore, the outer contact point can be represented by the intersection of line L and the outer shape of the foot. This outer contact point is set for each cross-section; therefore, the line connecting multiple outer contact points set in each of the multiple cross-sections along the length of the foot... Figure 4 The outer grounding lines shown are roughly the same. Additionally, H is a value greater than 0, which can be predetermined according to specifications or can be set arbitrarily.

[0049] A line sloping inwards at an angle of 'a' degrees from the ground towards the inside of the foot (the inner 'a' degree line) and the point of tangency P1 between the inner shape of the foot and the foot's outline form part of the top line of the insole on the inside of the foot. Similarly, a line sloping inwards at an angle of 'a' degrees from the ground towards the outside of the foot (the outer 'a' degree line) and the point of tangency P2 between the outer shape of the foot and the foot's outline forms part of the top line of the insole on the outside of the foot. Furthermore, 'a' is a value greater than 0, for example, a specified value set within the range of 45 degrees to 65 degrees. 'a' can be predetermined according to specifications, etc., or it can be arbitrarily set.

[0050] Furthermore, Q1 is defined as the point of tangency between the line inclined at b degrees from the ground toward the inside of the foot (the inside b-degree line) and the outline of the inside of the foot, and Q2 is defined as the point of tangency between the line inclined at b degrees from the ground toward the outside of the foot (the outside a-degree line) and the outline of the outside of the foot. Additionally, b is a value greater than 0, for example, a specified value set within the range of 15 to 30 degrees. b can be predetermined according to specifications, or it can be set arbitrarily.

[0051] The upper part of the foot, from tangent point P1 to tangent point P2, is also called the instep. The lower part of the foot, from tangent point P1 to tangent point Q1, is also called the upturned inner part. The lower part of the foot, from tangent point P2 to tangent point Q2, is also called the upturned outer part. The lower part of the foot, from tangent point Q1 to tangent point Q2, is also called the bottom.

[0052] [Foot shape data]

[0053] While referring to Figure 6 On one hand, it explains the foot shape data used in making the insoles. Figure 6 It is a diagram used to illustrate the shape data of the foot. For example... Figure 6 As shown, the shape data of the foot includes the position data of multiple structural points configured along the shape of the foot's cross-section.

[0054] For example, Figure 6 In the example, the shape data includes 25 structural points obtained by dividing the bottom into 25 equal parts, 8 structural points obtained by dividing the inner part of the foot into 8 equal parts, 8 structural points obtained by dividing the outer part of the foot into 8 equal parts, and 40 structural points obtained by dividing the instep into 40 equal parts.

[0055] In shape data, this configuration involves multiple structural points on the cross-section ( Figure 6 In the example, there are 81 points arranged along the length of the foot at specified intervals (e.g., every 1 mm). That is, in the case of a foot with a length of 255 mm, the shape data includes the position data of each of the 81 structural points arranged on each cross section at the 255 mm cross section. In addition, the number of structural points at the bottom, the inner ridge, the outer ridge, and the instep is not limited to the stated number and can be arbitrarily set.

[0056] [Same Origin Model]

[0057] While referring to Figure 7 On the one hand, the homology model is explained. Figure 7 This is a diagram used to illustrate the common origin model. For example... Figure 7 As shown, the homologous model is a foot model that uses multiple lines to represent the shape of the foot. Specifically, it will... Figure 6The structural points at the bottom, inner upward curve, outer upward curve, and instep, obtained for each cross-section of the foot, are connected by lines along the length of the foot, thus creating eighty-one lines along the length of the foot. These eighty-one lines allow for the creation of a homologous model. For example, in the case of a foot with a length of 255mm, a homologous model containing 20655 structural points (positional data) can be created.

[0058] [Structure of the Prediction Device]

[0059] Figure 8 This is a block diagram illustrating the structure of the prediction device 1 according to the embodiment. For example... Figure 8 As shown, the prediction device 1 includes a processor 11, a memory 12, a storage unit 13, an interface 14, a media reading device 15, and a communication device 16. These components are connected via a processor bus 17.

[0060] Processor 11 is an example of a "prediction unit". Processor 11 is a computer that reads programs (such as operating system (OS) 132 and prediction program 131) stored in memory 13, expands the read programs in memory 12, and executes them. Processor 11 may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), or a multiprocessor (MPU). In addition, processor 11 has the function of performing various processes by executing programs, but some or all of these functions may be implemented using dedicated hardware circuits such as application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs). "Processor" is not limited to a processor in the narrow sense that uses a stored-program approach to execute processes like a CPU or MPU, and may include hard-wired circuits such as ASICs or FPGAs. Therefore, processor may also include processing circuitry that predefines processing through computer-readable code and / or hard-wired circuitry.

[0061] The memory 12 includes volatile memory such as Dynamic Random Access Memory (DRAM) or Static Random Access Memory (SRAM), or non-volatile memory such as Read Only Memory (ROM) or Flash Memory.

[0062] Memory 13 is an example of a "storage unit". Memory 13 may include, for example, a non-volatile storage device such as a hard disk drive (HDD) or a solid state drive (SSD). Memory 13 stores a prediction program 131, an operating system 132, load pin data 133, and no-load pin data 134.

[0063] Prediction program 131 is used to perform the following processing (described later). Figure 14 The procedure shown is a prediction process in which the prediction device 1 predicts the shape of the subject's foot in the unloaded state based on the shape of the subject's foot in the loaded state obtained by the measuring device 2.

[0064] Load-bearing leg shape data 133 is an example of "first sample data". Load-bearing leg shape data 133 contains data calculated based on measurement data of the shape of multiple sample legs under load conditions. Regarding load-bearing leg shape data 133, the following will be used... Figures 9 to 11B Then it will be discussed.

[0065] The no-load foot shape data 134 is an example of "second sample data". The no-load foot shape data 134 contains data calculated based on measurement data of the shape of multiple sample feet under no-load conditions. Regarding the no-load foot shape data 134, the following will be used... Figure 12 as well as Figure 13 (A) to (C) will be discussed later.

[0066] Interface 14 accepts input from the user of the prediction device 1, including keyboard, mouse and touch elements.

[0067] The media reading device 15 accepts storage media such as the removable disk 18 and retrieves the data stored in the removable disk 18.

[0068] The communication device 16 is an example of an "acquisition unit". The communication device 16 transmits and receives data with other devices via wired or wireless communication. For example, the communication device 16 communicates with the measuring device 2 to acquire measurement data of the foot shape obtained by the measuring device 2. The communication device 16 also communicates with the 3D printer 3 to output foot shape data for use as an insole to the 3D printer 3.

[0069] Furthermore, the prediction device 1 is not limited to acquiring foot shape measurement data from the measuring device 2 via the communication device 16. For example, the prediction device 1 may also use the interface 14 to acquire foot shape measurement data input by the user. In this case, the interface 14 becomes an example of an "acquisition unit". Alternatively, the prediction device 1 may also read foot shape measurement data stored in the removable disk 18 via the media reading device 15. In this case, the media reading device 15 becomes an example of an "acquisition unit".

[0070] [Load-bearing foot type data]

[0071] Reference Figures 9 to 11B To illustrate the load-bearing foot type data 133. Figure 9 This is a diagram showing an example of the load profile data stored in the prediction device 1. Figure 10 Figures (A) to (C) in the figure represent an example of obtaining load foot data. Figure 11A as well as Figure 11B It is a diagram used to illustrate the leg length and orthogonal leg width of the reference.

[0072] like Figure 9 As shown, the load foot shape data includes measurement data of the shape of multiple sample feet under load conditions (specifically, homologous models made based on the measurement data) categorized according to each of multiple foot shape types based on at least one feature related to the shape of the foot. Figure 9 In the example shown, the arch height-to-foot length ratio and the heel tilt angle (the angle at which the heel tilts inward) were used as at least one feature. Furthermore, based on the three arch types classified according to the arch height-to-foot length ratio and the three heel tilt types classified according to the heel tilt angle, the load-bearing foot type data were classified into a total of nine foot type types.

[0073] Arch type is based on the height of the arch ( Figure 3H Divide by foot length ( Figure 3AThe calculated arch height-to-length ratio is used for classification. If the arch height-to-length ratio of a sample foot is less than A1%, the sample foot is classified as flat. If the arch height-to-length ratio of a sample foot is greater than or equal to A1% but less than A2%, the sample foot is classified as average. If the arch height-to-length ratio of a sample foot is greater than or equal to A2%, the sample foot is classified as high arch. Furthermore, A1 and A2 are values ​​greater than 0 (0 < A1 < A2). For example, A1 is set to a specified value within the range of 12% to 16%, and A2 is set to a specified value within the range of 18% to 22%. A1 and A2 can be predetermined according to specifications, or they can be arbitrarily set.

[0074] The type of heel tilt is based on the angle of heel tilt ( Figure 3G The angle of inclination of the heel of the sample foot is calculated as follows: If the inclination angle of the heel of the sample foot is less than B1 degrees, the sample foot is classified as inverted. If the inclination angle of the heel of the sample foot is greater than B1 degrees but less than B2 degrees, the sample foot is classified as average. If the inclination angle of the heel of the sample foot is greater than B2 degrees, the sample foot is classified as outward. For example, B1 is set to a specified value within the range of -2 degrees to 0 degrees, and B2 is set to a specified value within the range of 2 degrees to 5 degrees. B1 and B2 can be predetermined according to specifications, etc., or they can be set arbitrarily.

[0075] In the generation of load foot type data, such as Figure 10 As shown in (A), firstly, the shape of the feet of multiple sample subjects under load is obtained using measuring device 2. Furthermore, the method by which measuring device 2 measures the feet of the sample subjects is similar to... Figure 1 The measuring device 2 shown uses the same method to measure the feet of the subject. Specifically, when the subject places their feet on the top plate 21 in a standing position, the subject's weight applies a load to the top plate 21 from their feet. While the subject's feet are under load, the measuring device 2 measures the shape of the feet by moving from the toes to the heels using the laser measuring unit 22.

[0076] like Figure 10 As shown in (B), the measurement data of the sample foot shape acquired by the measuring device 2 is classified according to each of multiple foot type types based on at least one characteristic quantity related to the shape of the sample foot (in this example, the arch height-to-length ratio and the heel inclination angle). Specifically, a model is made based on the measurement data of the sample foot shape acquired by the measuring device 2. Figure 7 The homologous model shown classifies the created homologous models according to each type of multiple foot types.

[0077] The homologous model of the sample feet after classification according to each of the multiple foot types is changed based on the baseline foot length and orthogonal foot width.

[0078] While referring to Figure 11A as well as Figure 11B The length of the reference foot and the width of the orthogonal foot are explained on one side. For example... Figure 11A As shown, multiple foot types can be set based on arch type and heel slope type. Figure 11B As shown, when the base leg length is set to X mm (e.g., 255 mm), the orthogonal leg width is predetermined according to the leg type. Furthermore, X and Y1 to Y9 are values ​​greater than 0, which can be predetermined according to specifications or can be arbitrarily set.

[0079] The prototype model of the sample feet varies based on the base foot length and orthogonal foot width. Therefore, the prototype model (measurement data) can be used to calculate... Figure 4 The curve of the foot shown also changes.

[0080] Return to Figure 10 In (A) to (C), after the homologous model of the sample foot shape is modified according to the reference foot length and orthogonal foot width, the average value of the homologous model of the modified sample foot shape is calculated for each of the multiple foot type types. For example... Figure 10 As shown in (C), the average values ​​calculated for each of the multiple foot types are included as data A1 to data A9 in the load foot type data 133.

[0081] In this way, the designer of the prediction device 1 classifies the homologous models created based on the measurement data of the sample foot shape obtained by the measuring device 2 according to different types based on at least one feature (in this example, the arch height-to-length ratio and the heel tilt angle). The classified homologous models are then modified according to the reference foot length and orthogonal foot width, and the average value is calculated based on the modified homologous models. Thus, sample data under load conditions is obtained for each of the multiple foot type types. The obtained sample data under load conditions is pre-stored in the memory 13 as load foot type data 133 (first sample data). That is, the load foot type data 133 (first sample data) stored in the memory 13 contains the average foot shape data under load conditions for each of the multiple foot type types.

[0082] [Load-free foot type data]

[0083] While referring to Figure 12 as well as Figure 13 (A) to (C) in the text, while explaining the unloaded foot type data 134. Figure 12 This is a diagram representing an example of the unloaded foot type data stored in the prediction device 1. Figure 13 Figures (A) to (C) in the figure represent an example of obtaining unloaded foot data.

[0084] like Figure 12 As shown, the unloaded foot shape data includes measurement data of the shape of multiple sample feet in the unloaded state (specifically, homologous models made based on the measurement data) classified according to each of multiple foot shape types based on at least one feature related to the shape of the foot. Figure 12 In the example shown, the arch height-to-foot length ratio and heel inclination angle were used as at least one feature. Furthermore, the unloaded foot data were classified into a total of nine foot types based on three arch types categorized according to the arch height-to-foot length ratio and three heel inclination types categorized according to the heel inclination angle.

[0085] In the generation of no-load foot type data, such as Figure 13 As shown in (A), firstly, the shape of the feet of multiple sample subjects in an unloaded state was obtained using plaster casts. Additionally, the shapes of the feet of multiple sample subjects in an unloaded state were compared with... Figure 10 The multiple sample subjects under load conditions (A) to (C) are identical. Furthermore, the foot shape of the obtained plaster cast is measured using measuring device 2, thereby obtaining the foot shape of each of the multiple sample subjects under unloaded conditions.

[0086] like Figure 13 As shown in (B), the measurement data of the sample foot shape obtained using plaster casts are classified according to each of multiple foot type types based on at least one feature related to the shape of the sample foot (in this example, the arch-to-length ratio and the heel inclination angle). Additionally, Figure 10 Multiple sample objects under load states (A) to (C) and Figure 13 Since the multiple sample subjects in the unloaded state (A) to (C) are identical, the foot shape measurement data of the multiple sample subjects in the unloaded state can be classified according to the foot type based on the foot shape measurement data of the multiple sample subjects in the loaded state. Specifically, the foot shape measurement data of the sample subjects acquired by the measuring device 2 is used to create... Figure 7 The homologous model shown is classified as having the same foot type as the homologous model of the foot of the sample object under load.

[0087] The homologous model of the sample feet, categorized according to multiple foot types, is modified based on the baseline foot length and orthogonal foot width. The modification of the homologous model of the sample feet under no-load conditions is related to... Figure 10 The changes to the original model of the sample foot under load conditions (A) to (C) are the same.

[0088] The prototype model of the sample feet varies based on the base foot length and orthogonal foot width. Therefore, the prototype model (measurement data) can be used to calculate... Figure 4 The curve of the foot shown also changes.

[0089] After modifying the homologous model of the sample foot according to the baseline foot length and orthogonal foot width, the average value of the homologous model of the modified sample foot is calculated for each of the multiple foot types. For example... Figure 13 As shown in (C), the average values ​​calculated for each of the multiple foot types are included as data B1 to B9 in the unloaded foot type data 134.

[0090] Therefore, the designer of the prediction device 1 classifies homologous models created based on measurement data of the shape of sample feet obtained using plaster casts, according to different types, based on at least one feature (in this example, the arch height-to-foot-length ratio and the heel tilt angle). The classified homologous models are then modified according to the baseline foot length and orthogonal foot width. An average value is calculated based on the modified homologous models, thereby acquiring sample data under no-load conditions for each of the multiple foot type types. The acquired sample data under no-load conditions is pre-stored in memory 13 as no-load foot type data 134 (second sample data). That is, the no-load foot type data 134 (second sample data) stored in memory 13 contains average foot shape data under no-load conditions for each of the multiple foot type types.

[0091] [Prediction of the shape of the subject's feet]

[0092] While referring to Figures 14-16 The description then goes on to explain the predictive processing of the shape of the subject's foot in an unloaded state by the predictive device 1. Figure 14 This is a flowchart illustrating the prediction process performed by the prediction device 1 in the embodiment. Figure 15 It is a graph used to illustrate the calculation of the difference between the data of the subjects and the data of the first sample. Figure 16 This is a graph used to illustrate the changes in the second sample data based on the differences. Figure 14 Each step shown (hereinafter referred to as "S") is implemented by the processor 11 of the prediction device 1 executing the prediction program 131.

[0093] like Figure 14 As shown, the prediction device 1 acquires subject data, which includes measurement data of the subject's foot shape under load acquired by the measurement device 2 (S1). The prediction device 1 then creates a prediction device based on the subject data. Figure 7The model shown is a homologous model, and feature quantities (arch height to foot length ratio and heel inclination angle in this example) are extracted from the subject's data (S2). The prediction device 1 selects the foot type of the subject's foot based on the feature quantities of the subject's data (S3). For example, the prediction device 1 classifies the foot type based on the arch type and heel inclination type of the subject's foot. Figure 11A Choose one of the foot types shown.

[0094] The prediction device 1 extracts first sample data (S4) from the load foot type data 133 stored in the memory 13, which corresponds to the foot type of the subject selected in S3 under load conditions. The extracted first sample data includes average foot shape data (homogeneous model) under load conditions that correspond to the foot type of the subject.

[0095] Then, the prediction device 1 extracts second sample data (S5) from the unloaded foot shape data 134 stored in the memory 13, which matches the foot shape type of the subject selected in S3 under the unloaded state. The extracted second sample data contains the average foot shape data (homogeneous model) under the unloaded state that matches the foot shape type of the subject.

[0096] The prediction device 1 makes the leg length and orthogonal leg width of the first sample data under the load condition extracted in S4 consistent with the leg length and orthogonal leg width of the homologous model made based on the subject data (S6). As a result, the curve of the average leg under the load condition corresponding to the first sample data changes according to the leg length and orthogonal leg width of the subject.

[0097] Furthermore, the prediction device 1 makes the leg length and orthogonal leg width of the second sample data under no-load conditions extracted in S5 consistent with the leg length and orthogonal leg width of the homologous model made based on the subject data (S7). As a result, the curve of the average leg under no-load conditions corresponding to the second sample data changes according to the subject's leg length and orthogonal leg width.

[0098] The prediction device 1 calculates the foot curve based on the subject data and the data of the first sample data that are modified in S6. It compares the foot curve in the subject data with the foot curve under the load state corresponding to the first sample data that is modified in S6, and calculates the difference between the two (S8).

[0099] Specifically, such as Figure 15 As shown, the prediction device 1 compares the curve of the foot in the subject data represented by the solid line with the curve of the foot under the load state corresponding to the first sample data represented by the dashed line, thereby calculating the difference between the two curves in the foot length direction.

[0100] Here, the foot curves of the first sample data under load and the foot curves of the subject's data can be calculated separately based on the foot shape acquired by the measuring device 2. Specifically, as follows... Figure 2A as well as Figure 2B As shown, even under load, the outline, inner ground contact line, and outer ground contact line can be identified. Therefore, if used... Figure 4 As explained, the foot curves of the first sample data under load and the foot curves of the subject's data can be calculated based on the contour line, the inner contact line, and the outer contact line. Alternatively, the foot curve of the first sample data can also be derived from the foot curve of the second sample data under no-load conditions. For example, it can also be derived using... Figure 4 as well as Figure 5 As explained, the inner and outer ground contact lines are calculated using the intersection of line L at a height of H mm from the lowest line and the inner or outer shape of the foot. The calculated inner and outer ground contact lines are then used to calculate the curve of the foot in the second sample data, and the calculated curve is used as the curve of the foot in the first sample data.

[0101] The prediction device 1 modifies the degree of foot bending (curve) in the unloaded state corresponding to the second sample data in S6 based on the difference in the calculated curve, thereby calculating the shape of the subject's foot (homogeneous model) in the unloaded state (S9). Then, the prediction device 1 ends the process.

[0102] Specifically, such as Figure 16 As shown, the prediction device 1 moves a plurality of structural points in the second sample data, arranged along the shape of the foot's cross-section, in a direction that cancels out the difference calculated in S8. That is, the prediction device 1 moves the plurality of structural points in the second sample data, arranged along the shape of the foot's cross-section, so that the curve of the foot in the second sample data matches the curve of the foot in the subject's data. The prediction device 1 performs this movement of the plurality of structural points at predetermined intervals (e.g., every 1 mm) along the length of the foot.

[0103] Therefore, the prediction device 1 can calculate the shape data of the subject's foot under no-load conditions (homogeneous model) based on the measurement data of the subject's foot shape under load conditions obtained by the measuring device 2.

[0104] [Making Insoles]

[0105] While referring to Figure 17 This illustrates an example of how insoles are made. Figure 17 This is an illustration of an example of how insoles are made. Figure 17 The diagram shows the prediction device 1 through... Figure 14A cross section of a homologous model of the shape of the subject's foot under no-load conditions, obtained through predictive processing. Figure 17 In, with Figure 5 Similarly, set a portion of the top line points on the inner side of the same model as P1, set a portion of the top line points on the outer side of the same model as P2, set the tangent point between the inner b-degree line and the inner shape of the same model as Q1, and set the tangent point between the outer b-degree line and the outer shape of the same model as Q2.

[0106] The insole designer measures the length T1 of the tangent point Q1 relative to the bottom surface of the insole, adds the support adjustment amount T2 to the length T1, and obtains point U. The designer connects point P1, point U, the lowest point V of the same model on the inner top line, and point P2 on the outer top line of the same model with a line, thereby obtaining the surface shape of the insole on a cross section of the same model. The designer performs this operation for each of multiple cross sections along the foot length direction, thus enabling the fabrication of the insole.

[0107] [Variation Example]

[0108] This disclosure is not limited to the embodiments described, and various modifications and applications are possible. The following describes modifications applicable to this disclosure.

[0109] In the prediction process, the prediction device 1 of the embodiment uses, for example, Figure 1 As shown, the measurement data of the shape of the feet of the subject in a standing position, and as shown... Figure 10 The first sample data is calculated based on measurement data of the shape of the feet of the sample subject in a standing position, as shown in (A) to (C), but is not limited to using such data measured in a standing position to perform predictive processing.

[0110] For example, the prediction device 1 may also use measurement data of the shape of the feet of the subject in a seated position and first sample data calculated based on the measurement data of the shape of the feet of the sample subject in a seated position to perform prediction processing.

[0111] In the prediction device 1 of the embodiment, as at least one feature quantity, the subject data, the first sample data and the second sample data are classified based on the arch height-to-foot length ratio and the heel tilt angle, but it is not limited to classifying the data based on the arch height-to-foot length ratio and the heel tilt angle.

[0112] For example, in the prediction device 1, as at least one feature, the subject data, the first sample data, and the second sample data can be classified based on at least one of the following: arch height-to-length ratio, heel tilt angle, foot circumference, degree of foot flexion (curve), toe shape, and age. These features are all parameters that may affect the shape of the foot, and by using any one of these features, the prediction device 1 can classify the subject data, the first sample data, and the second sample data with high accuracy.

[0113] In the prediction system 100 of the embodiment, the prediction device 1 can be installed in a shop where the measuring device 2 is installed, or it can exist as a server device in the cloud. Furthermore, the prediction device 1, which exists as a server device in the cloud, can also be communicatively connected to the measuring devices 2 installed in multiple shops, and predict the shape of the feet of each subject in an unloaded state based on the subject data obtained from each measuring device 2.

[0114] In S6, the prediction device 1 of the embodiment makes the leg length and orthogonal leg width of the first sample data under load conditions consistent with the leg length and orthogonal leg width of the homologous model made based on the subject data, and in S7, makes the leg length and orthogonal leg width of the second sample data under unload conditions consistent with the leg length and orthogonal leg width of the homologous model made based on the subject data, but the consistent items may be other than leg length and orthogonal leg width.

[0115] For example, in S6, the prediction device 1 may make the foot length and orthogonal foot width of the first sample data under load consistent with the foot length and orthogonal foot width of the homologous model made based on the subject data, and then correct the modified first sample data based on the apparent arch length of the homologous model in the subject data. Furthermore, in S7, the prediction device 1 may make the foot length and orthogonal foot width of the second sample data under no-load consistent with the foot length and orthogonal foot width of the subject data, and then correct the modified second sample data based on the apparent arch length of the homologous model in the subject data.

[0116] For example, Figures 18A-18C This is a graph used to illustrate changes in sample data based on appearance of the foot arch. For example... Figure 18A As shown, in the cross-section of the foot, the point of tangency between the line inclined at degree 'a' from the ground towards the inside of the foot (the inside 'a' degree line) and the outer shape of the inside of the foot is designated as P1. Figure 18B As shown, tangent points P1 are obtained at specified intervals (e.g., every 1 mm) along the length of the foot. The line connecting the obtained tangent points P1 is defined as the apparent arch of the foot. Furthermore, the length between the end point of the apparent arch of the foot and the heel point is defined as the length of the apparent arch of the foot.

[0117] In step S6, the prediction device 1 matches the foot length and orthogonal foot width of the first sample data under load with the foot length and orthogonal foot width of the homologous model created based on the subject's data. Therefore, it modifies the average foot curve under load corresponding to the first sample data based on the subject's foot length and orthogonal foot width. Furthermore, the prediction device 1 matches the apparent arch length in the modified first sample data with the apparent arch length of the homologous model in the subject's data, thereby correcting the foot curve in the first sample data.

[0118] Furthermore, in S7, the prediction device 1 aligns the foot length and orthogonal foot width of the second sample data under no-load conditions with the foot length and orthogonal foot width of the homologous model created based on the subject's data. This alters the average foot curve under no-load conditions corresponding to the second sample data based on the subject's foot length and orthogonal foot width. Further, the prediction device 1 aligns the apparent arch length in the altered second sample data with the apparent arch length of the homologous model in the subject's data, thereby correcting the foot curve in the second sample data.

[0119] By performing this correction, the prediction device 1 is able to... Figure 18C As shown, the leg length of the sample data before correction (represented by dashed lines) is adjusted to the leg length of the sample data after correction (represented by solid lines). Subsequently, the prediction device 1 only needs to execute the processing after S8.

[0120] [Summarize]

[0121] like Figure 8 As shown, the prediction device 1 includes: a communication device 16 for acquiring subject data, the subject data including measurement data of the shape of the subject's feet under load; a storage device 13 for storing first sample data under load and second sample data under unload, calculated based on the same multiple sample foot shape measurement data under both load and unload conditions; and a processor 11 for predicting the shape of the subject's feet under unload conditions. Figure 14 As shown, the processor 11 calculates the difference between the subject's data and the first sample data (S8), and predicts the shape of the subject's foot under no-load conditions based on the difference and the second sample data (S9).

[0122] Therefore, by using first sample data under load and second sample data under no-load conditions, the prediction device 1 can predict the shape of the subject's foot under no-load conditions based on the measurement data of the subject's foot shape under load conditions. Thus, the user of the prediction device 1 can easily obtain the shape of the subject's foot under no-load conditions simply by measuring the shape of the subject's foot under load conditions.

[0123] like Figure 10 As shown in (A) to (C), the first sample data is data obtained by classifying the measurement data of the shape of multiple sample feet under load conditions according to each type of multiple foot type, based on at least one feature quantity related to the shape of the foot. Figure 13 As shown in (A) to (C), the second sample data is data obtained by classifying the measurement data of the shape of multiple sample feet under no-load conditions according to each of multiple foot type types based on at least one feature quantity. Figure 14 As shown, the processor 11 selects one foot type from multiple foot type types based on the subject's data (S3), calculates the difference between the subject's data and the first sample data belonging to a foot type (S8), and predicts the shape of the subject's foot under no-load conditions based on the difference and the second sample data belonging to a foot type (S9).

[0124] Therefore, the prediction device 1 can use first sample data and second sample data that correspond to the foot shape type of the subject under load to predict the shape of the subject's foot under no-load conditions. Thus, the prediction device 1 can improve the prediction accuracy of the shape of the subject's foot under no-load conditions.

[0125] like Figure 10 As shown in (A) to (C), the first sample data is obtained by averaging the measurement data of the shape of multiple sample feet under load conditions for each of the multiple foot types. Figure 13 As shown in (A) to (C), the second sample data is obtained by averaging the measurement data of the shape of multiple sample feet under no-load conditions for each of the multiple foot types.

[0126] Therefore, the prediction device 1 can use averaged first sample data and second sample data that correspond to the foot shape type of the subject under load to predict the shape of the subject's foot under no-load conditions. Thus, the prediction device 1 does not need to store large amounts of first and second sample data, thereby suppressing the increase in storage capacity consumption of the memory 13.

[0127] like Figure 14As shown, the processor 11 changes the length and width of the feet in the first sample data belonging to a foot type based on the length and width of the feet in the subject data, thereby calculating the changed first sample data (S6). Based on the length and width of the feet in the second sample data belonging to a foot type based on the length and width of the feet in the subject data, the processor 11 changes the length and width of the feet in the second sample data belonging to a foot type, thereby calculating the changed second sample data (S7). By comparing the degree of curvature of the feet in the subject data with the degree of curvature of the feet in the changed first sample data, the processor 11 calculates the difference (S8). Based on the difference, the processor 11 changes the degree of curvature of the feet in the changed second sample data, thereby predicting the shape of the subject's feet under no-load conditions (S9).

[0128] Therefore, the prediction device 1 modifies the length and width of the feet in the first and second sample data according to the length and width of the feet contained in the subject's data, and then modifies the degree of curvature of the feet in the second sample data to match the degree of curvature of the feet contained in the subject's data. Thus, it can predict the shape of the subject's feet under no-load conditions. Therefore, the prediction device 1 can further improve the prediction accuracy of the shape of the subject's feet under no-load conditions.

[0129] like Figures 18A-18C As shown, the processor 11 corrects the modified first sample data based on the length of the lateral arch (apparent arch) of the foot contained in the subject data, and corrects the modified second sample data based on the length of the lateral arch (apparent arch) of the foot contained in the subject data.

[0130] Therefore, the prediction device 1 corrects the first and second sample data based on the apparent arch length of the foot contained in the subject's data, thus making the first and second sample data closer to the foot in the subject's data. Therefore, the prediction device 1 can further improve the prediction accuracy of the subject's foot shape under no-load conditions.

[0131] At least one characteristic quantity includes any one of the following: arch height to foot length ratio, heel inclination angle, foot circumference, foot flexion, toe shape, and age.

[0132] Therefore, the prediction device 1 can classify the subject data, the first sample data, and the second sample data based on any one of the following: arch height-to-foot length ratio, heel inclination angle, foot circumference, foot flexion, toe shape, and age. Furthermore, by increasing the number of features used for classification, the prediction device 1 can classify the subject data, the first sample data, and the second sample data in greater detail.

[0133] like Figure 1As shown, the subject data includes measurements of the shape of the subject's feet in a standing position. Figure 10 As shown in (A) to (C), the first sample data is calculated based on the measurement data of the shape of multiple sample feet measured by multiple sample subjects in a standing posture.

[0134] Therefore, the user of the prediction device 1 can easily obtain the shape of the subject's feet in an unloaded state simply by measuring the feet of the person visiting the store while they are standing. Thus, it is not necessary for an experienced technician to measure the shape of the subject's feet, improving convenience in the store.

[0135] The method for predicting the shape of a subject's foot under no-load conditions, performed by processor 11, includes the following steps: acquiring subject data, which includes measurement data of the subject's foot shape under load conditions; storing first sample data under load conditions and second sample data under no-load conditions calculated from the same multiple sample foot shape measurement data under both load and no-load conditions; and predicting the shape of the subject's foot under no-load conditions. Figure 14 As shown, the steps for making the prediction include: step (S8), calculating the difference between the subject's data and the first sample data; and step (S9), predicting the shape of the subject's foot under no-load conditions based on the difference and the second sample data.

[0136] Therefore, by using first sample data under load and second sample data under no-load conditions, the prediction device 1 can predict the shape of the subject's foot under no-load conditions based on the measurement data of the subject's foot shape under load conditions. Thus, the user of the prediction device 1 can easily obtain the shape of the subject's foot under no-load conditions simply by measuring the shape of the subject's foot under load conditions.

[0137] like Figure 1 As shown, the prediction system 100 includes: a measuring device 2 for measuring the shape of the subject's foot under load; and a prediction device 1 for predicting the shape of the subject's foot under no-load conditions. Figure 8 As shown, the prediction device 1 includes: a communication device 16 for acquiring subject data from the measuring device 2, the subject data including measurement data of the shape of the subject's feet under load; a storage device 13 for storing first sample data under load and second sample data under unload, calculated based on the same multiple sample foot shape measurement data under both load and unload conditions; and a processor 11 for predicting the shape of the subject's feet under unload conditions. Figure 14As shown, the processor 11 calculates the difference between the subject's data and the first sample data (S8), and predicts the shape of the subject's foot under no-load conditions based on the difference and the second sample data (S9).

[0138] Therefore, by using first sample data under load and second sample data under no-load conditions, the prediction system 100 can predict the shape of the subject's foot under no-load conditions based on the measurement data of the subject's foot shape under load conditions. Thus, the user of the prediction system 100 can easily obtain the shape of the subject's foot under no-load conditions by measuring the shape of the subject's foot under load conditions using the prediction device 1.

[0139] Embodiments of this disclosure have been described, but should be considered as illustrative in all respects and not as limiting. The scope of this disclosure is defined by the claims and is intended to include all modifications equivalent to and within the scope of the claims.

Claims

1. A predictive device for predicting the shape of a subject's foot under no-load conditions, the predictive device comprising: The acquisition unit acquires subject data, which includes measurement data of the shape of the subject's feet under load. The storage unit stores first sample data under the load state and second sample data under the unload state, calculated based on measurement data of the shape of the same multiple sample feet under the load state and the unload state. as well as The prediction unit predicts the shape of the subject's foot under the unloaded state. The prediction unit calculates the difference between the subject's data and the first sample data, and predicts the shape of the subject's foot in the unloaded state based on the difference and the second sample data.

2. The prediction device according to claim 1, wherein The first sample data is data obtained by classifying the measurement data of the shape of the plurality of sample feet under the load state according to each of the plurality of foot type types based on at least one feature quantity related to the shape of the foot. The second sample data is data obtained by classifying the measurement data of the shape of the plurality of sample feet under the no-load state according to each of the plurality of foot type types based on the at least one feature quantity. The prediction unit selects one foot type from the plurality of foot type types based on the subject's data. The prediction unit calculates the difference between the subject's data and the first sample data belonging to the foot type. The prediction unit predicts the shape of the subject's foot in the unloaded state based on the difference and the second sample data belonging to the foot type.

3. The prediction device according to claim 2, wherein The first sample data is obtained by averaging the measurement data of the shape of the multiple sample feet under the load state according to each of the multiple foot type types. The second sample data is obtained by averaging the measurement data of the shape of the multiple sample feet in the unloaded state according to each of the multiple foot type types.

4. The prediction device according to claim 3, wherein The prediction unit modifies the length and width of the feet in the first sample data belonging to the specified foot type based on the foot length and width contained in the subject's data, thereby calculating the modified first sample data. The prediction unit modifies the length and width of the feet in the second sample data belonging to the same foot type based on the foot length and width contained in the subject's data, thereby calculating the modified second sample data. The prediction unit compares the degree of foot curvature in the subject's data with the degree of foot curvature in the modified first sample data to calculate the difference. The prediction unit modifies the degree of foot curvature contained in the modified second sample data based on the difference, thereby predicting the shape of the subject's foot in the unloaded state.

5. The prediction device according to claim 4, wherein The prediction unit corrects the modified first sample data based on the length of the arch of the foot on the lateral side, which is included in the data of the subject. The prediction unit corrects the modified second sample data based on the length of the arch of the foot on the side of the foot included in the data of the subject.

6. The prediction device according to any one of claims 2 to 5, wherein The at least one characteristic includes any one of the following: arch height to foot length ratio, heel inclination angle, foot circumference, foot flexion, toe shape, and age.

7. The prediction device according to any one of claims 1 to 5, wherein The subject data includes measurement data of the shape of the subject's feet in a standing position. The first sample data is calculated based on measurement data of the shape of the feet of the multiple sample subjects in the standing posture.

8. A prediction method, performed by a computer, for predicting the shape of a subject's foot in a no-load state, the prediction method comprising the following steps: Acquire subject data, which includes measurement data of the shape of the subject's feet under load conditions; The data stored in the loaded state and the unloaded state are calculated based on measurement data of the shape of the same multiple sample feet. The first sample data in the loaded state and the second sample data in the unloaded state are stored in the loaded state and the unloaded state. as well as Predict the shape of the subject's foot under the no-load condition. The step of predicting the shape of the subject's foot under the no-load state includes the following steps: Calculate the difference between the data of the subject and the data of the first sample; as well as Based on the difference and the second sample data, the shape of the subject's foot in the unloaded state is predicted.

9. A prediction system for predicting the shape of a subject's foot under no-load conditions, the prediction system comprising: A measuring device for measuring the shape of the subject's feet under load; as well as The predictive device predicts the shape of the subject's foot in the unloaded state. The prediction device includes: The acquisition unit acquires subject data from the measuring device, the subject data including measurement data of the shape of the subject's feet under the load state; The storage unit stores first sample data under the load state and second sample data under the unload state, calculated based on measurement data of the shapes of the same multiple sample feet under the load state and the unload state; and The prediction unit predicts the shape of the subject's foot under the unloaded state. The prediction unit calculates the difference between the subject's data and the first sample data, and predicts the shape of the subject's foot in the unloaded state based on the difference and the second sample data.

Images