Footwear recommendation method and information processing device

Abstract

This method for recommending footwear of a size and structure suitable for a user by means of a computer comprises: acquiring foot shape data on the user (S506); acquiring product purchase data on the user (S510); estimating the level of activity of the user on the basis of the purchase data (S512); determining footwear of a size and structure suitable for the user on the basis of the foot shape data and the level of activity (S514); and recommending at least one footwear of the size and structure suitable for the user (S516).

Description

Method for Recommending Footwear and Information Processing Apparatus

[0001] The present disclosure relates to a method for recommending footwear and an information processing apparatus used therefor.

[0002] In recent years, in response to the desire of users to purchase footwear that fits the size and purpose of their feet, techniques for recommending footwear based on information such as scan data of the users' feet have been proposed. For example, methods for recommending footwear that fits the users' feet and desires based on information such as scan data of the users' feet, the users' preferences, the users' age, and the users' physique have been proposed.

[0003] One aspect of the present disclosure is a method for recommending footwear having a size and structure suitable for a user by a computer, the method comprising: obtaining foot shape data of the user; obtaining purchase data of products of the user; estimating a level of activity of the user based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the level of activity; and recommending at least one footwear having a size and structure suitable for the user.

[0004] Another aspect of the present disclosure is an information processing apparatus for recommending footwear having a size and structure suitable for a user, the apparatus performing: obtaining foot shape data of the user; obtaining purchase data of products of the user; estimating a level of activity of the user based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the level of activity; and recommending at least one footwear having a size and structure suitable for the user.

[0005] Figure 1 is a system overview diagram showing a footwear recommendation system according to an embodiment of this disclosure. Figure 2 is a functional block diagram of a footwear recommendation device according to an embodiment of this disclosure. Figure 3 is a functional block diagram of a user terminal according to an embodiment of this disclosure. Figure 4 is a diagram showing an example of hardware configuration of a footwear recommendation device, etc., according to an embodiment of this disclosure. Figure 5 is a diagram showing the sequence of footwear recommendation processing performed by the footwear recommendation system according to an embodiment of this disclosure. Figure 6 is a diagram showing the sequence of footwear recommendation processing performed by the footwear recommendation system according to an embodiment of this disclosure. Figure 7 is a diagram showing the sequence of footwear recommendation processing performed by the footwear recommendation system according to an embodiment of this disclosure. Figure 8 is a diagram showing an example of the display screen of a user terminal according to an embodiment of this disclosure. Figure 9 is a functional block diagram of a pronation type estimation device according to an embodiment of this disclosure. Figure 10 is a tree diagram schematically showing the decision tree analysis results of pronation estimation in this embodiment. Figure 11 is a flowchart showing the process of pronation estimation processing using the pronation estimation algorithm according to this embodiment. Figure 12 is a diagram showing the sequence of footwear recommendation processing performed by the footwear recommendation system according to an embodiment of this disclosure. Figure 13 is a flowchart of the footwear recommendation method according to the embodiment of the present disclosure. Figure 14 is a flowchart of the footwear recommendation method according to the embodiment of the present disclosure.

[0006] Embodiments of the present invention will be described below with reference to the accompanying drawings. The embodiments described below are merely examples of how to implement the present invention and are not intended to limit the scope of the invention. Furthermore, to facilitate understanding of the explanation, the same reference numerals are used for identical components in each drawing whenever possible, and redundant explanations may be omitted.

[0007] A method for recommending footwear according to the embodiments of this disclosure is a method for recommending footwear having a size and structure suitable for a user using a computer, comprising: acquiring the user's foot shape data; acquiring the user's product purchase data; estimating the user's activity level based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the activity level; and recommending at least one pair of footwear having a size and structure suitable for the user.

[0008] [Configuration of the Footwear Recommendation System] Figure 1 is a schematic diagram of a footwear recommendation system 10 that performs the footwear recommendation method according to the embodiment of this disclosure. As shown in Figure 1, the footwear recommendation system 10 includes a footwear recommendation device 100 and a user terminal 200.

[0009] In this embodiment, the user using the user terminal 200 may be, for example, a user considering purchasing footwear and wishing to receive recommendations for footwear. Furthermore, the footwear recommendation method according to this embodiment can be applied to the process of recommending footwear used for exercise activities such as running. Examples of exercise activities include running, jogging, walking, cycling, and skateboarding, as well as ball games such as soccer and tennis. It can also be applied to recommending footwear used for purposes other than exercise, such as fashion.

[0010] In the footwear recommendation system according to this embodiment, the footwear recommendation system 10 may, for example, capture an image showing the shape of the user's foot using a user terminal 200. Furthermore, the footwear recommendation system 10 of this embodiment may further include a device 500 for capturing images of the foot, such as a three-dimensional foot shape measuring instrument. In addition, the footwear recommendation system 10 of this embodiment may further include, for example, a database 300.

[0011] The footwear recommendation device 100 is, for example, a server device, and is configured to exchange data with the user terminal 200 via a network NE such as the Internet.

[0012] Specifically, the footwear recommendation device 100 acquires foot shape data from, for example, a user terminal 200. It also acquires the user's footwear purchase data from, for example, a database 300. Based on the acquired purchase data, the footwear recommendation device 100 estimates the user's activity level. Based on the foot shape data and the activity level, the footwear recommendation device 100 determines footwear with a size and structure suitable for the user and recommends at least one pair of footwear with a size and structure suitable for the user.

[0013] The footwear recommendation device 100 may obtain the data used for these processes by accessing one or more databases 300 (databases 300-1, 300-2, ..., 300-n (where n is a natural number)) located outside the footwear recommendation device 100, as described above, or the footwear recommendation device 100 may have a database in which the data used for these processes is stored. The detailed configuration of the footwear recommendation device 100 will be described later. Note that the network NE here can utilize various networks such as WAN (Wide Area Network), LAN (Local Area Network), and short-range wireless communication.

[0014] The user terminal 200 is configured, for example, to capture an image of the user's feet and transmit it to the footwear recommendation device 100. The user terminal 200 may also be configured to output recommended footwear that has a size and structure suitable for the user, as determined by the footwear recommendation device 100. As shown in Figure 1, the footwear recommendation system 10 according to this embodiment illustrated in Figure 1 may have a plurality of user terminals 200-1, 200-2, 200-3, ..., 200-m (where m is a natural number). Hereinafter, any user terminal among user terminals 200-1 to 200-m will also be referred to as user terminal 200.

[0015] The user terminal 200 may be, for example, a portable information terminal such as a smartphone or tablet, or a personal computer. The user terminal 200 may be composed of a combination of hardware such as a camera module, a distance sensor, a microprocessor, a touch panel, memory, and a communication module. The user terminal 200 may be the information processing terminal of the person whose foot shape is being measured, or it may be a general-purpose information processing terminal such as a smartphone or tablet provided by a shoe store or the like. In addition, the user terminal 200 may access a website provided by the footwear recommendation device 100 via a web browser, or information provided by the footwear recommendation device 100 may be output via screen display or the like by application software running on the user terminal 200.

[0016] In this embodiment, the footwear recommendation system 10 performs footwear recommendation processing. For example, for a user who is considering purchasing footwear and wishes to receive recommendations, the system can determine footwear with a size and structure that suits the user based on the user's foot shape acquired via a user terminal 200, etc., and the activity level estimated based on the user's purchase data. As a result, the user is recommended footwear with a size and structure that takes into account the user's own physical data and the activities they perform, thus improving the accuracy of footwear recommendations.

[0017] [Configuration of the Footwear Recommendation Device] Figure 2 is a functional block diagram showing the functions of the footwear recommendation device 100 according to the embodiment of this disclosure. As shown in Figure 2, the footwear recommendation device 100 includes a foot shape data acquisition unit 110, a purchase data acquisition unit 120, an activity level estimation unit 130, a footwear determination unit 140, and a footwear recommendation unit 150. Furthermore, as shown in Figure 2, the footwear recommendation device 100 may also include a usage estimation unit 160, a questionnaire data acquisition unit 162, a positional relationship estimation unit 164, a foot shape data correction unit 166, a questionnaire screen display unit 168, a footwear image acquisition unit 170, a footwear image comparison unit 172, a wear position calculation unit 174, a wear amount calculation unit 176, a usage state estimation unit 178, a feature quantity extraction unit 180, a pronation type estimation unit 182, a stiffness information acquisition unit 184, a predicted deformation amount calculation unit 186, a deformation judgment unit 187, a stiffness calculation unit 188, and a storage unit 190.

[0018] When the footwear recommendation device 100 is implemented using the computer 400 (see Figure 4) described later, the foot shape data acquisition unit 110, the purchase data acquisition unit 120, the activity level estimation unit 130, the footwear determination unit 140, and the footwear recommendation unit 150 can be implemented, for example, by the processor 401 of the computer 400 described later in the footwear recommendation device 100 executing a program stored in the storage device 403 of the computer 400. Furthermore, when the footwear recommendation device 100 is implemented using the computer 400 (see Figure 4), the storage unit 190 can be implemented, for example, using the storage device 403 of the computer 400 described later.

[0019] Similarly, if the footwear recommendation device 100 further includes all or part of the following: application estimation unit 160, questionnaire data acquisition unit 162, position relationship estimation unit 164, foot shape data correction unit 166, questionnaire screen display unit 168, footwear image acquisition unit 170, footwear image comparison unit 172, wear position calculation unit 174, wear amount calculation unit 176, usage state estimation unit 178, feature quantity extraction unit 180, pronation type estimation unit 182, stiffness information acquisition unit 184, predicted deformation amount calculation unit 186, deformation judgment unit 187, and stiffness calculation unit 188, then the application estimation unit 160 and the questionnaire data acquisition unit 162 are included. All or part of the following can be realized, for example, by the processor 401 of the computer 400 of the footwear recommendation device 100 executing a program stored in the storage device 403: the position relationship estimation unit 164, the foot shape data correction unit 166, the questionnaire screen display unit 168, the footwear image acquisition unit 170, the footwear image comparison unit 172, the wear position calculation unit 174, the wear amount calculation unit 176, the usage state estimation unit 178, the feature quantity extraction unit 180, the pronation type estimation unit 182, the stiffness information acquisition unit 184, the predicted deformation amount calculation unit 186, the deformation judgment unit 187, and the stiffness calculation unit 188.

[0020] The program may be stored on a storage medium. The storage medium on which the program is stored may be a non-transitory computer-readable medium. The non-transitory storage medium is not particularly limited, but may be, for example, a USB memory stick or a CD-ROM.

[0021] The foot shape data acquisition unit 110 acquires information about the user's foot shape. The user may, for example, use a user terminal 200, such as a mobile phone terminal with a built-in image sensor, to capture an image of their foot and transmit it to the footwear recommendation device 100 as information about their foot shape, which will then be acquired by the foot shape data acquisition unit 110 of the footwear recommendation device 100. If the user terminal 200 has a three-dimensional scanner function using technology such as LiDAR (Light Detection And Ranging), it may scan around the foot to generate a three-dimensional model of the foot shape and transmit it to the footwear recommendation device 100. Even if the user terminal 200 does not have a three-dimensional scanner function using LiDAR or the like, it may generate a three-dimensional model of the foot shape by image synthesis processing such as photogrammetry and transmit it to the footwear recommendation device 100. Alternatively, for example, the user being measured may place their feet on a dedicated measurement mat or the like, scan their foot shape using the camera function and foot shape acquisition application of the user terminal 200, generate a three-dimensional model of the foot shape, and transmit it to the footwear recommendation device 100.

[0022] Furthermore, in this embodiment, for example, a foot image capture device 500 such as a three-dimensional foot shape measuring device may be used, and foot shape data may be generated based on the foot image captured by the foot image capture device and transmitted to the footwear recommendation device 100. The foot image capture device 500 may be configured to generate three-dimensional data of the foot shape by laser measurement, for example.

[0023] In this embodiment, the foot shape data acquired by the foot shape data acquisition unit 110 may include, for example, data on the shape of the outer surface of the foot, the shape of the top surface of the foot, the shape of the side of the foot, the shape of the sole of the foot, and at least one data on foot pressure. Furthermore, the foot shape data acquired by the foot shape data acquisition unit 110 may include, for example, three-dimensional shape data of the user's foot as described above, or two-dimensional shape data, or both three-dimensional and two-dimensional shape data. In addition, the user's foot shape data may include data on the shape of the sole of the footwear used by the user. In this embodiment, the foot shape data acquired by the foot shape data acquisition unit 110 may be configured to be stored in a database such as, for example, a foot shape database 300-1 (see Figure 1).

[0024] The purchase data acquisition unit 120 is configured to acquire data about footwear purchased by a user who is considering purchasing footwear. The data about footwear purchased by the user may include information such as the store where it was purchased, the date of purchase, the manufacturer, the product number, and the size. For footwear purchased online by the user, the purchase data may also include information about the website where it was purchased.

[0025] The purchase data acquisition unit 120 may be configured to acquire user purchase data from, for example, a database owned by a footwear retailer. Alternatively, the footwear recommendation system 10 according to this embodiment may have a database such as a purchase database 300-2 (see Figure 1), and the purchase data acquisition unit 120 may be configured to acquire purchase data from the purchase database 300-2. Or, the purchase data acquisition unit 120 may acquire user purchase data by receiving it from a user terminal 200, for example. In this case, the purchase data acquired by the purchase data acquisition unit 120 may be configured to be stored in the purchase database 300-2.

[0026] The activity level estimation unit 130 is configured to estimate the user's activity level based on purchase data about the user acquired by the purchase data acquisition unit 120, for example. The activity level estimation unit 130 may also be configured to further estimate information such as the intensity of running performed by the user, the activity being performed, and the intensity level of the activity being performed, based on information such as the user's purchase history.

[0027] The footwear determination unit 140 is configured to determine footwear with a size and structure suitable for the target user, based on foot shape data acquired by the foot shape data acquisition unit 110 and the activity level estimated by the activity level estimation unit 130. The footwear determination unit 140 may, for example, determine footwear with a size (for example, a sole shape and size suitable for high-intensity running) and structure suitable for the activity performed by the user, based on foot characteristics such as foot length, foot width, arch height, toe shape, pronation type, heel width, and heel shape, as well as activity level data such as the type and intensity of the activity that the user is estimated to perform. The footwear determination unit 140 may determine one pair of footwear with a size and structure suitable for the user, or if there are multiple candidates for footwear with a size and structure suitable for the user, it may determine multiple pairs of footwear with a size and structure suitable for the user.

[0028] The footwear recommendation unit 150 is configured to recommend footwear that has a size and structure suitable for the user, as determined by the footwear determination unit 140. The footwear recommendation unit 150 may be configured to recommend footwear that has a size and structure suitable for the user to the user terminal 200 by, for example, transmitting the footwear that has a size and structure suitable for the user to the user terminal 200 so that it is output by display or other means on the user terminal 200. In addition, when the footwear recommendation unit 150 determines multiple footwear that has a size and structure suitable for the user as described above, the footwear recommendation unit 150 may be configured to recommend multiple footwear that has a size and structure suitable for the user to the user. Furthermore, in this embodiment, the footwear recommendation unit 150 may recommend footwear that includes, for example, information about the product number and brand of the footwear recommended to the user. Furthermore, if the footwear recommendation unit 150 can recommend multiple brands or models of footwear, it may be configured to recommend the same or different sizes and structures for each brand, series, or model.

[0029] As described above, the footwear recommendation device 100 may include, as shown in Figure 2, a usage estimation unit 160, a questionnaire data acquisition unit 162, a positional relationship estimation unit 164, a foot shape data correction unit 166, a questionnaire screen display unit 168, a footwear image acquisition unit 170, a footwear image comparison unit 172, a wear position calculation unit 174, a wear amount calculation unit 176, a usage state estimation unit 178, a feature quantity extraction unit 180, a pronation type estimation unit 182, a stiffness information acquisition unit 184, a predicted deformation amount calculation unit 186, a deformation judgment unit 187, a stiffness calculation unit 188, and a storage unit 190. The usage estimation unit 160 may be configured to estimate the user's intended use of footwear based on information such as purchase data. In the footwear recommendation device 100 according to this embodiment, as will be described later, for example, a provider of multiple pairs of footwear may be configured to estimate the intended use of the footwear based on the output result when the purchase data of the user for whom footwear recommendation is to be performed is input to a pre-trained model generated by machine learning using as training data information, which is pre-set for each of the multiple pairs of footwear by a provider of multiple pairs of footwear, the purchase data of multiple other users other than the user, and the activity history information (e.g., activity history such as running) of each of the multiple other users. This model may be configured to estimate the intended use of the footwear in addition to, or instead of, the user's activity level.

[0030] Furthermore, the survey data acquisition unit 162 may be configured to acquire survey data, including the content of responses entered by the user to survey items shown to the user, for example, by displaying them on a display unit. In the footwear recommendation system 10 according to this embodiment, for example, a survey template including operation input fields may be displayed on the display unit of the user terminal 200, and the user may perform operation input on the operation input fields to perform an answer to the survey, and the survey data acquisition unit 162 of the footwear recommendation device 100 may acquire the survey data when the answers to the survey entered by the user are transmitted to the footwear recommendation device 100. Alternatively, the footwear recommendation system 10 may include a survey database 300-3 in which survey data is pre-stored, and the survey data acquisition unit 162 of the footwear recommendation device 100 may acquire the survey data from such survey database 300-3.

[0031] Furthermore, in this embodiment, the questionnaire data input to the user terminal 200 and acquired by the questionnaire data acquisition unit 162 may be configured to be stored in the questionnaire database 300-3. In this embodiment, the questionnaire data acquired by the questionnaire data acquisition unit 162 may, for example, be input by the user and may include information regarding the user's footwear size preferences.

[0032] The positional relationship estimation unit 164 may be configured to estimate the positional relationship between the user's foot and the footwear when the user is wearing the footwear, for example, based on questionnaire data acquired by the questionnaire data acquisition unit 162.

[0033] In the footwear recommendation device 100 according to this embodiment, for example, it may be configured to accept input of information regarding the user's size preferences, and the positional relationship between the user's foot and the footwear when wearing the footwear may be estimated based on the input information regarding size preferences. For example, as will be described later with reference to Figure 8, in this embodiment, the questionnaire data may be entered by the user on the questionnaire screen displayed on the display unit 220A of the user terminal 200, and the device may be configured to allow the user to select one or more locations on the image of the foot shape displayed on the display unit 220A where they have a size preference. In addition to or instead of inputting information regarding size preferences on the image of the foot shape, in this embodiment, for example, the device may be configured to accept input of text information regarding the content of the preference for the locations where the user has a size preference. In this case, for example, the information contained in the string entered by the user may be identified using a machine learning model that has been trained in advance to distinguish the content of the text information. Furthermore, instead of inputting images of foot shapes or text strings, or in addition to these, the system may be configured to display images such as photographs of footwear on the display unit 220A of the user terminal 200, allowing the user to input information regarding size preferences on the image of the footwear.

[0034] The positional relationship estimation unit 164 may be configured to estimate the positional relationship between the user's foot and the footwear based on information such as size preferences entered by the user, as described above.

[0035] The foot shape data correction unit 166 may be configured to correct the foot shape data based, for example, on information regarding the user's footwear size preferences.

[0036] The foot shape data correction unit 166 may be configured to correct the foot shape data in areas where information regarding the user's size preferences has been entered, based on information such as redness, pain, or discomfort in the questionnaire data entered by the user. For example, if the input indicates that the tips of the fourth or fifth toes tend to hurt, the foot shape data correction unit 166 may correct the foot shape data so that the footwear recommendation unit 150 (described later) recommends footwear that is approximately 2 mm to 5 mm larger in length. Also, for example, if the input indicates that the base of the first or fifth toe hurts, the foot shape data may correct the foot shape data so that the footwear recommendation unit 150 recommends footwear that is approximately 1 mm to 5 mm wider in width and / or circumference (wide shoes). Furthermore, for example, if input is received indicating that the instep becomes red due to contact with the upper, the foot shape data may be corrected so that the footwear recommendation section 150 recommends footwear that is approximately 1 to 5 mm larger in width and / or circumference. Alternatively, if these areas feel loose, the foot shape data may be corrected so that the footwear recommendation section 150 recommends footwear that is approximately 1 to 5 mm narrower (narrow shoes).

[0037] Furthermore, in this embodiment, for example, if input indicates that the high part of the foot is painful, the foot shape data may be corrected so that footwear with a foot width of +1 to +5 mm (wide shoes) is recommended. Also, in this embodiment, for example, if input indicates that the heel is painful, the foot shape data may be corrected so that footwear with a foot length of +2 to +5 mm larger is recommended, or if input indicates that the footwear is loose, the foot shape data may be corrected so that footwear with a relatively narrow width (narrow shoes) is recommended by the footwear recommendation unit 150.

[0038] In this embodiment, the above-mentioned correction values ​​for foot length, foot width, and foot circumference are merely examples and may be other values. For example, different correction values ​​or ranges of correction values ​​may be set depending on the user's physique and age. Alternatively, instead of correction values, a percentage or the like may be used to set the correction ratio. Furthermore, the system may be configured such that the amount of correction for the foot shape data is adjusted based on predetermined priority information regarding these data, for example, when the foot shape data, purchase data, and other data are compared with the questionnaire data.

[0039] Furthermore, in this embodiment, the positional relationship estimation unit 164 may be configured to estimate the positional relationship between the user's foot and the footwear when the user wears the footwear, based on the questionnaire data acquired by the questionnaire data acquisition unit 162, for example, when the questionnaire data acquired by the questionnaire data acquisition unit 162 includes information on the user's footwear size preferences. Also, in this embodiment, for example, the user's foot shape data acquired by the foot shape data acquisition unit 110 may be corrected by the foot shape data correction unit 166 based on information on the user's footwear size preferences acquired by the questionnaire data acquisition unit 162. In this case, the footwear determination unit 140 may be configured to determine footwear with a size and structure suitable for the user, based on, for example, the positional relationship between the user's foot and the footwear when the footwear is worn, estimated by the positional relationship estimation unit 164, the corrected foot shape data, and the activity level estimated by the activity level estimation unit 130.

[0040] The survey screen display unit 168 may be configured to display, for example, an image of the user's foot shape. For example, the survey screen display unit 168 may be configured to transmit information about the user's foot shape image to the user terminal 200 so that the image of the user's foot shape is displayed on the user terminal 200's display unit. The survey screen display unit 168 may be configured to display, for example, an input field on the user terminal 200 in addition to the image of the user's foot shape, where the user can enter their answers. For example, the survey screen display unit 168 may be configured to display an image of the user's foot shape on the user terminal 200, and also display a field on the user terminal 200 where the user can enter information about areas that the user finds uncomfortable when wearing footwear.

[0041] Furthermore, in the footwear recommendation process performed by the footwear recommendation system 10 according to this embodiment, when questionnaire data is acquired by the questionnaire data acquisition unit 162, the questionnaire screen display unit 168 is configured to display an image including an image of the user's foot shape. In addition, the system may be configured to accept user input, for example, to the user terminal's operation input unit 210 (see Figure 3 described later), regarding the image of the user's foot shape and information about areas that the user finds uncomfortable when wearing footwear.

[0042] The footwear image acquisition unit 170 may be configured, for example, to acquire images of used footwear that the user has worn. The footwear image acquisition unit 170 may be configured, for example, to acquire images of used footwear when the user starts using the footwear, an image of the footwear being used is captured by an image sensor or the like built into the user terminal 200, and the captured image of the footwear being used is transmitted to the footwear recommendation device 100.

[0043] The footwear image acquisition unit 170 may also be configured to acquire, for example, an image of the footwear before use. The footwear recommendation system 10 according to the present embodiment may include, for example, a footwear image database 300-4, and the footwear image database 300-4 may store, for example, an image of the footwear before use provided by the manufacturer of the footwear. At this time, the footwear image acquisition unit 170 may be configured to acquire, as an image of the footwear before use, the image of the footwear before use stored in the footwear image database 300-4.

[0044] Also, for example, when a user uses an image pickup device of the user terminal 200 to capture an image of the footwear before use, and the image of the footwear before use is stored in a storage unit or the like of the user terminal 200, the footwear image acquisition unit 170 may be configured to acquire the image of the footwear before use stored in the user terminal 200. In the present embodiment, at this time, for example, the acquired image of the footwear before use may be configured to be stored in the footwear image database 300-4.

[0045] The footwear image comparison unit 172 may be configured to compare, for example, an image of the footwear after use with an image of the footwear before use.

[0046] The wear position calculation unit 174 may be configured to calculate, for example, the worn position of the footwear. In the present embodiment, for example, an image of the footwear taken from a predetermined angle of the footwear used by the user is uploaded, and the photographed footwear used by the uploaded user is compared with a photograph of the same footwear in a new state taken from the same predetermined angle, so that the wear position (for example, damage to the mesh or wear of the sole, etc.) is identified, and the wear position calculation unit 174 may be configured to calculate the worn position of the footwear. For example, the worn position may be identified using a machine learning model generated by performing machine learning using teacher data including image data related to damage to the mesh or wear of the sole. In the present embodiment, the predetermined photographing angle of the above-mentioned footwear photograph may be, for example, the upper surface and both side surfaces of the footwear, or the bottom surface of the sole. Also, the footwear of both the left and right feet may be photographed together, or only the footwear of one of the feet may be photographed and used for calculating the wear position.

[0047] Note that, as described later, in the present embodiment, the worn position of the footwear may be configured to be input by the user on the questionnaire screen displayed on the user terminal 200, for example, instead of being calculated by the wear position calculation unit 174.

[0048] The wear amount calculation unit 176 may be configured to calculate, for example, the worn amount of the footwear. In the present embodiment, as the wear amount, for example, the images of the new state and the state after use by the user of the outer sole of the footwear are superimposed, and the thickness of the outer sole in the state after use and the outer sole in the new state may be calculated as the wear amount. Also, in addition to the outer sole, for example, for rubbing, tearing, perforation, etc. of the upper part or the heel counter, the wear amount may be calculated by quantitatively evaluating based on the size, degree of surface damage, etc.

[0049] The usage state estimation unit 178 may be configured to estimate, for example, the usage state of the footwear by the user.

[0050] In this embodiment, the footwear image comparison unit 172 may be configured to compare, for example, an image of the footwear after use, transmitted by the user terminal 200 and acquired by the footwear image acquisition unit 170, with an image of the footwear before use, provided by the footwear manufacturer, stored in the footwear image database 300-4, and acquired by the footwear image acquisition unit 170. The wear position calculation unit 174 may be configured to calculate the worn position on the footwear based on the comparison result between the image of the footwear after use and the image of the footwear before use. The wear amount calculation unit 176 may be configured to calculate the amount of wear on the footwear based on the comparison result between the image of the footwear after use and the image of the footwear before use. The usage state estimation unit 178 may be configured to estimate the usage state of the footwear by the user based on at least one of the worn position of the footwear calculated by the wear position calculation unit 174 and the amount of wear on the footwear calculated by the wear amount calculation unit 176. Furthermore, the footwear determination unit 140 may be configured to determine footwear with a size and structure suitable for the user, based on the usage condition of the footwear estimated by the usage condition estimation unit 178.

[0051] The feature extraction unit 180 may be configured, for example, to extract features of a predetermined part of the user's foot that exhibits a predetermined shape.

[0052] The pronation type estimation unit 182 may be configured to estimate the pronation type of the user's foot. In this embodiment, the pronation type estimation unit 182 may be configured to estimate, for example, that the pronation type of the user's foot is one of overpronation, neutral pronation, or underpronation. In this embodiment, for example, a trained model may be generated using the correlation between the pronation type, the movement of the footwear, and the wear state of the footwear as training data, and the pronation type may be estimated by inputting, for example, the wear state of the user's footwear, which is the subject of the pronation type estimation, into the trained model to output the pronation type.

[0053] In this embodiment, for example, the foot shape data acquisition unit 110 may be configured to acquire data relating to the top surface shape of the user's foot, such as a top view image of the user's foot. The feature extraction unit 180 may be configured to extract feature quantities of predetermined parts that indicate the top view contour shape of the user's foot from the top view image of the user's foot acquired by the foot shape data acquisition unit 110. In this embodiment, the pronation type estimation unit 182 may be configured to estimate the pronation type of the user's foot based on a comparison between the feature quantities of predetermined parts of the user's foot extracted by the feature extraction unit 180 and predetermined reference values. The pronation type estimation unit 182 may be configured to estimate, for example, that the pronation type is overpronation when the feature quantities of predetermined parts of the user's foot are greater than (or less than) one of the reference values, underpronation when the feature quantities of predetermined parts of the user's foot are less than (or greater than) the other reference value, and neutral pronation when the feature quantities of predetermined parts of the user's foot are between the two reference values.

[0054] Furthermore, the footwear determination unit 140 may be configured to determine footwear with a size and structure suitable for the user, based, for example, on the pronation type estimated by the pronation type estimation unit 182.

[0055] The stiffness information acquisition unit 184 may be configured to acquire information on the stiffness of at least a part of each of several footwear items that differ in size and structure. In this embodiment, the stiffness information acquisition unit 184 may be configured to acquire information on the stiffness of at least one part of the footwear, such as the outsole, insole, and upper.

[0056] The predicted deformation amount calculation unit 186 may be configured to calculate, for example, the predicted deformation amount of footwear. In this embodiment, the predicted deformation amount calculation unit 186 may be configured to calculate the predicted deformation amount of footwear when used by a user for each of multiple pairs of footwear, based on, for example, the user's foot shape data acquired by the foot shape data acquisition unit 110 and information on the stiffness of footwear acquired by the stiffness information acquisition unit 184.

[0057] The deformation determination unit 187 may be configured to determine, for example, whether the predicted deformation amount is less than or equal to a deformation threshold. In this embodiment, the deformation determination unit 187 may be configured to determine, for example, whether the predicted deformation amount of footwear calculated by the predicted deformation amount calculation unit 186 is less than or equal to a predetermined deformation threshold. In this embodiment, the footwear recommendation system 10 may include a threshold database 300-5, and the deformation threshold may be stored in the threshold database 300-5. The deformation determination unit 187 may be configured to determine whether the predicted deformation amount is less than or equal to the deformation threshold using the deformation threshold stored in the threshold database 300-5.

[0058] Furthermore, in the footwear recommendation system 10 according to this embodiment, the footwear recommendation unit 150 may be configured to recommend footwear having a size and structure such that the predicted deformation amount calculated by the predicted deformation amount calculation unit 186 is less than or equal to the deformation amount threshold stored in the threshold database 300-5, based on the deformation determination unit 187.

[0059] The stiffness calculation unit 188 may be configured to calculate, for example, the stiffness of the user's foot. In the footwear recommendation system 10 according to this embodiment, for example, the foot shape data acquired by the foot shape data acquisition unit 110 may include the user's foot shape data when the user is in a static standing position, and in this case, the user's foot shape data when the user is in a static standing position may include at least one of the user's foot length and arch height when the user is in a static standing position, and information regarding the user's weight may also be acquired, and the stiffness calculation unit 188 may be configured to calculate the stiffness of the user's foot based on the information regarding the user's weight and at least one of the user's foot length and arch height when the user is in a static standing position. In this embodiment, the footwear recommendation unit 150 may be configured to recommend footwear with a size and structure that suits the user based on the stiffness of the user's foot thus calculated.

[0060] The storage unit 190 may be configured to store, for example, the user's foot shape data or footwear purchase data. However, the information stored in the storage unit 190 is not limited to these; other data used in the processing of the footwear recommendation device 100 may also be stored, or data may be temporarily stored during the processing.

[0061] The footwear recommendation device 100 according to this embodiment has been described above using, for example, one information processing device as an example, but is not limited to this. The footwear recommendation device 100 according to this embodiment may be implemented using, for example, multiple information processing devices. The footwear recommendation device 100 may consist of, for example, one or more physical servers, or it may be configured using a virtual server operating on a hypervisor. Alternatively, the footwear recommendation device 100 may be configured using one or more cloud servers.

[0062] [User Terminal Configuration] Figure 3 is a functional block diagram showing the functions of a user terminal 200 according to an embodiment of the present disclosure. As shown in Figure 3, the user terminal 200 may include an operation input unit 210, an output unit 220, and a storage unit 230.

[0063] The operation input unit 210 is configured to receive, for example, the operations of a user who is a user receiving footwear recommendations from the footwear recommendation system 10 according to this embodiment. The operation input unit 210 may also be configured to receive, for example, information about the user's problems when using footwear, as described later, or answers to questionnaires, based on the user's operations.

[0064] The output unit 220 may include, for example, a display device. The output unit 220 may be configured to display, for example, information about footwear that has been determined to have a size and structure suitable for the user, which is transmitted from the footwear recommendation device 100 to the user terminal 200. The output unit 220 may be configured to display information such as the manufacturer, product number, and appearance photograph of the footwear that has been determined to have a size and structure suitable for the user.

[0065] The storage unit 230 may be configured to store one or more programs executed on the user terminal 200, as well as data used in each process and operation executed on the user terminal 200.

[0066] Similar to the footwear recommendation device 100, when the user terminal 200 is implemented by the computer 400 (see Figure 4) described later, the operation input unit 210 and the output unit 220 can be implemented, for example, by the processor 401 of the computer 400, which is part of the user terminal 200, executing a program stored in the storage device 403 of the computer 400. Furthermore, when the user terminal 200 is implemented by the computer 400, the storage unit 230 of the user terminal 200 can be implemented, for example, by using the storage device 403 of the computer 400, which is part of the computer 400, as described later.

[0067] [Hardware Configuration of Footwear Recommendation Device 100] Next, with reference to Figure 4, an example of the hardware configuration when the footwear recommendation device 100 is implemented using a computer 400 will be described. Figure 4 is a diagram showing an example of the hardware configuration of the computer 400.

[0068] The footwear recommendation device 100 according to this embodiment includes a memory for storing information (e.g., programs and various data) and a processor that operates based on the information stored in the memory, as will be described later. The processor may, for example, have the functions of each part implemented by individual hardware, or the functions of each part may be implemented by integrated hardware. The processor may be, for example, a CPU. However, the processor is not limited to a CPU, and various types of processors such as a GPU (Graphics Processing Unit) or a DSP (Digital Signal Processor) can be used. The processor may also be a hardware circuit using an ASIC (Application Specific Integrated Circuit). The memory may be, for example, a semiconductor memory such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory), a register, a magnetic storage device such as a hard disk drive, or an optical storage device such as an optical disk drive. For example, the memory stores instructions that can be read by a computer, and the functions of each part of the footwear recommendation device 100 are realized when these instructions are executed by the processor. The instructions referred to here may be instructions from the instruction set that makes up the program, or they may be instructions that instruct the processor's hardware circuits to perform actions.

[0069] As shown in Figure 4, the computer 400 includes, for example, a processor 401, memory 402, storage device 403, input I / F unit 404, data I / F unit 405, communication I / F unit 406, and display device 407.

[0070] Computer 400 may be, for example, a server computer, a personal computer (e.g., a desktop, laptop, tablet, etc.), a media computer platform (e.g., a cable, satellite set-top box, digital video recorder, etc.), a handheld computer device (e.g., a PDA, email client, etc.), or another type of computer or communication platform.

[0071] The processor 401 is a control unit that controls various processes in the computer 400 by executing programs stored in the memory 402.

[0072] Memory 402 is a storage medium such as RAM (Random Access Memory). Memory 402 temporarily stores the program code of the program executed by the processor 401, as well as data required during program execution.

[0073] The storage device 403 is a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 403 stores the operating system and various programs for realizing the above configurations.

[0074] The input interface unit 404 is a device for receiving input from the user. The input interface unit 404 may be, for example, a keyboard, mouse, touch panel, various sensors, or wearable devices. The input interface unit 404 may be connected to the computer 400 via an interface such as USB (Universal Serial Bus).

[0075] The data I / F unit 405 is a device for inputting data from outside the computer 400. The data I / F unit 405 is, for example, a drive device for reading data stored on various storage media. The data I / F unit 405 may be provided outside the computer 400. If the data I / F unit 405 is provided outside the computer 400, it is connected to the computer 400 via an interface such as USB.

[0076] The communication interface unit 406 is a device for performing data communication with external devices of the computer 400 via a network such as the Internet, either by wire or wireless connection. The communication interface unit 406 may be located outside the computer 400. If the communication interface unit 406 is located outside the computer 400, it is connected to the computer 400 via an interface such as USB.

[0077] The display device 407 is a device for displaying various types of information. The display device 407 may be, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, or a display for a wearable device. The display device 407 may be provided outside the computer 400. If the display device 407 is provided outside the computer 400, it is connected to the computer 400, for example, via a display cable. Also, if a touch panel is used as the input I / F unit 404, the display device 407 may be configured to be integrated with the input I / F unit 404.

[0078] The footwear recommendation program or a part thereof, which is a program that recommends footwear according to this embodiment, may be stored and provided on a computer-readable storage medium such as the storage device 403. The storage medium storing the program may be a non-transitory computer-readable medium. The non-transitory storage medium is not particularly limited, but may be a storage medium such as a USB memory or CD-ROM.

[0079] Alternatively, the footwear recommendation program according to this embodiment may be provided from outside the footwear recommendation device 100 via a communication network to which the footwear recommendation device 100 is connected. In the footwear recommendation device 100, for example, the processor 401 may execute the footwear recommendation program according to this embodiment, thereby realizing various processes and operations described later with reference to Figures 5, 6, and 7, etc.

[0080] These physical configurations are illustrative and do not necessarily have to be independent. For example, the footwear recommendation device 100 and user terminal 200 according to this embodiment may include an LSI (Large-Scale Integration) in which the processor 401 and storage device 403 are integrated. Also, as described above, the footwear recommendation device 100 and user terminal 200 may include a GPU as the processor 401, in which case the GPU executes the footwear recommendation program, thereby realizing various operations and processes described later using Figures 5, 6, and 7, etc.

[0081] Furthermore, the footwear recommendation device 100 and / or user terminal 200 are not limited to the configuration described above. For example, some or all of the functions of the footwear recommendation device 100 and / or user terminal 200 may be performed by other information processing devices.

[0082] Furthermore, the functional units of the footwear recommendation device 100 and user terminal 200 described with reference to Figures 2, 3, and 4 are not limited to the above-described configuration. That is, the functional units of the footwear recommendation device 100 and user terminal 200 described with reference to Figures 2, 3, and 4 may be merely illustrative examples for the convenience of explanation in this embodiment, and some of the functions performed by the above-described multiple functional units may be performed by other functional units or other servers. Also, multiple functional units may be configured to be performed by a single piece of hardware.

[0083] [Footwear Recommendation Process] Next, an example of the footwear recommendation process according to this embodiment will be described with reference to Figure 5. The footwear recommendation process according to this embodiment may be performed, for example, by the footwear recommendation system 10 described above with reference to Figures 1 to 4.

[0084] Figure 5 shows an example sequence of footwear recommendation processing performed by the footwear recommendation system 10. In the footwear recommendation processing exemplified in Figure 5, footwear is recommended based on foot shape data generated using the user terminal 200.

[0085] First, the user generates foot shape data of their feet using the user terminal 200 (S502). The user may generate foot shape data by, for example, taking one or more external photographs of their feet using an image sensor or the like built into the user terminal 200.

[0086] Next, the foot shape data generated using the user terminal 200 is transmitted from the user terminal 200 to the footwear recommendation device 100 (S504).

[0087] In the footwear recommendation device 100, the foot shape data acquisition unit 110 acquires foot shape data transmitted from the user terminal 200 (S506).

[0088] Next, the user terminal 200 transmits the user's product purchase data to the footwear recommendation device 100 (S508). In this embodiment, for example, the user terminal 200 may be configured to obtain purchase data such as the purchase history of footwear by accessing the database of the product vendor via a browser, and the obtained purchase data may be transmitted to the footwear recommendation device 100.

[0089] Furthermore, user purchase data may be configured to be acquired from, for example, a server that can communicate with the footwear recommendation device 100. For example, the footwear recommendation system 10 according to this embodiment may have a database such as the purchase database 300-2 (see Figure 1) described above, and purchase data may be acquired from the purchase database 300-2 by a server that can communicate with the footwear recommendation device 100, and the acquired purchase data may be transmitted from the server to the footwear recommendation device 100. Alternatively, as described above, the purchase data acquisition unit 120 may be configured to acquire user purchase data from, for example, the purchase database 300-2, or from a database owned by a footwear retailer or the like.

[0090] In the footwear recommendation device 100, the purchase data acquisition unit 120 acquires the purchase data transmitted from the user terminal 200 (S510).

[0091] Furthermore, if the user's purchase data is stored in, for example, a purchase database 300-2, the footwear recommendation device 100 may be configured to access the purchase database 300-2 and obtain the user's purchase data.

[0092] Next, in the footwear recommendation device 100, the activity level estimation unit 130 estimates the user's activity level based on the acquired purchase data (S512).

[0093] Next, in the footwear recommendation device 100, the footwear determination unit 140 determines footwear with a size and structure suitable for the user based on the foot shape data acquired by the foot shape data acquisition unit 110 and the activity level estimated by the activity level estimation unit 130 (S514).

[0094] Next, in the footwear recommendation device 100, the footwear recommendation unit 150 recommends footwear that has a size and structure suitable for the user, as determined by the footwear determination unit 140 (S516). The footwear recommendation unit 150 is configured to transmit, for example, information regarding footwear that has a size and structure suitable for the user to the user terminal 200.

[0095] Next, the footwear recommended by the footwear recommendation unit 150 is displayed on the user terminal 200 (S518). For example, the recommended footwear may be displayed on a display unit such as the display of the user terminal 200.

[0096] Furthermore, in this embodiment, for example, if one pair of footwear with a suitable size and structure for the user is determined, that pair of footwear may be recommended and displayed on the user terminal 200. Also, if multiple pairs of footwear with a suitable size and structure for the user are determined, one or more pairs of footwear may be recommended and displayed on the user terminal 200. When multiple pairs of footwear are displayed on the user terminal 200, for example, the multiple pairs of footwear may be displayed in order of their suitability to the user, such as by size and / or structure. Alternatively, the system may be configured to allow the user to specify sorting conditions, such as displaying them in order of price (lowest first) or by ratings from other users (highest first). In addition, an upper limit on the number of items to be displayed may be set in advance, and if the number of items to be displayed exceeds this limit, the system may be configured to display the items in order from highest to lowest rank according to the sorting conditions specified by the user, up to the upper limit.

[0097] With the above, the exemplary footwear recommendation process performed in the footwear recommendation system 10 in this embodiment is terminated.

[0098] According to the footwear recommendation method of this embodiment, which is a footwear recommendation process performed by the footwear recommendation system 10 described above, it is possible to determine footwear with a size and structure that suits the user based on foot shape data and information such as the user's footwear purchase history and activity level. Therefore, it is possible to recommend footwear that suits the user's body, preferences, and intended use. As a result, for example, it is possible to recommend footwear that can improve the user's satisfaction.

[0099] Next, with reference to Figure 6, another example of the footwear recommendation process according to this embodiment will be described. Figure 6 is a diagram showing a sequence of another exemplary footwear recommendation process performed by the footwear recommendation system 10. The footwear recommendation process illustrated in Figure 6 differs from the footwear recommendation process illustrated in Figure 5 in that, instead of foot shape data generated using the user terminal 200, footwear is recommended based on foot shape data generated using a foot shape measuring device (a device 500 that captures images of the foot), such as a three-dimensional foot shape measuring device.

[0100] First, the user generates foot shape data using a device 500 that captures images of the foot, such as a three-dimensional foot shape measuring device (S602).

[0101] Next, the foot image acquisition device 500 transmits the foot shape data generated using the foot image acquisition device 500 to the footwear recommendation device 100 (S604).

[0102] Next, in the footwear recommendation device 100, the foot shape data acquisition unit 110 acquires the foot shape data transmitted from the foot image acquisition device 500 (S606).

[0103] Next, the user terminal 200 transmits purchase data related to the user's products to the footwear recommendation device 100 (S608). Similar to the embodiments described above, the user's purchase data may be configured to be obtained from, for example, a server that can communicate with the footwear recommendation device 100. For example, the footwear recommendation system 10 according to this embodiment may have a database such as the purchase database 300-2 (see Figure 1) described above, and the server may acquire purchase data from the purchase database 300-2, and the acquired purchase data may be transmitted from the server to the footwear recommendation device 100. Alternatively, the purchase data acquisition unit 120 may be configured to acquire the user's purchase data from, for example, the purchase database 300-2 or a database owned by a footwear retailer, etc.

[0104] Next, in the footwear recommendation device 100, the purchase data acquisition unit 120 acquires the purchase data transmitted from the user terminal 200 (S610). Referring to Figure 5, similar to the footwear recommendation process described above, if the user's purchase data is stored in the purchase database 300-2, etc., the footwear recommendation device 100 may be configured to access the purchase database 300-2 and acquire the user's purchase data.

[0105] Next, the activity level estimation unit 130 of the footwear recommendation device 100 estimates the user's activity level based on the acquired purchase data (S612).

[0106] Next, the footwear selection unit 140 of the footwear recommendation device 100 determines footwear with a size and structure suitable for the user, based on the foot shape data acquired by the foot shape data acquisition unit 110 and the activity level estimated by the activity level estimation unit 130 (S614).

[0107] Next, the footwear recommendation unit 150 of the footwear recommendation device 100 recommends footwear that has a size and structure suitable for the user, as determined by the footwear determination unit 140 (S616).

[0108] Next, the footwear recommended by the footwear recommendation unit 150 is displayed on the user terminal 200 (S618).

[0109] With the above, the other exemplary footwear recommendation processes performed in the footwear recommendation system 10 in this embodiment are terminated.

[0110] Referring to Figure 7, yet another example of the footwear recommendation process performed in this embodiment will be described. Figure 7 is a diagram showing yet another exemplary sequence of footwear recommendation processes performed by the footwear recommendation system 10. Similar to the footwear recommendation process illustrated in Figure 6, the footwear recommendation process illustrated in Figure 7 also recommends footwear based on foot shape data generated using a foot shape measuring device (a device 500 that captures images of the foot), such as a three-dimensional foot shape measuring device.

[0111] As shown in Figure 7, first, the user generates foot shape data of their feet using a device 500 that captures images of the feet, such as a three-dimensional foot shape measuring device (S702).

[0112] Next, the foot image acquisition device 500 transmits the foot shape data generated using the foot image acquisition device 500 to the footwear recommendation device 100 (S704).

[0113] Next, in the footwear recommendation device 100, the foot shape data acquisition unit 110 acquires the foot shape data transmitted from the foot image acquisition device 500 (S706).

[0114] Next, the user terminal 200 transmits purchase data related to the user's products to the footwear recommendation device 100 (S708). In this case as well, similar to the embodiments described above, the user's purchase data may be configured to be obtained from, for example, a server that can communicate with the footwear recommendation device 100. If the footwear recommendation system 10 according to this embodiment has a database such as the purchase database 300-2 (see Figure 1) described above, the server may obtain purchase data from the purchase database 300-2, and the obtained purchase data may be transmitted from the server to the footwear recommendation device 100. Alternatively, the purchase data acquisition unit 120 may be configured to obtain the user's purchase data from, for example, the purchase database 300-2 or a database owned by a footwear retailer, etc.

[0115] Next, in the footwear recommendation device 100, the purchase data acquisition unit 120 acquires the purchase data transmitted from the user terminal 200 (S710).

[0116] As shown in Figure 7, in the footwear recommendation process according to this embodiment, in addition to the above process, for example, the user's foot length and at least one of the user's foot width and foot circumference may be calculated based on the acquired foot shape data (S712). In this embodiment, for example, the footwear recommendation device 100 may calculate the user's foot length and foot width, or the user's foot length and foot circumference, based on the foot shape data. In this embodiment, for example, the system may be configured to calculate the size of footwear that suits the user, as described later, based on the calculated user's foot length and foot width, or the user's foot length and foot circumference. In this embodiment, the user's foot length, foot width, and foot circumference may also be calculated. By calculating footwear that suits the user based on the user's foot length, foot width, and foot circumference, the accuracy of the fit of the calculated footwear size to the user's foot can be improved compared to when the size of footwear that suits the user is calculated based on the user's foot length and foot width, or the user's foot length and foot circumference.

[0117] In this embodiment, in addition to the user's foot length and width, or the user's foot length and circumference, at least one of the following may be calculated based on the foot shape data: for example, the shape of the user's toes, arch circumference, heel circumference, and heel width. The system may then be configured to calculate the appropriate footwear size for the user based on this data. The accuracy of the fit of the calculated footwear size to the user's feet can also be further improved by calculating the footwear size based on one or more of the following: the shape of the user's toes, arch circumference, heel circumference, and heel width.

[0118] Furthermore, in this embodiment, information regarding a predetermined recommended athletic ability level for multiple footwear may be obtained in place of, or in addition to, at least a part of, the above processing (S714). In this case, for example, a provider of multiple footwear may obtain information regarding a predetermined recommended athletic ability level for each of the multiple footwear items. For example, a footwear provider such as a manufacturer may have set up information regarding the correspondence between athletic ability levels, such as the level of advanced runners who use carbon-reinforced shoes, the level of runners aiming to complete a full marathon in under four hours (Sub 4.0), and the level of recreational runners, and footwear suitable for each athletic ability level.

[0119] In this embodiment, for example, the footwear recommendation system 10 may include a product information database 300-6 managed by a provider of multiple footwear items, and information regarding recommended athletic ability levels, which are pre-set for each of the multiple footwear items by the provider, may be stored in the product information database 300-6. The footwear recommendation device 100 may also be configured to acquire the information regarding the recommended athletic ability levels from the product information database 300-6. The product information database 300-6 may also store information about products set by multiple providers, for example. Alternatively, a product information database may be provided for each provider, and the footwear recommendation device 100 may be configured to access each provider's product information database and acquire product information, such as the information regarding the recommended athletic ability levels, for each provider.

[0120] Furthermore, in this embodiment, information about other users may be obtained in place of or in addition to at least a part of the above processing (S716). In this embodiment, information about other users may include, for example, the purchase data of multiple other users other than the user (the user receiving footwear recommendations) and the activity history information of each of those multiple other users.

[0121] In this embodiment, for example, the footwear recommendation system 10 includes a user information database 300-7 that stores information about multiple users, and information about multiple other users may be stored in the user information database 300-7, for example, and the footwear recommendation device 100 may be configured to acquire information about the multiple other users from the user information database 300-7. Alternatively, in this embodiment, the footwear recommendation device 100 may be configured to acquire information about each of the multiple other users from user terminals 200 owned by each of the multiple other users.

[0122] In this embodiment, information about the user may include, for example, information about product evaluations of footwear by other users. Information about product evaluations by other users may be obtained, for example, from a database provided by the product's distributor (e.g., product information database 300-6). For example, by using evaluation information evaluated by other users for multiple sizes, the system may be configured to identify an acceptable range for the size and structure that suits the user. Based on the identified acceptable range, a process is performed to determine footwear with a size and structure that suits the user, as described later, thereby improving the accuracy of recommending footwear to the user.

[0123] Furthermore, in this embodiment, in place of at least a part of the above processing, or in addition to at least a part of the above processing, a pre-trained model may be generated by machine learning using as training data information provided by the provider of the multiple footwear, which includes information on the recommended athletic ability level pre-set for each of the multiple footwear, the purchase data of multiple other users other than the user, and the activity history information of each of the multiple other users (S718). The pre-trained model may, for example, be generated in advance.

[0124] Furthermore, in this embodiment, the activity level of the user may be estimated by the activity level estimation unit 130 of the footwear recommendation device 100 based on the output result of the trained model when the user's purchase data is input to the trained model (S720), and / or the use estimation unit 160 may estimate the use of the footwear by the user (S722). The use may be, for example, everyday wear, or sports such as running, tennis, or soccer.

[0125] In this embodiment, the footwear recommendation process may be used, for example, when purchasing footwear for family members or others besides the user themselves. In this case, the process of estimating the activity level described above may be performed by appropriately grouping the other footwear wearers, such as family members, based on information such as their size, gender, age group, and whether they are children or adults. Furthermore, the system may be configured to confirm with the user whether or not to recommend footwear that the user will wear, and if the recommendation is for footwear that the user will not wear, such as a gift, the data used in this footwear recommendation process may be excluded from the training data.

[0126] In the footwear recommendation process of this embodiment, instead of or in addition to at least a part of the above process, for example, questionnaire data entered by the user may be acquired by the questionnaire data acquisition unit 162. In this case, for example, first, the questionnaire screen may be displayed on the user terminal 200 (S724).

[0127] The user terminal 200 may accept input from the user regarding the displayed questionnaire screen (S726). The display unit of the user terminal 200 may display a questionnaire screen that includes an input field where information regarding the user's footwear size preferences can be entered, and the user may input information regarding the user's footwear size preferences into the user terminal 200.

[0128] For example, survey data including information about the user's footwear size preferences may be transmitted from the user terminal 200 to the footwear recommendation device 100 (S728).

[0129] The transmitted questionnaire data may be acquired by the questionnaire data acquisition unit 162 of the footwear recommendation device 100 (S730).

[0130] In the footwear recommendation device 100, for example, the positional relationship estimation unit 164 may estimate the positional relationship between the user's foot and the footwear when the user is wearing the footwear, based on the questionnaire data acquired by the questionnaire data acquisition unit 162 (S732). In this embodiment, the questionnaire data can be used to estimate, for example, the state of the foot inside the footwear when the user is wearing the footwear. For example, based on the positional relationship estimated from the questionnaire data, information can be obtained regarding which point the toes of the foot are in contact with the upper part of the footwear, and information can be obtained regarding how much pressure the toes of the foot are in contact with the upper part of the footwear.

[0131] Furthermore, in the footwear recommendation device 100, for example, the foot shape data may be corrected by the foot shape data correction unit 166 based on information regarding the user's footwear size preferences from the questionnaire data acquired by the questionnaire data acquisition unit 162 (S734). As described later, in the footwear recommendation process according to this embodiment, for example, footwear having a size and structure suitable for the user may be determined based on the positional relationship between the user's foot and the footwear when the user wears the footwear, estimated by the positional relationship estimation unit 164, the foot shape data corrected by the foot shape data correction unit 166, and the activity level estimated by the activity level estimation unit 130.

[0132] In the footwear recommendation process according to this embodiment, in place of or in addition to at least a part of the above process, the system may be configured to accept input from the user regarding areas that the user finds uncomfortable when wearing footwear, for example, on a questionnaire screen displayed on the user terminal 200. For example, the questionnaire screen display unit 168 may cause the user terminal 200 to display an image of the shape of the user's feet (S736), and the user terminal 200 may be configured to accept input from the user regarding areas that the user finds uncomfortable in the displayed image of the shape of the user's feet (S738).

[0133] Figure 8 shows an example of the display unit 220A of the user terminal 200 where the questionnaire screen is displayed in this case. As shown in Figure 8, the display unit 220A may display, for example, a shoe information input field 222 and a user information input field 224. The user terminal 200 may be configured to accept input from the user into the shoe information input field 222 for information about the shoes currently in use, such as the brand and size of the shoes, and into the user information input field 224 for user information such as the user's gender, age, shoe usage conditions, and intended use of the shoes.

[0134] As shown in Figure 8, for example, the display unit 220A may be configured to display a field for specifying uncomfortable areas 226, and the field for specifying uncomfortable areas 226 may be configured to display an image of the user's foot shape. The user terminal 200 may be configured to accept input from the user specifying areas on the image of the user's foot shape that are prone to fatigue, rubbing, redness, pain, or excess space when wearing footwear. The image of the user's foot shape may be an image captured by an image sensor built into the user terminal 200 and stored in the memory unit of the user terminal 200. Furthermore, the foot image displayed on the display unit 220A of the user terminal 200 is not limited to an image obtained by imaging the user's foot, but may be, for example, a general-purpose foot shape image. In addition, multiple general-purpose foot shape images may be prepared, and the system may be configured to select and display an image of a foot shape that is relatively similar to the user's foot shape from among the multiple images of foot shapes. These general-purpose foot shapes may be stored in a database 300 that can be accessed from the user terminal 200, for example. As shown in Figure 8, the user may be able to specify different sizes depending, for example, the degree and extent of the user's pain.

[0135] Returning to Figure 7, information regarding the uncomfortable areas entered by the user into the user terminal 200 is transmitted from the user terminal 200 to the footwear recommendation device 100 as questionnaire data (S740). The questionnaire data, including the information regarding the uncomfortable areas specified by the user, may be acquired by the questionnaire data acquisition unit 162 of the footwear recommendation device 100 (S742).

[0136] In the footwear recommendation process according to this embodiment, in addition to or instead of at least a part of the above process, for example, an image of the used footwear may be taken by the user terminal 200 (S744), and the taken image of the used footwear may be transmitted to the footwear recommendation device 100 (S746). In this embodiment, the image of the used footwear may be, for example, an image of footwear that the user has used in the past. Alternatively, the image of the used footwear may be, for example, an image of footwear that the user is currently using. The image of the used footwear may be acquired, for example, by the footwear image acquisition unit 170 of the footwear recommendation device 100 (S748).

[0137] Furthermore, in the footwear recommendation process according to this embodiment, the footwear image acquisition unit 170 may acquire an image of the footwear before use (S750). The image of the footwear before use may be stored in a product information database 300-6 of, for example, the manufacturer or distributor of the footwear, and the footwear image acquisition unit 170 may be configured to acquire it from the product information database 300-6. Alternatively, for example, an image taken by the user before the user starts using the footwear using an image sensor built into the user terminal 200 may be acquired by the footwear image acquisition unit 170.

[0138] In the footwear recommendation process according to this embodiment, the footwear image comparison unit 172 may compare the image of the footwear after use, acquired by the footwear image acquisition unit 170 as described above, with the image of the footwear before use (S752).

[0139] Furthermore, based on the comparison result obtained by the footwear image comparison unit 172, which compares an image of the footwear after use with an image of the footwear before use, the wear position calculation unit 174 calculates the wear position caused by the user's use of the footwear (S754), and / or the wear amount calculation unit 176 calculates the amount of wear (S756). In other words, in this embodiment, either the calculation of the wear position by the wear position calculation unit 174 or the calculation of the wear amount by the wear amount calculation unit 176 may be performed, or both may be performed.

[0140] In this embodiment, the wear position is calculated by the wear position calculation unit 174 as described above, for example. However, the footwear recommendation process according to this embodiment is not limited to this, and for example, information regarding the wear position may be input by the user. For example, the user may input information regarding the wear position of the footwear on a questionnaire screen displayed on the display unit 220A of the user terminal 200, and the received information regarding the wear position of the footwear may be used in each process of the footwear recommendation process according to this embodiment (for example, the usage state estimation process (S758) performed by the usage state estimation unit 178 described below). Information regarding the wear position may be input as text information such as terms indicating the wear position and / or sentences explaining the wear position on the questionnaire screen displayed on the display unit 220A, or an image of the footwear may be displayed on the questionnaire screen and the wear position may be input by the user on the displayed image of the footwear.

[0141] In the footwear recommendation process according to this embodiment, the user's usage state of the footwear may be estimated by the usage state estimation unit 178 based on at least one of the worn position calculated by the wear position calculation unit 174 and the amount of wear calculated by the wear amount calculation unit 176 (S758). As described later, in this embodiment, the footwear determination unit 140 may be configured to determine footwear having a size and structure suitable for the user, based on the user's usage state of the footwear estimated by the usage state estimation unit 178.

[0142] In the footwear recommendation process according to this embodiment, a top view image of the user's foot may be captured using, for example, an image sensor built into the user terminal 200, instead of or in addition to at least a part of the above process (S760). The captured top view image of the user's foot may be transmitted from the user terminal 200 to the footwear recommendation device 100 (S762), and the top view image of the foot may be acquired by the footwear recommendation device 100 (S764). In this embodiment, for example, the foot shape data acquired by the foot shape data acquisition unit 110 may include data relating to the top surface shape of the foot, such as a top view image of the foot.

[0143] In this embodiment, feature quantities of predetermined parts indicating the top view contour shape of the user's foot may be extracted from the acquired top view image of the user's foot by the feature quantity extraction unit 180 (S766). In this embodiment, the feature quantities of the predetermined parts may be compared with a predetermined reference value (S768). Furthermore, based on the comparison result obtained by comparing the feature quantities of the predetermined parts with the predetermined reference value, the pronation type of the user's foot may be estimated by the pronation type estimation unit 182 (S770).

[0144] As will be described later, in the footwear recommendation process according to this embodiment, the footwear determination unit 140 may determine footwear having a structure suitable for the user, based on the pronation type estimated by the pronation type estimation unit 182.

[0145] The pronation type estimation process according to this embodiment will be described in detail with reference to Figures 9 to 11.

[0146] Figure 9 shows a functional block diagram of the pronation type estimation device 600 used in the footwear recommendation system 10 according to this embodiment. In the footwear recommendation system 10 according to this embodiment, the pronation type estimation device 600 may be, for example, an information processing device such as a personal computer separate from the footwear recommendation device 100. Alternatively, in this embodiment, for example, the footwear recommendation device 100 may have the functions and configuration of the pronation type estimation device 600, in which case the feature extraction unit 180 and the pronation type estimation unit 182 of the footwear recommendation device 100 may have the functions and configuration of the pronation type estimation device 600 described below.

[0147] In this embodiment, the pronation type estimation process performed by the pronation type estimation device may include, for example, a process of acquiring at least a top view image of the foot as an image showing the contour shape of the foot in a top view; a process of extracting feature quantities of predetermined parts showing the top view contour shape of the foot from the top view image by image processing; and a process of estimating the degree of pronation of the foot based on a comparison process between the feature quantities of the predetermined parts and reference values.

[0148] In this embodiment, feature quantities indicating the top view contour shape of the foot are extracted from a top view image of the subject's foot while they are seated, and the degree of foot pronation is estimated based on a comparison with a reference value. The top view image may be an image showing the top view contour shape of the subject's foot. The top view image may include the contour shape of the entire foot, such as the shape of the toes and heel, and feature quantities of foot parts, such as foot length and foot width, can be extracted from the top view image. As a method for estimating the pronation type based on the feature quantities of foot parts, a method may be employed in which the relationship between the feature quantities of foot parts measured for multiple subjects and the pronation type is analyzed in advance using a decision tree, and the estimation is performed using an estimation algorithm based on the results of this analysis.

[0149] In this embodiment, for example, a person whose pronation type is to be measured may use the user terminal 200 or a three-dimensional foot shape measuring device (such as the three-dimensional foot shape measuring device 500 that captures images of the foot) to determine the pronation type of their own foot, and a top view image may be acquired for each foot, and the pronation type may be determined for each of the left and right feet.

[0150] The user terminal 200 used in the pronation type estimation process may, as described above, be a general-purpose information processing terminal such as a smartphone or tablet provided by the user who is the subject of measurement, or by the shoe store. The user terminal 200, such as an information processing terminal, may, for example, access a website provided by the pronation type estimation device 600 via a web browser, or the information provided by the pronation type estimation device 600 may be displayed on the screen by application software running on the user terminal 200.

[0151] When a user terminal 200 is used, for example, the user who is the subject of measurement may take a picture of their feet while sitting using an image sensor such as a camera built into the user terminal 200, such as a mobile phone terminal, and acquire an image. For example, in the case of a method in which the entire foot is photographed from directly above, even if the heel is sufficiently captured, the ankle may also be captured, making it difficult to capture the entire contour shape of the foot in a single image. Therefore, it may be assumed that the image will be taken in such a way that at least the contours of the toes and heel, and the contours of both the left and right sides from the forefoot to the midfoot are captured.

[0152] If the user terminal 200 has a three-dimensional scanner function using technology such as LiDAR (Light Detection And Ranging), it may scan around the foot to generate a three-dimensional model of the foot shape and obtain a two-dimensional top-view image from that three-dimensional model. Even if the user terminal 200 does not have a three-dimensional scanner function using LiDAR or the like, it may generate a three-dimensional model of the foot shape by image synthesis processing such as photogrammetry and obtain a two-dimensional top-view image from that three-dimensional model. The user, who is the subject of measurement, may place their foot on a dedicated measurement mat and scan their foot shape using the camera function of the user terminal 200 and a foot shape acquisition application, etc., to generate a three-dimensional model of the foot shape.

[0153] When a foot imaging device 500, such as a three-dimensional foot shape measuring device, is used, the user being measured may generate a three-dimensional shape of their foot using the foot imaging device 500 installed in, for example, a shoe store, and obtain a two-dimensional top view image from that three-dimensional model. The foot imaging device 500, such as a three-dimensional foot shape measuring device, may acquire three-dimensional data of the foot shape by laser measurement. The measured values ​​as a result of three-dimensional measurement of the foot shape scanned by the foot imaging device 500 are transmitted from the foot imaging device 500 to the pronation type estimation device 600, and the pronation type estimation device 600 may generate a two-dimensional top view image from the three-dimensional model.

[0154] In addition, a lateral view image may be acquired instead of a top view image of the user's foot. Alternatively, both top view and lateral view images of the user's foot may be acquired. Alternatively, a top view or lateral view image of the user's foot in a standing position may be acquired.

[0155] The pronation type estimation device 600 may be connected to a user terminal 200 or a device 500 that captures images of the foot, such as a three-dimensional foot shape measuring device, via a network line such as the Internet or a LAN (Local Area Network), and / or communication means such as wireless communication. The pronation type estimation device 600 may be implemented as a server that estimates the pronation type based on measurement data transmitted from multiple user terminals 200 or devices 500 that capture images of the foot, such as a three-dimensional foot shape measuring device. The pronation type estimation device 600 may consist of a single server computer or a combination of multiple server computers.

[0156] As shown in the functional block diagram of the pronation type estimation device 600 in Figure 9, the pronation type estimation device 600 may run a program having the following functions. For example, the pronation type estimation device 600 may include a communication unit 610, an image acquisition unit 620, a feature extraction unit 630, an evaluation unit 640, a storage unit 650, an output unit 660, and an analysis processing unit 670. The communication unit 610 of the pronation type estimation device 600 and the user terminal 200 or the device 500 that captures images of the feet may be connected, for example, via a network.

[0157] The image acquisition unit 620 may, for example, acquire a top-view image transmitted from a user terminal 200 or a device 500 that captures images of the feet, via the communication unit 610. The image acquisition unit 620 may acquire an image showing the top-view contour shape of the user's feet in a seated position as the top-view image. The image acquisition unit 620 may acquire a top-view image of one foot at a time for both the left and right feet, or it may acquire an image of either the left or right foot. Alternatively, the image acquisition unit 620 may acquire top-view and lateral views of the user's feet, or it may acquire a top-view or lateral view of the feet in a standing position.

[0158] The image acquisition unit 620 may include a measurement value acquisition unit 622 and an image generation unit 624. If three-dimensional measurement values ​​of the foot shape are transmitted from the user terminal 200 or the foot image capture device 500 instead of a top view image, the measurement value acquisition unit 622 may acquire the three-dimensional measurement values ​​via the communication unit 610. In this case, the image generation unit 624 may generate a three-dimensional model based on the three-dimensional measurement values, and a top view image, which is a two-dimensional image, may be generated from the three-dimensional model.

[0159] The feature extraction unit 630 may extract feature quantities for multiple foot parts from a top-view image. The feature quantities for multiple foot parts may be at least one of the following: (1) foot length, (2) foot width, (3) amount of indentation in the arch shape (hereinafter also referred to as "inner indentation amount"), and (4) amount of protrusion in the outer shape near the little toe ball (hereinafter also referred to as "outer protrusion amount"). The feature extraction unit 630 may include a foot length calculation unit 632, a foot width calculation unit 634, an indentation amount calculation unit 636, and an outtrusion amount calculation unit 638. The foot length calculation unit 632 may calculate the foot length from the top-view image. The foot width calculation unit 634 may calculate the foot width from the top-view image. The indentation amount calculation unit 636 may calculate the inner indentation amount from the top-view image. The outtrusion amount calculation unit 638 may calculate the outer protrusion amount from the top-view image.

[0160] The evaluation unit 640 may include a pronation estimation unit 642. The pronation estimation unit 642 may estimate the pronation type of the user's foot, who is the subject of measurement, using a pronation estimation algorithm. The pronation estimation unit 642 of the evaluation unit 640 may also be configured to estimate the degree of foot pronation based on a comparison between a feature quantity including at least one of foot length, foot width, medial indentation, and lateral protrusion and a reference value. The pronation estimation unit 642 may estimate which of several pronation types the user's foot falls under, for example, using a pronation estimation algorithm predetermined at the design stage by decision tree analysis. The pronation estimation unit 642 may estimate the pronation type for each of the user's left and right feet.

[0161] The memory unit 650 may include a reference memory unit 652 and a pronation type memory unit 654. The reference memory unit 652 may store, for example, reference values ​​for each of the feature quantities of multiple foot regions determined by decision tree analysis.

[0162] The pronation type memory unit 654 may store a plurality of pronation types, which are classified by the degree of foot pronation, and which include at least a first type in which the degree of pronation is higher than a predetermined standard, and a second type in which the degree of pronation is below a predetermined standard. The predetermined standard here may be, for example, "neutral pronation" in which the heel collapses moderately inward upon landing.

[0163] The output unit 660 may include a result output unit 662. The result output unit 662 may transmit information regarding the pronation type of the user's foot, which is the subject of measurement, as determined by the pronation estimation unit 642, to the user terminal 200 via the communication unit 610.

[0164] The analysis processing unit 670 may, during the design phase of the pronation type estimation device 600, determine a pronation estimation algorithm for estimating whether the degree of foot pronation corresponds to a first type or a second type, based on multiple feature quantities measured from images of the feet of multiple subjects. The analysis processing unit 670 may also determine the pronation estimation algorithm using decision tree analysis, particularly regression trees. Decision tree analysis may be performed in advance at a stage prior to estimating foot pronation for the user, for example, during the design phase of the footwear recommendation system 10 including the pronation type estimation device 600. The judgment procedure and judgment threshold for each feature quantity determined by decision tree analysis may be adopted as the pronation estimation algorithm in the foot pronation estimation process of the pronation estimation unit 642. The judgment threshold for each feature quantity determined by decision tree analysis may be stored in the reference storage unit 652 as a judgment criterion value for each feature quantity in the pronation estimation process. Candidate features for each foot region used to estimate foot pronation may include foot length, foot width, medial indentation, and lateral protrusion, all of which are features that can be extracted from a top-view image.

[0165] Decision tree analysis in the design phase may be performed using the following procedure. First, the three-dimensional heel eversion angle may be detected from video footage of the subject running barefoot using a motion capture system, and the actual pronation type may be determined. In particular, if the heel eversion angle is greater than a predetermined threshold X, it may be determined to be overpronation or type 1. Alternatively, a method may be used to detect the two-dimensional heel eversion angle from rear-facing video footage of the subject running barefoot on a treadmill. Furthermore, even if not barefoot, running may be performed while wearing shoes that do not have a pronation suppression function. This pronation type determination may be performed for n subjects, and they may be classified by pronation type. On the other hand, multiple foot feature quantities may be measured as target data for decision tree analysis of these subjects. As foot feature quantities, for example, foot length, foot width, medial indentation, and lateral protrusion may be extracted from top-view images of the foot.

[0166] Decision tree analysis may be performed with the classification of whether or not n subjects have overpronation as the dependent variable, and two or more elements from foot length, foot width, medial indentation, and lateral overhang as independent variables. Decision tree analysis may also be performed for all combination patterns by changing the combination of elements used as independent variables, such as combinations of two elements, three elements, or four elements from the four elements of foot length, foot width, medial indentation, and lateral overhang. In decision tree analysis, the maximum depth of the node may be set to 5, and the elements of the independent variables and their thresholds that minimize the squared error, which is the loss function for each branched node, may be determined regressively.

[0167] The classification results of subjects obtained by decision tree analysis may be compared with the classification results of pronation types based on three-dimensional eversion angles. If the classification results of all subjects match 100% as a result of the comparison, the combination of features can be considered an effective explanatory variable that can estimate foot pronation with high accuracy. The branching conditions and branching order in the decision tree analysis that were able to estimate foot pronation with high accuracy may be adopted in the pronation estimation algorithm used in the pronation estimation unit 642. The threshold values ​​for each feature determined as branching conditions may be stored in the reference storage unit 652 as reference values ​​for each feature in the pronation estimation algorithm. The reference storage unit 652 may store not only the reference values ​​for each feature, but also the pronation estimation algorithm itself. For example, if an algorithm or reference values ​​for each feature that can determine the foot pronation type with even greater accuracy is determined by decision tree analysis through subsequent additional experiments, the information stored in the reference storage unit 652 may be rewritten. This allows the pronation estimation algorithm and reference values ​​for each feature to be updated, and the estimation accuracy can be easily improved.

[0168] Figure 10 shows an illustrative tree diagram illustrating the results of a decision tree analysis for pronation estimation based on three elements: foot length, foot width, and inward indentation. In the example in Figure 10, measured values ​​with a sample size n of 11 are classified using decision tree analysis with a maximum node depth of 5. At the root node N10, "foot length" is determined regressively as the explanatory variable and "a predetermined value" as the threshold, and whether the foot length is less than or equal to a may be used as the branching condition.

[0169] If the foot length is less than or equal to a, leaf node N11, where the squared error is 0 and the sample size n is 1, may be classified as underpronation based on its eversion angle. If the foot length exceeds a, the branching point is node N12. At node N12, where the sample size n is 10, "foot width" is determined regressively as an explanatory variable and "a predetermined value b" as a threshold, and whether or not the foot width is less than or equal to b may be used as the branching condition.

[0170] If the foot width is less than or equal to b, the branching point may be node N13. At node N13 with a sample size n of 2, "foot width" is determined regressively as the explanatory variable and "a predetermined value c" as the threshold, and whether or not the foot width is less than or equal to c may be used as the branching condition. If the foot width is less than or equal to c, leaf node N14, where the squared error is 0 and the sample size n is 1, may be classified as overpronation if its eversion angle exceeds the threshold X. If the foot width exceeds c, leaf node N15, where the squared error is 0 and the sample size n is 1, may also be classified as overpronation if its eversion angle exceeds the threshold X.

[0171] If the foot width exceeds b at node N12, the branching destination may be node N16. At node N16 with a sample size n of 8, "foot width" may be regressively determined as an explanatory variable and "a predetermined value d" as a threshold, and the branching condition may be whether the foot width is d or less. If the foot width is d or less, the branching destination may be node N17. At node N17 with a sample size n of 3, "amount of inward indentation" may be regressively determined as an explanatory variable and "a predetermined value e" as a threshold, and the branching condition may be whether the amount of inward indentation is e or less. If the amount of inward indentation is e or less, leaf node N18, where the squared error is 0 and the sample size n is 2, may be classified as neutral pronation based on its average eversion angle. If the amount of inward indentation exceeds e, leaf node N19, where the squared error is 0 and the sample size n is 1, may also be classified as neutral pronation based on its eversion angle.

[0172] If the foot width exceeds d at node N16, the branching destination may be node N20. At node N20, where the sample size n is 5, the "amount of inward indentation" is determined regressively as the explanatory variable and the "predetermined value f" as the threshold, and the branching condition is whether the amount of inward indentation is less than or equal to f. If the amount of inward indentation is less than or equal to f, leaf node N21, where the squared error is approximately 0.9 and the sample size n is 4, may be classified as overpronation because its average eversion angle exceeds the threshold X. If the amount of inward indentation exceeds f, leaf node N22, where the squared error is 0 and the sample size n is 1, may be classified as neutral pronation based on its eversion angle.

[0173] By using decision tree analysis for classification, even if samples with significantly outward-angle values, such as leaf node N11, are included, suitable features and their thresholds for classification can be determined regressively. Therefore, classification can be performed appropriately without affecting the overall accuracy of pronation estimation.

[0174] The pronation estimation algorithm used in the pronation estimation unit 642 may be determined according to the procedure determined by the decision tree analysis in Figure 10. Here, the estimation process by the pronation estimation unit 642 does not determine all of overpronation, neutral pronation, and underpronation, but only estimates whether it is a first type or a second type. In other words, the estimation process to distinguish between neutral pronation and underpronation does not have to be performed. Also, the estimation process does not have to be performed when all branch destinations, such as nodes N13 and N17, result in the same classification. As a result, the foot pronation estimation algorithm adopted in the pronation estimation unit 642 may be simpler than the procedure by the decision tree analysis in Figure 10. The predetermined values ​​a, b, d, and f that serve as thresholds for branching conditions may be determined by decision tree analysis, may be part of the foot pronation estimation algorithm, or each may be stored in the reference storage unit 652 as a reference value for each feature.

[0175] Figure 11 shows a flowchart illustrating an example of the process of estimating foot pronation using a pronation estimation algorithm based on three elements: foot length, foot width, and medial indentation. In the example shown in Figure 11, branching decisions corresponding to nodes N10, N12, N16, and N20 in the decision tree analysis in Figure 10 may be used as the pronation estimation algorithm. The image acquisition unit 620 acquires a top view image of the user's foot (S1102), and the feature extraction unit 630 extracts foot length, foot width, and medial indentation as feature quantities for the foot area (S1104). The pronation estimation unit 642 may estimate that the foot is of the second type if the foot length is less than or equal to a predetermined value a (Y in S1106) (S1116). If the foot length exceeds the predetermined value a (N in S1106) and the foot width is less than or equal to a predetermined value b (Y in S1108), it may estimate that the foot is of the first type (S1114). If, in S1108, the foot width exceeds a predetermined value b (N in S1108), and the foot width is less than or equal to a predetermined value d (Y in S1110), it may be estimated to be the second type (S1116). If, in S1110, the foot width exceeds a predetermined value d (N in S1110), and the amount of inward indentation is less than or equal to a predetermined value f (Y in S1112), it may be estimated to be the first type (S1114), and if the amount of inward indentation exceeds a predetermined value f (N in S1112), it may be estimated to be the second type (S1116). Based on the estimation of whether it is the first type or the second type (S1114 and S1116), the output unit 660 outputs the pronation type (S1118), and the foot pronation estimation process ends. In the above flow, the processes of S1104, S1106, S1108, and S1120 may be branch determination processes corresponding to, for example, nodes N10, N12, N16, and N20 in Figure 10.

[0176] In the footwear recommendation process according to this embodiment, by using the pronation estimation process described with reference to Figures 9 to 11, etc., it becomes possible to more easily determine the pronation type of the user who is the subject of measurement.

[0177] Returning to Figure 7, in the footwear recommendation process according to this embodiment, in place of or in addition to at least a part of the above process, information regarding the rigidity of at least a portion of multiple footwear items of different sizes and structures may be acquired by the rigidity information acquisition unit 184 of the footwear recommendation device 100 (S772). The information regarding the rigidity of the footwear may be, for example, information regarding the rigidity provided by the footwear supplier. For example, the rigidity information acquisition unit 184 may be configured to acquire information regarding the rigidity of footwear from a product information database 300-6 provided by the footwear supplier. Alternatively, the rigidity information acquisition unit 184 may be configured to access the website of the footwear supplier or the like and acquire information regarding the rigidity of footwear.

[0178] In this embodiment, for example, information on the rigidity of the insole or upper part of the footwear may be acquired as part of the footwear information. The rigidity information acquisition unit 184 may be configured to acquire rigidity information for all footwear stored in the product information database 300-6, or it may be configured to acquire rigidity information for some of the footwear among the information on footwear stored in the product information database 300-6.

[0179] Furthermore, in this embodiment, based on the foot shape data acquired by the foot shape data acquisition unit 110 and the information regarding the rigidity of the footwear acquired by the rigidity information acquisition unit 184, the predicted deformation amount of each of the multiple pairs of footwear used by the user may be calculated by the predicted deformation amount calculation unit 186 (S774).

[0180] Furthermore, the deformation determination unit 187 may determine whether the predicted deformation amount calculated by the predicted deformation amount calculation unit 186 is less than or equal to the deformation amount threshold (S776). In this embodiment, the deformation amount threshold may be stored in the threshold database 300-5 described above, and the deformation determination unit 187 may be configured to perform the above determination based on the deformation amount threshold obtained from the threshold database 300-5.

[0181] Furthermore, as described later, in this embodiment, for example, if the predicted deformation amount calculated by the predicted deformation amount calculation unit 186 is determined by the deformation determination unit 187 to be below the deformation amount threshold, such footwear may be recommended to the user as footwear with a size and structure that suits the user.

[0182] Next, referring to Figures 5 and 6, similar to the footwear recommendation process described above, the footwear determination unit 140 of the footwear recommendation device 100 determines footwear with a size and structure suitable for the user based on the foot shape data acquired by the foot shape data acquisition unit 110 and the activity level estimated by the activity level estimation unit 130 (S778).

[0183] Next, the footwear recommendation unit 150 of the footwear recommendation device 100 recommends footwear that has a size and structure suitable for the user, as determined by the footwear determination unit 140 (S780).

[0184] Next, the footwear recommended by the footwear recommendation unit 150 is displayed on the user terminal 200 (S782).

[0185] With the above, the exemplary footwear recommendation process performed in the footwear recommendation system 10 in this embodiment is terminated.

[0186] In this embodiment, in addition to the user's foot shape data and activity level, the system may be configured to determine footwear with a size and structure suitable for the user based on, for example, the user's intended use of the footwear as estimated in the above processing (S722, etc.). Alternatively, or in addition to the above, the system may be configured to determine footwear with a size and structure suitable for the user based on the positional relationship between the user's foot and the footwear when wearing the footwear, the corrected foot shape data, and the activity level.

[0187] Similarly, in this embodiment, instead of or in addition to the above, the system may be configured to determine footwear with a size and structure suitable for the user based on the usage state of the footwear estimated by the above process (S758, etc.). Furthermore, in this embodiment, instead of or in addition to the above, the system may be configured to determine footwear with a size and structure suitable for the user based on the pronation type of the user estimated by the above process (S770, etc.). In this embodiment, the system may be configured to determine footwear with a size and structure suitable for the user based on one or more of the following: the stiffness data of the footwear obtained by the above process (S772, etc.), the predicted deformation amount calculated by the above process (S774, etc.), and the comparison result between the predicted deformation amount of the footwear and the deformation threshold determined by the above process (S778, etc.).

[0188] Furthermore, in cases where footwear with a suitable size and structure for a user is determined based on multiple factors, information, or data, such as when footwear with a suitable size and structure for a user is determined based on other factors in addition to the user's foot shape data and activity level, the footwear with a suitable size and structure for a user may be determined using, for example, a formula or model that calculates the degree of suitability of the footwear to the user by assigning predetermined different weights to multiple factors, information, or data.

[0189] In this embodiment, even when the system is configured to determine footwear with a size and structure suitable for the user based on any of the data, it is possible to improve the accuracy of recommending footwear with a size and structure suitable for the user.

[0190] Referring to Figure 12, an example of a footwear recommendation process that recommends footwear with a size and structure suitable for the user based on the above-mentioned information regarding the rigidity of the footwear will be explained. Figure 12 is a diagram showing a sequence of other exemplary footwear recommendation processes performed by the footwear recommendation system 10. Similar to the footwear recommendation processes exemplified in Figures 6 and 7, the footwear recommendation process exemplified in Figure 12 also recommends footwear based on foot shape data generated using a foot shape measuring device (a device 500 that captures images of the foot), such as a three-dimensional foot shape measuring device.

[0191] As shown in Figure 12, first, the user generates foot shape data of their feet using a device 500 that captures images of the feet, such as a three-dimensional foot shape measuring device (S1202).

[0192] Next, the foot image acquisition device 500 transmits the foot shape data generated using the foot image acquisition device 500 to the footwear recommendation device 100 (S1204).

[0193] Next, the footwear recommendation device 100 acquires foot shape data transmitted from the foot image acquisition device 500 using the foot shape data acquisition unit 110 (S1206).

[0194] Next, information regarding the rigidity of at least a portion of multiple footwear items of different sizes and structures is acquired by the rigidity information acquisition unit 184 of the footwear recommendation device 100 (S1208). The information regarding the rigidity of the footwear may be, for example, information regarding the rigidity provided by the footwear provider, similar to the footwear recommendation process described above with reference to Figure 7. For example, the rigidity information acquisition unit 184 may be configured to acquire information regarding the rigidity of footwear from a product information database 300-6 provided by the footwear provider, or the rigidity information acquisition unit 184 may be configured to access the website of the footwear provider and acquire information regarding the rigidity of footwear.

[0195] In this embodiment, information regarding the rigidity of at least a part of the footwear may include, for example, information regarding the rigidity of at least one of the upper, sole, forefoot, midfoot, and heel portions of the footwear. Alternatively, the rigidity of all parts of the footwear may be calculated in advance by the footwear manufacturer or other provider, and footwear having a size and structure suitable for the user, as described later, may be determined based on information regarding the rigidity of, for example, the upper and sole, the forefoot, midfoot, and heel, or the entire footwear (the entire footwear including the upper and sole), or based on information obtained by appropriately combining this information on rigidity.

[0196] Next, based on the foot shape data acquired by the foot shape data acquisition unit 110 and the information on the stiffness of the footwear acquired by the stiffness information acquisition unit 184, the predicted deformation amount of each of the multiple pairs of footwear used by the user is calculated by the predicted deformation amount calculation unit 186 (S1210).

[0197] Next, the deformation determination unit 187 determines whether the predicted deformation amount calculated by the predicted deformation amount calculation unit 186 is less than or equal to the deformation amount threshold (S1212). Referring to Figure 7, similar to the footwear recommendation process described above, the deformation amount threshold may be stored in the threshold database 300-5, for example, and the deformation determination unit 187 may perform the above determination based on the deformation amount threshold obtained from the threshold database 300-5.

[0198] In this embodiment, the rigidity of the user's foot may be further calculated in place of, or in addition to, at least a part of, the above processing (S1214). Furthermore, in the process of acquiring foot shape data by the foot shape data acquisition unit 110, for example, the user's foot shape data may be acquired when the user is in a static standing position. Here, the user's foot shape data when the user is in a static standing position may include at least one of the foot length and arch height when the user is in a static standing position.

[0199] In this embodiment, foot stiffness may be defined, for example, from the relationship between the load acting on the foot and the arch height. More specifically, foot stiffness may be defined by measuring the foot shape in both an unloaded state (e.g., sitting or a state with half the body weight applied) and a loaded state (e.g., a static standing position), and then determining the change in arch height between the two states. For example, foot stiffness may be defined by the change in arch height relative to half the body weight. In this case, the change in arch height may be calculated, for example, based on the difference between the arch height when standing with both feet, where half the body weight can act on the foot being measured, and the arch height when standing with one foot, where the entire body weight can act on the foot being measured. Based on the change in arch height thus calculated, foot stiffness may be defined, for example, as the change in arch height relative to half the body weight (i.e., foot stiffness = change in arch height / half the body weight). In this way, the foot stiffness may be configured to evaluate, for example, the flexibility of the joints, particularly in the arch area. In this embodiment, the rigidity of the foot may be defined, for example, by the relationship between the load and the change in foot length, instead of the relationship between the load and the change in arch height described above.

[0200] When foot stiffness is calculated, for example, information about the user's weight may be obtained, and the foot stiffness may be calculated based on the information about the user's weight and at least one of the user's foot length and arch height in a static standing position.

[0201] In addition, in this embodiment, for example, data relating to at least one activity performed by the user while using the footwear may be acquired (S1216).

[0202] In this embodiment, instead of or in addition to at least a part of the above processing, an activity threshold, which is a threshold related to user activity, may also be obtained (S1218). The activity threshold may be stored in a threshold database 300-5, for example, and retrieved from the threshold database 300-5.

[0203] The activity data, which is data about the user's activities that has been acquired, is compared with the activity threshold (S1220), and the level of the user's activity may be estimated based on the result of this comparison (S1222).

[0204] In the footwear recommendation process of this embodiment, instead of or in addition to at least a part of the above process, for example, questionnaire data entered by the user may be acquired by the questionnaire data acquisition unit 162. In this case, for example, first, the questionnaire screen may be displayed on the user terminal 200 (S1224).

[0205] The user terminal 200 may accept input from the user regarding the displayed questionnaire screen (S1226). The display unit of the user terminal 200 may display a questionnaire screen that includes an input field where information regarding the user's footwear size preferences can be entered, and the user may input information regarding the user's footwear size preferences into the user terminal 200.

[0206] For example, survey data including information about the user's footwear size preferences may be transmitted from the user terminal 200 to the footwear recommendation device 100 (S1228).

[0207] The transmitted questionnaire data may be acquired by the questionnaire data acquisition unit 162 of the footwear recommendation device 100 (S1230).

[0208] In the footwear recommendation device 100, for example, the positional relationship estimation unit 164 may estimate the positional relationship between the user's foot and the footwear when the user is wearing the footwear, based on the questionnaire data acquired by the questionnaire data acquisition unit 162 (S1232).

[0209] In the above process (S1212), if the deformation determination unit 187 determines that the predicted deformation amount calculated by the predicted deformation amount calculation unit 186 is less than or equal to the deformation amount threshold, then the footwear may be determined to have a size and structure that is suitable for the user (S1234).

[0210] Next, referring to Figures 5, 6, and 7, the footwear recommendation unit 150 of the footwear recommendation device 100 recommends footwear that has a size and structure suitable for the user determined by the footwear determination unit 140, similar to the footwear recommendation process described above (S1236).

[0211] Next, the footwear recommended by the footwear recommendation unit 150 is displayed on the user terminal 200 (S1238).

[0212] With the above, the exemplary footwear recommendation process performed in the footwear recommendation system 10 in this embodiment is terminated.

[0213] In this embodiment, in addition to the rigidity of the footwear, the system may be configured to determine footwear with a size and structure suitable for the user based on, for example, the rigidity of the user's foot calculated by the above process (S1214, etc.). Alternatively, the system may be configured to determine footwear with a size and structure suitable for the user based on, for example, the user's activity level estimated by the above process (S1222, etc.). Furthermore, in this embodiment, the system may be configured to determine footwear with a size and structure suitable for the user based on the positional relationship between the user's foot and the footwear when the user is wearing the footwear, estimated in the above process (S1232, etc.). Alternatively, the system may be configured to determine footwear with a size and structure suitable for the user based on any one of the above-mentioned rigidity of the user's foot, the user's activity level, and the positional relationship between the user's foot and the footwear when the user is wearing the footwear, or two or three of these.

[0214] In the footwear recommendation process described above, for example, the deformation of the footwear when worn by the user and the contact state between the foot and the footwear can be calculated using the rigidity of the footwear and foot shape data to determine footwear with a size and structure that suits the user. If a user wears footwear that is too small, the upper part may not be able to wrap around the foot, the distance between the eyelets may increase, and areas of strong contact may occur, which may lead to injury or pain. Conversely, if a user wears footwear that is too large, a gap will be created between the footwear and the foot, preventing the footwear from moving as intended and potentially reducing performance. For this reason, for example, thresholds may be set for the distance between eyelets and the contact pressure between the footwear and the foot, and footwear of a size that is smaller than the threshold may be recommended.

[0215] Figure 13 is a flowchart illustrating an exemplary footwear recommendation method according to an embodiment of the present disclosure. The footwear recommendation method according to an embodiment of the present disclosure may be performed, for example, by the footwear recommendation system 10 described above. Alternatively, the footwear recommendation method according to an embodiment of the present disclosure may be performed, for example, by the footwear recommendation device 100 described above.

[0216] First, as shown in Figure 13, the user's footprint data is acquired (S1302).

[0217] Next, the user's product purchase data is obtained (S1304).

[0218] Next, the user's activity level is estimated based on the acquired purchase data (S1306).

[0219] Next, based on the acquired foot shape data and the estimated activity level, footwear with a size and structure suitable for the user is determined (S1308).

[0220] Next, we recommend at least one pair of footwear with a suitable size and structure for the user (S1310).

[0221] This concludes the footwear recommendation method illustrated by this embodiment.

[0222] Figure 14 is a flowchart illustrating another exemplary footwear recommendation method according to the embodiments of this disclosure. Similar to the footwear recommendation method described above with reference to Figure 13, the other exemplary footwear recommendation method may also be performed, for example, by the footwear recommendation system 10 described above, or, for example, by the footwear recommendation device 100 described above.

[0223] First, as shown in Figure 14, the user's footprint data is acquired (S1402).

[0224] Next, information regarding the rigidity of at least a portion of several footwear items with different sizes and structures is obtained (S1404).

[0225] Next, based on the acquired user foot shape data and information regarding the rigidity of the footwear, the predicted deformation amount of each of the multiple footwear items used by the user is calculated (S1406).

[0226] Furthermore, it is determined whether the calculated predicted deformation amount is below the deformation threshold (S1408).

[0227] Next, we recommend footwear with a size and structure such that the predicted deformation amount is below the deformation threshold (S1410).

[0228] This concludes the description of the other exemplary footwear recommendation method according to this embodiment.

[0229] [Summary of the effects of this disclosure] According to one aspect of this disclosure, footwear with a size and structure suitable for the user can be determined based on foot shape data, user footwear purchase data, and information such as activity level. For example, according to the above aspect of this disclosure, footwear that is more suitable for the user's preferences and intended use can be recommended.

[0230] Alternatively, according to another aspect of the present disclosure, based on foot shape data and information on the stiffness of at least a portion of several footwear items of different sizes and structures, it is possible to calculate the predicted deformation when a user wears footwear and determine footwear with a size and structure that suits the user. According to another aspect of the present disclosure, for example, footwear with a stiffness that better fits the user's foot shape can be recommended.

[0231] Therefore, in either embodiment, it is possible to determine footwear with a size and structure that suits the user based on an evaluation of the user's individual physical characteristics and other information about the user, and thus recommend footwear that can improve user satisfaction.

[0232] [Aspects] (1) A method for recommending footwear according to one aspect of the present disclosure is a method for recommending footwear having a size and structure suitable for a user using a computer, comprising: acquiring foot shape data of the user; acquiring product purchase data of the user; estimating the user's activity level based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the activity level; and recommending at least one piece of footwear having the size and structure suitable for the user.

[0233] According to the footwear recommendation method described in (1) above, footwear with a suitable size and structure can be determined based on foot shape data and information such as the user's footwear purchase history, usage status, and activity level, so that footwear that is more suitable to the user's preferences and intended use can be recommended.

[0234] (2) The method for recommending footwear described in (1) above may further include calculating the user's foot length and at least one of the user's foot width and foot circumference based on the foot shape data.

[0235] According to the footwear recommendation method described in (2) above, the accuracy of foot shape data used to determine footwear with a size and structure that suits the user can be improved.

[0236] (3) In the method for recommending footwear described in (1) or (2) above, estimating the user's activity level includes estimating the user's activity level and / or the intended use of the footwear based on the output result when the user's purchase data is input to a pre-trained model generated by machine learning using as training data information provided by a provider of multiple footwear for each of the multiple footwear items, the purchase data of multiple other users other than the user, and the activity history information of each of the multiple other users.

[0237] According to the footwear recommendation method described in (3) above, it is possible to improve at least one of the following: the accuracy of estimating the user's activity level and the accuracy of estimating how the user intends to use the footwear.

[0238] (4) A method for recommending footwear as described in any of (1) to (3) above, further comprising: obtaining questionnaire data entered by the user and including information on the user's preference for footwear size; estimating the positional relationship between the user's foot and the footwear when the user wears the footwear based on the questionnaire data; and correcting the foot shape data based on the user's preference for footwear size, wherein determining the footwear having the size and structure suitable for the user includes determining the footwear having the size and structure based on the positional relationship between the user's foot and the footwear when the footwear is worn, the corrected foot shape data, and the activity level.

[0239] According to the footwear recommendation method described in (4) above, in addition to the level of activity, footwear with a size and structure that suits the user is determined based on corrected foot shape data, taking into account information about the user's footwear size preferences, such as whether the user prefers to wear footwear that is larger or smaller than the size that suits their feet. This makes it possible to improve the accuracy of recommending footwear that suits the user's preferences.

[0240] (5) In the method for recommending footwear described in (4) above, obtaining the questionnaire data includes displaying an image of the shape of the user's feet and receiving input from the user regarding the image of the shape of their feet, which may cause discomfort when the user wears the footwear.

[0241] According to the footwear recommendation method described in (5) above, the user's concerns are taken into consideration when determining the footwear, so it is possible to determine and recommend footwear with a size and structure that is more suitable for the user's preferences.

[0242] (6) The method for recommending footwear described in any of (1) to (5) above further comprises: obtaining an image of footwear after use that the user has worn; obtaining an image of footwear before use; calculating at least one of the location and amount of wear caused by the user's use of the footwear by comparing the image of footwear after use with the image of footwear before use; and estimating the user's usage condition of the footwear based on the at least one of the location and amount of wear, and determining the footwear having the size and structure that suits the user, further based on the usage condition of the footwear.

[0243] According to the footwear recommendation method described in (6) above, it is possible to estimate the user's wearing habits and usage based on photos provided by the user, making it possible to determine a structure that is more suitable for the user's activities.

[0244] (7) The method for recommending footwear described in any of (1) to (6) above further comprises: obtaining a top view image of the user's foot; extracting feature quantities of a predetermined part that shows the top view contour shape of the user's foot from the top view image; and estimating the pronation type of the user's foot based on a comparison of the feature quantities of the predetermined part with a predetermined reference value, and determining the footwear having the size and structure that suits the user further determines the footwear having the structure that suits the user based on the pronation type.

[0245] According to the footwear recommendation method described in (7) above, the user's foot pronation type can be calculated, which makes it possible to further improve the accuracy of footwear recommendations to users.

[0246] (8) The method for recommending footwear described in any of (1) to (7) above further comprises: obtaining information on the rigidity of at least a portion of a plurality of footwear of different sizes and structures; calculating a predicted deformation amount of each of the plurality of footwear when used by the user, based on the user's foot shape data and the information on the rigidity of the footwear; and determining whether the predicted deformation amount is less than or equal to a deformation threshold, wherein recommending at least one of the footwear having the size and structure that suits the user includes recommending the footwear having the size and structure such that the predicted deformation amount is less than or equal to the deformation threshold.

[0247] According to the footwear recommendation method described in (8) above, the amount of deformation of the footwear due to user use can be predicted. For example, footwear that deforms less due to user use can be determined as footwear with a size and structure that suits the user, thus further improving the accuracy of footwear recommendations to users.

[0248] (9) An information processing device according to one aspect of the present disclosure is an information processing device for recommending footwear having a size and structure suitable for a user, which performs the following: acquiring foot shape data of the user; acquiring product purchase data of the user; estimating the user's activity level based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the activity level; and recommending at least one pair of footwear having the size and structure suitable for the user.

[0249] According to the information processing device described in (9) above, foot shape data and information such as the user's footwear purchase history, usage status, and activity level can be used to determine footwear with a size and structure that suits the user, so that footwear that is more suitable to the user's preferences and intended use can be recommended.

[0250] The embodiments described above are provided to facilitate understanding of this disclosure and are not intended to limit it. The flowcharts, sequences, elements, and their arrangement, materials, conditions, shapes, and sizes described in the embodiments are not limited to those exemplified and can be modified as appropriate. Furthermore, configurations shown in different embodiments can be partially substituted or combined.

Claims

1. A method for recommending footwear having a size and structure suitable for a user using a computer, comprising: acquiring foot shape data of the user; acquiring product purchase data of the user; estimating the user's activity level based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the activity level; and recommending at least one pair of footwear having the size and structure suitable for the user.

2. The recommended method according to claim 1, further comprising calculating the user's foot length and at least one of the user's foot width and foot circumference based on the foot shape data.

3. The recommendation method according to claim 1, wherein estimating the user's activity level includes estimating the user's activity level and / or the intended use of the footwear based on the output result when the user's purchase data is input to a pre-trained model generated by machine learning, which uses information on a pre-set recommended athletic ability level for each of the multiple footwear items provided by a provider of multiple footwear items, the purchase data of each of several other users other than the user, and the activity history information of each of the several other users as training data.

4. The recommendation method according to claim 1, further comprising: obtaining questionnaire data entered by the user and including information on the user's footwear size preferences; estimating the positional relationship between the user's foot and the footwear when the user wears the footwear based on the questionnaire data; and correcting the foot shape data based on the user's footwear size preferences, wherein determining the footwear having the size and structure suitable for the user includes determining the footwear having the size and structure based on the positional relationship between the user's foot and the footwear when the footwear is worn, the corrected foot shape data, and the activity level.

5. The recommended method according to claim 4, wherein obtaining the survey data includes displaying an image of the user's foot shape and receiving input from the user regarding information about areas of the foot shape that cause discomfort to the user when wearing the footwear.

6. The recommended method according to claim 1, further comprising: obtaining an image of footwear after use that the user has worn; obtaining an image of the footwear before use; calculating at least one of the location and amount of wear caused by the user's use of the footwear by comparing the image of the footwear after use with the image of the footwear before use; and estimating the user's usage condition of the footwear based on the at least one of the location and amount of wear, wherein determining the footwear having the size and structure suitable for the user is determined based on the usage condition of the footwear.

7. The recommended method according to claim 1, further comprising: obtaining a top view image of the user's foot; extracting feature quantities of a predetermined part that shows the top view contour shape of the user's foot from the top view image; and estimating the pronation type of the user's foot based on a comparison of the feature quantities of the predetermined part with a predetermined reference value, wherein determining the footwear having the size and structure suitable for the user is determined based on the pronation type.

8. The recommendation method according to claim 1, further comprising: obtaining information on the rigidity of at least a portion of a plurality of footwear of different sizes and structures; calculating a predicted deformation amount of each of the plurality of footwear when used by the user, based on the user's foot shape data and the information on the rigidity of the footwear; and determining whether the predicted deformation amount is less than or equal to a deformation threshold, wherein recommending the at least one footwear having the size and structure that suits the user includes recommending the footwear having the size and structure such that the predicted deformation amount is less than or equal to the deformation threshold.

9. An information processing device for recommending footwear having a size and structure suitable for a user, the device performing the following actions: acquiring foot shape data of the user; acquiring product purchase data of the user; estimating the user's activity level based on the purchase data; determining footwear having a size and structure suitable for the user based on the foot shape data and the activity level; and recommending at least one pair of footwear having the size and structure suitable for the user.

Images