JP7158146B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

Traditionally, shoes have been produced according to wooden patterns handcrafted by craftsmen, and standardization has been delayed. In order to perform optimal matching, it is necessary to know the inner dimensions of the shoe, taking account of the elongation and deformation of the shoe. Moreover, since the error is large, it is necessary to use a destructive method, which is costly.

Japanese Unexamined Patent Application Publication No. 2012-033128

For this reason, there is a demand for a new technique that enables uniform and easy measurement of items such as shoes whose shapes are not standardized.

The present invention has been made in view of this situation, and aims to provide a new method that can easily and equally match even items whose shape is not standardized. .

In order to achieve the above object, an information processing device according to one aspect of the present invention includes:
Based on the measurement data of the item, identifying the facing, detecting one or more landmark points, calculating a reference symbol based on a predetermined rule for eliminating the design of the item, measurement means for calculating each measurement value of a plurality of items based on the landmark points and the reference symbol, and generating information including at least each of the measurement values of the plurality of items as measurement data of the item. .

According to the present invention, even items whose shapes are not standardized can be equally and easily matched.

1 is a block diagram showing a configuration example of an information processing system including an information processing device to which the present invention is applied; FIG. FIG. 2 is a conceptual diagram schematically showing processing such as machine learning, which is a prerequisite for matching in this service to which the information processing system shown in FIG. 1 is applied. 1 is a configuration diagram of an information processing system including a matching device that is an embodiment of an information processing device of the present invention; FIG. 2 is a conceptual diagram schematically showing processing such as matching in this service to which the information processing system shown in FIG. 1 is applied; FIG. 2 is a block diagram showing an example of a hardware configuration of a matching device 5 in the information processing system of FIG. 1 capable of realizing this service (matching); FIG. Functional block diagram showing an example of a functional configuration capable of realizing processing such as machine learning shown in FIG. 2 among the processing executed by the information processing system 1 of FIG. is. FIG. 4 is a diagram showing an outline of the appearance configuration of a foot for explaining the standardized foot measurement method; FIG. 4 is a diagram showing the outline of the external configuration of a shoe and a shoe anchor for explaining the standardized shoe measurement method; 4 is a functional block diagram showing an example of a functional configuration capable of realizing processing such as matching shown in FIG. 3 among the processing executed by the information processing system 1 of FIG. 1; FIG. It is a figure explaining an example of the matching method determined based on the result of machine learning. FIG. 4 is a diagram showing an outline of processing that can be performed by the information processing system in FIG. 1 and that is different from the example in FIG. 3 ; FIG. 3 is a diagram showing an overview of processing that can be performed by the information processing system in FIG. 1 and that performs machine learning that is different from the example in FIG. 2 ; An example of the measurement data of the user U (including the tester T) when standardized measurement is performed when the item is clothing is shown. An example of measurement data of an item when standardized measurement is performed when the item is clothing (jacket) is shown. It is an example of a mock screen of an EC site. It is an example of a mock screen of an EC site. It is an example of a mock screen of an EC site.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing a configuration example of an information processing system including an information processing device to which the present invention is applied.
The information processing system shown in FIG. It is configured to include a measurement DB 12 and an evaluation DB 13 .
The shoe measurement device 1 through the user terminal 6 and the shoe measurement DB 11 through the evaluation DB 13 are interconnected via a predetermined network N such as the Internet.

An outline of a service (hereinafter referred to as "this service") realized by using such an information processing system in FIG. 1 will be described below.
This service can measure even items whose shape is not standardized (e.g., shoes) equally and easily, and match users who wish to purchase them (recommendation of recommended shoes, etc.). It is a service that can According to this service, as will be described later, since the tendencies seen in the shape of the user's body and the shape of the item are captured abstractly, it is possible to match them equally and easily without necessarily comparing the same position. It can be performed. Furthermore, since the error at the time of measurement is statistically captured, practical matching can be performed even for measured values obtained by inexpensive sensors that are susceptible to errors.
The item to which this service is applied is not particularly limited as long as it is worn on at least a part of the user's body, but in the following example, it is assumed to be shoes.

FIG. 2 is a conceptual diagram schematically showing processing such as machine learning, which is a prerequisite for matching in this service to which the information processing system shown in FIG. 1 is applied.

Here, in modeling the matching object, actual shoes may be used for measurement, but in this embodiment, m shoe anchors Sh1 to Shm (where m is an integer value of 1 or more) are used. When it is not necessary to distinguish each of the shoe anchors Sh1 to Shm individually, they are hereinafter collectively referred to as "shoe anchor Sh".
At step Sa, the shoe measuring apparatus 1 scans the shoe anchors Sh1 to Shm to generate 3D scan data Ds1 to Dsm.
In step Sb, the shoe measurement apparatus 1 applies a shoe measurement method devised by the present inventors and adopted as a standard in this embodiment (details will be described later) to each of the 3D scan data Ds1 to Dsm. However, hereinafter referred to as a "standardized shoe measurement method"), data obtained as a result of the measurement (hereinafter referred to as "shoe measurement data") Ks1 to Ksm are stored in the shoe measurement DB 11. Let
In the following, when it is not necessary to distinguish each of the shoe measurement data Ks1 to ksm, they are collectively referred to as "shoe measurement data Ks".

On the other hand, each of n natural persons T1 to Tn (where n is an integer value of 1 or more) is asked to actually wear m pieces of shoes and evaluate them. Such natural persons T1 to Tn are hereinafter referred to as "testers T1 to Tn", respectively. When it is not necessary to distinguish each of the testers T1 to Tn individually, they are collectively referred to as "testers T" hereinafter.
In step Sc, the tester's foot measurement device 2 generates 3D scan data Dt1 to Dtn by scanning both feet of testers T1 to Tn.
In step Sd, the tester's foot measurement device 2 applies the foot measurement method (details will be described later, but hereinafter referred to as a "standardized foot measurement method"), and the data obtained as a result of the measurement (hereinafter referred to as "foot measurement data") Kt1 to Ktm are stored in the foot measurement DB 12, respectively. be memorized.
In the following, when there is no need to individually distinguish the foot measurement data Kt1 to ktn, they are collectively referred to as "foot measurement data Kt".
Further, evaluation data Ht1 to Htn regarding comfort when m shoes are actually worn are obtained for each of the testers T1 to Tn and stored in the evaluation DB 13. Stored.
In addition, hereinafter, when it is not necessary to distinguish each of the evaluation data Ht1 to Htn, they are collectively referred to as "evaluation data Ht".

The learning device 3 combines shoe measurement data Ks1 to Ksm of m shoes (shoe anchors Sh1 to Shm) with foot measurement data Kt1 to Ktn of n testers T1 to Tn, respectively; Machine learning is performed using each of evaluation data Ht1 to Htn for m shoes of each of n testers T1 to Tn.
As a result of this learning, for example, trends in wearing comfort are obtained for each of various combinations of a predetermined foot and a predetermined shoe. It should be noted here that the shoe measurement data Ks and the foot measurement data Kt do not necessarily include data measured at the same position. In other words, even if measurements are taken at different positions, machine learning can provide trends in comfort for various combinations of a given foot and a given shoe.
By using such learning results, it becomes possible to grasp the tendency of the shapes of the feet and shoes in an abstract manner, and it is possible to perform matching (details will be described later) without necessarily comparing the same position. becomes possible.
In addition, by using such a machine learning method, it becomes possible to treat errors during measurement statistically, enabling practical matching even with scans using inexpensive sensors with large errors.

FIG. 3 is a conceptual diagram schematically showing processing such as matching in this service to which the information processing system shown in FIG. 1 is applied.

In step Sf, the user foot measurement device 4 scans both feet of the user U to generate 3D scan data Du.
In step Sg, the user foot measurement device 4 measures the 3D scan data Du according to the standardized foot measurement method, and stores the foot measurement data Ku obtained as a result of the measurement in the foot measurement DB 12 .

At step Si, the matching device 5 combines the foot measurement data Ku of the user U obtained at step Sg with the shoe measurement data Ks1 to Ks1 to Ks1 to Shm for each of the m shoes (shoe anchors Sh1 to Shm) described above with reference to FIG. Each Ksm is used to perform matching (for estimating which shoes are comfortable for the user U).
Here, the matching device 5 may acquire the preference of the user U in step Sh, and perform matching considering the preference in step Si, instead of simply comparing the measurement data. As a result, for example, if user U prefers tight-fitting shoes, size B, which is smaller than size A, is suitable for user U, even if it is generally determined that shoes of size A are comfortable to wear. Matching suitable for each user U is possible.
In step Sj, the matching device 5 supplies shoes suitable for the user U (that the user U will feel comfortable wearing) to the user U (user terminal 6) based on the result of matching in step Si. recommended against.

As necessary, the comfort when the user U actually wears the recommended shoes (shoe anchor Sh: h is an arbitrary integer value from 1 to m) is evaluated. In this case, the user U's evaluation data Hu is stored in the evaluation DB 13 .
Then, when the evaluation data Hu of the user U, the foot measurement data Ku of the user U, and the shoe measurement data Ksk of the recommended shoes (shoe anchor Sh) are provided to the learning device 3, the learning device 3 performs , machine learning (relearning). In this way, the actual recommendation results and their evaluations are fed back and re-learning is performed, which enables more accurate matching.

FIG. 4 is a block diagram showing an example of the hardware configuration of the matching device 5 in the information processing system of FIG. 1 capable of realizing this service (matching).

The matching device 5 includes a CPU (Central Processing Unit) 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23, a bus 24, an input/output interface 25, an output section 26, and an input section 27. , a storage unit 28 , a communication unit 29 , and a drive 30 .

The CPU 21 executes various processes according to programs recorded in the ROM 22 or programs loaded from the storage unit 28 to the RAM 23 .
The RAM 23 also stores data necessary for the CPU 21 to execute various processes.

The CPU 21 , ROM 22 and RAM 23 are interconnected via a bus 24 . An input/output interface 25 is also connected to this bus 24 . An output unit 26 , an input unit 27 , a storage unit 28 , a communication unit 29 and a drive 30 are connected to the input/output interface 25 .

The output unit 26 includes a display, a speaker, and the like, and outputs various information as images and sounds.
The input unit 27 is composed of a keyboard, a mouse, etc., and inputs various information.

The storage unit 28 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data.
The communication unit 29 communicates with other devices via a network N including the Internet.

A removable medium 31 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory is mounted in the drive 30 as appropriate. A program read from the removable medium 31 by the drive 30 is installed in the storage unit 28 as necessary.
The removable medium 31 can also store various data stored in the storage unit 28 in the same manner as the storage unit 28 .

Note that the shoe measuring device 1, the tester's foot measuring device 2, the learning device 3, the user's foot measuring device 4, and the user terminal 6 can each adopt a hardware configuration similar to that shown in FIG. Therefore, description of these hardware configurations is omitted.

FIG. 5 shows an example of a functional configuration capable of realizing processing such as machine learning shown in FIG. 2 among the processing executed by the information processing system 1 of FIG. It is a functional block diagram showing.

As shown in FIG. 5, in the shoe measuring device 1, a scanning unit 111 and a standardized shoe measuring unit 112 function.
In the tester foot measurement device 2, a scanning section 121, a standardized foot measurement section 122, and an evaluation acquisition section 123 function.

The scanning unit 111 of the shoe measuring device 1 scans the shoe anchor Sh to generate the 3D scan data Ds.
The standardized shoe measurement unit 112 measures the 3D scan data Ds according to the standardized shoe measurement method, and stores the shoe measurement data Ks obtained as a result of the measurement in the shoe measurement DB 11 .
Here, the shoe measurement data Ks of the shoe (or shoe anchor Sh) can be stored in the shoe measurement DB 11 in association with various information related to the shoe. Specifically, for example, the 3D scan data Ds can be linked to the shoe measurement data Ks. Further, for example, information on the type of material for each part of the shoe and information on properties of the material such as tensile strength (specific strength) can be linked to the shoe measurement data Ks.

On the other hand, the scanning unit 121 of the tester's foot measurement device 2 scans both feet of the tester T to generate 3D scan data Dt.
The standardized foot measurement unit 122 measures the 3D scan data Dt according to the standardized foot measurement method, and stores the foot measurement data Kt obtained as a result of the measurement in the foot measurement DB 12 .
Here, the foot measurement data Kt of the tester T can be associated with various information related to the tester T. FIG. Specifically, for example, the 3D scan data Dt can be linked to the foot measurement data Kt. In addition, for example, information such as gender, age, weight, average number of steps per day, shoe purchase history and return history, shoes worn often, shoes not interested, favorite brands, disliked brands, etc. Various information can be linked to the foot measurement data Kt. Further, for example, information such as the address and occupation of the tester T may be linked to the foot measurement data Kt. When a large number of foot measurement data Kt and the shoe measurement data Ks described above are obtained, these data can be utilized as big data for various purposes such as various analyses.
The evaluation acquisition unit 123 also acquires the evaluation data Ht indicating the evaluation of comfort when the tester T actually wears each shoe, and stores the evaluation data Ht in the evaluation DB 13 .

Here, the standardized foot measurement method will be described with reference to FIG. 6, and then the standardized shoe measurement method will be described with reference to FIG.
FIG. 6 is a diagram showing an outline of the appearance configuration of a foot for explaining the standardized foot measurement method.
FIG. 7 is a diagram showing the outline of the external configuration of a shoe and a shoe anchor for explaining the standardized shoe measurement method.

The standardized foot measurement unit 122 of the tester's foot measurement device 2 performs measurement according to the standardized foot measurement method, for example, as follows.

The standardized foot measurement unit 122 identifies the “front”.
That is, the standardized foot measurement unit 122 uses PCA (principal component analysis) on the point group of the 3D scan data Dt of the foot of the tester T to determine the direction in which the distribution of the data spreads widely, and determines the facing direction. uniquely determined. This eliminates the need for the tester T to strictly align the directions of the feet during measurement.
In other words, in order to extract and compare lengths and angles from feet that can have various shapes according to a certain rule, it is first necessary to determine a reference axial direction. Therefore, the standardized foot measurement unit 122 defines the axis along which the shape of the footprint of the foot is most widely distributed in the 3D scan data Dt as the traveling direction axis, takes the direction of gravity as the vertical axis as it is, and divides the traveling direction axis and the vertical axis into By defining the orthogonal axis as the left-right axis, we specify "facing".

The standardized foot measurement unit 122 detects the "landmark point L".
That is, the standardized foot measurement unit 122 detects landmark points L such as the tip of the toe and the top of the heel using the features of the shape of the foot. Points that are difficult to extract from shape characteristics alone (ball joint (toe axis), base of thumb, end points of thumb and little finger) are measured by attaching colored markers to the feet of the tester T, and using the standardized foot measurement unit. 122 decides based on that.

The standardized foot measurement unit 122 obtains a "measurement value".
That is, the standardized foot measurement unit 122 performs geometric calculation based on the landmark points L thus obtained, and treats the values obtained by the calculation as standardized measurement values.

The following measurements are used.
"Foot Circumference A": Circumference of the foot when the foot is sliced by the ball joint J (L).
"Foot Width B": Linear distance between ball joints J (L).
“Foot length C”: the length of the toe (most forward point) and heel vertex (most backward point) on the floor plane.
"Heel Shape D", "Toe Height E", "Toe Shape F", and "Distortion G".
In addition, the following measured values may be used as necessary.
"Heel length": length in a fixed ratio to the leg length C;
"Heel Width": The width of the foot on the plane extended forward by the length of the heel from the posteriormost point.
"Heel Depth": The distance (depth) from the point vertically extended upward from the heel apex position to the foot.
"Toe Width": The distance between the endpoints of the base of the thumb and the base of the little finger.
"Height of base of thumb, thumb and little finger": Height from each landmark point L to the floor surface.

On the other hand, the standardized shoe measurement unit 112 of the shoe measurement device 1 performs measurement according to the standardized shoe measurement method, for example, as follows.
That is, conventionally, there are various methods for measuring the inner dimensions of shoes (photographing by CT, taking a mold using plaster or the like, measuring a mold (wood pattern) at the time of manufacturing, etc.). However, when machine learning is used as in this embodiment, only the relative differences that characterize the individual need to be known, so it is sufficient to obtain the following "measurement values". In other words, any method (various name methods) for obtaining the following "measurement values" is a standardized shoe measurement method.

The standardized shoe measurement unit 112 determines the "measurement value" by specifying the "front" and detecting the "landmark point L" in the same manner as in the standardized foot measurement method described above with reference to FIG.

The standardized shoe measurement unit 112 also obtains the next reference symbol (line, plane).
The following reference symbols are required according to the following rules to eliminate shoe design.
"Toe Position"
(Rule) Due to the design, there is a hollow part where the foot cannot enter, so in order to eliminate the influence of that part, the position where the foot circumference A is constant (eg 100 mm) is the toe position.
"Ball joint (the connecting part of the bone that connects the toe and heel) position"
(Rule) Let the point farthest laterally correspond to the ball joint of the foot.

The standardized shoe measurement unit 112 calculates "foot circumference A", "foot width B", "foot length C", " "Heel shape D", "toe height E", "toe shape F", "distortion G", etc. are obtained as "measured values".

According to the standardized shoe measurement method, for the same reason as the standardized foot measurement method, it is necessary to determine the reference axial direction (orientation) in the case of shoes as well. In addition, unlike a leg with bones inside, the position of the ball joint is indeterminate, so it is necessary to stably acquire the position.
Therefore, as shown in FIG. 7, a shoe anchor Sh having a shape that perfectly fits the toe of the foot is created, and three-dimensional measurement (scanning) is performed together with the shoe anchor Sh stuffed into the shoe. As a result, the reference axis (facing) and the reference symbol based on the shoe anchor Sh are obtained, and each measurement value is appropriately obtained based on these.
In this way, the standardized shoe measurement unit 112 can construct a model (shoe measurement data Ks) from which design elements such as the toe are eliminated by using the shoe anchor Sh as a reference.

Any shoe anchor Sh can be used as long as the above-described reference axis (facing) and reference symbol can be determined, but a shape as shown in FIG. 7 is preferable. That is, as shown in FIG. 7, the shoe anchor Sh is produced up to the ball joint portion, thereby eliminating the need to prepare for each heel height. Although the toe shape of the shoe anchor Sh adopts an average shape in the example of FIG. 7, it is more preferable to create variations using a statistical model.

As described above, the standardized shoe measurement method and the standardized foot measurement method are methods for obtaining a plurality of "measurement values" newly proposed by the present inventors. Based on these multiple "measurement values", machine learning is performed, and matching between the foot (of the new user U) and the shoe is performed using the learning result.
That is, the standardized shoe measurement method and the standardized foot measurement method are methods in which measurement lengths that affect matching are standardized and obtained from unstandardized shoe and foot shapes. That is, the standardized shoe measurement method and the standardized foot measurement method are measurement methods that enable equal comparison regardless of the types of shoes or feet extracted.
Therefore, machine learning is performed using the shoe measurement data Ks obtained by the standardized shoe measurement method and the foot measurement data Kt obtained by the standardized foot measurement method. It is possible to automatically obtain the relationship (weighting), which in the past was determined by craftsmen's intuition, such as which value among them affects matching (comfort, etc.) and how much.

Here, the difference between the measured value obtained by the standardized shoe measurement method (abbreviated as "shoes" in this paragraph) and the measured value obtained by the standardized foot measurement method (abbreviated as "foot" in this paragraph) will be explained.
Regarding the "foot circumference A", the "foot" is the contour length and shape of the ball joint section cut perpendicular to the ground, while the "shoe" is the contour of the corresponding part of the shoe anchor Sh that fits snugly. Line length and shape.
As for the "foot width B", the "foot" is the length of the horizontal line connecting the ball joint portion to the ground, while the "shoe" is the horizontal length of the most protruding portion.
Regarding the "foot length C", the "foot" is the length of the leading edge of the toe and the trailing edge of the heel with respect to the axis of travel, while the "shoe" is the length of the axis of travel (shoe anchor Sh from the reference symbol of the shoe anchor Sh to the toe of the shoe anchor Sh)+(path length along the insole from the reference symbol of the shoe anchor Sh to the rearmost end of the heel).
Regarding the "heel shape D", the "foot" is the change in contour shape when the rearmost end of the heel is shifted in the height direction and cut horizontally on the ground. (Change in contour shape when cut horizontally to the ground while shifting in the height direction with the rear end of the heel as a reference) + (shape of the opening portion).
Regarding the "toe height E", the "foot" is the height (average or distribution) of the foot at a certain length forward from the line of the ball joint, while the "shoe" is the ball joint It is the average height of the foot at a certain length ahead of the line (the bottom surface is the top surface of the insole).
Regarding the "toe shape F", the "foot" is a trapezoidal shape (angle, length, etc.) connecting the ball joint, thumb and little finger, while the "shoe" is a certain distance above the top of the insole. This is the contour shape when the toe part is sliced.
For "distortion G", "foot" is the relative angle from the ball joint to the heel tip, while "shoe" is the relative angle from the ball joint to the heel tip.

As described above, the shoe measurement data Ks1 to Ksm of m shoes (shoe anchors Sh1 to Shm) are obtained by the standardized shoe measurement method. Further, foot measurement data Kt1 to Ktn of n testers T1 to Tn are obtained by the standardized foot measurement method.
Then, the learning device 3 of FIG. 5 generates shoe measurement data Ks1 to Ksm of m shoes (shoe anchors Sh1 to Shm) and foot measurement data Kt1 to Ktn of n testers T1 to Tn. , and the evaluation data Ht1 to Htn for each of the m shoes of the n testers T1 to Tn, respectively, are used to perform machine learning.

Next, among the processes executed by the information processing system shown in FIG. 1, a functional configuration capable of realizing the processing such as matching shown in FIG.
FIG. 8 is a functional block diagram showing an example of a functional configuration capable of realizing processing such as matching shown in FIG. 3 among the processing executed by the information processing system 1 of FIG.

As shown in FIG. 8, in the user foot measurement device 4, a scanning unit 141, a standardized foot measurement unit 142, and an evaluation acquisition unit 143 function.

The scanning unit 141 of the user foot measurement device 4 scans both feet of the user U to generate 3D scan data Du.
The standardized foot measurement unit 122 measures the 3D scan data Du according to the standardized foot measurement method described above, and stores the foot measurement data Ku obtained as a result of the measurement in the foot measurement DB 12 .
Here, the foot measurement data Ku of the user U can be associated with various information related to the user U in the same manner as the tester T's. Specifically, for example, the 3D scan data Du can be linked to the foot measurement data Ku. In addition, for example, information such as gender, age, weight, average number of steps per day, shoe purchase history and return history, shoes worn often, shoes not interested, favorite brands, disliked brands, etc. Various information can be linked to the foot measurement data Ku. Further, for example, information such as the address and occupation of the user U may be linked to the foot measurement data Ku. The foot measurement data Ku of the user U can be used together with the measurement data Kt of the tester T as part of big data for various purposes such as various analyses.
Further, the evaluation acquisition unit 143 acquires, from the user terminal 6 or the like, evaluation data Hu indicating an evaluation of comfort when the user U actually wears the shoes recommended as a result of matching by the matching device 5, and evaluates them. Store in DB 13.

In the matching device 5, a matching method determination unit 151, a user preference acquisition unit 152, a matching unit 153, and a recommendation unit 154 function for such a user foot measurement device 4. FIG.

The matching method determination unit 151 determines a matching method suitable for the user U based on the result of machine learning by the learning device 3 .
The user preference acquisition unit 152 acquires user U's preferences regarding shoes from the user terminal 6 or the like.
The matching unit 153 uses the foot measurement data Ku of the user U, shoe measurement data Ks1 to Ksm of m shoes (shoe anchors Sh1 to Shm), and preferences of the user U to match the user U Matching is performed (to estimate) which shoes are comfortable to wear.
Based on the matching result of the matching unit 153, the recommendation unit 154 recommends shoes that are suitable for the user U (that the user U will feel comfortable wearing) to the user U (user terminal 6). do.

Here, an example of the matching method determined by the matching method determining unit 151 based on the result of machine learning by the learning device 3 will be described with reference to FIG. 9 .
FIG. 9 is a diagram illustrating an example of a matching method determined based on machine learning results.
As shown in FIG. 9, for each of the testers T1 to Tm, the combination of the shoe measurement data Ksk of the predetermined shoe (shoe anchor Sh) and the foot measurement data Kt of the tester T and the actual wearing of the predetermined shoe are shown. Machine learning is performed by the learning device 3 using a set of evaluation data Ht at the time of learning.
Here, each of the shoe measurement data Ksk and the foot measurement data Kt of the tester T is a set of a plurality of measurement values such as "foot circumference A", "foot width B", and "foot length C", as described above. is the body. Also, the shoe evaluation data Ht is a set of individual evaluations of comfort for each item corresponding to a plurality of measurement values such as "foot circumference A", "foot width B", and "foot length C". .
Therefore, when machine learning as shown in FIG. 9 is performed, prediction of user U's evaluation is performed for a combination of shoe measurement data Ksk of a predetermined shoe (shoe anchor Sh) and user U's foot measurement data Ku. will be adopted. Here, prediction of the user's evaluation is prediction of individual evaluation of comfort for each item corresponding to a plurality of measurement values such as "foot girth A", "foot width B", and "foot length C".

Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the range that can achieve the object of the present invention are included in the present invention. is.

In the above-described embodiment, machine learning is performed on the relationship between the tester U's foot and the m number of shoes. Therefore, shoes suitable for the feet of the user U (shoes that are presumed to be highly evaluated by the user U) were recommended. Not limited.

For example, a machine learning target (matching and recommendation target using the machine learning result) may be as shown in FIG.
FIG. 10 is a diagram showing an outline of processing that can be performed by the information processing system in FIG. 1 and that is different from the example in FIG.
As shown in FIG. 10, for m existing shoes S1 to Sm (shoe anchors Sh1 to Shm), respectively, shoe measurement data Ks1 to Ksm and a large number of users U1 to Uk (k is an arbitrary integer value; In the example of k=3), the shoes are matched based on the combination with the evaluation data Hu (including the evaluation data Ht of the tester T), and existing shoes with similar evaluations to the new shoes are recommended. .
That is, each of m existing shoes (shoe anchors Sh1 to Shm, which are comparison targets for matching) on a two-dimensional plane with the shoe measurement data Ks as the A axis and the evaluation data Hu as the B axis. are plotted (projected) based on combinations of the shoe measurement data Ks1 to Ksm and a large number of users U1 to Uk for machine learning. In other words, machine learning is performed so as to generate a two-dimensional plane (space) in which shoes (items) with similar evaluations are arranged close to each other.
As a result of this machine learning, new shoes (comparison source for matching) are plotted (projected) on the two-dimensional plane (space) based on combinations of shoe measurement data Ks and a large number of users U1 to Uk. This makes it possible to search (match) shoes placed near the two-dimensional plane (space) and recommend them as shoes with similar evaluations, that is, shoes with similar comfort.

Further, for example, the target of machine learning (the target of matching and recommendation using the results of the machine learning) may be those shown in FIG. 11 .
FIG. 11 is a diagram showing an overview of processing that can be performed by the information processing system in FIG. 1, and which is different from the example in FIG. 2 and performs machine learning.
In the machine learning shown in FIG. 3, a model (existing model) based on general evaluations of n (many) testers T is obtained for m shoes.
On the other hand, in the example of FIG. 11, feedback information from the user U who has been matched and recommended using these existing models, such as information indicating various histories (purchase history and return history) regarding the user U, is also taken into consideration. Then, additional learning is done. As a result of this additional learning, a model specialized for the preferences of the user U (compared to the existing model), ie, a user-specific model is obtained.
By performing matching using this user-specific model, it is possible to recommend shoes that are more suitable for the user U than when using an existing model.

Also, for example, the object of machine learning (the object of matching and recommendation using the results of the machine learning) is shoes in the above-described embodiment, but is not particularly limited to this, and is worn by user U (including tester T). Any item possible, such as clothing, hats, protective or auxiliary helmets, corsets, supporters, etc., may be used.

FIG. 12 shows an example of the measurement data of the user U (including the tester T) when standardized measurement is performed when the item is clothing.
That is, since the measurement method of the human body (the body of the user U) is standardized, the measurement by the measurement method is adopted as the standardized measurement, and the measurement result is adopted as the standardized measured value. An example of measurement data of is shown in FIG.

FIG. 13 shows an example of item measurement data when standardized measurement is performed when the item is clothing (jacket).
In other words, since the measurement method for which part of clothing (jacket) is to be measured is standardized for each category, the measurement by this measurement method is adopted as standardized measurement, and the measurement result is the standardized measurement value. An adopted example, ie, measurement data for a garment (jacket), is shown in FIG.

Also, for example, in the above-described embodiment, matching is performed based on the shape of the item, but the present invention is not limited to this, and matching may be performed in consideration of other factors along with the shape or separately from the shape. . In other words, factors that determine the comfort of an item (comfort to wear if the item is shoes) are not only differences in shape, but also factors such as weight, age, heel height, and shoe material in the case of shoes. In the case of clothes, there are factors such as material of fabric, gender, and age.
In the past, when trying to consider the influence of these "other elements", it was necessary to attach rules to all the influences. On the other hand, by adopting a machine learning method (based on decision trees) that can automatically learn the influence of multiple different elements, the influence of "other elements" can be learned without rules. can be realized.
Here, the following can be adopted as "another element".
In other words, if described in the format of "other elements"=(data type, influence), it will be as follows.
“Ease of extensibility of material” = (Tensile strength [N/cm], influence on allowable range of difference in shape)
"Material type" = (category (cloth, polyester, etc.), affecting the pain of the contact area)
"Body weight" = (kg, influences load on toe in heel)
"Heel height" = (cm, affects the load on the toe at the heel)
“Age” = (Influences differences in preferences such as numerical value and ease of walking)
Affects differences in preferences such as average number of steps per day and ease of fatigue

Further, for example, in the above-described embodiment, indirect machine learning was performed using the evaluation when the tester T actually wore m shoes, but it is not particularly limited to this, and together with or instead of this evaluation For example, a cloth-type pressure distribution sensor is used to measure the wearing pressure of each of the m shoes by the tester T, and machine learning is performed using the measurement results. The prediction may be made even when there is no pressure distribution sensor.
Also in this case, the result of the prediction is used to estimate the final taste of the user U (comfort in shoes), and to recommend the user U based on the result of the estimation.

Further, for example, in the above-described embodiment, the shoe measurement data Ks of shoes, the foot measurement data Kt of the tester T, and the foot measurement data Ku of the user U are associated with various pieces of information (metadata). This is because machine learning, matching (preference estimation), and recommendation are performed with higher accuracy by considering these various types of information (metadata).
Such metadata is not limited to the above-described embodiment, and any metadata can be adopted. For example, the following metadata can be adopted. Metadata in parentheses (better) is metadata that is suitable for use. Metadata marked with (advanced) in parentheses does not necessarily need to be used, but is metadata that enables more appropriate machine learning, matching (preference estimation), and recommendation if used. .
That is, elongation rate (better), surface hardness (better), and material type (enamel, smooth, cloth, etc.) (advanced) can be employed as material property metadata.
Brand name, manufacturer name, factory name (advanced), and manufacturing method (advanced) can be adopted as metadata of the manufacturing information.
As the user U's attribute information, proficiency level (better), usage frequency (better), and age (advanced) can be employed.

In the above-described embodiment, the user U goes to a shoe store or the like, has his/her feet scanned there, and performs matching using the resulting foot measurement data Ku. Appropriate shoes for U (shoes expected to be comfortable) were recommended.
However, it is not essential to use the foot measurement data Ku for matching.
For example, in an EC site or the like, in order to recommend shoes or clothes without user U's foot/body shape data, for example, matching is performed using shoes or clothes that user U has purchased in the past and fits, You may search for and recommend objects with the same or similar shape as them.
In this case, there are a large number of types of shoe and clothing measurements, and their simple similarity may not necessarily emphasize the numbers that are important for fitting. Therefore, adopting the information processing system that applies the above-mentioned machine learning, using the similarity of the preliminary evaluation by the tester T (test user), calculate the degree of contribution to the similarity to the measured value of shoes and clothes, It is preferable to perform a search that reflects the degree of contribution.

Specifically, for example, the evaluation by the combination of the tester T1 and the shoe (hereinafter referred to as the "first combination") is (foot length difference, knob thickness difference, heel width difference, ease of taking off) = (+0.1, -0.8, +0.1, A). In addition, evaluation by a combination of another tester T2 and shoes (hereinafter referred to as "second combination") is (foot length difference, knob thickness difference, heel width difference, ease of taking off) = (+0.1, -0 .8, +0.1, A).
In this case, in order to estimate the ease of coming off, it is assumed that the percentage of important items (contribution) is calculated as follows, for example. That is, it is assumed that contribution=(foot length difference, knob thickness difference, heel width difference)=(0.3, 0.1, 0.6).
This contribution can be used to weight the shoe similarity index (each measured value of the shoe measurement data Ks) for matching (search).
For example, the shoe measurement data Ks1 of the first shoe is (foot length, knob thickness, heel width)=(23.2, 2.4, 4.55), and the shoe measurement data Ks1 of the second shoe is ( Foot length, knob thickness, heel width)=(23.6, 3.6, 4.6). In this case, in the above example, since the contribution of the heel width difference is 0.6, which is the highest, matching (retrieval) is performed with emphasis on the heel width among the measured values. That is, since the heel width of the first shoe is 4.55 and the heel width of the second shoe is 4.6, it is determined that the first shoe and the second shoe are very similar in ease of taking off. That is, if the first shoe was purchased by the user U in the past and was perfect, the second shoe is recommended to the user U who attaches importance to ease of taking off the shoe.

The EC site screen displayed on the user terminal 6 when such a search (recommendation) is performed, and the user U's foot scanned at the store and displayed on the store side device (for example, the user's foot measurement device 4). 14 to 16, for example.
FIG. 14 is a diagram showing an example of a mock recommendation screen at a store.
FIG. 15 is an example of a mock recommendation screen at a store, and is a diagram showing an example of a screen displayed after the screen of FIG. 14 is displayed.
FIG. 16 is an example of a mock screen of an EC site.

Also, for example, each hardware configuration shown in FIG. 4 is merely an example for achieving the object of the present invention, and is not particularly limited.

Also, the functional block diagrams shown in FIGS. 5 and 8 are merely examples and are not particularly limited. In other words, it is sufficient for the information processing system to have a function capable of executing the above-described series of processes as a whole. It is not particularly limited.

Also, the locations of the functional blocks are not limited to those shown in FIGS. 5 and 8, and may be arbitrary. For example, at least part of the functional blocks of each device may be provided on the user terminal 6 side. In other words, when viewed from the user terminal 6, an information processing system may be constructed that causes an external server or the like to execute processing using a browser, or an information processing system that causes an installed application program to execute processing may be constructed. Alternatively, an information processing system consisting of a combination of these may be constructed.
One functional block may be composed of hardware alone, or may be composed of a combination of software alone.

When the processing of each functional block is to be executed by software, a program that constitutes the software is installed in a computer or the like from a network or recording medium.
The computer may be a computer built into dedicated hardware. Also, the computer may be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smart phone, or a personal computer.

A recording medium containing such a program is distributed separately from the main body of the device in order to provide the program, and is not only composed of removable media, but also provided to each user in a state pre-installed in the main body of the device. It consists of a recording medium, etc.

In this specification, the steps of writing a program recorded on a recording medium are not only processes performed chronologically in that order, but also processes performed in parallel or individually. It also includes the processing to be performed.

In summary, the information processing apparatus to which the present invention is applied only needs to have the following configuration, and can take various embodiments.
That is, an information processing device to which the present invention is applied (for example, the matching device 5 in FIG. 1) is
Type 1 standard data (for example, shoe measurement data Ks1 in FIG. 2) obtained by standardizing measurement data (for example, 3D scan data Ds1 to Dsm in FIG. 2) of a predetermined item (for example, shoes, which may be shoe anchors Sh1 to Shm) to Ksm) and second-class standard data (e.g., Foot measurement data Kt1 to Ktn in FIG. 2) are combined with each of a plurality of items and a plurality of testers based on the results of machine learning (for example, step Se in FIG. 2). ) for predicting the degree of suitability of the item (for example, the matching unit 153 in FIG. 8 that performs matching in step Si in FIG. 3);
a recommendation unit (for example, the recommendation unit 154 in FIG. 8 that performs the recommendation in step Sj in FIG. 3) that recommends an item to the user based on the prediction result of the prediction unit;
Prepare.

In addition, another aspect of the information processing device to which the present invention is applied (for example, the shoe measuring device 1 in FIG. 1)
Based on the measurement data of the item (for example, the 3D scan data Ds1 to Dsm in FIG. 2 generated by the scanning unit 111 in FIG. 5), identify the facing, detect one or more landmark points, and design the item. A reference symbol is calculated based on a predetermined rule for eliminating inequality, and each measurement value of a plurality of items is calculated based on the facing, the landmark point, and the reference symbol (for example, see FIG. 7 ), and measuring means (for example, the standardized shoe measurement unit 112 in FIG. 5) that generates information including at least each of the measured values of the plurality of items as measurement data of the item (for example, shoe measurement data Ks1 to Ksm in FIG. 2).
Prepare.

1: shoe measurement device 2: tester foot measurement device 3: learning device 4: user foot measurement device 5: matching device 6: user terminal 11: shoe measurement DB
12: Foot measurement DB
13: Evaluation DB
21: CPU
22: ROM
23: RAM
24: Bus 25: Input/output interface 26: Output unit 27: Input unit 28: Storage unit 29: Communication unit 30: Drive 31: Removable medium 111: Scan unit 112: Standardized shoe measurement unit 121: Scan unit 122: Standardized foot measurement Unit 123: Evaluation acquisition unit 141: Scan unit 142: Standardized foot measurement unit 143: Evaluation acquisition unit 151: Matching method determination unit 152: User preference acquisition unit 153: Matching unit 154: Recommendation unit J: Ball joint A: Foot circumference B : Foot width C: Foot length D: Heel shape E: Toe height F: Toe shape G: Distortion H: Evaluation data L: Landmark point U: User

Claims (4)

Based on 3D measurement data of an item worn on a part of the human body at least in contact with or in close proximity to the first part and the second part of the human body, identifying the facing position, and making contact with or in close proximity to the first part of the human body Detecting each of one or more points of an item as a landmark point, and detecting one or more lines or planes of the item that are in contact with or close to the second part based on predetermined rules for eliminating the design of the item. Calculation using position information of each of the landmark point and the reference symbol in the coordinate system based on the facing, by obtaining each of one or more lines or planes whose position is indefinite for each item as a reference symbol. a first measuring means for calculating each measured value of a plurality of items according to a method and generating information including at least each measured value of the plurality of items as measurement data of the item ;
wherein said item is a shoe, said first part is a toe or heel apex and said second part is a ball joint;
Information processing equipment. Based on the 3D measurement data of the part of the human body on which the item is worn, identifying a facing position, detecting each of one or more points in the first part as landmark points, and determining a coordinate system based on the facing position and calculating each measured value of the plurality of items according to a calculation method using the position information of the landmark points, and generating information including at least each of the measured values of the plurality of items as the measured data of the human body. 2. The information processing apparatus according to claim 1 , further comprising: a second measuring means for measuring. An information processing method executed by an information processing device,
Based on 3D measurement data of an item worn on a part of the human body at least in contact with or in close proximity to the first part and the second part of the human body, identifying the facing position, and making contact with or in close proximity to the first part of the human body Detecting each of one or more points of an item as a landmark point, and detecting one or more lines or planes of the item that are in contact with or close to the second part based on predetermined rules for eliminating the design of the item. Calculation using position information of each of the landmark point and the reference symbol in the coordinate system based on the facing, by obtaining each of one or more lines or planes whose position is indefinite for each item as a reference symbol. a measuring step of calculating each measured value of a plurality of items according to the method and generating information including at least each of the measured values of the plurality of items as measured data of the item ;
wherein said item is a shoe, said first part is a toe or heel apex and said second part is a ball joint;
Information processing methods. The computer that controls the information processing device,
Based on 3D measurement data of an item worn on a part of the human body at least in contact with or in close proximity to the first part and the second part of the human body, identifying the facing position, and making contact with or in close proximity to the first part of the human body Detecting each of one or more points of an item as a landmark point, and detecting one or more lines or planes of the item that are in contact with or close to the second part based on predetermined rules for eliminating the design of the item. Calculation using position information of each of the landmark point and the reference symbol in the coordinate system based on the facing, by obtaining each of one or more lines or planes whose position is indefinite for each item as a reference symbol. a measuring step of calculating each measured value of a plurality of items according to the method and generating information including at least each of the measured values of the plurality of items as measured data of the item;
wherein said item is a shoe, said first part is a toe or heel apex and said second part is a ball joint;
A program that executes control processing.

Images