A shoe recommendation method, system and computer-readable storage medium

Abstract

The present application provides a shoe recommendation method, system and computer-readable storage medium, the method comprising obtaining a first foot point cloud model and a second foot point cloud model of a foot in different states; calculating a foot point cloud model conversion matrix based on the first foot point cloud model and the second foot point cloud model; transforming a pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model; calculating a final comfort of the first shoe model based on a first comfort level and a second comfort level, the first comfort level being determined based on the first foot point cloud model and the first shoe model, the second comfort level being determined based on the second shoe model and the corresponding foot point cloud model, and being able to simultaneously consider shoe models corresponding to foot point cloud models in a non-motion state and a motion state, and calculating shoe comfort levels corresponding to the two states, so that a user can learn about the comfort levels of the shoe models in the two states, thereby enabling the user to select suitable shoes.

Description

Technical Field

[0001] The present application belongs to the field of laser technology, and in particular, relates to a shoe recommendation method, system and computer-readable storage medium. Background Art

[0002] With the rapid development of science and technology, online shopping has become an increasingly important way of shopping. Based on the demand for online shopping experience, VR virtual reality technology has emerged.

[0003] When shopping for shoes online, the static foot shape of consumers is collected, and then shoes that match the foot shape are found and recommended to customers. The shoes recommended in this way only have static shoe comfort. Users only select shoes based on static shoe comfort, and the selected shoes may not meet the user's comfort requirements when using them. Summary of the invention

[0004] The embodiments of the present application provide a shoe recommendation method, system, and computer-readable storage medium, which can solve the problem that the comfort level of shoes recommended by existing methods cannot meet the needs of consumers.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending shoes, comprising:

[0006] Obtain the first foot point cloud model and the second foot point cloud model of the foot in different states;

[0007] Calculate a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model;

[0008] Transforming a pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model;

[0009] The final comfort of the first shoe model is calculated based on the first comfort level and the second comfort level, wherein the first comfort level is determined based on the first foot point cloud model and the first shoe model, and the second comfort level is determined based on the second shoe model and the corresponding foot point cloud model.

[0010] Furthermore, the step of calculating a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model includes:

[0011] Between the first height difference and the second height difference, K acquisition height differences and NK simulation height differences are determined, wherein the value of K is in [0, N], and the value of N is greater than 0;

[0012] If the value of K is not equal to 0, then for each of the collected height differences, a third foot point cloud model is obtained;

[0013] For each of the simulated height differences, performing point cloud simulation based on the first foot point cloud model, the second foot point cloud model and the third foot point cloud model to obtain a fourth foot point cloud model;

[0014] If the value of K is equal to 0, then for each of the simulated height differences, point cloud simulation is performed based on the first foot point cloud model and the second foot point cloud model to obtain the fourth foot point cloud model;

[0015] Based on the first foot point cloud model, calculate the foot point cloud model conversion matrix of N+1 foot point cloud models, wherein the N+1 foot point cloud models include the third foot point cloud model, the fourth foot point cloud model and the second foot point cloud model;

[0016] Among them, the first height difference is the height difference between the first foot area and the second foot area in the first foot point cloud model, and the second height difference is the height difference between the first foot area and the second foot area in the second foot point cloud model.

[0017] Furthermore, the step of calculating the foot point cloud model conversion matrix of N+1 foot point cloud models based on the first foot point cloud model includes:

[0018] For each of the N+2 foot point cloud models, the foot point cloud model is cut through two cutting planes, each of the cutting planes intersects with the foot point cloud model only at one line, the two cutting planes are parallel to each other, and the distance between the two cutting planes is the largest;

[0019] At least one dividing surface is provided between the two cutting surfaces, and each of the dividing surfaces is parallel to the cutting surface;

[0020] Based on all the segmentation surfaces, segment the foot point cloud model to obtain at least two modules;

[0021] For the i-th foot point cloud model among the N+1 foot point cloud models, taking the module of the first foot point cloud model as a reference, calculating the variable parameters of each module in the i-th foot point cloud model;

[0022] Based on the variable parameters of each module of the i-th foot point cloud model, form an i-th foot point cloud model conversion matrix, where the value of i is in [1, N+1];

[0023] Among them, the N+2 foot point cloud models include the N+1 foot point cloud models and the first foot point cloud model.

[0024] Furthermore, the step of transforming the pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model includes:

[0025] Based on the i-th foot point cloud model conversion matrix, the first shoe model is transformed to obtain a second shoe model corresponding to the i-th foot point cloud model conversion matrix.

[0026] Furthermore, the second comfort level is determined according to the second shoe model and the corresponding foot point cloud model, including:

[0027] Calculating the comfort level of the second shoe model corresponding to the i-th foot point cloud model;

[0028] If the comfort level of each of the second shoe models is greater than or equal to the first comfort threshold, the comfort levels of all the second shoe models are normalized to obtain the second comfort level of the first shoe model.

[0029] Furthermore, calculating the final comfort level of the first shoe model according to the first comfort level and the second comfort level includes:

[0030] If the first comfort level is greater than or equal to a second comfort threshold, and the second comfort level is greater than or equal to a third comfort threshold, a final comfort level is calculated based on the first comfort level and the second comfort level.

[0031] Furthermore, after calculating the final comfort level of the first shoe model, the method further includes:

[0032] If the final comfort level is greater than a fourth comfort threshold, the shoe corresponding to the first shoe model is determined as a recommended shoe.

[0033] Furthermore, after determining the shoe corresponding to the first shoe model as the recommended shoe, the method further includes:

[0034] After receiving a try-on instruction from a user, in response to the try-on instruction, selecting a target shoe corresponding to the try-on instruction;

[0035] Perform static simulation try-on on each foot point cloud model and show the static try-on effect to the user;

[0036] Based on the point cloud model of all feet, dynamic simulation try-on is performed in the order of height difference, and the dynamic try-on effect is displayed to the user;

[0037] A mold insole corresponding to the target shoe is selected for the user to try on.

[0038] In a second aspect, an embodiment of the present application provides a shoe recommendation system, including: a processor, a laser radar, a support platform, a first driver, a first lifting assembly, and a second driver;

[0039] The first driver is disposed on the support platform, and is power-coupled with the laser radar to drive the laser radar to rotate along the support platform. The laser radar is used to collect point cloud data of the foot on the support platform, and the point cloud data is used to determine a point cloud model of the foot;

[0040] The second driver is disposed on the support platform, and the second driver is connected to the first lifting assembly by power coupling, and is used to drive the first lifting assembly to rise and fall, so as to change the state of the foot on the first lifting assembly;

[0041] The processor is electrically connected to the laser radar, the first driver and the second driver respectively, and is used to execute the method as described in any one of the first aspects above.

[0042] Furthermore, the system further comprises: a storage rack, a second lifting assembly and a third driver;

[0043] The storage rack is connected to the support platform, and the storage rack accommodates at least one mold insole;

[0044] The third driver is disposed on the supporting platform, and is power-coupled with the second lifting assembly to drive the second lifting assembly to move up and down, so as to move the mold insole onto the supporting platform.

[0045] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the above-mentioned first aspects is implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described in the first aspect above.

[0047] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0048] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0049] The embodiment of the present application obtains a first foot point cloud model and a second foot point cloud model of the foot in different states; calculates a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model; transforms a pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model; calculates the final comfort of the first shoe model according to the first comfort and the second comfort, wherein the first comfort is determined according to the first foot point cloud model and the first shoe model, and the second comfort is determined according to the second shoe model and the corresponding foot point cloud model. The shoe models corresponding to the foot point cloud models in a non-motion state and a motion state can be considered at the same time, and the shoe comfort corresponding to the two states is calculated, so that the user can know the comfort of the shoe model in the two states, thereby enabling the user to choose suitable shoes to meet the user's comfort requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 is a flowchart of a shoe recommendation method provided by an embodiment of the present application;

[0052] Figure 2 It is a structural schematic diagram of a segmented foot point cloud model provided in an embodiment of the present application;

[0053] Figure 3 is a schematic structural diagram of a recommended shoe device provided in an embodiment of the present application;

[0054] Figure 4 It is a structural schematic diagram of the shoe recommendation system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0056] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0057] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0059] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0060] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0061] Figure 1 is a flow chart of a shoe recommendation method provided by an embodiment of the present application. As an example and not a limitation, Figure 1 As shown, the method includes:

[0062] S101: Obtain a first foot point cloud model and a second foot point cloud model in different states.

[0063] Specifically, a first foot point cloud model of a foot in a non-moving state and a second foot point cloud model of a foot in a moving state are obtained.

[0064] S102: Calculate a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model.

[0065] Specifically, based on the pre-stored world coordinate system, the foot point cloud model transformation matrix is ​​calculated according to the first foot point cloud model and the second foot point cloud model.

[0066] S103: transforming the pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model.

[0067] Among them, transforming the first shoe model may be transforming the first shoe model whose matching degree with the first foot point cloud model is greater than or equal to a preset matching degree, may be transforming the first shoe model selected by the user, or may be transforming all the first shoe models.

[0068] S104: Calculate a final comfort level of the first shoe model according to the first comfort level and the second comfort level.

[0069] Among them, the first comfort level is determined based on the first foot point cloud model and the first shoe model, and the second comfort level is determined based on the second shoe model and the corresponding foot point cloud model.

[0070] The first comfort level is the comfort level of the first shoe model in a non-motion state, and the second comfort level is the comfort level of the first shoe model in a motion state. The second comfort level is calculated by the comfort level of each second shoe model, specifically, the comfort level of each second shoe model is normalized to obtain the second comfort level.

[0071] For example, the comfort level can be calculated based on the matching degree between the shoe model and the foot point cloud model, the height difference between the first foot area and the second foot area, the contact area between the sole and the shoe model, and the softness of the sole of the shoe corresponding to the shoe model.

[0072] Generally speaking, the greater the matching degree, the higher the comfort, and vice versa, the lower the comfort; the smaller the height difference, the larger the contact area, the higher the comfort, and vice versa, the lower the comfort.

[0073] This embodiment obtains a first foot point cloud model and a second foot point cloud model in different states; calculates a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model; transforms a pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model; calculates a final comfort of the first shoe model according to the first comfort and the second comfort, wherein the first comfort is determined according to the first foot point cloud model and the first shoe model, and the second comfort is determined according to the second shoe model and the corresponding foot point cloud model. The shoe models corresponding to the foot point cloud models in a non-motion state and a motion state can be considered at the same time, and the shoe comfort corresponding to the two states is calculated, so that the user can know the comfort of the shoe model in the two states, thereby enabling the user to choose suitable shoes to meet the user's comfort requirements.

[0074] In another embodiment, different height differences between the first foot region and the second foot region are used to reflect different states of the foot. For example, the first foot region is the sole of the foot, and the second foot region is the heel.

[0075] Get the first point cloud model, including:

[0076] The first point cloud data of the foot is obtained, and the first point cloud data is preprocessed to obtain a first point cloud model of the foot.

[0077] The height difference between the first foot region and the second foot region when the foot is in a non-movement state is set as a non-movement height difference. The non-movement height difference is set according to the situation that the user's foot is in a non-movement state. The non-movement height difference can be set to a specific value or an interval value.

[0078] Specifically, when the height difference between the first foot area and the second foot area of ​​the user's foot is in a non-motion height difference, a laser radar is used to scan the user's foot. The laser radar can scan the foot multiple times to improve the accuracy of the acquisition; then the first point cloud data of the foot is obtained, and after preprocessing, the first foot point cloud model is obtained.

[0079] To ensure the high efficiency of the collection, it can be achieved by scanning at the collection position. When the laser radar reaches the collection position, the user's feet are scanned. In order to ensure the integrity of the foot point cloud model, the collection position is selected based on the overlap between the foot point cloud data of adjacent collection positions.

[0080] Get the second foot point cloud model, including:

[0081] The second point cloud data of the foot is obtained, and the second point cloud data is preprocessed to obtain a second point cloud model of the foot.

[0082] The height difference between the first foot area and the second foot area when the foot is in motion is used as the motion height difference. The motion height difference is set according to the situation that the user's foot is in motion. The motion height difference can be set to a specific value or to an interval value. For example, the foot is in motion when the user is running or walking, and the motion height difference is set according to the situation that the user is running or walking. Generally, the motion height difference is greater than the non-motion height difference.

[0083] Specifically, when the height difference between the first foot area and the second foot area of ​​the user's foot is in a moving height difference, a laser radar is used to scan and collect the user's feet, and then the second point cloud data of the feet is obtained. After preprocessing, a second foot point cloud model is obtained.

[0084] In order to facilitate the collection of the point cloud of the foot, the maximum height difference between the first foot area and the second foot area of ​​the user can be used as the movement height difference, or the height difference with a high probability of occurrence when the foot is in motion can be used as the movement height difference. If the probability of occurrence is greater than the preset probability, the probability of occurrence is high.

[0085] In another embodiment, preprocessing of point cloud data includes:

[0086] First, based on the pre-stored spatial transformation relationship between the radar coordinate system and the world coordinate system, the point cloud data is transformed into the world coordinate system.

[0087] For example, a radar coordinate system is established at the position scanned by the laser radar, and a world coordinate system is established at the position where the foot is placed. The directions of the x, y, and z axes of the radar coordinate system and the world coordinate system are the same. Based on the radar coordinate system and the world coordinate system, the spatial conversion relationship between the radar coordinate system and the world coordinate system is calculated and stored.

[0088] Then, the converted point cloud data is processed by point cloud matching and fusion.

[0089] This embodiment converts the point cloud data to the world coordinate system based on the pre-stored spatial conversion relationship between the radar coordinate system and the world coordinate system, and performs point cloud matching and fusion processing on the converted point cloud data, so that the pre-processed foot point cloud models are all in the same coordinate system, which is convenient for subsequent processing.

[0090] In another embodiment, calculating the foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model includes:

[0091] First, between the first height difference and the second height difference, K acquisition height differences and NK simulation height differences are determined, where the value of K is in [0, N], and the value of N is greater than zero.

[0092] The first height difference is the height difference between the first foot area and the second foot area in the first foot point cloud model, and the second height difference is the height difference between the first foot area and the second foot area in the second foot point cloud model.

[0093] For example, the K collected height differences can be selected by the user, or can be pre-set according to the result accuracy requirements. The height differences between the collected height differences are different. The value of N can be set according to actual usage requirements.

[0094] Next, first, if the value of K is not equal to 0, a third-leg point cloud model is obtained for each collected height difference.

[0095] K collected height differences correspond to K third point cloud models.

[0096] For each simulated height difference, point cloud simulation is performed based on the first foot point cloud model, the second foot point cloud model and the third foot point cloud model to obtain the fourth foot point cloud model.

[0097] Specifically, for each simulated height difference, point cloud simulation is performed based on the first foot point cloud model, the second foot point cloud model and K third foot point cloud models to obtain a fourth foot point cloud model.

[0098] NK simulated height differences correspond to NK fourth-leg point cloud models.

[0099] Secondly, if the value of K is equal to 0, for each simulated height difference, a point cloud simulation is performed based on the first foot point cloud model and the second foot point cloud model to obtain a fourth foot point cloud model.

[0100] Specifically, when the value of K is equal to 0, there are N simulated height differences. N simulated height differences correspond to N fourth-leg point cloud models, and there is no third-leg point cloud model.

[0101] Then, based on the first foot point cloud model, the foot point cloud model transformation matrix of N+1 foot point cloud models is calculated, and the N+1 foot point cloud models include the third foot point cloud model, the fourth foot point cloud model and the second foot point cloud model.

[0102] Specifically, based on the x, y, and z-axis directions of the pre-stored world coordinate system, the variable parameters of the first foot point cloud model in the x, y, and z-axis directions are first obtained, wherein the pre-stored world coordinate system includes x, y, and z-axis, and the directions of x, y, and z-axis can be set according to the specific usage scenario.

[0103] Then, for each of the N+1 foot point cloud models, based on the variable parameters of the first foot point cloud model in the x, y, z-axis directions, its variable parameters in the x, y, z-axis directions are obtained, and then the variable parameters in the x, y, z-axis directions are combined into a transformation matrix.

[0104] This embodiment obtains N foot point cloud models between the first height difference and the second height difference, and calculates the foot point cloud model conversion matrix of N+1 foot point cloud models, thereby providing a basis for obtaining the comfort of the first shoe model under different height differences and providing a basis for providing users with suitable shoes.

[0105] In another embodiment, obtaining a third foot point cloud model includes:

[0106] The third point cloud data of the foot is obtained, and the third point cloud data is preprocessed to obtain a third foot point cloud model.

[0107] Specifically, for each collected height difference, when the height difference between the first foot area and the second foot area of ​​the user's foot is the collected height difference, the user's foot is scanned and collected using a laser radar, and then the third point cloud data of the foot is obtained. After preprocessing, a third foot point cloud model is obtained.

[0108] In another embodiment, based on the first foot point cloud model, calculating the foot point cloud model conversion matrix of N+1 foot point cloud models includes:

[0109] First, for each of the N+2 foot point cloud models, the foot point cloud model is cut through two cutting planes, each cutting plane intersects with the foot point cloud model only at one line, the two cutting planes are parallel to each other, and the distance between the two cutting planes is the largest.

[0110] Among them, the N+2 foot point cloud models include the N+1 foot point cloud model and the first foot point cloud model.

[0111] For example, the cutting method may be vertical cutting, in which the foot point cloud model is cut vertically in the direction of the sole of the foot in the foot point cloud model through two cutting planes, but the present invention is not limited thereto.

[0112] Next, at least one dividing surface is arranged between the two cutting surfaces, and each dividing surface is parallel to the cutting surface.

[0113] The spacing between the two dividing planes can be set to be the same spacing, or different spacing can be set. For example, at least one dividing point can be set between the two dividing planes, and then the dividing planes can be set based on the dividing point.

[0114] Then, based on all segmentation surfaces, the foot point cloud model is segmented to obtain at least two modules.

[0115] For example, if one dividing surface is set, two modules are obtained; if two dividing surfaces are set, three modules are obtained. Therefore, if M dividing surfaces are set, M+1 modules will be obtained.

[0116] That is, each of the N+2 foot point cloud models has M+1 modules. The M+1 modules can be numbered from the same direction, and the value of the number j is in [1, M+1] for subsequent processing.

[0117] Figure 2 Schematic diagram of the structure of the segmented foot point cloud model provided by an embodiment of the present application. Figure 2 As shown, the cutting surface includes a first cutting surface 10 and a second cutting surface 11. The first cutting surface intersects with the toe in the foot point cloud model 12 at a line, and the second cutting surface 11 intersects with the heel in the foot point cloud model 12 at a line. At the same time, the distance between the first cutting surface 10 and the second cutting surface 11 is the largest. Three segmentation surfaces 13 are set between the first cutting surface 10 and the second cutting surface 11. The foot point cloud model 12 is segmented based on the three segmentation surfaces 13 to obtain 4 modules.

[0118] Next, for the i-th foot point cloud model among the N+1 foot point cloud models, the module of the first foot point cloud model is used as a benchmark to calculate the variable parameters of each module in the i-th foot point cloud model.

[0119] Among them, the value of i is in [1, N+1].

[0120] For example, in order to calculate the transformation matrix of N+1 foot point cloud models in order, the N+2 foot point cloud models are sorted according to the height difference, and then the N+1 foot point cloud models are processed in sequence from the first height difference to the second height difference.

[0121] Each module in the first foot point cloud model contains variable parameters in the x, y, and z axis directions, that is, the jth module in the first foot point cloud model contains variable parameters in the x, y, and z axis directions.

[0122] For the jth module in the ith foot point cloud model, the variable parameters in the x, y, and z-axis directions of the jth module in the first foot point cloud model are used as a reference to calculate the variable parameters in the x, y, and z-axis directions of the jth module.

[0123] The i-th foot point cloud model has M+1 modules, corresponding to M+1 variable parameters in the x, y, and z directions.

[0124] Finally, based on the variable parameters of each module of the i-th foot point cloud model, the i-th foot point cloud model transformation matrix is ​​composed.

[0125] For example, the variable parameters of each module of the i-th foot point cloud model are interpolated to obtain M+1 transformation functions in the x, y, and z-axis directions, and then the i-th foot point cloud model transformation matrix is ​​formed based on the M+1 transformation functions in the x, y, and z-axis directions.

[0126] This embodiment obtains at least two modules by segmenting each foot point cloud model; calculates the variable parameters of each module of the foot point cloud model, and composes a foot point cloud model conversion matrix based on the variable parameters of all modules, so as to obtain an accurate foot point cloud model conversion matrix.

[0127] In another embodiment, the foot point cloud model conversion matrix transforms the pre-stored first shoe model to obtain at least one second shoe model, including:

[0128] Based on the i-th foot point cloud model conversion matrix, the first shoe model is transformed to obtain a second shoe model corresponding to the i-th foot point cloud model conversion matrix.

[0129] Specifically, based on N+1 foot point cloud model conversion matrices, the pre-stored first shoe model is transformed to obtain N+1 second shoe models.

[0130] In another embodiment, the second comfort level is determined based on the second shoe model and the corresponding foot point cloud model, including:

[0131] First, the comfort level of the second shoe model corresponding to the i-th foot point cloud model is calculated.

[0132] Specifically, there are N+1 second shoe models, and correspondingly, the comfort levels of the N+1 second shoe models are obtained.

[0133] Then, if the comfort level of each second shoe model is greater than or equal to the first comfort threshold, the comfort levels of all the second shoe models are normalized to obtain the second comfort level of the first shoe model.

[0134] Specifically, if the comfort levels of the N+1 second shoe models are all greater than or equal to the first comfort threshold, the comfort levels of the N+1 second shoe models are normalized to obtain the second comfort level of the first shoe model.

[0135] If at least one of the comfort levels of the N+1 second shoe models is less than the first comfort threshold, the second comfort level of the first shoe model is set to a preset value. The preset value may be set to 0, but is not limited thereto.

[0136] This embodiment obtains the second comfort level of the first shoe model by normalizing the comfort levels of all second shoe models, thereby obtaining the comfort level of the first shoe model in motion, and providing a basis for providing the user with suitable shoes.

[0137] In another embodiment, calculating the final comfort level of the first shoe model according to the first comfort level and the second comfort level includes:

[0138] If the first comfort level is greater than or equal to the second comfort threshold, and the second comfort level is greater than or equal to the third comfort threshold, the final comfort level is calculated according to the first comfort level and the second comfort level.

[0139] Specifically, if the first comfort level is greater than or equal to the second comfort threshold, and the second comfort level is greater than or equal to the third comfort threshold, the first comfort level and the second comfort level are normalized and coefficient-weighted to obtain the final comfort level of the first shoe model.

[0140] If the first comfort level is less than the second comfort threshold, or the second comfort level is less than the third comfort threshold, the final comfort level of the first shoe model is set to a preset value.

[0141] This embodiment calculates the final comfort level based on the first comfort level and the second comfort level if the first comfort level is greater than or equal to the second comfort threshold, and the second comfort level is greater than or equal to the third comfort threshold, thereby ensuring that the comfort level of the recommended shoes can meet the needs of consumers, thereby improving the efficiency of users in selecting suitable shoes.

[0142] In another embodiment, after calculating the final comfort level of the first shoe model, the method further includes:

[0143] If the final comfort level is greater than the fourth comfort threshold, the shoe corresponding to the first shoe model is determined as the recommended shoe.

[0144] When the final comfort level is greater than the fourth comfort threshold, it indicates that the shoes corresponding to the first shoe model can meet the comfort requirements of the user during use, and the shoes corresponding to the first shoe model can be determined as recommended shoes.

[0145] In another embodiment, after determining the shoe corresponding to the first shoe model as the recommended shoe, the method further includes:

[0146] Firstly, after receiving a try-on instruction from a user, in response to the try-on instruction, a target shoe corresponding to the try-on instruction is selected.

[0147] For example, the user may send a try-on instruction through an interactive device.

[0148] Next, a static simulation try-on is performed on each foot point cloud model, and the static try-on effect is displayed to the user.

[0149] For example, static simulation fitting is performed on N+2 foot point cloud models, and the static fitting effect is fully displayed to the user. The comfort level corresponding to each foot point cloud model can also be displayed to the user.

[0150] Then, based on the point cloud models of all feet, dynamic simulation try-on is performed in the order of height difference, and the dynamic try-on effect is displayed to the user.

[0151] For example, based on N+2 foot point cloud models, the situation of shoes when the user's feet are in motion is simulated, and the dynamic try-on effect is fully displayed to the user.

[0152] Finally, the mold insole corresponding to the target shoe is selected for the user to try on.

[0153] Specifically, based on the first height difference, the second height difference, the collected height difference and the simulated height difference, the height difference of the mold insole is adjusted to allow users to experience the softness and comfort of the target shoes at different height differences.

[0154] This embodiment selects a mold insole corresponding to the target shoe for the user to try on, which can not only provide a virtual try-on, but also allow the user to truly experience the comfort of the shoe, thereby improving the efficiency of the user in selecting suitable shoes.

[0155] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0156] Corresponding to the method described in the above embodiment, for the convenience of explanation, only the part related to the embodiment of the present application is shown.

[0157] Figure 3 Schematic diagram of the structure of the device for recommending shoes provided in the embodiment of the present application. As an example but not a limitation, Figure 3 As shown, the device comprises:

[0158] A model processing unit 10, used to obtain a first foot point cloud model and a second foot point cloud model in different states;

[0159] Used to calculate the foot point cloud model transformation matrix based on the first foot point cloud model and the second foot point cloud model.

[0160] A transformation unit 11, configured to transform a pre-stored first shoe model based on a foot point cloud model transformation matrix to obtain at least one second shoe model;

[0161] A calculation unit 12, configured to calculate a final comfort level of the first shoe model according to the first comfort level and the second comfort level;

[0162] Among them, the first comfort level is determined based on the first foot point cloud model and the first shoe model, and the second comfort level is determined based on the second shoe model and the corresponding foot point cloud model.

[0163] In another embodiment, the apparatus further comprises:

[0164] A fitting unit, configured to receive a fitting instruction from a user and, in response to the fitting instruction, select a target shoe corresponding to the fitting instruction;

[0165] Used to perform static simulation try-on on each foot point cloud model and show the static try-on effect to the user;

[0166] It is used to perform dynamic simulation try-on based on all foot point cloud models in the order of height difference, and show the dynamic try-on effect to the user;

[0167] It is used to select the mold insole corresponding to the target shoe for the user to try on.

[0168] Figure 4 Schematic diagram of the structure of the shoe recommendation system provided in the embodiment of the present application. As an example and not a limitation, Figure 4 As shown, the system includes: a processor, a laser radar 20, a support platform 21, a first driver, a first lifting assembly 22 and a second driver;

[0169] For example, the supporting platform 21 is a circular platform.

[0170] The first driver is arranged on the supporting platform 21, and the first driver is power-coupled with the laser radar 20 to drive the laser radar 20 to rotate along the supporting platform 21. The laser radar 20 is used to collect point cloud data of the foot on the supporting platform, and the point cloud data is used to determine the point cloud model of the foot.

[0171] The second driver is disposed on the supporting platform 21, and is connected to the first lifting assembly 22 by power coupling, and is used to drive the first lifting assembly 22 to move up and down, so as to change the state of the foot on the first lifting assembly 22;

[0172] The processor is electrically connected to the laser radar 20, the first driver and the second driver respectively, and is used to execute the steps in the above-mentioned method embodiments.

[0173] Among them, the laser radar 20 can be set to collect point cloud data and then directly determine the foot point cloud model based on the collected point cloud data. The laser radar 20 can also be set to collect point cloud data and then send it to the processor, and the processor determines the foot point cloud model based on the point cloud data collected by the laser radar 20.

[0174] like Figure 4 As shown, the system further includes: a storage rack 23, a second lifting assembly and a third driver;

[0175] The rack 23 is connected to the support platform 21, and the rack 23 accommodates at least one mold insole, wherein the materials of each mold insole are different.

[0176] The second lifting assembly is disposed on the supporting platform 21;

[0177] The third driver is disposed on the supporting platform 21 , and is power-coupled with the second lifting assembly to drive the second lifting assembly to move up and down, so as to move the mold insole onto the supporting platform 21 .

[0178] In another embodiment, the storage rack and the support platform are integrally formed.

[0179] In another embodiment, the system further comprises at least one fourth driver;

[0180] The storage rack is provided with at least one mold insole accommodating unit, and at least one mold insole accommodating sheet is arranged in the mold insole accommodating unit along the direction vertical to the supporting platform for accommodating the mold insole.

[0181] The fourth driver is arranged on the storage rack, and is connected to the mold insole accommodating plate by power coupling, and is used to drive the mold insole accommodating plate to move, so as to place the mold insole in the mold insole accommodating plate on the second lifting assembly.

[0182] Specifically, in the processor, a corresponding relationship is established between the mold insole in the mold insole accommodating sheet and the shoe model. When the user selects the target shoe, the mold insole corresponding to the target shoe is selected, the mold insole accommodating sheet is driven to move by the fourth driver, the mold insole in the mold insole accommodating sheet is placed on the second lifting assembly, and the second lifting assembly is driven to move by the third driver to lift the mold insole onto the supporting platform.

[0183] After the mold insole is lifted to the support platform, the second lifting assembly is driven to move by the third driver so that the heel of the mold insole is placed on the first lifting assembly, so that the user can experience the softness and comfort of the mold insole at different height differences.

[0184] When the user has finished trying on the shoes, the fourth driver drives the corresponding mold insole accommodating sheet to move, and puts the mold insole placed on the second lifting assembly back onto the mold insole accommodating sheet.

[0185] In another embodiment, the system further comprises an interaction module;

[0186] The interactive module is electrically connected to the processor, the first driver, the second driver and the storage rack respectively.

[0187] Specifically, the processor can display static fitting effects and dynamic fitting effects to the user through the interactive module. The user can directly control the first driver through the interactive module to adjust the position of the laser radar. The user can directly control the second driver through the interactive module to adjust the position of the first lifting assembly. The user can select and put back the mold insole through the interactive module.

[0188] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0189] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0190] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0191] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0192] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0193] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0194] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0195] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0196] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0197] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for recommending shoes, characterized in that: include: Acquire a first foot point cloud model and a second foot point cloud model of the foot in different states, wherein the first foot point cloud model is a point cloud model collected when the foot is in a non-moving state, and the second foot point cloud model is a point cloud model collected when the foot is in a moving state; Calculate a foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model; Transforming a pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model; Calculating a final comfort level of the first shoe model according to a first comfort level and a second comfort level, wherein the first comfort level is determined according to the first foot point cloud model and the first shoe model, and the second comfort level is determined according to the second shoe model and the corresponding foot point cloud model; The step of calculating the foot point cloud model conversion matrix according to the first foot point cloud model and the second foot point cloud model includes: Between the first height difference and the second height difference, K acquisition height differences and NK simulation height differences are determined, wherein the value of K is in [0, N], and the value of N is greater than 0; If the value of K is not equal to 0, then for each of the collected height differences, a third foot point cloud model is obtained; For each of the simulated height differences, performing point cloud simulation based on the first foot point cloud model, the second foot point cloud model and the third foot point cloud model to obtain a fourth foot point cloud model; If the value of K is equal to 0, then for each of the simulated height differences, point cloud simulation is performed based on the first foot point cloud model and the second foot point cloud model to obtain the fourth foot point cloud model; For each of the N+2 foot point cloud models, the foot point cloud model is cut through two cutting planes, each of the cutting planes intersects with the foot point cloud model only at one line, the two cutting planes are parallel to each other, and the distance between the two cutting planes is the largest; At least one dividing surface is provided between the two cutting surfaces, and each of the dividing surfaces is parallel to the cutting surface; Based on all the segmentation surfaces, segment the foot point cloud model to obtain at least two modules; For the i-th foot point cloud model among the N+1 foot point cloud models, taking the module of the first foot point cloud model as a reference, calculating the variable parameters of each module in the i-th foot point cloud model; Based on the variable parameters of each module of the i-th foot point cloud model, form an i-th foot point cloud model conversion matrix, where the value of i is in [1, N+1]; Among them, the first height difference is the height difference between the first foot area and the second foot area in the first foot point cloud model, the second height difference is the height difference between the first foot area and the second foot area in the second foot point cloud model, the N+2 foot point cloud models include the N+1 foot point cloud model and the first foot point cloud model, and the N+1 foot point cloud model includes the third foot point cloud model, the fourth foot point cloud model and the second foot point cloud model.

2. The method according to claim 1, characterized in that The step of transforming the pre-stored first shoe model based on the foot point cloud model conversion matrix to obtain at least one second shoe model includes: Based on the i-th foot point cloud model conversion matrix, the first shoe model is transformed to obtain a second shoe model corresponding to the i-th foot point cloud model conversion matrix.

3. The method according to claim 2, characterized in that The second comfort level is determined according to the second shoe model and the corresponding foot point cloud model, including: Calculating the comfort level of the second shoe model corresponding to the i-th foot point cloud model; If the comfort level of each of the second shoe models is greater than or equal to the first comfort threshold, the comfort levels of all the second shoe models are normalized to obtain the second comfort level of the first shoe model.

4. The method according to claim 1, characterized in that The calculating the final comfort level of the first shoe model according to the first comfort level and the second comfort level includes: If the first comfort level is greater than or equal to a second comfort threshold, and the second comfort level is greater than or equal to a third comfort threshold, a final comfort level is calculated based on the first comfort level and the second comfort level.

5. The method according to claim 1, characterized in that After calculating the final comfort of the first shoe model, the method further includes: If the final comfort level is greater than a fourth comfort threshold, the shoe corresponding to the first shoe model is determined as a recommended shoe.

6. The method according to claim 5, characterized in that After determining the shoe corresponding to the first shoe model as the recommended shoe, the method further includes: After receiving a try-on instruction from a user, in response to the try-on instruction, selecting a target shoe corresponding to the try-on instruction; Perform static simulation try-on on each foot point cloud model and show the static try-on effect to the user; Based on the point cloud model of all feet, dynamic simulation try-on is performed in the order of height difference, and the dynamic try-on effect is displayed to the user; A mold insole corresponding to the target shoe is selected for the user to try on.

7. A shoe recommendation system, characterized in that: include: A processor, a laser radar, a support platform, a first driver, a first lifting assembly, and a second driver; The first driver is disposed on the support platform, and is power-coupled with the laser radar to drive the laser radar to rotate along the support platform. The laser radar is used to collect point cloud data of the foot on the support platform, and the point cloud data is used to determine a point cloud model of the foot; The second driver is disposed on the support platform, and the second driver is connected to the first lifting assembly by power coupling, and is used to drive the first lifting assembly to rise and fall, so as to change the state of the foot on the first lifting assembly; The processor is electrically connected to the laser radar, the first driver and the second driver respectively, and is used to execute the method according to any one of claims 1 to 6.

8. The system according to claim 7, characterized in that Also includes: A storage rack, a second lifting assembly and a third driver; The storage rack is connected to the support platform, and the storage rack accommodates at least one mold insole; The third driver is disposed on the supporting platform, and is power-coupled with the second lifting assembly to drive the second lifting assembly to move up and down, so as to move the mold insole onto the supporting platform.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images