Shoe cavity space optimization design method

Abstract

This application relates to the field of shoe cavity customization design technology, and particularly to a shoe cavity space optimization design method. The method includes: acquiring initial shoe last data and static contact pressure data; acquiring first pressure data of the user in a first state and second pressure data of the user in a second state; determining cavity adjustment data based on the initial shoe last data, first pressure data, second pressure data, and static contact pressure data; and determining optimized shoe last data based on the cavity adjustment data and the initial shoe last data. The shoe cavity space optimization design method provided by this application enables shoes produced from customized shoe last models to improve the user's walking experience and comfort.

Description

Technical Field

[0001] This application belongs to the field of shoe cavity customization design technology, and in particular relates to a shoe cavity space optimization design method. Background Technology

[0002] The shoe cavity is the geometric shape of the internal space of a shoe defined by the shoe last. The shoe cavity directly affects the comfort, fit, and athletic performance of the footwear.

[0003] In related technologies, traditional shoe cavity design methods mainly rely on standard shoe last databases and the experience of shoemakers. Mass production is achieved by selecting standard shoe lasts similar to the user's foot length and width. Existing technologies have seen the emergence of personalized shoe last customization methods based on 3D foot scanning. For example, by collecting point cloud data of the user's foot shape, a 3D foot model is constructed. Then, by scaling or freely deforming, a standard shoe last is adjusted to fit the foot surface, thus producing a customized shoe last. However, during walking, the ground reaction force on the foot can be several times the body weight, and the pressure distribution in different areas changes significantly with walking speed and gait phase. For example, the heel area experiences a peak impact at the moment of landing, the forefoot area requires greater flexion space during push-off, and the arch area needs stable support rather than rigid compression. This leads to problems such as heel slippage, forefoot pressure, and arch fatigue when walking at high speeds or wearing shoes for extended periods. Custom-produced shoe lasts may not fit the user well, resulting in a decreased wearing experience. Summary of the Invention

[0004] This application provides a method for optimizing the design of shoe cavity space, which can improve the problem that the shoe last after custom production cannot fit the user well, resulting in a decrease in the user's walking experience and comfort.

[0005] In a first aspect, embodiments of this application provide a method for optimizing shoe cavity space design, including: Acquire initial shoe last data and static contact pressure data; wherein, the initial shoe last data is used to reflect the spatial morphology data of the internal cavity of the shoe, and the static contact pressure data is used to reflect the pressure borne by various parts of the user's feet when the user wears the shoe corresponding to the initial shoe last data and stands still with both feet. Acquire first pressure data of the user in a first state and second pressure data of the user in a second state; wherein, the first state refers to the user walking at a first speed, and the first pressure data is used to reflect the pressure borne by the user's feet at various points in the first state; the second state refers to the user walking at a second speed greater than the first speed, and the second pressure data is used to reflect the pressure borne by the user's feet at various points in the second state. Based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data, cavity adjustment data is determined; wherein, the cavity adjustment data is used to reflect the adjustment data for adjusting the space of various parts of the internal cavity of the shoe; Based on the cavity adjustment data and the initial shoe last data, optimized shoe last data is determined; wherein, the optimized shoe last data refers to the data after optimizing and adjusting the space of each part of the internal cavity of the shoe.

[0006] The technical solutions described in this application embodiment have at least the following technical effects: The shoe cavity space optimization design method provided in this application first acquires initial shoe last data reflecting the spatial morphology of the shoe's internal cavity, and static contact pressure data reflecting the pressure exerted on various parts of the user's foot when the user is wearing the shoe corresponding to the initial shoe last data and standing still with both feet. Then, it acquires first pressure data reflecting the pressure exerted on various parts of the user's foot in a first state of walking at a first speed, and second pressure data reflecting the pressure exerted on various parts of the user's foot in a second state of walking at a second speed greater than the first speed. Based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data, it determines cavity adjustment data reflecting adjustments to the space of various parts of the shoe's internal cavity. Finally, based on the cavity adjustment data and the initial shoe last data, it determines the optimized data for the space of various parts of the shoe's internal cavity. This method, by simultaneously collecting dynamic pressure data from the user at two different speeds, can obtain sensitivity information of different areas of the sole to speed changes compared to using only static pressure data. Specifically, for the same foot position, the pressure difference under slow and fast walking reflects the area's response to dynamic loads. Areas with large pressure differences indicate that the area experiences additional impact loads with increasing speed, requiring more cushioning space in the shoe cavity design. Conversely, areas with small pressure differences indicate that the stress under dynamic conditions is similar to that under static conditions, allowing the original design to be maintained. This speed-sensitive zoning optimization strategy, compared to the traditional uniform adjustment strategy based on static pressure, concentrates adjustment resources on the areas most sensitive to dynamic loads. This significantly improves the efficiency and precision of personalized shoe cavity design and enhances the fit between the custom-made shoe last and the user, thereby improving the user's walking experience and comfort.

[0007] Secondly, embodiments of this application provide a shoe cavity space optimization design system, including: The acquisition module is used to acquire initial shoe last data and static contact pressure data; wherein, the initial shoe last data is used to reflect the spatial morphology data of the internal cavity of the shoe, and the static contact pressure data is used to reflect the pressure borne by various parts of the user's feet when the user wears the shoe corresponding to the initial shoe last data and stands still with both feet. The detection module is used to acquire first pressure data of the user in a first state and second pressure data of the user in a second state; wherein, the first state refers to the user walking at a first speed, and the first pressure data is used to reflect the pressure borne by the user's feet at various points in the first state; the second state refers to the user walking at a second speed greater than the first speed, and the second pressure data is used to reflect the pressure borne by the user's feet at various points in the second state. The first analysis module is used to determine cavity adjustment data based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data; wherein, the cavity adjustment data is used to reflect the adjustment data for adjusting the space of various parts of the internal cavity of the shoe; The second analysis module is used to determine optimized shoe last data based on the cavity adjustment data and the initial shoe last data; wherein, the optimized shoe last data refers to the data after optimizing and adjusting the space of each part of the internal cavity of the shoe.

[0008] Thirdly, embodiments of this application provide a shoe cavity space optimization design device, the shoe cavity space optimization design device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method as described in any of the first aspects above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the first aspects above.

[0010] Fifthly, embodiments of this application provide a computer program that, when run on a shoe cavity space optimization design device, causes the shoe cavity space optimization design device to execute the shoe cavity space optimization design method described in any one of the first aspects.

[0011] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic flowchart of a shoe cavity space optimization design method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation process of a shoe cavity space optimization design method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a shoe cavity space optimization design system provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a shoe cavity space optimization design device provided in one embodiment of this application. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the described embodiments are merely some, not all, embodiments of this application, and are used to explain this application, not to limit it. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes and to distinguish descriptions only, and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Furthermore, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein.

[0018] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0019] In related technologies, traditional shoe cavity design methods mainly rely on standard shoe last databases and the experience of shoemakers. Mass production is achieved by selecting standard shoe lasts similar to the user's foot length and width. Existing technologies have seen the emergence of personalized shoe last customization methods based on 3D foot scanning. For example, by collecting point cloud data of the user's foot shape, a 3D foot model is constructed. Then, by scaling or freely deforming, a standard shoe last is adjusted to fit the foot surface, thus producing a customized shoe last. However, during walking, the ground reaction force on the foot can be several times the body weight, and the pressure distribution in different areas changes significantly with walking speed and gait phase. For example, the heel area experiences a peak impact at the moment of landing, the forefoot area requires greater flexion space during push-off, and the arch area needs stable support rather than rigid compression. This leads to problems such as heel slippage, forefoot pressure, and arch fatigue when walking at high speeds or wearing shoes for extended periods. Custom-produced shoe lasts may not fit the user well, resulting in a decreased wearing experience.

[0020] To address the aforementioned issues, this application provides a method for optimizing the design of shoe cavity space. This method first acquires initial shoe last data reflecting the spatial morphology of the shoe's internal cavity, and static contact pressure data reflecting the pressure exerted on various parts of the user's feet when the user is wearing the shoe corresponding to the initial shoe last data and standing still. Then, it acquires first pressure data reflecting the pressure exerted on various parts of the user's feet in a first state of walking at a first speed, and second pressure data reflecting the pressure exerted on various parts of the user's feet in a second state of walking at a second speed greater than the first speed. Based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data, cavity adjustment data reflecting adjustments to the space of various parts of the shoe's internal cavity is determined. Finally, based on the cavity adjustment data and the initial shoe last data, data after optimizing and adjusting the space of various parts of the shoe's internal cavity is determined. This method effectively reduces the problem of insufficient optimization in traditional static standing detection and analysis by comparing the changes in plantar pressure during slow and fast walking, combined with a static pressure benchmark when standing still. This dual-speed pressure comparison logic effectively reduces the problem of insufficient optimization in traditional static standing detection and analysis processes. Furthermore, by simultaneously acquiring pressure changes under both slow and fast conditions and referencing static benchmarks, it further optimizes each area of ​​the user's foot based on dynamic pressure changes in different functional areas. This transforms the optimization process, which previously required multiple wears and user feedback, into an automated process. Consequently, it significantly improves the efficiency and precision of personalized shoe cavity design and enhances the fit between the customized shoe last and the user, thereby improving the user's walking experience and comfort.

[0021] The shoe cavity space optimization design method provided in this application embodiment can be applied to a shoe cavity space optimization design device. In this case, the shoe cavity space optimization design device is the execution subject of the shoe cavity space optimization design method provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of shoe cavity space optimization design device.

[0022] The equipment for optimizing shoe cavity space can be a terminal device, which can be a mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, smart screen, smart TV, handheld device with wireless communication function, desktop computer, computer, laptop computer, handheld computing device, etc.

[0023] To better understand the shoe cavity space optimization design method provided in the embodiments of this application, the specific implementation process of the shoe cavity space optimization design method provided in the embodiments of this application will be described by way of example below.

[0024] Figure 1 and Figure 2 A schematic flowchart illustrating the shoe cavity space optimization design method provided in this application is shown. Please refer to [link / reference]. Figure 1 and Figure 2 The methods for optimizing shoe cavity space include: S100, acquire initial shoe last data and static contact pressure data; wherein, the initial shoe last data is used to reflect the spatial shape data of the internal cavity of the shoe, and the static contact pressure data is used to reflect the pressure borne by various parts of the user's feet when the user wears the shoe corresponding to the initial shoe last data and stands still with both feet.

[0025] It's understandable that the shoe last, as the molding die in shoemaking, directly determines the fit between the shoe's internal space and the wearer's foot. Initial shoe last data refers to the set of three-dimensional geometric parameters of the reference shoe last used in shoe manufacturing. This data includes the specific shape of the shoe's internal cavity in terms of length, width, height, and the contours of various parts. Initial shoe last data can be obtained by scanning a standard shoe last with a 3D scanner or directly constructed using computer-aided design software. Static contact pressure data typically uses a foot pressure detection device, which consists of a flexible insole and flexible socks with numerous pressure sensors. When a user stands on it, each sensor outputs a corresponding pressure value, thus forming a complete foot pressure distribution map.

[0026] S200, acquire the first pressure data of the user in the first state and the second pressure data of the user in the second state; wherein, the first state refers to the user walking at a first speed, and the first pressure data is used to reflect the pressure borne by the user's feet at various points in the first state; the second state refers to the user walking at a second speed greater than the first speed, and the second pressure data is used to reflect the pressure borne by the user's feet at various points in the second state.

[0027] It's understandable that the first speed and the second speed can be two speeds with a fixed difference, or they can be the speeds corresponding to "slow walking" and "fast walking," respectively. The main difference between the first speed and the second speed is that they cannot be the same. The first state and the second state represent two walking conditions of different intensities, corresponding to daily slow walking and fast walking, respectively. At different walking speeds, the human gait changes significantly. Generally, as speed increases, stride length increases, impact force increases, and the relative sliding and deformation of the foot within the shoe cavity becomes more intense. The first pressure data is the data recorded in real time by a foot pressure detection device, showing the pressure changes over time at various locations on the entire foot while the user walks continuously for a fixed period of time wearing the test shoes at the first speed. The second pressure data is obtained by repeating the same data collection process at the second speed. Both the first and second pressure data contain complete information on pressure fluctuations over time, reflecting the pressure changes at various points on the foot throughout the complete gait cycle from heel strike to toe liftoff.

[0028] For example, the first speed can be 3-5 km / h (corresponding to slow daily walking), and the second speed can be 6-8 km / h (corresponding to brisk daily walking). The specific values ​​of the first and second speeds can be controlled by setting a fixed speed on the treadmill, or by setting a timing device on a track with a set distance to verify and adjust the walking speed based on the time required for the user to cover that distance, so that the user's actual walking speed falls within the corresponding speed range.

[0029] S300, based on initial last data, first pressure data, second pressure data and static contact pressure data, determines cavity adjustment data; wherein, cavity adjustment data is used to reflect the adjustment data for adjusting the space of various parts of the internal cavity of the shoe.

[0030] It can be understood that cavity adjustment data is a set of parameters calculated based on a comprehensive analysis of static pressure data and two types of dynamic pressure data, used to correct the geometry of various parts of the initial shoe last. A good pressure distribution during static standing may result in excessively high or low pressure in certain areas during dynamic walking due to foot deformation, impact, and slippage. By comparing the pressure differences between static and dynamic, and slow and fast walking, areas within the shoe cavity that are insufficiently adapted to movement can be identified, and the required increase or decrease in space can be quantified. Cavity adjustment data may include the increase or decrease in thickness values ​​at specific locations within the shoe cavity.

[0031] For example, multiple pressure data can be used to determine the changes in pressure on various parts of the user's foot in a first state and in a second state. Based on initial shoe last data and these changes, multiple functional areas of the foot can be determined to reflect the fit to the user's foot. Finally, based on the first pressure data, second pressure data, static contact pressure data, and these functional areas, cavity adjustment data can be determined. Alternatively, by spatially registering and time-normalizing the static contact pressure data, first pressure data, and second pressure data in a unified plantar coordinate system, the peak pressure and pressure-time integral at each discrete location under slow and fast walking can be extracted. The dynamic pressure ratios of these two values ​​relative to the static pressure can be calculated, and the difference between these two dynamic pressure ratios can be used to obtain the incremental change in additional pressure load caused by the increase in speed. Continuous closed regions where this incremental change exceeds a preset threshold can be identified and marked as areas to be adjusted. In each region to be adjusted, a linear or nonlinear response surface model between the dynamic pressure ratio and the shoe cavity thickness is established (which can be obtained through finite element simulation or experimental calibration). With the goal of minimizing the pressure ratio variance within the region, the gradient descent algorithm is used to calculate and analyze the required thickness increase or decrease at the corresponding position of the shoe cavity. Finally, the adjustment amounts of each region are synthesized according to spatial coordinates to form complete cavity adjustment data.

[0032] In one possible implementation, in step S300, cavity adjustment data is determined based on initial last data, first pressure data, second pressure data, and static contact pressure data, including: S310, based on the first pressure data and the second pressure data, determine multiple gait condition data; wherein, the gait condition data is used to reflect the changes in the pressure borne by the user's foot at various points in the first state and the pressure borne by the user's foot at various points in the second state.

[0033] It is understandable that gait condition data is data that characterizes gait features and their changes with speed, obtained by analyzing dynamic pressure data at two different speeds.

[0034] For example, the data can be divided into two parts based on the first pressure data and the second pressure data. Multiple gait status data can then be determined based on these two types of data divided by each walking cycle. Alternatively, feature extraction can be performed on the pressure-time curves at each sensor location, extracting feature parameters including average pressure, pressure-time integral, and peak pressure occurrence time. Then, two feature matrices corresponding to slow walking and fast walking are constructed for all sensor locations on the sole of the foot. Principal component analysis is then used to reduce the dimensionality of the two feature matrices, extracting the top principal components whose cumulative contribution rate exceeds a preset threshold. The cosine similarity of the angle between the principal component vectors of slow walking and fast walking is calculated to obtain the global gait similarity. For each sensor location, the Mahalanobis distance of its multiple feature vectors under slow and fast walking is calculated. Locations with Mahalanobis distances exceeding the global threshold are marked as significant change regions. Finally, the feature differences and their spatial distribution within all significant change regions are statistically analyzed to form the gait status data.

[0035] In one possible implementation, in step S310, based on the first pressure data and the second pressure data, multiple gait condition data are determined, including: S311, Based on the first pressure data, determine the first cycle sequence data; wherein, the first cycle sequence data is used to reflect the data after the first pressure data is divided according to each walking cycle.

[0036] The first pressure data is understood to be a continuous time series, recording the complete data on pressure changes over time at each sensor location during a slow walk. A complete gait cycle includes foot contact with the ground and foot liftoff. The first cycle sequence data is an ordered set of data obtained by segmenting the first pressure data according to a complete gait cycle. Gait cycle segmentation can be determined by detecting the sudden increase in pressure at the moment of heel contact with the ground in the pressure signal. It can also be determined by analyzing the user's walking speed in the first state.

[0037] S312, Based on the second pressure data, determine the second cycle sequence data; wherein, the second cycle sequence data is used to reflect the data of the second pressure data after being divided according to each walking cycle.

[0038] It is understandable that the second period sequence data can be obtained by using the second pressure data in the same way that the first period sequence data was obtained in step S311, and will not be elaborated here.

[0039] S313, based on the first cycle sequence data and the second cycle sequence data, determines multiple gait status data.

[0040] For example, by using each sequence node of the first-cycle sequence data and each sequence node of the second-cycle sequence data, we can determine the common location of the first-cycle sequence data and the second-cycle sequence data at the same position on the user's foot, as well as the time difference between each sequence node of the first-cycle sequence data and each sequence node of the second-cycle sequence data. Then, based on the common location of the user's foot, we determine the average value of the i-th sequence node of the first-cycle sequence data at the same position in one walking cycle, and the average value of the i-th sequence node of the second-cycle sequence data at the same position in one walking cycle, determined from the i-th sequence node of the second-cycle sequence data. Finally, based on these multiple average values, we determine the mean difference at the same location on the user's foot, reflecting the multiple first average data and multiple second average data. Finally, based on this mean difference and the corresponding time difference, we determine multiple gait status data. Alternatively, the first-cycle sequence data and the second-cycle sequence data can be input into a learning model, and the learning model outputs the corresponding multiple gait status data.

[0041] This setup discretizes continuous walking data into multiple independent gait cycle samples in the first cycle sequence, allowing for the elimination of random noise in periodic fluctuations and the extraction of statistically significant average gait features. The second cycle sequence shares the same structure as the first, enabling period-by-cycle and position-by-position comparative analysis within the same gait cycle framework. The gait data clearly and quantitatively demonstrates the impact of walking speed on pressure in different plantar regions, revealing which areas are most sensitive to speed changes and providing direct input for subsequent feature region segmentation and cavity adjustment.

[0042] In one possible implementation, in step S313, multiple gait status data are determined based on the first cycle sequence data and the second cycle sequence data, including: S3131, based on each sequence node of the first period sequence data and each sequence node of the second period sequence data, determine co-location information and multiple time differences; wherein, co-location information means that the first period sequence data and the second period sequence data are both located at the same position on the user's foot, and time difference means the time difference between each sequence node of the first period sequence data and each corresponding sequence node of the second period sequence data.

[0043] It is understandable that since the same pressure detection device is used for walking at both speeds, the spatial coordinate system of the sensor array is exactly the same, thus a one-to-one mapping table between pressure and spatial position can be established. Same position information refers to sensors with the same coordinates in the plantar pressure sensor array recording pressure in both the first and second cycle data. Time difference refers to the time deviation between the peak pressure moment or heel strike moment recorded by the same sensor location on the sole of the foot during slow walking and the corresponding peak pressure moment or heel strike moment during fast walking.

[0044] S3132, based on the same location information, determine the i-th first average data from the i-th sequence node of the first period sequence data and determine the i-th second average data from the i-th sequence node of the second period sequence data; wherein, the first average data is used to reflect the average value of the sequence nodes of the first period sequence data at the same location under one walking cycle, and the second average data is used to reflect the average value of the sequence nodes of the second period sequence data at the same location under one walking cycle.

[0045] It can be understood that the first average data is the average of pressure data at the same location in the first cycle sequence data. The second average data is the average of pressure data at the same location in the second cycle sequence data. For the pressure data collected from each sensor location on the foot, the pressure data of the sensor at the same location on the user's foot in each gait cycle is extracted from the first cycle sequence data, and the average value of the waveform is calculated to obtain the first average data. The same operation is performed on the second cycle sequence data to obtain the second average data.

[0046] S3133, based on multiple first average data and multiple second average data, determine the pressure change data corresponding to the same location information; wherein, the pressure change data is used to reflect the average difference between multiple first average data and multiple second average data.

[0047] It can be understood that pressure change data is calculated by subtracting the average of multiple first average data points from the average of multiple second average data points for each sensor location. Pressure change data = Average of multiple second average data points - Average of multiple first average data points.

[0048] S3134 determines multiple gait status data based on pressure change data and multiple time differences.

[0049] It can be understood that gait data = pressure change data ÷ data corresponding to pressure change data from multiple time differences.

[0050] For example, for each sensor location on the sole of the foot, the gait data is the change in pressure at that location over time differences under different conditions, which can describe the overall response characteristics of that location under speed changes.

[0051] This setup allows for the spatial normalization of speed comparisons based on location information, while the time difference quantifies the impact of speed variations on gait timing, providing parameters for subsequent time-axis normalization of pressure data. The first and second average data eliminate random fluctuations within a single gait cycle and variability across multiple cycles, providing a stable and repeatable baseline gait waveform, enabling meaningful quantitative comparisons of pressure characteristics at different speeds. Pressure variation data directly quantifies the degree and direction of speed changes' impact on the biomechanical environment of different areas of the foot, providing a quantitative basis for identifying areas sensitive to speed changes.

[0052] S320 determines multiple feature division regions based on initial shoe last data and multiple gait status data; among them, the feature division regions are used to reflect the foot functional areas adapted to the user's foot.

[0053] It can be understood that the feature-defined regions are functional areas of the foot adapted to the current user, redefined based on the geometric shape of the initial shoe last data and gait data. These regions differ from simple geometric partitions; they are functional partitions that incorporate the user's personalized pressure data. Each user's feature-defined regions are unique, and there are differences between different feature-defined regions. The feature-defined regions are determined by using the feature vectors at each location in the gait data as input and employing a region growing algorithm based on adjacency relationships to divide the shoe last space into several continuous, internally uniform blocks.

[0054] For example, basic foot functional regions that reflect the geometric shape pre-divided according to the initial shoe last data can be determined using initial shoe last data. Then, based on each basic foot functional region, a data subset corresponding to each basic foot functional region and reflecting the region extracted from the gait data corresponding to the initially divided region can be matched from the gait data. Then, based on each data subset and the basic foot functional region corresponding to the data subset, other regions belonging to the data subset can be determined from the adjacent regions of the regions corresponding to the data subset in multiple basic foot functional regions. Finally, these two types of regions are jointly identified as feature division regions unique to the user's foot. It is also possible to extract the three-dimensional spatial coordinates of each position on the sole of the foot from the initial shoe last data, and at the same time extract the pressure change feature vector of each position during slow and fast walking from the gait data. Then, the spatial coordinates of each sensor position and the corresponding gait feature vector are concatenated into a dataset. Cluster analysis is then performed on this dataset so that sample points that are spatially adjacent and have similar gait pressure response characteristics are classified into the same cluster. Finally, each cluster forms a continuous area on the sole of the foot, and the boundary of the cluster can be used as the boundary of the feature division region.

[0055] In one possible implementation, in step S320, based on the initial shoe last data and multiple gait condition data, multiple feature division regions are determined, including: S321, Based on the initial shoe last data, determine multiple initial division regions; wherein, the initial division regions are used to reflect the basic foot functional regions pre-divided according to the geometric shape of the initial shoe last data.

[0056] It is understandable that the initial division of the area is a standardized regional division of the shoe cavity space based on the geometry of the shoe last. This division does not consider the pressure data of individual users, but is based on general foot functional zoning rules. The initial division of the area can also refer to the foot skeletal structure, such as the first metatarsal area, the second-third metatarsal area, the fourth-fifth metatarsal area, the cuboid area, the calcaneus area, etc.

[0057] For example, the foot can be divided into the forefoot area, arch area and heel area according to the length ratio of the shoe last, and the forefoot area can be further divided into three sub-areas: medial, middle and lateral, according to the width direction.

[0058] S322, based on each initial segmentation region, match the matching periodic data sequence corresponding to each initial segmentation region from the gait status data; wherein, the matching periodic data sequence is used to reflect the data subset corresponding to the initial segmentation region extracted from the gait status data.

[0059] It can be understood that for each initially defined region, gait data corresponding to all sensor locations falling within that region's spatial range can be extracted to form a subset of data associated with that region, which is the matching periodic data sequence. This sequence contains gait data from all sensor locations within that region.

[0060] S323, based on each matching period data sequence and the initial partition region corresponding to the matching period data sequence, determine the feature partition region from the adjacent regions of the initial partition region corresponding to the matching period data sequence from multiple initial partition regions.

[0061] It's understandable that after analyzing the matching periodic data sequences within each initial partitioned region, some adjacent initial partitioned regions might be found to have similar stress response characteristics. In such cases, it's necessary to merge these similar regions into a larger, functionally consistent region. The feature partitioning region is an expanded feature region formed by judging the feature similarity between the initial partitioned region and its adjacent regions. Specifically, starting from a seed region, it checks whether the matching periodic data sequences of its adjacent regions are similar to the statistical characteristics of a seed region. If similar, the adjacent regions are included in the feature partitioning region, and this process continues to expand outwards until a boundary with significant feature differences is encountered.

[0062] For example, the geometric center point of the initial segmentation region can be determined by matching the initial segmentation region corresponding to the periodic data sequence. Then, based on the geometric center point and the initial segmentation region, a direction vector reflecting the boundary of the corresponding initial segmentation region originating from the geometric center point can be determined. Finally, based on the periodic data sequence corresponding to each of the direction vectors and the adjacent regions of the initial segmentation region, the feature segmentation region can be determined. Alternatively, each matching periodic data sequence and the initial segmentation region corresponding to the matching periodic data sequence can be input into the learning model, and the learning model outputs the corresponding feature segmentation region.

[0063] This setup standardizes the entire shoe cavity space according to general anatomical knowledge in the initial partitioning, providing a reference system for mapping personalized pressure data onto physiologically meaningful regions. Matching periodic data sequences correlates personalized pressure response data with standardized geometric partitions, allowing each initial partition to be characterized by the statistical features of all pressure data within it, providing a data foundation for subsequent region merging or re-segmentation. The encompassing region, through a data-driven region growing method, merges the initial standard anatomical partitions into functional areas with similar dynamic pressure response characteristics, facilitating subsequent adjustments and optimizations to different areas.

[0064] In one possible implementation, in step S323, based on each matching period data sequence and the initial partition region corresponding to the matching period data sequence, a feature partition region is determined from the adjacent regions of the initial partition region corresponding to the matching period data sequence from multiple initial partition regions, including: S3231, Based on the initial partitioned region corresponding to the matching periodic data sequence, determine the region center point; wherein, the region center point is used to reflect the geometric center point of the initial partitioned region.

[0065] It can be understood that the center point of a region refers to the centroid of the initially defined region within its two-dimensional geometric contour or the position of the initially defined region on the three-dimensional geometric contour of the region surface.

[0066] For example, for a regularly shaped region, the center point can be obtained by calculating the average of the vertex coordinates, while for an irregularly shaped region, the center point can be obtained by calculating the average of the coordinates of all points within the region.

[0067] S3232, based on the region center point and the initial division region, determine multiple feature vectors; where the feature vectors are used to reflect the direction vectors that start from the region center point and point to the boundary of the corresponding initial division region.

[0068] As can be understood, a feature vector is a unit vector that originates from the center point of a region and points to multiple representative directions on the boundary of that region. By sampling uniformly along the circumference, a set of feature vectors can be obtained, with each vector corresponding to a direction (e.g., 0° corresponds to the right, 90° corresponds to the top, etc.).

[0069] S3233, based on each feature vector and the periodic data sequence corresponding to the adjacent regions of the initial segmentation region, determine the feature segmentation region.

[0070] For example, for each feature vector pointing in a direction, starting from the center point of the region and extending outwards, passing through a series of points along that direction, each point corresponding to a pressure sensor location, gait data is acquired at each point along this ray, forming a pressure feature variation curve along that direction. By analyzing the variation pattern of this curve, it is determined at which distance the pressure feature changes significantly, and this location of significant change is the boundary of the region in that direction. By connecting the boundary points in multiple directions, a new, expanded region boundary can be delineated; this region is the new feature segmentation region adapted to the user's foot. Alternatively, the similarity of periodic data sequences between each point within each initial segmentation region and its corresponding points in adjacent regions can be calculated. Then, using the pair of adjacent regions with the highest similarity as seed points, region growth is performed outwards, incorporating spatially continuous regional units with similarity greater than a preset fixed threshold into the current feature region, thereby obtaining the feature segmentation region.

[0071] This setup provides a common starting point for subsequent eigenvector analysis at the region's center point, laying the foundation for exploring adjacent regions in all directions. Eigenvectors transform the problem of region boundary exploration into the analysis of feature changes along rays in fixed directions, making the determination of the directionality of region growth structured and computationally achievable. Through ray scanning and feature change detection along multiple eigenvectors, the encompassing region can be adaptively and accurately determined to have a functionally consistent spatial extent, with its boundaries precisely corresponding to the locations where abrupt changes in pressure response characteristics require adjustment.

[0072] In one possible implementation, step S3233 involves determining the feature partitioning region based on each feature vector and the periodic data sequence corresponding to the adjacent regions of the initially partitioned region, including: S32331, Based on each feature vector, determine the cumulative change data from the periodic data sequence corresponding to the initial division region and the adjacent regions of the initial division region; wherein, the cumulative change data is used to reflect the data sequence obtained by accumulating the periodic data sequence corresponding to the adjacent regions of the initial division region point by point along the feature vector direction from the center point of the region outward.

[0073] It can be understood that cumulative change data is generated by moving outwards along the direction indicated by each feature vector, starting from the center point of the region, and accumulating the feature values ​​in the periodic data sequence corresponding to each location point along the way, thus obtaining a cumulative sum sequence that varies with distance. Since the pressure response feature values ​​may fluctuate within and adjacent regions, cumulative change data can smooth out such local fluctuations into an overall trend change. However, if the characteristics of the regions traversed are significantly different, the growth slope of the cumulative change data near that point will change significantly.

[0074] S32332, when the cumulative change data changes, determine the first feature point; wherein, the first feature point is used to reflect the position point corresponding to the sudden change in the slope of the cumulative change data.

[0075] It is understandable that changes in cumulative change data do not refer to any change in the exponential value, but rather to the location where the rate of change undergoes a significant abrupt change. In the cumulative change data curve, if the characteristic value remains constant along a certain direction, the cumulative curve is a straight line with a constant slope. However, if the characteristic value experiences a step drop or rise, the slope of the cumulative curve will suddenly change direction. The first characteristic point is precisely the spatial location corresponding to this inflection point, reflecting the boundary point where the pressure response characteristics begin to deviate significantly from the initial regional characteristics.

[0076] S32333, based on multiple feature vectors and their corresponding first feature points, constructs a feature segmentation region.

[0077] It can be understood that the construction of the feature partitioning region is achieved by connecting and closing the first feature points identified in all feature vector directions. Specifically, for each feature vector direction, a first feature point has been determined. This feature point has a polar coordinate. These first feature points are connected in order of angle to form a closed polygon or smooth curve. The spatial range enclosed by this closed curve is the feature partitioning region.

[0078] S330 determines cavity adjustment data based on first pressure data, second pressure data, static contact pressure data, and multiple feature division regions.

[0079] For example, by using first pressure data, second pressure data, static contact pressure data, and multiple feature-divided regions, the region reflecting the need for shoe cavity space adjustment within the feature-divided regions, and the deviation of the impact experienced by the region requiring shoe cavity space adjustment during user walking relative to when the user is standing, can be determined. Then, based on this deviation, cavity adjustment data corresponding to the region requiring shoe cavity space adjustment can be determined. Alternatively, the first pressure data, second pressure data, static contact pressure data, and multiple feature-divided regions can be input into a learning model, and the learning model can output the corresponding cavity adjustment data.

[0080] This configuration transforms the raw dynamic pressure waveform of gait data into feature vectors with clear physiological and mechanical significance. This reduces the impact of differences in gait cycle duration at different speeds, allowing for the quantification and comparison of response changes at various points on the sole at different walking speeds. Feature segmentation discretizes the continuous and complex plantar pressure distribution into several functionally consistent independent analysis units, enabling targeted and independent cavity adjustments within each region. By independently comparing the static baseline with the dynamic response within each feature segmentation region, the cavity adjustment data can accurately identify which areas require adjustment and which do not, achieving refined, zoned optimization of the shoe cavity space based on actual wearing experience.

[0081] In one possible implementation, in step S330, cavity adjustment data is determined based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature-divided regions, including: S331, based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature division regions, determines the region to be optimized and the degree of condition difference; wherein, the region to be optimized is used to reflect the area in the feature division region that needs to be adjusted in the shoe cavity space, and the degree of condition difference is used to reflect the deviation of the region to be optimized from the impact when the user walks to the deviation when the user is standing.

[0082] It is understandable that not all feature-defined areas require shoe cavity adjustments. Some user-specific feature-defined areas exhibit pressure levels within a reasonable range under both static standing and dynamic walking conditions; these areas can be considered as requiring no adjustment. Areas requiring optimization refer to those feature-defined areas where the pressure response under dynamic walking conditions differs significantly from the static baseline pressure.

[0083] For example, by using first pressure data, second pressure data, and static contact pressure data, we can determine the changes in the first pressure data compared to the static contact pressure data, and the changes in the second pressure data compared to the static contact pressure data. Based on these two changes, we determine the difference between the changes in the first pressure data and the changes in the second pressure data at the same location on the user's foot. Then, based on this difference and multiple feature-divided regions, we determine the region to be optimized and the region after removing the region to be optimized from the feature-divided data. Finally, we calculate the average difference in the changes in the region to be optimized and the average difference in the region after removing the region to be optimized from the feature-divided data. The difference between the average changes in the regions is identified as the degree of difference in conditions. Furthermore, for each feature region, pressure peak data of each sampling point on the sole of the foot can be extracted under three working conditions: static standing, walking at the first speed, and walking at the second speed. The mean and standard deviation of the pressure peak in each region can be calculated. Then, using the static pressure peak as a benchmark, the relative change rate of the pressure peak under the first speed and the second speed is calculated, i.e., relative change rate = (dynamic peak - static peak) ÷ static peak. For each feature region, the relative change rate of all sampling points within it is used to form a data set. When the mean of the relative change rate of a region under the second speed exceeds the upper limit of the preset threshold, the region is determined to be a region to be optimized.

[0084] In one possible implementation, in step S331, based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature-divided regions, the region to be optimized and the degree of difference in conditions are determined, including: S3311, based on the first pressure data, the second pressure data, and the static contact pressure data, determine the first change state and the second change state; wherein, the first change state is used to reflect the change state of the first pressure data compared to the static contact pressure data, and the second change state is used to reflect the change state of the second pressure data compared to the static contact pressure data.

[0085] The first variation condition is understood to be the degree of difference obtained by comparing the first pressure data under slow walking with the static contact pressure data under static standing conditions point by point. For each sensor location on the foot, the first variation condition can calculate the difference between the pressure data during slow walking and the static pressure data. The second variation condition is the difference obtained by comparing the second pressure data under fast walking with the static pressure data.

[0086] S3312, based on the first change condition and the second change condition, determine the change condition difference at the same position of the user's foot; wherein, the change condition difference is used to reflect the difference between the first change condition and the second change condition at the same position of the user's foot.

[0087] It can be understood that the difference in changes is the difference obtained by subtracting the first change from the second change at each sensor location on the sole of the foot. That is, the difference in changes = the second change - the first change.

[0088] S3313, Based on the difference in change status and multiple feature division regions, determine the region to be optimized and the non-optimized region; where the non-optimized region refers to the region after removing the region to be optimized from the feature division region.

[0089] It is understandable that, for each feature-divided region, the average and standard deviation of the variation differences at all sensor locations within that region are calculated. If the average variation difference within a region is significantly greater than the overall average variation difference across all regions of the entire sole, that region is marked as a region to be optimized.

[0090] For example, for each feature segmentation region, the statistical dispersion corresponding to each feature segmentation region can be determined from the variation difference. Then, for each feature segmentation region, a traversal analysis is performed on the variation difference of the corresponding feature segmentation region to identify the data reflecting the removal of a location point in the feature segmentation region. After that, the statistical dispersion of the variation difference of the remaining locations in the region is recalculated. Based on these two statistical dispersions, when the statistical dispersion of the variation difference of the remaining locations in the region changes significantly relative to the statistical dispersion of the feature segmentation region after removing a location point, the location point corresponding to the degree of removal fluctuation is identified. Finally, the region constructed from multiple locations is designated as the region to be optimized, and the region in the feature segmentation region excluding the region to be optimized is designated as the non-optimized region. Alternatively, the variation difference and multiple feature segmentation regions can be input into a learning model, and the learning model outputs the corresponding regions to be optimized and non-optimized.

[0091] In one possible implementation, in step S3313, the region to be optimized and the non-optimized region are determined based on the difference in change conditions and multiple features, including: S33131, based on each feature division region, determine the baseline fluctuation degree corresponding to each feature division region from the difference in change status; wherein, the baseline fluctuation degree is used to reflect the statistical dispersion in the feature division region.

[0092] The baseline fluctuation level can be understood as the standard deviation of the difference in changes within each feature segmentation region. For a given feature segmentation region, the difference in changes at all sensor locations within that region is extracted to form a dataset. The standard deviation of this dataset is then calculated, yielding the baseline fluctuation level. The baseline fluctuation level reflects the uniformity of pressure sensitivity within that region. A small standard deviation indicates that the differences in changes at various points within the region are similar, indicating consistent overall behavior. Conversely, a large standard deviation indicates significant local differences within the region.

[0093] S33132, based on each feature division region, perform a traversal analysis to eliminate the variation differences in the corresponding feature division region and determine the degree of elimination fluctuation; wherein, the degree of elimination fluctuation is used to reflect the statistical dispersion of the variation differences of the remaining positions in the feature division region after removing the data of a position point.

[0094] As can be understood, outlier analysis is used to identify outliers within a region, i.e., isolated locations whose characteristics are significantly different from other points. For each sensor location within the feature-defined region, the variation value of that point is temporarily removed, and then the standard deviation is recalculated based on the remaining data points to obtain the degree of outlier fluctuation. If, after removing a point, the standard deviation of the remaining data significantly decreases compared to the baseline fluctuation, it indicates that that point is an outlier.

[0095] S33133, based on the baseline volatility and the elimination volatility, determine multiple second feature points; wherein, the second feature points are used to reflect the position point of elimination corresponding to the elimination volatility when the elimination volatility changes significantly relative to the baseline volatility.

[0096] It is understandable that a preset threshold can be set. When the decrease in the degree of fluctuation of the excluded point relative to the baseline fluctuation exceeds the preset value, the position corresponding to the excluded point is determined to be a second feature point. Thus, multiple such second feature points can be identified in each feature division area. The preset threshold can also be obtained directly from a threshold database.

[0097] S33134, the region constructed by multiple second feature points is taken as the region to be optimized, and the region in the corresponding feature division region excluding the region to be optimized is taken as the non-optimized region.

[0098] It can be understood that the region to be optimized is not necessarily the entire feature partitioning region, but rather a local area composed of the second feature points. Each second feature point is used as a reference, and these second feature points are merged to form a continuous region to be optimized. The remaining part of the feature partitioning region not covered by the region to be optimized is the non-optimized region.

[0099] This setup uses the baseline volatility as the background level of variability within the region, providing a benchmark for judging whether the volatility changes significantly after removing a certain point. The volatility removal analysis automatically identifies locations within the region that deviate from the mainstream trend and require adjustment. The second feature point transforms the original approach of uniform adjustment across the entire region into a targeted, precise adjustment, concentrating optimization resources on the localized locations that contribute most to pressure anomalies. By limiting the optimization area to a small region around the second feature point, over-optimization that might result from uniform adjustment across the entire feature area is reduced. This makes the optimization design more refined and targeted, solving the core problem while preserving good fit for other parts of the shoe cavity.

[0100] S3314, the difference between the average change difference of the region to be optimized and the average change difference of the non-optimized region is identified as the degree of difference in condition.

[0101] It can be understood that the degree of difference in conditions equals the average difference in conditions between the region to be optimized and the average difference in conditions between the non-optimized regions. The larger this difference value, the stronger the response of the region to be optimized to speed changes, and the more necessary it is to make special adjustments to the shoe cavity space.

[0102] This setup, using static pressure as a baseline, normalizes the additional load exerted on different areas of the foot by dynamic walking in both the first and second conditional changes. By filtering areas with poor conditional changes based on statistical characteristics, the optimization focuses on those locations most sensitive to speed changes and requiring special design within the shoe cavity. The degree of conditional difference is expressed as a single, comparable value, highlighting the prominence of the optimization area's pressure sensitivity. This provides input parameters for mapping the degree of conditional difference to specific adjustment amounts and also serves as a basis for prioritizing the adjustments of multiple optimization areas.

[0103] S332, determine the cavity adjustment data corresponding to the area to be optimized based on the degree of difference in conditions.

[0104] It is understandable that for each feature segmentation region marked as to be optimized, its corresponding cavity adjustment data is calculated by mapping the degree of condition difference to the geometric adjustment amount of the shoe cavity. A higher degree of condition difference corresponds to a larger spatial adjustment amount, that is, increasing the shoe cavity space in that region, reducing pressure on the foot, or increasing cushioning. A lower degree of condition difference corresponds to a smaller adjustment amount, that is, reducing space or increasing padding to provide better support.

[0105] This setup specifies the spatial location requiring intervention within the area to be optimized, and quantifies the degree of difference in conditions to determine the intensity of intervention needed. This provides a clear target and magnitude for subsequent calculations of the specific cavity adjustment amount. The cavity adjustment data is then transformed into specific geometric correction amounts through a quantification model. This ensures that the adjustment not only has a clear direction but also precise adjustment data, enabling an executable and verifiable shoe cavity space optimization design.

[0106] S400, based on cavity adjustment data and initial shoe last data, determines optimized shoe last data; where optimized shoe last data refers to data after optimizing and adjusting the space of each part of the shoe's internal cavity.

[0107] It can be understood that optimizing shoe last data involves applying cavity adjustment data as a deformation quantity to the initial shoe last data to obtain new three-dimensional geometric parameters for the shoe last. This can be achieved by matching and mapping the cavity adjustment data with an adjustment database, matching corresponding adjustment parameters based on the degree of difference in the cavity adjustment data's condition, and adjusting the spatial morphology of the areas to be optimized in the initial shoe last data according to these adjustment parameters. Finally, after targeted adjustments to the spatial morphology of each area to be optimized in the initial shoe last data, the resulting adjusted spatial morphology is the optimized shoe last data. The adjustment database can obtain raw data from multiple sets of experiments or simulations (such as pressure distribution data of different users' feet at different speeds). Then, the raw data is preprocessed and features are extracted. Key feature indicators are obtained through gait cycle segmentation, Fourier transform, or statistical methods. The extracted feature indicators are then correlated with the corresponding working condition parameters. By comparing the deviation between the theoretical benchmark and the actual response, regression fitting, interpolation, or machine learning methods are used to establish a mapping relationship from working conditions to adjustment quantities. Finally, these mapping parameters are classified and stored according to region, working condition type, or optimization objective, forming an adjustment database that can be directly called by the control system or optimization algorithm.

[0108] This setup, by simultaneously collecting dynamic pressure data from users at two different speeds, provides more information on the sensitivity of different areas of the foot to speed changes compared to using only static pressure data. Specifically, for the same foot location, the pressure difference between slow and fast walking reflects the area's response to dynamic loads. Areas with large pressure differences indicate that the area experiences additional impact loads as speed increases, requiring more cushioning space in the shoe cavity design. Conversely, areas with small pressure differences indicate that the stress under dynamic conditions is similar to that under static conditions, allowing the original design to be maintained. This speed-sensitivity-based zonal optimization strategy, compared to the traditional uniform adjustment strategy based on static pressure, concentrates adjustment resources on the areas most sensitive to dynamic loads. This significantly improves the efficiency and accuracy of personalized shoe cavity design and enhances the fit between the custom-made shoe last and the user, thereby improving the user's walking experience and comfort.

[0109] It should be understood that the sequence number of each step in the above embodiments does not imply 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 this application.

[0110] Corresponding to the shoe cavity space optimization design method described in the above embodiments, this application also provides a shoe cavity space optimization design system, the various modules of which can implement the various steps of the shoe cavity space optimization design method. Figure 3 The diagram shows a structural block diagram of the shoe cavity space optimization design system provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0111] Reference Figure 3 The shoe cavity space optimization design system includes: The acquisition module is used to acquire initial shoe last data and static contact pressure data. The initial shoe last data reflects the spatial morphology of the internal cavity of the shoe, and the static contact pressure data reflects the pressure borne by various parts of the user's feet when the user wears the shoe corresponding to the initial shoe last data and stands still with both feet.

[0112] The detection module is used to acquire first pressure data of the user in a first state and second pressure data of the user in a second state. The first state refers to the user walking at a first speed, and the first pressure data is used to reflect the pressure on various parts of the user's feet in the first state. The second state refers to the user walking at a second speed greater than the first speed, and the second pressure data is used to reflect the pressure on various parts of the user's feet in the second state.

[0113] The first analysis module is used to determine cavity adjustment data based on initial shoe last data, first pressure data, second pressure data, and static contact pressure data; wherein, the cavity adjustment data is used to reflect the adjustment data for adjusting the space of various parts of the internal cavity of the shoe.

[0114] The second analysis module is used to determine the optimized last data based on the cavity adjustment data and the initial last data; whereby the optimized last data refers to the data after optimizing and adjusting the space of each part of the internal cavity of the shoe.

[0115] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0116] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system 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 embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0117] This application also provides a shoe cavity space optimization design device. Figure 4 This is a schematic diagram of the shoe cavity space optimization design device 4 provided in one embodiment of this application. Figure 4 As shown, the shoe cavity space optimization design device 4 of this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown in the image), at least one memory 41 ( Figure 4 (Only one is shown in the image) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40. When the processor 40 executes the computer program 42, it causes the shoe cavity space optimization design device 4 to implement the steps in any of the above-described shoe cavity space optimization design method embodiments, or causes the shoe cavity space optimization design device 4 to implement the functions of each module / unit in the above-described system embodiments.

[0118] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 42 in the shoe cavity space optimization design device 4.

[0119] The shoe cavity space optimization design device 4 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. This shoe cavity space optimization design device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of the shoe cavity space optimization design device 4 and does not constitute a limitation on the shoe cavity space optimization design device 4. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0120] The processor 40 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0121] In some embodiments, the memory 41 may be an internal storage unit of the shoe cavity space optimization design device 4, such as a hard disk or memory of the shoe cavity space optimization design device 4. In other embodiments, the memory 41 may be an external storage device of the shoe cavity space optimization design device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the shoe cavity space optimization design device 4. Further, the memory 41 may include both internal storage units and external storage devices of the shoe cavity space optimization design device 4. The memory 41 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0122] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0123] This application provides a computer program product that, when run on a shoe cavity space optimization design device, enables the shoe cavity space optimization design device to implement the steps in any of the above method embodiments.

[0124] If the integrated unit is implemented as 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to the shoe cavity space optimization design device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0125] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0126] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0127] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for optimizing shoe cavity space, characterized in that, include: Acquire initial shoe last data and static contact pressure data; wherein, the initial shoe last data is used to reflect the spatial morphology data of the internal cavity of the shoe, and the static contact pressure data is used to reflect the pressure borne by various parts of the user's feet when the user wears the shoe corresponding to the initial shoe last data and stands still with both feet. Acquire first pressure data of the user in a first state and second pressure data of the user in a second state; wherein, the first state refers to the user walking at a first speed, and the first pressure data is used to reflect the pressure borne by the user's feet at various points in the first state; the second state refers to the user walking at a second speed greater than the first speed, and the second pressure data is used to reflect the pressure borne by the user's feet at various points in the second state. Based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data, cavity adjustment data is determined; wherein, the cavity adjustment data is used to reflect the adjustment data for adjusting the space of various parts of the internal cavity of the shoe; Based on the cavity adjustment data and the initial shoe last data, optimized shoe last data is determined; wherein, the optimized shoe last data refers to the data after optimizing and adjusting the space of each part of the internal cavity of the shoe.

2. The shoe cavity space optimization design method as described in claim 1, characterized in that, The step of determining cavity adjustment data based on the initial shoe last data, the first pressure data, the second pressure data, and the static contact pressure data includes: Based on the first pressure data and the second pressure data, multiple gait status data are determined; wherein, the gait status data is used to reflect the changes in the pressure borne by the user's foot at various points in the first state and the pressure borne by the user's foot at various points in the second state. Based on the initial shoe last data and multiple gait status data, multiple feature division regions are determined; wherein, the feature division regions are used to reflect the foot functional areas adapted to the user's foot; Based on the first pressure data, the second pressure data, the static contact pressure data, and the multiple feature division regions, cavity adjustment data is determined.

3. The shoe cavity space optimization design method as described in claim 2, characterized in that, The determination of multiple gait status data based on the first pressure data and the second pressure data includes: Based on the first pressure data, a first cycle sequence data is determined; wherein, the first cycle sequence data is used to reflect the data of the first pressure data after being divided according to each walking cycle; Based on the second pressure data, a second cycle sequence data is determined; wherein, the second cycle sequence data is used to reflect the data of the second pressure data after being divided according to each walking cycle; Based on the first periodic sequence data and the second periodic sequence data, multiple gait status data are determined.

4. The shoe cavity space optimization design method as described in claim 3, characterized in that, The determination of multiple gait status data based on the first periodic sequence data and the second periodic sequence data includes: Based on each sequence node of the first periodic sequence data and each sequence node of the second periodic sequence data, co-location information and multiple time differences are determined; wherein, the co-location information refers to the first periodic sequence data and the second periodic sequence data being located at the same position on the user's foot, and the time difference refers to the time difference between each sequence node of the first periodic sequence data and each corresponding sequence node of the second periodic sequence data; Based on the same location information, the i-th first average data is determined from the i-th sequence node of the first periodic sequence data and the i-th second average data is determined from the i-th sequence node of the second periodic sequence data; wherein, the first average data is used to reflect the average value of the sequence nodes of the first periodic sequence data at the same location in a walking cycle, and the second average data is used to reflect the average value of the sequence nodes of the second periodic sequence data at the same location in a walking cycle. Based on multiple first average data points and multiple second average data points, pressure change data corresponding to the same location information is determined; wherein, the pressure change data is used to reflect the average difference between multiple first average data points and multiple second average data points; Based on the pressure change data and the multiple time differences, multiple gait status data are determined.

5. The shoe cavity space optimization design method as described in claim 2, characterized in that, Based on the initial shoe last data and multiple gait status data, multiple feature division regions are determined, including: Based on the initial shoe last data, multiple initial division regions are determined; wherein, the initial division regions are used to reflect the basic foot functional regions pre-divided according to the geometric shape of the initial shoe last data; Based on each of the initial segmented regions, a matching periodic data sequence corresponding to each of the initial segmented regions is matched from the gait status data; wherein, the matching periodic data sequence is used to reflect the data subset corresponding to the initial segmented region extracted from the gait status data; Based on each of the matching periodic data sequences and the initial partitioning regions corresponding to the matching periodic data sequences, feature partitioning regions are determined from the adjacent regions of the initial partitioning regions corresponding to the initial partitioning regions of the matching periodic data sequences among the multiple initial partitioning regions.

6. The shoe cavity space optimization design method as described in claim 5, characterized in that, The step of determining feature partitioning regions from adjacent regions of the initial partitioning regions corresponding to the matching periodic data sequences within a plurality of initial partitioning regions based on each of the matching periodic data sequences and the initial partitioning regions corresponding to the matching periodic data sequences includes: Based on the initial partitioned region corresponding to the matching periodic data sequence, the region center point is determined; wherein, the region center point is used to reflect the geometric center point of the initial partitioned region; Based on the center point of the region and the initial division region, multiple feature vectors are determined; wherein, the feature vectors are used to reflect the direction vectors that start from the center point of the region and point to the boundary of the corresponding initial division region; The feature division region is determined based on each feature vector and the periodic data sequence corresponding to the adjacent regions of the initial division region.

7. The shoe cavity space optimization design method as described in claim 6, characterized in that, The step of determining the feature partitioning region based on each feature vector and the periodic data sequence corresponding to the adjacent regions of the initial partitioning region includes: Based on each of the feature vectors, cumulative change data is determined from the initial partitioned region and the periodic data sequence corresponding to the adjacent regions of the initial partitioned region; wherein, the cumulative change data is used to reflect the data sequence obtained by accumulating the periodic data sequence corresponding to the adjacent regions of the initial partitioned region point by point outward from the center point of the region along the direction of the feature vector; When the cumulative change data changes, a first feature point is determined; wherein, the first feature point is used to reflect the position point corresponding to the abrupt change in the slope of the change in the cumulative change data; Based on multiple feature vectors and the corresponding first feature points, a feature segmentation region is constructed.

8. The shoe cavity space optimization design method as described in claim 2, characterized in that, The step of determining cavity adjustment data based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature division regions includes: Based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature division regions, the region to be optimized and the degree of condition difference are determined; wherein, the region to be optimized is used to reflect the area in the feature division region that needs to be adjusted in the shoe cavity space, and the degree of condition difference is used to reflect the deviation of the impact received by the region to be optimized when the user walks relative to when the user is standing. Based on the degree of difference in the conditions, cavity adjustment data corresponding to the region to be optimized is determined.

9. The shoe cavity space optimization design method as described in claim 8, characterized in that, The step of determining the region to be optimized and the degree of difference in condition based on the first pressure data, the second pressure data, the static contact pressure data, and multiple feature-divided regions includes: Based on the first pressure data, the second pressure data, and the static contact pressure data, a first change state and a second change state are determined; wherein, the first change state is used to reflect the change state of the first pressure data compared to the static contact pressure data, and the second change state is used to reflect the change state of the second pressure data compared to the static contact pressure data. Based on the first change and the second change, a difference in change at the same position on the user's foot is determined; wherein, the difference in change is used to reflect the difference between the first change and the second change at the same position on the user's foot. Based on the difference in the change status and the multiple feature division regions, the region to be optimized and the non-optimized region are determined; wherein, the non-optimized region refers to the region after removing the region to be optimized from the feature division regions; The difference between the average change difference of the region to be optimized and the average change difference of the non-optimized region is defined as the degree of difference in condition.

10. The shoe cavity space optimization design method as described in claim 9, characterized in that, The step of determining the region to be optimized and the region not to be optimized based on the difference in the change status and multiple features includes: Based on each of the feature division regions, a baseline fluctuation degree corresponding to each of the feature division regions is determined from the difference in change status; wherein, the baseline fluctuation degree is used to reflect the statistical dispersion of the feature division regions; Based on each of the feature division regions, the change status differences that fall within the corresponding feature division region are subjected to elimination traversal analysis to determine the elimination fluctuation degree; wherein, the elimination fluctuation degree is used to reflect the statistical dispersion of the change status differences of the remaining positions in the feature division region after removing the data of a position point in the feature division region. Based on the baseline fluctuation level and the elimination fluctuation level, a plurality of second feature points are determined; wherein, the second feature points are used to reflect the position point of elimination corresponding to the elimination fluctuation level when the elimination fluctuation level changes significantly relative to the baseline fluctuation level; The region constructed from multiple second feature points is taken as the region to be optimized, and the region in the corresponding feature division region excluding the region to be optimized is taken as the non-optimized region.

Images