Method, device and terminal equipment for generating personalized insoles

Abstract

The application relates to the field of 3D printing technology and discloses a personalized insole generation method, device and terminal equipment, which comprises the following steps: according to plantar stress distribution data and user demand data, dividing the plantar region of a three-dimensional foot model into sub-regions provided with target mechanical parameters; for each sub-region, searching a filler matching the target mechanical parameters of the sub-region from a filler database; based on the type of the filler, determining the filler interpolation data of the transition region and the non-transition region in each sub-region, and based on the filler interpolation data, constructing a filler structure model; and performing Boolean operation on the filler structure model and the three-dimensional foot model to generate a 3D printable personalized insole model. The method can realize personalized design in the true sense from two dimensions of "morphological adaptation" and "functional response".

Description

Technical Field

[0001] This application relates to the field of 3D printing technology, and in particular to a method, apparatus and terminal device for generating personalized insoles. Background Technology

[0002] With the development of additive manufacturing (3D printing) technology, personalized insoles have attracted widespread attention due to their potential to improve wearing comfort, gait function and assist in rehabilitation treatment.

[0003] Traditional insoles are mostly produced using standardized molds, resulting in uniform materials and structures. This makes them unsuitable for adapting to the differences in foot shape and biomechanical properties among individuals, especially in meeting specific needs such as arch support, pressure distribution, or gait correction. Although customized insoles based on foot shape scanning have emerged on the market, their improvements mainly focus on adapting the external contours, while the internal structure still lacks functional design, failing to achieve true personalization. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, and terminal device for generating personalized insoles, which can effectively solve the technical problem that traditional insoles cannot adapt to the differences in foot shape and mechanical properties of different individuals.

[0005] In a first aspect, embodiments of this application provide a method for generating personalized insoles, including:

[0006] Based on plantar stress distribution data and user demand data, the plantar region of the three-dimensional foot model is divided into sub-regions with set target mechanical parameters;

[0007] For each of the aforementioned sub-regions, a filler that matches the target mechanical parameters of the sub-region is searched from the filler database;

[0008] Based on the type of infill material, determine the infill interpolation data for the transition and non-transition regions in each sub-region, and construct an infill structure model based on the infill interpolation data;

[0009] Boolean operations are performed on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0010] Secondly, embodiments of this application provide a personalized insole generating device, comprising:

[0011] The segmentation module is used to segment the plantar region of the 3D foot model into sub-regions with set target mechanical parameters based on plantar stress distribution data and user demand data.

[0012] The search module is used to search the filler database for each of the sub-regions for fillers that match the target mechanical parameters of the sub-region.

[0013] A construction module is used to determine the interpolation data of the filler in the transition area and the non-transition area in each of the sub-regions based on the type of filler, and to construct the filler structure model based on the filler interpolation data;

[0014] The generation module is used to perform Boolean operations on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0015] Thirdly, this application also provides a terminal device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0016] Based on plantar stress distribution data and user demand data, the plantar region of the three-dimensional foot model is divided into sub-regions with set target mechanical parameters;

[0017] For each of the aforementioned sub-regions, a filler that matches the target mechanical parameters of the sub-region is searched from the filler database;

[0018] Based on the type of infill material, determine the infill interpolation data for the transition and non-transition regions in each sub-region, and construct an infill structure model based on the infill interpolation data;

[0019] Boolean operations are performed on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0021] Based on plantar stress distribution data and user demand data, the plantar region of the three-dimensional foot model is divided into sub-regions with set target mechanical parameters;

[0022] For each of the aforementioned sub-regions, a filler that matches the target mechanical parameters of the sub-region is searched from the filler database;

[0023] Based on the type of infill material, determine the infill interpolation data for the transition and non-transition regions in each sub-region, and construct an infill structure model based on the infill interpolation data;

[0024] Boolean operations are performed on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0025] The embodiments of this application have the following beneficial effects:

[0026] The insole shape is constructed based on the user's three-dimensional foot geometry model, and individualized foot stress distribution data and user specific needs data are integrated to achieve truly personalized design from the two dimensions of "shape adaptation" and "functional response".

[0027] By dividing the sole of the foot into multiple functional sub-regions with set target mechanical parameters, the insole can make differentiated structural responses to the pressure characteristics and biomechanical needs of different regions, which greatly improves the fit and performance of the footwear.

[0028] Based on an interpolation mechanism using infill type, non-transitional and transitional regions are distinguished, and corresponding infill interpolation data are calculated to construct a non-uniform infill structure model with gradually changing mechanical properties. This achieves seamless integration between different infill types, avoids the structural discontinuity problem in traditional modular design, and improves the success rate of 3D printing and product durability. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This diagram illustrates an application environment for the personalized insole generation method according to an embodiment of this application.

[0031] Figure 2 This paper illustrates a flowchart of a personalized insole generation method according to an embodiment of this application.

[0032] Figure 3 A schematic diagram of a personalized insole generation device according to an embodiment of this application is shown. Detailed Implementation

[0033] The technical solutions in 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.

[0034] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0035] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0036] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0037] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0038] The following examples illustrate the method for generating personalized insoles.

[0039] The personalized insole generation method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 generates a personalized insole generation request and sends it to server 104, enabling server 104 to perform Boolean operations on the filling structure model and the 3D foot model to generate a 3D-printable personalized insole model. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, vehicle diagnostic equipment, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection equipment, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0040] Figure 2 A flowchart illustrating a personalized insole generation method according to an embodiment of this application is shown. Exemplarily, the personalized insole generation method includes the following steps:

[0041] Step S202: Based on the plantar stress distribution data and user demand data, the plantar region of the three-dimensional foot model is divided into sub-regions with set target mechanical parameters.

[0042] Among them, plantar stress distribution data refers to the pressure intensity and spatial distribution information of various parts of the sole of the foot collected by pressure sensing devices (such as plantar pressure plates, embedded pressure sensing insoles, etc.) under static (such as standing) or dynamic (such as walking, running, and other exercise states) conditions. This plantar stress distribution data can be represented as a two-dimensional or three-dimensional pressure cloud map, containing the vertical stress value at each coordinate point (x, y), used to identify high-stress areas (such as heel and forefoot), low-stress areas, and areas of localized pressure concentration risk.

[0043] User demand data refers to a set of information reflecting the target user's purpose for using insoles, functional preferences, or specific health conditions, including but not limited to: daily comfort needs, improvement of athletic performance (such as cushioning and rebound), correction of gait abnormalities (such as pigeon toes and toeing), chronic disease management (such as prevention of diabetic foot ulcers and rehabilitation of plantar fasciitis), and foot structural abnormalities (such as flat feet and high arches).

[0044] A three-dimensional foot model is a digital model that accurately represents the external geometry of a target user's foot, obtained through a 3D scanner, photogrammetry, or other digital modeling methods. This 3D foot model includes spatial information such as the foot's outline, arch height, foot length, foot width, and surface topology. It serves as the basic geometric basis for subsequent region division, lattice structure embedding, and Boolean operations, ensuring that the generated insoles perfectly conform to the individual's foot shape.

[0045] The plantar area refers to the bottom surface area in a three-dimensional foot model that is in contact with the ground and bears mechanical force. It corresponds to the functional division of the human foot's anatomical structure and mainly includes: the heel area, the arch area, and the forefoot area, which can be further subdivided into the first to fifth metatarsal bone areas and the phalangeal bone areas.

[0046] Target mechanical parameters refer to ideal physical performance indicators pre-set in a specific sub-region to meet specific biomechanical functions, including but not limited to: compressive stiffness (or equivalent elastic modulus), buffer coefficient (energy absorption rate), resilience, fatigue resistance, and stress dispersion capability. These target mechanical parameters are determined comprehensively based on plantar stress distribution data and user requirement data.

[0047] For example, the goal is to set "low stiffness and high cushioning" in high-impact areas, "high stiffness" in the arch area that needs support, and "local high stiffness" in high-risk areas of diabetic foot to distribute pressure.

[0048] A sub-region refers to dividing the sole of the foot into multiple functional units with independent target mechanical parameters based on the characteristics of sole stress distribution and user needs. Each sub-region corresponds to one or more local areas that need to achieve specific mechanical behaviors, such as "high cushioning heel area", "strong support arch area", and "gradient transition lateral edge area".

[0049] Specifically, the first step is to acquire two types of input data from the target user: a three-dimensional foot model and plantar stress distribution data, wherein:

[0050] 3D foot model: The target user's bare feet are scanned from all angles using an optical 3D scanner to reconstruct the geometric shape of the user's foot's outer contour and obtain a triangular mesh model that includes anatomical details such as the curvature of the sole, the height of the arch, and the arrangement of the toes.

[0051] Plantar stress distribution data: Dynamic pressure maps of the target user during natural walking and jogging were collected using a plantar pressure plate system. The plantar pressure plate system outputs a pressure value matrix per square centimeter, forming a spatially continuous pressure distribution map. The sampling frequency is no less than 100Hz to ensure the capture of peak pressure points in the gait cycle.

[0052] At the same time, user demand data is obtained. For example, user A is a long-distance runner whose demand is to "improve the cushioning performance of sports and reduce joint impact"; user B is a diabetic patient with peripheral neuropathy, and is clinically diagnosed with a high risk of subtotal ulceration of the forefoot and metatarsal heads, whose demand is to "prevent local high pressure and redistribute plantar pressure".

[0053] Secondly, based on human foot anatomy standards, the sole region of the 3D foot model is automatically divided into five basic functional zones: the heel zone corresponds to the calcaneal projection area, bearing the main impact force in the initial stage of landing; the medial longitudinal arch zone supports the arch structure and affects the stability of inversion / eversion; the lateral longitudinal arch zone assists in support and balance control; the forefoot zone includes the area below the first to fifth metatarsal heads, bearing peak pressure during propulsion; and the phalangeal zone participates in the final push-off movement. Optionally, this partitioning can be automated by mapping standard foot anatomy atlases onto the individualized 3D model using image registration algorithms (such as non-rigid registration based on template matching).

[0054] Next, by combining the collected plantar stress distribution data and user demand data, the above-mentioned basic functional areas are refined and functionally labeled to form sub-regions with specific target mechanical parameters.

[0055] For example, regarding user A's need for cushioning during exercise, analysis of dynamic pressure maps revealed that during running, the peak pressure in the heel area reached 850 kPa, while the first and fifth metatarsal areas experienced localized high pressures of 720 kPa and 680 kPa, respectively. Combined with the user's requirement for "enhanced cushioning," the following target biomechanical parameters were set:

[0056] For the heel area, a sub-region of "high energy absorption, low compressive stiffness" is defined (target elastic modulus: 0.5–1.0 MPa). For the first / fifth metatarsal area, a sub-region of "high cushioning" is also defined, but with moderate rebound characteristics (target rebound rate >60%). For the medial longitudinal arch area, the pressure is low (<150 kPa), but gait stability needs to be maintained, so a sub-region of "medium-high stiffness support" is defined (target modulus: 2.5–3.0 MPa). For the lateral longitudinal arch area and phalangeal area, moderate cushioning is combined with flexibility (target modulus: 1.2–1.8 MPa). Thus, the original plantar area is divided into five functional sub-regions, each of which is bound to one or more sets of quantifiable target mechanical parameters.

[0057] For example, regarding user B's need for pressure management of diabetic foot, stress data shows that the pressure under the second and third metatarsal heads is abnormally concentrated, with a peak value of 910 kPa, which exceeds the safety threshold (generally, >800 kPa is considered to indicate a risk of ulceration); medical needs indicate that continuous pressure on soft tissues must be avoided to prevent ulceration.

[0058] For the high-pressure areas of the second and third metatarsals, instead of soft structures, they are designed as "high-rigidity platform type" sub-regions (target modulus: 3.5 MPa) to become rigid support points and actively disperse surrounding pressure. For surrounding areas (such as the first, fourth, and fifth metatarsal areas), they are designed as "medium-rigidity transition type" sub-regions (target modulus: 1.5–2.0 MPa) to achieve a smooth transfer of pressure. Normal support is maintained for the arch area (target modulus: 2.0 MPa). For the heel area, due to the degeneration of the fat pad, a certain amount of cushioning capacity is still retained (target modulus: 0.8 MPa).

[0059] Finally, a spatially labeled digital plantar model is output, where each sub-region is associated with the following information: geometric coordinate range (3D mesh index); anatomical name and functional label; the set of target mechanical parameters to be achieved (such as compressive modulus, Poisson's ratio, energy absorption rate, etc.); and the corresponding application scenario identifier (such as cushioning, support, pressure shielding). Understandably, this output serves as the input basis for the subsequent step of "matching the optimal structure from the filling database," achieving a closed-loop transformation from physiological data to engineering design parameters.

[0060] Through the above embodiments, the sub-region division method proposed in this application not only relies on objectively measured plantar stress distribution data, but also deeply integrates subjective or clinical user demand data, enabling functional zoning to transcend simple geometric division and possess clear biomechanical significance and medical orientation. This significantly improves the scientific rigor, precision, and practicality of insole design.

[0061] Step S204: For each sub-region, search the infill database for an infill material that matches the target mechanical parameters of the sub-region.

[0062] The filler refers to a functional three-dimensional porous material structural unit used to constitute the internal structure of personalized insoles. It is not limited to traditional homogeneous foam materials, but refers to a spatially configured entity with adjustable mechanical properties that can be precisely formed through additive manufacturing processes. In this application, the filler refers to a lattice, including but not limited to: TPMS (Triple Periodic Minimal Surface Lattices) lattices and rod-shaped lattices.

[0063] TPMS-type lattices are mathematically defined surfaces with highly continuous and smooth surfaces, having an average curvature of zero, and repeating periodically in three directions in three-dimensional space. When used as solid structures, TPMS-type lattices can form boundaryless, highly interconnected shell or hollow channel structures.

[0064] A rod-shaped lattice is a porous structure composed of slender rods periodically connected in three-dimensional space. These rods are usually straight or slightly curved and are interconnected by nodes to form classic topological configurations such as body-centered cubic, face-centered cubic, and diamond.

[0065] A filler database is a pre-built structure-performance mapping knowledge base stored in a computer system to support the technical decision-making process of automatically matching the optimal filler based on target mechanical parameters. This filler database must contain at least the following key data items: filler type identifier (a unique code identifying each filler structure), geometric configuration information (PMS-like lattices and rod-shaped lattices), mechanical property data (static compressive modulus, unit: MPa), dynamic impact energy absorption efficiency (%), springback coefficient, and stress relaxation rate.

[0066] Specifically, once the target mechanical parameters for a certain sub-region have been set, the system initiates the matching process, which includes the following steps:

[0067] Input the target parameter vector. For example, a sub-region is set as "high-buffered heel area", with the following targets: compressive modulus: 0.9–1.3 MPa; energy absorption efficiency >70%; resilience >60%; printing material is limited to flexible TPU. The database is initially screened, first filtering out all filler entries that meet the material conditions and whose compressive modulus falls within the range of [0.9, 1.3] MPa.

[0068] Multi-attribute similarity calculation assigns different weight coefficients to the remaining candidates (i.e., the fillers that have passed the initial screening) for compressive modulus, energy absorption efficiency, and rebound rate. A weighted Euclidean distance method is then used to calculate the deviation between the remaining candidates and the target requirement. Finally, the optimal matching result is output, and the filler corresponding to the smallest Euclidean distance is selected as the recommended filler.

[0069] In the above embodiments, different foot regions have different biomechanical requirements (such as the heel needing cushioning and the arch needing support). This application ensures that each sub-region is assigned the structural type that best matches its functional positioning by matching the target stiffness, energy absorption and other parameters with the filling performance in the database, which significantly improves the practicality of the insole in terms of shock absorption, support and pressure redistribution.

[0070] Step S206: Based on the type of infill, determine the infill interpolation data for the transition and non-transition regions in each sub-region, and construct the infill structure model based on the infill interpolation data.

[0071] The type of insulator refers to the functional three-dimensional porous structural unit used to constitute the internal support / cushioning structure of the insole. This includes, but is not limited to: periodic lattice structures (such as octahedrons and tetrahedrons), triple periodic minimal surface (TPMS) structures, rod-shaped lattices, shell-shaped lattices, or other topological structures with adjustable mechanical properties. Each type of insulator has a specific geometric configuration and implicit or explicit modeling method, and its stiffness, cushioning, energy absorption, and other mechanical properties can be continuously varied by adjusting parameters (such as unit size, rod diameter, wall thickness, relative density, etc.). The selection of the insulator type directly affects the functional characteristics of the support or cushioning it provides.

[0072] A transition region is an intermediate area set between two adjacent sub-regions to achieve a smooth transition between regions with different mechanical properties. The structural parameters or type of the infill material in the transition region changes continuously and gradually through interpolation methods to avoid stress concentration and mechanical discontinuity. The transition region is located at the boundary between high-stiffness and low-stiffness regions (such as between the arch and forefoot regions), and its geometric distribution is determined by the boundary of the target sub-region, exhibiting a gradient characteristic in space.

[0073] Non-transition areas refer to the core functional areas of the foot's plantar functional zones that do not require structural interpolation processing. These areas are filled directly using a single matching infill type and its fixed or preset parameters. Examples include the heel high-pressure buffer zone and the arch support zone. In non-transition areas, the infill maintains relatively consistent structural characteristics and mechanical response, and these are the main parts with the most clearly defined functional requirements.

[0074] Infill interpolation data refers to intermediate numerical information used to control the continuous transition of infill materials in space. The form of infill interpolation data depends on the type of infill material. For infill materials with implicit function expressions (such as TPMS), the interpolation data is a weighted fusion of implicit function values ​​at each spatial coordinate point; for rod-shaped infill materials, the infill interpolation data is a spatially weighted combination of geometric structural parameters (such as rod diameter, element size, and wall thickness). Understandably, infill interpolation data ensures that the mechanical properties evolve continuously and without abrupt changes when transitioning from one type of infill material to another.

[0075] The insulator structure model refers to a complete three-dimensional digital model of the internal structure generated based on insulator interpolation data. It represents the spatial distribution, type configuration, and parameter gradation of the insulator in all non-transitional and transitional regions within the insole. Optionally, the insulator structure model is obtained by extracting the isosurface of implicit functions or solidifying rod / shell-shaped geometric elements, ultimately forming a printable three-dimensional mesh structure that can be used for Boolean operations and combined with the external foot contour.

[0076] In one embodiment, each sub-region is divided into a transition region and a non-transition region; the target sub-region to which the non-transition region belongs, and the target filler that matches the target sub-region are determined; based on the type of the target filler, the filler interpolation data of the non-transition region is determined; within the transition region, the filler interpolation data of the non-transition region is interpolated to obtain the filler interpolation data of the transition region.

[0077] In one example, the target filler type is a TPMS-type lattice with implicit functions. The filler interpolation data for the non-transition region includes the first implicit function to the Nth implicit function (e.g., the first implicit function, the second implicit function) and the transition implicit interpolation function.

[0078] The methods for determining the first implicit function to the Nth implicit function (e.g., the first implicit function, the second implicit function) include:

[0079] Obtain the implicit functions (first implicit function to Nth implicit function) of multiple padding types (first padding type to Nth padding type) in the plantar region. The function value of the implicit function represents the coordinate point in the non-transition region at one end of the transition region. Understandably, the padding types are not limited to two types.

[0080] For example, obtain a first implicit function of the first padding type in the plantar region, the function value of the first implicit function representing the coordinate point in the non-transition region at one end of the transition region; obtain a second implicit function of the second padding type in the plantar region, the function value of the second implicit function representing the coordinate point in the non-transition region at the other end of the transition region.

[0081] The first type of filler refers to the filler structure type used in the non-transition region corresponding to one end of the transition region (starting side) in two adjacent target sub-regions, such as filler A with implicit functions.

[0082] The second filler type refers to the filler structure type used in the non-transition region corresponding to the other end (termination side) of the transition region between two adjacent target sub-regions, such as filler B with implicit functions. Understandably, the topology of the second filler type differs from that of the first filler type.

[0083] Understandably, the two ends of the transition region belong to the non-transition region. One end is described by the non-transition region at one end of the transition region, and the other end is described by the non-transition region at the other end of the transition region. One end of the transition region does not include the transition region itself, and similarly, the other end of the transition region does not include the transition region itself.

[0084] The first implicit function, denoted as fA(x, y, z), is a scalar function expression used for mathematical modeling of the three-dimensional structure of the first infill type. The zero isosurface of the first implicit function, fA(x, y, z) = 0, defines the surface geometry of the first infill type. The function values ​​of the first implicit function are continuously distributed in space and can be used for subsequent weighted fusion to generate transitional structures.

[0085] The second implicit function, denoted as fB(x, y, z), is a scalar function expression used for mathematical modeling of the 3D structure of the second infill type. The zero isosurface of the second implicit function, fB(x, y, z) = 0, defines the surface geometry of the second infill type. The function values ​​of the second implicit function are continuously distributed in space and can be used for subsequent weighted fusion to generate transition structures.

[0086] The methods for determining the implicit interpolation function include:

[0087] Based on the position of each coordinate point in the transition region, a continuously changing weight parameter is assigned to each coordinate point. The weight parameter increases in the direction from the first fill type to the Nth fill type. Based on the weight parameter, the function values ​​of the first implicit function to the Nth implicit function corresponding to each coordinate point are weighted and fused to obtain the transition implicit interpolation function of the transition region.

[0088] For example, based on the position of each coordinate point in the transition region, a continuously changing weight parameter is assigned to each coordinate point, and the weight parameter increases in the direction from the first filling type to the second filling type; based on the weight parameter, the function values ​​of the first implicit function and the second implicit function corresponding to each coordinate point are weighted and fused to obtain the transition implicit interpolation function of the transition region.

[0089] The weight parameter refers to a spatially related continuous variable introduced in the transition region between two adjacent non-transition regions to achieve a smooth evolution from one filling structure to another. The value range of the weight parameter is [0, 1].

[0090] Understandably, the weighting parameter monotonically increases along the spatial direction from the first infill type to the Nth infill type: near the boundary of the first infill type, the weighting parameter is 0; near the boundary of the Nth infill type, the weighting parameter is 1; in the intermediate region, the weighting parameter is determined by linear or nonlinear interpolation based on the coordinate position (such as distance weighting, gradient distribution, etc.). The role of the weighting parameter is to serve as a coefficient in the weighted fusion operation, controlling the contribution ratio of two different structural features (such as implicit function values ​​or geometric parameters) at various points in space, thereby generating a transitional lattice structure with continuously changing mechanical properties, avoiding stress concentration and structural abrupt changes.

[0091] The transition implicit interpolation function refers to a new implicit scalar function, denoted as fT(x, y, z), obtained by weighting and fusing the first to the Nth implicit function (e.g., when N=2, it represents the second implicit function, where N is an integer greater than or equal to 1) according to weight parameters. The isosurface of fT(x, y, z) = 0 constitutes a new three-dimensional lattice surface within the transition region. Understandably, the structure generated by this transition implicit interpolation function is neither entirely fA nor entirely fB, but rather an intermediate structure exhibiting continuous and gradual changes in topology, porosity, and stiffness. This effectively achieves seamless geometric and mechanical integration between two types of TPMS or other implicit structures.

[0092] Optionally, based on the plantar pressure distribution σ(x, y), the insole plane can be divided into regions with different mechanical requirements. High-pressure regions are assigned lattice type A, low-pressure regions are assigned lattice type B, and the region in between is defined as the transition region T. (This is not limited to two lattice types; it depends on the target mechanical performance requirements of the region).

[0093] A “mixed transition layer” is generated at the boundary region where lattice type A is assigned in the high-pressure region and lattice type B is assigned in the low-pressure region, using the interpolation formula f(x) = (1-α)fA + αfB, where α varies smoothly with position.

[0094] For lattices with implicit functions, let fA(x, y, z) be the implicit function for lattice type A and fB(x, y, z) be the implicit function for lattice type B. In the transition region, linear interpolation is used to construct the implicit functions of the transition lattice:

[0095] fT(x, y, z) = (1 -α) ×fA +α×fB;

[0096] Among them, when α = 0, the structure is completely A; when α = 1, the structure is completely B; and the rest are smooth fusion structures.

[0097] In another example, the target filler is a rod-shaped structure, i.e., a rod-shaped lattice; the filler interpolation data for the non-transition region includes the first geometric parameter to the Nth geometric parameter (e.g., the first geometric parameter, the second geometric parameter) and the transition geometric parameter.

[0098] The determination methods for the first geometric parameter to the Nth geometric parameter (for example, N=1 represents the first geometric parameter, N=2 represents the second geometric parameter, and N is an integer greater than or equal to 1) include:

[0099] Determine the geometric parameters of various padding types in the plantar region. These geometric parameters characterize coordinate points in the non-transitional region at one end of the transition area. For example, determine the first geometric parameter of the third padding type in the plantar region, which characterizes the coordinate points in the non-transitional region at one end of the transition area; and determine the second geometric parameter of the fourth padding type in the plantar region, which characterizes the coordinate points in the non-transitional region at the other end of the transition area.

[0100] The third type of filler refers to the rod-shaped structure filler used in the non-transition region at one end of the transition region set between target sub-regions, such as rod-shaped structure filler A.

[0101] The fourth type of filler refers to another type of rod-shaped filler used in the non-transition region at the other end of the transition region set between target sub-regions, such as rod-shaped filler B.

[0102] The first geometric parameter refers to a key adjustable geometric variable used to characterize the mechanical behavior of a third type of infill material in space. Its value directly affects the infill material's equivalent modulus, energy absorption efficiency, compression resilience, and other properties. Common first geometric parameters include, but are not limited to: rod diameter, unit cell size, relative density, porosity, and lattice tilt angle.

[0103] The second geometric parameter refers to the key adjustable geometric variable used to characterize the mechanical behavior of the fourth type of infill in space. Its form is the same as the first geometric parameter (such as rod diameter or unit size), but the values ​​are different, reflecting the differences in mechanical function between the two structures.

[0104] The methods for determining the implicit interpolation function include:

[0105] Based on the position of each coordinate point in the transition region, a continuously changing weight parameter is assigned to each coordinate point. The weight parameter increases in the direction from the third fill type to the Nth fill type (such as the fourth fill type). Based on the weight parameter, the first to Nth geometric parameters corresponding to each coordinate point (such as the first geometric parameter when N=1 and the second geometric parameter when N=2, where N is an integer greater than or equal to 1) are weighted and fused to obtain the transition geometric parameters of the transition region.

[0106] For example, based on the position of each coordinate point in the transition region, a continuously changing weight parameter is assigned to each coordinate point, and the weight parameter increases in the direction from the third fill type to the fourth fill type; based on the weight parameter, the first geometric parameter and the second geometric parameter corresponding to each coordinate point are weighted and fused to obtain the transition geometric parameter of the transition region.

[0107] Optionally, for rod-shaped lattices, the geometric parameters are interpolated. Let the geometric parameters of lattice A be pA (such as relative density, rod diameter, unit cell size, etc.), and the geometric parameters of lattice B be pB, then the transition geometric parameters are:

[0108] pT(x,y,z) = (1-α)×pA +α×pB.

[0109] In one embodiment, the first implicit function, the second implicit function, and the transition implicit interpolation function are numerically solved to obtain the function values ​​of each grid node in the plantar region; based on the preset threshold and function values, isosurfaces are extracted from each grid node in the plantar region, and the extracted isosurfaces are converted into a filling structure model.

[0110] In this context, a grid node refers to the set of basic spatial coordinate points in the numerical computation grid established during the three-dimensional spatial discretization of the foot region. This grid is used to represent the function values ​​of implicit functions (such as the first implicit function, the second implicit function, or the transitional implicit interpolation function). This grid is typically a regularly distributed voxel grid or a finite element grid, and its spatial resolution is determined by the design accuracy requirements (e.g., one node per millimeter).

[0111] Each grid node has explicit spatial coordinates (xi, yj, zk), which are used in the numerical solution process to calculate the scalar field function value f(x, y, z) at the corresponding location, thus providing a data basis for subsequent extraction of the geometric structure.

[0112] The preset threshold, denoted as T, is the critical value of the scalar field function used when extracting the solid / void boundary defined by the implicit function. It is used to determine whether a point belongs to the filling material region. Optionally, for a standardized implicit function system, this preset threshold is often set to 0, that is, when f(x, y, z) = 0, it represents the structural surface; however, in some normalized or offset functions, a non-zero threshold may also be set (such as within ±ε).

[0113] An isosurface is a continuous surface in a three-dimensional scalar field (such as the sole of the foot) where all function values ​​equal a preset threshold T. By extracting isosurfaces, the function values ​​calculated on discretized mesh nodes are transformed into a three-dimensional geometric model in the form of a triangular mesh, which can then be used for subsequent modeling and manufacturing.

[0114] The filling structure model refers to a complete three-dimensional digital geometric model representing the non-uniform porous filling structure inside the insole, generated based on the above isosurface extraction results. It includes the following features: spatially divided into multiple sub-regions, each region using different filling types; gradient transition zones between adjacent regions obtained through implicit function fusion or geometric parameter interpolation; the overall structure has a continuously varying mechanical property distribution to meet personalized support and cushioning needs; and the model format is a standard format that can be recognized by 3D printing equipment.

[0115] Specifically, the entire sole area is discretized into a three-dimensional regular mesh, which includes mesh nodes. At each mesh node, the function values ​​fA, fB, and fT are calculated, and a preset threshold T=0 is set; that is, when the function value is equal to zero, it is considered a material surface. All network elements are traversed to identify all coordinate points that satisfy fA=0, fB=0, and fT=0, generating a closed three-dimensional surface, which is the infill structure model.

[0116] Step S208: Perform Boolean operations on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0117] The aforementioned filling structure model and the user's foot shape model are subjected to a Boolean union operation to obtain a complete 3D model of the insole with an outer contour that conforms to the foot shape and an internal structure optimized according to stress distribution. Optionally, the model can be exported as a 3MF file and sent to a 3D printing device for 3D printing. The final insole achieves a seamless transition from a soft cushioning structure to a rigid support structure in key areas, with uniform stress transfer and no local stress concentration.

[0118] Through the above embodiments, differentiated lattice types are allocated according to the actual pressure requirements of different foot regions, and the wall thickness and porosity are precisely controlled through isosurfaces. This enables high-stress areas to possess excellent energy absorption capabilities, while low-stress support areas maintain structural stability. This reduces user fatigue and significantly improves impact upon landing.

[0119] Figure 3 A schematic diagram of a personalized insole generation apparatus according to an embodiment of this application is shown. Exemplarily, the personalized insole generation apparatus 300 includes:

[0120] The segmentation module 302 is used to segment the plantar region of the three-dimensional foot model into sub-regions with set target mechanical parameters based on plantar stress distribution data and user demand data.

[0121] The lookup module 304 is used to search the filler database for each sub-region and find the filler that matches the target mechanical parameters of the sub-region.

[0122] Module 306 is used to determine the interpolation data of the infill in the transition and non-transition regions of each sub-region based on the type of infill, and to construct the infill structure model based on the infill interpolation data;

[0123] The generation module 308 is used to perform Boolean operations on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

[0124] It is understood that the device in this embodiment corresponds to the personalized insole generation method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0125] This application also provides a terminal device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the terminal device to perform the functions of the various modules in the above-described personalized insole generation method or the above-described personalized insole generation device.

[0126] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0127] Memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM). Memory is used to store computer programs, and the processor can execute these programs upon receiving execution instructions.

[0128] This application also provides a computer-readable storage medium for storing computer programs used in the aforementioned terminal devices. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0130] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0131] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.

[0132] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for generating personalized insoles, characterized in that, include: Based on plantar stress distribution data and user demand data, the plantar region of the three-dimensional foot model is divided into sub-regions with set target mechanical parameters; For each of the aforementioned sub-regions, a filler that matches the target mechanical parameters of the sub-region is searched from the filler database; Each of the sub-regions is divided into transition regions and non-transition regions; the target sub-region to which the non-transition region belongs, and the target filler that matches the target sub-region are determined; based on the type of the target filler, the filler interpolation data of the non-transition region is determined; within the transition region, the filler interpolation data of the non-transition region is interpolated to obtain the filler interpolation data of the transition region, and based on the filler interpolation data, a filler structure model is constructed. Boolean operations are performed on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

2. The method according to claim 1, characterized in that, The target filler type is a target filler with an implicit function; The step of determining the filler interpolation data for the non-transition region based on the type of the target filler includes: Obtain a first implicit function for the first filling type in the plantar region, wherein the function value of the first implicit function represents the coordinate point in the non-transition region at one end of the transition region; Obtain a second implicit function for the second filling type in the plantar region, the function value of the second implicit function representing the coordinate point in the non-transition region at the other end of the transition region.

3. The method according to claim 2, characterized in that, The process of interpolating the filler interpolation data of the non-transition region within the transition region to obtain the filler interpolation data of the transition region includes: Based on the position of each coordinate point in the transition region, each coordinate point is assigned a continuously changing weight parameter, which increases in the direction from the first filler type to the second filler type. Based on the weight parameters, the function values ​​of the first implicit function and the second implicit function corresponding to each coordinate point are weighted and fused to obtain the transition implicit interpolation function of the transition region.

4. The method according to claim 1, characterized in that, The target filler is a rod-shaped target filler; The step of determining the filler interpolation data for the non-transition region based on the type of the target filler includes: Determine a first geometric parameter for the third type of filler in the plantar region, the first geometric parameter representing a coordinate point in the non-transition region at one end of the transition region; A second geometric parameter is determined for the fourth filling type in the plantar region, the second geometric parameter representing the coordinate point in the non-transition region at the other end of the transition region.

5. The method according to claim 4, characterized in that, The process of interpolating the filler interpolation data of the non-transition region within the transition region to obtain the filler interpolation data of the transition region includes: Based on the position of each coordinate point in the transition region, each coordinate point is assigned a continuously changing weight parameter, which increases in the direction from the third filler type to the fourth filler type. Based on the weight parameters, the first geometric parameters and the second geometric parameters corresponding to each coordinate point are weighted and fused to obtain the transition geometric parameters of the transition region.

6. The method according to claim 3, characterized in that, The step of constructing a filler structure model based on the filler interpolation data includes: Numerical solutions are performed on the first implicit function, the second implicit function, and the transition implicit interpolation function to obtain the function values ​​of each grid node in the plantar region. Based on a preset threshold and the function value, isosurfaces are extracted from each grid node in the foot region, and the extracted isosurfaces are converted into a filling structure model.

7. A personalized insole generating device, characterized in that, include: The segmentation module is used to segment the plantar region of the 3D foot model into sub-regions with set target mechanical parameters based on plantar stress distribution data and user demand data. The search module is used to search the filler database for each of the sub-regions for fillers that match the target mechanical parameters of the sub-region. A construction module is used to divide each of the sub-regions into transition regions and non-transition regions; determine the target sub-region to which the non-transition region belongs, and the target filler that matches the target sub-region; determine the filler interpolation data of the non-transition region based on the type of the target filler; perform interpolation processing on the filler interpolation data of the non-transition region within the transition region to obtain the filler interpolation data of the transition region, and construct a filler structure model based on the filler interpolation data; The generation module is used to perform Boolean operations on the filling structure model and the three-dimensional foot model to generate a personalized insole model that can be 3D printed.

8. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the personalized insole generation method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed on a processor, implements the personalized insole generation method according to any one of claims 1-6.

Images