Intelligent dynamic adaptive 3D printing orthopedic insole system and preparation method

Abstract

The invention provides an intelligent dynamic adaptive 3D printing orthopedic insole system and a preparation method, and relates to the technical field of orthopedic insoles, the intelligent dynamic adaptive 3D printing orthopedic insole system comprises an insole body, an intelligent sensor module, a transmission analysis module and a regulation and control module, the insole body is of a multi-layer dynamic structure, the intelligent sensor module is embedded in the insole body, and the transmission analysis module is connected with the regulation and control module. The transmission and analysis module is used for monitoring foot pressure distribution, gait parameters and foot posture change data of a user in real time, and the transmission and analysis module is arranged in the insole body and wirelessly transmits the data to a user intelligent terminal application program for analysis and recognition through the Bluetooth technology; through monitoring, remote analysis and regulation and control of the intelligent sensor module, real-time dynamic adjustment of the functions of the orthopedic insole is achieved, the orthopedic insole adapts to the progress of the activity state, the health condition change and the correction requirement of a user, intelligent sensing, real-time monitoring, cloud data analysis, real-time regulation and control and a multi-layer dynamic structure are integrated, and the practicability is high. And an omnibearing and intelligent foot health management solution is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of orthopedic insoles, and in particular to an intelligent dynamic adaptive 3D printing orthopedic insole system and a preparation method thereof. Background Art

[0002] The existing 3D printed orthopedic insole technologies on the market mainly focus on personalized customization, and are precisely made according to the user's foot scan data to provide better support and alleviate specific foot problems. However, these technologies often lack dynamic adjustment capabilities. Once printed, their shape is fixed and cannot be adjusted in time according to the user's actual foot changes or gait feedback during use. This is specifically manifested in the following aspects:

[0003] Traditional orthotic insoles cannot be adjusted in real time according to the actual needs of users in daily activities and changes in foot conditions, resulting in limited orthotic effects or insufficient comfort;

[0004] Traditional orthopedic insoles mainly rely on hand-made or semi-customized methods based on preset molds, which are difficult to accurately match the complex anatomical characteristics and pathological changes of individual feet, and the orthopedic effect is limited;

[0005] Traditional orthotic insoles are usually designed based on static foot measurements or one-time scanning data, and cannot adapt to dynamic changes in the wearer's foot during walking, such as arch collapse and heel inversion, which affects the correction effect;

[0006] Once manufactured, the shape and function of traditional orthopedic insoles are difficult to adjust in real time. If the correction needs change or the correction effect is not ideal, they often need to be remade, which is costly and time-consuming.

[0007] Therefore, the present invention proposes an intelligent dynamic adaptive 3D printing orthopedic insole system and a preparation method to solve the problems existing in the prior art. Summary of the invention

[0008] In response to the above problems, the present invention proposes an intelligent dynamic adaptive 3D printed orthopedic insole system and preparation method. The intelligent dynamic adaptive 3D printed orthopedic insole system and preparation method realize real-time dynamic adjustment of the orthopedic insole function through intelligent sensor module monitoring, remote analysis and regulation, adapting to the user's activity status, changes in health status and progress in correction needs, integrating intelligent sensing, real-time monitoring, cloud data analysis, real-time regulation and multi-layer dynamic structure, and providing a comprehensive and intelligent foot health management solution.

[0009] To achieve the purpose of the present invention, the present invention is implemented through the following technical solutions: an intelligent dynamic adaptive 3D printing orthopedic insole system, including an insole body, an intelligent sensor module, a transmission analysis module, and a control module. The insole body is a multi-layer dynamic structure. The intelligent sensor module is embedded in the insole body and is used to monitor the user's foot pressure distribution, gait parameters, and foot posture change data in real time. The transmission analysis module is built into the insole body and wirelessly transmits data to the user's intelligent terminal application for analysis and identification through Bluetooth technology;

[0010] The user's smart terminal application remotely uploads data to the cloud server. The cloud server uses big data analysis technology to analyze the data, combines user information, forms an individualized database, combines medical advice to generate an individual's orthopedic strategy, and provides users with an online download channel. After downloading through the smart terminal application, it drives the control module. The control module is built into the insole body, and the control module adjusts the multi-layer dynamic structure of the insole body according to the orthopedic strategy.

[0011] Further improvements are: the multi-layer dynamic structure of the insole body includes a supporting structure layer, a buffer layer and a thermosensitive adaptive material layer; the supporting structure layer is a supporting structure with targeted corrective function printed according to the three-dimensional scanning data of the user's foot, including a corrective structure for specific pathological morphology; the buffer layer contains an inflatable or liquid-filled microcapsule structure, and the internal medium pressure is adjusted by remote commands to adapt to the shock absorption requirements and support strength in different activity scenarios; the thermosensitive adaptive material layer is a temperature-sensitive material body, which automatically adjusts the hardness as the body temperature changes to provide a corresponding fit.

[0012] Further improvements are: the intelligent sensor module includes a pressure sensor, an accelerometer, and a gyroscope; the transmission analysis module has a built-in machine learning algorithm to analyze data in real time and identify changes in user walking patterns, fatigue status, and orthopedic needs; the control module is combined with user information, including age, gender, weight, physical condition, and exercise habits.

[0013] A method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system comprises the following steps:

[0014] Use high-precision plantar 3D scanning equipment to obtain the user's foot morphology data, and combine it with gait analysis results to generate a personalized insole model;

[0015] Apply artificial intelligence algorithms to set the layout of the support structure layer, the distribution of the cushioning layer, and the functional layer parameters of the thermosensitive adaptive material layer according to the user's data and orthopedic goals;

[0016] Use multi-material 3D printing technology to print out the insole body including all functional layers at one time, and embed the intelligent sensor module, transmission analysis module, and control module during the printing process, calibrate and waterproof the insole;

[0017] Present the design plan to relevant experts in a 3D visualization way to obtain their professional opinions on the orthopedic effect, and at the same time obtain the user's subjective evaluation on comfort and aesthetics;

[0018] Incorporate the above feedback information into model training and continuously iterate the intelligent algorithm.

[0019] Further improvements are: Applying artificial intelligence algorithms using the following algorithm architecture:

[0020] Data input and preprocessing;

[0021] Core analysis of functional layer algorithms.

[0022] A further improvement is that the data input and preprocessing includes the following steps:

[0023] Collect user's individualized information, including biomechanical indicators, medical images, and description of orthopedic needs;

[0024] Perform quality checks on the collected data, remove outliers and redundant information, and convert all types of data into a unified format;

[0025] Features that are closely related to orthopedic insole design are extracted and used as inputs for intelligent algorithms.

[0026] A further improvement is that the core analysis of the functional layer algorithm includes the following steps:

[0027] Using the convolutional neural network (CNN) or graph neural network (GNN) model, the position, shape and material properties of the ideal support structure are predicted based on the user's gait data and joint torque distribution. The model accepts preprocessed biomechanical features as input and outputs design suggestions for the support structure layer. Combining expert knowledge and design constraints, the genetic algorithm or particle swarm optimization method is used to iteratively search for the optimal support structure layer layout. Each generation of design solutions is generated by the above deep learning model, and its performance is evaluated by the fitness function. The next generation of candidate solutions is generated based on selection, crossover and mutation.

[0028] Based on the user's gait data and pressure distribution characteristics, a reinforcement learning agent is trained, including the environment state, action space and reward function. The environment state includes the current buffer layer distribution and user gait feedback. The action space is to adjust the buffer layer thickness, material, and position parameters. The reward function reflects the buffer effect and user comfort. Combined with the strategy guidance of the reinforcement learning model, the simulated annealing algorithm is used to explore the global optimal solution of the buffer layer distribution.

[0029] Based on historical orthosis usage data and user-specific thermal environment conditions, a regression model is trained to predict the temperature distribution of the orthosis under different thermosensitive material parameters. In the predefined thermosensitive material parameter search space, the Bayesian optimization algorithm is used to find the optimal parameter combination that can keep the orthosis temperature in a comfortable range. The true objective function is approximated by constructing a proxy model, and an efficient search is performed based on the uncertainty-guided sampling strategy to determine the parameters of the thermosensitive adaptive material layer.

[0030] Further improvements are: using 3D printed support structure layer: printing support structure with targeted corrective function according to the three-dimensional scanning data of the foot, including corrective elements of specific pathological morphology, selecting materials according to the required support force, and making them through 3D printing process, based on the following principles to control the relationship between material hardness and support strength: the higher the hardness of the material, the stronger its ability to resist deformation, and the greater the support provided to the arch of the foot, F (support force) = k*(D1-D2)+D3, where k reflects the coefficient of the influence of hardness change on support strength, D1 is the hardness of the material used, D2 is the benchmark hardness, which refers to the minimum effective hardness required for the arch pad, and D3 is the basic support strength, which refers to the basic support that can be provided even at the benchmark hardness. According to user data and orthopedic goals, F is determined to select the appropriate printing material.

[0031] Further improvements are: a 3D printed buffer layer containing an inflatable microcapsule structure, the microcapsule structure is inflatable or can be filled with hydrogel. When inflatable microcapsules are selected, the gas is encapsulated in a closed space formed in one or more layers of polymer films. The microcapsules are manufactured by solvent dispersion, interfacial polymerization, and spray drying processes. The shell of the microcapsule is prepared with a high molecular polymer and filled with nitrogen. After the microcapsules are made, they are evenly distributed in the buffer layer material reserved for the insole body and embedded with a circuit to control inflation and deflation. When hydrogel is selected, a microcontroller is added to regulate the temperature of the gel by electric current to cause a phase change, thereby changing the hardness and shape of the material.

[0032] Further improvements include: using temperature-sensitive smart materials to prepare a thermosensitive adaptive material layer that automatically adjusts hardness as body temperature changes, including thermosensitive polymers, PORON polyurethane and graphene composite materials. The thermosensitive adaptive material layer adjusts by monitoring and responding to changes in foot temperature.

[0033] The beneficial effects of the present invention are:

[0034] 1. The present invention realizes real-time dynamic adjustment of the function of orthopedic insoles through intelligent sensor module monitoring, remote analysis and regulation, adapts to the user's activity status, changes in health status and progress in correction needs, integrates intelligent sensing, real-time monitoring, cloud data analysis, real-time regulation and multi-layer dynamic structure, and provides a comprehensive and intelligent foot health management solution.

[0035] 2. The present invention combines 3D scanning with algorithm-assisted design to provide highly personalized foot support and correction, effectively addressing various foot diseases and gait problems. Users can easily monitor the orthotic effect, receive doctor's advice and remotely adjust the insole settings through smart terminal applications, greatly improving user experience and treatment compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a front view of the present invention;

[0037] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0038] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0039] Embodiment 1

[0040] according to Figure 1 , 2 As shown, this embodiment proposes an intelligent dynamic adaptive 3D printed orthopedic insole system, including an insole body, an intelligent sensor module, a transmission analysis module, and a control module. The insole body is a multi-layer dynamic structure. The intelligent sensor module is embedded in the insole body and is used to monitor the user's foot pressure distribution, gait parameters, and foot posture change data in real time. The transmission analysis module is built into the insole body and wirelessly transmits the data to the user's smart terminal application for analysis and identification through Bluetooth technology;

[0041] The user's smart terminal application remotely uploads data to the cloud server. The cloud server uses big data analysis technology to analyze the data, combines user information, forms an individualized database, combines medical advice to generate an individual's orthopedic strategy, and provides users with an online download channel. After downloading through the smart terminal application, it drives the control module. The control module is built into the insole body, and the control module adjusts the multi-layer dynamic structure of the insole body according to the orthopedic strategy.

[0042] The multi-layer dynamic structure of the insole body includes a supporting structure layer, a buffer layer and a thermosensitive adaptive material layer. The supporting structure layer is a supporting structure with targeted correction function printed according to the three-dimensional scanning data of the user's foot, including a correction structure for specific pathological morphology. The buffer layer contains an inflatable or liquid-filled microcapsule structure, and the internal medium pressure is adjusted by remote commands to adapt to the shock absorption requirements and support strength in different activity scenarios. The thermosensitive adaptive material layer is a temperature-sensitive material body, which automatically adjusts the hardness as the body temperature changes to provide a corresponding fit.

[0043] The intelligent sensor module includes a pressure sensor, an accelerometer, and a gyroscope. The transmission analysis module has a built-in machine learning algorithm to analyze data in real time and identify changes in user walking patterns, fatigue status, and orthopedic needs. The control module combines user information including age, gender, weight, physical condition, and exercise habits.

[0044] A method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system comprises the following steps:

[0045] Use high-precision plantar 3D scanning equipment to obtain the user's foot morphology data, and combine it with gait analysis results to generate a personalized insole model;

[0046] Artificial intelligence algorithms are applied to set the layout of the support structure layer, the distribution of the buffer layer, and the functional layer parameters of the thermosensitive adaptive material layer according to user data and orthopedic goals; the artificial intelligence algorithm adopts the following algorithm architecture: data input and preprocessing; functional layer algorithm core analysis. The data input and preprocessing include the following steps: collecting individualized information of users, including biomechanical indicators, medical images, and orthopedic needs descriptions; performing quality checks on the collected data, removing outliers and redundant information, and converting various types of data into a unified format; extracting features that are closely related to orthopedic insole design, and using these features as inputs to the intelligent algorithm. The core analysis of the functional layer algorithm includes the following steps: using a convolutional neural network (CNN) or a graph neural network (GNN) model to predict the position, shape and material properties of an ideal support structure based on user gait data and joint torque distribution. The model accepts preprocessed biomechanical features as input and outputs design suggestions for the support structure layer. Combining expert knowledge and design constraints, a genetic algorithm or a particle swarm optimization method is used to iteratively search for the optimal support structure layer layout solution. Each generation of design solutions is generated by the above-mentioned deep learning model, and its performance is evaluated by a fitness function. The next generation of candidate solutions is generated based on selection, crossover and mutation. Based on user gait data and pressure distribution characteristics, a reinforcement learning agent is trained, including environmental state, action space and reward function. The environmental state includes the current buffer layer distribution and user gait feedback. The action space is to adjust the buffer layer thickness, material, and position parameters. The reward function reflects the buffer effect and user comfort. Combined with the strategy guidance of the reinforcement learning model, the simulated annealing algorithm is used to explore the global optimal solution for the buffer layer distribution. According to the historical orthosis usage data and the user's specific thermal environment conditions, a regression model is trained to predict the temperature distribution of the orthosis under different thermosensitive material parameters. In the predefined thermosensitive material parameter search space, the Bayesian optimization algorithm is used to find the best parameter combination that can keep the orthosis temperature in a comfortable range. The true objective function is approximated by constructing a proxy model, and an efficient search is performed based on the uncertainty-guided sampling strategy to determine the parameters of the thermosensitive adaptive material layer.

[0047] Use multi-material 3D printing technology to print out the insole body containing all functional layers at one time, and embed intelligent sensor modules, transmission analysis modules, and control modules during the printing process, calibrate and waterproof seal; use 3D printing support structure layer: according to the three-dimensional scanning data of the foot, print a support structure with targeted correction function, including correction elements for specific pathological morphology, select materials according to the required support force, and make it through 3D printing process. The relationship between material hardness and support strength is controlled based on the following principles: the higher the hardness of the material, the stronger its ability to resist deformation, and the greater the support strength provided to the arch of the foot. F (support force) = k*(D1-D2)+D3, where k reflects the coefficient of the influence of hardness change on support strength, D1 is the hardness of the material used, D2 is the baseline hardness, which refers to the minimum effective hardness required for the arch pad, and D3 is the basic support strength, which refers to the basic support that can be provided even at the baseline hardness. According to user data and orthopedic goals, determine F, Thus, a suitable printing material can be selected; a 3D printed buffer layer containing an inflatable microcapsule structure, the microcapsule structure is inflatable or can be filled with hydrogel. When an inflatable microcapsule is selected, the gas is encapsulated in a closed space formed in one or more polymer films. The microcapsules are manufactured by solvent dispersion, interfacial polymerization, and spray drying processes. The shell of the microcapsule is prepared by a high molecular polymer, and the inside is filled with nitrogen. After the microcapsules are made, they are evenly distributed in the buffer layer material reserved in the insole body, and a control inflation and deflation circuit is embedded. When hydrogel is selected, a microcontroller is added to regulate the temperature of the gel by electric current to cause a phase change, thereby changing the hardness and morphology of the material; a thermosensitive adaptive material layer is prepared using a temperature-sensitive intelligent material, which automatically adjusts the hardness as the body temperature changes, including thermosensitive polymers, PORON polyurethane, and graphene composite materials. The thermosensitive adaptive material layer is adjusted by monitoring and responding to changes in foot temperature;

[0048] Present the design plan to relevant experts in a 3D visualization way to obtain their professional opinions on the orthopedic effect, and at the same time obtain the user's subjective evaluation on comfort and aesthetics;

[0049] Incorporate the above feedback information into model training and continuously iterate the intelligent algorithm.

[0050] Embodiment 2

[0051] according to Figure 1 , 2 As shown, this embodiment proposes an intelligent dynamic adaptive 3D printing orthopedic insole system and preparation method, comprising the following steps:

[0052] Smart sensor module: Multiple groups of micro sensors are embedded inside the insole, including pressure sensors, accelerometers, gyroscopes, etc., which are used to monitor the user's foot pressure distribution, gait parameters (such as step length, step frequency, landing impact force, etc.), foot posture changes and other data in real time.

[0053] Transmission and Analysis Module: Sensor data is wirelessly transmitted to the user’s smartphone application via Bluetooth Low Energy technology. The application has built-in advanced machine learning algorithms that can analyze data in real time and identify changes in the user’s walking pattern, fatigue status, and orthopedic needs.

[0054] Transmission and analysis module: The mobile application uploads real-time data to the cloud server, which uses big data analysis technology to combine the user's age, gender, weight, physical condition (such as diabetes, arthritis, etc.), exercise habits and other basic information to form a comprehensive individualized database. Combined with the doctor's professional advice, it generates individual correction strategy updates.

[0055] Users can remotely receive and download these strategies and adjust the electronic module inside the insole through a mobile phone application to achieve dynamic adjustment of the orthotic function.

[0056] The insole adopts a multi-layer structure design, including: Support structure layer: According to the 3D scanning data of the foot, the support structure with targeted correction function is accurately printed, such as correction elements for specific pathological morphologies such as flat feet, high arches, inversion / extroversion, etc. Buffer layer: Contains an inflatable or liquid-filled microcapsule structure, and adjusts the internal medium pressure through remote commands to adapt to the shock absorption needs and support strength in different activity scenarios. Thermosensitive adaptive material layer: Using intelligent materials with temperature sensitivity, it automatically adjusts the hardness as the body temperature changes, providing all-weather comfortable fit.

[0057] Personalized foot scanning and modeling: Use high-precision plantar 3D scanning equipment to obtain the user's foot morphology data, combine it with gait analysis results, and generate a personalized insole model.

[0058] Intelligent algorithm-assisted design: Apply artificial intelligence algorithms to optimize support structure layout, buffer layer distribution, and thermosensitive material parameters based on user data and orthopedic goals. The following algorithm architecture is used:

[0059] Data input and preprocessing

[0060] User data collection: Collect users' individual information, including but not limited to biomechanical indicators (such as gait analysis data, range of joint motion, weight, height, gender, etc.), medical images (such as CT, MRI scan results), and orthopedic needs description (correction site, orthopedic goal, expected wearing time, etc.).

[0061] Data cleaning and standardization: Perform quality checks on the collected data, remove outliers and redundant information, and convert various types of data into a unified format to facilitate subsequent algorithm processing.

[0062] Feature engineering: Extract features that are closely related to orthotic insole design, such as arch height, which will serve as input for intelligent algorithms.

[0063] Intelligent algorithm core module

[0064] Support structure layer layout optimization submodule: Using models such as convolutional neural networks (CNN) or graph neural networks (GNN), the ideal support structure's position, shape, and material properties (such as stiffness, strength, etc.) are predicted based on user gait data and joint torque distribution. The model can accept preprocessed biomechanical features as input and output design recommendations for the support structure. Combining expert knowledge and design constraints (such as weight limits, comfort requirements), optimization methods such as genetic algorithms or particle swarm optimization are used to iteratively search for the optimal support structure layout solution. Each generation of design solutions is generated by the above-mentioned deep learning model, and its performance is evaluated by the fitness function. The next generation of candidate solutions is generated based on operations such as selection, crossover, and mutation.

[0065] Buffer layer distribution optimization submodule: Reinforcement learning model: Based on the user gait data and pressure distribution characteristics, a reinforcement learning agent (such as DQN, PPO, etc.) is trained. The environmental state includes the current buffer layer distribution and user gait feedback. The action space is to adjust the buffer layer thickness, material, position and other parameters. The reward function reflects the buffer effect (such as pressure balance, impact absorption capacity) and user comfort. Combined with the strategy guidance of the reinforcement learning model, the simulated annealing algorithm is used to explore the global optimal solution for the buffer layer distribution. Under the premise of meeting the design constraints, non-optimal solutions are accepted with a certain probability to avoid falling into the local optimum and gradually approach the global optimal buffer layer distribution.

[0066] Thermosensitive material parameter optimization submodule: Based on historical orthosis usage data and user-specific thermal environment conditions (such as exercise volume, ambient temperature, humidity, etc.), a regression model (such as random forest, neural network, etc.) is trained to predict the temperature distribution of the orthosis under different thermosensitive material parameters (such as thermal conductivity, specific heat capacity, phase transition temperature, etc.). In the predefined thermosensitive material parameter search space, the Bayesian optimization algorithm is used to find the best parameter combination that can keep the orthosis temperature in a comfortable range (such as avoiding overheating or overcooling). The true objective function is approximated by constructing a proxy model (such as a Gaussian process), and efficient search is performed based on uncertainty-guided sampling strategies.

[0067] 3D printing and electronic module integration: Use multi-material 3D printing technology to print out insoles containing all functional layers at one time, and embed electronic sensors and control modules during the printing process to ensure electronic module calibration and waterproof sealing.

[0068] 3D printing support structure layer: According to the three-dimensional scanning data of the foot, accurately print the support structure with targeted correction function, such as correction elements for specific pathological morphologies such as flat feet, high arches, inversion / external valgus, etc. Generally, TPU, PLA and other materials are selected according to the required support force, and they are made by 3D printing process. The relationship between material hardness and support strength is that within a certain range, the higher the hardness of the material, the stronger its ability to resist deformation, and the greater the support provided to the arch of the foot. F (support force) = k*(D1–D2)+D3, where k is a coefficient reflecting the influence of hardness changes on support strength, D1 is the hardness of the material used, D2 base hardness refers to the minimum effective hardness required for the arch pad, and D3 basic support strength is the basic support that can be provided even at the base hardness. According to user data and orthopedic goals, F is determined to select the appropriate printing material.

[0069] Buffer layer: Contains an inflatable microcapsule structure, which adjusts the internal medium pressure through remote commands to adapt to the shock absorption needs and support strength in different activity scenarios. The microcapsule structure is inflatable or can be filled with water (hydrogel). An inflatable microcapsule structure is selected to encapsulate the gas in one or more polymer films to form a tiny closed space. The microcapsules can be manufactured by solvent dispersion, interfacial polymerization, spray drying and other processes. The shell material of the microcapsule is usually a high molecular polymer, such as polyurethane (PU), polyester (PET), polypropylene (PP), etc. These materials not only ensure sufficient strength to prevent rupture, but also have a certain degree of flexibility to facilitate embedding in the insole and change shape with pressure. The nitrogen filled inside is stable, not easy to leak, and can quickly return to its original state after the external force is released. After the microcapsules are made, they are evenly distributed in the buffering layer material reserved when designing the insole to ensure that each position can play a buffering role according to the orthopedic goal when under pressure. It is necessary to embed a circuit to control inflation and deflation; if hydrogel is used, when the pressure sensor detects a change in gait, the microcontroller regulates the temperature of the gel through electric current to cause a phase change, thereby changing the hardness and shape of the material, and realizing dynamic adjustment of the buffering effect of the insole.

[0070] Thermosensitive adaptive material layer: Using temperature-sensitive smart materials, the hardness is automatically adjusted as the body temperature changes, providing a comfortable fit all day long. Temperature-sensitive smart materials mainly include thermosensitive polymers, PORON polyurethane, and graphene composite materials. By monitoring and responding to changes in foot temperature, the insole control module output provides heat management or improves the comfort of the foot microenvironment.

[0071] Real-time data transmission and adjustment: Pressure and other sensor data are wirelessly transmitted to the user's smartphone application via low-power Bluetooth technology. The application has built-in advanced machine learning algorithms that can analyze data in real time and identify changes in the user's walking pattern, fatigue status, and orthotic needs. Based on these changes, the insole automatically adjusts dynamically by adjusting the cushioning layer to inflation or deflation or hardness.

[0072] User interaction and feedback: The design plan is presented to users and medical experts in a 3D visualization to obtain users' subjective evaluations on comfort, aesthetics, etc., as well as experts' professional opinions on the orthopedic effect. This feedback information is incorporated into model training to continuously iterate and optimize the intelligent algorithm.

[0073] The development of an inflatable microcapsule structure can accurately adjust the thickness and hardness of the insole in specific areas to cope with changes in foot pressure distribution during walking and achieve real-time dynamic correction.

[0074] Develop an embedded sensor network that can monitor foot pressure, posture and motion parameters in real time to ensure accurate capture of gait information and provide data support for dynamic adaptive adjustments.

[0075] Develop machine learning models for gait data to interpret information collected by sensors, identify abnormal gait patterns, predict orthotic needs, and generate real-time adjustment instructions;

[0076] Build a cloud data center to achieve efficient storage, processing and analysis of massive gait data, and support remote monitoring, data analysis and model iteration and upgrade.

[0077] Build a safe and reliable wireless communication protocol and control system so that the cloud analysis results can be instantly transmitted to the micro-control unit built into the orthotic insole, driving the inflatable microcapsule structure to perform precise inflation and deflation operations, thereby achieving remote dynamic adjustment of the insole shape.

[0078] Integrate medical imaging, clinical diagnostic data and personalized gait analysis to form a comprehensive correction strategy to ensure that the insole design not only meets the individual's foot pathology characteristics, but also adapts to their unique gait habits.

[0079] By continuously monitoring the user's wearing data, combining user feedback, and using machine learning algorithms to continuously optimize the orthotic strategy, we can achieve long-term dynamic optimization of insole performance and adapt to changes in disease progression or rehabilitation process.

[0080] This intelligent dynamic adaptive 3D printed orthopedic insole system and preparation method can realize real-time dynamic adjustment of the orthopedic insole function through intelligent sensor module monitoring, remote analysis and regulation, adapt to the user's activity status, health changes and the progress of correction needs, and integrate intelligent sensing, real-time monitoring, cloud data analysis, real-time regulation and multi-layer dynamic structure to provide a full range of intelligent foot health management solutions. In addition, the present invention combines 3D scanning with algorithm-assisted design to provide highly personalized foot support and correction, effectively responding to various foot diseases and gait problems. Users can easily monitor the orthopedic effect, receive doctor's advice and remotely adjust the insole settings through the smart terminal application, which greatly improves the user experience and treatment compliance.

[0081] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent dynamic adaptive 3D printing orthopedic insole system, comprising an insole body, an intelligent sensor module, a transmission analysis module, and a control module, characterized in that: The insole body is a multi-layer dynamic structure. The intelligent sensor module is embedded in the insole body and is used to monitor the user's foot pressure distribution, gait parameters, and foot posture change data in real time. The transmission analysis module is built into the insole body and wirelessly transmits the data to the user's intelligent terminal application for analysis and identification through Bluetooth technology. The user's smart terminal application remotely uploads data to the cloud server. The cloud server uses big data analysis technology to analyze the data, combines user information, forms an individualized database, combines medical advice to generate an individual's orthopedic strategy, and provides users with an online download channel. After downloading through the smart terminal application, it drives the control module. The control module is built into the insole body, and the control module adjusts the multi-layer dynamic structure of the insole body according to the orthopedic strategy.

2. The intelligent dynamic adaptive 3D printing orthopedic insole system according to claim 1, characterized in that: The multi-layer dynamic structure of the insole body includes a supporting structure layer, a buffer layer and a thermosensitive adaptive material layer. The supporting structure layer is a supporting structure with targeted correction function printed according to the three-dimensional scanning data of the user's foot, including a correction structure for specific pathological morphology. The buffer layer contains an inflatable or liquid-filled microcapsule structure, and the internal medium pressure is adjusted by remote commands to adapt to the shock absorption requirements and support strength in different activity scenarios. The thermosensitive adaptive material layer is a temperature-sensitive material body, which automatically adjusts the hardness as the body temperature changes to provide a corresponding fit.

3. The intelligent dynamic adaptive 3D printing orthopedic insole system according to claim 1, characterized in that: The intelligent sensor module includes a pressure sensor, an accelerometer, and a gyroscope. The transmission analysis module has a built-in machine learning algorithm to analyze data in real time and identify changes in user walking patterns, fatigue status, and orthopedic needs. The control module combines user information including age, gender, weight, physical condition, and exercise habits.

4. A method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system, using an intelligent dynamic adaptive 3D printed orthopedic insole system as described in any one of claims 1 to 3, characterized in that: The following steps are involved: Use high-precision plantar 3D scanning equipment to obtain the user's foot morphology data, and combine it with gait analysis results to generate a personalized insole model; Apply artificial intelligence algorithms to set the layout of the support structure layer, the distribution of the cushioning layer, and the functional layer parameters of the thermosensitive adaptive material layer according to the user's data and orthopedic goals; Use multi-material 3D printing technology to print out the insole body including all functional layers at one time, and embed the intelligent sensor module, transmission analysis module, and control module during the printing process, calibrate and waterproof the insole; Present the design plan to relevant experts in a 3D visualization way to obtain their professional opinions on the orthopedic effect, and at the same time obtain the user's subjective evaluation on comfort and aesthetics; Incorporate the above feedback information into model training and continuously iterate the intelligent algorithm.

5. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 4, characterized in that: The applied artificial intelligence algorithm adopts the following algorithm architecture: Data input and preprocessing; Core analysis of functional layer algorithms.

6. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 5, characterized in that: The data input and preprocessing includes the following steps: Collect user's individualized information, including biomechanical indicators, medical images, and description of orthopedic needs; Perform quality checks on the collected data, remove outliers and redundant information, and convert all types of data into a unified format; Features that are closely related to orthopedic insole design are extracted and used as inputs for intelligent algorithms.

7. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 6, characterized in that: The functional layer algorithm core analysis includes the following steps: Using the convolutional neural network (CNN) or graph neural network (GNN) model, the position, shape and material properties of the ideal support structure are predicted based on the user's gait data and joint torque distribution. The model accepts preprocessed biomechanical features as input and outputs design suggestions for the support structure layer. Combining expert knowledge and design constraints, the genetic algorithm or particle swarm optimization method is used to iteratively search for the optimal support structure layer layout. Each generation of design solutions is generated by the above deep learning model, and its performance is evaluated by the fitness function. The next generation of candidate solutions is generated based on selection, crossover and mutation. Based on the user's gait data and pressure distribution characteristics, a reinforcement learning agent is trained, including the environment state, action space and reward function. The environment state includes the current buffer layer distribution and user gait feedback. The action space is to adjust the buffer layer thickness, material, and position parameters. The reward function reflects the buffer effect and user comfort. Combined with the strategy guidance of the reinforcement learning model, the simulated annealing algorithm is used to explore the global optimal solution of the buffer layer distribution. Based on historical orthosis usage data and user-specific thermal environment conditions, a regression model is trained to predict the temperature distribution of the orthosis under different thermosensitive material parameters. In the predefined thermosensitive material parameter search space, the Bayesian optimization algorithm is used to find the optimal parameter combination that can keep the orthosis temperature in a comfortable range. The true objective function is approximated by constructing a proxy model, and an efficient search is performed based on the uncertainty-guided sampling strategy to determine the parameters of the thermosensitive adaptive material layer.

8. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 4, characterized in that: Use 3D printed support structure layer: According to the three-dimensional scanning data of the foot, print a support structure with targeted correction function, including correction elements for specific pathological morphology. Select materials according to the required support force, and make it through 3D printing process. The relationship between material hardness and support strength is controlled based on the following principles: The higher the hardness of the material, the stronger its ability to resist deformation, and the greater the support provided to the arch of the foot. F (support force) = k*(D1-D2)+D3, where k reflects the coefficient of the influence of hardness change on support strength, D1 is the hardness of the material used, D2 is the baseline hardness, which refers to the minimum effective hardness required for the arch pad, and D3 is the basic support strength, which refers to the basic support that can be provided even at the baseline hardness. Determine F based on user data and orthopedic goals, and then select the appropriate printing material.

9. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 8, characterized in that: The 3D printed buffer layer contains an inflatable microcapsule structure. The microcapsule structure is inflatable or can be filled with hydrogel. When inflatable microcapsules are selected, the gas is encapsulated in a closed space formed in one or more layers of polymer films. The microcapsules are manufactured by solvent dispersion, interfacial polymerization, and spray drying processes. The shell of the microcapsule is prepared with a high molecular polymer and filled with nitrogen. After the microcapsules are made, they are evenly distributed in the buffer layer material reserved in the insole body and embedded with a circuit to control inflation and deflation. When hydrogel is selected, a microcontroller is added to regulate the temperature of the gel through electric current to cause a phase change, thereby changing the hardness and morphology of the material.

10. The method for preparing an intelligent dynamic adaptive 3D printed orthopedic insole system according to claim 9, characterized in that: A thermosensitive adaptive material layer is prepared using temperature-sensitive smart materials that automatically adjust hardness as body temperature changes. The thermosensitive adaptive material layer includes thermosensitive polymers, PORON polyurethane, and graphene composite materials. The thermosensitive adaptive material layer adjusts by monitoring and responding to changes in foot temperature.

Images