Sleep-aid linkage system based on ankle recovery monitoring

Abstract

The application discloses an aid-sleep linkage system based on ankle recovery monitoring and relates to the technical field of medical health and intelligent monitoring.The aid-sleep linkage system based on ankle recovery monitoring collects rich biomechanical parameters of the ankle area in real time through a multi-modal sensor, covers plantar pressure distribution, ankle joint motion trajectory, foot temperature and skin impedance, performs multi-dimensional fusion analysis on the data, combines with built-in neural network model calculation, can accurately analyze the ankle fatigue state and recovery stage, is different from the traditional fixed threshold judgment mode, can be dynamically adjusted according to individual differences and historical data of the user, greatly improves the judgment accuracy, and then, the aid-sleep equipment linkage control module adjusts the running parameters of the sleep monitoring equipment, the environmental temperature control equipment, the hardness of the mattress, the environmental light intensity and the sound wave frequency according to the analysis result, and creates a special sleep environment for the user in line with the ankle recovery process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical health and intelligent monitoring, in particular to a sleep-aiding linkage system based on ankle recovery monitoring. BACKGROUND

[0002] With the increasing incidence of ankle injuries, ankle injuries not only affect the normal walking and motor function of patients, but also can lead to decreased sleep quality, and thus affect the overall recovery of the body. Therefore, how to effectively monitor the ankle recovery and improve the sleep quality of patients through a sleep-aiding linkage system has become a hot topic in current rehabilitation medicine research.

[0003] Currently, existing ankle recovery monitoring systems mainly focus on collecting and analyzing biomechanical parameters of the ankle, such as plantar pressure distribution and ankle joint motion trajectory. However, these systems often have the following shortcomings:

[0004] Lack of accurate judgment of ankle fatigue state and recovery stage. Existing monitoring systems usually use fixed thresholds to judge the fatigue state and recovery stage of the ankle, which cannot be dynamically adjusted according to individual differences and historical data of patients, resulting in inaccurate judgment results.

[0005] The sleep-aiding linkage system is not intelligent enough. Existing sleep-aiding linkage systems can only adjust the operation mode of sleep-aiding devices according to preset parameters, and cannot be adjusted in real time according to the ankle recovery, resulting in poor sleep-aiding effect.

[0006] In summary, the existing ankle recovery monitoring system lacks accurate judgment of ankle fatigue state and recovery stage. Therefore, a sleep-aiding linkage system based on ankle recovery monitoring is developed to solve the above problems. SUMMARY

[0007] The purpose of the present application is to overcome the shortcomings of the prior art and provide a sleep-aiding linkage system based on ankle recovery monitoring. The system can collect biomechanical parameters of the ankle area in real time, and accurately judge the fatigue state and recovery stage of the ankle through multi-dimensional fusion analysis and neural network model calculation. At the same time, the system can dynamically adjust the operation parameters of the sleep-aiding devices according to the ankle recovery, improve the sleep-aiding effect, and thus promote the recovery of the ankle. In addition, the system has a visual user interface, and users can easily view the ankle recovery and adjust the operation parameters of the sleep-aiding devices, improving the user experience.

[0008] To solve the above technical problems, the present application provides the following technical solution: a sleep-aiding linkage system based on ankle recovery monitoring, which comprises an ankle data collection module, an ankle state analysis module, an ankle pressure dynamic control module, a sleep-aiding device linkage control module, and a user interaction module.

[0009] The ankle data acquisition module is configured to acquire biomechanical parameters of the ankle region in real time through a multi-modal sensor, including plantar pressure distribution, ankle joint motion trajectory, foot temperature and skin impedance data, and transmit the data to the ankle state analysis module through a wireless transmission protocol.

[0010] The ankle state analysis module is configured to perform multi-dimensional fusion analysis on the collected data, combine a preset ankle recovery model and a fatigue threshold, determine the fatigue state and recovery stage of the user's ankle, and generate a dynamic control instruction.

[0011] The foot pressure dynamic control module is configured to adjust the plantar pressure distribution in real time through a micro motor driven air bag array according to the dynamic control instruction of the ankle state analysis module.

[0012] The sleep aid device linkage control module is configured to interact data between the ankle state analysis result and a sleep monitoring device, an environmental temperature control device, dynamically adjust the operating parameters of the sleep aid device according to the ankle recovery stage, including the hardness of the mattress, the intensity of the environmental light and the frequency of the sound wave.

[0013] The user interaction module is configured to provide a visual operation interface, support the user to customize the ankle recovery target, the pressure adjustment intensity and the sleep preference parameters, and real-time feedback the system operation state and the data log.

[0014] Further, the ankle data acquisition module comprises:

[0015] A high-precision pressure sensor array is embedded in the foot pad in the form of a flexible circuit board to measure the pressure value of the foot bottom at a fixed sampling interval.

[0016] An inertial measurement unit is integrated in the ankle strap to capture the three-dimensional motion trajectory of the ankle joint through a three-axis accelerometer and a gyroscope to obtain the motion amplitude and frequency.

[0017] A temperature-impedance composite sensor is distributed in the arch and heel area to synchronously measure the skin surface temperature change and impedance value for evaluating the local blood circulation state.

[0018] A data preprocessing unit is configured to perform noise reduction processing on the original signal, remove non-periodic interference, and eliminate motion artifacts.

[0019] Further, the ankle state analysis module comprises:

[0020] A multi-source data fusion unit is configured to align the plantar pressure distribution, ankle joint motion trajectory, foot temperature and skin impedance data by time stamp, and generate an ankle comprehensive state feature vector using a weighted fusion strategy, wherein the weight of the pressure data accounts for 40%, the weight of the motion data accounts for 30%, and the weight of the temperature and impedance each accounts for 15%.

[0021] An ankle recovery model calculation unit, which is built-in an ankle recovery model based on biomechanical characteristics training, outputs the current fatigue level numerical value after inputting the feature vector;

[0022] A dynamic threshold judgment unit, which dynamically adjusts the fatigue threshold range according to the user's historical data, determines that the ankle is in an acute fatigue state when the fatigue level numerical value exceeds 120% of the fatigue threshold in three consecutive samplings, otherwise, determines that the ankle is in a stable fatigue state;

[0023] A recovery stage decision unit, which compares the fatigue level numerical value with the preset fatigue threshold of the acute phase, transition phase and stable phase to determine the recovery stage, and triggers the stage switching instruction when the numerical value exceeds the upper limit of the fatigue threshold interval for three consecutive sampling periods;

[0024] An instruction generation unit, which maps the fatigue state and the recovery stage into a dynamic control instruction, including the air bag pressure target value, the adjustment rate and the partition priority.

[0025] Further, the foot pressure dynamic control module includes a pressure adjustment execution unit, a pressure feedback monitoring unit and a control strategy generation unit;

[0026] The pressure adjustment execution unit is composed of a plurality of independently controllable micro-motors driving an air bag array, and the micro-motors adjust the air bag inflation amount according to the dynamic control instruction of the ankle state analysis module, so as to change the pressure distribution of different areas of the foot bottom;

[0027] The pressure feedback monitoring unit contains pressure sensors distributed on the surface of the air bag, which monitors the adjusted foot bottom pressure data in real time and feeds back the data to the control strategy generation unit;

[0028] The control strategy generation unit receives the data of the pressure feedback monitoring unit and the dynamic control instruction of the ankle state analysis module, combines the foot bottom pressure distribution standard and the user's individual needs, judges the expected effect of the current pressure adjustment, and when the expected effect does not meet the user's needs, the pressure adjustment instruction is regenerated and sent to the pressure adjustment execution unit, realizing the closed-loop dynamic control of the foot bottom pressure distribution.

[0029] Further, the sleep aid device linkage control module includes a device communication unit, a parameter matching unit, a linkage coordination unit and an instruction execution unit;

[0030] The device communication unit adopts a unified communication protocol to establish a data interaction channel with the sleep monitoring device and the environmental temperature control device, receives the user sleep data collected by the sleep monitoring device and the current running parameters of the environmental temperature control device, and transmits the results of the ankle state analysis module to the sleep aid device, which includes the sleep monitoring device and the environmental temperature control device;

[0031] The parameter matching unit stores a sleep-aiding device parameter configuration table corresponding to different stages of foot-ankle recovery, matches the recovery stage result obtained by the foot-ankle state analysis module with the configuration table, and determines the device operation parameters of the bed mattress hardness, environmental light intensity, and sound wave frequency;

[0032] The linkage coordination unit coordinates the working order among the sleep-aiding devices according to the device operation parameters determined by the parameter matching unit.

[0033] The instruction execution unit sends control instructions to the sleep-aiding devices according to the working order of the linkage coordination unit, so that the sleep monitoring device and the environmental temperature control device are cooperatively operated according to the set device operation parameters.

[0034] Further, the user interaction module includes:

[0035] The interface display unit displays the real-time data collected by the foot-ankle data collection module, the analysis result of the foot-ankle state analysis module, the pressure distribution state of the foot pressure dynamic regulation module, and the device operation parameters of the sleep-aiding device linkage control module in a graphical interface.

[0036] The input processing unit receives the foot-ankle recovery target, pressure regulation intensity, and sleep preference parameter information input by the user on the operation interface.

[0037] The data feedback unit records the user operation and the data log in the system running process, including the foot-ankle data change and the device control instruction execution situation, and feeds back the data in a chart form to the user.

[0038] The setting storage unit encrypts the user-defined parameter information, automatically calls the information when the system runs next time, regularly backs up the stored data to prevent data loss.

[0039] Further, the implementation process of the neural network model of the foot-ankle recovery model calculation unit is as follows:

[0040] The input layer receives the foot-ankle comprehensive state feature vector , wherein and the four-dimensional data of the foot pressure distribution, ankle joint motion trajectory, foot temperature, and skin impedance are normalized to obtain a four-dimensional vector , wherein represents the normalized pressure data, is the motion data, is the temperature data, is the impedance data;

[0041] The first hidden layer: the data of the input layer is subjected to full connection feature transformation, the input data is subjected to weighted summation and nonlinear transformation, and representative features are extracted. The calculation formula of the full connection feature transformation is Weight matrix This refers to the connection relationships and weights between the input layer and the first hidden layer. The weight matrix has 8 rows and 4 columns, corresponding to the four neurons of the four data classes in the input layer being connected to the eight neurons of the first hidden layer. Each element in the matrix... Represents the input layer The first hidden layer contains neurons. The weights of each neuron when transmitting signals The numbers represent the sequence numbers of the neurons in the first hidden layer, from 1 to 8. The input layer neurons are numbered from 1 to 4, and their biases are... It is a constant term set separately for each neuron in the first hidden layer, each Corresponding to the first hidden layer One neuron, It is an activation function and During the calculation process, when When the result is less than 0, the neuron outputs 0, and the first hidden layer outputs an 8-dimensional vector. ;

[0042] The second hidden layer processes the output of the first hidden layer by introducing an attention mechanism and performing a weighted transformation to obtain the feature representation. This attention mechanism calculates the attention weight matrix. ,in, This is the attention weight matrix, used to measure the importance of each feature output from the first hidden layer in calculating the output of the neurons in the second hidden layer. The elements in the matrix... Indicates the first hidden layer. The first neuron in the second hidden layer... The degree of influence of the attention weights of each neuron, the softmax function is used to... The calculation results are converted into a probability distribution form, resulting in the attention weight matrix. Each element in the array takes a value between 0 and 1, and the sum of all elements is 1. ,in This indicates that the output of the first hidden layer is related to the output of the second hidden layer. The attention weights of each neuron are used to calculate the output of the second hidden layer. ,in This is the weight matrix of the second hidden layer, responsible for converting the 8-dimensional output of the first hidden layer into the 4-dimensional input of the second hidden layer. The matrix elements... Indicates the first hidden layer. The first neuron and the second hidden layer The weight values ​​of the connections between neurons It is the bias of the second hidden layer, each the i-th neuron of the second hidden layer, the symbol represents multiplying the attention weight matrix with the corresponding element of , in this way, the data is weighted by the attention weight, and the second hidden layer is obtained;

[0043] Output layer: according to the features extracted by the hidden layer, the final ankle fatigue grade value is calculated , where is a weight vector and , represents the transpose of the weight vector and the dot product operation with , each element in the weight vector represents the contribution weight of the i-th neuron of the second hidden layer to the final fatigue grade output, that is, it determines the influence degree of the output of the corresponding neuron of the second hidden layer on the final result, the bias term is the bias value of the output layer, used to adjust the calculation result and is a real set, which maps the calculated value to the interval [0, 10] to represent the fatigue state of the ankle.

[0044] Further, the dynamic threshold judgment unit calculates the fatigue grade value according to the neural network model, combines the dynamically adjusted fatigue threshold, sets the initial fatigue threshold as , records the historical fatigue grade value sequence , where represents the fatigue grade value of the i-th sampling, calculates the mean and the standard deviation of the historical data, and the dynamically adjusted fatigue threshold , where and are adjustment coefficients, used to control the influence degree of the mean on the fatigue threshold, used to control the influence degree of the standard deviation on the fatigue threshold, and , when the fatigue score in the continuous 3 times of sampling is all greater than , it is determined that the ankle is in acute fatigue state, otherwise, it is determined that the ankle is in stable fatigue state;

[0045] The recovery stage decision unit calculates the fatigue grade value ​​​​Compared with preset acute phase, transition phase and stable phase threshold interval, when the value exceeds the upper limit of the threshold interval for three consecutive sampling periods, the stage switching instruction is triggered, the acute phase threshold interval is [0, 3], the transition phase threshold interval is (3, 6], the stable phase threshold interval is (6, 10], and when the fatigue level value of three consecutive sampling periods all greater than 3, the acute phase is switched to the transition phase; when the fatigue level value of three consecutive sampling periods all greater than 6, the transition phase is switched to the stable phase, in this way, the dynamic threshold judgment unit and the recovery stage decision unit are closely linked, the dynamic and accurate evaluation of the foot and ankle recovery state is realized, and the basis for the subsequent regulation and intervention of the system is provided.

[0046] Compared with the prior art, the sleep-aiding linkage system based on foot and ankle recovery monitoring has the following beneficial effects:

[0047] Firstly, the sleep-aiding linkage system based on foot and ankle recovery monitoring of the present application can collect rich biomechanical parameters of the foot and ankle region in real time through multi-modal sensors, including plantar pressure distribution, ankle joint motion trajectory, foot temperature and skin impedance. These data are analyzed through multi-dimensional fusion and combined with the calculation of the built-in neural network model to accurately analyze the foot and ankle fatigue state and recovery stage. Unlike the traditional fixed threshold judgment method, the system can dynamically adjust according to individual differences and historical data, greatly improving the judgment accuracy. Furthermore, the sleep-aiding device linkage control module adjusts the running parameters of the sleep monitoring device, the environmental temperature control device, the bed mattress hardness, the environmental light intensity and the sound wave frequency according to the analysis results, creates a special sleep environment that matches the foot and ankle recovery process for the user, effectively promotes the foot and ankle recovery, and significantly improves the sleep quality.

[0048] Secondly, the user interaction module of the system provides an intuitive visual operation interface, and the user can conveniently customize the foot and ankle recovery target, pressure adjustment intensity and sleep preference parameters, and can also obtain real-time system running state and data log feedback, thereby enhancing the participation and control, continuously adapting to the unique needs and foot and ankle recovery process changes of different users, and comprehensively improving the overall performance of the system and the user satisfaction.

[0049] Other advantages, objects, and features of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other accompanying drawings can also be obtained by those skilled in the art without any creative effort on the premise of the accompanying drawings.

[0051] Figure 1 Operation flowchart of the sleep-aiding linkage system based on ankle recovery monitoring;

[0052] Figure 2 Module composition schematic diagram of the sleep-aiding linkage system based on ankle recovery monitoring. DETAILED DESCRIPTION

[0053] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined application purposes, the specific embodiments, structures, features and effects according to the present application will be described in detail below in combination with the accompanying drawings and preferred embodiments. Embodiment one

[0054] This embodiment details the module composition and working principle of the sleep-aiding linkage system based on ankle recovery monitoring, as shown in Figure 2 The system integrates an ankle data acquisition module, an ankle state analysis module, a foot pressure dynamic regulation module, a sleep-aiding equipment linkage control module and a user interaction module, collects ankle biomechanics parameters through multi-modal sensors, performs multi-dimensional fusion analysis and neural network model calculation, accurately judges the ankle fatigue state and recovery stage, dynamically adjusts the sleep-aiding equipment parameters, provides a visual interaction interface for the user, improves the user experience, effectively promotes ankle recovery and improves sleep quality.

[0055] The ankle data acquisition module is responsible for obtaining key biomechanical parameters of the ankle region. The module is composed of a high-precision pressure sensor array, an inertial measurement unit, a temperature-impedance composite sensor, and a data preprocessing unit. The high-precision pressure sensor array is embedded in the foot pad in the form of a flexible circuit board, which aims to accurately measure the pressure distribution on the foot bottom. In the state of walking or standing, different areas of the foot bottom bear different pressures, and these pressure changes reflect the stress of the ankle. The sensor works at a fixed sampling interval and continuously collects pressure values at each point on the foot bottom to form pressure distribution data. The inertial measurement unit is integrated into the ankle strap. The internal three-axis accelerometer and gyroscope work together. The three-axis accelerometer can capture the acceleration changes of the ankle joint in three axial directions (usually front-back, left-right, and up-down). The gyroscope focuses on measuring the rotational angular velocity of the ankle joint. Through analysis of these data, the three-dimensional motion trajectory of the ankle joint can be accurately calculated, and the motion amplitude and frequency information can be obtained. The temperature-impedance composite sensor is distributed in the arch and heel regions, which play a key role in blood circulation and support of the ankle. The sensor synchronously measures the temperature change and impedance value of the skin surface. The temperature change can reflect the heat change of local blood circulation, while the change of impedance value is related to the physiological state of the tissue and can be used to evaluate the local blood circulation state. For example, when blood circulation is poor, the temperature may decrease, and the impedance value will also change accordingly. The data preprocessing unit processes the original signals collected by the above sensors. Due to various disturbances in the actual collection process, such as environmental noise and artifacts generated by human motion, noise reduction processing is needed. The data preprocessing unit can effectively separate the useful signal and the interference signal. At the same time, by eliminating motion artifacts, it ensures that the data for subsequent analysis is accurate and reliable. The preprocessed data is sent to the ankle state analysis module in a wireless transmission protocol.

[0056] The foot and ankle status analysis module receives data from the foot and ankle data acquisition module and performs in-depth analysis to determine the fatigue state and recovery stage of the foot and ankle. This module includes a multi-source data fusion unit, a foot and ankle recovery model calculation unit, a dynamic threshold judgment unit, a recovery stage decision unit, and an instruction generation unit. The multi-source data fusion unit first aligns the plantar pressure distribution, ankle joint movement trajectory, foot temperature, and skin impedance data by timestamp. This is because there are slight differences in the time of data acquisition from different sensors; timestamp alignment ensures data synchronization during subsequent analysis. Then, a weighted fusion strategy is used to generate a foot and ankle recovery model. The ankle comprehensive status feature vector is composed of several weighted data points. Pressure data accounts for 40% of the weight, as plantar pressure distribution directly reflects the stress on the ankle during support and movement, and is crucial for assessing ankle condition. Motion data accounts for 30%, with information such as ankle joint movement trajectory and frequency reflecting ankle function and fatigue accumulation. Temperature and impedance each account for 15%, providing supplementary information on blood circulation and tissue physiological state. This weighted fusion method integrates multi-source data into a comprehensive feature vector, providing a more complete description of ankle condition. The ankle recovery model calculation unit incorporates a biomechanical feature-based training... Ankle rehabilitation model The input to this model is the foot and ankle integrated state feature vector generated by the multi-source data fusion unit. ( The data (corresponding to four-dimensional data of plantar pressure distribution, ankle joint movement trajectory, foot temperature, and skin impedance) is normalized before being input into the model to obtain a four-dimensional vector. ,in This represents the normalized stress data. It's motion data. It's temperature data. This is impedance data. After the input layer receives this vector, the data enters the first hidden layer. The first hidden layer performs a fully connected feature transformation on the input data, and the calculation formula is as follows: Weight matrix This describes the connection relationships and weights between the input layer and the first hidden layer. The matrix has 8 rows and 4 columns, meaning that the four neurons of the four data classes in the input layer are connected to the eight neurons of the first hidden layer. Each element in the matrix... Represents the input layer The first hidden layer contains neurons. The weights of each neuron when transmitting signals This indicates the sequence number (from 1 to 8) of the neurons in the first hidden layer. Indicates the index (from 1 to 4) of the input layer neurons. Bias It is a constant term set separately for each neuron in the first hidden layer, each Corresponding to the first hidden layer neuron, activation function , during the calculation process, when the result is less than 0, the output of the neuron is 0; when the result is greater than 0, the output of the neuron is equal to the result value, after such calculation, the first hidden layer outputs an 8-dimensional vector , which realizes the preliminary feature extraction and nonlinear transformation of the input data, so that the model can learn more complex patterns, the second hidden layer introduces an attention mechanism to further process the output of the first hidden layer, first calculate the attention weight matrix , wherein is the attention weight matrix, which is used to measure the importance of each feature output by the first hidden layer to the calculation of the output of the second hidden layer neuron, the elements in the matrix represent the attention weight influence degree of the first hidden layer neuron to the second hidden layer neuron, the softmax function is used to convert the calculation result of to a probability distribution form, so that each element in the obtained attention weight matrix takes a value between 0 and 1, and the sum of all elements is 1, that is , wherein represents the attention weight of the first hidden layer output to the second hidden layer neuron, then calculate the output of the second hidden layer , wherein is the weight matrix of the second hidden layer, which is responsible for converting the 8-dimensional output of the first hidden layer to the 4-dimensional input of the second hidden layer, the matrix element represents the weight value of the connection between the first hidden layer neuron and the second hidden layer neuron, is the bias of the second hidden layer, each corresponds to the neuron of the second hidden layer, the symbol represents the multiplication of the attention weight matrix and the corresponding element of , in this way, the data is weighted by using the attention weight, highlighting the features that are more important for judging the foot fatigue grade, obtaining the output of the second hidden layer , the output layer calculates the final foot fatigue grade value according to the features extracted by the hidden layer, wherein is the weight vector , represents the dot product operation of transposing the weight vector and , the weight vector Each element in Indicates the second hidden layer The contribution weight of each neuron to the final fatigue level output determines the degree of influence of the output of the corresponding neuron in the second hidden layer on the final result. The bias term... It is the bias value of the output layer, used to adjust the calculation results, and finally the calculated value is... The values ​​are mapped to the interval [0, 10] to represent the fatigue state of the foot and ankle; the larger the value, the higher the degree of fatigue. The dynamic threshold judgment unit judges the fatigue state of the foot and ankle based on the fatigue level value calculated by the neural network model and the dynamically adjusted fatigue threshold. The initial fatigue threshold is first set to... Record the user's historical fatigue level numerical sequence ,in Indicates the first The fatigue level value from the sampled data was calculated by taking the mean of historical data. and standard deviation Dynamically adjusted fatigue threshold ,in and To adjust the coefficient, Used to control the degree of influence of the mean on the fatigue threshold. Used to control the degree of influence of standard deviation on fatigue threshold, and , When fatigue scores are in 3 consecutive samples All exceeded When the foot and ankle are in an acute fatigue state, they are determined to be in a stable fatigue state; otherwise, they are determined to be in a stable fatigue state. This dynamic adjustment of the fatigue threshold can more accurately determine the fatigue state of the foot and ankle based on individual differences and historical data changes. During the recovery phase, the decision unit will assign a fatigue level value. Compared with preset threshold ranges for acute, transition, and stable phases, the preset threshold ranges for acute phase are [0, 3], for transition phase are (3, 6], and for stable phase are (6, 10]. When the value exceeds the upper limit of the threshold range for three consecutive sampling periods, a phase switching command is triggered. For example, if the fatigue level value exceeds the upper limit of the threshold range for three consecutive sampling periods... If all values ​​are greater than 3, then the process switches from the acute phase to the transition phase; if the values ​​are greater than 3 for three consecutive sampling periods... If all are greater than 6, switch from the transition period to the stable period. In this way, the recovery stage of the foot and ankle can be tracked in real time, providing a basis for subsequent regulation; the instruction generation unit maps the fatigue state and recovery stage to dynamic regulation instructions, including airbag pressure target value, adjustment rate and partition priority, according to different fatigue states and recovery stages, to determine the appropriate plantar pressure adjustment scheme to promote the relaxation of foot and ankle muscles and the improvement of blood circulation, for example, in the acute fatigue state, the airbag pressure needs to be adjusted more significantly, and the plantar area that is more critical to relieve fatigue is adjusted first; while in the stable fatigue state, the pressure adjustment is relatively mild.

[0057] The foot pressure dynamic regulation module adjusts the plantar pressure distribution in real time according to the dynamic regulation instructions generated by the foot and ankle state analysis module, which consists of a pressure regulation execution unit, a pressure feedback monitoring unit and a regulation strategy generation unit. The pressure regulation execution unit consists of a plurality of independently controllable micro-motors driving an airbag array, which adjusts the airbag inflation according to the pressure regulation instructions of the foot and ankle state analysis module, thereby changing the pressure distribution of different areas of the foot. For example, when the instruction requires to increase the pressure of the plantar area, the corresponding micro-motor will drive the airbag to increase the inflation, so that the pressure of the area is increased; conversely, the inflation is reduced to reduce the pressure. In this way, accurate control of the plantar pressure is achieved; the pressure feedback monitoring unit contains pressure sensors distributed on the surface of the airbag, which monitor the adjusted plantar pressure data in real time. After the pressure regulation execution unit adjusts the airbag pressure, the pressure feedback monitoring unit immediately collects the current plantar pressure data and feeds it back to the regulation strategy generation unit, which can ensure that the system knows the actual effect of pressure regulation in time and provides a basis for subsequent regulation; the regulation strategy generation unit receives the data of the pressure feedback monitoring unit and the dynamic regulation instructions of the foot and ankle state analysis module, combines the plantar pressure distribution standard and the user's individual needs, and judges the expected effect of the current pressure regulation. The plantar pressure distribution standard is determined according to medical research and clinical experience, and different foot and ankle states and recovery stages correspond to different reasonable pressure distribution ranges. The user's individual needs take into account the user's special circumstances, such as the user's sensitivity to pressure and the user's habitual walking style. When the expected effect does not meet the user's needs, the regulation strategy generation unit generates new pressure regulation instructions and sends them to the pressure regulation execution unit, for example, if the pressure of a certain area after adjustment still deviates from the standard range and does not meet the user's individual needs, the regulation strategy generation unit will adjust the airbag pressure target value, adjustment rate and other parameters to resend the instructions, realizing closed-loop dynamic regulation of the plantar pressure distribution and ensuring that the plantar pressure is always in a state conducive to the recovery of the foot and ankle.

[0058] The sleep-aiding device linkage control module is responsible for data interaction between the foot-ankle state analysis result and the sleep monitoring device, the environmental temperature control device, and dynamically adjusting the operation parameters of the sleep-aiding device according to the foot-ankle recovery stage. The module is composed of a device communication unit, a parameter matching unit, a linkage coordination unit and an instruction execution unit. The device communication unit adopts a unified communication protocol to establish a data interaction channel with the sleep monitoring device and the environmental temperature control device. Through this channel, the device communication unit receives the user sleep data collected by the sleep monitoring device, such as sleep duration, sleep depth, and the number of turning over, and the current operation parameters of the environmental temperature control device, such as indoor temperature and humidity. At the same time, the results of the foot-ankle state analysis module, including foot-ankle fatigue state and recovery stage information, are transmitted to each device to realize data sharing and interaction. The parameter matching unit stores the sleep-aiding device parameter configuration table corresponding to different stages of foot-ankle recovery. When receiving the recovery stage result obtained by the foot-ankle state analysis module, the parameter matching unit matches it with the configuration table to determine the device operation parameters such as mattress hardness, environmental light intensity, and sound wave frequency. For example, in the acute stage, in order to reduce the pressure on the foot and ankle, the mattress hardness is adjusted to a softer state, the environmental light intensity is reduced, and soothing low-frequency sound waves are played to help users relax and promote sleep. In the transition and stable stages, these parameters are gradually adjusted according to the recovery situation. The linkage coordination unit coordinates the working order of each sleep-aiding device according to the parameters determined by the parameter matching unit. Since the adjustment of different sleep-aiding devices affects each other, the linkage coordination unit needs to reasonably arrange their working order to avoid conflicts, such as adjusting the mattress hardness first, then adjusting the environmental light intensity, and finally adjusting the sound wave frequency, to ensure the coordinated adjustment of each device and create a comfortable sleep environment for the user. The instruction execution unit sends control instructions to each sleep-aiding device according to the working order of the linkage coordination unit. These instructions accurately control the sleep monitoring device and the environmental temperature control device to operate according to the set parameters, such as sending instructions to the mattress control system to adjust the support structure inside the mattress and change the mattress hardness, sending instructions to the light control system to adjust the environmental light intensity, and sending instructions to the audio playback device to play sound waves of a specific frequency. Through the coordinated work of each device, a sleep-aiding environment suitable for the foot-ankle recovery stage is provided for the user, the sleep-aiding effect is improved, and the foot-ankle recovery is promoted.

[0059] The user interaction module provides a visual operation interface for the user to interact with the system, which is convenient for the user to customize various parameters and real-time understand the system running state and data. The module is composed of interface display unit, input processing unit, data feedback unit and setting storage unit. The interface display unit displays the real-time data collected by the foot and ankle data acquisition module, the analysis results of the foot and ankle state analysis module, the pressure distribution state of the foot pressure dynamic regulation module and the equipment running parameters of the sleep aid equipment linkage control module in a graphical interface, such as the change curve of the plantar pressure over time, the dynamic graphics of the ankle joint motion trajectory, the intuitive identification of the foot and ankle fatigue grade and recovery stage, and the current values of the mattress hardness, environmental light intensity and sound wave frequency, etc. In this way, the user can intuitively understand the real-time state of the foot and ankle and the running situation of the sleep aid equipment. The input processing unit receives the foot and ankle recovery target, pressure regulation intensity, sleep preference and other parameter information input by the user on the operation interface. After receiving the user input, the input processing unit performs format checking and validity verification on these information. Only the data that passes the verification will be accepted by the system and processed subsequently. The data feedback unit feeds back the user operation record and the data log in the system running process, including the foot and ankle data change and the equipment control instruction execution, to the user in the form of charts. Through these charts, the user can clearly see the influence of his operation on the system and the data change trend in the foot and ankle recovery process, for example, the user can view the change curve of the foot and ankle fatigue grade in a period of time to understand his recovery situation, or view the execution record of the sleep aid equipment control instruction to confirm whether the equipment has been adjusted according to his requirements. The setting storage unit stores the user-defined parameter information in an encrypted manner and automatically calls it when the system runs next time. In this way, the user does not need to set the parameters every time he uses the system, improving the convenience of use. At the same time, the setting storage unit regularly backs up the stored data to prevent data loss. Even in the case of system failure or unexpected situations, the user's setting information can be protected, ensuring the stability of the system and the security of the user data.

[0060] In summary, the embodiment details the combination and working principle of each module of the sleep aid linkage system based on foot and ankle recovery monitoring. Through the foot and ankle data acquisition module, comprehensive biomechanical parameters are obtained. The foot and ankle state analysis module uses multi-dimensional fusion analysis and neural network model for accurate judgment. The foot pressure dynamic regulation module realizes real-time pressure regulation. The sleep aid equipment linkage control module optimizes the sleep environment according to the recovery stage. The user interaction module provides convenient operation and feedback. Each module closely cooperates to form an efficient and intelligent system. The system can dynamically adjust various parameters according to the individual differences of the user and the foot and ankle recovery process, not only improving the accuracy of foot and ankle fatigue state and recovery stage judgment, but also significantly improving the sleep aid effect and enhancing the user experience. Example Two

[0061] As Figure 1 shown, this embodiment describes in detail the specific steps of the patient's ankle recovery monitoring through the sleep-aiding linkage system based on ankle recovery monitoring, which are:

[0062] The patient inputs information from the visual operation interface of the user interaction module;

[0063] Input personal basic information such as age, gender, height, weight, etc., which helps the system more accurately analyze the ankle state;

[0064] Customize ankle recovery goals, such as desired recovery level, recovery time, etc.; Set pressure adjustment strength, choose the appropriate adjustment strength according to the tolerance and comfort of the pressure;

[0065] Input sleep preference parameters such as preferred sleep posture, desired ambient temperature, and preferred sleep-aiding sound type;

[0066] The high-precision pressure sensor array in the ankle data acquisition module continuously measures the pressure values of the foot bottom at fixed sampling intervals, and monitors the pressure changes of different areas of the foot bottom in real time when the patient walks, stands or rests;

[0067] The three-axis accelerometer and gyroscope in the inertial measurement unit cooperatively capture the three-dimensional motion trajectory of the ankle joint, and obtain the motion amplitude and frequency data;

[0068] The temperature-impedance composite sensor synchronously measures the skin surface temperature changes and impedance values of the arch and heel areas to evaluate the local blood circulation state;

[0069] The collected raw data will first be transmitted to the data preprocessing unit to remove non-periodic interference and motion artifacts, ensuring the accuracy and reliability of the data, and then sent to the ankle state analysis module through a wireless transmission protocol;

[0070] After receiving the data, the ankle state analysis module, the multi-source data fusion unit aligns the foot pressure distribution, ankle motion trajectory, foot temperature and skin impedance data by time stamp, and generates an ankle comprehensive state feature vector using a weighted fusion strategy;

[0071] The ankle recovery model calculation unit evaluates the fatigue level of the ankle according to the feature vector, and at the same time, the dynamic threshold judgment unit combines the patient's historical fatigue data to dynamically adjust the fatigue threshold range, and then judges whether the ankle is in acute fatigue state or stable fatigue state;

[0072] The recovery stage decision unit compares the fatigue level value with preset threshold intervals of acute stage, transition stage and stable stage, judges the current recovery stage of the foot and ankle, and if the value exceeds the upper limit of a threshold interval for three consecutive sampling periods, a stage switching instruction is triggered;

[0073] The instruction generation unit generates pressure regulation instructions according to the fatigue state and the recovery stage, including information such as the air bag pressure target value, the adjustment rate and the partition priority, and sends the instructions to the foot pressure dynamic regulation module;

[0074] The pressure regulation execution unit of the foot pressure dynamic regulation module receives the instructions, and the multiple independently controllable micro-motors drive the air bag array to adjust the inflation amount, changing the pressure distribution of different areas of the foot bottom;

[0075] The pressure feedback monitoring unit monitors the adjusted foot bottom pressure data in real time through the pressure sensors distributed on the surface of the air bag, and feeds back the data to the regulation strategy generation unit;

[0076] The regulation strategy generation unit judges the current pressure regulation effect in combination with the foot bottom pressure distribution standard and the personalized needs of the patient, and if the expected effect is not achieved, it generates pressure regulation instructions again and sends them to the pressure regulation execution unit, realizing closed-loop dynamic regulation of the foot bottom pressure distribution;

[0077] The device communication unit of the sleep aid equipment linkage control module obtains the results of the foot and ankle state analysis module, and simultaneously interacts with the sleep monitoring equipment and the environmental temperature control equipment to obtain relevant data;

[0078] The parameter matching unit matches the appropriate sleep aid equipment operating parameters, such as mattress hardness, environmental light intensity, and sound wave frequency, from the preset configuration table according to the foot and ankle recovery stage;

[0079] The linkage coordination unit coordinates the working order of each sleep aid equipment according to the determined parameters to avoid conflicts between the equipment;

[0080] The instruction execution unit sends control instructions to the sleep monitoring equipment and the environmental temperature control equipment according to the working order, so that these devices operate cooperatively to create a sleep environment suitable for the recovery of the foot and ankle for the patient;

[0081] The patient can view the real-time data collected by the foot and ankle data acquisition module, the analysis results of the foot and ankle state analysis module, the pressure distribution state of the foot pressure dynamic regulation module, and the equipment operating parameters of the sleep aid equipment linkage control module through the interface display unit of the user interaction module at any time;

[0082] During the system operation, the data feedback unit arranges the patient's operation records, foot and ankle data changes, and equipment control instruction execution conditions into chart form and feeds back to the patient on the interface, making it convenient for the patient to understand the working condition of the system and the recovery progress of the foot and ankle.

[0083] If the patient is not satisfied with the operation effect of the system or has new requirements, the parameters such as the foot and ankle recovery target, the pressure adjustment intensity, and the sleep preference can be modified again through the input processing unit, and the system will re-analyze and regulate according to the new parameters.

[0084] The above is only the preferred embodiment of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed as above with the preferred embodiment, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, without departing from the technical solution of the present application. Any modification, change, and modification of the above embodiments, equivalent changes, and modifications, which are based on the technical essence of the present application, still belong to the scope of the technical solution of the present application.

Claims

1. A sleep-aid linkage system based on ankle recovery monitoring, characterized in that, The system comprises: an ankle data acquisition module, an ankle state analysis module, a foot pressure dynamic regulation module, a sleep aid equipment linkage control module, and a user interaction module; The ankle data acquisition module is configured to acquire real-time biomechanical parameters of the ankle region through a multi-modal sensor, including plantar pressure distribution, ankle joint motion trajectory, foot temperature, and skin impedance data, and transmit the data to the ankle state analysis module through a wireless transmission protocol; The ankle state analysis module is configured to perform multi-dimensional fusion analysis on the collected data, combine a preset ankle recovery model and a fatigue threshold, determine the fatigue state and recovery stage of the user's ankle, and generate a dynamic regulation instruction; The ankle state analysis module comprises: A multi-source data fusion unit is configured to align the plantar pressure distribution, ankle joint motion trajectory, foot temperature, and skin impedance data by timestamp, and generate an ankle comprehensive state feature vector using a weighted fusion strategy, wherein the weight of the pressure data is 40%, the weight of the motion data is 30%, and the weights of the temperature and impedance are each 15%; An ankle recovery model calculation unit is configured to internally store an ankle recovery model trained based on biomechanical characteristics, and output a current fatigue level value after inputting the feature vector; A dynamic threshold judgment unit is configured to dynamically adjust the fatigue threshold range based on user historical data, and determine that the ankle is in an acute fatigue state when the fatigue level value exceeds 120% of the fatigue threshold in three consecutive samplings, otherwise, determine that the ankle is in a stable fatigue state; A recovery stage decision unit is configured to compare the fatigue level value with preset fatigue threshold intervals of the acute phase, transition phase, and stable phase to determine the recovery stage, and trigger a stage switching instruction when the value exceeds the upper limit of the fatigue threshold interval in three consecutive sampling periods, wherein the acute phase threshold interval is [0, 3], the transition phase threshold interval is (3, 6], and the stable phase threshold interval is (6, 10]; An instruction generation unit is configured to map the fatigue state and recovery stage to a dynamic regulation instruction, including an air bag pressure target value, a regulation rate, and a partition priority; The foot pressure dynamic regulation module is configured to adjust the plantar pressure distribution in real time through an air bag array driven by a micro motor according to the dynamic regulation instruction of the ankle state analysis module; The sleep aid equipment linkage control module is configured to interact data of the ankle state analysis result with a sleep monitoring device and an environmental temperature control device, and dynamically adjust the operating parameters of the sleep aid equipment, including mattress hardness, environmental light intensity, and sound wave frequency, according to the ankle recovery stage; The user interaction module is configured to provide a visual operation interface, support user-defined ankle recovery targets, pressure regulation intensity, and sleep preference parameters, and provide real-time feedback of system operation status and data logs.

2. The sleep-aid linkage system based on ankle recovery monitoring according to claim 1, wherein, The ankle data acquisition module comprises: A pressure sensor array is embedded in a foot pad in the form of a flexible circuit board to measure the pressure value of the sole at a fixed sampling interval; An inertial measurement unit is integrated in an ankle strap to capture the three-dimensional motion trajectory of the ankle joint through a three-axis accelerometer and a gyroscope to obtain the motion amplitude and frequency. Temperature-impedance composite sensor, distributed in the arch and heel area, synchronously measures the changes of skin surface temperature and impedance value, and is used for evaluating the local blood circulation state; The data preprocessing unit carries out noise reduction processing on the original signal, removes non-periodic interference, and eliminates motion artifacts.

3. The sleep-aid linkage system based on ankle recovery monitoring according to claim 1, wherein, The foot pressure dynamic regulation module comprises: The pressure regulation execution unit is composed of a plurality of independently controllable micro-motors driving an air bag array, and the micro-motors adjust the air bag inflation amount according to the dynamic regulation instruction of the ankle state analysis module, so as to change the pressure distribution of different regions of the foot bottom; The pressure feedback monitoring unit comprises a pressure sensor distributed on the surface of the air bag, which monitors the adjusted foot bottom pressure data in real time, and feeds back the data to the regulation strategy generation unit; The regulation strategy generation unit receives the data of the pressure feedback monitoring unit and the dynamic regulation instruction of the ankle state analysis module, combines the foot bottom pressure distribution standard and the user's individualized demand, judges the expected effect of the current pressure regulation, and when the expected effect does not meet the user's demand, the pressure regulation instruction is regenerated and sent to the pressure regulation execution unit.

4. The sleep-aid linkage system based on ankle recovery monitoring according to claim 1, wherein, The sleep aid device linkage control module comprises: The device communication unit adopts a unified communication protocol to establish a data interaction channel with the sleep monitoring device and the environment temperature control device, receives the user sleep data collected by the sleep monitoring device and the current running parameters of the environment temperature control device, and transmits the results of the ankle state analysis module to the sleep aid device, wherein the sleep aid device comprises the sleep monitoring device and the environment temperature control device; The parameter matching unit stores a parameter configuration table corresponding to different stages of ankle recovery, matches the recovery stage result obtained by the ankle state analysis module with the configuration table, and determines the device running parameters of the bed mattress hardness, the environment light intensity and the sound wave frequency; The linkage coordination unit coordinates the working order between the sleep aid devices according to the device running parameters determined by the parameter matching unit; The instruction execution unit sends control instructions to the sleep aid device according to the working order of the linkage coordination unit, so that the sleep monitoring device and the environment temperature control device are cooperatively operated according to the set device running parameters.

5. The sleep aiding linkage system based on ankle recovery monitoring according to claim 1, wherein, The user interaction module comprises: The interface display unit displays the real-time data collected by the ankle data acquisition module, the analysis results of the ankle state analysis module, the pressure distribution state of the foot pressure dynamic regulation module and the device running parameters of the sleep aid device linkage control module in a graphical interface; The input processing unit receives the ankle recovery target, pressure regulation intensity and sleep preference parameter information input by the user on the operation interface; The data feedback unit records the user operation, data logs in the system running process, including ankle data changes and device control instruction execution, and feeds back the data to the user in the form of a chart; The setting storage unit stores the user-defined parameter information in an encrypted manner, automatically calls the parameter information in the next system running, and regularly backs up the stored data to prevent data loss.

6. The sleep aiding linkage system based on ankle recovery monitoring according to claim 1, wherein, The implementation process of the neural network model of the ankle recovery model calculation unit is as follows: Input layer: the input layer receives the foot-ankle comprehensive state feature vector wherein, and the corresponding four-dimensional data of plantar pressure distribution, ankle joint motion trajectory, foot temperature and skin impedance are obtained as a four-dimensional vector after normalization wherein represents normalized pressure data, is motion data, is temperature data, is impedance data; First hidden layer: A fully connected feature transformation is performed on the input data. This involves weighted summation of the input data and the introduction of a non-linear transformation to extract representative features. The calculation formula for the fully connected feature transformation is as follows: Weight matrix This refers to the connection relationships and weights between the input layer and the first hidden layer. The weight matrix has 8 rows and 4 columns, corresponding to the four neurons of the four data classes in the input layer being connected to the eight neurons of the first hidden layer. Each element in the matrix... Represents the input layer The first hidden layer contains neurons. The weights of each neuron when transmitting signals The numbers represent the sequence numbers of the neurons in the first hidden layer, from 1 to 8. The input layer neurons are numbered from 1 to 4, and their biases are... It is a constant term set separately for each neuron in the first hidden layer, each Corresponding to the first hidden layer One neuron, It is an activation function and During the calculation process, when When the result is less than 0, the neuron outputs 0, and the first hidden layer outputs an 8-dimensional vector. ; The second hidden layer: processing the output of the first hidden layer, introducing an attention mechanism to perform weighted transformation to obtain feature representation, the attention mechanism is calculated by attention weight matrix wherein, is the attention weight matrix, which is used to measure the importance of each feature of the first hidden layer output to the calculation of the output of the second hidden layer neurons, the elements in the matrix represent the attention weight influence degree of the first hidden layer The first neuron to the second hidden layer The first neuron, the softmax function is used to convert the calculation result of Into a probability distribution form, so that each element in the obtained attention weight matrix The value is between 0 and 1, and the sum of all elements is 1, and the wherein represents the attention weight of the first hidden layer output to the second hidden layer The first neuron, the output of the second hidden layer is calculated wherein is the weight matrix of the second hidden layer, which is responsible for converting the 8-dimensional output of the first hidden layer into the 4-dimensional input of the second hidden layer, the matrix elements represent the weight value of the connection between the first hidden layer The first neuron and the second hidden layer The first neuron, is the bias of the second hidden layer, each Corresponds to the first neuron of the second hidden layer Symbol represents the multiplication of the attention weight matrix And the corresponding elements of , in this way, the data is weighted by using the attention weight, and the second hidden layer ; Output layer: Calculates the final ankle fatigue level value based on the features extracted from the hidden layer. ,in, The weight vector and , This indicates that the weight vector Transpose and Perform dot product operation, weight vector Each element in Indicates the second hidden layer The contribution weight of each neuron to the final fatigue level output determines the degree of influence of the output of the corresponding neuron in the second hidden layer on the final result. The bias term... It is the bias value of the output layer, used to adjust the calculation results and Given the set of real numbers, the calculated values ​​will be... The values ​​are mapped to the interval [0, 10] to represent the fatigue state of the foot and ankle.

7. The sleep aiding linkage system based on ankle recovery monitoring according to claim 1, wherein, The dynamic threshold judgment unit calculates the fatigue level value based on the neural network model, and combines it with a dynamically adjusted fatigue threshold. It sets an initial fatigue threshold as follows: Record the user's historical fatigue level numerical sequence ,in Indicates the first The fatigue level values ​​from the previous sample were used to calculate the mean of the historical data. and standard deviation Dynamically adjusted fatigue threshold ,in, and To adjust the coefficient, Used to control the degree of influence of the mean on the fatigue threshold. Used to control the degree of influence of standard deviation on fatigue threshold, and , When fatigue scores are in 3 consecutive samples All exceeded If the condition is met, the ankle is considered to be in an acute state of fatigue; otherwise, the ankle is considered to be in a stable state of fatigue.

Images