An internet-based remote rehabilitation comprehensive service system and method

Abstract

This application provides a comprehensive service system and method for remote rehabilitation based on the Internet, relating to the field of communication technology. This application acquires historical movement trajectory data and initial physiological parameters of elderly patients; based on this data and parameters, it simulates fall risk prediction results for elderly patients under candidate training programs corresponding to different training intensities; according to a preset fall risk assessment index system, it obtains an adjusted training program; it acquires real-time movement trajectory data and training physiological parameters of elderly patients during training according to the adjusted training program, generating training effect analysis information and risk intervention suggestion information; based on historical movement trajectory data, initial physiological parameters, fall risk prediction results, adjusted training program, real-time movement trajectory data, training physiological parameters, training effect analysis information, and risk intervention suggestion information, it realizes personalized and safe training guidance and closed-loop management of rehabilitation records for elderly patients during remote rehabilitation.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a comprehensive service system and method for remote rehabilitation based on the Internet. Background Technology

[0002] With the arrival of an aging society, the demand for comprehensive internet-based remote rehabilitation services for personalized home training and fall risk prevention among the elderly is becoming increasingly urgent. When elderly patients conduct rehabilitation training at home, they not only need scientific and personalized exercise guidance, but also urgently need to identify and intervene in advance the risk of falls and other emergencies during the training process.

[0003] Currently, some mainstream technologies attempt to collect acceleration and angular velocity information of the elderly during training in real time by deploying wearable sensor devices, and then analyze the collected posture data online using a cloud computing platform. Once abnormal swaying or near-fall movement patterns are detected, the system triggers an immediate alarm and notifies family members or medical personnel to intervene. However, existing solutions have certain shortcomings. For example, they rely solely on real-time sensor data for post-event or critical judgments, lacking the ability to simulate and extrapolate the potential fall risks of different training movements before training begins. Therefore, they cannot proactively avoid high-risk movement combinations before the program is implemented. Furthermore, because they do not integrate historical motor performance and basic physiological state for comprehensive modeling, the system struggles to predict individual body response trends under different intensities of stimulation, and cannot achieve pre-emptive optimization and personalized adaptation of training plans. Summary of the Invention

[0004] The purpose of this application is to provide a comprehensive service system and method for remote rehabilitation based on the Internet, in order to solve the problems in the existing technology, such as the lack of simulation and extrapolation of fall risk and the inability to achieve pre-emptive optimization and personalized adaptation of training plans.

[0005] To address the aforementioned technical problems, in a first aspect, this application provides a comprehensive service method for remote rehabilitation based on the Internet, comprising:

[0006] Acquire historical movement trajectory data and initial physiological parameters of elderly patients;

[0007] Based on the historical movement trajectory data and the initial physiological parameters, the fall risk simulation results of the elderly patient under candidate training programs corresponding to different training intensities are simulated through the Internet remote rehabilitation integrated service platform.

[0008] Based on the preset fall risk assessment index system, the risk level of the fall risk simulation results is determined, and the candidate training schemes corresponding to different risk levels are adjusted to obtain the adjusted training scheme.

[0009] The system acquires real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compares the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generates training effect analysis information and risk intervention suggestion information.

[0010] Based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, the rehabilitation records of the elderly patients are updated to achieve comprehensive remote rehabilitation services.

[0011] Optionally, based on the historical movement trajectory data and the initial physiological parameters, a remote rehabilitation service platform is used to simulate the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities, including:

[0012] Motion feature parameters are extracted from the historical motion trajectory data, and physiological feature parameters are extracted from the initial physiological parameters. The motion feature parameters include stride length, stride frequency, turning angle, and center of gravity offset. The physiological feature parameters include muscle strength value, balance ability score, movement coordination index, and reaction speed value.

[0013] From the motor characteristic parameters and the physiological characteristic parameters, parameter pairs related to fall risk are selected, and the correlation coefficient of each parameter pair is calculated to obtain multiple correlation values. The parameter pairs include stride length and muscle strength value, center of gravity offset and balance ability score.

[0014] Based on a preset training intensity grading standard, candidate training schemes corresponding to different training intensities are generated. The candidate training schemes include action type, action amplitude, and number of action repetitions.

[0015] Based on the training intensity, motion characteristic parameters, physiological characteristic parameters, and correlation values ​​corresponding to each candidate training program, the elderly patient is simulated to execute each candidate training program through an Internet-based remote rehabilitation integrated service platform, combined with a biomechanical model, to obtain the fall risk prediction results corresponding to each candidate training program. The fall risk prediction results include balance stabilization time, maximum center of gravity offset distance, and movement completion deviation.

[0016] Optionally, based on a preset fall risk assessment index system, the risk level of the fall risk simulation results is determined, and the candidate training schemes corresponding to different risk levels are adjusted to obtain an adjusted training scheme, including:

[0017] The assessment indicators and corresponding risk reference ranges are extracted from the preset fall risk assessment indicator system. The assessment indicators include balance ability indicators, muscle strength indicators, motor coordination indicators and reaction speed indicators. The risk reference ranges include safety reference range, warning reference range and danger reference range.

[0018] Evaluation index values ​​are extracted from the results of various fall risk simulations. These evaluation index values ​​include balance ability index value, muscle strength index value, motor coordination index value, and reaction speed index value.

[0019] By comparing the assessment index values ​​with the corresponding risk reference ranges, risk sub-levels for balance ability, muscle strength, motor coordination, and reaction speed are obtained.

[0020] Based on the balance ability risk sub-level, the muscle strength risk sub-level, the motor coordination risk sub-level, and the reaction speed risk sub-level, a comprehensive risk level is calculated, which includes low risk level, medium risk level, and high risk level.

[0021] Based on the comprehensive risk level, the corresponding candidate training schemes are adjusted to obtain the adjusted training scheme.

[0022] Optionally, based on the comprehensive risk level, the corresponding candidate training scheme is adjusted to obtain the adjusted training scheme, including:

[0023] When the overall risk level is high, the corresponding candidate training program is adjusted to obtain the adjusted training program. The adjustment operations include adjusting the movement amplitude to a preset first proportion, reducing the number of repetitions of the movement to a preset second proportion, and increasing the preset auxiliary support movement types and implementation timing.

[0024] When the overall risk level is medium risk, the corresponding candidate training scheme is adjusted to obtain the adjusted training scheme. The adjustment steps include increasing the time interval and prompting method of the preset action rhythm prompts.

[0025] When the overall risk level is low, the corresponding candidate training scheme will be used as the adjusted training scheme.

[0026] Optionally, the real-time motion trajectory data and the training physiological parameters are compared with preset rehabilitation indicators to generate training effect analysis information and risk intervention suggestion information, including:

[0027] Multiple real-time motion feature parameters are extracted from the real-time motion trajectory data, and multiple real-time physiological feature parameters are extracted from the training physiological parameters. Based on preset rehabilitation indicators, the standard range of motion trajectory and normal range of physiological parameters corresponding to the adjusted training plan are determined.

[0028] Each real-time motion feature parameter is compared with the standard range of the motion trajectory to obtain multiple motion comparison results. All motion comparison results are integrated to obtain the motion trajectory difference result. Each real-time physiological feature parameter is compared with the normal range of the physiological parameters to obtain multiple physiological comparison results. All physiological comparison results are integrated to obtain the physiological parameter difference result.

[0029] The differences in motion trajectories and physiological parameters are classified and labeled to generate training effect analysis information and risk intervention suggestions.

[0030] Optionally, the differences in motion trajectories and physiological parameters are classified and labeled to generate training effect analysis information and risk intervention recommendations, including:

[0031] Calculate the motion deviation value of each real-time motion feature parameter and the corresponding standard range of motion trajectory in the motion trajectory difference result. Mark the real-time motion feature parameter whose motion deviation value is within the preset allowable range as a motion standard item, and mark the real-time motion feature parameter whose motion deviation value exceeds the preset allowable range as a motion deviation item.

[0032] The physiological deviation values ​​of each real-time physiological feature parameter and its corresponding normal range in the physiological parameter difference results are calculated. Real-time physiological feature parameters whose physiological deviation values ​​are within the preset allowable range are marked as physiological standard items, and real-time physiological feature parameters whose physiological deviation values ​​exceed the preset allowable range are marked as physiological deviation items.

[0033] The exercise achievement items, exercise deviation items, physiological achievement items, and physiological deviation items are integrated to form training effect analysis information;

[0034] Based on the motor deviation items and the physiological deviation items, risk intervention recommendation information is generated.

[0035] Optionally, risk intervention recommendation information is generated based on the motor deviation item and the physiological deviation item, including:

[0036] Based on the step length deviation, step frequency deviation, turning angle deviation, and center of gravity offset deviation values ​​in the motion deviation items, corresponding suggestions for step length adjustment range, step frequency rhythm correction, turning speed control, and center of gravity adjustment direction are generated.

[0037] Based on the deviation values ​​of muscle strength, balance ability score, movement coordination index, and reaction speed in the physiological deviation items, corresponding suggestions for increasing or decreasing local training intensity, adding balance assistance movements, decomposing movement exercises, and increasing reaction training frequency are generated.

[0038] The suggestions for adjusting stride length, correcting stride frequency, controlling turning speed, adjusting center of gravity, increasing or decreasing local training intensity, adding balance-assisted movements, decomposing movement exercises, and increasing reaction training frequency are integrated to form risk intervention suggestion information.

[0039] Secondly, this application provides a comprehensive service system for remote rehabilitation based on the Internet, including:

[0040] The acquisition module is used to acquire historical movement trajectory data and initial physiological parameters of elderly patients;

[0041] The simulation module is used to simulate the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities, based on the historical movement trajectory data and the initial physiological parameters, through the Internet remote rehabilitation integrated service platform.

[0042] The adjustment module is used to determine the risk level of the fall risk simulation result according to the preset fall risk assessment index system, so as to adjust the candidate training schemes corresponding to different risk levels and obtain the adjusted training scheme.

[0043] The comparison module is used to acquire real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compare the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generate training effect analysis information and risk intervention suggestion information.

[0044] The update module is used to update the rehabilitation records of elderly patients based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, so as to realize comprehensive remote rehabilitation services.

[0045] Thirdly, this application provides an electronic device, comprising:

[0046] Memory, used to store computer programs;

[0047] A processor, configured to execute the computer program to implement the steps of the comprehensive service method for Internet-based remote rehabilitation as described in the first aspect above.

[0048] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the comprehensive service method for Internet-based remote rehabilitation as described in the first aspect above.

[0049] This application provides a comprehensive service method for remote rehabilitation based on the Internet, which involves: acquiring historical movement trajectory data and initial physiological parameters of elderly patients; simulating fall risk prediction results of the elderly patients under candidate training programs corresponding to different training intensities through an Internet-based remote rehabilitation service platform based on the historical movement trajectory data and initial physiological parameters; determining the risk level of the fall risk prediction results according to a preset fall risk assessment index system, and adjusting the candidate training programs corresponding to different risk levels to obtain an adjusted training program; acquiring real-time movement trajectory data and training physiological parameters of the elderly patients during training according to the adjusted training program, comparing the real-time movement trajectory data and training physiological parameters with preset rehabilitation indicators to generate training effect analysis information and risk intervention suggestion information; and updating the rehabilitation records of the elderly patients based on the historical movement trajectory data, initial physiological parameters, fall risk prediction results, adjusted training programs, real-time movement trajectory data, training physiological parameters, training effect analysis information, and risk intervention suggestion information to achieve comprehensive remote rehabilitation services. By acquiring historical movement trajectory data and initial physiological parameters of elderly patients, a data foundation is provided for subsequent personalized modeling and risk prediction, enhancing a systematic understanding of the physical condition of elderly patients. It enables proactive simulation of potential safety risks before training implementation, overcoming the limitations of relying solely on real-time monitoring for post-event response and placing risk prevention at the forefront. It achieves personalized adaptation and dynamic optimization of training programs, avoiding high-risk movement combinations and improving the safety and individual suitability of rehabilitation training. It enables closed-loop monitoring and multi-dimensional evaluation of the training execution process, allowing for timely detection of deviations and provision of intervention guidance, enhancing the real-time nature and intelligence of remote rehabilitation services. It achieves continuous accumulation and structured management of data throughout the rehabilitation process, providing complete data support for long-term rehabilitation trend analysis and program iteration, forming a traceable and optimizable closed-loop remote rehabilitation service.

[0050] Furthermore, multiple real-time motion feature parameters are extracted from real-time motion trajectory data, and multiple real-time physiological feature parameters are extracted from training physiological parameters. These are combined with preset rehabilitation indicators to determine and adjust the standard range of motion trajectory and the normal range of physiological parameters corresponding to the training plan. The results of motion trajectory difference and physiological parameter difference are integrated to ultimately generate training effect analysis information and risk intervention suggestions. This process achieves a refined and structured assessment of training execution status, transforming multi-source data differences into interpretable analytical results and actionable intervention suggestions. It solves the problems of delayed intervention and broad guidance caused by the lack of multi-dimensional data fusion assessment, enabling accurate identification of potential risks and rehabilitation progress during training. This enhances the depth and granularity of remote rehabilitation services in dynamic monitoring and intelligent feedback, and strengthens the scientific rigor and safety of home-based rehabilitation. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating a comprehensive service method for remote rehabilitation based on the Internet, provided as an embodiment of this application;

[0053] Figure 2 A schematic diagram illustrating a specific implementation of a comprehensive service method for remote rehabilitation based on the Internet, provided in this application embodiment;

[0054] Figure 3 A schematic diagram of the structure of a comprehensive service system for remote rehabilitation based on the Internet provided in this application embodiment; Detailed Implementation

[0055] Addressing the urgent need for personalized training and proactive fall risk prevention in home-based rehabilitation for the elderly, existing mainstream solutions, while capable of real-time monitoring of posture data and triggering critical alarms via wearable devices, remain limited to reactive or critical responses. They cannot predict potential risks associated with different solutions before training begins and lack comprehensive modeling capabilities of individual historical motor performance and initial physiological states, hindering proactive optimization and personalized adaptation of training programs. This application proposes a comprehensive service system and method for remote rehabilitation based on the internet. By comprehensively acquiring historical motor trajectory data and initial physiological parameters of elderly patients, and utilizing a comprehensive remote rehabilitation service platform... The system simulates and rehearses fall risks for various candidate training programs, and then dynamically adjusts the training programs to avoid high-risk movements, thus shifting from passive response to proactive prevention. During the training process, real-time motion trajectory data and training physiological parameters are continuously collected, and training effect analysis and risk intervention suggestions are generated by combining them with preset rehabilitation indicators. All multi-source data throughout the process are uniformly incorporated into the rehabilitation record for dynamic updates, thereby constructing a closed-loop service system that solves the shortcomings of existing technologies in terms of risk predictability, program personalization, and management continuity, and improves the safety and intelligence level of Internet-based remote rehabilitation services in the context of elderly people living at home.

[0056] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The core of this application is to provide a comprehensive service method for remote rehabilitation based on the Internet. A flowchart of one specific implementation method is shown below. Figure 1 As shown, the method includes:

[0058] Step 101: Obtain historical movement trajectory data and initial physiological parameters of elderly patients.

[0059] In this step, "elderly patients" refers to the elderly population who require remote rehabilitation training. Historical movement trajectory data refers to trajectory data, including movement paths and changes in motion, recorded by motion acquisition devices during past exercise sessions. Initial physiological parameters refer to parameters reflecting the body's physiological state collected by physiological monitoring devices before the start of this rehabilitation training.

[0060] In this embodiment of the application, the movement trajectory data of elderly patients over a period of time is collected as historical movement trajectory data, and the physiological parameters of elderly patients when they are not currently training are collected as initial physiological parameters. These data will be used for subsequent training program simulation.

[0061] Step 102: Based on the historical movement trajectory data and the initial physiological parameters, simulate the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities through the Internet remote rehabilitation integrated service platform.

[0062] In this step, the Internet-based remote rehabilitation service platform refers to a comprehensive platform built using Internet technology to provide rehabilitation training-related services. Training intensity refers to indicators reflecting the amount of training, such as the difficulty level of movements and the number of repetitions. Candidate training programs refer to pre-designed rehabilitation training programs based on different training intensities, available for elderly patients to choose from. Fall risk simulation results refer to the risk-related outcomes of simulated falls when elderly patients perform candidate training programs.

[0063] Step 103: Based on the preset fall risk assessment index system, determine the risk level of the fall risk simulation results, so as to adjust the candidate training schemes corresponding to different risk levels and obtain the adjusted training scheme.

[0064] In this step, the pre-set fall risk assessment index system refers to a series of pre-defined indicators and corresponding reference ranges used to assess fall risk. The risk level refers to the classification based on the fall risk rehearsal results, reflecting the degree of fall risk. The adjusted training program refers to the rehabilitation training program suitable for elderly patients obtained by adjusting candidate training programs according to the risk level.

[0065] Step 104: Obtain real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compare the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generate training effect analysis information and risk intervention suggestion information.

[0066] In this step, real-time motion trajectory data refers to the trajectory data recorded in real time by motion acquisition devices during the implementation of the adjusted training program by the elderly patient. Training physiological parameters refer to the physiological parameters collected in real time by physiological monitoring devices during the training process. Pre-set rehabilitation indicators refer to the pre-defined indicators and standard ranges used to evaluate the effectiveness of rehabilitation training. Training effect analysis information refers to the information obtained after analyzing the training effect. Risk intervention recommendation information refers to intervention recommendations proposed for potential risks in the training.

[0067] Step 105: Based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, update the rehabilitation record of the elderly patient to realize comprehensive remote rehabilitation services.

[0068] In this step, the rehabilitation record refers to the file that records relevant information about the elderly patient's rehabilitation training. Comprehensive remote rehabilitation services refer to all-round rehabilitation services provided to elderly patients remotely, including training program development, training process monitoring, and effectiveness evaluation.

[0069] In this embodiment, historical movement trajectory data, initial physiological parameters, fall risk simulation results, adjusted training plans, real-time movement trajectory data, training physiological parameters, training effect analysis information, and risk intervention suggestions are integrated and updated into the rehabilitation records of elderly patients. By continuously updating the records, the entire process of rehabilitation training for elderly patients can be tracked and managed, thereby providing comprehensive remote rehabilitation services.

[0070] This application embodiment acquires historical and real-time data of elderly patients, simulates the fall risk of the training program, assesses the risk level and adjusts the program, monitors the training process and generates analysis and suggestions, and finally updates the rehabilitation record. This realizes the personalization, precision and full-process of remote rehabilitation services, and improves the safety and effectiveness of remote rehabilitation training for elderly patients.

[0071] This application provides a specific embodiment. Step 102 involves simulating the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities, based on the historical movement trajectory data and the initial physiological parameters, through an internet-based remote rehabilitation integrated service platform. This specifically includes the following steps:

[0072] Step 201: Extract motion feature parameters from the historical motion trajectory data and extract physiological feature parameters from the initial physiological parameters. The motion feature parameters include stride length, stride frequency, turning angle, and center of gravity offset. The physiological feature parameters include muscle strength value, balance ability score, movement coordination index, and reaction speed value.

[0073] In this step, motion characteristic parameters refer to parameters reflecting motion characteristics extracted from historical motion trajectory data. Physiological characteristic parameters refer to parameters reflecting physiological state extracted from initial physiological parameters.

[0074] In this embodiment, historical motion trajectory data is analyzed. Step length is obtained by measuring the distance between the two feet during walking, step frequency is obtained by counting the number of steps taken per unit time, turning angle is obtained by recording the angle of body rotation when turning, and center of gravity offset is obtained by calculating the distance of the body's center of gravity from the stable point, thereby extracting motion characteristic parameters. Initial physiological parameters are analyzed. Muscle strength value is obtained by measuring the force generated by muscle contraction, balance ability score is obtained through balance test, movement coordination index is obtained through movement coordination assessment, and reaction speed value is obtained through reaction test, thereby extracting physiological characteristic parameters.

[0075] Step 202: Select parameter pairs related to fall risk from the motion characteristic parameters and the physiological characteristic parameters, calculate the correlation coefficient of each parameter pair, and obtain multiple correlation values. The parameter pairs include stride length and muscle strength value, center of gravity offset and balance ability score.

[0076] In this step, a parameter pair refers to a pair of parameters consisting of a motor characteristic parameter and a physiological characteristic parameter. The correlation coefficient is a numerical value that measures the degree of correlation between two parameters. Step length and muscle strength value refers to a parameter pair consisting of step length and muscle strength value. Center of gravity shift and balance ability score refers to a parameter pair consisting of center of gravity shift and balance ability score. The correlation value refers to the specific numerical value of the calculated correlation coefficient.

[0077] In this embodiment, parameter pairs related to fall risk are selected based on clinical experience, namely stride length and muscle strength values, and center of gravity shift and balance ability score; for each parameter pair, a correlation coefficient is calculated using a correlation analysis method, and the calculation formula is as follows: , where x and y are the two types of parameters in the parameter pair, n is the number of data, and Σ is the summation symbol, resulting in multiple correlation values, which are used to reflect the degree of correlation between parameters.

[0078] Step 203: Based on the preset training intensity grading standard, generate candidate training schemes corresponding to different training intensities. The candidate training schemes include action type, action amplitude, and number of action repetitions.

[0079] In this step, the preset training intensity grading standard refers to the pre-defined criteria for classifying training intensity levels. Movement type refers to the specific types of movements in rehabilitation training. Movement amplitude refers to the range of motion during movement execution. Movement repetition count refers to the number of times the movement is performed. Candidate training programs refer to training programs generated based on different training intensities, offering a selection of options.

[0080] In this embodiment of the application, a corresponding candidate training scheme is generated for each level based on a preset training intensity grading standard; the action type of each scheme is determined, the action amplitude is set according to the intensity level, and the number of repetitions of the action is set, thereby obtaining candidate training schemes corresponding to different training intensities.

[0081] Step 204: Based on the training intensity, the motion characteristic parameters, the physiological characteristic parameters, and the correlation values ​​corresponding to each candidate training program, the elderly patient is simulated to perform each candidate training program through the Internet remote rehabilitation integrated service platform and in combination with the biomechanical model, so as to obtain the fall risk pre-simulation results corresponding to each candidate training program. The fall risk pre-simulation results include balance stabilization time, maximum center of gravity offset distance, and movement completion deviation.

[0082] In this step, the biomechanical model refers to the model used to simulate the biomechanical characteristics of human movement. Balance stabilization time refers to the duration of maintaining a balanced state. Maximum center of gravity shift distance refers to the maximum distance the center of gravity shifts. Movement completion deviation refers to the degree of deviation between the actual movement and the standard movement. Fall risk simulation results refer to the results reflecting fall risk obtained after simulating the execution of the training program.

[0083] In this embodiment, the training intensity, motion characteristic parameters, physiological characteristic parameters, and related values ​​corresponding to each candidate training program are input into the Internet-based remote rehabilitation integrated service platform. The platform calls a biomechanical model to simulate elderly patients performing each candidate training program. During the simulation, the duration from the start of the movement to the occurrence of an imbalance state is recorded as the balance stabilization time, the maximum distance of the center of gravity deviating from the initial position is measured as the maximum offset distance of the center of gravity, and the difference ratio between the actual movement and the standard movement is calculated as the movement completion deviation. These data are integrated to obtain the fall risk simulation results corresponding to each candidate training program.

[0084] This application embodiment extracts motion and physiological characteristic parameters, calculates the correlation coefficient of parameter pairs, generates candidate training programs, and combines them with biomechanical models to simulate fall risk prediction results. This enables risk prediction of personalized training programs for elderly patients, provides accurate reference for subsequent program adjustments, and improves the safety and relevance of remote rehabilitation training.

[0085] For example, after analyzing the historical movement trajectory data of elderly patient A, the following movement characteristic parameters were extracted: stride length 0.5m, cadence 75 steps / minute, turning angle 85 degrees, and center of gravity offset 4cm. After analyzing the initial physiological parameters, the following physiological characteristic parameters were extracted: muscle strength 280N, balance score 65 points, movement coordination index 0.7, and reaction speed 0.6 seconds. Step length and muscle strength, and center of gravity shift and balance score were selected as parameter pairs. Five historical data sets for step length and muscle strength were used: step length x = 0.4m, 0.45m, 0.5m, 0.55m, 0.6m; muscle strength y = 250N, 260N, 280N, 290N, 300N. The calculated values ​​were: Σx = 2.5m, Σy = 1380N, Σxy = 0.4×250 + 0.45×260 + 0.5×280 + 0.55×290 + 0.6×300 = 696.5, Σx² = 0.4² + 0.45² + 0.5² + 0.55² + 0.6² = 1.275, Σy² = 250² + 260² + 280² + 290² + 300² = 379000. The correlation coefficient was... To obtain the correlation coefficient The five sets of historical data for center of gravity offset and balance ability score are as follows: center of gravity offset x = 3cm, 3.5cm, 4cm, 4.5cm, 5cm, balance ability score y = 70, 68, 65, 63, 60. Calculations yield Σx = 20cm, Σy = 326, Σxy = 3×70 + 3.5×68 + 4×65 + 4.5×63 + 5×60 = 1287.5, Σx² = 3² + (3.5)² + 4² + (4.5)² + 5² = 82.5, Σy² = 70² + 68² + 65² + 63² + 60² = 21318. Substituting these values ​​into the formula yields... Based on a preset training intensity grading standard, three candidate training programs were generated: low intensity (walking motion, stride length 0.4m, repetitions 10), medium intensity (walking + turning motion, stride length 0.5m, repetitions 15), and high intensity (fast walking + turning motion, stride length 0.6m, repetitions 20). After inputting the above data into the platform and simulating using a biomechanical model, the fall risk prediction results for the low-intensity program were: balance stabilization time 28 seconds, maximum center of gravity shift distance 3cm, and motion completion deviation 4%; for the medium intensity program, 24 seconds, 5cm, and 7%; and for the high intensity program, 19 seconds, 7cm, and 10%.

[0086] This application provides a specific embodiment. Step 103 involves determining the risk level of the fall risk simulation result based on a preset fall risk assessment index system, and adjusting the candidate training schemes corresponding to different risk levels to obtain an adjusted training scheme. This specifically includes the following steps:

[0087] Step 301: Extract assessment indicators and corresponding risk reference ranges from the preset fall risk assessment indicator system. The assessment indicators include balance ability indicators, muscle strength indicators, motor coordination indicators, and reaction speed indicators. The risk reference ranges include safety reference ranges, warning reference ranges, and danger reference ranges.

[0088] In this step, the assessment indicators refer to the specific indicators used to assess the risk of falls. The risk reference range refers to the range within which the assessment indicators correspond to a level of risk. The balance ability indicator refers to the indicator used to assess balance ability. The muscle strength indicator refers to the indicator used to assess muscle strength. The motor coordination indicator refers to the indicator used to assess motor coordination. The reaction speed indicator refers to the indicator used to assess reaction speed. The safety reference range is the numerical range within which the indicator is in a safe state. The warning reference range is the numerical range within which the indicator is in a warning state. The danger reference range is the numerical range within which the indicator is in a dangerous state.

[0089] In this embodiment of the application, assessment indicators and corresponding risk reference ranges are retrieved from a preset fall risk assessment indicator system. Among them, balance ability indicators, muscle strength indicators, motor coordination indicators and reaction speed indicators correspond to safety reference range, warning reference range and danger reference range, respectively. Each reference range is divided into different intervals according to the characteristics of the indicators.

[0090] Step 302: Extract assessment index values ​​from each fall risk simulation result. The assessment index values ​​include balance ability index value, muscle strength index value, movement coordination index value, and reaction speed index value.

[0091] In this step, the assessment index value refers to the specific numerical value of the assessment index. The balance ability index value refers to the specific numerical value of the balance ability index. The muscle strength index value refers to the specific numerical value of the muscle strength index. The motor coordination index value refers to the specific numerical value of the motor coordination index. The reaction speed index value refers to the specific numerical value of the reaction speed index.

[0092] In this embodiment of the application, corresponding evaluation index values ​​are extracted from each fall risk simulation result, including balance ability index value, muscle strength index value, movement coordination index value and reaction speed index value corresponding to each candidate training program.

[0093] Step 303: Compare the assessment index values ​​with the corresponding risk reference ranges to obtain the risk sub-levels of balance ability, muscle strength, motor coordination, and reaction speed.

[0094] In this step, the balance ability risk sub-level refers to the risk sub-level determined based on the balance ability index value. The muscle strength risk sub-level refers to the risk sub-level determined based on the muscle strength index value. The motor coordination risk sub-level refers to the risk sub-level determined based on the motor coordination index value. The reaction speed risk sub-level refers to the risk sub-level determined based on the reaction speed index value.

[0095] In this embodiment of the application, the values ​​of each evaluation index are compared with the corresponding risk reference range. If the evaluation index value is within the safe reference range, the corresponding risk sub-level is the safe level; if it is within the warning reference range, the corresponding risk sub-level is the warning level; if it is within the dangerous reference range, the corresponding risk sub-level is the dangerous level, thus obtaining the risk sub-level of each index.

[0096] Step 304: Calculate the comprehensive risk level based on the balance ability risk sub-level, the muscle strength risk sub-level, the movement coordination risk sub-level, and the reaction speed risk sub-level. The comprehensive risk level includes low risk level, medium risk level, and high risk level.

[0097] In this step, the overall risk level refers to the combined risk level obtained by integrating all risk sub-levels. A low risk level indicates a relatively low overall risk. A medium risk level indicates a moderate overall risk. A high risk level indicates a relatively high overall risk.

[0098] In this embodiment, each risk sub-level is assigned a corresponding score: a lower score for a safe level, a medium score for a warning level, and a higher score for a dangerous level. Based on each risk sub-level and preset weights—balance ability index weight, muscle strength index weight, motor coordination index weight, and reaction speed index weight—the comprehensive risk level is calculated as follows: Balance Ability Risk Sub-level × Balance Ability Index Weight + Muscle Strength Risk Sub-level × Muscle Strength Index Weight + Motor Coordination Risk Sub-level × Motor Coordination Index Weight + Reaction Speed ​​Risk Sub-level × Reaction Speed ​​Index Weight. The comprehensive risk level is then determined based on the calculation results: a low risk level falls within the lower range, a medium risk level within the middle range, and a high risk level within the higher range.

[0099] Step 305: Adjust the corresponding candidate training scheme according to the comprehensive risk level to obtain the adjusted training scheme.

[0100] In this embodiment, the candidate training schemes are adjusted according to the comprehensive risk level. The candidate training schemes corresponding to the low risk level are adjusted by a small amount, the schemes corresponding to the medium risk level are adjusted moderately, and the schemes corresponding to the high risk level are adjusted by a large amount, thereby obtaining the adjusted training scheme.

[0101] This application embodiment determines the risk level of the fall risk simulation results through a preset evaluation index system, and adjusts the candidate training program accordingly, thereby achieving standardization of risk assessment and personalized adaptation of training programs, and improving the safety and pertinence of remote rehabilitation training.

[0102] This application provides a specific embodiment. Step 305 involves adjusting the corresponding candidate training scheme according to the comprehensive risk level to obtain the adjusted training scheme, which specifically includes the following steps:

[0103] Step 311: When the overall risk level is high risk level, adjust the corresponding candidate training plan to obtain the adjusted training plan. The adjustment operation includes adjusting the movement amplitude to a preset first proportion, reducing the number of repetitions of the movement to a preset second proportion, and adding preset auxiliary support movement types and implementation timing.

[0104] In this step, the preset first ratio refers to the pre-set adjustment ratio of the movement amplitude. The preset second ratio refers to the pre-set reduction ratio of the number of repetitions of the movement. The preset auxiliary support movement type refers to the pre-set type of movement used for auxiliary support. The implementation timing refers to the point in time when the auxiliary support movement is executed.

[0105] In this embodiment of the application, when the overall risk level is high risk level, for the corresponding candidate training scheme, the movement amplitude is adjusted according to a preset first ratio, that is, the original movement amplitude is multiplied by the preset first ratio to obtain the adjusted movement amplitude; the number of movement repetitions is reduced according to a preset second ratio, that is, the original number of movement repetitions is multiplied by the preset second ratio to obtain the adjusted number of movement repetitions; at the same time, preset auxiliary support movement types are added, and the timing of implementation of these movements in the training process is clarified. These adjusted contents are integrated to obtain the adjusted training scheme.

[0106] Step 312: When the overall risk level is medium risk, adjust the corresponding candidate training scheme to obtain the adjusted training scheme. The adjustment steps include increasing the time interval and prompting method of the preset action rhythm prompts.

[0107] In this step, the adjustment step refers to the specific operations of adjusting the candidate training scheme. The preset movement rhythm cue refers to the pre-set signal used to indicate the movement rhythm. The time interval refers to the length of time between two movement rhythm cues. The cue method refers to the form in which the movement rhythm cues are delivered.

[0108] In this embodiment of the application, when the overall risk level is medium risk, an adjustment step is performed for the corresponding candidate training scheme, namely, increasing the time interval between preset action rhythm prompts to make the time between two prompts longer; at the same time, the prompting method is increased, and these adjusted contents are integrated to obtain the adjusted training scheme.

[0109] Step 313: When the overall risk level is low, the corresponding candidate training scheme is used as the adjusted training scheme.

[0110] In this embodiment of the application, when the overall risk level is low, since the risk is low, there is no need to adjust the corresponding candidate training scheme. The candidate training scheme is directly used as the adjusted training scheme to maintain the continuity and effectiveness of the training.

[0111] This application embodiment makes targeted adjustments to candidate training programs based on different comprehensive risk levels, making the adjusted training programs more suitable for the risk status of elderly patients, thereby improving the safety and applicability of the training.

[0112] This application provides a specific embodiment, such as Figure 2 As shown, step 104 compares the real-time motion trajectory data and the training physiological parameters with preset rehabilitation indicators to generate training effect analysis information and risk intervention suggestion information, specifically including the following steps:

[0113] Step 401: Extract multiple real-time motion feature parameters from the real-time motion trajectory data, and extract multiple real-time physiological feature parameters from the training physiological parameters. Based on preset rehabilitation indicators, determine the standard range of motion trajectory and the normal range of physiological parameters corresponding to the adjusted training plan.

[0114] In this step, real-time motion characteristic parameters refer to parameters extracted from real-time motion trajectory data that reflect the characteristics of real-time motion. Real-time physiological characteristic parameters refer to parameters extracted from training physiological parameters that reflect the real-time physiological state. The standard range of motion trajectory refers to the standard numerical range of the motion trajectory corresponding to the adjusted training plan. The normal range of physiological parameters refers to the normal numerical range of the physiological parameters corresponding to the adjusted training plan.

[0115] In this embodiment, the real-time motion trajectory data collected during training of elderly patients according to the adjusted training plan is analyzed to extract multiple real-time motion feature parameters; the training physiological parameters collected during the training process are analyzed to extract multiple real-time physiological feature parameters; and the corresponding standard range of motion trajectory and normal range of physiological parameters are determined according to the content of the preset rehabilitation indicators that matches the adjusted training plan.

[0116] Step 402: Compare each real-time motion feature parameter with the standard range of the motion trajectory to obtain multiple motion comparison results. Integrate all motion comparison results to obtain motion trajectory difference results. Compare each real-time physiological feature parameter with the normal range of the physiological parameters to obtain multiple physiological comparison results. Integrate all physiological comparison results to obtain physiological parameter difference results.

[0117] In this step, the motion comparison result refers to the result obtained by comparing a single real-time motion feature parameter with the standard range of motion trajectory. The motion trajectory difference result refers to the result reflecting the overall motion trajectory difference after integrating all motion comparison results. The physiological comparison result refers to the result obtained by comparing a single real-time physiological feature parameter with the normal range of physiological parameters. The physiological parameter difference result refers to the result reflecting the overall physiological parameter difference after integrating all physiological comparison results.

[0118] In this embodiment, each real-time motion feature parameter is compared with the corresponding standard range of motion trajectory to determine whether the parameter is within the standard range, resulting in multiple motion comparison results; all motion comparison results are integrated to obtain motion trajectory difference results; simultaneously, each real-time physiological feature parameter is compared with the corresponding normal range of physiological parameters to determine whether the parameter is within the normal range, resulting in multiple physiological comparison results; all physiological comparison results are integrated to obtain physiological parameter difference results.

[0119] Step 403: Classify and label the results of the differences in motion trajectories and the results of the differences in physiological parameters to generate training effect analysis information and risk intervention suggestion information.

[0120] In this embodiment, the various motion comparison results in the motion trajectory difference results are classified, and parameters within the standard range and parameters outside the standard range are marked; the various physiological comparison results in the physiological parameter difference results are similarly classified, and parameters within the normal range and parameters outside the normal range are marked; these classified and marked results are integrated to generate training effect analysis information reflecting the training effect and risk intervention suggestion information for the difference parameters.

[0121] This application embodiment extracts real-time feature parameters and compares them with preset standards to achieve real-time monitoring and effect evaluation of the training process, providing a basis for timely adjustment of training and improving the dynamic adaptability of remote rehabilitation services.

[0122] This application provides a specific embodiment. Step 403 involves classifying and labeling the differences in motion trajectories and physiological parameters to generate training effect analysis information and risk intervention recommendations. This specifically includes the following steps:

[0123] Step 411: Calculate the motion deviation value of each real-time motion feature parameter and the corresponding standard range of motion trajectory in the motion trajectory difference result. Mark the real-time motion feature parameters whose motion deviation value is within the preset allowable range as motion compliance items, and mark the real-time motion feature parameters whose motion deviation value exceeds the preset allowable range as motion deviation items.

[0124] In this step, the motion deviation value refers to the difference between the real-time motion characteristic parameter and the corresponding standard range of the motion trajectory. The preset allowable range refers to the pre-defined numerical range within which the parameter is allowed to deviate from the standard range. The motion compliance item refers to real-time motion characteristic parameters whose motion deviation values ​​are within the preset allowable range. The motion deviation item refers to real-time motion characteristic parameters whose motion deviation values ​​exceed the preset allowable range.

[0125] In this embodiment of the application, for each real-time motion feature parameter in the motion trajectory difference result, the difference between it and the corresponding standard range of motion trajectory is calculated as a motion deviation value; each motion deviation value is compared with a preset allowable range, and if it is within the range, the real-time motion feature parameter is marked as a motion compliance item; if it exceeds the range, it is marked as a motion deviation item.

[0126] Step 412: Calculate the physiological deviation value between each real-time physiological feature parameter and the corresponding normal range of physiological parameters in the physiological parameter difference results. Mark the real-time physiological feature parameters whose physiological deviation value is within the preset allowable range as physiological standard items, and mark the real-time physiological feature parameters whose physiological deviation value exceeds the preset allowable range as physiological deviation items.

[0127] In this step, the physiological deviation value refers to the difference between the real-time physiological characteristic parameter and the corresponding normal range of the physiological parameter. The physiological target item refers to the real-time physiological characteristic parameter whose physiological deviation value is within the preset allowable range. The physiological deviation item refers to the real-time physiological characteristic parameter whose physiological deviation value exceeds the preset allowable range.

[0128] In this embodiment of the application, for each real-time physiological feature parameter in the physiological parameter difference results, the difference between it and the corresponding normal range of physiological parameters is calculated as a physiological deviation value; each physiological deviation value is compared with a preset allowable range, and if it is within the range, the real-time physiological feature parameter is marked as a physiological standard item; if it exceeds the range, it is marked as a physiological deviation item.

[0129] Step 413: Integrate the exercise achievement items, the exercise deviation items, the physiological achievement items, and the physiological deviation items to form training effect analysis information.

[0130] In this embodiment, all exercise achievement items, exercise deviation items, physiological achievement items, and physiological deviation items are integrated and statistically analyzed according to the real-time exercise characteristic parameter type and the real-time physiological characteristic parameter type. This clarifies which parameters meet the standards, which parameters have deviations, and the direction of the deviations. This information is then integrated to form training effect analysis information.

[0131] Step 414: Generate risk intervention recommendation information based on the motor deviation item and the physiological deviation item.

[0132] In this embodiment of the application, for motion deviation items, the corresponding real-time motion characteristic parameter types and motion deviation values ​​are analyzed; for physiological deviation items, the corresponding real-time physiological characteristic parameter types and physiological deviation values ​​are analyzed; based on these analysis results, targeted adjustment suggestions are formulated, and all suggestions are integrated to form risk intervention suggestion information.

[0133] This application's embodiments calculate and classify deviation values, integrating them into training effect analysis information and risk intervention suggestion information. This enables accurate identification and quantitative assessment of parameter differences during training, providing a clear basis for adjusting rehabilitation training.

[0134] For example, in the results of the movement trajectory differences for elderly patient A, the real-time step length is 0.55m, the median of the standard range for movement trajectory is 0.5m, and the movement deviation is 0.55 - 0.5 = 0.05m, with a preset allowable range of ±0.06m, thus it is marked as a movement target achievement item. The real-time cadence is 80 steps / minute, the median of the standard range is 75 steps / minute, and the movement deviation is 5 steps / minute, with a preset allowable range of ±4 steps / minute, thus it is marked as a movement deviation item. In the results of the physiological parameter differences, the real-time muscle strength is 290N, the median of the normal range for physiological parameters is 300N, and the physiological deviation is -10N, with a preset allowable range of ±15N, thus it is marked as a physiological target achievement item. The real-time balance ability score is 62 points, the median of the normal range is 70 points, and the physiological deviation is -8 points, with a preset allowable range of ±5 points, thus it is marked as a physiological deviation item. These marked results are integrated to form training effect analysis information; based on the cadence deviation and balance ability score deviation, risk intervention suggestions for increasing cadence control prompts and strengthening balance training are generated.

[0135] This application provides a specific embodiment, step 414, which generates risk intervention suggestion information based on the motor deviation item and the physiological deviation item, specifically including the following steps:

[0136] Step 421: Based on the step length deviation, step frequency deviation, turning angle deviation, and center of gravity offset deviation values ​​in the motion deviation items, generate corresponding suggestions for step length adjustment range, step frequency rhythm correction, turning speed control, and center of gravity adjustment direction.

[0137] In this step, the stride length deviation refers to the difference between the real-time motion characteristic parameter related to stride length and the corresponding standard range of the motion trajectory. The cadence deviation refers to the difference between the real-time motion characteristic parameter related to cadence and the corresponding standard range of the motion trajectory. The turn angle deviation refers to the difference between the real-time motion characteristic parameter related to turn angle and the corresponding standard range of the motion trajectory. The center of gravity offset deviation refers to the difference between the real-time motion characteristic parameter related to center of gravity offset and the corresponding standard range of the motion trajectory. The stride length adjustment range suggestion refers to a suggestion for adjusting the stride length range based on the stride length deviation. The cadence rhythm correction suggestion refers to a suggestion for correcting the cadence rhythm based on the cadence deviation. The turn speed control suggestion refers to a suggestion for controlling the turn speed based on the turn angle deviation. The center of gravity adjustment direction suggestion refers to a suggestion for adjusting the center of gravity direction based on the center of gravity offset deviation.

[0138] In this embodiment, for the step length deviation value in the motion deviation item, the specific range of step length adjustment to be determined based on the magnitude and direction of the deviation, and a step length adjustment range suggestion is generated; for the step frequency deviation value, the situation of excessively fast or slow step frequency is analyzed, and a specific method for correcting the step frequency rhythm is proposed, and a step frequency rhythm correction suggestion is generated; for the turning angle deviation value, based on the degree of deviation, specific guidance for controlling the turning speed is given, and a turning speed control suggestion is generated; for the center of gravity offset deviation value, based on the direction of the offset, the direction of adjusting the center of gravity is determined, and a center of gravity adjustment direction suggestion is generated.

[0139] Step 422: Based on the deviation values ​​of muscle strength, balance ability score, movement coordination index, and reaction speed in the physiological deviation items, generate corresponding suggestions for increasing or decreasing local training intensity, adding balance assistance movements, decomposing movement exercises, and increasing reaction training frequency.

[0140] In this step, the muscle strength deviation value refers to the difference between the real-time physiological characteristic parameter related to muscle strength and the corresponding normal range of physiological parameters. The balance ability score deviation value refers to the difference between the real-time physiological characteristic parameter related to balance ability score and the corresponding normal range of physiological parameters. The movement coordination index deviation value refers to the difference between the real-time physiological characteristic parameter related to movement coordination index and the corresponding normal range of physiological parameters. The reaction speed value deviation value refers to the difference between the real-time physiological characteristic parameter related to reaction speed value and the corresponding normal range of physiological parameters. Suggestions for increasing or decreasing local training intensity refer to recommendations for increasing or decreasing the intensity of local training based on the muscle strength deviation value. Suggestions for adding balance assistance movements refer to recommendations for adding balance assistance movements based on the balance ability score deviation value. Suggestions for performing movement breakdown exercises refer to recommendations for performing movement breakdown exercises based on the movement coordination index deviation value. Suggestions for adjusting the reaction training frequency refer to recommendations for adjusting the reaction training frequency based on the reaction speed value deviation value.

[0141] In this embodiment, for the muscle strength deviation value in the physiological deviation item, if the deviation value is negative, it is recommended to increase the local training intensity; if it is positive, it is recommended to appropriately decrease it, generating a suggestion to increase or decrease the local training intensity. For the balance ability score deviation value, depending on the degree of low score, it is recommended to add auxiliary movements such as holding onto a wall or using a balance mat, generating a suggestion to add balance auxiliary movements. For the movement coordination index deviation value, complex movements are broken down into multiple simple steps for practice, generating a suggestion to decompose the movement into practice steps. For the reaction speed value deviation value, depending on the situation of slow reaction speed, it is recommended to increase or decrease the number of reaction training sessions, generating a suggestion to increase or decrease the reaction training frequency.

[0142] Step 423: Integrate the suggestions for step length adjustment range, step frequency rhythm correction, turning speed control, center of gravity adjustment direction, local training intensity increase / decrease, balance auxiliary movement addition, movement decomposition practice, and reaction training frequency to form risk intervention suggestion information.

[0143] In this embodiment, suggestions for stride length adjustment, stride frequency correction, turning speed control, center of gravity adjustment direction, local training intensity increase / decrease, balance assistance movement addition, movement breakdown exercise, and reaction training frequency are integrated and categorized into exercise-related and physiological-related suggestions to ensure that each suggestion clearly corresponds to a specific deviation, thus forming a complete risk intervention suggestion information.

[0144] This application's embodiments generate and integrate targeted suggestions for both motor and physiological deviations, making risk intervention suggestions more specific and comprehensive. This provides clear guidance for adjusting rehabilitation training for elderly patients and improves the accuracy and effectiveness of interventions.

[0145] For example, in the motor deviation category for elderly patient A, the step length deviation is +0.08m, with a suggested adjustment of 0.05m to reduce the step length; the cadence deviation is -10 steps / minute, with a suggested adjustment of increasing the cadence to the standard range; the turning angle deviation is +15 degrees, with a suggested adjustment of slowing the turning speed; and the center of gravity shift deviation is +3cm, with a suggested adjustment of the center of gravity to the left. In the physiological deviation category, the muscle strength deviation is -30N, with a suggested adjustment of increasing leg training intensity; the balance score deviation is -8 points, with a suggested addition of balance assistance exercises such as standing with support against a wall; the motor coordination index deviation is -0.1, with a suggested breakdown of the turning motion into two steps: preparation and completion; and the reaction speed deviation is +0.2 seconds, with a suggested increase in reaction training frequency by two sessions per week. These suggestions are then integrated to form risk intervention recommendations.

[0146] Figure 3 This application provides a schematic diagram of a specific implementation of an internet-based remote rehabilitation comprehensive service system, with reference to... Figure 3 The system may include:

[0147] Module 21 is used to acquire historical movement trajectory data and initial physiological parameters of elderly patients;

[0148] Simulation module 22 is used to simulate the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities, based on the historical movement trajectory data and the initial physiological parameters, through the Internet remote rehabilitation integrated service platform.

[0149] The adjustment module 23 is used to determine the risk level of the fall risk simulation result according to the preset fall risk assessment index system, so as to adjust the candidate training schemes corresponding to different risk levels and obtain the adjusted training scheme.

[0150] The comparison module 24 is used to acquire real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compare the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generate training effect analysis information and risk intervention suggestion information.

[0151] The update module 25 is used to update the rehabilitation records of the elderly patients based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, so as to realize comprehensive remote rehabilitation services.

[0152] This application provides an embodiment of an integrated service system for remote rehabilitation based on the Internet, which is used to implement the aforementioned integrated service method for remote rehabilitation based on the Internet. Therefore, the specific implementation of the integrated service system for remote rehabilitation based on the Internet can be found in the embodiment section of the integrated service method for remote rehabilitation based on the Internet mentioned above. The specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0153] This application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described Internet-based remote rehabilitation integrated service methods.

[0154] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described comprehensive service methods for remote rehabilitation based on the Internet.

[0155] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, random access memory, portable hard drives, magnetic disks, or optical disks.

[0156] Embodiments of the present invention also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the comprehensive service method for Internet-based remote rehabilitation.

[0157] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0158] The above provides a detailed description of the comprehensive service system and method for remote rehabilitation based on the Internet provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A comprehensive service method for remote rehabilitation based on the Internet, characterized in that, include: Acquire historical movement trajectory data and initial physiological parameters of elderly patients; Based on the historical movement trajectory data and the initial physiological parameters, the fall risk simulation results of the elderly patient under candidate training programs corresponding to different training intensities are simulated through the Internet remote rehabilitation integrated service platform. Based on the preset fall risk assessment index system, the risk level of the fall risk simulation results is determined, and the candidate training schemes corresponding to different risk levels are adjusted to obtain the adjusted training scheme. The system acquires real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compares the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generates training effect analysis information and risk intervention suggestion information. Based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, the rehabilitation records of the elderly patients are updated to achieve comprehensive remote rehabilitation services. Based on the historical movement trajectory data and the initial physiological parameters, the fall risk simulation results of the elderly patient under candidate training programs corresponding to different training intensities are conducted through an internet-based remote rehabilitation service platform, including: Motion feature parameters are extracted from the historical motion trajectory data, and physiological feature parameters are extracted from the initial physiological parameters. The motion feature parameters include stride length, stride frequency, turning angle, and center of gravity offset. The physiological feature parameters include muscle strength value, balance ability score, movement coordination index, and reaction speed value. From the motor characteristic parameters and the physiological characteristic parameters, parameter pairs related to fall risk are selected, and the correlation coefficient of each parameter pair is calculated to obtain multiple correlation values. The parameter pairs include stride length and muscle strength value, center of gravity offset and balance ability score. The correlation coefficient refers to the value that measures the degree of correlation between two parameters in the parameter pair. Based on a preset training intensity grading standard, candidate training schemes corresponding to different training intensities are generated. The candidate training schemes include action type, action amplitude, and number of action repetitions. Based on the training intensity, motion characteristic parameters, physiological characteristic parameters, and correlation values ​​corresponding to each candidate training program, the elderly patient is simulated to execute each candidate training program through an Internet-based remote rehabilitation integrated service platform, combined with a biomechanical model, to obtain the fall risk prediction results corresponding to each candidate training program. The fall risk prediction results include balance stabilization time, maximum center of gravity offset distance, and movement completion deviation.

2. The method according to claim 1, characterized in that, Based on a pre-defined fall risk assessment index system, the risk level of the fall risk simulation results is determined, and the candidate training schemes corresponding to different risk levels are adjusted to obtain the adjusted training schemes, including: The assessment indicators and corresponding risk reference ranges are extracted from the preset fall risk assessment indicator system. The assessment indicators include balance ability indicators, muscle strength indicators, motor coordination indicators and reaction speed indicators. The risk reference ranges include safety reference range, warning reference range and danger reference range. Evaluation index values ​​are extracted from the results of various fall risk simulations. These evaluation index values ​​include balance ability index value, muscle strength index value, motor coordination index value, and reaction speed index value. By comparing the assessment index values ​​with the corresponding risk reference ranges, risk sub-levels for balance ability, muscle strength, motor coordination, and reaction speed are obtained. Based on the balance ability risk sub-level, the muscle strength risk sub-level, the motor coordination risk sub-level, and the reaction speed risk sub-level, a comprehensive risk level is calculated, which includes low risk level, medium risk level, and high risk level. Based on the comprehensive risk level, the corresponding candidate training schemes are adjusted to obtain the adjusted training scheme.

3. The method according to claim 2, characterized in that, Based on the comprehensive risk level, the corresponding candidate training schemes are adjusted to obtain the adjusted training scheme, including: When the overall risk level is high, the corresponding candidate training program is adjusted to obtain the adjusted training program. The adjustment operations include adjusting the movement amplitude to a preset first proportion, reducing the number of repetitions of the movement to a preset second proportion, and increasing the preset auxiliary support movement types and implementation timing. When the overall risk level is medium risk, the corresponding candidate training scheme is adjusted to obtain the adjusted training scheme. The adjustment steps include increasing the time interval and prompting method of the preset action rhythm prompts. When the overall risk level is low, the corresponding candidate training scheme will be used as the adjusted training scheme.

4. The method according to claim 1, characterized in that, The real-time motion trajectory data and training physiological parameters are compared with preset rehabilitation indicators to generate training effect analysis information and risk intervention suggestions, including: Multiple real-time motion feature parameters are extracted from the real-time motion trajectory data, and multiple real-time physiological feature parameters are extracted from the training physiological parameters. Based on preset rehabilitation indicators, the standard range of motion trajectory and normal range of physiological parameters corresponding to the adjusted training plan are determined. Each real-time motion feature parameter is compared with the standard range of the motion trajectory to obtain multiple motion comparison results. All motion comparison results are integrated to obtain the motion trajectory difference result. Each real-time physiological feature parameter is compared with the normal range of the physiological parameters to obtain multiple physiological comparison results. All physiological comparison results are integrated to obtain the physiological parameter difference result. The differences in motion trajectories and physiological parameters are classified and labeled to generate training effect analysis information and risk intervention suggestions.

5. The method according to claim 4, characterized in that, The differences in motion trajectories and physiological parameters are categorized and labeled to generate training effect analysis information and risk intervention recommendations, including: Calculate the motion deviation value of each real-time motion feature parameter and the corresponding standard range of motion trajectory in the motion trajectory difference result. Mark the real-time motion feature parameter whose motion deviation value is within the preset allowable range as a motion standard item, and mark the real-time motion feature parameter whose motion deviation value exceeds the preset allowable range as a motion deviation item. The physiological deviation values ​​of each real-time physiological feature parameter and its corresponding normal range in the physiological parameter difference results are calculated. Real-time physiological feature parameters whose physiological deviation values ​​are within the preset allowable range are marked as physiological standard items, and real-time physiological feature parameters whose physiological deviation values ​​exceed the preset allowable range are marked as physiological deviation items. The exercise achievement items, exercise deviation items, physiological achievement items, and physiological deviation items are integrated to form training effect analysis information; Based on the motor deviation items and the physiological deviation items, risk intervention recommendation information is generated.

6. The method according to claim 5, characterized in that, Based on the motor deviation items and the physiological deviation items, risk intervention recommendation information is generated, including: Based on the step length deviation, step frequency deviation, turning angle deviation, and center of gravity offset deviation values ​​in the motion deviation items, corresponding suggestions for step length adjustment range, step frequency rhythm correction, turning speed control, and center of gravity adjustment direction are generated. Based on the deviation values ​​of muscle strength, balance ability score, movement coordination index, and reaction speed in the physiological deviation items, corresponding suggestions for increasing or decreasing local training intensity, adding balance assistance movements, decomposing movement exercises, and increasing reaction training frequency are generated. The suggestions for adjusting stride length, correcting stride frequency, controlling turning speed, adjusting center of gravity, increasing or decreasing local training intensity, adding balance-assisted movements, decomposing movement exercises, and increasing reaction training frequency are integrated to form risk intervention suggestion information.

7. A comprehensive service system for remote rehabilitation based on the Internet, characterized in that, include: The acquisition module is used to acquire historical movement trajectory data and initial physiological parameters of elderly patients; The simulation module is used to simulate the fall risk prediction results of the elderly patient under candidate training programs corresponding to different training intensities, based on the historical movement trajectory data and the initial physiological parameters, through the Internet remote rehabilitation integrated service platform. The adjustment module is used to determine the risk level of the fall risk simulation result according to the preset fall risk assessment index system, so as to adjust the candidate training schemes corresponding to different risk levels and obtain the adjusted training scheme. The comparison module is used to acquire real-time motion trajectory data and training physiological parameters of the elderly patient during the training process according to the adjusted training plan, compare the real-time motion trajectory data and training physiological parameters with preset rehabilitation indicators, and generate training effect analysis information and risk intervention suggestion information. The update module is used to update the rehabilitation records of the elderly patients based on the historical movement trajectory data, the initial physiological parameters, the fall risk simulation results, the adjusted training plan, the real-time movement trajectory data, the training physiological parameters, the training effect analysis information, and the risk intervention suggestion information, so as to realize comprehensive remote rehabilitation services. Based on the historical movement trajectory data and the initial physiological parameters, the fall risk simulation results of the elderly patient under candidate training programs corresponding to different training intensities are conducted through an internet-based remote rehabilitation service platform, including: Motion feature parameters are extracted from the historical motion trajectory data, and physiological feature parameters are extracted from the initial physiological parameters. The motion feature parameters include stride length, stride frequency, turning angle, and center of gravity offset. The physiological feature parameters include muscle strength value, balance ability score, movement coordination index, and reaction speed value. From the motor characteristic parameters and the physiological characteristic parameters, parameter pairs related to fall risk are selected, and the correlation coefficient of each parameter pair is calculated to obtain multiple correlation values. The parameter pairs include stride length and muscle strength value, center of gravity offset and balance ability score. The correlation coefficient refers to the value that measures the degree of correlation between two parameters in the parameter pair. Based on a preset training intensity grading standard, candidate training schemes corresponding to different training intensities are generated. The candidate training schemes include action type, action amplitude, and number of action repetitions. Based on the training intensity, motion characteristic parameters, physiological characteristic parameters, and correlation values ​​corresponding to each candidate training program, the elderly patient is simulated to execute each candidate training program through an Internet-based remote rehabilitation integrated service platform, combined with a biomechanical model, to obtain the fall risk prediction results corresponding to each candidate training program. The fall risk prediction results include balance stabilization time, maximum center of gravity offset distance, and movement completion deviation.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of a comprehensive service method for remote rehabilitation based on the Internet as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables the implementation of a comprehensive service method for remote rehabilitation based on the Internet as described in any one of claims 1 to 6.

Images