An intelligent assistance system and method for rehabilitation nursing

Abstract

The present invention relates to the field of computer science and technology, and discloses an intelligent assistance system and method for rehabilitation nursing, including: acquiring and entering user data to form a personalized rehabilitation threshold; initializing a reinforcement learning model, collecting real-time physiological feedback from the user and combining it with the personalized rehabilitation threshold to generate a preliminary training plan, and optimizing the training plan by combining the user's micro-expressions and gestures; evaluating the rehabilitation progress of the user data after training to determine whether the training plan needs to be adjusted; and updating the training plan based on the judgment results and adjusting the personalized rehabilitation goals. This system improves the intelligent decision-making ability of the training strategy, reduces the need for human intervention, and ultimately enhances the user's rehabilitation experience and training results, accelerating the rehabilitation process.

Description

Technical Field

[0001] The present invention relates to the field of computer science and technology, and in particular to an intelligent assistance system and method for rehabilitation nursing. Background Art

[0002] With the rapid development of artificial intelligence and the Internet of Things (IoT) technologies, the field of rehabilitation nursing is gradually evolving towards intelligent and personalized approaches. Traditional rehabilitation training methods primarily rely on physician experience and static rehabilitation plans, lacking dynamic monitoring and adjustment of patients' real-time physiological status and training effectiveness. In recent years, intelligent rehabilitation systems based on sensor technology and machine learning algorithms have gradually emerged. For example, wearable devices collect patients' physiological data (such as heart rate and blood oxygen saturation) and combine them with machine learning models to generate training recommendations. Furthermore, the introduction of micro-expression analysis and gesture recognition technologies has provided a richer dimension of user feedback for rehabilitation training. However, existing technologies are often limited to analyzing a single data source and lack the deep integration of multimodal data (such as physiological signals, micro-expressions, gestures, etc.). Furthermore, adjustments to training plans often rely on preset rules, making it difficult to achieve true personalization and dynamic optimization. Summary of the Invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: the technical problem that the training program is out of touch with actual needs, user compliance is poor, and the rehabilitation effect is poor due to the lack of multimodal data fusion and dynamic personalized adjustment in existing rehabilitation nursing technology.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent assistance method for rehabilitation nursing, comprising:

[0006] Acquire and input user data to form personalized rehabilitation thresholds;

[0007] Forming personalized rehabilitation thresholds includes using the user's real-time physiological signals before training to establish the user's static physiological characteristics baseline USB; ≤MET< The low-intensity movements are collected during training, and the user's real-time physiological signals and micro-expressions are collected. The key features of each movement are extracted, and a low-intensity exercise physiological characteristic curve DUS is established. This is compared with the static physiological characteristic baseline USB and the relative change rate RCR is calculated. MET stands for metabolic equivalent, a unit for measuring exercise intensity. Indicates the lower limit of MET value, Indicates the upper limit of MET value; personalized rehabilitation threshold includes the lower limit of individualized training LBT and the upper limit of individualized training UBT;

[0008] When RCR is lower than When the RCR exceeds , is the upper limit of individual training UBT, where represents the lower threshold of individualized training, Indicates the upper threshold of individualized training;

[0009] Initialize the reinforcement learning model, collect real-time physiological feedback from the user and combine it with the personalized rehabilitation threshold to generate a preliminary training plan, and optimize the training plan by combining the user's micro-expressions and gestures;

[0010] Evaluate the user's rehabilitation progress based on post-training data to determine whether the training program needs to be adjusted;

[0011] Based on the judgment results, update the training plan and adjust the personalized rehabilitation goals.

[0012] As a preferred solution of the intelligent assistance method for rehabilitation nursing described in the present invention, forming a personalized rehabilitation threshold includes using OpenFace to analyze the user's micro-expressions and extract the user's expression characteristics during low-intensity movements.

[0013] As a preferred embodiment of the intelligent auxiliary method for rehabilitation nursing described in the present invention, initializing the reinforcement learning model includes defining the state variables of the reinforcement learning and action space , set the reward function ;

[0014] The state variable Including: user's real-time physiological signals, RCR, facial features and personalized rehabilitation threshold; the action space Including: training intensity, training duration, rest interval and training type conversion; the reward function Including: training effect rewards, personalized recovery threshold rewards, training compliance rewards, training goal achievement rewards and user expression feature rewards;

[0015] The personalized rehabilitation threshold rewards include: When punishment is given; when When punishment is given; when When, give rewards;

[0016] The training compliance reward includes giving a reward when the user actively indicates through gestures that he or she is more willing to participate in the training;

[0017] The facial expression features include concentration and pain index; when concentration And the pain index When the pain index When a punishment is given, where represents the concentration threshold, and represents the pain index threshold.

[0018] As a preferred solution of the intelligent assistance method for rehabilitation care described in the present invention, wherein: generating a preliminary training plan includes collecting , and for n time steps, recording the policy model , calculating the probability distribution of taking each action under each state ; , and for n time steps are combined with , and the advantage function is calculated using the generalized advantage estimation method;

[0019] Generating the preliminary training plan further includes constructing a policy optimization objective function and updating the policy parameters by the gradient descent method;

[0020] A clipping mechanism is used to construct the policy optimization objective function ; updating the policy parameters includes defining the final loss function , updating , and mapping the policy parameters to the training plan, which is represented by the formula:

[0021]

[0022] where, represents the probability distribution of the optimal action calculated according to the policy under the current state ; represents sampling a specific action from the probability distribution for training; is the policy parameter, representing 's parameter vector.

[0023] As a preferred solution of the intelligent assistance method for rehabilitation care described in the present invention, wherein: optimizing the training plan by combining the user's micro-expression and gesture includes using , the expression feature and the user's gesture as inputs, and adjusting using the IF-THEN rule;

[0024] The IF-THEN rule includes: IF the user's micro-expression pain index > q and the concentration < d, THEN reduce the training intensity and in the subsequent During the training, the user's adaptation is continuously observed and the training target is automatically adjusted to a low-intensity load. If the pain index after the round continues to be higher than a, active interaction is introduced to ask the user whether to pause the training;

[0025] IF users' micro-expression pain index And focus , THEN increase the training time each time in the future training, and monitor the pain index changes at the same time. If the user's pain index increases to , the adjustment will be automatically withdrawn and the original duration will be restored;

[0026] IF user gestures to continue training or concentration , THEN the user shortens the rest interval in the next training session. If the user's pain index increases during training, the regular rest interval is restored;

[0027] in, Indicates a high threshold for the pain index, Indicates the low threshold of the pain index, Represents the recovery threshold of the pain index, Indicates a low threshold of concentration, Indicates a medium threshold of concentration, Indicates a high threshold for concentration.

[0028] As a preferred embodiment of the intelligent auxiliary method for rehabilitation nursing described in the present invention, the rehabilitation progress assessment includes extracting rehabilitation features from the user data after training and constructing rehabilitation progress indicators; fitting the rehabilitation progress indicators to the rehabilitation progress curve using the time series method. , every ten trainings are set as an analysis window. In an analysis window, when When p% of the data points are not within the personalized recovery threshold, the training plan is updated. p% indicates the proportion of data points that exceed the personalized recovery threshold in the current analysis window.

[0029] As a preferred embodiment of the intelligent auxiliary method for rehabilitation nursing of the present invention, the updating of the training program based on the judgment result includes utilizing the user's real-time physiological feedback, , facial expression features constitute a decision adjustment matrix; use the decision adjustment matrix to reversely deduce the deviation of training intensity and update the training plan.

[0030] An intelligent assistance system for rehabilitation nursing, comprising:

[0031] Data module, which acquires and enters user data to form personalized rehabilitation thresholds;

[0032] The training program module initializes the reinforcement learning model, collects real-time physiological feedback from the user based on the personalized rehabilitation threshold, generates a preliminary training program, and optimizes the training program based on the user's micro-expressions and gestures;

[0033] The evaluation module evaluates the rehabilitation progress of user data after training and determines whether the training plan needs to be adjusted;

[0034] The adjustment module updates the training plan and adjusts the personalized rehabilitation goals based on the judgment results.

[0035] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0036] A computer-readable storage medium stores a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0037] Beneficial effects of the present invention: The intelligent auxiliary method for rehabilitation care provided by the present invention constructs a personalized rehabilitation threshold (LBT / UBT) by acquiring multimodal data of the user, and combines the RCR calculation model of the static physiological baseline (USB) and dynamic motion characteristics (DUS) to accurately identify the user's tolerance range and avoid training overload or insufficient intensity; adopts a reinforcement learning framework to integrate real-time physiological signals, micro-expressions and gesture interactions, and realizes multi-dimensional target optimization through state space modeling and reward function design, thereby improving training safety and user participation; constructs a policy gradient optimization objective function based on the PPO algorithm, dynamically adjusts training parameters using generalized advantage estimation, and realizes human-computer collaborative decision-making in combination with the IF-THEN rule base, significantly improving the real-time and robustness of the program adjustment; analyzes the rehabilitation progress curve through time series, combines the decision matrix to reversely deduce the deviation cause, dynamically calibrates the personalized goal, and forms an "evaluation-adjustment-verification" closed loop, ultimately achieving triple dynamic adaptation of the rehabilitation program to the user's physiological state, psychological feedback and rehabilitation progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 This is an overall flow chart of an intelligent assistance method for rehabilitation nursing provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0040] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0041] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides an intelligent assistance method for rehabilitation nursing, comprising:

[0042] S1: Obtain and enter user data to form a personalized rehabilitation threshold.

[0043] User data includes user name, user age, user gender, user health status, user current exercise ability, user rehabilitation goals, user real-time physiological signals, user real-time physiological feedback and overall exercise data of rehabilitation training users.

[0044] Preprocessing the collected user data includes ensuring that the user's basic information (name, age, gender, etc.) is complete.

[0045] Missing data is removed, and the user's real-time physiological signals are converted to a unified data unit. Motion data is represented as a numerical vector for subsequent calculations.

[0046] The Z-score method is used to detect abnormal data points and eliminate outliers caused by sensor failure or misoperation.

[0047] According to experience, , , , , +20%.

[0048] Forming a personalized rehabilitation threshold involves using the user's real-time physiological signals before training to establish the user's static physiological characteristic baseline USB. Through five low-intensity movements with a range of 1.5 ≤ MET < 3.0, the user's real-time physiological signals and micro-expressions during training are collected, the key features of each movement are extracted, and a low-intensity exercise physiological characteristic curve DUS is established. This is compared with the static physiological characteristic baseline USB and the relative change rate RCR is calculated using the formula:

[0049]

[0050] OpenFace is used to analyze user micro-expressions and extract the user's facial features during low-intensity actions.

[0051] The key features include physiological signal features, motion features, and training load features.

[0052] The threshold of personalized rehabilitation includes the lower limit of personalized training LBT and the upper limit of personalized training UBT.

[0053] When RCR is lower than -10%, it is the lower limit of individualized training LBT, and when RCR exceeds +20%, it is the upper limit of individualized training UBT.

[0054] Furthermore, by collecting basic user information, real-time physiological signals, and motion data, we ensure that training plans can be tailored to individual characteristics, rather than using a uniform, fixed training standard. At the same time, through preprocessing (data format conversion, outlier removal, etc.), data integrity and reliability are guaranteed, making subsequent calculations more stable and accurate. Furthermore, a low-intensity exercise test (MET 1.5 ≤ MET < 3.0) is used to establish a static physiological characteristic baseline (USB) and a low-intensity exercise physiological characteristic curve (DUS), and the relative rate of change (RCR) is calculated.

[0055] Furthermore, personalized rehabilitation thresholds (LBT and UBT) ensure that users' training plans are within their capabilities, avoiding injuries caused by excessive training loads or reduced rehabilitation efficiency due to low training intensity. Furthermore, through micro-expression analysis and cosine similarity feature matching, the system comprehensively considers physiological signals, movement characteristics, and subjective feelings, making training adjustments more intelligent. Abnormal data is also eliminated and normalized.

[0056] S2: Initialize the reinforcement learning model, collect the user's real-time physiological feedback and combine it with the personalized rehabilitation threshold to generate a preliminary training plan, and optimize the training plan based on the user's micro-expressions and gestures.

[0057] Initializing the reinforcement learning model includes defining the state variables and action space of reinforcement learning and setting the reward function.

[0058] The state variable Including: user's real-time physiological signals, RCR, facial features and personalized rehabilitation threshold. Including: training intensity, training duration, rest interval and training type conversion. Including: training effect rewards, personalized rehabilitation threshold rewards, training compliance rewards, training goal achievement rewards and user expression feature rewards.

[0059] The formula is:

[0060]

[0061] in, Indicates that at time step The total reward on . Indicates training effect reward. Represents personalized recovery threshold reward. Indicates training compliance reward. Indicates the reward for achieving the training goal. Represents rewards based on user expression features.

[0062]

[0063]

[0064] in, Indicates rewards reflecting training results. Indicates the reward for achieving the training goal.

[0065] The personalized rehabilitation threshold rewards include: When , a penalty of -5 is imposed. When , a penalty of -10 is imposed. , reward +5.

[0066] The training compliance reward includes a reward of +5 when the user actively indicates through gestures that he or she is more willing to participate in the training.

[0067] Based on experience , , .

[0068] The expression feature includes concentration and pain index. The expression feature reward is when concentration And the pain index When the pain index is , the penalty is -5.

[0069] Generating a preliminary training plan includes setting a time step to 15 seconds and collecting 10 time steps 、 and , record policy model , calculate each state Take the following actions The probability distribution of . 10 time steps 、 and Combine , using the generalized advantage estimation method to calculate the advantage function .

[0070] The formula is expressed as:

[0071]

[0072] in, represents the advantage function, represents the contribution of weighted future rewards, Indicates immediate reward, represents the discounted future state value, Indicates the future state The status value of Represents the discount factor. Indicates that the status The following value assessment.

[0073] Generating a preliminary training plan also includes constructing a policy optimization objective function and updating the policy parameters via gradient descent.

[0074] Adopting the pruning mechanism to construct a strategy to optimize the objective function , the formula is:

[0075]

[0076]

[0077] in, represents the policy optimization objective function, Represents the time step Perform expectation calculations, represents the probability ratio, Indicates that under the current policy, in the state Select Action probability. Indicates that under the old policy, in the state Select Action The probability of represents the advantage function. represents the clipping function, Indicates the clipping range.

[0078] Updating strategy parameters includes defining the final loss function ,renew , the formula is:

[0079]

[0080]

[0081]

[0082] in, represents the final loss function, represents the policy optimization objective function, and represents the hyperparameter, represents the error term of the value function; is a strategy parameter, indicating parameter vector of ; represents the learning rate, Represents the loss function Calculate the gradient, represents the policy entropy.

[0083] Mapping the policy parameters to the training scheme is expressed as:

[0084]

[0085] in, According to the strategy Calculate the current state Next best action The probability distribution of . Indicates sampling a specific action according to the probability distribution Conduct training.

[0086] Optimizing training programs based on user micro-expressions and gestures includes: , facial features and user gestures as input, and use IF-THEN rules to Make adjustments.

[0087] The IF-THEN rule includes: IF the user's micro-expression pain index is greater than 0.8 and the concentration is less than 0.3, THEN reduce the training intensity by 20%, observe the user's adaptation in the subsequent three rounds of training, and automatically adjust the training target to a low-intensity load. If the pain index continues to be higher than 0.8 after three rounds, active interaction is introduced to ask the user whether to pause the training.

[0088] Based on experience , , 0.9.

[0089] If the user's micro-expression pain index is <0.4 and their concentration is >0.7, THEN will increase the training time by 10% in each of the next two rounds of training while monitoring the changes in the pain index. If the user's pain index rises to >0.7 in subsequent training, the adjustment will be automatically withdrawn and the original duration will be restored.

[0090] If the user gestures to continue training or the concentration level is >0.9, THEN the user shortens the rest interval by 10% in the next training session. If the user's pain index increases during training, the normal rest interval is restored.

[0091] Furthermore, by defining the state variables, action space, and reward function of the reinforcement learning model, the system can perceive the user's physiological signals, micro-expression feedback, and training compliance, thereby dynamically adjusting training parameters within each training time step. Secondly, through the advantage function and policy optimization objective function, the system can efficiently learn the optimal training strategy and adopt a clipping mechanism to avoid excessive strategy updates and improve training stability. In addition, the combination of IF-THEN rules for micro-expression and gesture optimization ensures that when the user's physiological or psychological state is abnormal, the system can make adaptive adjustments to avoid excessive training load or hindered rehabilitation progress.

[0092] Furthermore, through the introduction of a reinforcement learning framework, the system can autonomously learn the optimal training plan. Compared with traditional fixed training plans, it can dynamically adapt to the user's status, improving the efficiency of rehabilitation training and user experience. Secondly, the personalized rehabilitation threshold reward mechanism ensures that the training load is always within an appropriate range, avoiding the risks of overtraining and preventing insufficient training intensity from affecting the progress of rehabilitation. Furthermore, by optimizing the training plan based on the user's micro-expressions and gestures, the system can perceive the user's real-time status and provide more personalized training adjustments, allowing users to adapt to the training rhythm both physically and mentally. In addition, the strategy optimizes the objective function and the gradient descent update strategy.

[0093] S3: Evaluate the rehabilitation progress of the user data after training to determine whether the training plan needs to be adjusted.

[0094] Rehabilitation progress assessment includes extracting rehabilitation features from user data after training and constructing rehabilitation progress indicators. The rehabilitation progress indicators are fitted into a rehabilitation progress curve using a time series method. The rehabilitation characteristics include physiological characteristics, movement characteristics and subjective characteristics.

[0095]

[0096] in, Rehabilitation progress indicator, represents the weight of physiological characteristics, represents the motion feature weight, represents the subjective feature weight.

[0097] Arrange the rehabilitation progress indicators at each moment after training in chronological order to form a time series representation:

[0098]

[0099] in, Represents the rehabilitation progress indicator after the first training session. Represents the rehabilitation progress indicator after the second training session. represents the rehabilitation progress indicator after the nth training session, Indicates the total number of training times.

[0100] Based on experience .

[0101] The sliding average method is fitted to the series as Every ten trainings are set as an analysis window. In an analysis window, when When 30% of the data points are not within the personalized recovery threshold, the training plan is updated.

[0102] Furthermore, through rehabilitation feature extraction, rehabilitation progress indicator construction, time series analysis, and sliding average fitting, the system can accurately track changes in the user's status during training. The setting of the analysis window ensures a trend assessment of rehabilitation progress, enabling the system to identify the stability of training effects and make adjustments when appropriate.

[0103] Furthermore, through time series analysis, the system can promptly detect abnormal training effects and trigger intelligent adjustments when 30% of data points exceed the personalized rehabilitation threshold, thereby preventing users from entering an ineffective training phase and improving rehabilitation efficiency.

[0104] S4: Based on the judgment results, update the training plan and adjust the personalized rehabilitation goals. The facial features are aligned and normalized within the same time window (10 seconds) to form a state vector. The state vectors of 10 time steps are combined to form a decision adjustment matrix. The decision adjustment matrix is ​​used to reversely deduce the deviation of training intensity and update the training plan.

[0105] The formula of the decision adjustment matrix is ​​expressed as:

[0106]

[0107] in, represents the state vector, represents the decision adjustment matrix, represents the current time step, represents how many past time steps are included in the decision adjustment matrix, represents the earliest time step.

[0108] Using the decision adjustment matrix and RCR value, the deviation of training intensity, training duration and rest interval is reversely deduced: when RCR>+20%, it means that the current training intensity is too high, and the training intensity is reduced by 20% while shortening the training duration.

[0109] When RCR<-10%, it means that the current training intensity is insufficient and the training time should be increased.

[0110] The adjustment suggestions derived from reverse derivation are used as feedback and input into the reinforcement learning model to update the training plan.

[0111] Furthermore, by aligning and normalizing data within a fixed time window (10 seconds), the system can effectively capture short-term trends in user status. Using historical data from multiple time steps (i.e., the decision adjustment matrix), the system can analyze and reverse-infer deviations in training intensity, duration, and rest intervals. Based on this information, the training plan can be adjusted to ensure accuracy, adaptability, and progression, avoiding fatigue caused by excessively high training intensity or slow recovery progress caused by too low a training intensity.

[0112] Furthermore, by constructing a decision adjustment matrix, the system can more accurately identify the user's physiological state and rehabilitation progress, reducing misjudgments caused by data noise or single time-step judgments. Secondly, based on RCR threshold judgment, it can timely adjust the training plan when the user's training load is too high or too low, reducing the risk of sports injuries while ensuring the steady progress of rehabilitation. In addition, the introduction of reinforcement learning models enables the training plan to be continuously optimized over time, improving the intelligent decision-making ability of training strategies, reducing the need for human intervention, and ultimately improving the user's rehabilitation experience and training effects, accelerating the rehabilitation process.

[0113] Embodiment 2, an embodiment of the present invention, provides an intelligent assistance system for rehabilitation nursing, including:

[0114] The data module obtains and enters user data to form a personalized rehabilitation threshold.

[0115] The training program module initializes the reinforcement learning model, collects real-time physiological feedback from the user according to the personalized rehabilitation threshold, generates a preliminary training program, and optimizes the training program in combination with the user's micro-expressions and gestures.

[0116] The evaluation module evaluates the rehabilitation progress of user data after training and determines whether the training plan needs to be adjusted.

[0117] The adjustment module updates the training plan and adjusts the personalized rehabilitation goals based on the judgment results.

[0118] Example 3, an embodiment of the present invention, is different from the previous two embodiments in that:

[0119] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0120] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0121] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0122] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0123] Example 4 is an embodiment of the present invention, which provides an intelligent auxiliary system and method for rehabilitation nursing. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0124] Twenty postoperative hip replacement rehabilitation subjects, aged between 45 and 70 years, were selected, including eleven men and nine women. Within seven to ten days after surgery, these subjects were assigned to the same rehabilitation facility and trained twice daily, each session lasting approximately thirty minutes. The goal was to dynamically regulate and evaluate their recovery process through the introduction of personalized thresholds and reinforcement learning models.

[0125] Before the trial began, all subjects had their basic information collected, including name, age, gender, medical history, current exercise capacity, and rehabilitation goals. A baseline measurement of real-time physiological signals was also performed. This baseline measurement, which included the root mean square value and frequency domain parameters of electromyographic (EMG) signals, heart rate variability (HRV), and blood oxygen saturation (SpO2), was recorded for at least three minutes to extract a static physiological baseline (USB). Subsequently, all subjects were required to complete five low-intensity exercises with a MET score of 1.5 ≤ MET < 3.0. These exercises included slow leg raises, seated stepping, simple squats, slow walking, and ankle mobility exercises. During this process, facial expressions were captured using OpenFace software, extracting micro-expression features such as concentration and pain index. Simultaneously, a low-intensity exercise physiological characteristic curve (DUS) was constructed using real-time physiological data recording and compared with the USB to calculate the relative rate of change (RCR). If the RCR is below -10%, the subject's individualized lower training limit (LBT) is set to a lower level to prevent excessive fatigue or injury; if the RCR exceeds +20%, the individualized upper training limit (UBT) is set to a more cautious threshold to avoid excessive physiological burden.

[0126] Based on the above data, a reinforcement learning model is initialized. The model's state variables include the user's real-time physiological signals (such as EMG and HRV) and facial expressions (concentration, pain index), as well as personalized recovery thresholds (LBT and UBT) and the current RCR value. The action space encompasses training intensity, duration, rest intervals, and training type transitions. For example, if the system detects a pain index exceeding 0.8 and a significant decrease in concentration, the reinforcement learning model triggers the action options of "reducing intensity" or "shortening duration." The reward function consists of five components: training effect reward, personalized recovery threshold reward, training compliance reward, training goal achievement reward, and user expression reward. These components correspond to the improvement in the user's ProgressIndex after training, whether the threshold is exceeded, the patient's willingness to participate, the completion of the phased goal, and the status reflected by micro-expressions. The training time step is set to 15 seconds, with each training round lasting ten time steps, for a total of 150 seconds to complete a reinforcement learning policy update. After completing several rounds of training, the system calculates the advantage function through the generalized advantage estimation method, then uses the gradient descent method to update the strategy parameters, and combines the clipping mechanism to stabilize the optimization process of reinforcement learning.

[0127] During the implementation process, in order to make micro-expressions and gestures better play a role in training optimization, several IF-THEN rules were set: when the pain index exceeds 0.8 and the concentration is lower than 0.3, the system automatically reduces the training intensity by 20% and observes the next three rounds of training; when the pain index is lower than 0.4 and the concentration is higher than 0.7, the training time will be increased by 10% each time in the next two rounds, but if the pain index rises to greater than 0.7, the adjustment will be immediately withdrawn. If the user's gesture clearly indicates to continue training or the concentration is detected to be higher than 0.9, the rest interval will be shortened by 10% in the next round of training. When evaluating the rehabilitation progress of user data after training, the time series method is used to fit the rehabilitation progress curve, and in every ten training sessions, it is checked whether 30% of the data points exceed the personalized rehabilitation threshold range to determine whether the training plan needs to be updated again or the LBT and UBT need to be adjusted.

[0128] After the test, the main data were recorded as follows:

[0129] The initial ProgressIndex values ​​of the experimental subjects ranged from 41.20 to 42.90, with an average of 42.15 and a standard deviation of approximately 1.08. One month after the application of the method of the present invention, the average ProgressIndex detected rose to 71.56, with a minimum of 69.20, a maximum of 73.45, and a standard deviation of approximately 1.85. The initial ProgressIndex value of the traditional method (fixed training program) group for reference was 42.05 on average, and the final average value detected after the same length of time was 62.34, with a minimum of 59.90, a maximum of 64.10, and a standard deviation of approximately 1.66. The pain index was averaged under the reinforcement learning optimization. The average decrease was 0.33, from the initial 1.05 to 0.72, with the minimum decrease of 0.28 and the maximum decrease of 0.38; the average decrease in the control group was only 0.15; the number of times the user actively gestured to indicate that he was more willing to train reached an average of 3.20 times per ten training sessions in the method group of the present invention, while it was only 1.54 times in the control group; during the training process, it was observed that the time period with concentration above 0.80 increased by 17.50% cumulatively, and the time period with pain index exceeding 0.80 decreased by 22.40% cumulatively; in the last three training sessions, the system detected that the RCR of two subjects was greater than +20% for a long time, so it automatically reduced the training intensity by 15% to 20% and extended the rest interval by 10.00%.

[0130] It can be seen from the above data that the personalized rehabilitation threshold and reinforcement learning model used in this embodiment realize flexible adjustment of the rehabilitation training process, and show significant advantages when compared with the traditional fixed scheme. First, the average Progress Index in the experimental subjects increased from 42.15 to 71.56, an increase of more than 29 percentage points, while the control group only increased from 42.05 to 62.34, an increase of about 20 percentage points. In terms of magnitude, the progress brought about by the method of the present invention is obviously more obvious, indicating that personalized rehabilitation thresholds and adaptive training strategies can more effectively tap the user's physical potential and avoid ineffective or overtraining.

[0131] Further analysis shows that the significant decrease in the pain index is one of the important advantages of the method of the present invention compared to traditional methods. The average decrease in the method group was 0.33, while that of the control group was only 0.15. Combined with micro-expression analysis, it can be inferred that the reinforcement learning model immediately reduced the training intensity after sensing that the user's pain index was higher than 0.8 and the concentration was lower than 0.3, which greatly reduced the user's training discomfort. In traditional fixed training programs, fine-tuning is usually performed during routine checkups, and the amplitude may be too large or the timing is not timely, resulting in low user acceptance of the training program, which in turn affects the overall rehabilitation effect.

[0132] At the same time, the number of times the user actively gestured to indicate a preference for training was as high as 3.20 times per ten training sessions in the group using the method of the present invention, almost double the 1.54 times in the control group. This shows that when the system can promptly refine or call back the training plan based on the user's fatigue, pain index, and concentration, the user's training compliance is significantly improved, and the continuity and durability of the training are enhanced. Especially with the cooperation of the IF-THEN rule, if the pain index is detected to be continuously high, the system will also actively ask the user whether to interrupt or change the action. This level of detail in human-computer interaction allows users to gain a greater sense of security and initiative during the training process.

[0133] Furthermore, both high values ​​(over +20%) and low values ​​(below -10%) in the RCR data are promptly controlled. Under the method of the present invention, if the RCR is greater than +20% for a long time, the system will immediately reduce the training intensity within a certain range (15% to 20%) and extend the rest interval. The control group lacks timely monitoring and response, which may cause some trainees to passively persist due to fatigue and joint pain, resulting in a greater increase in the pain index. This shows that the method of the present invention helps to balance the training effect and patient comfort and reduce unnecessary risks. Increasing the training time in a state of high concentration can also maximize the training benefits when the user is in good physical and mental state.

[0134] In terms of algorithm operation and application scenarios, multiple rounds of iterative training of a reinforcement learning model (PPO algorithm) demonstrated that it can effectively capture fluctuating user data at different time periods, and that it can also take into account training effect rewards, recovery threshold rewards, and expression feature rewards in the strategy optimization objective function. This demonstrates that the algorithm framework possesses sufficient adaptability to address individual differences. Compared with traditional methods, the intelligent assistance method in this embodiment demonstrates its creativity and novelty: it not only enables real-time dynamic adjustment of rehabilitation plans, but also fully considers human-computer interaction factors such as micro-expressions and gestures, making the training process more humane and effectively avoiding the shortcomings of fixed plans. Data analysis shows that the recovery efficiency and comfort of users' physical functions are both improved, demonstrating the distinct advantages of personalization, intelligence, and sustainability, and providing reliable technical support for subsequent large-scale promotion and application.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent assistance method for rehabilitation nursing, characterized in that: include: Acquire and input user data to form personalized rehabilitation thresholds; Forming personalized rehabilitation thresholds involves using OpenFace to analyze user micro-expressions and extract the user's facial features during low-intensity movements; Using the user's real-time physiological signals before training, a static physiological characteristic baseline USB of the user is established; Through x ≤MET< The low-intensity movements are collected during training, and the user's real-time physiological signals and micro-expressions are collected. The key features of each movement are extracted, and a low-intensity exercise physiological characteristic curve DUS is established. This is compared with the static physiological characteristic baseline USB and the relative change rate RCR is calculated. MET stands for metabolic equivalent, a unit for measuring exercise intensity. Indicates the lower limit of MET value, Indicates the upper limit of MET value; personalized rehabilitation threshold includes the lower limit of individualized training LBT and the upper limit of individualized training UBT; When RCR is lower than When the RCR exceeds , is the upper limit of individual training UBT, where represents the lower threshold of individualized training, Indicates the upper threshold of individualized training; Initialize the reinforcement learning model, collect the user's real-time physiological feedback and combine it with the personalized rehabilitation threshold to generate a preliminary training plan, and optimize the training plan by combining the user's micro-expressions and gestures; the initialization of the reinforcement learning model includes defining the state variables of the reinforcement learning and action space , set the reward function ; The state variable Including: user's real-time physiological signals, RCR, facial features and personalized rehabilitation threshold; the action space Including: training intensity, training duration, rest interval and training type conversion; the reward function Including: training effect rewards, personalized recovery threshold rewards, training compliance rewards, training goal achievement rewards and user expression feature rewards; The personalized rehabilitation threshold rewards include: When punishment is given; when When punishment is given; when When, give rewards; The training compliance reward includes giving a reward when the user actively indicates through gestures that he or she is more willing to participate in the training; The facial expression features include concentration and pain index; when concentration And the pain index When the pain index When punishment is imposed, represents the concentration threshold, and represents the pain index threshold; Evaluate the user's rehabilitation progress based on post-training data to determine whether the training program needs to be adjusted; Rehabilitation progress assessment includes extracting rehabilitation features from user data after training and constructing rehabilitation progress indicators; fitting rehabilitation progress curves with rehabilitation progress indicators using time series methods. , every ten trainings are set as an analysis window. In an analysis window, when When p% of the data points are outside the personalized recovery threshold, the training plan is updated. p% indicates the percentage of data points that exceed the personalized recovery threshold within the current analysis window. Based on the judgment results, the training plan is updated and the personalized rehabilitation goals are adjusted; the user's real-time physiological feedback, , the facial features are aligned and normalized in the same time window to form a state vector, which is then combined into a decision adjustment matrix. The decision adjustment matrix is ​​used to reversely deduce the deviation of the training intensity and update the training plan; In the process of updating the training scheme, a pruning mechanism is used to construct a strategy to optimize the objective function. , the formula is: ， in, represents the policy optimization objective function, Represents the time step Perform expectation calculations, represents the probability ratio, Indicates that under the current policy, in the state Select Action The probability of Indicates that under the old policy, in the state Select Action The probability of represents the advantage function, represents the clipping function, Indicates the clipping range.

2. The intelligent assistance method for rehabilitation nursing according to claim 1, characterized in that: Generating a preliminary training plan involves collecting n time steps 、 and , record policy model , calculate each state Take the following actions The probability distribution of ; n time steps 、 and Combine , using the generalized advantage estimation method to calculate the advantage function ; Generating a preliminary training plan also includes constructing a policy optimization objective function and updating policy parameters via gradient descent; Adopting the pruning mechanism to construct a strategy to optimize the objective function ; Updating strategy parameters includes defining the final loss function ,renew , mapping the strategy parameters to the training scheme, the formula is expressed as: ， in, According to the strategy Calculate the current state Next best action The probability distribution of Indicates sampling a specific action according to the probability distribution Conduct training; is a strategy parameter, indicating The parameter vector of .

3. The intelligent assistance method for rehabilitation nursing according to claim 2, characterized in that: Optimizing training programs based on user micro-expressions and gestures includes: , facial features and user gestures as input, and use IF-THEN rules to Make adjustments; The IF-THEN rule includes: IF the user's micro-expression pain index > q and the concentration < d, THEN reduce the training intensity, and continuously observe the user's adaptation situation in subsequent rounds of training. At the same time, automatically adjust the training goal to be biased towards low-intensity load. If the pain index remains higher than a after rounds, then introduce active interaction and ask the user whether to suspend the training; IF users' micro-expression pain index And focus , THEN increase the training time each time in the future training, and monitor the pain index changes at the same time. If the user's pain index increases to , the adjustment will be automatically withdrawn and the original duration will be restored; IF user gestures to continue training or concentration , THEN the user shortens the rest interval in the next training session. If the user's pain index increases during training, the regular rest interval is restored; in, Indicates a high threshold of pain index, Indicates the low threshold of the pain index, Represents the recovery threshold of the pain index, Indicates a low threshold of concentration, Indicates a medium threshold of concentration, Indicates a high threshold for concentration.

4. An intelligent assistance system for rehabilitation nursing using the method according to any one of claims 1 to 3, characterized in that: Data module, which acquires and enters user data to form personalized rehabilitation thresholds; The training program module initializes the reinforcement learning model, collects real-time physiological feedback from the user based on the personalized rehabilitation threshold, generates a preliminary training program, and optimizes the training program based on the user's micro-expressions and gestures; The evaluation module evaluates the rehabilitation progress of user data after training and determines whether the training plan needs to be adjusted; The adjustment module updates the training plan and adjusts the personalized rehabilitation goals based on the judgment results.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent assistance method for rehabilitation nursing described in any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent assistance method for rehabilitation nursing described in any one of claims 1 to 3 are implemented.

Images