Intelligent leg training rehabilitation method

Abstract

The invention discloses an intelligent leg training rehabilitation method which comprises the following steps: constructing a leg training rehabilitation system based on a deep learning model and a data mining analysis algorithm; according to the output of the leg training rehabilitation system, the rehabilitation training healing degree of the patient is analyzed, and the leg rehabilitation training content of the patient is customized; monitoring the expression and progress of the patient in the rehabilitation training process through the leg training rehabilitation system, and adjusting the leg rehabilitation training content; based on the monitoring result of the leg training rehabilitation system, an expression analysis module is introduced, the expression state of the patient is monitored, and human intervention is carried out; evaluating and optimizing the training content of the leg training rehabilitation system; in order to avoid excessive dependence on deep learning and a data mining algorithm, an expression analysis module is introduced, real-time expression state analysis is provided, a training rehabilitation strategy is adjusted in real time according to an analysis result, leg rehabilitation support better conforming to the expression state of a patient is provided for the patient, and the rehabilitation speed of the legs of the patient is increased.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence rehabilitation medicine, and specifically refers to an intelligent leg training rehabilitation method. Background Art

[0002] The demand for rehabilitation medical services continues to rise. Although my country's rehabilitation medical industry has established a three-level rehabilitation medical system, it still faces problems such as insufficient awareness and talent shortage.

[0003] The development of artificial intelligence technology has brought new possibilities to rehabilitation medicine. AI technology can provide differentiated rehabilitation solutions and improve rehabilitation efficiency and effectiveness by analyzing large amounts of data. For example, through deep learning algorithms, AI can predict the patient's rehabilitation process and adjust the rehabilitation plan.

[0004] Chinese Patent Publication No.: CN1 17672457A discloses an intelligent knee rehabilitation nursing method and device with micro-feedback, the method comprising: collecting the patient's leg nerve signal and gait posture parameters, filtering the leg nerve signal to obtain the primary nerve signal; constructing a primary nerve signal feature extraction model to extract the features of the primary nerve signal; using the rehabilitation gait correction model to generate knee care correction parameters, and perform real-time correction on the patient's leg knee posture during walking. The present invention performs multi-scale convolution feature and spatial perception information fusion processing on the leg nerve signal filtering results at different scales, obtains the neural signal features of spatial perception that are conducive to characterizing the abnormal neural signal, generates correction parameters based on the patient's gait posture parameters according to the abnormality of the neural signal feature distribution, and realizes knee movement rehabilitation correction nursing based on the patient's leg nerve micro-feedback.

[0005] However, over-reliance on deep learning and data mining algorithms in rehabilitation medicine may lead to neglect of the importance of differentiated leg training rehabilitation. Over-reliance on deep learning and algorithms can easily ignore the patient's leg rehabilitation training expressions and leg action expressions, resulting in slow recovery of patients. Summary of the invention

[0006] In order to solve the problems in the above-mentioned prior art that over-reliance on deep learning and algorithms in rehabilitation medicine may lead to neglect of the importance of differentiated leg training rehabilitation, and over-reliance on deep learning and algorithms easily ignores the patient's emotions and behavioral expressions, resulting in slow patient recovery, the present invention proposes an intelligent leg training rehabilitation method to improve the above-mentioned problems.

[0007] The specific application is as follows:

[0008] An intelligent leg training rehabilitation method comprises the following steps:

[0009] S1: Based on deep learning models and data mining analysis algorithms, build a leg training rehabilitation system to collect and analyze patient data;

[0010] S2: Analyze the patient's rehabilitation training healing degree according to the output of the leg training rehabilitation system, create rehabilitation training goals according to each patient, and customize the patient's leg rehabilitation training content in combination with the patient's leg rehabilitation training goals;

[0011] S3: monitoring the patient's performance and progress during the rehabilitation training process through the leg training rehabilitation system, and adjusting the leg rehabilitation training content and goals according to the patient's performance and feedback;

[0012] S4: Based on the monitoring results of the leg training rehabilitation system, an expression analysis module is introduced to monitor the patient's expression state and perform human intervention;

[0013] S5: Evaluate the leg rehabilitation training content of the leg training rehabilitation system, and optimize the system based on the evaluation result.

[0014] Furthermore, the leg training rehabilitation system at least includes a data analysis and prediction module, a leg rehabilitation training target setting module, a leg rehabilitation training monitoring and adjustment module, an expression analysis module and an evaluation and optimization module;

[0015] The data analysis and prediction module is based on deep learning and data mining algorithms to analyze patient data and predict the patient's performance and progress during leg rehabilitation training;

[0016] The leg rehabilitation training target formulation module formulates leg rehabilitation training targets and leg rehabilitation training contents for each target patient according to the analysis results of all patient data in the system;

[0017] The leg rehabilitation training monitoring and adjustment module monitors the patient's performance and progress during the leg rehabilitation training and adjusts the content and goals of the leg rehabilitation training;

[0018] The expression analysis module monitors the patient's expression state through the leg training rehabilitation system;

[0019] The evaluation and optimization module is used to evaluate the leg rehabilitation training content of the leg training rehabilitation system, and improve the system through the evaluation results, update patient data, and retrain and optimize the leg training rehabilitation system.

[0020] Furthermore, the leg rehabilitation training target setting module specifically includes:

[0021] L1: The training feature data extracted from the historical leg rehabilitation training data of all patients in the system are input into the leg rehabilitation training analysis model, and the data mining technology of the clustering algorithm and the cosine similarity algorithm are used to output the target recommended training content for the target patient;

[0022] L2: Determine the target patient's preference weights for multiple training contents based on the patient's historical training content data obtained from the system, generate a training content preference weight table, and calculate the recommended values ​​of multiple training and rehabilitation courses in the target training and rehabilitation course set based on the training content preference weight table and the attention value of each training and rehabilitation course;

[0023] L3: Sort the recommendation values ​​and recommend the courses with the highest recommendation values ​​to patients;

[0024] The specific implementation of L2 is:

[0025] The first training duration of the patient's training rehabilitation course for each training content in the historical training content data is extracted, and the second training duration of the patient's training rehabilitation course for each training content within the target time range is extracted from the historical training content data, and the preference weight of any training content of the patient is calculated by the following formula:

[0026] B = β1T1 + β2T2;

[0027] In the formula, B is the inclination weight of the training content, T1 is the first training duration of the training content, T2 is the second training duration of the content format, β1 and β2 are the first weight coefficient and the second weight coefficient respectively;

[0028] The above formula is used to calculate the inclination weight of each training content, and a training content inclination weight table is generated. The recommended value of any training rehabilitation course is calculated according to the following formula:

[0029] Q = BD;

[0030] In the formula, Q is the recommended value of the training and rehabilitation course, B is the preference weight of the training content to which the training and rehabilitation course belongs, and D is the attention value of the training and rehabilitation course. The recommended value of each training and rehabilitation course in the target training and rehabilitation course set is calculated by the above formula;

[0031] The leg rehabilitation training analysis model is specifically implemented as follows:

[0032] The leg rehabilitation training analysis model is trained through the training data set. For the historical training data of multiple patients in the leg training rehabilitation system, the time characteristic data of each patient in each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are extracted. The time characteristic data of each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are associated to construct a data subset, and a training set composed of multiple data subsets is generated. The leg rehabilitation training analysis model is trained through the training set to obtain a trained leg rehabilitation training analysis model.

[0033] Furthermore, in S2, the leg training rehabilitation system uses a data analysis algorithm based on a time series analysis method to analyze the healing degree of the patient's leg rehabilitation training, wherein the specific analysis steps of the time series analysis method are:

[0034] S21: Collect the patient's leg rehabilitation training healing data;

[0035] S22: Define the mean μ used to calculate the time series in the sliding average;

[0036] S23: using a sliding average method to perform a sliding average operation on the patient's leg rehabilitation training healing degree data;

[0037] S24: Based on the analysis results, infer the changing trend of the patient's leg rehabilitation training healing degree and set leg rehabilitation training goals.

[0038] Furthermore, the specific calculation method of the sliding average method is:

[0039]

[0040] Among them, X t represents the sliding average at time point t; θ t-i+1 represents the leg rehabilitation training healing data points from time point t-i+1 to t; q is the order of the model, μ is the mean of the time series, and γt is the random error term at time t.

[0041] Furthermore, in S3, the leg training rehabilitation system predicts the patient's performance and progress during the leg rehabilitation training based on the deep learning model, and compares the predictions with the actual leg rehabilitation training performance and progress to determine the leg rehabilitation training effect of the patient, wherein the specific calculation method of the deep learning model prediction is: in the long short-term memory network LSTM:

[0042] f t =tanh(F hx ·x t +F hh ·f t-1+a h );

[0043] Among them, x t represents the input data at time point t; f t-1 represents the forgetting state at time point t-1; F hx represents the weight matrix input to the forget state; F hh Represents the weight matrix from the forgotten state to the forgotten state; a h Represents the bias term of the forgetting state; tanh represents the hyperbolic tangent activation function;

[0044] At each time point t, based on the forgetting state f t Predict the leg rehabilitation training progress at the next time step, then the prediction of the output layer is expressed as:

[0045]

[0046] in, represents the predicted leg rehabilitation training progress at time point t+1; Fyh represents the weight matrix from the forgotten state to the output layer; a y Represents the bias term of the output layer; Sigmoid represents the activation function.

[0047] Furthermore, in said S4, the expression analysis module is based on a natural language understanding system and is used to analyze the patient's expression;

[0048] Wherein, the natural language understanding system includes at least a visual analysis module, a speech analysis module and an expression analysis module;

[0049] The visual analysis module captures the patient's facial expression and leg walking posture through a camera; the voice analysis module captures the patient's voice information using a microphone device.

[0050] Furthermore, the expression analysis module analyzes the patient's expression state based on the multimodal deep leg training rehabilitation model through the patient's facial expression, leg walking posture and voice data collected by the visual analysis module and the voice analysis module, wherein the multimodal deep leg training rehabilitation model is specifically:

[0051] Suppose there are three inputs, namely facial expression data Q a , Leg walking posture data Q b and voice data Q c , define three branch neural networks respectively, let g(Q a ) represents the neural network output of the facial expression data branch, g(Q b ) represents the neural network output of the leg walking posture data branch, g(Q c ) represents the neural network output of the speech data branch, then:

[0052] D=Stack(g(Q a ), g(Q b ), g(Q c ));

[0053] P(Y=i|Q a , Q b , Q c ) = Sigmoid((m(D))i;

[0054] Where D represents the three-branch neural network g(Q a ), g(Q b ), g(Q c ) outputs stacked together in a new dimension; Stack means that multiple tensors will be stacked in a new dimension to generate a larger tensor; P(Y=i|Q a , Q b , Q c ) indicates that given the facial expression data Q a , Leg walking posture data Q b and voice data Q c In the case of , the probability that the sample belongs to the i-th type of expression; m(D) represents the neural network layer that further processes the stacked tensor D; (m(D)) i It represents the value of the i-th element in the vector output by the neural network model m; Sigmoid represents the activation function.

[0055] Furthermore, in S5, a mean square error loss function is used to measure the difference between the predicted value and the true value, so as to evaluate the leg rehabilitation training content of the leg training rehabilitation system:

[0056]

[0057] Among them, Loss represents the loss function; T represents the number of steps in the time series data; N represents the total number of output types; x t+1，i The i-th element in the one-hot encoding form represents the actual leg rehabilitation training progress at time point t+1; represents the predicted probability for the i-th category at time t+1; w i is the weight of the ith category.

[0058] Furthermore, the parameters of the model are adjusted by using the Bayesian optimization algorithm to minimize the loss function and achieve optimization and improvement of the system. The specific adjustment parameters of the Bayesian optimization algorithm are:

[0059] K m =Ka·δ KLoss;

[0060] Among them, K m represents the parameters of the updated model; a represents the leg training recovery rate, which is used to control the frequency of parameter updating; δ K Loss represents the gradient of the loss function with respect to the parameter K; K represents a hyperparameter used to control the balance between model iteration and utilization.

[0061] The beneficial effects of an intelligent leg training rehabilitation method of the present invention are as follows:

[0062] The present invention constructs a leg training and rehabilitation system based on a deep learning model and a data mining analysis algorithm; analyzes the patient's rehabilitation training healing degree and customizes the patient's leg rehabilitation training content according to the output of the leg training and rehabilitation system; monitors the patient's performance and progress during the rehabilitation training process through the leg training and adjusts the leg rehabilitation training content; introduces an expression analysis module based on the monitoring results of the leg training and rehabilitation system to monitor the patient's expression state and perform human intervention; evaluates and optimizes the training content of the leg training and rehabilitation system; introduces an expression analysis module to provide real-time expression state analysis to avoid over-reliance on deep learning and data mining algorithms, and adjusts the training and rehabilitation strategy in real time according to the analysis results, so as to provide the patient with leg rehabilitation support that is more in line with his or her expression state and improve the patient's leg rehabilitation speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 The present invention is a flowchart of an intelligent leg training and rehabilitation method. DETAILED DESCRIPTION

[0064] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] Example 1

[0066] Figure 1 The present invention is a flowchart of an intelligent leg training and rehabilitation method.

[0067] The method comprises steps S1-S5:

[0068] S1: Based on deep learning models and data mining analysis algorithms, build a leg training rehabilitation system to collect and analyze patient data;

[0069] Specifically, patient data includes age, gender, historical medical records, clinical registration data, clinical symptom report data, clinical diagnosis and treatment test data, and clinical imaging data;

[0070] S2: Analyze the patient's rehabilitation training healing degree according to the output of the leg training rehabilitation system, create rehabilitation training goals according to each patient, and customize the patient's leg rehabilitation training content in combination with the patient's leg rehabilitation training goals;

[0071] S3: monitoring the patient's performance and progress during the rehabilitation training process through the leg training rehabilitation system, and adjusting the leg rehabilitation training content and goals according to the patient's performance and feedback;

[0072] S4: Based on the monitoring results of the leg training rehabilitation system, an expression analysis module is introduced to monitor the patient's expression state and perform human intervention;

[0073] S5: Evaluate the leg rehabilitation training content of the leg training rehabilitation system, and optimize the system based on the evaluation result.

[0074] Furthermore, the leg training rehabilitation system at least includes a data analysis and prediction module, a leg rehabilitation training target setting module, a leg rehabilitation training monitoring and adjustment module, an expression analysis module and an evaluation and optimization module;

[0075] The data analysis and prediction module is based on deep learning and data mining algorithms to analyze patient data and predict the patient's performance and progress during leg rehabilitation training;

[0076] The leg rehabilitation training target formulation module formulates leg rehabilitation training targets and leg rehabilitation training contents for each target patient according to the analysis results of all patient data in the system;

[0077] Specifically, the leg rehabilitation training goals and leg rehabilitation training content will be adjusted according to the patient's rehabilitation training progress, rehabilitation training healing degree and needs;

[0078] The leg rehabilitation training monitoring and adjustment module monitors the patient's performance and progress during the leg rehabilitation training and adjusts the content and goals of the leg rehabilitation training;

[0079] The expression analysis module monitors the patient's expression state through the leg training rehabilitation system;

[0080] Specifically, the patient's expression state includes happiness, joy, excitement, anxiety, disgust or frustration. If necessary, the system conducts human intervention to promote the patient's emotional health and development and ensure that the patient is in a good emotional state during leg rehabilitation training;

[0081] The evaluation and optimization module is used to evaluate the leg rehabilitation training content of the leg training rehabilitation system, and improve the system through the evaluation results, update patient data, and retrain and optimize the leg training rehabilitation system.

[0082] Furthermore, the leg rehabilitation training target setting module specifically includes:

[0083] L1: The training feature data extracted from the historical leg rehabilitation training data of all patients in the system are input into the leg rehabilitation training analysis model, and the data mining technology of the clustering algorithm and the cosine similarity algorithm are used to output the target recommended training content for the target patient;

[0084] Specifically, the patient training features are classified through a clustering algorithm to match the target patient's feature type. In simple terms, the target patient's specific condition is of a certain type. Through big data, the recommended training content for the patient is further formulated quickly for the condition type. The clustering algorithm includes but is not limited to the K-Means algorithm or the DBSCAN algorithm.

[0085] L2: Determine the target patient's preference weights for multiple training contents based on the patient's historical training content data obtained from the system, generate a training content preference weight table, and calculate the recommended values ​​of multiple training and rehabilitation courses in the target training and rehabilitation course set based on the training content preference weight table and the attention value of each training and rehabilitation course;

[0086] L3: Sort the recommendation values ​​and recommend the courses with the highest recommendation values ​​to patients;

[0087] The specific implementation of L2 is:

[0088] The first training duration of the patient's training rehabilitation course for each training content in the historical training content data is extracted, and the second training duration of the patient's training rehabilitation course for each training content within the target time range is extracted from the historical training content data, and the preference weight of any training content of the patient is calculated by the following formula:

[0089] B = β1T1 + β2T2;

[0090] In the formula, B is the inclination weight of the training content, T1 is the first training duration of the training content, T2 is the second training duration of the content format, β1 and β2 are the first weight coefficient and the second weight coefficient respectively;

[0091] The above formula is used to calculate the inclination weight of each training content, and a training content inclination weight table is generated. The recommended value of any training rehabilitation course is calculated according to the following formula:

[0092] Q = BD;

[0093] In the formula, Q is the recommended value of the training and rehabilitation course, B is the preference weight of the training content to which the training and rehabilitation course belongs, and D is the attention value of the training and rehabilitation course. The recommended value of each training and rehabilitation course in the target training and rehabilitation course set is calculated by the above formula;

[0094] The leg rehabilitation training analysis model is specifically implemented as follows:

[0095] The leg rehabilitation training analysis model is trained through the training data set. For the historical training data of multiple patients in the leg training rehabilitation system, the time characteristic data of each patient in each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are extracted. The time characteristic data of each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are associated to construct a data subset, and a training set composed of multiple data subsets is generated. The leg rehabilitation training analysis model is trained through the training set to obtain a trained leg rehabilitation training analysis model.

[0096] Furthermore, in S2, the leg training rehabilitation system uses a data analysis algorithm based on a time series analysis method to analyze the healing degree of the patient's leg rehabilitation training, wherein the specific analysis steps of the time series analysis method are:

[0097] S21: Collect the patient's leg rehabilitation training healing data;

[0098] S22: Define the mean μ used to calculate the time series in the sliding average;

[0099] S23: using a sliding average method to perform a sliding average operation on the patient's leg rehabilitation training healing degree data;

[0100] S24: Based on the analysis results, infer the changing trend of the patient's leg rehabilitation training healing degree and set leg rehabilitation training goals.

[0101] Furthermore, the specific calculation method of the sliding average method is:

[0102]

[0103] Among them, X t represents the sliding average at time point t; θ t-i+1 represents the leg rehabilitation training healing data points from time point t-i+1 to t; q is the order of the model, μ is the mean of the time series, and Yt is the random error term at time t.

[0104] Specifically, the sliding average method is used to observe the overall trend of the patient's healing degree over time. Based on the results calculated in the sliding average, the trends of the patient's healing degree such as increase, decrease or stability can be observed, so as to better understand the patient's leg healing status, and combine the historical healing data, healing assessment data, healing speed and other information of other patients in the past, and then predict the patient's future leg rehabilitation training performance.

[0105] Furthermore, in S3, the leg training rehabilitation system predicts the patient's performance and progress during the leg rehabilitation training based on the deep learning model, and compares the predictions with the actual leg rehabilitation training performance and progress to determine the leg rehabilitation training effect of the patient, wherein the specific calculation method of the deep learning model prediction is: in the long short-term memory network LSTM:

[0106] f t =tanh(F hx ·x t +F hh ·f t-1 +a h );

[0107] Among them, x t represents the input data at time point t; f t-1 represents the forgetting state at time point t-1; F hx represents the weight matrix input to the forget state; F hh Represents the weight matrix from the forgotten state to the forgotten state; a h Represents the bias term of the forgetting state; tanh represents the hyperbolic tangent activation function;

[0108] At each time point t, based on the forgetting state f t To predict the leg rehabilitation training progress at the next time step, the prediction of the output layer is expressed as:

[0109]

[0110] in, represents the predicted leg rehabilitation training progress at time point t+1; F yh Represents the weight matrix from the forgotten state to the output layer; a y Represents the bias term of the output layer; Sigmoid represents the activation function.

[0111] In this embodiment, the leg training rehabilitation system predicts the patient's performance and progress during rehabilitation training based on a deep learning model, and compares the predictions with the actual rehabilitation training performance and progress to determine the patient's rehabilitation training effect.

[0112] Furthermore, in said S4, the expression analysis module is based on a natural language understanding system and is used to analyze the patient's expression;

[0113] Wherein, the natural language understanding system includes at least a visual analysis module, a speech analysis module and an expression analysis module;

[0114] The visual analysis module captures the patient's facial expression and leg walking posture through a camera; the voice analysis module captures the patient's voice information using a microphone device.

[0115] Specifically, voice information includes the patient's speaking speed, pitch, tone and language expression characteristics; the expression analysis module can provide real-time expression state analysis, and adjust the patient's rehabilitation training strategy or provide support in real time based on the analysis results. Expression recognition helps to improve the patient's interactive experience with the artificial intelligence system, making the leg rehabilitation training process more humane, closer to patient needs, and improving patient enthusiasm. Through expression recognition, medical staff can more comprehensively evaluate the patient's leg rehabilitation status and emotional state, not only paying attention to the patient's healing progress, but also paying attention to the patient's emotions and mental health. The expression state analysis includes at least emotional information.

[0116] In this embodiment, natural language processing technology is used to extract the patient's leg walking posture features through the mmPose-NLP method, which is a sequence-to-sequence (Seq2Seq) skeleton key point estimator inspired by natural language processing. It uses millimeter wave (mmWave) radar data to accurately estimate up to 25 skeleton key points. This method voxelizes the radar point cloud (PCL) data, similar to the tokenization process in NLP, and then inputs the voxelized radar data frame into the mmPose-NLP architecture to predict the voxel indexes of 25 skeleton key points, which are then converted back to real-world 3D coordinates. This process is similar to keyword extraction in NLP. Through keyword extraction analysis, the patient's current leg rehabilitation walking status is determined as painful, comfortable, improving recovery, and unsatisfactory recovery, and the patient's rehabilitation training strategy is adjusted in real time or support is provided based on the analysis results.

[0117] Furthermore, the expression analysis module analyzes the patient's expression state based on the multimodal deep leg training rehabilitation model through the patient's facial expression, leg walking posture and voice data collected by the visual analysis module and the voice analysis module, wherein the multimodal deep leg training rehabilitation model is specifically:

[0118] Suppose there are three inputs, namely facial expression data Q a , Leg walking posture data Q b and voice data Q c , define three branch neural networks respectively, let g(Q a) represents the neural network output of the facial expression data branch, g (Q b ) represents the neural network output of the leg walking posture data branch, g(Q c ) represents the neural network output of the speech data branch, then:

[0119] D=Stack(g(Q a ), g(Q b ), g(Q c ));

[0120] P(Y=i|Q a , Q b , Q c ) = Sigmoid((m(D))i;

[0121] Where D represents the three-branch neural network g(Q a ), g(Q b ), g(Q c ) outputs stacked together in a new dimension; Stack means that multiple tensors will be stacked in a new dimension to generate a larger tensor; P(Y=i|Q a , Q b , Q c ) indicates that given the facial expression data Q a , Leg walking posture data Q b and voice data Q c In the case of , the probability that the sample belongs to the i-th type of expression; m(D) represents the neural network layer that further processes the stacked tensor D; (m(D)) i It represents the value of the i-th element in the vector output by the neural network model m; Sigmoid represents the activation function.

[0122] In this embodiment, the expression of the Sigmoid function is:

[0123]

[0124] Wherein, Sigmoid(Q)i represents the output of the Sigmoid function acting on the i-th element of the vector Q, that is, the predicted probability of the i-th category; Q = [Q1, Q1, ..., Q N ] represents a real-valued vector of length N, Q i Represents the i-th element of the vector, which usually corresponds to the linear transformation result of the output layer of the neural network; Represents the exponential form of Qi; It represents the exponential summation of all elements in the vector Q, which is used for the normalization process of the Sigmoid function. The Sigmoid function ensures that the sum of the output probabilities of all categories is 1. In various classification problems, the output of the model can be interpreted as the predicted probability distribution of each category, and finally the category with the highest probability is selected as the prediction result.

[0125] Furthermore, in S5, a mean square error loss function is used to measure the difference between the predicted value and the true value, so as to evaluate the leg rehabilitation training content of the leg training rehabilitation system:

[0126]

[0127] Among them, Loss represents the loss function; T represents the number of steps in the time series data; N represents the total number of output types; x t+1，i The i-th element in the One-Hot encoding form represents the actual leg rehabilitation training progress at time point t+1; represents the predicted probability for the i-th category at time t+1; w i is the weight of the ith category.

[0128] Furthermore, the parameters of the model are adjusted by using the Bayesian optimization algorithm to minimize the loss function and achieve optimization and improvement of the system. The specific adjustment parameters of the Bayesian optimization algorithm are:

[0129] Km=Ka·δ K LoSs;

[0130] Among them, K m represents the parameters of the updated model; a represents the leg training recovery rate, which is used to control the frequency of parameter updating; δ K Loss represents the gradient of the loss function with respect to the parameter K; K represents a hyperparameter used to control the balance between model iteration and utilization.

[0131] The present invention constructs a leg training and rehabilitation system based on a deep learning model and a data mining analysis algorithm; analyzes the patient's rehabilitation training healing degree and customizes the patient's leg rehabilitation training content according to the output of the leg training and rehabilitation system; monitors the patient's performance and progress during the rehabilitation training process through the leg training and adjusts the leg rehabilitation training content; introduces an expression analysis module based on the monitoring results of the leg training and rehabilitation system to monitor the patient's expression state and perform human intervention; evaluates and optimizes the training content of the leg training and rehabilitation system; introduces an expression analysis module to provide real-time expression state analysis to avoid over-reliance on deep learning and data mining algorithms, and adjusts the training and rehabilitation strategy in real time according to the analysis results, so as to provide the patient with leg rehabilitation support that is more in line with his or her expression state and improve the patient's leg rehabilitation speed.

[0132] The present invention and its embodiments are described above, which is not restrictive. What is shown in the accompanying drawings is only one of the embodiments of the present invention, and the actual content is not limited to this. In short, if ordinary technicians in this field are inspired by it and do not deviate from the purpose of the invention, they can creatively design structural methods and embodiments similar to the technical scheme, which should all fall within the scope of protection of the present invention.

Claims

1. An intelligent leg training rehabilitation method, characterized in that: The following steps are involved: S1: Based on deep learning models and data mining analysis algorithms, build a leg training rehabilitation system to collect and analyze patient data; S2: Analyze the patient's rehabilitation training healing degree according to the output of the leg training rehabilitation system, create rehabilitation training goals according to each patient, and customize the patient's leg rehabilitation training content in combination with the patient's leg rehabilitation training goals; S3: monitoring the patient's performance and progress during the rehabilitation training process through the leg training rehabilitation system, and adjusting the leg rehabilitation training content and goals according to the patient's performance and feedback; S4: Based on the monitoring results of the leg training rehabilitation system, an expression analysis module is introduced to monitor the patient's expression state and perform human intervention; S5: Evaluate the leg rehabilitation training content of the leg training rehabilitation system, and optimize the system based on the evaluation result.

2. An intelligent leg training and rehabilitation method according to claim 1, characterized in that: The leg training rehabilitation system at least includes a data analysis and prediction module, a leg rehabilitation training target setting module, a leg rehabilitation training monitoring and adjustment module, an expression analysis module and an evaluation and optimization module; The data analysis and prediction module is based on deep learning and data mining algorithms to analyze patient data and predict the patient's performance and progress during leg rehabilitation training; The leg rehabilitation training target formulation module formulates leg rehabilitation training targets and leg rehabilitation training contents for each target patient according to the analysis results of all patient data in the system; The leg rehabilitation training monitoring and adjustment module monitors the patient's performance and progress during the leg rehabilitation training and adjusts the content and goals of the leg rehabilitation training; The expression analysis module monitors the patient's expression state through the leg training rehabilitation system; The evaluation and optimization module is used to evaluate the leg rehabilitation training content of the leg training rehabilitation system, and improve the system through the evaluation results, update patient data, and retrain and optimize the leg training rehabilitation system.

3. An intelligent leg training and rehabilitation method according to claim 2, characterized in that: The leg rehabilitation training target formulation module specifically includes: L1: The training feature data extracted from the historical leg rehabilitation training data of all patients in the system are input into the leg rehabilitation training analysis model, and the data mining technology of the clustering algorithm and the cosine similarity algorithm are used to output the target recommended training content for the target patient; L2: Determine the target patient's preference weights for multiple training contents based on the patient's historical training content data obtained from the system, generate a training content preference weight table, and calculate the recommended values ​​of multiple training and rehabilitation courses in the target training and rehabilitation course set based on the training content preference weight table and the attention value of each training and rehabilitation course; L3: Sort the recommendation values ​​and recommend the courses with the highest recommendation values ​​to patients; The specific implementation of L2 is: The first training duration of the patient's training rehabilitation course for each training content in the historical training content data is extracted, and the second training duration of the patient's training rehabilitation course for each training content within the target time range is extracted from the historical training content data, and the preference weight of any training content of the patient is calculated by the following formula: B = β1T1 + β2T2; In the formula, B is the inclination weight of the training content, T1 is the first training duration of the training content, T2 is the second training duration of the content format, β1 and β2 are the first weight coefficient and the second weight coefficient respectively; The above formula is used to calculate the inclination weight of each training content, and a training content inclination weight table is generated. The recommended value of any training rehabilitation course is calculated according to the following formula: Q = BD; In the formula, Q is the recommended value of the training and rehabilitation course, B is the preference weight of the training content to which the training and rehabilitation course belongs, and D is the attention value of the training and rehabilitation course. The recommended value of each training and rehabilitation course in the target training and rehabilitation course set is calculated by the above formula; The leg rehabilitation training analysis model is specifically implemented as follows: The leg rehabilitation training analysis model is trained through the training data set. For the historical training data of multiple patients in the leg training rehabilitation system, the time characteristic data of each patient in each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are extracted. The time characteristic data of each training behavior and the proportion of training time of the training rehabilitation courses for each training content in the training behavior are associated to construct a data subset, and a training set composed of multiple data subsets is generated. The leg rehabilitation training analysis model is trained through the training set to obtain a trained leg rehabilitation training analysis model.

4. The intelligent leg training and rehabilitation method according to claim 3, characterized in that: In S2, the leg training rehabilitation system uses a data analysis algorithm based on a time series analysis method to analyze the healing degree of the patient's leg rehabilitation training, wherein the specific analysis steps of the time series analysis method are: S21: Collect the patient's leg rehabilitation training healing data; S22: Define the mean μ used to calculate the time series in the sliding average; S23: using a sliding average method to perform a sliding average operation on the patient's leg rehabilitation training healing degree data; S24: Based on the analysis results, infer the changing trend of the patient's leg rehabilitation training healing degree and set leg rehabilitation training goals.

5. The intelligent leg training and rehabilitation method according to claim 4, characterized in that: The specific calculation method of the sliding average method is: Among them, X t represents the sliding average at time point t; θ t-i+1 represents the leg rehabilitation training healing data points from time point t-i+1 to t; q is the order of the model, μ is the mean of the time series, and γt is the random error term at time t.

6. The intelligent leg training and rehabilitation method according to claim 5, characterized in that: In S3, the leg training rehabilitation system predicts the patient's performance and progress in the leg rehabilitation training process based on the deep learning model, and compares it with the actual leg rehabilitation training performance and progress to determine the patient's leg rehabilitation training effect. The specific calculation method of the deep learning model prediction is: in the long short-term memory network LSTM: f t =tanh(F hx ·x t +F hh ·f t-1 +a h ); Among them, x t represents the input data at time point t; f t-1 represents the forgetting state at time point t-1; F hx represents the weight matrix input to the forget state; F hh Represents the weight matrix from the forgotten state to the forgotten state; a h Represents the bias term of the forgetting state; tanh represents the hyperbolic tangent activation function; At each time point t, based on the forgetting state f t To predict the leg rehabilitation training progress at the next time step, the prediction of the output layer is expressed as: in, represents the predicted leg rehabilitation training progress at time point t+1; F yh Represents the weight matrix from the forgotten state to the output layer; a y Represents the bias term of the output layer; Sigmoid represents the activation function.

7. An intelligent leg training and rehabilitation method according to claim 6, characterized in that: In S4, the expression analysis module is based on a natural language understanding system and is used to analyze the patient's expression; Wherein, the natural language understanding system includes at least a visual analysis module, a speech analysis module and an expression analysis module; The visual analysis module captures the patient's facial expression and leg walking posture through a camera; the voice analysis module captures the patient's voice information using a microphone device.

8. An intelligent leg training and rehabilitation method according to claim 7, characterized in that: The expression analysis module analyzes the patient's expression state based on the multimodal deep leg training rehabilitation model through the patient's facial expression, leg walking posture and voice data collected by the visual analysis module and the voice analysis module, wherein the multimodal deep leg training rehabilitation model is specifically: Suppose there are three inputs, namely facial expression data Q a , Leg walking posture data Q b and voice data Q c , define three branch neural networks respectively, let g(Q a ) represents the neural network output of the facial expression data branch, g(Q b ) represents the neural network output of the leg walking posture data branch, g(Q c ) represents the neural network output of the speech data branch, then: D=Stack(g(Q a ),g(Q b ),g(Q c )); P(Y=i|Q a ,Q b ,Q c )=Sigmoid((m(D)) i ; Where D represents the three-branch neural network g(Q a ), g(Q b ), g(Q c ) outputs stacked together in a new dimension; Stack means that multiple tensors will be stacked in a new dimension to generate a larger tensor; P(Y=i|Q a , Q b , Q c ) indicates that given the facial expression data Q a , Leg walking posture data Q b and voice data Q c In the case of , the probability that the sample belongs to the i-th type of expression; m(D) represents the neural network layer that further processes the stacked tensor D; (m(D)) i It represents the value of the i-th element in the vector output by the neural network model m; Sigmoid represents the activation function.

9. An intelligent leg training and rehabilitation method according to claim 8, characterized in that: In S5, a mean square error loss function is used to measure the difference between the predicted value and the true value, so as to evaluate the leg rehabilitation training content of the leg training rehabilitation system: Among them, Loss represents the loss function; T represents the number of steps in the time series data; N represents the total number of output types; x t+1，i The i-th element in the one-hot encoding form represents the actual leg rehabilitation training progress at time point t+1; represents the predicted probability for the i-th category at time t+1; w i is the weight of the ith category.

10. An intelligent leg training and rehabilitation method according to claim 9, characterized in that: The parameters of the model are adjusted by the Bayesian optimization algorithm to minimize the loss function and achieve optimization and improvement of the system. The specific adjustment parameters of the Bayesian optimization algorithm are: K m =K-a·δ K Loss; Among them, K m represents the parameters of the updated model; a represents the leg training recovery rate, which is used to control the frequency of parameter updating; δ K Loss represents the gradient of the loss function with respect to the parameter K; K represents a hyperparameter used to control the balance between model iteration and utilization.

Images