A digital traditional Chinese medicine physiotherapy method and system

Abstract

The present invention relates to the field of medical data processing technology, and in particular to a digital Chinese medicine physiotherapy method and system, comprising step S1, collecting patient medical history files; step S2, judging the patient's applicable physique according to the patient's medical history files; step S3, collecting EEG signals of applicable patients; step S4, standardizing the collected EEG signals of applicable patients; step S5, judging the standardized effectiveness of standardized EEG signals; step S6, judging the data effectiveness according to the collection interval; step S7, inputting the standardized EEG signals into a disease judgment model; step S8, making a physiotherapy plan for the patient's disease according to an expert physiotherapy knowledge database; step S9, real-time monitoring of the EEG signals of the patient during the physiotherapy process and judging the effectiveness of the physiotherapy; step S10, judging the physiotherapy results. The present invention improves the efficiency of digital Chinese medicine physiotherapy.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a digital traditional Chinese medicine physiotherapy method and system. Background Art

[0002] Digital TCM therapy is a new type of TCM treatment method that has emerged in recent years with the development of medical technology and digital technology. It combines the meridian theory, viscera and meridian theory of TCM and the anatomy, physiology and other knowledge of modern medicine, and uses digital technology to assist the process of TCM therapy. Digital technology is the basis of digital TCM therapy. It can digitize the diagnosis and treatment process of TCM, such as digital pulse diagnosis and tongue diagnosis. Through digital technology, it can more accurately obtain the patient's physical condition information, provide a basis for subsequent TCM treatment, and use machine learning and other technologies to analyze and process the patient's pulse, tongue and other information to more accurately judge the patient's physical condition and condition. In addition, artificial intelligence technology can also be used to optimize TCM treatment plans and improve treatment effects.

[0003] Chinese Patent Publication No.: CN113223703A discloses a method and device for evaluating TCM physiotherapy based on big data, by obtaining a first user physiotherapy plan; inputting the first user physiotherapy plan into a physiotherapy principle analysis model to obtain the plan principle information; obtaining a first matching degree according to the first user's condition information and the plan principle information; obtaining first evaluation information according to the first matching degree and the plan principle information; obtaining the first plan historical case information according to the first user physiotherapy plan; obtaining second evaluation information according to the first plan historical case information; obtaining second historical case information according to the first plan historical case information and the first user's condition information; obtaining third evaluation information according to the second historical case information; obtaining the first physiotherapy plan evaluation result according to the first, second, and third evaluation information. However, the scheme has a low accuracy rate in analyzing the patient's symptoms and cannot improve the TCM physiotherapy effect of the patient. Summary of the invention

[0004] To this end, the present invention provides a digital TCM physiotherapy method and system to overcome the problems in the prior art of inaccurate EEG signal analysis, low EEG signal analysis and processing efficiency, and inability to improve the TCM physiotherapy effect on patients due to differences in EEG signals generated by individual patients themselves.

[0005] To achieve the above objectives, on the one hand, the present invention provides a digital TCM physiotherapy method, comprising:

[0006] Step S1, collecting patient medical history files;

[0007] Step S2, judging the patient's applicable constitution according to the patient's medical history file;

[0008] Step S3, collecting EEG signals from applicable patients;

[0009] Step S4, standardizing the collected EEG signals of applicable patients and outputting standardized EEG signals;

[0010] Step S5, judging the validity of the standardized EEG signals, and correcting invalid standardized EEG signals according to the judgment result;

[0011] Step S6, judging the validity of the data according to the acquisition interval, and adjusting the validity judgment result of the standardized EEG signal and the patient acquisition site according to the judgment result;

[0012] Step S7, inputting the standardized EEG signal into the disease judgment model and outputting the patient's disease;

[0013] Step S8, making a physical therapy plan for the patient's condition according to the expert physical therapy knowledge database, and performing physical therapy;

[0014] Step S9, real-time monitoring of the patient's EEG signals during the physical therapy process, judging the effectiveness of the physical therapy, and adjusting the physical therapy plan according to the judgment result;

[0015] Step S10, judging the physical therapy result and optimizing the physical therapy plan according to the judgment result.

[0016] Furthermore, in step S2, when judging the patient's applicable constitution according to the patient's medical history file, the patient's constitution data in the patient's medical history file is compared with the standard applicable constitution threshold, and the patient's applicable constitution is judged according to the comparison result, wherein:

[0017] When the patient's physical fitness data falls within the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be qualified and marked as an applicable patient;

[0018] When the patient's physical fitness data falls outside the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be unqualified and is marked as a non-applicable patient.

[0019] Furthermore, in step S4, the method of standardizing the collected EEG signals of applicable patients includes:

[0020] Step S40, preprocessing the collected EEG signals of the applicable patients;

[0021] Step S41, extracting features from the preprocessed EEG signals of the applicable patients to obtain feature EEG signals;

[0022] Step S42, performing feature classification on the characteristic EEG signal to obtain a standardized EEG signal.

[0023] Furthermore, in step S5, when judging the effectiveness of standardization of the standardized EEG signal, the standardized EEG signal noise peak value K is compared with the preset EEG signal noise peak value K0, and the effectiveness of standardization is judged according to the comparison result, wherein:

[0024] When K≤K0, the standardized EEG signal is determined to be valid;

[0025] When K>K0, the standardized EEG signal is determined to be invalid, and the invalid standardized EEG signal is corrected and the EEG signal is standardized again.

[0026] Furthermore, in step S6, when judging the validity of the data according to the acquisition interval, the time T of the EEG signal acquisition is compared with the preset minimum acquisition time T1 and the preset maximum acquisition time T2, and the validity of the data is judged according to the comparison result, wherein:

[0027] When T<T1, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, and the patient acquisition site is adjusted to re-acquire the EEG signal of the applicable patient;

[0028] When T1≤T≤T2, the EEG signal acquisition is judged to be effective, and the preprocessing effectiveness judgment result is not adjusted;

[0029] When T>T2, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, the patient acquisition site is adjusted, and the EEG signal of the applicable patient is re-collected.

[0030] Furthermore, in step S7, a symptom judgment model is established based on historical symptom information, the standardized EEG signal is input into the symptom judgment model, and the patient's symptom is output;

[0031] Furthermore, in step S8, the patient's symptoms are compared with the preset patient symptoms in the expert physiotherapy knowledge database, wherein:

[0032] When there is a preset patient condition that is consistent with the patient's condition in the expert physical therapy knowledge database, the preset physical therapy plan corresponding to the preset patient condition is output as the patient's physical therapy plan;

[0033] When there is no preset patient symptom consistent with the patient's symptom in the expert physiotherapy knowledge database, the patient's symptom and the applicable patient EEG signal are pushed to the expert user terminal to obtain the patient physiotherapy plan given by the expert user terminal.

[0034] Furthermore, in step S9, after real-time monitoring of the EEG signal of the patient during the physical therapy, the monitoring data is obtained and the similarity P between the monitoring data and the preset monitoring data is calculated, and the similarity P is compared with the preset similarity P0, and the effectiveness of the physical therapy is judged according to the comparison result, wherein:

[0035] When P ≥ P0, the physical therapy is judged to be effective, the physical therapy plan is not adjusted, and the physical therapy continues;

[0036] When P<P0, it is determined that physical therapy is ineffective, the patient's symptoms and applicable patient EEG signals are pushed to the expert user terminal, a patient physical therapy plan given by the expert user terminal is obtained, and physical therapy is performed using the patient physical therapy plan given by the expert user terminal.

[0037] Furthermore, in step S10, the acupoint pressure resistance value R of the patient after physical treatment is compared with the preset acupoint pressure resistance value R0, and the physical treatment result is judged according to the comparison result, wherein:

[0038] When R≤R0, the physical therapy result is judged to be up to standard;

[0039] When R>R0, the physical therapy result is determined to be substandard, and the physical therapy plan is optimized according to the physical therapy plan optimization method.

[0040] Furthermore, in step S10, the method for optimizing the physical therapy plan includes:

[0041] Step S100, obtaining the patient's physical characteristic variance value Z;

[0042] Step S101, comparing the patient's physical characteristic variance value Z with a preset variance value Z0, and optimizing the physical therapy plan according to the comparison result.

[0043] Furthermore, in step S100, the variance value of the physical characteristics of the patient with the same patient disease as that corresponding to the standardized EEG signal in the training set of the patient's physical characteristics and disease judgment model is obtained and used as the patient's physical characteristics variance value Z.

[0044] Furthermore, in step S101, the patient's physical characteristic variance value Z is compared with a preset variance value Z0, and the physical therapy program is optimized according to the comparison result, wherein:

[0045] When Z ≥ Z0, the disease judgment model is optimized;

[0046] When Z<Z0, a notification is sent to the manager to remind him that the therapy device is distorted.

[0047] On the other hand, the present invention also provides a digital Chinese medicine physiotherapy system, comprising:

[0048] Information collection module, used to collect patient medical history files;

[0049] A module for judging the patient's applicable constitution is used to judge the patient's applicable constitution;

[0050] An EEG signal acquisition module is used to collect EEG signals from applicable patients;

[0051] An EEG signal processing module is used to perform standardized processing on the collected EEG signals of applicable patients and output standardized EEG signals;

[0052] The validity judgment module is used to judge the validity of the standardized EEG signals, and correct invalid standardized EEG signals according to the judgment results, and also judge the validity of the data according to the collection interval, and adjust the validity judgment results of the standardized EEG signals and the patient collection site according to the judgment results;

[0053] Symptom judgment module, used to judge the patient's symptoms and output;

[0054] The physiotherapy module is used to formulate a physiotherapy plan for the patient's condition based on the expert physiotherapy knowledge database and perform physiotherapy;

[0055] The real-time monitoring module is used to monitor the EEG signals of patients during physical therapy in real time and judge the effectiveness of physical therapy, and adjust the physical therapy plan according to the judgment results;

[0056] Feedback optimization module, used to judge the treatment results and optimize the treatment plan according to the results;

[0057] The distortion feedback module is used to remind the administrator of the distortion of the physical therapy device.

[0058] Compared with the prior art, the beneficial effects of the present invention are that the method collects the patient's medical history files through step S1, and judges the patient's applicable physique according to the patient's medical history files through step S2, so as to avoid discomfort and potential risks of the patient during physical therapy. The method collects EEG signals of applicable patients through step S3, and also performs standardization processing on the collected EEG signals of applicable patients through step S4, and outputs standardized EEG signals, so as to facilitate subsequent analysis based on the standardized EEG signals, thereby improving the analysis efficiency of EEG signals. The method judges the standardized validity of the standardized EEG signals through step S5, and corrects invalid standardized EEG signals. The method also judges the validity of the data through step S6, and adjusts the validity judgment results of the standardized EEG signals and the patient's collection site, and further The method improves the efficiency and accuracy of EEG signal analysis. The method inputs the standardized EEG signal into the disease judgment model through step S7, and outputs the patient's disease. Then, a physical therapy plan is made for the patient's disease according to the expert physical therapy knowledge database through step S8, and physical therapy is performed, thereby performing intelligent analysis of the patient's disease and the physical therapy plan based on the expert physical therapy knowledge database obtained from big data to improve the physical therapy effect. The method monitors the EEG signal of the patient during the physical therapy in real time and judges the effectiveness of the physical therapy through step S9, and adjusts the physical therapy plan according to the judgment result to improve the accuracy of the output of the physical therapy plan, thereby further improving the physical therapy effect. The method judges the physical therapy result through step S10, and optimizes the physical therapy plan according to the judgment result to ensure the effectiveness of the physical therapy result and improve the efficiency of traditional Chinese medicine physical therapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flow chart of the digital TCM physiotherapy method of this embodiment;

[0060] Figure 2 This is a schematic diagram of the process of the standardization processing method of this embodiment;

[0061] Figure 3 This is a flow chart of the method for optimizing the physical therapy program of this embodiment;

[0062] Figure 4 Schematic diagram of the structure of the digital Chinese medicine therapy system of this embodiment. DETAILED DESCRIPTION

[0063] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0065] See also Figure 1 As shown, a flow chart of the digital TCM physiotherapy method of this embodiment is shown, and the digital TCM physiotherapy method includes:

[0066] Step S1, collecting patient medical history files;

[0067] Step S2, judging the patient's applicable constitution according to the patient's medical history file;

[0068] Step S3, collecting EEG signals from applicable patients;

[0069] Step S4, standardizing the collected EEG signals of applicable patients and outputting standardized EEG signals;

[0070] Step S5, judging the validity of the standardized EEG signals, and correcting invalid standardized EEG signals according to the judgment result;

[0071] Step S6, judging the validity of the data according to the acquisition interval, and adjusting the validity judgment result of the standardized EEG signal and the patient acquisition site according to the judgment result;

[0072] Step S7, inputting the standardized EEG signal into the disease judgment model and outputting the patient's disease;

[0073] Step S8, making a physical therapy plan for the patient's condition according to the expert physical therapy knowledge database, and performing physical therapy;

[0074] Step S9, real-time monitoring of the patient's EEG signals during the physical therapy process, judging the effectiveness of the physical therapy, and adjusting the physical therapy plan according to the judgment result;

[0075] Step S10, judging the physical therapy result and optimizing the physical therapy plan according to the judgment result.

[0076] Specifically, the method is applied to a digital TCM physiotherapy device, and the EEG signals collected by the digital TCM physiotherapy device are analyzed and processed in combination with big data, and the patient's symptoms and physiotherapy plan are output to improve the working efficiency of the digital TCM physiotherapy device, realize the intelligence of the digital TCM physiotherapy device, and make corresponding TCM physiotherapy plans for different symptoms of the patient, thereby improving the efficiency and effect of TCM physiotherapy. The method collects the patient's medical history file through step S1, and judges the patient's applicable physique according to the patient's medical history file through step S2 to avoid discomfort and potential risks to the patient during the physiotherapy process. The method collects EEG signals of applicable patients through step S3, and also standardizes the collected EEG signals of applicable patients through step S4, and outputs standardized EEG signals for subsequent analysis based on the standardized EEG signals, thereby improving the analysis efficiency of EEG signals. The method judges the effectiveness of standardization of standardized EEG signals through step S5, and performs standardization on invalid standardized EEG signals. The EEG signal is corrected, and the validity of the data is judged through step S6, and the validity judgment result of the standardized EEG signal and the patient's collection site are adjusted to further improve the efficiency and accuracy of the EEG signal analysis. The method inputs the standardized EEG signal into the disease judgment model through step S7, and outputs the patient's disease, and then makes a physical therapy plan for the patient's disease according to the expert physical therapy knowledge database through step S8, and performs physical therapy, so as to perform intelligent analysis of the patient's disease and the physical therapy plan according to the expert physical therapy knowledge database obtained by big data to improve the physical therapy effect. The method monitors the EEG signal of the patient during the physical therapy in real time and judges the effectiveness of the physical therapy through step S9, and adjusts the physical therapy plan according to the judgment result to improve the accuracy of the output of the physical therapy plan, thereby further improving the physical therapy effect. The method judges the physical therapy result through step S10, and optimizes the physical therapy plan according to the judgment result to ensure the effectiveness of the physical therapy result and improve the efficiency of traditional Chinese medicine physical therapy.

[0077] Specifically, in step S1, the patient medical history file refers to a file that records in detail the patient's health status, disease occurrence, development and treatment process. This embodiment does not limit the method of collecting the patient's medical history file, and technical personnel in this field can set it freely, as long as the collection requirements of the patient's medical history file are met. For example, the patient's medical history file can be collected through big data or patient input.

[0078] Specifically, in step S2, when judging the patient's applicable constitution according to the patient's medical history file, the patient's constitution data in the patient's medical history file is compared with the standard applicable constitution threshold, and the patient's applicable constitution is judged according to the comparison result, wherein:

[0079] When the patient's physical fitness data falls within the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be qualified and marked as an applicable patient;

[0080] When the patient's physical fitness data falls outside the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be unqualified and is marked as a non-applicable patient.

[0081] Specifically, the patient's applicable physique refers to a physique capable of performing EEG signal acquisition, the applicable patient refers to a patient capable of performing EEG signal acquisition, the non-applicable patient refers to a patient incapable of performing EEG signal acquisition, and the patient's physique data refers to data characterizing the patient's physique in the patient's medical history file. This embodiment does not limit the content of the patient's physique data, and those skilled in the art can freely set it according to actual conditions, as long as the requirements for characterizing the patient's physique are met. For example, the patient's physique data can be set to include the patient's blood pressure value, blood sugar value, and body fat value. The standard applicable physique threshold value refers to The physical constitution regulations for the patient's applicable physical constitution, such as setting the standard applicable physical constitution threshold value including the preset patient blood pressure value threshold value [60, 139], the preset blood sugar value threshold value [3.9, 7.0], and the preset body fat value threshold value [0.15, 0.28], the patient's physical constitution data falling within the standard applicable physical constitution threshold value means that the patient's physical constitution data are all within the range of the standard applicable physical constitution threshold value, such as the patient's blood pressure value, blood sugar value and body fat value are all within the range of the preset patient blood pressure value threshold value [60, 139], the preset blood sugar value threshold value [3.9, 7.0] and the preset body fat value threshold value [0.15, 0.28].

[0082] Specifically, in step S3, when collecting EEG signals from applicable patients, EEG signals from applicable patients are collected by an electroencephalograph, and the EEG signal refers to the sum of electrical activities of brain neurons recorded from the scalp surface.

[0083] See also Figure 2 As shown, it is a schematic diagram of the process of the standardization processing method of this embodiment, and the standardization processing method includes:

[0084] Step S40, preprocessing the collected EEG signals of the applicable patients;

[0085] Step S41, extracting features from the preprocessed EEG signals of the applicable patients to obtain feature EEG signals;

[0086] Step S42, performing feature classification on the characteristic EEG signal to obtain a standardized EEG signal.

[0087] Specifically, the standardization process is performed by preprocessing the collected applicable patient EEG signals, extracting features from the preprocessed applicable patient EEG signals to obtain feature EEG signals, and then performing feature classification on the feature EEG signals.

[0088] Specifically, through step S4, the collected EEG signals of applicable patients are standardized to obtain standardized EEG signals for data analysis, thereby improving the therapeutic effect.

[0089] Specifically, in step S40, when preprocessing the collected EEG signals of the applicable patients, the collected EEG signals of the applicable patients are subjected to detrending, independent component analysis, bandpass filtering, notch filtering and blind source analysis.

[0090] Specifically, it can be understood that the present embodiment does not limit the detrending method, and relevant personnel in this field can freely set it according to actual conditions, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals. For example, the detrending method can be set to eliminate the long-term trend data in the applicable patient EEG signals. The present embodiment does not limit the independent component analysis method, and relevant personnel in this field can freely set it according to actual conditions, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals. For example, the independent component analysis method can be set to separate and remove components that are not related to the applicable patient EEG signals, such as electrooculography and electromyography. The present embodiment does not limit the bandpass filtering method, and relevant personnel in this field can freely set it according to actual conditions, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals. For example, the bandpass filtering method can be set to extract the applicable patient EEG signals within a specific frequency range. When removing low-frequency and high-frequency noise, this embodiment does not limit the notch filtering method, and relevant personnel in this field can freely set it according to actual conditions, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals. For example, the notch filtering method can be set to remove noise of a specific frequency, such as power frequency noise. This embodiment does not limit the blind source analysis method, and relevant personnel in this field can freely set it according to actual conditions, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals. For example, the blind source analysis method can be set to recover the source signal from the mixed signal when the source signal and the transmission channel are unknown. The specific frequency refers to a specific frequency band associated with brain activity and state. This embodiment does not set the range of the specific frequency, and those skilled in the art can freely set it, and it only needs to meet the needs of pre-processing the collected applicable patient EEG signals, such as A l pha waves (α waves) with a frequency range of 8 to 13 Hz.

[0091] Specifically, in step S41, when feature extraction is performed on the preprocessed applicable patient EEG signal, a feature EEG signal is extracted from the preprocessed applicable patient EEG signal.

[0092] Specifically, the characteristic EEG signal refers to signal segments and features that reflect different EEG states and pathological changes in the EEG signal.

[0093] Specifically, this embodiment does not set the method of feature extraction, and technical personnel in this field can set it freely, as long as the requirements for feature extraction of the preprocessed applicable patient EEG signals are met. For example, it can be set to directly extract the period, amplitude, mean, standard deviation, peak value and valley value from the time domain signal.

[0094] Specifically, in step S42, when the characteristic EEG signal is subjected to feature classification, the characteristic EEG signal is input into a classifier, and a standardized EEG signal is obtained through the classifier.

[0095] Specifically, the feature classification refers to dividing the EEG signal features extracted by features into different EEG states and categories through algorithms and models. The classifier refers to the algorithm and model used to identify the category to which the data item belongs. This embodiment does not set the selection of the classifier, and technical personnel in this field can set it freely as long as it meets the requirements for feature classification of feature EEG signals. For example, it can be set to use a naive Bayes classifier.

[0096] Specifically, in step S5, when judging the effectiveness of the standardization of the standardized EEG signal, the standardized EEG signal noise peak value K is compared with the preset EEG signal noise peak value K0, and the effectiveness of the standardization is judged according to the comparison result, wherein:

[0097] When K≤K0, the standardized EEG signal is determined to be valid;

[0098] When K>K0, the standardized EEG signal is determined to be invalid, and the invalid standardized EEG signal is corrected and the EEG signal is standardized again.

[0099] Specifically, this embodiment does not limit the method for obtaining the standardized EEG signal noise peak value. Those skilled in the art can set it freely as long as the need for judging the effectiveness of standardization is met. For example, it can be set to be calculated by the following formula: (U_{no ise}=\frac{U_{max}-U_{min}}{Ga in}), wherein (U_{max}) is the maximum value of the collected signal, (U_{min}) is the minimum value of the collected signal, Ga in is the gain of the system, and (U_{no ise}) is the standardized EEG signal noise peak value. The preset EEG signal noise peak value K0 refers to a preset threshold value that can accurately reflect the effectiveness of the standardized EEG signal. This embodiment does not set the preset EEG signal noise peak value K0. Those skilled in the art can set it freely as long as the need for reflecting the effectiveness of the standardized EEG signal is met. For example, K0 can be set to 300.

[0100] Specifically, in step S6, when judging the validity of the data according to the acquisition interval, the time T of the EEG signal acquisition is compared with the preset minimum acquisition time T1 and the preset maximum acquisition time T2, and the validity of the data is judged according to the comparison result, wherein:

[0101] When T<T1, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, and the patient acquisition site is adjusted to re-acquire the EEG signal of the applicable patient;

[0102] When T1≤T≤T2, the EEG signal acquisition is judged to be effective, and the preprocessing effectiveness judgment result is not adjusted;

[0103] When T>T2, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, the patient acquisition site is adjusted, and the EEG signal of the applicable patient is re-collected.

[0104] Specifically, the collection interval refers to the time period from the start time point of collecting the applicable patient EEG signal to the end time point of collecting the applicable patient EEG signal. The preset minimum collection time T1 refers to the minimum time period required from the start time of collecting EEG signals to the end time of collecting EEG signals. The preset maximum collection time T2 refers to the maximum time period required from the start time of collecting EEG signals to the end time of collecting EEG signals. This embodiment does not set the preset minimum collection time T1 and the preset maximum collection time T2. Those skilled in the art can set them freely as long as they meet the requirements for reflecting the validity of the data. For example, the preset minimum collection time T1 can be set to 10min and the preset maximum collection time T2 can be set to 20min.

[0105] Specifically, through the step S6, when the EEG signal acquisition time is less than the preset minimum acquisition time, the EEG signal acquisition is determined to be invalid, so as to identify the situation that the acquisition process result appears too fast and the acquisition result is not a true result, so as to avoid the situation that the operator obtains an erroneous result due to improper operation. Through the step S6, the preprocessing validity judgment result is adjusted to invalid, and the patient's acquisition site is adjusted, and the EEG signal of the patient is re-collected to ensure the validity of the subsequent analysis results. When the EEG signal acquisition time is greater than the preset minimum acquisition time, the EEG signal acquisition is determined to be invalid, so as to identify the situation that the acquisition process result appears too slow and the acquisition result is not a true result, so as to avoid the situation that the operator obtains an erroneous result due to improper operation. Through the step S6, the preprocessing validity judgment result is adjusted to invalid, and the patient's acquisition site is adjusted, and the EEG signal of the patient is re-collected to ensure the validity of the subsequent analysis results.

[0106] Specifically, in step S7, a symptom judgment model is established based on historical symptom information, the standardized EEG signal is input into the symptom judgment model, and the patient's symptom is output.

[0107] Specifically, the symptom judgment model refers to a model that meets a preset accuracy rate by training a convolutional neural network model according to historical symptom information. The convolutional neural network model refers to a feedforward neural network that includes convolution calculations and has a deep structure. This embodiment does not limit the way in which the convolutional neural network model is trained. Those skilled in the art can set it freely, as long as the requirements for the symptom judgment model are met. For example, it can be set to divide 70% of the historical symptom information into a training set and 30% into a test set, input the training set into the convolutional neural network model for training, and input the test set into the trained convolutional neural network model, optimize the parameters in the convolutional neural network iteratively, until the accuracy of the output result of the convolutional neural network model test set reaches 98%, and the convolutional neural network model is output as a symptom judgment model. The historical symptom information refers to the standardized EEG signal and the patient symptom information corresponding to the standardized EEG signal within the model training cycle. The model training cycle refers to the preset time interval for obtaining the historical symptom information when training the model. If the model training cycle time is set to half a year, the standardized EEG signal and the patient symptom information corresponding to the standardized EEG signal half a year ago are obtained as the historical symptom information.

[0108] Specifically, in step S8, the patient's symptoms are compared with the preset patient symptoms in the expert physiotherapy knowledge database, wherein:

[0109] When there is a preset patient condition that is consistent with the patient's condition in the expert physical therapy knowledge database, the preset physical therapy plan corresponding to the preset patient condition is output as the patient's physical therapy plan;

[0110] When there is no preset patient symptom consistent with the patient's symptom in the expert physiotherapy knowledge database, the patient's symptom and the applicable patient EEG signal are pushed to the expert user terminal to obtain the patient physiotherapy plan given by the expert user terminal.

[0111] Specifically, the expert physiotherapy knowledge database refers to a database system that stores and integrates expert-level physiotherapy knowledge, experience and research results, including preset patient symptoms and preset physiotherapy plans. This embodiment does not limit the setting method of the expert physiotherapy knowledge database. Those skilled in the art can freely set it according to actual conditions, and only need to meet the output requirements of patient physiotherapy plans. For example, the expert physiotherapy knowledge database can be set through big data, and the expert physiotherapy knowledge database can be updated in real time. The preset patient symptoms refer to pre-set and stored simulated and real patient symptom cases. The preset physiotherapy plan refers to a standardized and normalized physiotherapy treatment plan pre-designed and stored for preset patient symptoms. The expert user terminal refers to an expert user terminal with the ability to set the physiotherapy plan. This embodiment does not limit the method for obtaining the patient physiotherapy plan given by the expert user terminal. Relevant personnel in this field can freely set it according to actual conditions, and only need to meet the requirements for obtaining the patient physiotherapy plan given by the expert user terminal. For example, it can be set to push a collection window to the expert user terminal, and the expert user inputs in the collection window to obtain the content entered by the expert user in the collection window as the patient physiotherapy plan given by the expert user terminal.

[0112] Specifically, in step S9, after real-time monitoring of the EEG signal of the patient during the physical therapy, the monitoring data is obtained and the similarity P between the monitoring data and the preset monitoring data is calculated, and the similarity P is compared with the preset similarity P0, and the effectiveness of the physical therapy is judged according to the comparison result, wherein:

[0113] When P ≥ P0, the physical therapy is judged to be effective, the physical therapy plan is not adjusted, and the physical therapy continues;

[0114] When P<P0, it is determined that physical therapy is ineffective, the patient's symptoms and applicable patient EEG signals are pushed to the expert user terminal, a patient physical therapy plan given by the expert user terminal is obtained, and physical therapy is performed using the patient physical therapy plan given by the expert user terminal.

[0115] Specifically, the monitoring data refers to the EEG signal data collected when the EEG signal is monitored in real time, and the preset monitoring data refers to the EEG signal data reflecting the effectiveness of physical therapy. The present embodiment does not limit the calculation method of the similarity, and technical personnel in this field can set it freely, and only need to meet the calculation requirements of the similarity. For example, it can be set to convert the EEG signal into a frequency domain representation through a fast Fourier transform FFT, and calculate the similarity measure between the frequency spectra, and use the similarity measure as the similarity. The present embodiment does not limit the preset similarity P0, and technical personnel in this field can set it freely, and only need to meet the reflection requirements of the effectiveness of physical therapy. For example, the preset similarity P0 can be set to 0.9. The present embodiment does not limit the real-time monitoring method, and technical personnel in this field can set it freely, and only need to meet the requirements of real-time monitoring of EEG signals during the patient's physical therapy. For example, the real-time monitoring method can be set to electroencephalogram monitoring.

[0116] Specifically, in step S10, the acupoint pressure resistance value R of the patient after physical treatment is compared with the preset acupoint pressure resistance value R0, and the physical treatment result is judged according to the comparison result, wherein:

[0117] When R≤R0, the physical therapy result is judged to be up to standard;

[0118] When R>R0, the physical therapy result is determined to be substandard, and the physical therapy plan is optimized according to the physical therapy plan optimization method.

[0119] Specifically, the acupoint pressure resistance value R refers to the value obtained by measuring the impedance (resistance) of the tissue at the acupoint to the electric current. The present embodiment does not limit the measurement method, and relevant technical personnel in the field can set it freely, and it only needs to meet the measurement requirements of the acupoint pressure resistance value. For example, it can be set to be measured by a meridian acupoint detector. The preset acupoint pressure resistance value R0 refers to a preset value reflecting that the physical therapy result has reached the standard. The present embodiment does not limit the preset acupoint pressure resistance value R0, and relevant technical personnel in the field can set it freely, and it only needs to meet the reflection requirements of the physical therapy result having reached the standard. For example, the preset physical therapy standard threshold R0 can be set to 200kΩ.

[0120] See also Figure 3 As shown, it is a flow chart of the physical therapy program optimization method of this embodiment, and the physical therapy program optimization method includes:

[0121] Step S100, obtaining the patient's physical characteristic variance value Z;

[0122] Step S101, comparing the patient's physical characteristic variance value Z with a preset variance value Z0, and optimizing the physical therapy plan according to the comparison result.

[0123] Specifically, the physiotherapy program optimization method obtains the patient's physical characteristic variance value Z through step S100, and compares the patient's physical characteristic variance value Z with the preset variance value Z0 through step S101, and optimizes the physiotherapy program according to the comparison result to facilitate the analysis of the physiotherapy results, thereby improving the physiotherapy efficiency.

[0124] Specifically, in step S100, the variance value of the patient's physical characteristics and the physical characteristics of the patient with the same patient disease as the standardized EEG signal in the training set of the disease judgment model is obtained and used as the patient's physical characteristics variance value Z.

[0125] Specifically, the patient's physical characteristic variance value Z refers to a fluctuation value reflecting the patient's physical characteristics and the patient's physical characteristics in the training set of the disease judgment model, and the patient's physical characteristics refer to numerical values ​​representing the patient's physical characteristics, such as age, weight, height, etc.;

[0126] Specifically, in step S101, the patient's physical characteristic variance value Z is compared with the preset variance value Z0, and the physical therapy program is optimized according to the comparison result, wherein:

[0127] When Z ≥ Z0, the disease judgment model is optimized;

[0128] When Z<Z0, a notification is sent to the manager to remind him that the therapy device is distorted.

[0129] Specifically, this embodiment does not limit the way to optimize the disease judgment model. Relevant technical personnel in the field can freely set it, and it only needs to meet the needs of optimizing the disease judgment model. For example, it can be set to screen data according to the patient's physical characteristics, and use the screened data as a model optimization training set to optimize the disease judgment model. The manager refers to a person who has management responsibilities for the physiotherapy device, and the distortion refers to the phenomenon that the EEG signal deviates from the original EEG signal during the transmission process.

[0130] See also Figure 4 As shown, it is a structural diagram of the digital Chinese medicine physiotherapy system of this embodiment, and the system includes:

[0131] Information collection module, used to collect patient medical history files;

[0132] A module for judging the patient's applicable constitution is used to judge the patient's applicable constitution;

[0133] An EEG signal acquisition module is used to collect EEG signals from applicable patients;

[0134] An EEG signal processing module is used to perform standardized processing on the collected EEG signals of applicable patients and output standardized EEG signals;

[0135] The validity judgment module is used to judge the validity of the standardized EEG signals, and correct invalid standardized EEG signals according to the judgment results, and also judge the validity of the data according to the collection interval, and adjust the validity judgment results of the standardized EEG signals and the patient collection site according to the judgment results;

[0136] Symptom judgment module, used to judge the patient's symptoms and output;

[0137] The physiotherapy module is used to formulate a physiotherapy plan for the patient's condition based on the expert physiotherapy knowledge database and perform physiotherapy;

[0138] The real-time monitoring module is used to monitor the EEG signals of patients during physical therapy in real time and judge the effectiveness of physical therapy, and adjust the physical therapy plan according to the judgment results;

[0139] Feedback optimization module, used to judge the treatment results and optimize the treatment plan according to the results;

[0140] The distortion feedback module is used to remind the administrator of the distortion of the physical therapy device.

[0141] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A digital TCM physiotherapy method, characterized in that: include: Step S1, collecting patient medical history files; Step S2, judging the patient's applicable constitution according to the patient's medical history file; Step S3, collecting EEG signals from applicable patients; Step S4, standardizing the collected EEG signals of applicable patients and outputting standardized EEG signals; Step S5, judging the validity of the standardized EEG signals, and correcting invalid standardized EEG signals according to the judgment result; Step S6, judging the validity of the data according to the acquisition interval, and adjusting the validity judgment result of the standardized EEG signal and the patient acquisition site according to the judgment result; Step S7, inputting the standardized EEG signal into the disease judgment model and outputting the patient's disease; Step S8, making a physical therapy plan for the patient's condition according to the expert physical therapy knowledge database, and performing physical therapy; Step S9, real-time monitoring of the patient's EEG signals during the physical therapy process, judging the effectiveness of the physical therapy, and adjusting the physical therapy plan according to the judgment result; Step S10, judging the physical therapy result and optimizing the physical therapy plan according to the judgment result; In step S2, when judging the patient's applicable constitution according to the patient's medical history file, the patient's constitution data in the patient's medical history file is compared with the standard applicable constitution threshold, and the patient's applicable constitution is judged according to the comparison result, wherein: When the patient's physical fitness data falls within the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be qualified and marked as an applicable patient; When the patient's physical fitness data falls outside the standard applicable physical fitness threshold, the patient's applicable physical fitness is determined to be unqualified and marked as a non-applicable patient; In step S4, the method for standardizing the collected EEG signals of the applicable patients includes: Step S40, preprocessing the collected EEG signals of the applicable patients; Step S41, extracting features from the preprocessed EEG signals of the applicable patients to obtain feature EEG signals; Step S42, performing feature classification on the characteristic EEG signal to obtain a standardized EEG signal; In step S5, when judging the effectiveness of the standardization of the standardized EEG signal, the standardized EEG signal noise peak value K is compared with the preset EEG signal noise peak value K0, and the effectiveness of the standardization is judged according to the comparison result, wherein: When K≤K0, the standardized EEG signal is determined to be valid; When K>K0, the standardized EEG signal is determined to be invalid, and the invalid standardized EEG signal is corrected, and the EEG signal is standardized again; In step S6, when judging the validity of the data according to the acquisition interval, the time T of the EEG signal acquisition is compared with the preset minimum acquisition time T1 and the preset maximum acquisition time T2, and the validity of the data is judged according to the comparison result, wherein: When T<T1, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, and the patient acquisition site is adjusted to re-acquire the EEG signal of the applicable patient; When T1≤T≤T2, the EEG signal acquisition is judged to be effective, and the preprocessing effectiveness judgment result is not adjusted; When T>T2, the EEG signal acquisition is determined to be invalid, the preprocessing validity judgment result is adjusted to invalid, and the patient acquisition site is adjusted to re-acquire the EEG signal of the applicable patient; In step S7, a symptom judgment model is established based on historical symptom information, the standardized EEG signal is input into the symptom judgment model, and the patient's symptom is output; In step S8, the patient's symptoms are compared with the preset patient symptoms in the expert physiotherapy knowledge database, wherein: When there is a preset patient condition that is consistent with the patient's condition in the expert physical therapy knowledge database, the preset physical therapy plan corresponding to the preset patient condition is output as the patient's physical therapy plan; When there is no preset patient symptom consistent with the patient's symptom in the expert physiotherapy knowledge database, the patient's symptom and the applicable patient's EEG signal are pushed to the expert user terminal to obtain the patient physiotherapy plan given by the expert user terminal; In step S9, after real-time monitoring of the EEG signal of the patient during the physical therapy, the monitoring data is obtained and the similarity P between the monitoring data and the preset monitoring data is calculated, and the similarity P is compared with the preset similarity P0, and the effectiveness of the physical therapy is judged according to the comparison result, wherein: When P ≥ P0, the physical therapy is judged to be effective, the physical therapy plan is not adjusted, and the physical therapy continues; When P<P0, it is determined that the physical therapy is ineffective, the patient's symptoms and the applicable patient's EEG signals are pushed to the expert user terminal, a patient physical therapy plan given by the expert user terminal is obtained, and physical therapy is performed using the patient physical therapy plan given by the expert user terminal; In step S10, the acupoint pressure resistance value R of the patient after physical treatment is compared with the preset acupoint pressure resistance value R0, and the physical treatment result is judged according to the comparison result, wherein: When R≤R0, the physical therapy result is judged to be up to standard; When R>R0, the physical therapy result is judged to be substandard, and the physical therapy plan is optimized according to the physical therapy plan optimization method; In step S10, the method for optimizing the physical therapy plan includes: Step S100, obtaining the patient's physical characteristic variance value Z; Step S101, comparing the patient's physical characteristic variance value Z with a preset variance value Z0, and optimizing the physical therapy plan according to the comparison result.

2. A system applied to the TCM physiotherapy method as claimed in claim 1, characterized in that: include: Information collection module, used to collect patient medical history files; A module for judging the patient's applicable constitution is used to judge the patient's applicable constitution; An EEG signal acquisition module is used to collect EEG signals from applicable patients; An EEG signal processing module is used to perform standardized processing on the collected EEG signals of applicable patients and output standardized EEG signals; The validity judgment module is used to judge the validity of the standardized EEG signals, and correct invalid standardized EEG signals according to the judgment results, and also judge the validity of the data according to the collection interval, and adjust the validity judgment results of the standardized EEG signals and the patient collection site according to the judgment results; Symptom judgment module, used to judge the patient's symptoms and output; The physiotherapy module is used to formulate a physiotherapy plan for the patient's condition based on the expert physiotherapy knowledge database and perform physiotherapy; The real-time monitoring module is used to monitor the EEG signals of patients during physical therapy in real time and judge the effectiveness of physical therapy, and adjust the physical therapy plan according to the judgment results; Feedback optimization module, used to judge the treatment results and optimize the treatment plan based on the results; The distortion feedback module is used to remind the administrator of the distortion of the physical therapy device.

Images