Closed-loop transcutaneous acupoint electrical stimulation sedation method and system
By obtaining and processing human physiological index information in real time, using pre-trained models to identify the degree of calming and adjusting the electrical stimulation parameters, the problem of the inability to dynamically adjust the electrical stimulation parameters in the prior art is solved, and more effective sedation control is achieved.
Patent Information
- Application Number
- CN202410195455.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-02-22
AI Technical Summary
The existing closed-loop percutaneous acupoint electrical stimulation technology cannot adjust the electrical stimulation parameters according to the actual situation of the patient, and cannot automatically control and monitor the electrical stimulation process in real time, resulting in poor sedation effect.
By using sensors to obtain human physiological index information in real time, perform standardized processing and feature extraction, use pre-trained physiological index identification models to identify the degree of calmness, and adjust the current intensity according to the recognition results for electrical stimulation, continuously monitor and readjust to ensure that the calming value reaches Preset threshold.
The electrical stimulation parameters are dynamically adjusted according to the actual situation of the patient, and the automatic control and real-time monitoring of the electrical stimulation process are realized, which improves the sedation effect.
Smart Images

Figure CN117797406B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a closed-loop transcutaneous acupoint electrical stimulation sedation method and system. Background Art
[0002] Transcutaneous electrical acupoint stimulation is a therapy that uses electric current to stimulate acupoints on the human body to adjust body functions and calm patients. In recent years, as people pay more attention to non-drug treatment methods, transcutaneous electrical acupoint stimulation technology has been widely used in clinical treatment.
[0003] However, the existing closed-loop transcutaneous electrical acupoint stimulation technology still has some problems in the sedation treatment process, such as the inability to adjust the electrical stimulation parameters according to the patient's actual situation to achieve the best sedation effect, and the inability to automatically control and monitor the electrical stimulation process in real time. Summary of the invention
[0004] The present invention provides a closed-loop transcutaneous acupoint electrical stimulation sedation method and system, the main purpose of which is to solve the problem that the electrical stimulation parameters cannot be adjusted according to the actual situation of the patient and the electrical stimulation process cannot be automatically controlled and monitored in real time.
[0005] To achieve the above object, the present invention provides a closed-loop transcutaneous acupoint electrical stimulation sedation method, comprising:
[0006] Using sensors to obtain human physiological index information in real time, and performing standardization processing on the human physiological index information to obtain standardized physiological index information;
[0007] Extracting features from the standardized physiological indicator information to obtain physiological indicator features;
[0008] Using a pre-trained physiological index recognition model to identify the calmness of a human body according to the physiological index characteristics, and obtaining a calmness value;
[0009] When the sedation value is less than a preset sedation threshold, setting the current intensity according to the physiological indicator characteristics and the sedation value;
[0010] Electrically stimulating the acupuncture points of the human body according to the current intensity value by means of an electrical stimulation device preset at the acupuncture points of the human body;
[0011] Continue to execute the above-mentioned step of using the pre-trained physiological indicator recognition model to identify the calmness level of the human body according to the physiological indicator characteristics to obtain the calmness value. If the calmness value is less than the preset calmness threshold, re-execute the above-mentioned step of electrically stimulating the human body acupuncture points according to the current intensity number through the electrical stimulation device preset at the human body acupuncture points.
[0012] Optionally, the real-time acquisition of human physiological index information by using sensors includes:
[0013] Using a temperature sensor to obtain the patient's temperature data;
[0014] Using a pulse sensor to obtain patient pulse data;
[0015] Using a blood pressure sensor to obtain blood pressure data of a patient;
[0016] Using a respiratory sensor to obtain patient respiratory data;
[0017] The blood oxygen concentration sensor is used to obtain the patient's blood oxygen concentration data.
[0018] Optionally, the step of performing standardization processing on the human physiological indicator information to obtain standardized physiological indicator information includes:
[0019] The standardization process is expressed by the following formula:
[0020]
[0021] Among them, Y n represents the nth group of data in the standardized physiological index information, X n represents the nth group of data of the human physiological indicator information, avg represents the average of the nth group of data of the human physiological indicator information, and std represents the standard deviation of the nth group of data of the human physiological indicator information.
[0022] Optionally, the extracting features of the standardized physiological indicator information to obtain physiological indicator features includes:
[0023] Performing missing value processing on the standardized physiological index information to obtain preprocessed physiological index information;
[0024] Performing word segmentation processing on the pre-processed physiological indicator information to obtain a word list;
[0025] Traversing the word list, deleting repeated words in the word list, and obtaining a vocabulary list;
[0026] Converting the words in the word list into vector form according to the occurrence positions and occurrence times of the words in the vocabulary to obtain a physiological indicator vector;
[0027] The physiological indicator vector is subjected to dimensionality reduction processing to obtain physiological indicator features.
[0028] Optionally, before the method uses the pre-trained physiological indicator recognition model to identify the calmness of the human body according to the physiological indicator characteristics to obtain the calmness value, the method further includes:
[0029] Acquire historical physiological indicator information of the patient, perform feature extraction on the historical physiological indicator information, and obtain historical physiological indicator features;
[0030] Using a neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics to obtain a training calmness value;
[0031] Calculating the difference between the training calmness value and the standard calmness value preset by the historical physiological index characteristic;
[0032] If the difference value is greater than or equal to a preset difference value threshold, then adjusting the weight parameters and bias items of the neural network model according to the difference value, and then re-performing the above step of using the neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics to obtain a training calmness value;
[0033] If the difference value is less than a preset difference value threshold, it is confirmed that the model training is completed and a physiological indicator recognition model is obtained.
[0034] Optionally, the calculating the difference between the training calmness value and the standard calmness value preset by the historical physiological indicator characteristic comprises:
[0035] The difference value is calculated using the following formula:
[0036]
[0037] Wherein, L represents the difference value, M represents the standard calmness value preset based on the historical physiological indicator characteristics, and N represents the training calmness value.
[0038] Optionally, the using of a pre-trained physiological indicator recognition model to identify the calmness level of a human body according to the physiological indicator characteristics to obtain a calmness value includes:
[0039] Using the physiological index recognition model to perform data conversion processing on the physiological index characteristics to obtain a feature matrix;
[0040] Using the physiological index recognition model to perform a convolution operation on the feature matrix through a convolution layer to obtain a convolution feature;
[0041] Using the physiological index recognition model, a maximum pooling operation is performed on the convolutional features through a pooling layer to obtain a pooling feature;
[0042] The physiological index recognition model is used to identify the patient's calmness level according to the pooling features through a fully connected layer to obtain a calmness value.
[0043] Optionally, the step of using the physiological index recognition model to identify the patient's calmness level according to the pooling features through a fully connected layer to obtain a calmness value includes:
[0044] The stabilization value is calculated using the following formula:
[0045] y=g(W*p+b)
[0046] Among them, y is the stabilization value, W is the weight parameter of the fully connected layer, p is the pooling feature, b is the bias term, and g is the softmax function.
[0047] Optionally, setting the current intensity according to the physiological indicator characteristics and the calmness value includes:
[0048] Calculate the difference between the stabilization value and a preset standard difference value to obtain a stabilization value difference;
[0049] Measuring the patient's body conductivity by conductometric method;
[0050] The current intensity is set according to the sedation value difference, human body conductivity and physiological index characteristics.
[0051] In order to solve the above problems, the present invention also provides a closed-loop transcutaneous acupoint electrical stimulation sedation system, the system comprising:
[0052] A data acquisition module is used to acquire human physiological index information in real time using sensors, and perform standardization processing on the human physiological index information to obtain standardized physiological index information;
[0053] A calmness identification module is used to extract features from the standardized physiological index information to obtain physiological index features, and use a pre-trained physiological index identification model to identify the calmness of the human body according to the physiological index features to obtain a calmness value;
[0054] A calmness judgment module, when the calmness value is less than a preset calmness threshold, sets the current intensity according to the physiological indicator characteristics and the calmness value;
[0055] The current stimulation module electrically stimulates the acupuncture points of the human body according to the current intensity through the electrical stimulation device preset at the acupuncture points of the human body;
[0056] The continuous monitoring module continuously executes the above-mentioned step of using the pre-trained physiological indicator recognition model to identify the calmness level of the human body according to the physiological indicator characteristics to obtain the calmness value. If the calmness value is less than the preset calmness threshold, the above-mentioned step of electrically stimulating the human body acupuncture points according to the current intensity number through the electric stimulation device preset at the human body acupuncture points is re-executed.
[0057] The embodiment of the present invention uses sensors to obtain human physiological indicator information in real time, performs standardization processing to obtain standardized physiological indicator information, performs feature extraction on the standardized physiological indicator information to obtain physiological indicator features, uses a pre-trained physiological indicator recognition model to identify the calmness of the human body according to the physiological indicator features, and obtains a calmness value. When the calmness value is less than a preset calmness value threshold, the current intensity is set according to the physiological indicator features and the calmness value, and an electrical stimulation device preset at the patient's acupoint is used to perform electrical stimulation according to the current intensity, continuously monitors the patient's calmness value, and re-executes the step of performing electrical stimulation on the patient when the calmness value is less than the preset calmness value threshold. Therefore, the closed-loop transcutaneous acupoint electrical stimulation sedation method and system proposed in the present invention can solve the problem that the electrical stimulation parameters cannot be adjusted according to the actual situation of the patient and the electrical stimulation process cannot be automatically controlled and monitored in real time. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Figure 1 A schematic diagram of a closed-loop transcutaneous acupoint electrical stimulation sedation method according to an embodiment of the present invention;
[0059] Figure 2 A schematic diagram of a process for extracting features of standardized physiological indicator information provided by an embodiment of the present invention;
[0060] Figure 3 A schematic diagram of a process for training a physiological index recognition model according to an embodiment of the present invention;
[0061] Figure 4 This is a functional module diagram of a closed-loop transcutaneous acupoint electrical stimulation sedation system provided in one embodiment of the present invention.
[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0063] 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 embodiment of the present application provides a closed-loop transcutaneous acupoint electrical stimulation sedation method. The execution subject of the closed-loop transcutaneous acupoint electrical stimulation sedation method includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the closed-loop transcutaneous acupoint electrical stimulation sedation method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.
[0065] Reference Figure 1 FIG. 1 is a flow chart of a closed-loop transcutaneous acupoint electrical stimulation sedation method according to an embodiment of the present invention. In this embodiment, the closed-loop transcutaneous acupoint electrical stimulation sedation method includes:
[0066] S1. Using sensors to obtain human physiological index information in real time, and performing standardization processing on the human physiological index information to obtain standardized physiological index information;
[0067] In the embodiment of the present invention, the sensor includes a temperature sensor, a pulse sensor, a blood pressure sensor, a respiration sensor, and a blood oxygen concentration sensor.
[0068] In detail, the real-time acquisition of human physiological index information by using sensors includes:
[0069] Using a temperature sensor to obtain the patient's temperature data;
[0070] Using a pulse sensor to obtain patient pulse data;
[0071] Using a blood pressure sensor to obtain blood pressure data of a patient;
[0072] Using a respiratory sensor to obtain patient respiratory data;
[0073] The blood oxygen concentration sensor is used to obtain the patient's blood oxygen concentration data.
[0074] In the embodiment of the present invention, the step of performing standardization processing on the human physiological index information to obtain standardized physiological index information includes:
[0075] The standardization process is expressed by the following formula:
[0076]
[0077] Among them, Y n represents the nth group of data in the standardized physiological index information, X n represents the nth group of data of the human physiological indicator information, avg represents the average of the nth group of data of the human physiological indicator information, and std represents the standard deviation of the nth group of data of the human physiological indicator information.
[0078] In the embodiment of the present invention, human physiological index information is acquired in real time by using sensors, and the human physiological index information is standardized to obtain standardized physiological index information, thereby providing necessary data for subsequent processing and improving the efficiency of subsequent data processing.
[0079] S2. Extracting features from the standardized physiological indicator information to obtain physiological indicator features.
[0080] In the embodiments of the present invention, feature extraction can reduce the dimension of data, simplify high-dimensional data, improve the quality of data, reduce the amount of calculation, and make the data easier to understand and analyze.
[0081] In the embodiment of the present invention, referring to Figure 2 As shown, a schematic diagram of a process for extracting features of standardized physiological indicator information is provided in an embodiment of the present invention. The feature extraction of the standardized physiological indicator information to obtain physiological indicator features includes:
[0082] S21, performing missing value processing on the standardized physiological index information to obtain pre-processed physiological index information;
[0083] S22, performing word segmentation processing on the pre-processed physiological indicator information to obtain a word list;
[0084] S23, traversing the word list, deleting repeated words in the word list, and obtaining a vocabulary list;
[0085] S24, converting the words in the word list into vector form according to the occurrence positions and occurrence times of the words in the vocabulary list to obtain a physiological indicator vector;
[0086] S25. Perform dimensionality reduction processing on the physiological indicator vector to obtain physiological indicator features.
[0087] In the embodiment of the present invention, by performing feature extraction on the standardized physiological indicator information, physiological indicator features are obtained, which improves the readability of the data and the efficiency of subsequent model processing of the data.
[0088] S3. Using a pre-trained physiological index recognition model, the calmness level of the human body is recognized according to the physiological index characteristics to obtain a calmness value.
[0089] In the embodiment of the present invention, referring to Figure 3 As shown, a flow chart of training a physiological indicator recognition model is provided in an embodiment of the present invention. The method further includes:
[0090] S31, obtaining historical physiological indicator information of the patient, performing feature extraction on the historical physiological indicator information, and obtaining historical physiological indicator features;
[0091] S32, using a neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics, and obtaining a training calmness value;
[0092] S33, calculating the difference between the training calmness value and the standard calmness value preset by the historical physiological index characteristic;
[0093] S34, if the difference value is greater than or equal to a preset difference value threshold, then adjusting the weight parameter and bias item of the neural network model according to the difference value, and then re-performing the above step of using the neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics to obtain a training calmness value;
[0094] S35. If the difference value is less than a preset difference value threshold, it is confirmed that the model training is completed and a physiological indicator recognition model is obtained.
[0095] In an embodiment of the present invention, the physiological indicator recognition model can be a neural network model, including but not limited to a CNN (Convolutional Neural Networks) model and an RNN (Recurrent Neural Network) model.
[0096] In the embodiment of the present invention, the calculating of the difference between the training calmness value and the standard calmness value preset by the historical physiological indicator characteristic comprises:
[0097] The difference value is calculated using the following formula:
[0098]
[0099] Wherein, L represents the difference value, M represents the standard calmness value preset based on the historical physiological indicator characteristics, and N represents the training calmness value.
[0100] In the embodiment of the present invention, the method of using the pre-trained physiological indicator recognition model to identify the calmness level of the human body according to the physiological indicator characteristics to obtain the calmness value includes:
[0101] Using the physiological index recognition model to perform data conversion processing on the physiological index characteristics to obtain a feature matrix;
[0102] Using the physiological index recognition model to perform a convolution operation on the feature matrix through a convolution layer to obtain a convolution feature;
[0103] Using the physiological index recognition model, a maximum pooling operation is performed on the convolutional features through a pooling layer to obtain a pooled feature;
[0104] The physiological index recognition model is used to identify the patient's calmness level according to the pooling features through a fully connected layer to obtain a calmness value.
[0105] In the embodiment of the present invention, the method of using the physiological index recognition model to identify the patient's calmness level according to the pooling feature through a fully connected layer to obtain a calmness value includes:
[0106] The stabilization value is calculated using the following formula:
[0107] y=g(W*p+b)
[0108] Among them, y is the stabilization value, W is the weight parameter of the fully connected layer, p is the pooling feature, b is the bias term, and g is the softmax function.
[0109] In the embodiment of the present invention, the data conversion process refers to expressing the physiological indicator characteristics in the form of word vectors, and then concatenating the word vectors to form a matrix.
[0110] In the embodiment of the present invention, the convolution operation refers to performing a convolution operation on the feature matrix and according to the convolution kernel parameters to extract some features in the feature matrix.
[0111] In the embodiment of the present invention, the convolution kernel parameter is an important concept in convolutional neural networks in deep learning. In convolutional neural networks, the convolution kernel is a parameter used to slide on the input data and perform convolution operations. Each convolution kernel has one or more weights, which are learned during the training process and used to determine the mode of convolution operation.
[0112] In the embodiment of the present invention, the maximum pooling operation can effectively reduce the dimension of the data while retaining the most important feature information. Since the maximum pooling operation only focuses on the maximum value in each pooling window and ignores other values, it can effectively reduce noise and redundant information and improve the generalization ability of the model.
[0113] In an embodiment of the present invention, the physiological indicator recognition model has the ability to learn implicit features. During the training process, the physiological indicator recognition model continuously updates the parameters of the model through the back propagation algorithm, so that the model can automatically learn the implicit features in the data. In the problem of safety detection of geotechnical engineering, these implicit features may be abstract features related to physiological indicators, such as a certain waveform shape, spectrum distribution, etc. Through deep neural networks, higher-level and more expressive features can be gradually extracted.
[0114] In detail, the performance of the physiological index recognition model depends largely on the quality of available data and the representativeness of the samples. Therefore, collecting sufficient, representative and accurately labeled physiological index information is the key to ensuring the accuracy of the model. In addition, timely updating and maintenance of the model is also an important factor to ensure the effectiveness of the model under different operating environments and data changes.
[0115] S4. When the sedation value is less than a preset sedation threshold, the current intensity is set according to the physiological indicator characteristics and the sedation value.
[0116] In the embodiment of the present invention, when the calming value is less than a preset calming threshold, electrical stimulation needs to be performed on the patient.
[0117] In the embodiment of the present invention, the step of setting the current intensity according to the physiological indicator characteristics and the calming value includes:
[0118] Calculate the difference between the stabilization value and a preset standard difference value to obtain a stabilization value difference;
[0119] Measuring the patient's body conductivity by conductometric method;
[0120] The current intensity is set according to the sedation value difference, human body conductivity and physiological index characteristics.
[0121] In the embodiment of the present invention, when the sedation value is less than a preset sedation threshold, the current intensity is set according to the physiological indicator characteristics and the sedation value, thereby providing necessary data for subsequent operations.
[0122] S5. Electrically stimulate the acupuncture points of the human body according to the current intensity value through the electrical stimulation device preset at the acupuncture points of the human body.
[0123] In the embodiment of the present invention, it is necessary to perform electrical stimulation on the patient according to a preset electrical stimulation time and frequency.
[0124] S6. Continue to execute the above step of using the pre-trained physiological indicator recognition model to identify the calmness level of the human body according to the physiological indicator characteristics to obtain the calmness value. If the calmness value is less than the preset calmness threshold, re-execute the above step of electrically stimulating the human acupuncture points according to the current intensity number through the electrical stimulation device preset at the human acupuncture points.
[0125] In the embodiment of the present invention, since it cannot be ensured that the patient returns to a calm state after receiving electrical stimulation, the patient's calm state needs to be continuously monitored.
[0126] In an embodiment of the present invention, the step of obtaining a calmness value by identifying the calmness degree of a human body according to the physiological indicator characteristics using a pre-trained physiological indicator recognition model is continuously executed, and when the calmness value is less than a preset calmness threshold, the step of electrically stimulating the acupoints of the human body according to the current intensity number using an electrical stimulation device preset at the acupoints of the human body is re-executed to ensure that the patient can remain in a calm state.
[0127] like Figure 4 , which is a functional module diagram of a closed-loop transcutaneous acupoint electrical stimulation sedation system provided by an embodiment of the present invention.
[0128] The closed-loop transcutaneous acupoint electrical stimulation sedation system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the closed-loop transcutaneous acupoint electrical stimulation sedation system 100 can include a data acquisition module 101, a calmness identification module 102, a calmness judgment module 103, a current stimulation module 104 and a continuous monitoring module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0129] In this embodiment, the functions of each module / unit are as follows:
[0130] The data acquisition module 101 is used to acquire human physiological index information in real time using sensors, and perform standardization processing on the human physiological index information to obtain standardized physiological index information;
[0131] The calmness identification module 102 is used to extract features from the standardized physiological index information to obtain physiological index features, and use a pre-trained physiological index identification model to identify the calmness of the human body according to the physiological index features to obtain a calmness value;
[0132] The calmness judgment module 103 sets the current intensity according to the physiological indicator characteristics and the calmness value when the calmness value is less than a preset calmness threshold;
[0133] The current stimulation module 104 performs electrical stimulation on the acupuncture points of the human body according to the current intensity value through the electrical stimulation device preset at the acupuncture points of the human body;
[0134] The continuous monitoring module 105 continuously executes the step of identifying the calmness degree of the human body according to the physiological indicator characteristics using the pre-trained physiological indicator recognition model to obtain a calmness value. If the calmness value is less than a preset calmness threshold, the step of electrically stimulating the human acupoints according to the current intensity value through the electrical stimulation device preset at the human acupoints is re-executed.
[0135] In detail, each module described in the closed-loop transcutaneous acupoint electrical stimulation sedation system 100 of the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The closed-loop transcutaneous acupoint electrical stimulation sedation method described in the invention has the same technical means and can produce the same technical effects, so it will not be repeated here.
[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A closed-loop transcutaneous acupoint electrical stimulation sedation system, characterized in that: The system comprises: A data acquisition module is used to acquire human physiological index information in real time using sensors, and perform standardization processing on the human physiological index information to obtain standardized physiological index information; A calmness identification module is used to extract features from the standardized physiological index information to obtain physiological index features, and use a pre-trained physiological index identification model to identify the calmness of the human body according to the physiological index features to obtain a calmness value; A calmness judgment module, when the calmness value is less than a preset calmness threshold, sets the current intensity according to the physiological indicator characteristics and the calmness value; The current stimulation module electrically stimulates the acupuncture points of the human body according to the current intensity through the electrical stimulation device preset at the acupuncture points of the human body; a continuous monitoring module, which continuously executes the step of identifying the calmness of the human body according to the physiological indicator characteristics using the pre-trained physiological indicator recognition model to obtain a calmness value, and if the calmness value is less than a preset calmness threshold, re-executes the step of electrically stimulating the acupuncture points of the human body according to the current intensity value by the electrical stimulation device preset at the acupuncture points of the human body; The step of performing standardization processing on the human physiological index information to obtain standardized physiological index information includes: The standardization process is expressed by the following formula: Among them, Y n represents the nth group of data in the standardized physiological index information, X n represents the nth group of data of the human physiological index information, avg represents the average of the nth group of data of the human physiological index information, and std represents the standard deviation of the nth group of data of the human physiological index information; The step of extracting features from the standardized physiological indicator information to obtain physiological indicator features includes: Performing missing value processing on the standardized physiological index information to obtain preprocessed physiological index information; Performing word segmentation processing on the pre-processed physiological indicator information to obtain a word list; Traversing the word list, deleting repeated words in the word list, and obtaining a vocabulary list; Converting the words in the word list into vector form according to the occurrence positions and occurrence times of the words in the vocabulary to obtain a physiological indicator vector; Performing dimensionality reduction processing on the physiological indicator vector to obtain physiological indicator features; The method of using the pre-trained physiological index recognition model to identify the calmness of the human body according to the physiological index characteristics and obtaining the calmness value also includes: Acquire historical physiological indicator information of the patient, perform feature extraction on the historical physiological indicator information, and obtain historical physiological indicator features; Using a neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics to obtain a training calmness value; Calculating the difference between the training calmness value and the standard calmness value preset by the historical physiological index characteristic; If the difference value is greater than or equal to a preset difference value threshold, then adjusting the weight parameters and bias items of the neural network model according to the difference value, and then re-performing the above step of using the neural network model to identify the patient's calmness level according to the historical physiological indicator characteristics to obtain a training calmness value; If the difference value is less than a preset difference value threshold, the model training is confirmed to be completed, and a physiological indicator recognition model is obtained; The calculating of the difference between the training calmness value and the standard calmness value preset by the historical physiological indicator characteristic comprises: The difference value is calculated using the following formula: Wherein, L represents the difference value, M represents the standard calm value preset by the historical physiological index characteristic, and N represents the training calm value; The step of setting the current intensity according to the physiological indicator characteristics and the calming value includes: Calculate the difference between the stabilization value and a preset standard difference value to obtain a stabilization value difference; Measuring the patient’s body conductivity by conductometric method; The current intensity is set according to the sedation value difference, human body conductivity and physiological index characteristics.
2. The closed-loop transcutaneous acupoint electrical stimulation sedation system according to claim 1, characterized in that: The method of using sensors to obtain human physiological index information in real time includes: Using a temperature sensor to obtain the patient's temperature data; Using a pulse sensor to obtain patient pulse data; Using a blood pressure sensor to obtain blood pressure data of the patient; Using a respiratory sensor to obtain patient respiratory data; The blood oxygen concentration sensor is used to obtain the patient's blood oxygen concentration data.
3. The closed-loop transcutaneous acupoint electrical stimulation sedation system according to claim 1, characterized in that: The method of using the pre-trained physiological index recognition model to identify the calmness of the human body according to the physiological index characteristics to obtain the calmness value includes: Using the physiological index recognition model to perform data conversion processing on the physiological index characteristics to obtain a feature matrix; Using the physiological index recognition model to perform a convolution operation on the feature matrix through a convolution layer to obtain a convolution feature; Using the physiological index recognition model, a maximum pooling operation is performed on the convolutional features through a pooling layer to obtain a pooling feature; The physiological index recognition model is used to identify the patient's calmness level according to the pooling features through a fully connected layer to obtain a calmness value.
4. The closed-loop transcutaneous acupoint electrical stimulation sedation system according to claim 3, characterized in that: The method of using the physiological index recognition model to identify the patient's calmness level according to the pooling features through a fully connected layer to obtain a calmness value includes: The stabilization value is calculated using the following formula: y=g(W*p+b) Among them, y is the stabilization value, W is the weight parameter of the fully connected layer, p is the pooling feature, b is the bias term, and g is the softmax function.
