Intelligent altitude stress monitoring management system and method based on ultrasonic probe

Abstract

The invention discloses an altitude stress intelligent monitoring management system and method based on an ultrasonic probe, and relates to the technical field of data analysis, the system comprises a data acquisition module, a data processing module, a user interaction module and a data management module; the data acquisition module is used for acquiring, acquiring and transmitting ultrasonic images, ultrasonic data and sensor data; the data processing module is used for processing and analyzing the collected data, evaluating the risk and predicting the trend; the user interaction module is used for feeding back data changes and trends to users and providing personalized suggestions for the users according to the data; and the data management module is used for storing the collected data and receiving user feedback so as to facilitate system optimization and data management. The invention also provides a method for realizing the system. According to the invention, the condition of inaccurate judgment caused by relatively single monitoring index in the prior art can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to an intelligent monitoring and management system and method for altitude sickness based on an ultrasonic probe. Background Art

[0002] Altitude sickness is a common acute high-altitude disease, mainly caused by hypoxia in the high-altitude environment, and often manifested as symptoms such as headache, fatigue, nausea, etc.

[0003] Currently, ultrasonic probes can be used to obtain ultrasonic images and related data of the heart, and then evaluate structural information such as the size, shape, and wall thickness of the left ventricle and right ventricle, as well as functional indicators such as stroke volume, cardiac output, and ejection fraction.

[0004] In the existing altitude sickness monitoring technologies, many altitude sickness monitoring devices mainly focus on simple physiological indicators such as blood oxygen saturation and heart rate. For example, a common portable blood oxygen meter can only provide real-time data of the blood oxygen saturation indicator. However, altitude sickness is a complex physiological process, and it is not accurate enough to judge the degree of altitude sickness only by relying on blood oxygen saturation. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent monitoring and management system and method for altitude sickness based on an ultrasonic probe to solve the problems raised in the prior art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An intelligent monitoring and management system for altitude sickness based on an ultrasonic probe, the system includes a data acquisition module, a data processing module, a user interaction module, and a data management module;

[0007] The data acquisition module is used to acquire, transmit ultrasonic images, ultrasonic data, and sensor data; the data processing module is used to process and analyze the acquired data, evaluate risks and predict trends; the user interaction module is used to feedback data changes and trends to the user and provide personalized suggestions for the user according to the data; the data management module is used to store the acquired data and receive user feedback to facilitate system optimization and data management;

[0008] The output end of the data acquisition module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the user interaction module; the output end of the user interaction module is connected to the input end of the data management module.

[0009] The data acquisition module includes an ultrasonic probe unit, a sensor unit, and a data acquisition unit;

[0010] The ultrasonic probe unit is used to collect ultrasonic images and ultrasonic data; the sensor unit is used to collect sensor data; the data acquisition unit is used to summarize and transmit the collected data for subsequent processing;

[0011] The output end of the ultrasonic probe unit is connected to the input end of the sensor unit; the output end of the sensor unit is connected to the input end of the data acquisition module; the output end of the data acquisition unit is connected to the input end of the data processing module.

[0012] The data processing module includes a preprocessing unit, a feature extraction unit, a risk assessment unit, and a trend prediction unit;

[0013] The preprocessing unit is used to preprocess the collected images and data; the feature extraction unit is used to extract features using a convolutional neural network in combination with ultrasonic images, data, and sensor data; the risk assessment unit is used to classify and predict the risk represented by the data by using a pre-trained SVM classification model for the feature vectors; the trend prediction unit is used to construct and train an LSTM time series model to predict ultrasonic data and sensor data;

[0014] The output end of the preprocessing unit is connected to the input end of the feature extraction unit; the output end of the feature extraction unit is connected to the input end of the risk assessment unit; the output end of the risk assessment unit is connected to the input end of the trend prediction unit; the output end of the trend prediction unit is connected to the input end of the user interaction module.

[0015] The user interaction module includes a real-time feedback unit and a personalized recommendation unit;

[0016] The real-time feedback unit is used to feedback the changes in each data and the prediction trend to the user in real time; the personalized recommendation unit is used to provide personalized recommendations for the user according to the classification of the data by the system and in combination with the prediction data trend;

[0017] The output end of the real-time feedback unit is connected to the input end of the personalized recommendation unit; the output end of the personalized recommendation unit is connected to the input end of the data management module.

[0018] The data management module includes a data storage unit and a feedback unit;

[0019] The data storage unit is used to store the historical data of the user in a specific format; the feedback unit is used to receive the response of the user to the system recommendations and feedback data;

[0020] The output end of the data storage unit is connected to the input end of the feedback unit.

[0021] An intelligent monitoring and management method for altitude sickness based on an ultrasonic probe, the method comprising the following steps:

[0022] Step 1: Obtain images and ultrasonic data through an ultrasonic probe, obtain sensor data through a sensor, and integrate the data;

[0023] Step 2: Preprocess the collected data, extract features from the integrated data; use a classification model for risk assessment and construct a time series model to predict data trends;

[0024] Step 3: The user monitors the changes in each data and the predicted trends in real time through an intelligent device, and the system provides suggestions for the user according to the different classifications to which the data belongs and combines the predicted data trends;

[0025] Step 4: The intelligent device stores the user's historical data and allows the user to independently select the way to use the data.

[0026] In step 1, the ultrasonic probe and the sensor are wirelessly connected to the intelligent device via Bluetooth or Wi-Fi;

[0027] The ultrasonic probe captures images through an array element linear array, expressed as: [P1, P2,..., P u ; where u is a positive integer representing the number of images, and P1 to P u respectively represent the 1st to u-th images;

[0028] The ultrasonic probe adopts the Doppler ultrasound mode, detects and calculates the ultrasonic data, expressed as: [t1: C1, C2,..., C v ;...; t m : C1, C2,..., C v ; where m is a positive integer representing the number of time instants, t1 to t m respectively represent the 1st to m-th time instants; v is a positive integer representing the number of ultrasonic data; C1 to C v respectively represent the 1st to v-th ultrasonic data;

[0029] The sensor obtains sensor data, expressed as: [t1: D1, D2,..., D a ;...; t m : D1, D2,..., D a ; where a is a positive integer representing the number of sensor data; D1 to D a respectively represent the 1st to a-th sensor data;

[0030] Integrate and store the data: The data is arranged as [P1,..., P u , t1: C1,..., C v ;...; tm : C1, ..., C v , t1: D1, ..., D a ;...; t m : D1, ..., D a are stored in this format.

[0031] In step 2, the specific method of the preprocessing is as follows: For the ultrasonic image, the image is normalized to a unified resolution, the region of interest ROI is extracted and converted into a grayscale feature matrix to reduce the data dimension: P k ’ = ∫ x，y∈ROI P k (x, y)·w(x, y)dx dy;

[0032] where x represents the pixel coordinate in the width direction of the image; y represents the pixel coordinate in the height direction of the image; k is a positive integer representing the image sequence; P k ∈{P1, P2, ..., P u}, P k ’ represents the processed image feature; P k (x, y) represents the pixel value of the image Pk; w(x, y) represents the weight function;

[0033] Align the multi-modal data according to the time stamp to generate a fused data vector: X = [P1’, ..., P u ’, t1: C1, ..., C v , D1, ..., D a ;...; t m : D1, ..., D a , C1, ..., C v ;

[0034] For the ultrasonic image, use a two-dimensional convolutional neural network to extract spatial features: Reduce the size of the feature map through max pooling to retain key information; map the convolutional features to a feature vector F1; where l represents the number of convolutional layers; m, n are positive integers representing the indices of the convolutional kernel in the width and height directions of the image respectively; represents the eigenvalue of the convolutional image; P′ k (x + m, y + n) represents the pixel value of the input image in the local window; represents the weight of the convolutional kernel; b l represents the bias;

[0035] For ultrasonic data and sensor data, a one-dimensional convolutional neural network is used to process time series: the convolutional layer extracts local dynamic features of the time series; the pooling layer downsamples the time step features to reduce the dimension; the fully connected layer maps the extracted time series features into vectors to obtain feature vectors F2 and F3; where F2 and F3 represent ultrasonic data features and sensor data features respectively;

[0036] The features extracted from all modalities are concatenated into a unified feature vector F: F = [F1, F2, F3];

[0037] For the unified feature vector F, a pre-trained SVM classification model is used to classify and predict the feature vector;

[0038] The pre-trained classification model is obtained by extracting and fusing a large amount of data from historical data, constructing an SVM classification model and training it;

[0039] For ultrasonic data and sensor data, an LSTM time series model is constructed, and an LSTM time series model applied to different types of ultrasonic data and sensor data is trained based on the data collected at different times; different types of ultrasonic data and sensor data are predicted according to the model; feature extraction and fusion are performed on the predicted different types of ultrasonic data and sensor data combined with ultrasonic images, and classification prediction is performed again according to the pre-trained SVM classification model.

[0040] In step 3, the user monitors the changes of each data and the prediction trend in real time through the intelligent device, and the system pre-sets corresponding suggestions for different classifications and outputs corresponding suggestions to the user according to the classification situation;

[0041] In step 4, the intelligent device stores the user's historical data and allows the user to independently select the data usage method; the usage methods include deleting data, exporting data, sharing data to obtain manual feedback, and sharing data for scientific research analysis.

[0042] Compared with the prior art, the beneficial effects of the present invention are: the present invention can comprehensively monitor a variety of data and has more advantages in the early diagnosis of altitude sickness-related diseases; the present invention combines a variety of data for comprehensive analysis, can discover potential health risks earlier, helps to take intervention measures in time, and improves the prognosis of patients; the present invention uses a pre-trained SVM classification model to classify and predict the fused feature vector, can intelligently evaluate the risk of altitude sickness, accurately judge the severity of the patient's altitude sickness and the risk level of complications, and provides a scientific basis for subsequent treatment and intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic flowchart of a smart monitoring and management system for altitude sickness based on an ultrasonic probe of the present invention;

[0044] Figure 2 This is a schematic diagram of the steps of an intelligent monitoring and management method for altitude sickness based on an ultrasonic probe according to the present invention. Detailed implementation manners

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment: As Figure 1 - Figure 2 shown, the present invention provides a technical solution, an intelligent monitoring and management system for altitude sickness based on an ultrasonic probe, and the system includes a data acquisition module, a data processing module, a user interaction module, and a data management module;

[0047] The data acquisition module is used to acquire ultrasonic images, ultrasonic data, and sensor data and perform acquisition and transmission; the data processing module is used to process and analyze the acquired data, evaluate risks, and predict trends; the user interaction module is used to feedback data changes and trends to users and provide personalized suggestions for users according to the data; the data management module is used to store the acquired data and receive user feedback to facilitate system optimization and data management;

[0048] The output end of the data acquisition module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the user interaction module; the output end of the user interaction module is connected to the input end of the data management module.

[0049] The data acquisition module includes an ultrasonic probe unit, a sensor unit, and a data acquisition unit;

[0050] The ultrasonic probe unit is used to acquire ultrasonic images and ultrasonic data; the sensor unit is used to acquire sensor data; the data acquisition unit is used to summarize and transmit the acquired data for subsequent processing;

[0051] The output end of the ultrasonic probe unit is connected to the input end of the sensor unit; the output end of the sensor unit is connected to the input end of the data acquisition module; the output end of the data acquisition unit is connected to the input end of the data processing module.

[0052] The data processing module includes a preprocessing unit, a feature extraction unit, a risk assessment unit, and a trend prediction unit;

[0053] The preprocessing unit is used to preprocess the acquired images and data; the feature extraction unit is used to extract features using a convolutional neural network in combination with ultrasonic images, data, and sensor data; the risk assessment unit is used to classify and predict the risk represented by the data by using a pre-trained SVM classification model for the feature vectors; the trend prediction unit is used to construct and train an LSTM time series model to predict ultrasonic data and sensor data;

[0054] The output end of the preprocessing unit is connected to the input end of the feature extraction unit; the output end of the feature extraction unit is connected to the input end of the risk assessment unit; the output end of the risk assessment unit is connected to the input end of the trend prediction unit; the output end of the trend prediction unit is connected to the input end of the user interaction module.

[0055] The user interaction module includes a real-time feedback unit and a personalized recommendation unit;

[0056] The real-time feedback unit is used to feedback the changes of each data and the prediction trend to the user in real time; the personalized recommendation unit is used to provide personalized recommendations for the user according to the classification of the data by the system and in combination with the prediction data trend;

[0057] The output end of the real-time feedback unit is connected to the input end of the personalized recommendation unit; the output end of the personalized recommendation unit is connected to the input end of the data management module.

[0058] The data management module includes a data storage unit and a feedback unit;

[0059] The data storage unit is used to store the historical data of the user in a specific format; the feedback unit is used to receive the response of the user to the system recommendations and feedback data;

[0060] The output end of the data storage unit is connected to the input end of the feedback unit.

[0061] An intelligent monitoring and management method for altitude sickness based on an ultrasonic probe, the method comprising the following steps:

[0062] Step 1, acquiring images and ultrasonic data through an ultrasonic probe, acquiring sensor data through a sensor, and integrating the data;

[0063] Step 2, preprocessing the acquired data, extracting features from the integrated data; using a classification model for risk assessment and constructing a time series model to predict the data trend;

[0064] Step 3, the user monitors the changes of each data and the prediction trend in real time through an intelligent device, and the system provides recommendations for the user according to the different classifications of the data and in combination with the prediction data trend;

[0065] Step 4: The intelligent device stores the user's historical data and allows the user to independently select the data usage path.

[0066] In Step 1, the ultrasonic probe and the sensor are wirelessly connected to the intelligent device via Bluetooth or Wi-Fi;

[0067] The ultrasonic probe captures images through an array element linear array, expressed as: [P1, P2,..., P u ; where u is a positive integer representing the number of images, and P1 to P u represent the 1st to u-th images respectively;

[0068] The ultrasonic probe adopts the Doppler ultrasound mode, detects and calculates the ultrasonic data, expressed as: [t1: C1, C2,..., C v ;...; t m : C1, C2,..., C v ; where m is a positive integer representing the number of time instances, t1 to t m represent the 1st to m-th time instances respectively; v is a positive integer representing the number of ultrasonic data; C1 to C v represent the 1st to v-th ultrasonic data respectively;

[0069] The sensor obtains sensor data, expressed as: [t1: D1, D2,..., D a ;...; t m : D1, D2,..., D a ; where a is a positive integer representing the number of sensor data; D1 to D a represent the 1st to a-th sensor data respectively;

[0070] Integrate and store the data: The data is stored in the format of [P1,..., P u , t1: C1,..., C v ;...; t m : C1,..., C v , t1: D1,..., D a ;...; t m : D1,..., D a .

[0071] In Step 2, the specific method of preprocessing is as follows: For ultrasonic images, the images are normalized to a unified resolution, the region of interest ROI is extracted and converted into a grayscale feature matrix to reduce the data dimension: P k ’ = ∫ x，y∈ROI P k (x, y)·w(x, y)dx dy;

[0072] Among them, x represents the pixel coordinate in the width direction of the image; y represents the pixel coordinate in the height direction of the image; k is a positive integer representing the image sequence; P k ∈{P1, P2,..., P u}, P k ’ represents the processed image feature; P k (x, y) represents the pixel value of the image Pk; w(x, y) represents the weight function;

[0073] Align the multi-modal data according to the time stamp to generate a fused data vector: X = [P1’,..., P u ’, t1:C1,..., C v , D1,..., D a ;...; t m : D1,..., D a , C1,..., C v ;

[0074] For ultrasonic images, use a two-dimensional convolutional neural network to extract spatial features: Reduce the size of the feature map through max pooling to retain key information; map the convolutional features to a feature vector F1; where l represents the number of convolutional layers; m and n are positive integers, representing the indices of the convolutional kernel in the width and height directions of the image respectively; represents the eigenvalue of the convolutional image; P′ k (x + m, y + n) represents the pixel value of the input image in the local window; represents the weight of the convolutional kernel; b l represents the bias;

[0075] For ultrasonic data and sensor data, use a one-dimensional convolutional neural network to process time series: The convolutional layer extracts the local dynamic features of the time series; the pooling layer downsamples the time step features to reduce the dimension; the fully connected layer maps the extracted time series features to a vector to obtain feature vectors F2 and F3; where F2 and F3 represent the ultrasonic data feature and the sensor data feature respectively;

[0076] Concatenate the features extracted from all modalities into a unified feature vector F: F = [F1, F2, F3];

[0077] For the unified feature vector F, use a pre-trained SVM classification model to classify and predict the feature vector;

[0078] The pre-trained classification model is obtained by extracting and fusing a large amount of data from historical data, constructing an SVM classification model and training it;

[0079] For ultrasonic data and sensor data, an LSTM time series model is constructed. Based on the data collected at different times, an LSTM time series model applied to different types of ultrasonic data and sensor data is trained; different types of ultrasonic data and sensor data are predicted according to the model; feature extraction and fusion are performed on the predicted different types of ultrasonic data and sensor data combined with ultrasonic images, and classification prediction is performed again according to the pre-trained SVM classification model.

[0080] In step 3, the user monitors the changes of each data and the prediction trend in real time through a smart device. The system pre-sets corresponding suggestions for different classifications and outputs corresponding suggestions to the user according to the classification situation.

[0081] In step 4, the smart device stores the user's historical data and allows the user to independently select the data usage method; the usage methods include deleting data, exporting data, sharing data to obtain manual feedback, and sharing data for scientific research analysis.

[0082] In this embodiment,

[0083] Step 1: Obtain images and ultrasonic data through an ultrasonic probe, obtain sensor data through a sensor, and integrate the data.

[0084] The ultrasonic probe and the sensor are wirelessly connected to the smart device via Bluetooth or Wi-Fi.

[0085] The ultrasonic probe captures images through an array linear array.

[0086] The ultrasonic probe adopts the Doppler ultrasound mode to detect and calculate ultrasonic data.

[0087] The sensor obtains sensor data.

[0088] Integrate and store the data: The data is stored in a fixed format.

[0089] Step 2: Preprocess the collected data, extract features from the integrated data; use a classification model for risk assessment and construct a time series model to predict the data trend.

[0090] The specific method of preprocessing is as follows: For ultrasonic images, standardize the images to a unified resolution, extract the region of interest (ROI) and convert it into a grayscale feature matrix to reduce the data dimension.

[0091] Align the multi-modal data according to the time stamp to generate a fused data vector.

[0092] For ultrasonic images, use a two-dimensional convolutional neural network to extract spatial features; reduce the size of the feature map through max pooling to retain key information; map the convolutional features to a feature vector F1.

[0093] For ultrasonic data and sensor data, a one-dimensional convolutional neural network is used to process the time series: the convolutional layer extracts the local dynamic features of the time series; the pooling layer downsamples the time-step features to reduce the dimension; the fully connected layer maps the extracted time-series features into vectors to obtain feature vectors F2 and F3;

[0094] The features extracted from all modalities are concatenated into a unified feature vector F: F = [F1, F2, F3];

[0095] For the unified feature vector F, a pre-trained SVM classification model is used to classify and predict the feature vector;

[0096] The pre-trained classification model is obtained by extracting and fusing a large amount of data from historical data, constructing an SVM classification model and training it; the types can be divided into: [risk-free, mild risk, moderate risk, high risk];

[0097] For ultrasonic data and sensor data, an LSTM time series model is constructed, and an LSTM time series model applied to different types of ultrasonic data and sensor data is trained based on the data collected at different times; different types of ultrasonic data and sensor data are predicted according to the model; feature extraction and fusion are performed on the predicted different types of ultrasonic data and sensor data combined with ultrasonic images, and classification prediction is performed again according to the pre-trained SVM classification model.

[0098] Step 3: The user monitors the changes in each data and the prediction trend in real time through the intelligent device. The system pre-sets corresponding suggestions for different classifications and outputs corresponding suggestions to the user according to the classification situation;

[0099] Step 4: The intelligent device stores the user's historical data and allows the user to independently select the data usage method; the usage methods include deleting data, exporting data, sharing data to obtain manual feedback, and sharing data for scientific research analysis.

[0100] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. An intelligent monitoring and management system for altitude sickness based on an ultrasonic probe, characterized in that: The system includes a data acquisition module, a data processing module, a user interaction module and a data management module; The data acquisition module is used to acquire ultrasound images, ultrasound data and sensor data and to collect and transmit them; the data processing module is used to process and analyze the collected data, assess risks and predict trends; The user interaction module is used to feed back data changes and trends to users and provide users with personalized suggestions based on the data; The data management module is used to store the collected data and receive user feedback to facilitate system optimization and data management; The output end of the data acquisition module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the user interaction module; the output end of the user interaction module is connected to the input end of the data management module.

2. The intelligent monitoring and management system for altitude sickness based on ultrasonic probe according to claim 1 is characterized by: The data acquisition module includes an ultrasound probe unit, a sensor unit and a data acquisition unit; The ultrasonic probe unit is used to collect ultrasonic images and ultrasonic data; the sensor unit is used to collect sensor data; the data acquisition unit is used to summarize and transmit the collected data for subsequent processing; The output end of the ultrasonic probe unit is connected to the input end of the sensor unit; the output end of the sensor unit is connected to the input end of the data acquisition module; the output end of the data acquisition unit is connected to the input end of the data processing module.

3. The intelligent monitoring and management system for altitude sickness based on ultrasonic probe according to claim 2 is characterized by: The data processing module includes a preprocessing unit, a feature extraction unit, a risk assessment unit and a trend prediction unit; The preprocessing unit is used to preprocess the collected images and data; the feature extraction unit is used to extract features by using a convolutional neural network in combination with ultrasound images, data and sensor data; the risk assessment unit is used to classify and predict the risk represented by the feature vector using a pre-trained SVM classification model; the trend prediction unit is used to construct and train an LSTM time series model to predict ultrasound data and sensor data; The output end of the preprocessing unit is connected to the input end of the feature extraction unit; the output end of the feature extraction unit is connected to the input end of the risk assessment unit; the output end of the risk assessment unit is connected to the input end of the trend prediction unit; the output end of the trend prediction unit is connected to the input end of the user interaction module.

4. The intelligent monitoring and management system for altitude sickness based on ultrasonic probe according to claim 3 is characterized by: The user interaction module includes a real-time feedback unit and a personalized suggestion unit; The real-time feedback unit is used to provide real-time feedback of data changes and predicted trends to users; the personalized suggestion unit is used to provide personalized suggestions to users based on the system's classification of data and combined with the predicted data trends; The output end of the real-time feedback unit is connected to the input end of the personalized suggestion unit; the output end of the personalized suggestion unit is connected to the input end of the data management module.

5. The intelligent monitoring and management system for altitude sickness based on ultrasonic probe according to claim 4 is characterized by: The data management module includes a data storage unit and a feedback unit; The data storage unit is used to store the user's historical data in a specific format; the feedback unit is used to receive the user's response to the system suggestions and feedback data; The output end of the data storage unit is connected to the input end of the feedback unit.

6. An intelligent monitoring and management method for altitude sickness based on an ultrasonic probe, characterized in that: The method comprises the following steps: Step 1: Acquire images and ultrasound data through an ultrasound probe, acquire sensor data through a sensor and integrate the data; Step 2: Preprocess the collected data and extract features from the integrated data; use the classification model to conduct risk assessment and build a time series model to predict data trends; Step 3: Users monitor data changes and forecast trends in real time through smart devices. The system provides suggestions to users based on the different categories of data and forecast data trends. Step 4: Smart devices store user historical data, allowing users to independently choose how to use the data.

7. The method for intelligent monitoring and management of altitude sickness based on ultrasonic probe according to claim 6 is characterized by: In step 1, the ultrasound probe and the sensor are wirelessly connected to a smart device via Bluetooth or Wi-Fi; The ultrasound probe captures images through a linear array of elements, represented as: [P1, P2, ..., P u ]; where u is a positive integer, indicating the number of images, P1~P u Represent the 1st to uth images respectively; The ultrasound probe uses Doppler ultrasound mode to detect and calculate the ultrasound data, which is expressed as: [t1: C1, C2, ..., C v ;...;t m : C1, C2, ..., C v ]; where m is a positive integer, indicating the number of moments, t1~t m Respectively represent the 1st to mth moments; v is a positive integer, indicating the number of ultrasonic data; C1~C v Respectively represent the 1st to vth ultrasound data; The sensor obtains sensor data, which is expressed as: [t1: D1, D2, ..., D a ;...;t m : D1, D2, ..., D a ]; where a is a positive integer, indicating the number of sensor data; D1~D a Respectively represent the 1st to ath sensor data; Integrate and store data: Data is stored in the order of [P1, ..., P u , t1:C1,...,C v ;...;t m : C1, ..., C v , t1:D1,...,D a ;...;t m : D1, ..., D a ] format for storage.

8. The method for intelligent monitoring and management of altitude sickness based on ultrasonic probe according to claim 7 is characterized by: In step 2, the specific method of preprocessing is as follows: for ultrasound images, the images are standardized to a uniform resolution, the region of interest ROI is extracted and converted into a grayscale feature matrix, and the data dimension is reduced: k '=∫ x，y∈ROI P k (x, y)·w(x, y)dxdy; Where x represents the pixel coordinates in the width direction of the image; y represents the pixel coordinates in the height direction of the image; k is a positive integer representing the image sequence; P k ∈{P1, P2, ..., P u }, P k ' represents the processed image features; P k (x, y) represents the pixel value of the image Pk; w(x, y) represents the weight function; Align the multimodal data by timestamp to generate a fused data vector: X = [P1', ..., P u ', t1: C1, ..., C v , D1, ..., D a ;...;t m : D1, ..., D a , C1, ..., C v ]; For ultrasound images, a two-dimensional convolutional neural network is used to extract spatial features: Reduce the size of the feature map through maximum pooling to retain key information; map the convolutional features to feature vector F1; where l represents the number of convolution layers; m and n are positive integers, representing the index of the convolution kernel in the image width and height directions respectively; Represents the eigenvalue of the image after convolution; P′ k (x+m, y+n) represents the pixel value of the input image in the local window; represents the weight of the convolution kernel; b l Indicates bias; For ultrasound data and sensor data, a one-dimensional convolutional neural network is used to process time series: the convolution layer extracts local dynamic features of the time series; the pooling layer downsamples the time step features to reduce the dimension; the fully connected layer maps the extracted time series features into vectors to obtain feature vectors F2 and F3; where F2 and F3 represent ultrasound data features and sensor data features, respectively; Concatenate the features extracted from all modalities into a unified feature vector F: F = [F1, F2, F3]; For the unified feature vector F, the pre-trained SVM classification model is used to classify and predict the feature vector; The pre-trained classification model is obtained by extracting and fusing features of a large amount of historical data, constructing an SVM classification model, and training it. For ultrasound data and sensor data, an LSTM time series model is constructed, and the LSTM time series model applied to different types of ultrasound data and sensor data is trained based on the data collected at different times; different types of ultrasound data and sensor data are predicted according to the model; the predicted different types of ultrasound data and sensor data are combined with ultrasound images for feature extraction and fusion, and classification prediction is performed again based on the pre-trained SVM classification model.

9. The method for intelligent monitoring and management of altitude sickness based on ultrasonic probe according to claim 8 is characterized by: In step 3, users monitor data changes and forecast trends in real time through smart devices. The system sets corresponding suggestions for different categories in advance and outputs corresponding suggestions to users based on the classification. In step 4, the smart device stores the user's historical data, allowing the user to independently choose how to use the data; the usage methods include deleting data, exporting data, sharing data to obtain manual feedback, and sharing data for scientific research analysis.

Images