AI-based remote medical monitoring system and method

Abstract

The application relates to the field of medical monitoring, in particular to an AI-based remote medical monitoring system and method; the method comprises the following steps: establishing remote user nodes and medical interaction nodes according to user identity information and medical identity information, collecting body sign data and body rest data of a target monitoring user, and establishing a user medical monitoring model; setting a remote interaction period, obtaining a focused data set according to the remote interaction period and the body sign index, and obtaining an abnormal data set according to the focused data set; obtaining user codes and user transmission data sets according to the abnormal data set and the user identity information, obtaining transmission encryption data sets according to an intelligent medical platform of the user medical monitoring model and the user transmission data sets, and sending the transmission encryption data sets to a medical rehabilitation unit; the medical rehabilitation unit processes the received transmission encryption data sets, obtains a medical data set, and evaluates the medical data set. The application can reduce abnormal recognition errors and improve data security.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring, and more specifically to an AI-based remote medical monitoring system and method. Background Technology

[0002] As information technology and healthcare services become increasingly integrated, telemedicine has gradually become an indispensable and important component of the global healthcare system. The global demand for contactless, cross-regional healthcare services is growing rapidly, and telemedicine monitoring is gaining significant attention because it enables real-time health management for patients at home or in non-medical settings.

[0003] The rapid development of artificial intelligence (AI) technology, especially breakthroughs in machine learning, deep learning, and natural language processing, has endowed remote medical monitoring with new connotations and capabilities. AI-based monitoring systems can extract potential patterns from large-scale, multi-dimensional, and multi-time-series data, dynamically identify trends in health status changes, and achieve more intelligent risk warnings and personalized health interventions.

[0004] Chinese Patent CN118762816B discloses an adaptive remote medical monitoring method and system based on the Internet of Things (IoT), including: creating patient files and allocating and configuring devices; collecting real-time health data of patients and transmitting it to a cloud server for data preprocessing; detecting anomalies in the preprocessed data and performing preliminary analysis of the abnormal data; assessing the patient's health status and developing response measures. This invention, by creating personalized patient files, performing intelligent device allocation and configuration, constructing anomaly detection algorithms, and performing preliminary analysis of abnormal data, ensures that the monitoring equipment can accurately meet the personalized monitoring needs of patients. This not only improves the efficiency and accuracy of remote medical monitoring but also enables timely detection of abnormal changes in the patient's health status, providing medical personnel with a scientific basis for decision-making.

[0005] In existing technologies, for scenarios requiring long-term monitoring and tracking, such as brain disease monitoring, postoperative rehabilitation monitoring, and health monitoring, the monitoring data cannot be used for personalized monitoring of users, which increases the error in identifying abnormal data in remote medical monitoring. Furthermore, there are data security risks associated with user-related medical monitoring data, which are problems we need to solve. Summary of the Invention

[0006] The purpose of this invention is to address the problems existing in the background technology by proposing an AI-based remote medical monitoring method.

[0007] The technical solution of this invention: an AI-based remote medical monitoring method, comprising the following steps:

[0008] S1. Using the acquired user identity information and medical staff identity information, establish remote user nodes and medical staff interaction nodes, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model.

[0009] S2. Set a remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle to obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets.

[0010] S3. Analyze the abnormal dataset and user identity information to obtain user codes and user transmission datasets. Process the user transmission datasets through the intelligent medical platform of the user medical monitoring model to obtain encrypted transmission datasets and send them to the medical and rehabilitation unit.

[0011] S4. The medical rehabilitation unit processes the received encrypted data set to obtain a medical dataset and evaluates the medical dataset.

[0012] Preferably, the process of establishing remote user nodes and medical staff interaction nodes using the acquired user identity information and medical staff identity information, collecting vital sign data and circadian rhythm data of the target monitored user, and establishing a user medical monitoring model includes:

[0013] Set up an intelligent medical platform, user monitoring unit, and medical rehabilitation unit, and obtain user identity information and medical staff identity information;

[0014] The user monitoring unit establishes several remote user nodes based on each user's identity information. It is equipped with various monitoring devices to collect the target user's vital signs and daily routine data, storing them at the corresponding remote user nodes. Vital signs data includes vital sign indices and durations; vital sign indices include brain monitoring data and vital sign monitoring indices; vital sign durations include brain monitoring time and vital sign monitoring time; daily routine data includes sleep structure data and activity behavior data; sleep structure data includes sleep structure state and sleep structure time; and activity behavior data includes activity behavior indicators and activity time.

[0015] The medical rehabilitation unit is used to store the historical medical records of each target user and to establish several medical interaction nodes based on the identity information of each medical staff member.

[0016] A monitoring and transmission link is constructed between each remote user node and the intelligent medical platform, and a medical and nursing transmission link is constructed between each medical and nursing interaction node and the intelligent medical platform. The remote nodes are linked to the intelligent medical platform through the monitoring and transmission link, and the medical and nursing interaction nodes are linked to the intelligent medical platform through the medical and nursing transmission link, so as to obtain a user medical monitoring model.

[0017] Preferably, the process of setting a remote interaction cycle and analyzing the organism's vital signs index through the remote interaction cycle to obtain a focused dataset is as follows:

[0018] The index monitoring period of the organism's vital signs index is obtained, and the least common multiple of the index monitoring periods corresponding to all the organism's vital signs indexes of each remote user node is set as the remote interaction period of the corresponding remote user node.

[0019] By setting a user two-dimensional coordinate system through remote interaction cycles, the physical signs index and brain monitoring index of the corresponding remote user node are mapped to the vertical axis of the user two-dimensional coordinate system. By mapping the sleep structure state of the corresponding sleep structure time and the activity behavior index of the corresponding activity time to the vertical axis of the user two-dimensional coordinate system through the time period corresponding to the horizontal axis of the user two-dimensional coordinate system.

[0020] Using an AI anomaly detection algorithm, anomaly analysis is performed on the body's vital signs indices within the user's two-dimensional coordinate system. If abnormal data is found, the abnormal data of the body's vital signs indices in the user's two-dimensional coordinate system is marked, the horizontal axis time period corresponding to the abnormal data is marked, and the sleep structure state, activity behavior indicators, and brain monitoring indices in the vertical axis data within the corresponding horizontal axis time period are marked. The marked vertical axis data and horizontal axis time periods are recorded as the focused dataset.

[0021] Preferably, the process of further analyzing the focused dataset to obtain the anomalous dataset includes:

[0022] Calculate the mean value of each bodily vital signs index in each remote interaction cycle within the user's two-dimensional coordinate system, and then calculate the mean value of each bodily vital signs index in each remote interaction cycle, which is denoted as the cycle vital signs balance index.

[0023] The index fluctuation threshold range is set using the periodic vital sign balance index;

[0024] Remove the labels from abnormal data of bodily vital signs within the index fluctuation threshold range in the focused dataset; retain the labels from abnormal data of bodily vital signs outside the index fluctuation threshold range in the focused dataset, and denote the retained labels as the abnormal dataset.

[0025] Preferably, the process of analyzing abnormal datasets and user identity information to obtain user codes and user transmission datasets includes:

[0026] By monitoring the abnormal datasets of the target user, the data in the user's two-dimensional coordinate system is divided into multiple datasets. The datasets other than the abnormal datasets are called normal datasets. The abnormal datasets and normal datasets are assigned numbers according to their order in the user's two-dimensional coordinate system, and the total number u of the normal datasets and abnormal datasets in the user's two-dimensional coordinate system is obtained.

[0027] Remove all relevant user identity information from the abnormal dataset and the normal dataset in the remote user node, and randomly generate user codes using the user identity information of the remote user node.

[0028] The user codes are divided into u-1 code segments according to the order of user coding. u-1 empty datasets are constructed using the u-1 code segments, and the corresponding code segments are stored in the empty datasets. The constructed empty datasets are first randomly inserted into the normal dataset, and then randomly inserted into the abnormal dataset. The index of the normal dataset and the index of the abnormal dataset are obtained in the order of random insertion into the normal dataset and the abnormal dataset, respectively. The initial dataset and the final dataset are constructed. The initial dataset and the final dataset are inserted into the beginning and the end of all datasets in the user's two-dimensional coordinate system, respectively, to obtain the user transmission dataset.

[0029] Preferably, the process of processing the user-transmitted dataset through an intelligent medical platform using a user medical monitoring model to obtain an encrypted dataset and sending it to the medical and rehabilitation unit includes:

[0030] The user transmits the dataset to the smart healthcare platform, which contains a medical public key. The platform uses the medical public key to encrypt the user transmit dataset, obtaining the encrypted dataset, and then sends the encrypted dataset to the medical rehabilitation unit.

[0031] Preferably, the process by which the medical rehabilitation unit processes the received encrypted dataset to obtain a medical dataset and evaluates the medical dataset includes:

[0032] The medical rehabilitation unit decrypts the received encrypted dataset, extracts the beginning and end of the decrypted dataset, and sequentially extracts the empty datasets from the decrypted datasets according to their numbers to obtain the medical dataset. The extracted empty datasets are then concatenated to reconstruct the user code of the target monitored user. Based on the user code, the unit searches for historical medical records within the medical rehabilitation unit, selects the most recent historical medical records and their corresponding medical interaction nodes, and sends the medical dataset to the medical interaction nodes. Combined with the corresponding historical medical records, the unit assesses the physical condition of the target monitored user.

[0033] This invention also discloses an AI-based remote medical monitoring system, including a management center, which is communicatively connected to a medical monitoring module, a medical analysis module, a medical encryption module, and a medical evaluation module.

[0034] The medical monitoring module is used to establish remote user nodes and medical staff interaction nodes by acquiring user identity information and medical staff identity information, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model.

[0035] The medical analysis module is used to set the remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle, obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets;

[0036] The medical encryption module is used to analyze abnormal datasets and user identity information to obtain user codes and user transmission datasets. The intelligent medical platform of the user medical monitoring model processes the user transmission datasets to obtain encrypted transmission datasets, which are then sent to the medical and rehabilitation unit.

[0037] The medical assessment module is used by the medical and rehabilitation unit to process the received encrypted dataset, obtain the medical dataset, and assess the medical dataset.

[0038] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects: By acquiring user identity information and medical staff identity information, remote user nodes and medical staff interaction nodes are established; the vital signs data and daily routine data of the target monitored user are collected to establish a user medical monitoring model; a personalized medical monitoring model is constructed to improve monitoring accuracy; a remote interaction cycle is set, and the vital signs index is analyzed through the remote interaction cycle to obtain a focused dataset; further analysis of the focused dataset yields an abnormal dataset; this helps to obtain the user's health change trend, improve the comparability between indices, achieve high efficiency in data filtering, and reduce errors in brain abnormality identification; the abnormal dataset and user identity information are analyzed to obtain user codes and user transmission datasets; the user transmission dataset is processed through the intelligent medical platform of the user medical monitoring model to obtain a transmission encrypted dataset, which is then sent to the medical staff rehabilitation unit; data security is improved; the medical staff rehabilitation unit processes the received transmission encrypted dataset to obtain a medical dataset and evaluates the medical dataset; this helps to assist in brain medical rehabilitation. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of one embodiment of the present invention. Detailed Implementation

[0040] Example 1, as Figure 1 As shown, the AI-based remote medical monitoring method proposed in this invention includes the following steps:

[0041] S1. Using the acquired user identity information and medical staff identity information, establish remote user nodes and medical staff interaction nodes, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model.

[0042] S2. Set a remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle to obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets.

[0043] S3. Analyze the abnormal dataset and user identity information to obtain user codes and user transmission datasets. Process the user transmission datasets through the intelligent medical platform of the user medical monitoring model to obtain encrypted transmission datasets and send them to the medical and rehabilitation unit.

[0044] S4. The medical rehabilitation unit processes the received encrypted data set to obtain a medical dataset and evaluates the medical dataset.

[0045] It should be further explained that, in the specific implementation process, the process of establishing remote user nodes and medical staff interaction nodes by acquiring user identity information and medical staff identity information, collecting vital sign data and physical activity data of the target monitored user, and establishing a user medical monitoring model is as follows:

[0046] Set up an intelligent medical platform, user monitoring unit, and medical rehabilitation unit, and obtain user identity information and medical staff identity information;

[0047] The user monitoring unit is used to establish several remote user nodes based on each user's identity information. It is equipped with various monitoring devices to collect the target user's physical characteristics data and physical activity data, and store them in the corresponding remote user nodes.

[0048] The bodily vital signs data includes bodily vital signs indices and bodily vital signs duration; the bodily vital signs indices include, but are not limited to, brain monitoring indices and vital signs monitoring indices; the bodily vital signs duration includes, but is not limited to, brain monitoring time and vital signs monitoring time; the bodily circadian rhythm data includes sleep structure data and activity behavior data; the sleep structure data includes sleep structure state and sleep structure time; the activity behavior data includes activity behavior indicators and activity time.

[0049] Specifically, the various monitoring devices include, but are not limited to, wearable devices, home health terminals, mobile devices, and medical devices; the wearable devices include, but are not limited to, smartwatches, ECG patches, and sleep wristbands; the home health terminals include, but are not limited to, smart blood pressure monitors, blood glucose meters, and thermometers; the mobile devices include, but are not limited to, smartphones and APP interfaces; the medical devices include, but are not limited to, multi-parameter monitors and portable ECG monitors; the vital signs monitoring indices include, but are not limited to, heart rate, blood pressure, blood oxygen, body temperature, and ECG; the brain monitoring indices include, but are not limited to, electroencephalogram (EEG) and cerebral blood oxygenation; the sleep structure states include, but are not limited to, NREM and REM states; and the activity behavior indicators include, but are not limited to, exercise volume and food intake.

[0050] The medical rehabilitation unit is used to store the historical medical records of each target user and to establish several medical interaction nodes based on the identity information of each medical staff member.

[0051] A monitoring and transmission link is constructed between each remote user node and the intelligent medical platform, and a medical and nursing transmission link is constructed between each medical and nursing interaction node and the intelligent medical platform. The monitoring and transmission links connect each remote node to the intelligent medical platform, and the medical and nursing transmission links connect each medical and nursing interaction node to the intelligent medical platform to obtain a user medical monitoring model. The user medical monitoring model is used to monitor and analyze the vital signs data and daily routine data of each remote user.

[0052] It should be further explained that, in the specific implementation process, the process of setting a remote interaction cycle, analyzing the organism's vital signs index through the remote interaction cycle to obtain a focused dataset, and further analyzing the focused dataset to obtain anomaly datasets is as follows:

[0053] The index monitoring period of the organism's vital signs index is obtained, and the least common multiple of the index monitoring periods corresponding to all the organism's vital signs indexes of each remote user node is set as the remote interaction period of the corresponding remote user node.

[0054] By setting a user two-dimensional coordinate system through remote interaction cycles, the physical signs index and brain monitoring index of the corresponding remote user node are mapped to the vertical axis of the user two-dimensional coordinate system. By mapping the sleep structure state of the corresponding sleep structure time and the activity behavior index of the corresponding activity time to the vertical axis of the user two-dimensional coordinate system through the time period corresponding to the horizontal axis of the user two-dimensional coordinate system.

[0055] Using an AI anomaly detection algorithm, anomaly analysis is performed on the body vital signs index in the user's two-dimensional coordinate system. If abnormal data is found, the abnormal data of the body vital signs index in the user's two-dimensional coordinate system is marked, the horizontal axis time period corresponding to the abnormal data is marked, and the sleep structure state, activity behavior indicators and brain monitoring index in the vertical axis data within the corresponding horizontal axis time period are marked. The marked vertical axis data and horizontal axis time period are recorded as the focused dataset.

[0056] Calculate the mean value of each bodily vital signs index in each remote interaction cycle within the user's two-dimensional coordinate system, and then calculate the mean value of each bodily vital signs index in each remote interaction cycle, which is denoted as the cycle vital signs balance index.

[0057] Specifically, the periodic vital signs balance index includes, but is not limited to, multiple brain-related indices and vital signs-related indices;

[0058] The index fluctuation threshold range is set using the periodic vital sign balance index;

[0059] Specifically, the cyclical vital signs balance index is centered within the index fluctuation threshold range;

[0060] Remove the labels from abnormal data of bodily vital signs within the index fluctuation threshold range in the focused dataset; retain the labels from abnormal data of bodily vital signs outside the index fluctuation threshold range in the focused dataset, and denote the retained labels as the abnormal dataset.

[0061] It should be further explained that, in the specific implementation process, the analysis of abnormal datasets and user identity information to obtain user codes and user transmission datasets, the processing of user transmission datasets by the intelligent medical platform of the user medical monitoring model to obtain encrypted transmission datasets, and the sending to the medical and rehabilitation unit are as follows:

[0062] By monitoring the abnormal datasets of target users, the data within the user's two-dimensional coordinate system is divided into multiple datasets. The datasets excluding the abnormal datasets are designated as normal datasets. Based on the order of the normal and abnormal datasets within the user's two-dimensional coordinate system, the abnormal and normal datasets are respectively assigned numbers p1, p2, p3, ..., p... n and q1, q2, q3, ..., q m , where n and m are natural numbers greater than 0, and obtain the total number u of normal datasets and abnormal datasets in the user's two-dimensional coordinate system;

[0063] Remove all relevant user identity information from the abnormal dataset and the normal dataset in the remote user node, and randomly generate user codes using the user identity information of the remote user node.

[0064] Specifically, the user code is unique and unrelated to user identity information, and is confidential; the historical medical records stored in the medical rehabilitation unit contain the user code, and the historical medical records refer to the medical history conclusions drawn by medical staff from the data analysis of the target monitored user at a historical time.

[0065] The user codes are divided into u-1 code segments according to the order of user coding. u-1 empty datasets are constructed using the u-1 code segments, and the corresponding code segments are stored in the empty datasets. The constructed empty datasets are first randomly inserted into the normal dataset, and then randomly inserted into the abnormal dataset. According to the order of random insertion into the normal dataset and the abnormal dataset, the index m of the normal dataset and the index n of the abnormal dataset are obtained in sequence. The initial dataset and the final dataset are constructed. The initial dataset and the final dataset are inserted into the beginning and the end of all datasets in the user's two-dimensional coordinate system, respectively, to obtain the user transmission dataset.

[0066] The user transmits a dataset to an intelligent medical platform, which contains a medical public key. The user transmits a dataset to an encrypted dataset, which is then sent to the medical rehabilitation unit.

[0067] Specifically, the medical public key is distributed through an intelligent medical platform, while the private key is distributed to the user monitoring unit and the medical rehabilitation unit. The user monitoring unit and the medical rehabilitation unit are equipped with verification ports to verify whether the user is a secure user or a medical user. Users who pass the verification are assigned a private key to ensure the security of the private key.

[0068] It should be further explained that, in the specific implementation process, the medical and rehabilitation unit processes the received encrypted dataset to obtain a medical dataset, and then evaluates the medical dataset as follows:

[0069] The medical rehabilitation unit decrypts the received encrypted dataset, extracts the beginning and end of the decrypted dataset, and sequentially extracts the empty datasets from the decrypted datasets according to their numbers to obtain the medical dataset. The extracted empty datasets are then concatenated to reconstruct the user code of the target monitored user. Based on the user code, the unit searches for historical medical records within the medical rehabilitation unit, selects the most recent historical medical records and their corresponding medical interaction nodes, and sends the medical dataset to the medical interaction nodes. Combined with the corresponding historical medical records, the unit assesses the physical condition of the target monitored user.

[0070] Example 2: The AI-based remote medical monitoring system proposed in this invention is applied to the AI-based remote medical monitoring method described in Example 1. Specifically, it includes a management center, which is communicatively connected to a medical monitoring module, a medical analysis module, a medical encryption module, and a medical evaluation module.

[0071] The medical monitoring module is used to establish remote user nodes and medical staff interaction nodes by acquiring user identity information and medical staff identity information, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model.

[0072] The medical analysis module is used to set the remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle, obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets;

[0073] The medical encryption module is used to analyze abnormal datasets and user identity information to obtain user codes and user transmission datasets. The intelligent medical platform of the user medical monitoring model processes the user transmission datasets to obtain encrypted transmission datasets, which are then sent to the medical and rehabilitation unit.

[0074] The medical assessment module is used by the medical and rehabilitation unit to process the received encrypted dataset, obtain the medical dataset, and assess the medical dataset.

[0075] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. An AI-based remote medical monitoring method, characterized in that, Includes the following steps: S1. Using the acquired user identity information and medical staff identity information, establish remote user nodes and medical staff interaction nodes, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model. S2. Set a remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle to obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets. S3. Analyze the abnormal dataset and user identity information to obtain user codes and user transmission datasets. Process the user transmission datasets through the intelligent medical platform of the user medical monitoring model to obtain encrypted transmission datasets and send them to the medical and rehabilitation unit. S4. The medical rehabilitation unit processes the received encrypted data set to obtain a medical dataset and evaluates the medical dataset. The process of setting up a remote interaction cycle and analyzing the organism's vital signs indexes through the remote interaction cycle to obtain a focused dataset is as follows: The index monitoring period of the organism's vital signs index is obtained, and the least common multiple of the index monitoring periods corresponding to all the organism's vital signs indexes of each remote user node is set as the remote interaction period of the corresponding remote user node. By setting a user two-dimensional coordinate system through remote interaction cycles, the physical signs index and brain monitoring index of the corresponding remote user node are mapped to the vertical axis of the user two-dimensional coordinate system. By mapping the sleep structure state of the corresponding sleep structure time and the activity behavior index of the corresponding activity time to the vertical axis of the user two-dimensional coordinate system through the time period corresponding to the horizontal axis of the user two-dimensional coordinate system. Using an AI anomaly detection algorithm, anomaly analysis is performed on the body vital signs index in the user's two-dimensional coordinate system. If abnormal data is found, the abnormal data of the body vital signs index in the user's two-dimensional coordinate system is marked, the horizontal axis time period corresponding to the abnormal data is marked, and the sleep structure state, activity behavior indicators and brain monitoring index in the vertical axis data within the corresponding horizontal axis time period are marked. The marked vertical axis data and horizontal axis time period are recorded as the focused dataset. The process of further analyzing the focused dataset to obtain the anomalous dataset includes: Calculate the mean value of each bodily vital signs index in each remote interaction cycle within the user's two-dimensional coordinate system, and then calculate the mean value of each bodily vital signs index in each remote interaction cycle, which is denoted as the cycle vital signs balance index. The index fluctuation threshold range is set using the periodic vital sign balance index; Remove the labels from abnormal data of bodily vital signs within the index fluctuation threshold range in the focused dataset; retain the labels from abnormal data of bodily vital signs outside the index fluctuation threshold range in the focused dataset, and denote the retained labels as abnormal datasets. The process of analyzing abnormal datasets and user identity information to obtain user codes and user transmission datasets includes: By monitoring the abnormal datasets of the target user, the data in the user's two-dimensional coordinate system is divided into multiple datasets. The datasets other than the abnormal datasets are called normal datasets. The abnormal datasets and normal datasets are assigned numbers according to their order in the user's two-dimensional coordinate system, and the total number u of the normal datasets and abnormal datasets in the user's two-dimensional coordinate system is obtained. Remove all relevant user identity information from the abnormal dataset and the normal dataset in the remote user node, and randomly generate user codes using the user identity information of the remote user node. The user code is divided into u-1 code segments according to the order of the user code. u-1 empty datasets are constructed using the u-1 code segments, and the corresponding code segments are stored in the empty datasets. The constructed empty datasets are first randomly inserted into the normal dataset, and then randomly inserted into the abnormal dataset. According to the order of random insertion into the normal dataset and the abnormal dataset, the index of the normal dataset and the index of the abnormal dataset are obtained in sequence. The initial dataset and the final dataset are constructed. The initial dataset and the final dataset are inserted into the beginning and the end of all datasets in the user's two-dimensional coordinate system, respectively, to obtain the user transmission dataset. The process of processing user-transmitted datasets through an intelligent medical platform using a user medical monitoring model to obtain encrypted datasets and then sending them to the medical and rehabilitation unit includes: The user transmits the dataset to the smart healthcare platform, which contains a medical public key. The platform uses the medical public key to encrypt the user transmit dataset, obtaining the encrypted dataset, and then sends the encrypted dataset to the medical rehabilitation unit.

2. The AI-based remote medical monitoring method according to claim 1, characterized in that, The process of establishing remote user nodes and medical staff interaction nodes by acquiring user and medical staff identity information, collecting vital sign data and daily routine data of the target monitored users, and building a user medical monitoring model includes: Set up an intelligent medical platform, user monitoring unit, and medical rehabilitation unit, and obtain user identity information and medical staff identity information; The user monitoring unit establishes several remote user nodes based on each user's identity information. It is equipped with various monitoring devices to collect the target user's vital signs and daily routine data, storing them at the corresponding remote user nodes. Vital signs data includes vital sign indices and durations; vital sign indices include brain monitoring indices and physical sign monitoring indices; vital sign durations include brain monitoring time and physical sign monitoring time; daily routine data includes sleep structure data and activity behavior data; sleep structure data includes sleep structure state and sleep structure time; and activity behavior data includes activity behavior indicators and activity time. The medical rehabilitation unit is used to store the historical medical records of each target user and to establish several medical interaction nodes based on the identity information of each medical staff member. A monitoring and transmission link is constructed between each remote user node and the intelligent medical platform, and a medical and nursing transmission link is constructed between each medical and nursing interaction node and the intelligent medical platform. The remote nodes are linked to the intelligent medical platform through the monitoring and transmission link, and the medical and nursing interaction nodes are linked to the intelligent medical platform through the medical and nursing transmission link, so as to obtain a user medical monitoring model.

3. The AI-based remote medical monitoring method according to claim 2, characterized in that, The healthcare rehabilitation unit processes the received encrypted dataset to obtain a medical dataset, and the process of evaluating the medical dataset includes: The medical rehabilitation unit decrypts the received encrypted dataset, extracts the beginning and end of the decrypted dataset, and sequentially extracts the empty datasets from the decrypted datasets according to their numbers to obtain the medical dataset. The extracted empty datasets are then concatenated to reconstruct the user code of the target monitored user. Based on the user code, the unit searches for historical medical records within the medical rehabilitation unit, selects the most recent historical medical records and their corresponding medical interaction nodes, and sends the medical dataset to the medical interaction nodes. Combined with the corresponding historical medical records, the unit assesses the physical condition of the target monitored user.

4. An AI-based remote medical monitoring system, used to execute the AI-based remote medical monitoring method according to any one of claims 1 to 3, comprising a management center, characterized in that, The management center's communication connections include a medical monitoring module, a medical analysis module, a medical encryption module, and a medical evaluation module. The medical monitoring module is used to establish remote user nodes and medical staff interaction nodes by acquiring user identity information and medical staff identity information, collect the target user's vital signs data and physical activity data, and establish a user medical monitoring model. The medical analysis module is used to set the remote interaction cycle, analyze the body's vital signs index through the remote interaction cycle, obtain a focused dataset, and further analyze the focused dataset to obtain anomaly datasets; The medical encryption module is used to analyze abnormal datasets and user identity information to obtain user codes and user transmission datasets. The intelligent medical platform of the user medical monitoring model processes the user transmission datasets to obtain encrypted transmission datasets, which are then sent to the medical and rehabilitation unit. The medical assessment module is used by the medical and rehabilitation unit to process the received encrypted dataset, obtain the medical dataset, and assess the medical dataset.

Images