Medical information cloud platform data dynamic encryption uploading method

Abstract

The invention discloses a medical information cloud platform data dynamic encryption uploading method, and relates to the technical field of medical information cloud platform data. Acquiring various parameter information generated in the process of uploading the locally encrypted medical information to the cloud, wherein the parameter information comprises network security information and network transmission quality information; by monitoring the network security and transmission quality information in real time, potential abnormal hidden dangers are recognized in time, and the data loss and damage risks in the medical information uploading process are remarkably reduced. By means of comparison between the transmission abnormal index and the preset reference threshold value, the system can quickly judge the risk state of the uploading process and take corresponding early warning measures. The intelligent monitoring and feedback mechanism not only ensures the integrity and accuracy of medical information, but also can quickly respond in emergency, and reduces the risk of misdiagnosis, treatment delay or drug use error, thereby effectively protecting the health and safety of patients.

Description

Technical Field

[0001] The present invention relates to the field of medical information cloud platform data technology, and in particular to a method for dynamically encrypting and uploading data of a medical information cloud platform. Background Art

[0002] The dynamic encryption data upload method of the medical information cloud platform is a technology that ensures the security of sensitive medical data during transmission. First of all, "dynamic encryption" means that in the process of uploading data from local devices (such as hospital computers or medical equipment) to the cloud platform, the system will generate and use different encryption keys in real time according to the specific circumstances of the transmission. This dynamic encryption method can effectively prevent large-scale data leakage after a single key is cracked. Even if an encryption key is obtained by an attacker, they can only decrypt a very small part of the data, not all of it. Dynamic encryption is usually combined with modern encryption algorithms, such as AES or RSA, to ensure the confidentiality and integrity of the data.

[0003] Secondly, the upload method usually refers to the encryption strategy and steps in the data transmission process. The medical information cloud platform will perform identity authentication before the data transmission begins to ensure the legality of the sender and receiver. After the data is encrypted locally, it is uploaded to the cloud through a secure transmission protocol to prevent interception or tampering during transmission. In addition, dynamic encrypted upload usually involves segmented transmission. Combined with distributed storage technology, the data is split into multiple small blocks and encrypted and uploaded separately to further improve security. This upload method can not only protect patient privacy, but also ensure the compliance of medical data during transmission and storage, and meet the requirements of relevant laws and regulations on medical information protection.

[0004] The prior art has the following deficiencies: If anomalies occur during the process of uploading medical information from local encryption to the cloud, a series of serious consequences may occur, especially when sensitive personal information and patient privacy are involved. If problems occur during the encrypted upload process, some data may be lost or damaged, and the integrity and accuracy of medical information are crucial. Especially in emergency situations, any erroneous or incomplete data may directly affect the patient's treatment plan and prognosis. If doctors cannot obtain complete and accurate medical records, it may lead to misdiagnosis, delayed treatment or medication errors, causing irreversible damage to the patient's health. In addition, many medical data are closely related to health monitoring and public health management at the regional or national level. If the encrypted upload fails, key public health data may be leaked or lost, hindering the government or public health agencies from monitoring and managing the epidemic and disease trends, thereby delaying epidemic warning and control measures, and threatening the health and safety of the entire society.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method for dynamically encrypting and uploading data on a medical information cloud platform to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: comprising the following steps: Obtain various parameter information generated during the process of uploading medical information to the cloud after being encrypted locally, including network security information and network transmission quality information; In the detection window, the obtained network security information and network transmission quality information are analyzed, and the analyzed network security information and network transmission quality information are input into the pre-learned machine model. The transmission anomaly index is generated through the learning model, and the process of uploading medical information to the cloud after local encryption is intelligently perceived based on the transmission anomaly index; Based on the results output by the machine learning model, the process of uploading medical information from local encryption to the cloud is divided into high-risk transmission abnormality state or low-risk transmission abnormality state, and the process of uploading medical information from local encryption to the cloud is intelligently evaluated; For the assessed high-risk transmission abnormality status, continuously obtain the process information of uploading medical information to the cloud after local encryption, and divide the high-risk transmission abnormality status into sudden status, unstable status and continuous status; Different early warning measures are taken for different types of high-risk transmission abnormal conditions.

[0008] Preferably, the network security information includes the TLS handshake failure rate, which refers to the number or proportion of failures that occur during the TLS handshake process when establishing a secure connection. The network transmission quality information includes jitter variance, which refers to the degree of fluctuation in arrival time during data packet transmission, reflecting the stability of the network connection.

[0009] Preferably, after performing an abnormal analysis on the TLS handshake failure rate and jitter variance within the detection window, a TLS handshake failure rate index and a jitter variance index are generated respectively, and the TLS handshake failure rate index and the jitter variance index are input into a pre-learned machine model, and a transmission anomaly index is generated through the machine model. Based on the transmission anomaly index, the process of uploading medical information to the cloud after being encrypted locally is intelligently perceived.

[0010] Preferably, in the detection window, after performing an abnormal analysis on the TLS handshake failure rate, the specific steps of generating the TLS handshake failure rate index are as follows: In the detection window, the network monitoring system collects TLS handshake related data. The specific data is the number of successful handshakes N. success and the number of failed handshakes N failure , calculate the total number of TLS handshake requests through data, the calculation expression is as follows: N total =N success +N failure , where N total Indicates the total number of TLS handshake requests; Based on a specific time period within the detection window, denoted as S, the dynamic change of the TLS handshake failure rate is calculated. The calculation expression is as follows: , where FR T Indicates the TLS handshake failure rate, N failure (S) represents the number of TLS handshake failures in time period S, N total (S) represents the total number of TLS handshake requests in time period S; Considering the impact of different network conditions on the TLS handshake failure rate, a weight factor is introduced to calculate the weighted failure rate. The calculation expression is as follows: WFR S =FR S ×W, where W represents the weight factor of network conditions, WFR S represents the weighted failure rate, where the weight factor W of the network condition is calculated as follows: , where L is the network delay and B is the bandwidth utilization; Calculate the TLS handshake failure rate index. The calculation expression is as follows: , where I TLS represents the TLS handshake failure rate index, C represents the number of potential threats, and D represents the system protection capability index.

[0011] Preferably, in the detection window, after performing abnormal analysis on the jitter variance, the specific steps of generating the jitter variance index are as follows: In the detection window, the arrival time of each data packet is recorded and marked as T i , then T i ={T1, T2, T3, …, T N}, N represents the total number of packets, T i represents the arrival time of each data packet i; Calculate the arrival time difference between two adjacent data packets. The calculation expression is as follows: , where ΔT iIt represents the arrival time difference between adjacent data packets, representing the delay jitter in network transmission, that is, the arrival time difference between the i-th and i-1-th data packets; A delay weight function is defined to accurately capture jitter. The calculation expression is as follows: , where W(T i ) represents the delay weight function, α is the adjustment parameter used to control the sensitivity of jitter; The delay weight function W(T i ) is substituted into the formula of jitter variance index, and the calculation expression is as follows: , where Jvar represents the jitter variance index.

[0012] Preferably, the TLS handshake failure rate index I TLS The jitter variance index Jvar is input into the pre-learned machine model, and the transmission anomaly index TE is generated through the machine model according to the following formula: ;, where k1 and k2 are the TLS handshake failure rate index I TLS The proportional coefficient of the jitter variance index Jvar is preset, and k1 and k2 are both greater than 0.

[0013] Preferably, the generated transmission anomaly index is compared with a preset transmission anomaly index reference threshold, and the comparison result is as follows: If the transmission anomaly index is greater than or equal to a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a high-risk transmission anomaly state; If the transmission anomaly index is less than a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a low-risk transmission anomaly state.

[0014] Preferably, for the assessed high-risk transmission abnormality state, a data set is established to conduct comprehensive analysis by continuously acquiring a number of transmission abnormality indexes generated under a number of detection windows during the process of uploading the medical information to the cloud after being encrypted locally; The average value and standard deviation of several transmission anomaly indexes in the data set are calculated, and the calculated average value and standard deviation of the transmission anomaly index are compared with the preset transmission anomaly index average value reference threshold and the preset transmission anomaly index standard deviation threshold, respectively. The comparison results are as follows: If the average value of the transmission anomaly index is greater than or equal to the preset transmission anomaly index reference threshold, the high-risk transmission anomaly state is further divided into a continuous state; If the average value of the transmission anomaly index is less than the preset transmission anomaly index reference threshold and the standard deviation of the transmission anomaly index is greater than or equal to the preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further classified as an unstable state; If the transmission anomaly index average value is less than a preset transmission anomaly index reference threshold and the transmission anomaly index standard deviation is less than a preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further divided into a burst state.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention can timely identify potential abnormal hidden dangers in the transmission process by real-time monitoring and analysis of network security information and network transmission quality information. This intelligent perception mechanism effectively reduces the risk of data loss or damage during the upload of medical information. By comparing the transmission anomaly index with a pre-set reference threshold, it is possible to quickly determine whether the upload process is in a high-risk state, so that corresponding early warning measures can be taken. Such a real-time monitoring and feedback mechanism not only ensures the integrity and accuracy of medical information, but also can respond in a timely manner in emergencies, reduce the incidence of misdiagnosis, treatment delays or medication errors, and ultimately protect the health and safety of patients.

[0016] Through intelligent evaluation of high-risk transmission abnormal states, the present invention can divide the system into continuous states, unstable states, and sudden states. This segmented management enables the medical information cloud platform to take targeted response measures according to different abnormal states. For example, for continuous states, in-depth network optimization and resource allocation can be carried out; for unstable states, real-time monitoring and appropriate traffic management can be carried out; and for sudden states, the system can quickly enable emergency response mechanisms to ensure the timeliness and reliability of data transmission. This flexible resource allocation and response mechanism not only improves the operating efficiency of the platform, but also enhances the defense capabilities against potential security threats, thereby providing medical institutions with more stable and efficient data transmission services. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 This is a method flow chart of a method for dynamically encrypting and uploading data on a medical information cloud platform according to the present invention. DETAILED DESCRIPTION

[0019] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0020] The present invention provides Figure 1 A method for dynamically encrypting and uploading data to a medical information cloud platform is shown, comprising the following steps: Obtain various parameter information generated during the process of uploading medical information to the cloud after being encrypted locally, including network security information and network transmission quality information; Network security information includes TLS handshake failure rate, which refers to the number or proportion of failures in the TLS handshake process when establishing a secure connection. Network transmission quality information includes jitter variance, which refers to the degree of fluctuation in the arrival time of data packets during transmission, reflecting the stability of the network connection. In the detection window, the obtained network security information and network transmission quality information are analyzed, and the analyzed network security information and network transmission quality information are input into the pre-learned machine model. The transmission anomaly index is generated through the learning model, and the process of uploading medical information to the cloud after local encryption is intelligently perceived based on the transmission anomaly index; Under the detection window, after performing anomaly analysis on the TLS (Transport Layer Security Protocol) handshake failure rate and jitter variance, the TLS handshake failure rate index and jitter variance index are generated respectively. The TLS handshake failure rate index and jitter variance index are input into the pre-learned machine model, and the transmission anomaly index is generated through the machine model. Based on the transmission anomaly index, the process of uploading medical information to the cloud after local encryption is intelligently perceived; When medical information is uploaded to the cloud after being encrypted locally, if the TLS handshake failure rate is unstable, it may indeed cause abnormalities in encrypted uploads. The TLS handshake is a key step in ensuring the establishment of a secure encrypted channel. Failure or instability in the handshake process will directly affect the establishment and maintenance of the encrypted connection. If the handshake is unsuccessful, data transmission cannot be carried out through the encrypted channel, which may cause the data to be exposed to an unsafe network environment during transmission, increasing the risk of data being intercepted or tampered with. Secondly, unstable TLS handshake failure rates can lead to transmission interruptions or retries, which in turn affect the order and integrity of data packets. During transmission interruptions or retries, some data packets may be lost, duplicated, or not correctly delivered to the cloud. Since medical information usually requires the transmission of high-precision and complete data (such as medical records, diagnosis results, etc.), any data packet loss or damage may result in incomplete transmission content, which in turn affects the overall accuracy and reliability of medical information. Finally, the integrity and accuracy of medical information are crucial to the diagnosis and treatment of patients. Any abnormality in transmission will directly affect medical decisions. Incomplete or damaged medical information may cause doctors to obtain wrong or incomplete data, which may lead to misdiagnosis, delayed treatment or medication errors, and in serious cases, even threaten the patient's life safety. In the detection window, after performing an abnormal analysis on the TLS handshake failure rate, the specific steps to generate the TLS handshake failure rate index are as follows: In the detection window, the network monitoring system collects TLS handshake related data. The specific data is the number of successful handshakes N. success and the number of failed handshakes N failure , calculate the total number of TLS handshake requests through data, the calculation expression is as follows: N total =N success +N failure , where N total Indicates the total number of TLS handshake requests; It should be noted that the number of successful TLS handshakes and the number of failed TLS handshakes can be obtained in the following ways: 1. Network Monitoring Tools Use network monitoring and analysis tools (such as Wireshark, tcpdump, etc.) to capture and analyze network traffic; these tools can identify the TLS handshake process and record the number of successful and failed handshakes by monitoring the status of data packets; A successful TLS handshake: Usually there are "ClientHello" and "ServerHello" messages, and finally the process of successfully establishing a secure connection; Failed TLS handshake: Recognized error messages (such as "HandshakeFailure", "Alert" messages) can be marked as failed handshakes; 2. Server logs Many application servers and web servers (such as Apache, Nginx, etc.) record detailed logs of TLS handshakes; in these logs, you can find information about the status of each connection, including successful and failed handshake records; Successful handshake records: There will usually be a log entry indicating that the connection was successfully established; Failed handshake records: log entries indicating errors or anomalies, such as certificate verification failure, key mismatch, etc. 3. Application Monitoring At the application layer, performance and security metrics of applications can be collected by integrating monitoring tools such as Prometheus and Grafana. These tools can provide detailed information about TLS connections and allow developers to customize metric collection. Successful handshake: counters can be defined to increase the number of successful connections; Failed handshake: Record the number of failed handshakes by capturing exception handling or error events; 4. Network equipment Some network devices (such as firewalls, load balancers, and intrusion detection systems) can also monitor the TLS handshake process and record the number of successes and failures; these devices usually have deep packet inspection (DPI) capabilities that can identify handshake messages in TLS traffic; Through the above methods, the system can fully capture and record the number of successful and failed TLS handshakes, providing a data basis for subsequent analysis and monitoring; Based on a specific time period within the detection window, denoted as S, the dynamic change of the TLS handshake failure rate is calculated. The calculation expression is as follows: , where FR T Indicates the TLS handshake failure rate, N failure (S) represents the number of TLS handshake failures in time period S, N total (S) represents the total number of TLS handshake requests in time period S; It should be noted that the time period S refers to a specific time period within the detection window, which is used to calculate the number of TLS handshake requests and failures within the time period; Considering the impact of different network conditions on the TLS handshake failure rate, a weight factor is introduced to calculate the weighted failure rate. The calculation expression is as follows: WFR S =FR S ×W, where W represents the weight factor of network conditions, WFR S represents the weighted failure rate, where the weight factor W of the network condition is calculated as follows: , where L is the network delay and B is the bandwidth utilization; It should be noted that the weight factor can be determined by the following methods: 1. Rule of thumb: Based on the actual performance of the network environment and historical data, experts or network administrators can determine the importance of each factor based on experience and assign weights to them. This method is suitable for situations where you are familiar with a specific environment. 2. Data analysis: By analyzing historical network performance data, statistical methods (such as regression analysis) are used to evaluate the specific impact of various network conditions (such as latency, bandwidth, packet loss rate, etc.) on the TLS handshake failure rate, so as to calculate the corresponding weight for each factor; 3. Machine Learning: Using machine learning algorithms, the model is trained to automatically identify and determine the impact of different network conditions on the TLS handshake failure rate. This method can handle complex nonlinear relationships and provide more accurate weight distribution. 4. Standardized indicators: You can refer to the weight settings in industry standards or best practices and standardize them according to the importance of different network conditions to ensure consistency in calculations; Through these methods, the weighting factors can be reasonably determined so that the calculation results can better reflect the impact of actual network conditions on the TLS handshake failure rate; Calculate the TLS handshake failure rate index. The calculation expression is as follows: , where I TLS represents the TLS handshake failure rate index, C represents the number of potential threats, and D represents the system protection capability index; It should be noted that the number of potential threats and system protection capability indicators can be determined by the following methods: 1. Number of potential threats Historical data analysis: By analyzing the records of historical security events (such as intrusion detection systems, log analysis, etc.), the number of security threats discovered in the past period of time is counted; this can help identify common attack types and frequencies; Threat intelligence: Use external threat intelligence sources (such as security reports, industry notices, vulnerability databases, etc.) to understand emerging threats and attack trends in the current network environment, thereby assessing the number of potential threats; Risk assessment: Regular cybersecurity risk assessments are performed to identify vulnerabilities and possible attack paths in the system, thereby determining the number of potential threats; 2. System protection capability indicators Security control assessment: Evaluate the effectiveness of existing security control measures (such as firewalls, intrusion detection systems, encryption technology, etc.) and determine protection capability indicators based on their ability to resist known threats; Compliance standards: Refer to industry standards and best practices (such as ISO27001, NIST framework, etc.) to assess whether the system complies with these standards to measure protection capabilities; Vulnerability scanning and penetration testing: Regularly conduct system vulnerability scanning and penetration testing to identify security weaknesses in the system and evaluate the system's protection capabilities based on the number and types of vulnerabilities found; Response capability assessment: Evaluate the system's response time and processing capabilities when a security incident occurs, and measure its effectiveness in responding to potential threats; Through these methods, the number of potential threats and system protection capability indicators can be reasonably determined, thus providing a basis for network security assessment; When medical information is encrypted locally and then uploaded to the cloud, the jitter variance is unstable, which may indeed cause anomalies in the encrypted upload process, leading to partial data loss or damage, affecting the integrity and accuracy of the medical information. The jitter variance reflects the volatility of the arrival time of data packets. Large fluctuations can cause data packets to arrive out of order or even be lost. If these problems occur during the transmission of encrypted data, the data packets may not be reassembled or processed in the expected order, causing interference to the complete data chain of the transmission. When the arrival time of data packets is inconsistent, the data receiver may not be able to reassemble the data in time, especially when the medical data is subjected to a complex encryption algorithm, the receiver needs a complete and correct ciphertext data packet for decryption; when the jitter variance is large, some data packets may be delayed too long or even lost, which will cause the encrypted information to be unable to be transmitted completely; any lost encrypted data packets will affect the decryption process, which may cause decryption failure or generate erroneous decrypted data; as a result, the data uploaded to the cloud may be incomplete or damaged, affecting the accuracy of medical information; The integrity and accuracy of medical information are crucial to diagnosis and treatment. Once data is lost or damaged, doctors may not be able to obtain complete medical records, resulting in deviations in diagnosis and treatment plans or delayed treatment. This is especially serious in emergency situations or critical medical decisions. Data loss or damage may directly affect patient health and lead to medical accidents. Therefore, transmission anomalies caused by unstable jitter variance not only threaten data integrity, but may also seriously affect the reliability and security of medical information. After performing anomaly analysis on the jitter variance in the detection window, the specific steps to generate the jitter variance index are as follows: In the detection window, the arrival time of each data packet is recorded and marked as T i , then T i ={T1, T2, T3, …, T N}, N represents the total number of packets, T i represents the arrival time of each data packet i; Calculate the arrival time difference between two adjacent data packets. The calculation expression is as follows: , where ΔT i It represents the arrival time difference between adjacent data packets, representing the delay jitter in network transmission, that is, the arrival time difference between the i-th and i-1-th data packets; A delay weight function is defined to accurately capture jitter. The calculation expression is as follows: , where W(T i ) represents the delay weight function, α is the adjustment parameter used to control the sensitivity of jitter; It should be noted that jitter refers to the fluctuation or inconsistency of the arrival time of data packets during network transmission. Generally, in an ideal network transmission environment, data packets should arrive at the receiver at uniform time intervals. However, due to network delays, congestion, routing changes, etc., the arrival time of data packets may deviate in actual situations. This deviation or fluctuation is jitter. Jitter mainly affects time-sensitive network applications, such as video calls, online games, and real-time data transmission (such as medical monitoring data). In these scenarios, data needs to be transmitted in a strict order and time interval to ensure smooth and reliable communication. When jitter is large, the arrival time of data packets will be uneven, which may cause video or audio freezes, delays, or data loss, affecting user experience or system functions. Jitter can be understood from the following aspects: 1. Reasons Jitter is mainly caused by network uncertainty. Specific reasons include network congestion, router forwarding delay, physical medium interference, and differences in the transmission time of data packets on different paths. As the complexity of the network increases, the impact of these factors will become more significant, resulting in an increase in the magnitude of jitter. 2. Impact Jitter has a significant impact on real-time data transmission, especially in applications that require real-time data processing, such as video conferencing, VoIP (Internet phone), and medical monitoring systems. Excessive jitter can cause packets to arrive out of order or even be lost, leading to a drop in audio or video quality, interruption of data flow, or errors in processing sensitive data. 3. Jitter Measurement Jitter is usually measured by analyzing the arrival time differences of multiple data packets. It does not rely on the delay of a single data packet, but focuses on the delay fluctuations between adjacent data packets. Common jitter measurement methods include jitter variance, maximum jitter, etc. The greater the jitter, the higher the instability of network transmission. Lower jitter means that data packets arrive at more even intervals and the network is more stable. In short, jitter reflects the instability in network transmission; time-sensitive network applications need to effectively control jitter to ensure the order and timely transmission of data packets to maintain the quality and reliability of transmission; The delay weight function W(T i ) is substituted into the formula of jitter variance index, and the calculation expression is as follows: , where Jvar represents the jitter variance index; Under the detection window, the jitter variance index calculation expression shows that the larger the jitter variance index performance value, the greater the time fluctuation of network transmission, and the more unstable the order and time of data packet arrival, which leads to a greater probability of abnormal hidden dangers in the process of uploading medical information to the cloud after local encryption. This instability increases the possibility of data packet loss, damage or delay, affecting the integrity of encrypted data and the accuracy of decryption. On the contrary, if the jitter variance index performance value is smaller, it means that the network transmission is more stable, the probability of abnormal hidden dangers is relatively small, and the upload process is more reliable.

[0021] The TLS handshake failure rate index I TLS The jitter variance index Jvar is input into the pre-learned machine model, and the transmission anomaly index TE is generated through the machine model according to the following formula: ;, where k1 and k2 are the TLS handshake failure rate index I TLS The proportional coefficient of the jitter variance index Jvar is preset, and k1 and k2 are both greater than 0.

[0022] Under the detection window, it can be seen from the transmission anomaly index calculation expression that the larger the TLS handshake failure rate index performance value generated in the process of uploading medical information to the cloud after local encryption, the larger the jitter variance index performance value, the larger the transmission anomaly index performance value, indicating that the probability of anomalies in the process of uploading medical information to the cloud after local encryption is greater; conversely, the smaller the TLS handshake failure rate index performance value generated in the process of uploading medical information to the cloud after local encryption, the smaller the jitter variance index performance value, the smaller the transmission anomaly index performance value, indicating that the probability of anomalies in the process of uploading medical information to the cloud after local encryption is smaller; Based on the results output by the machine learning model, the process of uploading medical information from local encryption to the cloud is divided into high-risk transmission abnormality state or low-risk transmission abnormality state, and the process of uploading medical information from local encryption to the cloud is intelligently evaluated; The generated transmission anomaly index is compared with the preset transmission anomaly index reference threshold, and the comparison results are as follows: If the transmission anomaly index is greater than or equal to a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a high-risk transmission anomaly state; If the transmission anomaly index is less than a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a low-risk transmission anomaly state; For the assessed high-risk transmission abnormality status, continuously obtain the process information of uploading medical information to the cloud after local encryption, and divide the high-risk transmission abnormality status into sudden status, unstable status and continuous status; For the assessed high-risk transmission abnormality status, several transmission abnormality indexes generated under several detection windows in the process of continuously obtaining medical information when it is locally encrypted and uploaded to the cloud are used to establish a data set for comprehensive analysis; The average value and standard deviation of several transmission anomaly indexes in the data set are calculated, and the calculated average value and standard deviation of the transmission anomaly index are compared with the preset transmission anomaly index average value reference threshold and the preset transmission anomaly index standard deviation threshold, respectively. The comparison results are as follows: If the average value of the transmission anomaly index is greater than or equal to the preset transmission anomaly index reference threshold, the high-risk transmission anomaly state is further divided into a continuous state; If the average value of the transmission anomaly index is less than the preset transmission anomaly index reference threshold and the standard deviation of the transmission anomaly index is greater than or equal to the preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further classified as an unstable state; If the average value of the transmission anomaly index is less than the preset transmission anomaly index reference threshold and the standard deviation of the transmission anomaly index is less than the preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further classified as a burst state; Different early warning measures are taken for different types of high-risk transmission abnormal conditions.

[0023] Different early warning measures are taken for different types of high-risk transmission abnormal states. For continuous and unstable high-risk transmission abnormal states, red early warning prompts (high-level warning) and yellow early warning prompts (medium-level warning) are issued to notify relevant personnel to conduct detailed inspections and repairs. For sudden high-risk transmission abnormal states, since they may recover by themselves in a short time, no early warning prompts are issued, but relevant information is recorded for subsequent analysis.

[0024] The present invention can timely identify potential abnormal hidden dangers in the transmission process by real-time monitoring and analysis of network security information and network transmission quality information. This intelligent perception mechanism effectively reduces the risk of data loss or damage during the upload of medical information. By comparing the transmission anomaly index with a pre-set reference threshold, it is possible to quickly determine whether the upload process is in a high-risk state, so that corresponding early warning measures can be taken. Such a real-time monitoring and feedback mechanism not only ensures the integrity and accuracy of medical information, but also can respond in a timely manner in emergencies, reduce the incidence of misdiagnosis, treatment delays or medication errors, and ultimately protect the health and safety of patients.

[0025] Through intelligent evaluation of high-risk transmission abnormal states, the present invention can divide the system into continuous states, unstable states, and sudden states. This segmented management enables the medical information cloud platform to take targeted response measures according to different abnormal states. For example, for continuous states, in-depth network optimization and resource allocation can be carried out; for unstable states, real-time monitoring and appropriate traffic management can be carried out; and for sudden states, the system can quickly enable emergency response mechanisms to ensure the timeliness and reliability of data transmission. This flexible resource allocation and response mechanism not only improves the operating efficiency of the platform, but also enhances the defense capabilities against potential security threats, thereby providing medical institutions with more stable and efficient data transmission services.

[0026] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for dynamically encrypting and uploading data on a medical information cloud platform, comprising the following steps; Obtain various parameter information generated during the process of uploading medical information to the cloud after being encrypted locally, including network security information and network transmission quality information; In the detection window, the obtained network security information and network transmission quality information are analyzed, and the analyzed network security information and network transmission quality information are input into the pre-learned machine model. The transmission anomaly index is generated through the learning model, and the process of uploading medical information to the cloud after local encryption is intelligently perceived based on the transmission anomaly index; Based on the results output by the machine learning model, the process of uploading medical information from local encryption to the cloud is divided into high-risk transmission abnormality state or low-risk transmission abnormality state, and the process of uploading medical information from local encryption to the cloud is intelligently evaluated; For the assessed high-risk transmission abnormality status, continuously obtain the process information of uploading medical information to the cloud after local encryption, and divide the high-risk transmission abnormality status into sudden status, unstable status and continuous status; Different early warning measures are taken for different types of high-risk transmission abnormal conditions.

2. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 1, characterized in that: Network security information includes TLS handshake failure rate. TLS handshake failure rate refers to the number or proportion of failures that occur during the TLS handshake process when establishing a secure connection. Network transmission quality information includes jitter variance. Jitter variance refers to the degree of fluctuation in the arrival time during data packet transmission, which reflects the stability of the network connection.

3. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 2, characterized in that: In the detection window, after performing anomaly analysis on the TLS handshake failure rate and jitter variance, the TLS handshake failure rate index and jitter variance index are generated respectively. The TLS handshake failure rate index and jitter variance index are input into the pre-learned machine model, and the transmission anomaly index is generated through the machine model. Based on the transmission anomaly index, the process of uploading medical information to the cloud after local encryption is intelligently perceived.

4. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 3, characterized in that: In the detection window, after performing an abnormal analysis on the TLS handshake failure rate, the specific steps to generate the TLS handshake failure rate index are as follows: In the detection window, the network monitoring system collects TLS handshake related data. The specific data is the number of successful handshakes N. success and the number of failed handshakes N failure , calculate the total number of TLS handshake requests through data, the calculation expression is as follows: N total =N success +N failure , where N total Indicates the total number of TLS handshake requests; Based on a specific time period within the detection window, denoted as S, the dynamic change of the TLS handshake failure rate is calculated. The calculation expression is as follows: , In the formula, FR T Indicates the TLS handshake failure rate, N failure (S) represents the number of TLS handshake failures in time period S, N total (S) represents the total number of TLS handshake requests in time period S; Considering the impact of different network conditions on the TLS handshake failure rate, a weight factor is introduced to calculate the weighted failure rate. The calculation expression is as follows: WFR S =FR S ×W, where W represents the weight factor of network conditions, WFR S represents the weighted failure rate, where the weight factor W of the network condition is calculated as follows: , where L is the network delay and B is the bandwidth utilization; Calculate the TLS handshake failure rate index. The calculation expression is as follows: , where I TLS represents the TLS handshake failure rate index, C represents the number of potential threats, and D represents the system protection capability index.

5. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 3, characterized in that: After performing anomaly analysis on the jitter variance in the detection window, the specific steps to generate the jitter variance index are as follows: In the detection window, the arrival time of each data packet is recorded and marked as T i , then T i ={T1, T2, T3, …, T N }, N represents the total number of packets, T i represents the arrival time of each data packet i; Calculate the arrival time difference between two adjacent data packets. The calculation expression is as follows: , where ΔT i It represents the arrival time difference between adjacent data packets, representing the delay jitter in network transmission, that is, the arrival time difference between the i-th and i-1-th data packets; A delay weight function is defined to accurately capture jitter. The calculation expression is as follows: , where W(T i ) represents the delay weight function, α is the adjustment parameter used to control the sensitivity of jitter; The delay weight function W(T i ) is substituted into the formula of jitter variance index, and the calculation expression is as follows: , where Jvar represents the jitter variance index.

6. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 3, characterized in that: The TLS handshake failure rate index I TLS The jitter variance index Jvar is input into the pre-learned machine model, and the transmission anomaly index TE is generated through the machine model according to the following formula: ;, where k1 and k2 are the TLS handshake failure rate index I TLS The proportional coefficient of the jitter variance index Jvar is preset, and k1 and k2 are both greater than 0.

7. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 6, characterized in that: The generated transmission anomaly index is compared with the preset transmission anomaly index reference threshold, and the comparison results are as follows: If the transmission anomaly index is greater than or equal to a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a high-risk transmission anomaly state; If the transmission anomaly index is less than a preset transmission anomaly index reference threshold, the process of uploading the medical information to the cloud after local encryption is classified as a low-risk transmission anomaly state.

8. A method for dynamically encrypting and uploading data on a medical information cloud platform according to claim 7, characterized in that: For the assessed high-risk transmission abnormality status, several transmission abnormality indexes generated under several detection windows in the process of continuously obtaining medical information when it is locally encrypted and uploaded to the cloud are used to establish a data set for comprehensive analysis; The average value and standard deviation of several transmission anomaly indexes in the data set are calculated, and the calculated average value and standard deviation of the transmission anomaly index are compared with the preset transmission anomaly index average value reference threshold and the preset transmission anomaly index standard deviation threshold, respectively. The comparison results are as follows: If the average value of the transmission anomaly index is greater than or equal to the preset transmission anomaly index reference threshold, the high-risk transmission anomaly state is further divided into a continuous state; If the average value of the transmission anomaly index is less than the preset transmission anomaly index reference threshold and the standard deviation of the transmission anomaly index is greater than or equal to the preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further classified as an unstable state; If the transmission anomaly index average value is less than a preset transmission anomaly index reference threshold and the transmission anomaly index standard deviation is less than a preset transmission anomaly index standard deviation reference threshold, the high-risk transmission anomaly state is further divided into a burst state.

Images