A smart medical system based on 5G remote communication

Abstract

The present invention provides a smart medical system based on 5G remote communication, which belongs to the technical field of data processing systems. The system includes: a first acquisition module for acquiring an immediate medical request initiated by a first terminal to a second terminal; an establishment module for establishing a communication channel between the first terminal and the second terminal through a dispatch center in response to the immediate medical request; an encryption module for dynamically encrypting the communication channel in a fragmented manner in combination with the information entropy of the data to be transmitted in the communication channel; a communication module for performing communication tasks regarding immediate medical requests through the encrypted communication channel; a second acquisition module for acquiring the communication channel delay during the communication task; a compensation module for combining a variational algorithm to smoothly compensate for the communication channel delay through a Kalman filter algorithm; and a return module for calling the second acquisition module until the communication task is terminated. This improves the real-time and security of medical communications.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing systems, and specifically relates to a smart medical system based on 5G remote communication. Background Art

[0002] 5G telecom is a communication method that leverages fifth-generation mobile communication technology to achieve high speed, low latency, and large-scale device connectivity. In the healthcare field, 5G can be used for scenarios such as remote surgery, real-time monitoring, and rapid sharing of patient data, significantly improving medical efficiency and coverage. Smart healthcare is a medical service model based on information technology (such as the Internet of Things, artificial intelligence, and big data). It integrates and analyzes medical resources to achieve intelligent and efficient medical services.

[0003] By combining 5G communications, artificial intelligence, and the Internet of Things (IoT), smart healthcare addresses issues such as uneven distribution of medical resources and inefficient chronic disease management. In an aging society with a growing number of chronic disease patients, smart healthcare can provide convenient remote diagnosis and treatment, efficient health monitoring, and intelligent diagnostics, helping to alleviate medical pressures, reduce costs, and enhance the patient experience.

[0004] However, the existing remote smart medical process is easily affected by the network status, and the encryption scheme is also a traditional encryption method with poor anti-interference ability. Communication delays are prone to frequent occurrences, affecting the communication quality and real-time performance of instant communication tasks. In severe cases, it may lead to medical accidents, which restricts the further development of telemedicine. Summary of the Invention

[0005] In order to solve the technical problems in the prior art that the existing remote smart medical process is easily affected by the network status, the encryption scheme is also a traditional encryption method with poor anti-interference ability, and communication delays are prone to frequent occurrence, which affects the communication quality and real-time performance of instant communication tasks, and may seriously lead to medical accidents, thus restricting the further development of telemedicine, the present invention provides a smart medical system based on 5G remote communication.

[0006] The present invention provides a smart medical system based on 5G remote communication, the smart medical system comprising a first terminal, a dispatching center, and a second terminal connected in sequence;

[0007] The smart medical system based on 5G remote communication also includes:

[0008] A first acquisition module is used to acquire an instant medical treatment request initiated by the first terminal to the second terminal;

[0009] an establishing module for establishing a communication channel between the first terminal and the second terminal through the dispatch center in response to the immediate medical treatment request;

[0010] An encryption module, which is used to dynamically encrypt the communication channel in a fragmented manner by combining the information entropy of the data to be transmitted in the communication channel;

[0011] A communication module, configured to communicate about immediate medical treatment requests through an encrypted communication channel;

[0012] The second acquisition module is used to obtain the communication channel delay during the communication task;

[0013] The compensation module is used to smoothly compensate for the communication channel delay by combining the variational algorithm and the Kalman filter algorithm;

[0014] The return module is used to call the second acquisition module until the communication task is terminated.

[0015] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0016] In this invention, remote communication data is encrypted using a sharding approach that incorporates the entropy of the data being transmitted. This allows for dynamic key generation based on data complexity, improving encryption randomness and security. Sharded storage also prevents single-point leaks, enhances attack resistance, and ensures the integrity and privacy of data transmission. During communication, communication channel delays are collected in real time and then smoothed and compensated for using a Kalman filter algorithm in conjunction with a variational algorithm. This compensation is combined with the variational and Kalman filter algorithms, and the target path for delay compensation is optimized using the variational algorithm to ensure smooth and optimal delay variations. The Kalman filter then fuses observed and predicted values to improve dynamic adaptability and accuracy to delay variations. This combination of methods can mitigate significant fluctuations while maintaining the real-time and stability of compensation. By avoiding frequent compensation strategies caused by delay fluctuations, the system adjusts gently even when network delays fluctuate, preventing sudden overallocation of bandwidth to the same communication channel, which could cause disconnection in other communication channels. This approach conserves network resources while ensuring smooth communication flow, maintaining the sustainability and stability of the entire smart healthcare process. Improving the data security of medical communications and the fluency of instant communications, reducing communication latency, and making medical communications with extremely high real-time requirements suitable for complex and changing network scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1This is a structural diagram of a smart medical system based on 5G remote communication provided by the present invention;

[0019] Figure 2 This is a structural diagram of another smart medical system based on 5G remote communication provided by the present invention. DETAILED DESCRIPTION

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific embodiments of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings and other embodiments can be obtained based on these drawings without inventive work.

[0021] To simplify the drawings, only portions relevant to the invention are schematically depicted in each figure; they do not represent the actual structure of the product. Furthermore, to simplify the drawings and facilitate understanding, in some figures, only one component with the same structure or function is schematically depicted or labeled. In this document, "one" not only means "only one" but also "more than one."

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] It should be noted that, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they can refer to fixed connections, removable connections, or integral connections. They can also refer to mechanical connections or electrical connections. They can also refer to direct connections or indirect connections through an intermediary, or to internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in the present invention based on the specific circumstances.

[0024] In addition, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0025] In one embodiment, referring to Figure 1 , shows a schematic diagram of the structure of a smart medical system based on 5G remote communication provided by the present invention. Figure 2 , showing a structural diagram of another smart medical system based on 5G remote communication provided by the present invention.

[0026] The present invention provides a smart medical system based on 5G remote communication, which includes a first terminal, a dispatching center and a second terminal connected in sequence.

[0027] The first and second terminals can be both patient-side devices, doctor-side devices, both patient-side devices, or both doctor-side devices. When both the first and second terminals are patient-side devices, the first terminal collects the patient's health data and shares it with the second terminal through the dispatch center. When the first terminal is a patient-side device and the second terminal is a doctor-side device, the patient initiates a video consultation request via their smartphone (the first terminal), and the doctor receives and provides a diagnosis via their computer (the second terminal). When the first terminal is a doctor-side device and the second terminal is a patient-side device, the doctor proactively contacts the patient or uses remote medical monitoring. When both the first and second terminals are doctor-side devices, doctors collaborate or consult with each other. The dispatch center is the core hub of the system, responsible for resource scheduling, communication channel establishment, security management, and data transfer. This design makes the system highly flexible and adaptable, meeting the needs of various scenarios, including patient-to-patient data sharing, doctor-patient interaction, remote monitoring, and doctor-to-doctor collaboration. Furthermore, the dispatch center centrally manages resources, establishes communication channels, and ensures data security, improving the system's versatility, scalability, and medical service efficiency.

[0028] The smart medical system based on 5G remote communication also includes:

[0029] The first obtaining module 1 is configured to obtain an instant medical treatment request initiated by a first terminal to a second terminal.

[0030] An instant medical request is a real-time medical service request initiated by a first terminal (e.g., a patient's device) to a second terminal (e.g., a doctor's device). This request includes operations such as video consultation, voice consultation, and access to vital sign data. It requires the rapid establishment of a communication channel to meet real-time requirements.

[0031] In one possible implementation, the instant medical request includes a video request, a voice request, and a request for access to patient vital sign monitoring data.

[0032] Establishing module 2 is used to establish a communication channel between the first terminal and the second terminal through the dispatch center in response to the immediate medical treatment request.

[0033] In a possible implementation, the establishment module 2 is specifically configured to:

[0034] When the instant medical treatment request is a video request or a voice request, a communication channel is established through the WebRTC protocol or the RTP protocol.

[0035] When the instant medical request is a request for access to patient vital sign monitoring data, a communication channel is established through the MQTT protocol or the HTTP / 2 protocol.

[0036] It's important to note that the system flexibly selects communication protocols based on the type of immediate medical request: video or voice requests utilize WebRTC or RTP, ensuring low-latency, real-time transmission. Requests for vital sign monitoring data utilize MQTT or HTTP / 2, supporting efficient and lightweight data transmission. This allows for diverse communication tasks and improves system adaptability and performance.

[0037] The encryption module 3 is used to dynamically encrypt the communication channel in a fragmented manner based on the information entropy of the data to be transmitted in the communication channel.

[0038] The data to be transmitted refers to the various medical information that needs to be transmitted over the communication channel, including patient vital sign monitoring data, diagnostic records, audio and video streams, and so on. Information entropy is a measure of data complexity and randomness; larger values indicate more complex data and higher randomness. Sharding involves dividing the data to be transmitted into multiple small fragments, each of which is independently encrypted and stored. By combining information entropy with fragmented encryption of the data to be transmitted, encryption keys can be dynamically generated, and encryption strength can be adjusted based on data complexity, enhancing data security and anti-attack capabilities. Sharded storage prevents single points of failure. Even if partial keys or data are leaked, the complete information cannot be restored, thereby improving the privacy of medical communications and system reliability.

[0039] In a possible implementation, the encryption module 3 is specifically configured to:

[0040] Get the data to be transmitted.

[0041] Calculate the information entropy value of the data to be transmitted:

[0042]

[0043] in, Represents the information entropy value of the data D to be transmitted, represents the probability of occurrence of the i-th symbol in the data to be transmitted, , n represents the total number of symbol types in the data to be transmitted, and log represents the logarithmic function;

[0044] Generate dynamic secret key based on information entropy value:

[0045]

[0046] in, represents a random seed, Represents a dynamic key, Represents exclusive OR operation;

[0047] Shard the dynamic key and use it in a distributed hash table for distributed storage:

[0048]

[0049] in, represents the jth dynamic key shard, represents the jth sharding parameter, N represents the upper limit of the sharding parameter, express The hash value of express Distributed hash table node, mod represents the modulo operation;

[0050] Each shard is stored separately, and the complete key can only be restored after reassembly, preventing single point failure or key leakage.

[0051] Shard the transmitted data based on the number of shards of the dynamic key:

[0052]

[0053] in, Indicates the i-th data fragment to be transmitted, , m represents the total number of data fragments to be transmitted, Indicates the total length of data to be transmitted. express Total length;

[0054] The dynamic key obtained by sharding is used to encrypt the data to be transmitted obtained by each shard:

[0055]

[0056] in, Indicates based on The encryption algorithm, Express The i-th data fragment obtained after encryption;

[0057] Among them, the encryption algorithm is based on dynamic key sharding Each key shard is used to encrypt the corresponding data shard. Even if a key shard is leaked, the complete data cannot be decrypted. The encryption algorithm can be AES (Advanced Encryption Standard), ChaCha20, or SM4, which complies with national encryption standards.

[0058] The data to be transmitted is transmitted in an encrypted manner to complete the encryption of the communication channel.

[0059] It's important to note that keys are dynamically generated through information entropy calculations, adjusting encryption strength based on data complexity. Keys are stored in shards and managed in a distributed hash table to prevent single points of failure and leakage. Sharded encryption encrypts each fragment of transmitted data individually, making it impossible to restore the complete data even if a portion of the key is compromised. This further enhances transmission security and attack resistance, ensuring encryption performance and standard compliance, and achieving comprehensive encryption protection for communication channels.

[0060] In a possible implementation, the encryption module 3 is further configured to:

[0061] When a receiving end receives the encrypted data to be transmitted, each dynamic key fragment is reassembled to obtain a dynamic key, wherein the receiving end includes a first terminal and a second terminal.

[0062] The encrypted data to be transmitted is decrypted using the reconstructed dynamic key, and the data to be transmitted is restored at the receiving end.

[0063] It should be noted that at the receiving end, the encryption module reassembles the dynamic key fragments to restore the complete key, ensuring the security and reliability of key recovery. The reassembled key is used to decrypt the encrypted data and successfully restore the transmitted data, thus achieving end-to-end data protection. Even if some fragments are leaked, the data cannot be decrypted, further improving communication security and privacy.

[0064] The communication module 4 is used to perform communication tasks regarding immediate medical treatment requests through an encrypted communication channel.

[0065] It is understandable that the task of executing instant medical requests through encrypted communication channels ensures the security and integrity of patient vital data, audio and video streams and other information during transmission, while meeting real-time requirements and improving the efficiency and privacy protection of telemedicine services.

[0066] The second acquisition module 5 is used to acquire the communication channel delay during the communication task.

[0067] Communication channel latency refers to the time interval required for data to be transmitted from one terminal (e.g., the patient) to another (e.g., the doctor). Latency is determined by a variety of factors, including network transmission speed, communication protocol efficiency, and data encryption and decryption time. By capturing communication channel latency in real time, the system can dynamically monitor network performance, ensuring the real-time transmission of medical data and audio and video streams. This provides a foundation for latency compensation and resource optimization, effectively improving the stability and responsiveness of telemedicine services.

[0068] The compensation module 6 is used to combine the variational algorithm and the Kalman filter algorithm to smoothly compensate for the communication channel delay.

[0069] Among them, the variational algorithm is a mathematical optimization method used to find the optimal path or value of a function. In communication delay compensation, the variational algorithm imposes smoothing constraints on the delay prediction value to avoid drastic fluctuations and ensure a more moderate and stable compensation strategy. The Kalman filter is a recursive estimation algorithm that combines predicted and observed values to dynamically adjust the state estimate. In delay compensation, the Kalman filter is used to correct the delay prediction value and balance the credibility of real-time observation data and historical prediction models. By combining the variational algorithm and the Kalman filter algorithm to smoothly compensate for communication channel delay, the delay prediction path can be optimized, unnecessary adjustments caused by sudden fluctuations can be reduced, and dynamic adaptability to delay changes can be enhanced, ensuring communication stability and efficient resource utilization.

[0070] It's important to note that network latency predictions can sometimes fluctuate dramatically, such as predicting a very low latency one second and then a very high latency the next. These sudden changes (for example, from 10ms to 50ms and then back to 10ms) can cause the system to frequently adjust, leading to instability. Unstable predictions can easily trigger unnecessary compensation. Variational processing smooths out predicted latency values, avoiding drastic fluctuations while maintaining accurate compensation.

[0071] By using the variational method and adding "smooth control", the system can be more gentle when predicting delay changes, avoiding sudden and drastic fluctuations. The system will give priority to the smoother predicted path, and even if the delay changes, it will gradually adjust, like slowly braking. Through this smoothing process, even if the network delay fluctuates, the system will adjust gently, and will not suddenly disconnect or waste network resources (that is, if the network bandwidth resources are limited, and the predicted delay value fluctuates too much: the system may occupy too many resources in a short period of time, resulting in a lack of bandwidth for other tasks (such as video streaming, audio streaming), triggering congestion management. In extreme cases, the system may be judged as an unstable connection and interrupted. For example, VoIP services or streaming media will actively disconnect unstable connections), increasing the stability and fluency of remote communications.

[0072] In a possible implementation, the compensation module 6 is specifically configured to:

[0073] S601: Determine a constraint function of a predicted value of a communication channel delay by using a variational method.

[0074] In a possible implementation, the constraint function is specifically:

[0075]

[0076] in, represents the constraint function value, represents the predicted value at time k, express The true value of represents the initial moment of integration, Indicates the end time of integration, represents the regularization parameter that controls the importance of smoothness, represents the partial derivative, represents the Lagrangian of the constraint function.

[0077] Specifically, if the observed value contains more random fluctuations or noise, take the larger , suppressing the drastic changes in the predicted value. For example: in a highly volatile network environment, the system needs to maintain a stable delay prediction. ≈0.5 or higher. If the observed value is relatively stable, the system can rely more on the prediction model and choose a smaller , to improve the sensitivity of the prediction. For example: in an environment where the delay changes relatively slowly, set =0.05.

[0078] In constrained optimization problems, the Lagrangian combines the objective function and constraints to find a solution to the optimization problem. By taking the derivative of the Lagrangian, we can find the point where the objective function reaches its extreme value under the constraints. In the constraint function of delay prediction, the Lagrangian represents the balance between the error term and smoothness of the delay prediction. By constructing a constraint function, the communication delay prediction value is optimized to balance the prediction accuracy and smoothness. Regularization parameter Importance of adjusting smooth control: When the observed data fluctuates greatly, increase Suppresses drastic changes in the predicted value. When the delay is stable, reduce Improve prediction sensitivity so that it can dynamically adapt to different network environments and ensure the stability and accuracy of predictions.

[0079] S602: With the goal of minimizing the constraint function value, determine the predicted value of the communication channel delay through the Kalman filter algorithm.

[0080] In a possible implementation, the predicted value of the communication channel delay is calculated as follows:

[0081]

[0082] Among them, min means taking the minimum value, represents the predicted value at time k+1 based on the state at time k, and A represents the state transition matrix of how the current state affects the state at the next moment. Represents The relevant k-time control input is the bandwidth adjustment amount, and B represents the control input A matrix of control inputs that influence the strength of the predicted values.

[0083] It should be noted that the delay prediction value is dynamically calculated through the state transfer matrix A and the control input matrix B, and the delay prediction result is optimized by combining the impact of the current state on the next moment and the control input (such as bandwidth adjustment). This function is used to suppress drastic latency fluctuations and ensure the smoothness of the predicted path. By minimizing the constraint function value, the system balances predicted and actual latency variations while ensuring accuracy, improving the real-time and stability of communications.

[0084] S603: Introduce network noise to correct the Kalman gain used to balance the prediction value weight and the observation value weight, and the error covariance used to evaluate the credibility of the prediction value, where the network noise includes process noise introduced due to the inability to describe the real noise and measurement noise caused by noise equipment errors.

[0085] In one possible implementation, the Kalman gain for balancing the predicted value weight and the observed value weight and the error covariance for evaluating the credibility of the predicted value are specifically:

[0086]

[0087] in, represents the Kalman gain at time k, that is, the corrected Kalman gain. Represents the observation value at time k The observation matrix that maps the relationship between the observation matrix and the true value, the subscript T represents the transpose, and Q represents the process noise including the k-time The process noise covariance matrix, R represents the measurement noise at time k The measurement noise covariance matrix, represents the stability factor, Represents the covariance of the error at time k The associated forecast error covariance represents the uncertainty of the forecast value at time k+1, represents the corrected error covariance, I represents the unit matrix, represents the initial process noise, represents the initial measurement noise, Represents the dynamic adjustment factor of the weight at time k, represents the process noise at time k, represents the measurement noise, The weight factor that controls the impact of noise.

[0088] Optionally, the stability factor takes a value of 0 to 0.2 under stable network delay, a value of 0.5 to 0.8 under sudden traffic fluctuations, and a value of 0.8 to 1 under long-term large traffic fluctuations.

[0089] Specifically, the error covariance, used to assess the confidence of predicted values, is used to adjust the bias toward predicted or observed values. If the observed value is very close to the predicted value, the system becomes more confident, and future trust in the prediction model increases (the error covariance decreases). If the observed value differs significantly from the predicted value, the system becomes less confident and relies more on the observed value for correction.

[0090] It should be noted that the Kalman gain dynamically balances the weights of predicted and observed values, combining them with the error covariance to dynamically assess the confidence of the predicted value. The error covariance adjusts based on the proximity of the observed and predicted values. If the two are highly consistent, the system increases its confidence in the predicted value and reduces the need for corrections. If the discrepancy is large, the prediction is more reliant on the observed value. The covariance matrix of process noise and measurement noise dynamically adjusts the weights to adapt to different network environments, ensuring that the system maintains high prediction efficiency under stable conditions while also responding quickly under fluctuating conditions, improving communication stability and delay compensation accuracy.

[0091] S604: Correct the predicted value of the communication channel delay according to the corrected Kalman gain and error covariance:

[0092]

[0093] in, represents the predicted value at time k+1, i.e. the predicted value of the corrected communication channel delay. express k Time observation value The observation matrix that maps the relationship between and the true value, represents the predicted value at time k+1 based on the state at time k, represents the Kalman gain at time k, that is, the corrected Kalman gain. represents the observation value at time k.

[0094] S605: Adjust the bandwidth adjustment amount according to the corrected prediction value to compensate for the communication channel delay.

[0095] Specifically, the compensation module constructs a smooth constraint function for the delay prediction value through a variational method to ensure a more stable prediction path. The Kalman filter algorithm is used to minimize the constraint function value and dynamically balance the weights of the predicted and observed values. A network noise correction mechanism is introduced to adjust the Kalman gain and error covariance based on process noise and measurement noise. The delay prediction value is optimized based on the modified Kalman gain. Based on the optimized prediction results, bandwidth allocation is dynamically adjusted to achieve precise compensation for communication channel delays, ensuring network stability and efficient resource utilization.

[0096] It should be noted that if there are multiple immediate medical requests at the same time, that is, multiple communication channels, the bandwidth adjustment amount can be balanced in the following way:

[0097]

[0098] in, represents the delay prediction value of the i-th communication channel at time k, represents the occupied bandwidth of the i-th communication channel, Indicates the total available bandwidth, N indicates the total number of current communication channels, State the constraints.

[0099] It is understandable that in the case of multiple concurrent instant medical requests, a dynamic balanced bandwidth allocation mechanism is used to adjust the bandwidth occupancy ratio according to the delay prediction value of each communication channel, while meeting the total available bandwidth limit, to avoid a channel occupying too many resources and affecting other channels, ensure the stability and fairness of all communication tasks, and improve the overall resource utilization efficiency and service quality of the system.

[0100] Return module 7 is used to call the second acquisition module until the communication task is terminated.

[0101] In one possible implementation, the system further includes:

[0102] The early warning module 8 is configured to issue an early warning when the duration of the communication channel delay is greater than a preset duration.

[0103] It's important to note that the early warning module monitors communication channel delays in real time. When the delay duration exceeds a preset threshold, the system immediately triggers an alert. This design helps promptly identify network anomalies or performance issues, alerting relevant personnel to take emergency measures to prevent data transmission failures or medical service interruptions caused by excessive delays, further ensuring the stability and service quality of smart healthcare.

[0104] In actual application, the dispatch center connects the first and second terminals, enabling flexible patient data sharing, remote diagnosis and treatment, and physician collaboration. Dynamic encryption, combined with information entropy, enhances data transmission security, while the communication module ensures the real-time and integrity of immediate medical tasks. Real-time acquisition of communication channel delays, combined with a variational algorithm and Kalman filter for smoothing compensation, avoids resource waste or connection interruptions caused by drastic delay fluctuations. This improves the stability, reliability, and service efficiency of medical communications, meeting the needs of telemedicine in multiple scenarios.

[0105] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0106] In this invention, remote communication data is encrypted using a sharding approach that incorporates the entropy of the data being transmitted. This allows for dynamic key generation based on data complexity, improving encryption randomness and security. Sharded storage also prevents single-point leaks, enhances attack resistance, and ensures the integrity and privacy of data transmission. During communication, communication channel delays are collected in real time and then smoothed and compensated for using a Kalman filter algorithm in conjunction with a variational algorithm. The variational and Kalman filter algorithms are combined to compensate for the communication channel delay, optimizing the target path for delay compensation using the variational algorithm to ensure smooth and optimal delay variations. The Kalman filter then fuses observed and predicted values to improve dynamic adaptability and accuracy to delay variations. This combination of methods can mitigate significant fluctuations while maintaining the real-time and stability of compensation. By avoiding frequent compensation strategies caused by delay fluctuations, the system adjusts gently even when network delays fluctuate, preventing sudden overallocation of bandwidth to the same communication channel, which could cause disconnection in other communication channels. This approach conserves network resources while ensuring smooth communication flow, maintaining the sustainability and stability of the entire smart healthcare process. Improving the data security of medical communications and the fluency of instant communications, reducing communication latency, and making medical communications with extremely high real-time requirements suitable for complex and changing network scenarios.

[0107] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above embodiments merely illustrate several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A smart medical system based on 5G remote communication, characterized in that: The smart medical system includes a first terminal, a dispatching center, and a second terminal connected in sequence; the system also includes: A first obtaining module is configured to obtain an immediate medical treatment request initiated by the first terminal to the second terminal; an establishing module, configured to establish, in response to the immediate medical treatment request, a communication channel between the first terminal and the second terminal through the dispatch center; An encryption module, configured to dynamically encrypt the communication channel in a fragmented manner based on the information entropy of the data to be transmitted in the communication channel; a communication module, configured to communicate the request for immediate medical treatment via an encrypted communication channel; A second acquisition module is used to acquire the communication channel delay during the process of performing the communication task; A compensation module, configured to smoothly compensate for the communication channel delay by combining a variational algorithm with a Kalman filter algorithm; A return module, configured to call the second acquisition module until the communication task is terminated; The encryption module is specifically used for: Acquiring the data to be transmitted; Calculate the information entropy value of the data to be transmitted: ; in, Indicates data to be transmitted D The information entropy value of Indicates the first i The probability of a symbol appearing, , n represents the total number of symbol types in the data to be transmitted, and log represents the logarithmic function; Generate a dynamic key based on the information entropy value: ; in, represents a random seed, Represents a dynamic key, Represents exclusive OR operation; The dynamic key is sharded and distributedly stored in a distributed hash table: ; in, Indicates the j Dynamic key shards, Indicates the j-th shard parameter, N Indicates the upper limit of the fragmentation parameter. express The hash value of express Distributed hash table node, mod represents the modulo operation; The data to be transmitted is fragmented based on the number of fragments of the dynamic key: ; in, Indicates the i-th data fragment to be transmitted, , m Indicates the total number of data fragments to be transmitted. Indicates the total length of data to be transmitted. express Total length; The dynamic key obtained by sharding is used to encrypt the data to be transmitted obtained by each shard: ; in, Indicates based on The encryption algorithm, Express The encrypted i data shards; Transmitting the data to be transmitted in an encrypted manner to complete encryption of the communication channel; Wherein, the compensation module is specifically used for: S601: Determine a constraint function of a predicted value of the communication channel delay by a variational method; S602: Determine a predicted value of the communication channel delay using a Kalman filter algorithm with the goal of minimizing the constraint function value; S603: Introducing network noise to correct the Kalman gain used to balance the predicted value weight and the observed value weight, and the error covariance used to evaluate the credibility of the predicted value, wherein the network noise includes process noise introduced due to the inability to describe the real noise and measurement noise caused by noise equipment errors; S604: Correct the predicted value of the communication channel delay according to the corrected Kalman gain and error covariance: ; in, express k The predicted value at time +1 is the predicted value of the corrected communication channel delay. express k Time observation value The observation matrix that maps the relationship between and the true value, Indicates based on k Time status k +1 moment prediction value, express k The moment Kalman gain is the corrected Kalman gain, express k Observation value at a moment; S605: Adjust the bandwidth adjustment amount according to the corrected prediction value to compensate for the communication channel delay.

2. The smart medical system based on 5G remote communication according to claim 1 is characterized in that: The instant medical requests include video requests, voice requests, and requests for access to patient vital sign monitoring data.

3. The smart medical system based on 5G remote communication according to claim 2 is characterized in that: The establishment module is specifically used for: When the instant medical treatment request is a video request or a voice request, establishing the communication channel through the WebRTC protocol or the RTP protocol; In the case where the instant medical treatment request is a request for access to patient vital sign monitoring data, the communication channel is established through the MQTT protocol or the HTTP / 2 protocol.

4. The smart medical system based on 5G remote communication according to claim 1, characterized in that: The encryption module is also used for: When a receiving end receives the encrypted data to be transmitted, reassembling the dynamic key fragments to obtain a dynamic key, wherein the receiving end includes the first terminal and the second terminal; The encrypted data to be transmitted is decrypted using the reorganized dynamic key, and the data to be transmitted is restored at the receiving end.

5. The smart medical system based on 5G remote communication according to claim 1 is characterized in that: The constraint function is specifically: ; in, represents the constraint function value, express k The predicted value at the moment, express The true value of represents the initial moment of integration, Indicates the end time of integration, represents the regularization parameter that controls the importance of smoothness, represents the partial derivative, represents the Lagrangian of the constraint function.

6. The smart medical system based on 5G remote communication according to claim 5, characterized in that: The calculation method of the predicted value of the communication channel delay is specifically as follows: ; Among them, min means taking the minimum value, Indicates based on k Time status k +1 moment prediction value, A The state transition matrix that represents how the current state affects the state at the next moment, Represents Related k The moment control input is the bandwidth adjustment amount, B Indicates control input A matrix of control inputs that influence the strength of the predicted values.

7. The smart medical system based on 5G remote communication according to claim 6, characterized in that: The Kalman gain for balancing the predicted value weight and the observed value weight and the error covariance for evaluating the credibility of the predicted value are specifically: ; in, express k The moment Kalman gain is the corrected Kalman gain, express k Time observation value The observation matrix of the mapping relationship between the true value and the subscript T represents transpose, Q Indicates including k Time process noise The process noise covariance matrix, R Indicates including k Measuring noise at all times The measurement noise covariance matrix, represents the stability factor, Represents k Time error covariance Relevant representatives k The forecast error covariance of the uncertainty of the forecast value at time +1, represents the corrected error covariance, I represents the identity matrix, represents the initial process noise, represents the initial measurement noise, express k The dynamic adjustment factor of the weight at each moment, express k Time process noise, represents the measurement noise, The weight factor that controls the impact of noise.

8. The smart medical system based on 5G remote communication according to claim 1, characterized in that: Also includes: The early warning module is used to issue an early warning when the duration of the communication channel delay is greater than a preset duration.

Images