Method, device and equipment for remote collection and processing of medical information based on 5G scenario

Abstract

The present invention relates to the field of 5G scenarios, and discloses a method, device, and equipment for remote collection and processing of medical information based on 5G scenarios, which are used to combine 5G network slicing technology, edge computing, quantum key distribution, and artificial intelligence algorithms and other advanced technical means to improve the efficiency, security, and intelligence level of remote medical information collection and processing. The method for remote collection and processing of medical information based on 5G scenarios includes dynamically allocating network resources using 5G network slicing technology to build a secure and isolated transmission channel; deploying task modules at the edge of the 5G network to process and analyze the collected medical information; enhancing medical information through a preset generative adversarial network; using quantum key distribution technology for encryption protection, receiving and storing encrypted data, and analyzing after decryption to obtain medical collection information analysis results. The present invention also covers aspects such as data visualization output, remote medical consultation, and intelligent medical equipment integration.

Description

Technical Field

[0001] The present invention relates to the field of 5G scenarios, and in particular to a method, device, and equipment for remote collection and processing of medical information based on 5G scenarios. Background Art

[0002] With the advancement of medical technology and people's increasing attention to health management, telemedicine information collection and processing technology plays an increasingly important role in the modern medical system. Especially driven by 5G network technology, high-speed, low-latency data transmission provides unprecedented possibilities for telemedicine services. However, in practical applications, there are still a series of technical challenges and security issues that need to be addressed.

[0003] Traditional medical information collection methods are often limited by network transmission speed and data processing capabilities, resulting in insufficient real-time and accuracy. In addition, with the continuous growth of medical data, how to effectively store, manage and analyze this data has become an urgent problem to be solved. Especially when it comes to patient privacy and data security, traditional information collection and processing methods often cannot provide sufficient protection.

[0004] The application of 5G network slicing technology provides a new idea for medical information collection. Through the flexible configuration of network slicing, network resources can be dynamically allocated according to the urgency and importance of medical data, thereby ensuring the real-time transmission of critical data. At the same time, the development of edge computing technology also makes it possible to perform efficient data processing at the source of data.

[0005] However, relying solely on 5G networks and edge computing technology is not enough to solve all problems. In particular, more advanced technical means need to be introduced in terms of data security and privacy protection.

[0006] Although the existing telemedicine information collection and processing technology has made some progress, it still has the following shortcomings:

[0007] Insufficient data transmission efficiency and security: Traditional network technology is difficult to meet the needs of large-scale, real-time medical data transmission, and there is a risk of interception or tampering during the data transmission process.

[0008] Limited data processing capabilities: Traditional data center processing models are often unable to cope with massive amounts of medical data, resulting in low data processing efficiency.

[0009] Insufficient data privacy protection: During the collection, transmission and processing of medical information, patients' privacy data is vulnerable to leakage and abuse.

[0010] The level of intelligence in data collection and analysis is not high: Existing medical information collection systems often lack intelligent data collection strategies and analysis methods, making it difficult to extract valuable information from massive amounts of data.

[0011] In summary, in order to overcome these shortcomings, this study proposed a method, device, and equipment for remote collection and processing of medical information based on 5G scenarios. Summary of the invention

[0012] The present invention provides a method, device, and equipment for remote collection and processing of medical information based on a 5G scenario, which is used to combine 5G network slicing technology, edge computing, quantum key distribution, artificial intelligence algorithms, and other advanced technical means to improve the efficiency, security, and intelligence level of remote medical information collection and processing.

[0013] The first aspect of the present invention provides a method for remote collection and processing of medical information based on a 5G scenario, and the method for remote collection and processing of medical information based on a 5G scenario includes: obtaining medical information collection data, setting a slice manager according to the 5G network slicing technology, the slice manager indicating that it is configured to dynamically allocate network resources, adjusting the priority and bandwidth allocation of the slice according to the urgency and importance of the medical data, and constructing a transmission isolation security channel for the medical information collection data; deploying a task module at the edge of the 5G network, and obtaining a medical collection information output group according to the medical information collection data combined with the task module; enhancing the medical information collection output group according to a preset generative adversarial network to obtain a medical collection information expansion group; encrypting and protecting the medical collection information expansion group according to quantum key distribution, and encrypting and transmitting the medical collection information expansion group by real-time updating and exchanging keys to obtain a medical collection information encryption group; receiving and storing the encrypted medical collection information encryption group, decrypting and restoring the original medical collection information expansion group, and obtaining a medical collection information analysis result according to the medical collection information expansion group.

[0014] Optionally, in the first implementation manner of the first aspect of the present invention, for obtaining the medical information collection data, a slice manager is set according to the 5G network slicing technology. The slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of the slice according to the urgency and importance of the medical data, and construct a transmission isolation security channel for the medical information collection data, including: receiving the original medical information collection data through an intelligent data collection interface, and performing preprocessing on the accessed medical information collection data, including format conversion, data cleaning, and standardization; performing compressive sensing processing on the preprocessed medical information collection data. Set the vector of the preprocessed medical information collection data as \(x\in\mathbb{R}^N\), where \(N\) is the dimension of the data, and the measurement matrix in compressive sensing is \(\Phi\in\mathbb{R}^{M\times N}\), which is used to project the data from a high-dimensional space to a low-dimensional space, where \(M < N\), and the measurement value \(y\in\mathbb{R}^M\) is obtained through the following formula: \(y = \Phi x\);

[0015] Set \(\Psi\) as the sparse basis matrix, then the signal \(x\) is expressed as:

[0016] \(x=\Psi\theta\);

[0017] where \(\theta\) is the sparse representation of the signal in the \((\Psi)\) domain;

[0018] It is transformed into solving:

[0019] \(\min_{\theta}||\theta||_1\quad\text{s.t.}\quad||y - \Phi\Psi\theta||_2\leq\epsilon\)

[0020] Among them, ||\theta||_1 is the L_1 norm of \theta, which is used to promote sparsity; ||y-\Phi\Psi\theta||_2 is the (L_2) norm of the measurement error; \epsilon is a small positive number, which indicates the allowable error range; the downscaling information collection data is obtained; the data evaluation model is used to evaluate the urgency and importance of the downscaling information collection data, and according to the evaluation results, the data is classified into different priorities, including emergency, high priority, medium priority and low priority, to obtain the priority classification result; the slice manager dynamically configures the network slice according to the priority classification result of the data and the resources and status information of the current 5G network, and allocates corresponding network slices to each priority data, ensuring that emergency and high priority data obtain more network resources and obtain a transmission isolation safety channel; the medical information collection data is transmitted through the configured transmission isolation safety channel, and the slice manager monitors the network status and data transmission in real time, and dynamically adjusts the slice resource allocation as needed.

[0021] Optionally, in a second implementation method of the first aspect of the present invention, the task module is deployed at the edge of the 5G network, and a medical information collection output group is obtained based on the medical information collection data combined with the task module, including: selecting edge computing nodes for deployment according to the geographical location of the medical institution, 5G network coverage and data processing requirements; defining the functions of the task module, including data preprocessing, feature extraction, and data analysis; and / or providing an artificial intelligence algorithm in the task module, including deep learning and machine learning; preprocessing the received medical information collection data, including denoising and normalization; using the task module to extract features and analyze the preprocessed data to obtain second medical information collection data and third medical information collection data; organizing the second medical information collection data and the third medical information collection data to obtain a medical information output group.

[0022] Optionally, in a third implementation method of the first aspect of the present invention, the medical information collection output group is enhanced according to a preset generative adversarial network to obtain an extended group of medical information, including: presetting a generative adversarial network, including a conditional generative adversarial network (cGAN), a cyclic generative adversarial network (CycleGAN), and a style transfer GAN; training the generative adversarial network to generate data similar to real medical information to obtain a trained generative adversarial network; processing the medical information collection output group and converting it into a format corresponding to the generative adversarial network, which includes images and sequence data; using the processed medical information collection output group as input data and inputting it into the trained generative adversarial network; and / or adding differential privacy in the process of data enhancement using the generative adversarial network to ensure that the generated extended data does not leak the patient's sensitive information; and / or inputting multiple modal medical information collection output groups, including images, medical record texts, and physiological signals, into the generative adversarial network at the same time to generate multimodal extended data; obtaining an extended group of medical information.

[0023] Optionally, in a fourth implementation manner of the first aspect of the present invention, the medical collection information extension group is encrypted and protected based on quantum key distribution, and the medical collection information extension group is encrypted and transmitted by real-time updating and exchanging keys to obtain the medical collection information encryption group, including: establishing a quantum communication link, deploying quantum communication equipment, the quantum communication equipment includes a quantum key distributor and a quantum receiver; using quantum key distribution technology to generate quantum keys between the communicating parties, and updating and exchanging keys in real time through the quantum communication link to ensure the freshness and security of the keys; and / or based on the edge computing capability of the 5G network, part of the computing tasks of the quantum key distribution process are offloaded to the edge nodes to reduce the burden on the core network; using a quantum-safe encryption algorithm, the encryption algorithm includes an AES encryption algorithm based on a quantum key, and the encryption formula is expressed as:

[0024] C_i=E_{K_i}(P_i);

[0025] Where: (C_i) represents the ciphertext of the (i)th data group; (E_{K_i}) represents the encryption algorithm using the (i)th round key (K_i); (P_i) represents the (i)th plaintext data group; in the process of quantum key distribution, the BB84 or B92 protocol is used to generate the initial key, and the key generation process is:

[0026] K = QKD(A,B);

[0027] Among them: (K) is the key generated by quantum key distribution; (QKD) represents the quantum key distribution process; (A) and (B) represent the two communicating parties respectively; the original medical collection information expansion group is obtained from the medical system and divided into data groups (P_i); the initial key (K) is generated between the two communicating parties through the quantum key distribution process; the round key (K_i) required for multi-round encryption is generated from the initial key (K) using the key expansion algorithm; each data group (P_i) is encrypted using the encryption algorithm (E_{K_i}) and the corresponding round key (K_i) to obtain the ciphertext (C_i), and the medical collection information encryption group is formed based on the ciphertext (C_i).

[0028] Optionally, in a fifth implementation of the first aspect of the present invention, the receiving and storing of the encrypted medical collection information encryption group, decrypting and restoring the original medical collection information extension group, and obtaining the medical collection information analysis result according to the medical collection information extension group include: receiving the encrypted medical collection information encryption group through the 5G network, performing integrity verification on the received medical collection information encryption group, setting the data of the received medical collection information encryption group to (D), and its corresponding hash value to (H(D)), the sender will first calculate the hash value (H_{original}(D)) before sending the data and send it together with the data, and the integrity verification formula is:

[0029] [\text{Verification results}=\begin{cases}

[0030] \text{Pass},&\text{if}H(D)=H_{original}(D)\

[0031] \text{Not passed},&\text{otherwise}

[0032] \end{cases}]

[0033] Where, (D): received encrypted group data; (H(D)): hash value of received data calculated by the server; (H_{original}(D)): original hash value provided by the sender;

[0034] Ensure that the data is not tampered with during transmission. After verification, the encrypted medical information collection group is securely stored in the database of the server; when data processing is required, retrieve the corresponding encrypted medical information collection group from the database, use the private key corresponding to the encryption stage to decrypt the encrypted medical information collection group, and restore the original extended medical information group; pre-process the extended medical information group, use machine learning or deep learning algorithms to extract key features from the pre-processed data, and analyze the medical information based on the extracted features, including disease prediction and health status assessment, to obtain the analysis results of the medical information; and / or use smart contract technology to automatically trigger the preset data verification and analysis smart contract after the encrypted medical information collection group is successfully received and decrypted. The contract will automatically perform preliminary data quality assessment, outlier detection and key indicator extraction on the decrypted extended medical information group, and generate the analysis results of the medical information; based on the analysis results of the medical information, the smart contract automatically adjusts the subsequent data collection strategy or triggers the alarm mechanism.

[0035] Optionally, in a sixth implementation manner of the first aspect of the present invention, it also includes: outputting the analysis results of the medical information collection in the form of a visual report or data interface; and / or developing a data visualization platform to display the analysis results of the medical information collection in the form of a chart to medical personnel and patients, providing interactive functions, allowing medical personnel to mark, discuss and share on the platform; and / or based on the high bandwidth and low latency characteristics of the 5G network, realizing remote medical consultation and services, and patients communicate with experts in real time through video calls or online chats to obtain professional advice and treatment plans; and / or integrating smart medical devices with the database of the server, and the smart medical devices collect the patient's health data in real time, and automatically upload it to the database of the server for analysis, so as to provide patients with more comprehensive health management services.

[0036] The second aspect of the present invention provides a medical information remote collection and processing device based on a 5G scenario, and the medical information remote collection and processing device based on the 5G scenario includes: an acquisition module, which is used to acquire medical information collection data, set a slice manager according to the 5G network slicing technology, and the slice manager indicates that it is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of the slice according to the urgency and importance of the medical data, and build a transmission isolation and security channel for the medical information collection data; a task module, which is used to deploy the task module at the edge of the 5G network, and obtain a medical collection information output group based on the medical information collection data and the task module; an enhancement module, which is used to enhance the medical information collection output group according to a preset generative adversarial network to obtain a medical collection information expansion group; an encryption module, which is used to encrypt and protect the medical collection information expansion group according to quantum key distribution, and encrypt and transmit the medical collection information expansion group by real-time updating and exchanging keys to obtain a medical collection information encryption group; a distribution module, which is used to receive and store the encrypted medical collection information encryption group, decrypt and restore the original medical collection information expansion group, and obtain a medical collection information analysis result according to the medical collection information expansion group.

[0037] The third aspect of the present invention provides a medical information remote collection and processing device based on a 5G scenario, comprising: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory so that the medical information remote collection and processing device based on the 5G scenario executes the above-mentioned medical information remote collection and processing method based on the 5G scenario.

[0038] The fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the above-mentioned method for remote collection and processing of medical information based on the 5G scenario.

[0039] The technical solution provided by the present invention integrates a number of advanced technologies such as 5G network slicing technology, edge computing, generative adversarial networks (GANs), quantum key distribution, and smart contracts. The overall process includes: first, using 5G network slicing technology to dynamically allocate network resources, adjusting slice priority and bandwidth according to the urgency and importance of the data, so as to build a secure and isolated transmission channel; then, deploying task modules at the edge of the 5G network to process and analyze the collected medical information; then, enhancing the medical information through a preset generative adversarial network; then, using quantum key distribution technology to encrypt and protect the enhanced information to ensure safe data transmission; finally, receiving and storing the encrypted data, decrypting and analyzing it, and obtaining the analysis results of the medical collection information. In addition, the present invention also covers aspects such as data visualization output, remote medical consultation, and intelligent medical equipment integration.

[0040] Beneficial effects and benefits:

[0041] Efficiency and real-time performance: 5G network slicing technology can dynamically allocate network resources to ensure that urgent and high-priority medical data can be transmitted in real time and quickly, greatly improving the efficiency of medical information collection and processing.

[0042] Security and privacy protection: Quantum key distribution technology is used to encrypt medical information to ensure the security of data transmission. At the same time, differential privacy is added when using generative adversarial networks for data enhancement to effectively prevent the leakage of sensitive patient information.

[0043] Data enhancement and analysis accuracy: By enhancing medical information through generative adversarial networks, we can expand the data set and improve the accuracy of subsequent data analysis. Combined with machine learning and deep learning algorithms, we can extract key features from large amounts of data and provide strong support for medical decision-making.

[0044] Edge computing capabilities: Deploying task modules at the edge of the 5G network can reduce data transmission delays, increase processing speed, and reduce the burden on the core network.

[0045] Intelligence and automation: Using smart contract technology, the data verification and analysis process can be automatically triggered after the data is received and decrypted, realizing the intelligence and automation of the process and improving work efficiency.

[0046] Visualization and interactivity: Through the data visualization platform, medical personnel can intuitively view and analyze the results of medical information collection analysis, while providing interactive functions to enhance communication and collaboration among medical teams.

[0047] Telemedicine services: Relying on the high bandwidth and low latency characteristics of 5G networks, the present invention can realize telemedicine consultation and services, allowing patients to obtain professional medical advice and treatment plans more conveniently.

[0048] In summary, the present invention not only improves the efficiency, security and accuracy of medical information collection and processing, but also provides strong technical support for telemedicine services, data visualization and intelligent medical equipment integration, which helps to promote the digital transformation and upgrading of the medical industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of an embodiment of a method for remotely collecting and processing medical information based on a 5G scenario in an embodiment of the present invention;

[0050] Figure 2 It is a schematic diagram of another embodiment of the method for remote collection and processing of medical information based on a 5G scenario in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of an embodiment of a medical information remote collection and processing device based on a 5G scenario in an embodiment of the present invention;

[0052] Figure 4 This is a schematic diagram of an embodiment of a medical information remote collection and processing device based on a 5G scenario in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The embodiments of the present invention provide a method, device, and equipment for remote collection and processing of medical information based on a 5G scenario, which is used to combine 5G network slicing technology, edge computing, quantum key distribution, and artificial intelligence algorithms and other advanced technical means to improve the efficiency, security, and intelligence level of remote medical information collection and processing. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0054] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of a method for remote collection and processing of medical information based on a 5G scenario in an embodiment of the present invention includes:

[0055] 101. Obtain medical information collection data, set a slice manager based on 5G network slicing technology, the slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of slices based on the urgency and importance of medical data, and build a transmission isolation security channel for the medical information collection data;

[0056] It is understandable that the execution subject of the present invention can be a medical information remote collection and processing device based on a 5G scenario, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0057] It should be noted that the data source: We obtained 1,000 medical records from an electronic medical record system of a large hospital. These data include basic patient information, diagnosis records, medication status, and examination results. Data preprocessing: Format conversion, data cleaning, and standardization are performed on these data to ensure data accuracy and consistency. For example, dates in different formats are uniformly converted to the YYYY-MM-DD format, and duplicate or invalid records are deleted. Slice manager is set up according to 5G network slicing technology. Slice manager configuration: According to the actual situation of the hospital network, a slice manager is configured, which can dynamically allocate network resources. For example, Huawei or Ericsson's 5G network slicing management solutions can be used. These solutions include slice policy control, slice resource management, and slice selection. Slice strategy formulation: Slice strategies are formulated according to the urgency and importance of medical data. For example, for real-time surgical imaging data that needs to be transmitted urgently, it can be configured as a high-priority slice to allocate more bandwidth resources; while for some regular medical record query requests, it can be configured as a low-priority slice. Dynamic allocation of network resources and adjustment of slice priority, resource allocation: The slice manager dynamically allocates network resources according to the real-time network status and slice strategy. For example, during peak hours, bandwidth allocation can be automatically adjusted to ensure that high-priority data can be transmitted smoothly. Priority adjustment: When there is urgent medical data to be transmitted, such as patient vital signs data in an ambulance, the slice manager can adjust the slice priority in real time to ensure that the data can be transmitted to the hospital in a timely manner.

[0058] Build a transmission isolation security channel, secure isolation: Utilize the isolation of 5G network slicing technology to build an independent transmission channel for each slice to ensure that data between different slices will not interfere with each other. Real-time monitoring and adjustment: The slice manager monitors the network status and data transmission in real time, and dynamically adjusts slice resource allocation and priority settings as needed to ensure real-time and secure transmission of medical information collection data.

[0059] 102. Deploy a task module at the edge of the 5G network, and obtain a medical collection information output group based on the medical information collection data combined with the task module;

[0060] It should be noted that the site selection and deployment: First, select the 5G network edge location near the hospital. Here we selected a 5G base station within 500 meters of the hospital as the edge computing node. The node has good communication infrastructure and stable 5G network coverage, which can ensure low latency and high reliability of data transmission. Task module design: According to the needs of medical information collection, a task module is designed that can receive and process medical data from the hospital. The task module includes functions such as data reception, data preprocessing, data analysis and feature extraction. Resource allocation: Allocate sufficient computing resources for the task module on the edge computing node. 10 CPU cores and 50GB of memory are allocated to process medical information data.

[0061] Medical information collection data processing, data collection: receive medical information collection data from the hospital in real time through the 5G network. Set to receive 10MB of electrocardiogram data per minute. Data preprocessing: The task module preprocesses the received data, including denoising, standardization and other operations. After preprocessing, the data size is reduced to 8MB / minute. Data analysis and feature extraction: Use machine learning algorithms to analyze the preprocessed data and extract key features. For example, extract key physiological indicators such as heart rate and heart rhythm from electrocardiogram data. Obtain a medical collection information output group, result integration: Integrate the extracted features into a medical collection information output group, which contains the patient's key physiological indicators such as heart rate and heart rhythm, as well as possible abnormal alarms.

[0062] Through the above examples, we can see that after deploying the task module at the edge of the 5G network, it can efficiently process medical information collection data and output key medical collection information groups, providing strong support for remote medical monitoring and diagnosis. At the same time, the high speed and low latency characteristics of the 5G network ensure the real-time and accuracy of the data.

[0063] 103. Enhance the medical information collection output group according to a preset generative adversarial network to obtain a medical collection information expansion group;

[0064] It should be noted that we already have a medical information collection output group, which contains 1,000 sets of ECG data, each of which is 30 seconds long and has a sampling rate of 300Hz, that is, each set of data contains 9,000 data points. These data have been preprocessed and feature extracted and can be used for training the Generative Adversarial Network (GAN). GAN model selection: Select a GAN model suitable for processing sequence data, such as LSTM-GAN or TimeGAN, which can generate new sequences similar to the original data sequence. Determine the parameters of the GAN model, such as the network structure and learning rate of the generator and discriminator. In the training phase, data division: divide the 1,000 sets of ECG data into a training set (800 sets) and a test set (200 sets). Model training: Use the training set to train the GAN model, and through the adversarial learning of the generator and the discriminator, enable the model to generate new data similar to the original ECG data. During the training process, the parameters and learning rate of the model can be adjusted as needed to achieve the best generation effect. The training cycle is set to 100 epochs, each epoch contains multiple batches, and each batch contains 32 ECG data.

[0065] Generation and evaluation phase, data generation: After training, the generator is used to generate new ECG data. We generated 200 new ECG data as an augmentation group. These generated data should be similar to the original data in statistical characteristics, but not completely copy the original data. Data evaluation: The generated data is evaluated using the test set, and the authenticity of the generated data is verified by comparing the statistical characteristics of the generated data with the test set data (such as mean, variance, waveform characteristics, etc.). The generated ECG data can be further analyzed using professional medical software or algorithms to ensure its medical rationality and usability. Data augmentation: The generated ECG data is added to the original dataset to form a larger dataset. This augmented dataset can be used for subsequent medical information analysis, model training and other tasks. Through data augmentation, we can increase the diversity and generalization ability of the data, thereby improving the performance of related medical applications. Continuous monitoring and updating: Regularly evaluate the quality and effectiveness of the generated data, adjust the parameters of the GAN model according to the actual situation, or retrain the model to adapt to the new data distribution. As time goes by and medical data accumulates, the dataset can be continuously updated and expanded to maintain its timeliness and representativeness.

[0066] 104. Encrypt and protect the medical collection information extension group according to quantum key distribution, encrypt and transmit the medical collection information extension group by real-time updating and exchanging keys, and obtain the medical collection information encryption group;

[0067] It should be noted that a quantum channel is established through a 5G network or a dedicated optical fiber to ensure the stable transmission of quantum signals. The sender prepares quantum bits: The sender uses a quantum signal transmitter to prepare a series of random quantum bit sequences as the original material of the key. Quantum bit transmission: Through the quantum channel, the sender sends the quantum bit sequence to the receiver. The receiver measures the quantum bits: The receiver uses a quantum signal receiver to measure the received quantum bits and obtains a series of measurement results. Key extraction: The two parties extract a consistent key sequence from the measurement results through comparison and negotiation. For example, a 256-bit quantum key can be generated. Encryption of the medical collection information expansion group, data encryption: Use the extracted quantum key to encrypt the medical collection information expansion group using a symmetric encryption algorithm (such as AES). Set the expansion group to contain 1,000 electrocardiogram data, each of which is 1MB in size, then a total of 1GB of data needs to be encrypted. Encryption effect verification: The encryption effect is verified through statistical tests and cryptographic analysis methods to ensure the confidentiality and integrity of the data. Real-time key update and exchange, regular key update: To ensure security, both parties update and exchange new quantum keys regularly (such as every hour). Key synchronization: The keys of both parties are synchronized and updated through secure communication protocols (such as SSL / TLS) to ensure the continuity of encrypted transmission.

[0068] 105. Receive and store the encrypted medical collection information encryption group, decrypt it to restore the original medical collection information expansion group, and obtain the medical collection information analysis result according to the medical collection information expansion group.

[0069] It should be noted that the establishment of a receiving system: a secure receiving system is established in a medical information center or data center, which is capable of receiving encrypted data transmitted through a 5G network. Data reception: encrypted medical collection information is received from the sender through a 5G network. For example, a 2GB encrypted data packet is received, which contains 1,000 encrypted electrocardiogram data. Storing encrypted medical collection information, secure storage: the received encrypted data is stored on a secure server, and a high-standard encrypted file system or hardware security module (HSM) is used to protect the security of the data. Backup mechanism: in order to ensure the security of the data, a data backup mechanism is established to regularly back up the encrypted data to another secure location. Decryption restores the original medical collection information expansion group, prepares the decryption key: obtains the quantum key shared with the sender from a secure key management system. Data decryption: decrypts the encrypted medical collection information using the obtained quantum key. For example, a 256-bit quantum key is used to decrypt a 2GB encrypted data packet and restore the original 1,000 electrocardiogram data. Data integrity verification: after decryption is completed, data integrity verification is performed to ensure that the data has not been tampered with or damaged during the decryption process. The analysis results are obtained based on the expanded group of medical collection information. Data preprocessing: preprocess the decrypted ECG data, such as denoising, waveform recognition, etc., to improve the accuracy of data analysis. Data analysis: use professional medical data analysis software or algorithms to analyze the preprocessed ECG data. For example, indicators such as heart rate, heart rhythm, and waveform abnormalities can be analyzed. Result output: Generate a medical collection information analysis report based on the analysis results. The report contains information such as the patient's heart rate data, abnormal heart rhythm alarm, and waveform analysis results. For example, the analysis report indicates that a patient has an irregular heartbeat and needs further attention and treatment.

[0070] In the embodiment of the present invention, the entire process from data collection, transmission to analysis and storage is covered. First, through the 5G network slicing technology, network resources are dynamically allocated, and the priority and bandwidth allocation of the slices are adjusted according to the urgency and importance of the medical data to ensure the real-time and security of data transmission. Secondly, the task module is deployed at the edge of the 5G network to preprocess and extract features of the collected medical information to obtain an output group of medical collection information. Then, the output group is enhanced using a preset generative adversarial network to obtain an extended group to increase the diversity and generalization ability of the data. Then, the quantum key distribution technology is used to encrypt and protect the extended group, and the security of encrypted transmission is ensured by real-time updating and exchanging keys. Finally, the encrypted medical collection information is received and stored, the original data is restored after decryption, and in-depth analysis is performed to obtain the analysis results of the medical collection information. Through 5G network slicing technology, network resources can be dynamically allocated to ensure that urgent and important medical data can be transmitted first, greatly improving the real-time and efficient processing of data transmission; quantum key distribution technology is used to encrypt and protect medical data, ensuring the security of data during transmission and storage, and effectively preventing data leakage and tampering; by generating adversarial networks to enhance medical collection information, an expansion group is obtained, which not only increases the amount of data, but also improves the diversity of data, providing more powerful support for subsequent medical information analysis and model training; deploying task modules at the edge of the 5G network can reduce the delay of data transmission, improve processing speed, and reduce dependence on central servers, achieving more efficient distributed processing; by conducting in-depth analysis of the decrypted medical collection information, the patient's health status can be more accurately grasped, potential health problems can be discovered in time, and doctors can be provided with more comprehensive diagnostic basis and treatment plans. In summary, the present invention not only improves the real-time, security and efficiency of medical information collection, transmission and processing, but also provides richer and more accurate data support for subsequent medical information analysis and diagnosis, which helps to improve the quality and efficiency of medical services.

[0071] See also Figure 2 Another embodiment of the medical information remote collection and processing method based on the 5G scenario in the embodiment of the present invention includes:

[0072] 201. Obtain medical information collection data, set a slice manager based on 5G network slicing technology, the slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of slices based on the urgency and importance of medical data, and build a transmission isolation security channel for the medical information collection data;

[0073] Specifically, the original medical information collection data is received through the intelligent data collection interface, and the accessed medical information collection data is preprocessed, including format conversion, data cleaning, and standardization; compressive sensing processing is performed based on the preprocessed medical information collection data. Let the vector of the preprocessed medical information collection data be \(x\in\mathbb{R}^N\), where \(N\) is the dimension of the data, and the measurement matrix in compressive sensing is \(\Phi\in\mathbb{R}^{M\times N}\), which is used to project the data from the high-dimensional space to the low-dimensional space, where \(M < N\). The measurement value \(y\in\mathbb{R}^M\) is obtained through the following formula: \(y = \Phi x\).

[0074] Let \(\Psi\) be the sparse basis matrix, then the signal \(x\) is expressed as: \(x=\Psi\theta\); where \(\theta\) is the sparse representation of the signal in the (\(\Psi\)) domain; it is transformed into solving:

[0075] \(\min_{\theta}||\theta||_1\quad\text{s.t.}\quad||y - \Phi\Psi\theta||_2\leq\epsilon\)

[0076] where \(||\theta||_1\) is the \(L_1\) norm of \(\theta\), which is used to promote sparsity; \(||y - \Phi\Psi\theta||_2\) is the (\(L_2\)) norm of the measurement error; \(\epsilon\) is a small positive number, representing the allowable error range; the downsampled information collection data is obtained; the data evaluation model is used to evaluate the urgency and importance of the downsampled information collection data. According to the evaluation results, the data is classified into different priorities, including urgent, high priority, medium priority, and low priority, to obtain the priority classification result; the slice manager dynamically configures the network slice according to the priority classification result of the data and the resource and status information of the current 5G network, allocates the corresponding network slice for each priority data, and ensures that urgent and high-priority data obtains more network resources to obtain the transmission isolation security channel; the medical information collection data is transmitted through the configured transmission isolation security channel, and the slice manager monitors the network status and data transmission situation in real time and dynamically adjusts the slice resource allocation according to the needs.

[0077] It should be noted that assume we are conducting a medical information remote collection and processing project based on the 5G scenario. The following are the specific implementation examples.

[0078] Intelligent data acquisition and preprocessing. Through the intelligent data acquisition interface, we received 1000 pieces of original medical record data from the electronic medical record system of a large hospital. This data includes patients' basic information, diagnosis records, medication situations, and examination results, etc. Preprocess this data, including format conversion, data cleaning, and standardization. For example, we uniformly convert dates in different formats to the "YYYY-MM-DD" format, delete duplicate or invalid records, and ensure that all data items conform to the predetermined data format and standards.

[0079] Compressed sensing processing. Set the preprocessed medical information acquisition data vector as x, where x is an N-dimensional vector and N = 1000 (assuming each medical record data is a dimension). Select a suitable measurement matrix Φ with dimensions M×N, where M < N. For simplicity of explanation, we set M = 800. Through the formula y = Φx, we obtain the 800-dimensional measurement value y. Set the sparse basis matrix Ψ and assume that the signal x is sparse in the Ψ domain, that is, x = Ψθ, where θ is the sparse representation of the signal in the Ψ domain. By solving the optimization problem \(\min_{\theta}||\theta||_1\quad\text{s.t.}\quad||y - \Phi\Psi\theta||_2\leq\epsilon\), we obtain the dimension-reduced information acquisition data θ.

[0080] Data evaluation and priority classification. Use the data evaluation model to evaluate the urgency and importance of the dimension-reduced information acquisition data θ. This model can be based on machine learning algorithms such as random forest or neural network, and learn how to evaluate the priority of new data by training historical data. According to the evaluation results, we classify the data into four priorities: urgent, high priority, medium priority, and low priority. For example, for the real-time surgical imaging data that needs to be transmitted urgently, we classify it as urgent or high priority.

[0081] Network slice configuration and data transmission. The slice manager dynamically configures network slices according to the data priority classification results and the resource and status information of the current 5G network. For example, for urgent and high-priority data, we will configure more bandwidth resources and higher transmission priorities. The medical information acquisition data is transmitted through the configured transmission isolation security channel. The slice manager monitors the network status and data transmission situation in real time and dynamically adjusts the slice resource allocation according to needs. For example, during peak hours, the slice manager can automatically adjust the bandwidth allocation to ensure that high-priority data can be transmitted smoothly.

[0082] Through the above embodiments, we can see that in the remote collection and processing of medical information based on 5G scenarios, through intelligent data collection, preprocessing, compressed sensing processing, data evaluation and priority classification, network slicing configuration and data transmission, we can efficiently process and transmit medical information collection data to ensure the real-time, security and accuracy of the data.

[0083] 202. Deploy a task module at the edge of the 5G network, and obtain a medical collection information output group based on the medical information collection data combined with the task module;

[0084] Specifically, according to the geographical location of the medical institution, the coverage of the 5G network and the data processing requirements, edge computing nodes are selected for deployment; the functions of the task module are defined, including data preprocessing, feature extraction, and data analysis; and / or artificial intelligence algorithms are set in the task module, including deep learning and machine learning; the received medical information collection data is preprocessed, including denoising and normalization; the feature extraction and analysis of the preprocessed data in the task module are performed to obtain the second medical information collection data and the third medical information collection data; the second medical information collection data and the third medical information collection data are organized to obtain a medical collection information output group;

[0085] It should be noted that we have a 5G-based medical information remote collection and processing system that serves multiple medical institutions in a large city. These medical institutions are located in different areas of the city, and the 5G network coverage and data processing requirements of each area are different.

[0086] Select edge computing nodes for deployment. Based on the geographical location of medical institutions, we choose to deploy edge computing nodes in five key locations: the city center, north, south, east, and west, to ensure that all medical institutions can quickly access them. Considering the 5G network coverage, we ensure that the selected edge computing nodes are located in areas with strong and stable 5G signals. In view of the large number of medical institutions in the city center and the large data processing needs, we deployed two edge computing nodes in this area to share the processing pressure.

[0087] Define the functions of the task modules. Data preprocessing module: responsible for denoising and normalizing the received raw medical information; feature extraction module: using deep learning algorithms to extract key medical features from preprocessed data; data analysis module: combining machine learning algorithms to conduct in-depth analysis of the extracted features to obtain diagnostic recommendations or disease predictions. Set up artificial intelligence algorithms. In the feature extraction module, we deployed a convolutional neural network (CNN) model to extract key lesion features from medical images; in the data analysis module, we used a random forest-based classifier to classify and predict the disease based on the extracted features.

[0088] Data preprocessing,We received 1000 sets of ECG data from a medical institution.,First, the data preprocessing module denoised these 1000 sets of data,removing the noise caused by equipment or environmental interference.,Next, these ECG data were normalized to ensure that all data were at the same,level for subsequent feature extraction and analysis.,Feature extraction and analysis,The feature extraction module uses the CNN model to extract key features related to heart disease,such as abnormal heart rate and waveform from the preprocessed ECG data.,Based on the key features, we organized these 1000 sets of ECG data and their,corresponding classification labels into a medical collection information output group.

[0089] 203. Enhance the medical information collection output group according to a preset generative adversarial network to obtain a medical collection information expansion group;

[0090] Specifically, a generative adversarial network is preset, including a conditional generative adversarial network (cGAN), a cyclic generative adversarial network (CycleGAN), and a style transfer GAN; the generative adversarial network is trained to enable it to generate data similar to real medical information, and a trained generative adversarial network is obtained; the medical information collection output group is processed and converted into a format corresponding to the generative adversarial network, which format includes images and sequence data; the processed medical information collection output group is used as input data and input into the trained generative adversarial network; and / or in the process of using the generative adversarial network for data enhancement, differential privacy is added to ensure that the generated extended data does not leak the patient's sensitive information; and / or multiple modal medical information collection output groups, including images, medical record texts, and physiological signals, are simultaneously input into the generative adversarial network to generate multimodal extended data; and an extended group of medical collection information is obtained;

[0091] It should be noted that in the medical information remote collection and processing system based on 5G scenarios, in order to enhance the medical data set and improve the generalization ability and robustness of the model, we use generative adversarial networks (GANs) for data enhancement. The following is a specific example that explains how to expand the medical data set by presetting and training GANs.

[0092] Step 1: Preset the generative adversarial network and select the conditional generative adversarial network (cGAN) to generate medical images according to specific conditions; select the cycle generative adversarial network (CycleGAN) for style transfer, such as converting MRI images to CT images; select the style transfer GAN to change the style of medical images while retaining their key medical features.

[0093] Step 2: Train the Generative Adversarial Network, using a dataset containing 10,000 real medical images (such as X-rays, MRI images, etc.) to train cGAN. After multiple iterations of training, cGAN is able to generate data similar to real medical images; use paired MRI and CT images to train CycleGAN, so that it can convert the style of MRI images to the style of CT images. The training set contains 5,000 pairs of images; use style transfer GAN to convert the style of medical images, such as converting normal X-rays into X-rays with certain specific pathological features, and the training set contains 3,000 images.

[0094] Step 3: Process the medical information collection output group, obtain a medical information collection output group containing 500 X-rays, 500 medical records and 500 sets of physiological signals from the medical information system; convert the X-rays into a unified image format (such as JPEG), convert the medical record text into sequence data (such as using word embedding), and convert the physiological signals into time series data.

[0095] Step 4: Input the generative adversarial network, input 500 X-rays into the trained cGAN to generate 500 new X-rays; input 500 MRI images into the trained CycleGAN and convert them into 500 CT-style images; input 500 normal X-rays into the style transfer GAN and convert them into 500 X-rays with specific pathological features.

[0096] Step 5: Add differential privacy. In the process of using GAN for data enhancement, differential privacy technology is added. By adding an appropriate amount of noise to the generated augmented data, the patient's sensitive information is ensured not to be leaked. For example, tiny random noise is added to the generated X-ray.

[0097] Step 6: Multimodal data input: X-rays, medical records, and physiological signals are simultaneously input into a multimodal GAN ​​(such as a custom GAN that can handle multimodal input) to generate multimodal augmented data containing images, text, and physiological signals. For example, 500 sets of multimodal augmented data are generated.

[0098] Step 7: Get the expanded set of medical information. Finally, we get an expanded dataset containing 2,000 X-rays (500 original + 500 generated by cGAN + 500 generated by style transfer GAN + 500 converted by CycleGAN), 500 medical records and 500 sets of physiological signals. This expanded dataset can be used for subsequent medical image analysis, disease prediction and other tasks to improve the performance and generalization ability of the model.

[0099] 204. Encrypt and protect the medical collection information extension group according to quantum key distribution, and encrypt and transmit the medical collection information extension group by real-time updating and exchanging keys to obtain the medical collection information encryption group;

[0100] Specifically, quantum communication links are established and quantum communication equipment is deployed, including quantum key distributors and quantum receivers; quantum key distribution technology is used to generate quantum keys between the communicating parties, and keys are updated and exchanged in real time through quantum communication links to ensure the freshness and security of the keys; and / or based on the edge computing capabilities of the 5G network, part of the computing tasks of the quantum key distribution process are offloaded to edge nodes to reduce the burden on the core network; quantum-safe encryption algorithms are used, including the AES encryption algorithm based on quantum keys, and the encryption formula is expressed as: C_i=E_{K_i}(P_i);

[0101] Where: (C_i) represents the ciphertext of the (i)th data group; (E_{K_i}) represents the encryption algorithm using the (i)th round key (K_i); (P_i) represents the (i)th plaintext data group; in the process of quantum key distribution, the BB84 or B92 protocol is used to generate the initial key, and the key generation process is: K=QKD(A,B);

[0102] Where: (K) is the key generated by quantum key distribution; (QKD) represents the quantum key distribution process; (A) and (B) represent the two parties in communication respectively;

[0103] Obtain the original medical collection information expansion group from the medical system and divide it into data groups (P_i); generate an initial key (K) between the communicating parties through a quantum key distribution process; use a key expansion algorithm to generate round keys (K_i) required for multi-round encryption from the initial key (K); encrypt each data group (P_i) using an encryption algorithm (E_{K_i}) and a corresponding round key (K_i) to obtain a ciphertext (C_i), and form a medical collection information encryption group based on the ciphertext (C_i);

[0104] It should be noted that quantum communication links are established between medical institutions covered by 5G networks. For example, two hospitals A and B located in different areas are selected, and the distance between them is 20km. Quantum communication equipment, including quantum key distributors and quantum receivers, are deployed in hospitals A and B respectively. These devices support BB84 or B92 protocols for generating initial keys.

[0105] Using quantum key distribution technology, an initial quantum key K is generated between hospital A and hospital B. The length of the generated initial key K is set to 128 bits. Based on the edge computing capabilities of the 5G network, some computing tasks (such as key screening, error correction, etc.) in the quantum key distribution process are offloaded to edge nodes for processing to reduce the burden on the core network. The round key Ki required for multiple rounds of encryption is generated from the initial key K using a key expansion algorithm. For example, the round keys required for 10 rounds of encryption can be generated, and the length of each round key is 128 bits.

[0106] Quantum-safe encryption algorithm is implemented to obtain the original medical collection information expansion group from the medical system. This expansion group is set to contain 1000 medical records, each of which is 1MB in size. These medical records are divided into data packets Pi, each of which is 128KB in size. Therefore, there are a total of 8000 data packets (1000 medical records x 1MB / copy ÷ 128KB / group = 8000 groups). Each data packet Pi is encrypted using the initial key K generated by quantum key distribution and the round key Ki generated by the key expansion algorithm. The encryption algorithm uses the AES encryption algorithm based on quantum keys, and the formula is expressed as: Ci=EKi(Pi), where Ci represents the ciphertext of the i-th data packet; EKi represents the encryption algorithm using the i-th round key Ki; Pi represents the i-th plaintext data packet. After encryption, 8000 ciphertext data packets Ci are obtained.

[0107] Form a medical collection information encryption group, combine these 8,000 ciphertext data groups Ci to form an encrypted medical collection information encryption group. This encryption group can be securely transmitted to hospital B or other institutions that need to receive data through the 5G network.

[0108] 205. Receive and store the encrypted medical collection information encryption group, decrypt and restore the original medical collection information expansion group, and obtain the medical collection information analysis result according to the medical collection information expansion group;

[0109] Specifically, the encrypted medical collection information encryption group is received through the 5G network, and the integrity of the received medical collection information encryption group is verified. The data of the received medical collection information encryption group is set to (D), and its corresponding hash value is (H(D)). The sender will calculate the hash value (H_{original}(D)) before sending the data and send it together with the data. The integrity verification formula is:

[0110] [\text{Verification results}=\begin{cases}

[0111] \text{Pass},&\text{if}H(D)=H_{original}(D)\

[0112] \text{Not passed},&\text{otherwise}

[0113] \end{cases}]

[0114] Wherein, (D): received encrypted group data; (H(D)): hash value of received data calculated by the server; (H_{original}(D)): original hash value provided by the sender; ensure that the data has not been tampered with during transmission. After verification, the encrypted group of medical collection information is securely stored in the database of the server; when data needs to be processed, retrieve the corresponding encrypted group of medical collection information from the database, use the private key corresponding to the encryption stage to decrypt the encrypted group of medical collection information, and restore the original extended group of medical collection information; pre-process the extended group of medical collection information, and use machine learning or The deep learning algorithm extracts key features from the preprocessed data, and analyzes the medical information based on the extracted features, including disease prediction and health status assessment, to obtain the analysis results of the medical collection information; and / or utilizes the smart contract technology to automatically trigger the preset data verification and analysis smart contract after the encrypted group of medical collection information is successfully received and decrypted. The contract will automatically perform preliminary data quality assessment, outlier detection, and key indicator extraction on the decrypted expanded group of medical collection information, and generate the analysis results of the medical collection information; based on the analysis results of the medical collection information, the smart contract automatically adjusts the subsequent data collection strategy or triggers the alarm mechanism;

[0115] It should be noted that to receive and verify the integrity of the medical collection information encryption group, Hospital A sends an encrypted medical collection information group containing 1,000 medical records to Hospital B through the 5G network. The total data is 1GB, and it is accompanied by the original hash value H_original(D) calculated by the sender. After receiving the encryption group, Hospital B first calculates the hash value H(D) of the received data. Hospital B compares the calculated hash value H(D) with the received H_original(D). Set the value of H(D) to 0x12345abc, and the value of H_original(D) is also 0x12345abc. Since H(D) is equal to H_original(D), the verification result is "passed", confirming that the data has not been tampered with during transmission.

[0116] Secure storage and data retrieval: After verification, Hospital B securely stores the encrypted group of medical information in the database of the server, using the AES-256 encryption standard for additional protection. When data processing is required, Hospital B retrieves the encrypted group from the database. Data decryption and preprocessing: Hospital B uses the private key corresponding to the encryption stage to decrypt the encrypted group of medical information and successfully recovers the original 1,000 medical records. The data is preprocessed, such as data cleaning and formatting conversion, to facilitate subsequent analysis. Feature extraction and analysis: Deep learning algorithms (such as convolutional neural networks (CNNs)) are used to extract key medical features from the preprocessed data. Based on these features, machine learning algorithms (such as random forest classifiers) are used to predict diseases and assess health status. After analysis, it was found that 200 medical records may be at risk of diabetes, with an accuracy rate of 85%.

[0117] The automatic execution of the smart contract automatically triggers the preset data verification and analysis smart contract after the encrypted group of medical collection information is successfully received and decrypted. The smart contract automatically performs preliminary data quality assessment and outlier detection on the 1,000 decrypted medical records. 10 medical records were detected to have outliers and require further review. The smart contract continues to extract key indicators, such as the average age of patients, gender distribution, common diseases, etc., and generates a report on the analysis results of medical collection information. Based on the analysis results, the smart contract automatically adjusts the subsequent data collection strategy, such as increasing the attention to a certain type of disease, and triggers the alarm mechanism to notify relevant personnel to review abnormal medical records.

[0118] 206. Output the analysis results of the medical information collection in the form of a visual report or data interface; and / or develop a data visualization platform to display the analysis results of the medical information collection in the form of charts to medical personnel and patients, provide interactive functions, and allow medical personnel to mark, discuss and share on the platform; and / or based on the high bandwidth and low latency characteristics of the 5G network, realize remote medical consultation and services, and patients communicate with experts in real time through video calls or online chats to obtain professional advice and treatment plans; and / or integrate smart medical devices with the database of the server, so that the smart medical devices collect the patient's health data in real time and automatically upload it to the database of the server for analysis, so as to provide patients with more comprehensive health management services;

[0119] It should be noted that the analysis results of medical information collection are output in the form of a visual report in PDF format, which includes various statistical charts, key indicator analysis and prediction model results. At the same time, a RESTful API data interface is provided to allow third-party systems or applications to obtain analysis result data. For example, a data interface about the average blood sugar level of a patient returns the following JSON format data:

[0120] json

[0121] {

[0122] "average_blood_sugar": "120 mg / dL",

[0123] "patient_count": "1000",

[0124] "analysis_date": "2023-04-01"

[0125] }

[0126] Data visualization platform development, develop a web-based data visualization platform that supports a variety of chart displays, such as bar charts, line charts, pie charts, etc. The platform displays the analysis results of medical information collection, such as the distribution of diseases in patients of different age groups, and the correlation between different symptoms. Medical personnel can annotate specific data on the platform, such as marking abnormal data points, and discuss and share with other medical personnel. The platform records the discussion content and annotation information of medical personnel to provide reference for subsequent data analysis. Telemedicine consultation and services, using the high bandwidth and low latency characteristics of 5G networks, develop a telemedicine consultation system. Patients can make high-definition video calls with experts through mobile phones or computers to communicate about their conditions in real time. In a remote consultation, 50 patients communicated with 10 medical experts in different fields through video calls, and the average consultation time for each patient was 15 minutes. Through the analysis results and patient feedback recorded by the system, 90% of patients expressed satisfaction or very satisfaction with the consultation results. Smart medical equipment is integrated with the server database, integrating medical equipment such as smart blood glucose meters and smart blood pressure monitors with the server database. These devices can collect patients' blood sugar, blood pressure and other health data in real time, and automatically upload them to the server through the 5G network. After receiving the data, the server immediately analyzes it and generates personalized health management suggestions. Within a month, the system received and analyzed real-time health data from 1,000 patients, successfully providing effective health management suggestions for 80% of the patients, helping them improve their health.

[0127] In the embodiment of the present invention, a number of advanced technologies such as 5G network slicing technology, edge computing, generative adversarial network (GAN), quantum key distribution (QKD) and smart contracts are comprehensively used to realize the complete process from medical information collection, processing, enhancement, encrypted transmission to result analysis. The specific steps include: receiving and preprocessing medical information through an intelligent data acquisition interface, using compressed sensing technology to reduce the dimension of data, dynamically allocating network resources according to the urgency and importance of data, deploying task modules at the edge of the 5G network for efficient data processing, using GAN for data enhancement, encrypting and transmitting data through QKD technology, receiving and decrypting data for analysis, and outputting results in the form of visual reports or data interfaces. In addition, the present invention also provides value-added services such as data visualization platform, telemedicine consultation and intelligent medical equipment integration. Through 5G network slicing technology, network resources are dynamically allocated according to the urgency and importance of data to ensure that key medical data can be transmitted and processed in real time and efficiently; quantum key distribution technology is used to encrypt and transmit medical information to ensure the confidentiality and integrity of data during transmission. At the same time, differential privacy technology is added in the GAN data enhancement process to protect the patient's sensitive information from being leaked; data enhancement is performed through GAN, the medical data set is expanded, and the generalization ability and accuracy of the subsequent analysis model are improved; task modules are deployed at the edge of the 5G network to reduce data transmission delays, improve processing efficiency, and reduce the burden on the central server; using smart contract technology, the data verification and analysis process is automatically triggered after the data is received and decrypted, and the process is intelligent and automated; through the data visualization platform, medical personnel can intuitively view and analyze the analysis results of medical collection information, and provide interactive functions to strengthen communication and collaboration between medical teams; based on the high bandwidth and low latency characteristics of the 5G network, remote medical consultation and services are realized, so that patients can more conveniently obtain professional medical advice and treatment plans; intelligent medical equipment is integrated with the server database to realize real-time health data collection and analysis, and provide patients with more comprehensive health management services. In summary, the present invention not only improves the efficiency, security and accuracy of medical information collection and processing, but also provides strong technical support for telemedicine services, data visualization and intelligent medical equipment integration, which helps to promote the digital transformation and upgrading of the medical industry.

[0128] The above describes the medical information remote collection and processing method based on the 5G scenario in the embodiment of the present invention. The following describes the medical information remote collection and processing device based on the 5G scenario in the embodiment of the present invention. Figure 3In one embodiment of the present invention, a remote medical information collection and processing device based on a 5G scenario includes: an acquisition module 301, which is used to acquire medical information collection data, set a slice manager according to the 5G network slicing technology, and the slice manager indicates that it is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of the slice according to the urgency and importance of the medical data, and build a transmission isolation and security channel for the medical information collection data; a task module 302, which is used to deploy the task module at the edge of the 5G network, and obtain a medical collection information output group according to the medical information collection data combined with the task module; an enhancement module 303, which is used to enhance the medical information collection output group according to a preset generative adversarial network to obtain a medical collection information expansion group; an encryption module 304, which is used to encrypt and protect the medical collection information expansion group according to quantum key distribution, and encrypt and transmit the medical collection information expansion group by real-time updating and exchanging keys to obtain a medical collection information encryption group; an allocation module 305, which is used to receive and store the encrypted medical collection information encryption group, decrypt and restore the original medical collection information expansion group, and obtain the medical collection information analysis result according to the medical collection information expansion group.

[0129] In the embodiment of the present invention, through the 5G network slicing technology, it is ensured that key medical data can be transmitted and processed in real time and efficiently to meet the real-time requirements of telemedicine; quantum key distribution technology provides unbreakable encryption protection for medical data to ensure the absolute security of data during transmission. The application of differential privacy technology further protects the privacy information of patients; the data enhancement technology of generative adversarial networks increases the diversity and generalization ability of medical data, and improves the accuracy and robustness of subsequent analysis models; the deployment of task modules at the edge of the 5G network reduces data transmission delays, improves processing efficiency, and reduces the burden on the central server; the entire system realizes intelligent and automated data processing and analysis processes, improves work efficiency and accuracy; provides strong technical support for telemedicine consultation and services, so that patients can more conveniently obtain professional medical advice and treatment plans; supports the integration of intelligent medical equipment and server databases, realizes real-time health data collection and analysis, and provides patients with more comprehensive health management services. In summary, the medical information remote collection and processing device based on the 5G scenario not only improves the efficiency, security and accuracy of medical information collection and processing, but also provides strong technical support for telemedicine services, intelligent medical equipment integration and other fields, which helps to promote the digital transformation and upgrading of the medical industry.

[0130] above Figure 3 The medical information remote collection and processing device based on the 5G scenario in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The medical information remote collection and processing device based on the 5G scenario in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0131] Figure 4 It is a structural diagram of a medical information remote collection and processing device based on a 5G scenario provided by an embodiment of the present invention. The medical information remote collection and processing device 400 based on the 5G scenario may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 410 (for example, one or more processors) and a memory 420, and one or more storage media 430 (for example, one or more mass storage devices) storing application programs 433 or data 432. Among them, the memory 420 and the storage medium 430 can be short-term storage or persistent storage. The program stored in the storage medium 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the medical information remote collection and processing device 400 based on the 5G scenario. Furthermore, the processor 410 can be configured to communicate with the storage medium 430 to execute a series of instruction operations in the storage medium 430 on the medical information remote collection and processing device 400 based on the 5G scenario.

[0132] The medical information remote collection and processing device 400 based on the 5G scenario may also include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input and output interfaces 460, and / or one or more operating systems 431, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that Figure 4 The structure of the medical information remote collection and processing device based on the 5G scenario shown does not constitute a limitation on the medical information remote collection and processing device based on the 5G scenario, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0133] The present invention also provides a medical information remote collection and processing device based on a 5G scenario, and the medical information remote collection and processing device based on a 5G scenario includes a memory and a processor, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the medical information remote collection and processing method based on the 5G scenario in the above-mentioned embodiments.

[0134] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the method for remote collection and processing of medical information based on the 5G scenario.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the whole or part of the solution of the present invention, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0137] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for remote collection and processing of medical information based on 5G scenarios, characterized in that: The medical information remote acquisition and processing method based on 5G scenarios includes: Obtain medical information acquisition data, set a slice manager according to 5G network slicing technology. The slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of the slice according to the urgency and importance of medical data, and construct a transmission isolation security channel for the medical information acquisition data; Deploy a task module at the edge of the 5G network, and combine the medical information acquisition data with the task module to obtain a medical acquisition information output group; Enhance the medical information acquisition output group according to a preset generative adversarial network to obtain a medical acquisition information expansion group; Encrypt and protect the medical acquisition information expansion group according to quantum key distribution, and perform encrypted transmission of the medical acquisition information expansion group by real-time updating and exchanging keys to obtain a medical acquisition information encrypted group; Receive and store the encrypted medical acquisition information encrypted group, decrypt and restore the original medical acquisition information expansion group, and obtain a medical acquisition information analysis result according to the medical acquisition information expansion group; The step of obtaining medical information acquisition data, setting a slice manager according to 5G network slicing technology. The slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of the slice according to the urgency and importance of medical data, and construct a transmission isolation security channel for the medical information acquisition data includes: Receive the original medical information acquisition data through an intelligent data acquisition interface, and perform preprocessing on the accessed medical information acquisition data, including format conversion, data cleaning, and standardization; Perform compressive sensing processing on the preprocessed medical information acquisition data. Set the vector of the preprocessed medical information acquisition data as \(x\in\mathbb{R}^N\), where \(N\) is the dimension of the data, and the measurement matrix in compressive sensing is \(\Phi\in\mathbb{R}^{M\times N}\), which is used to project the data from a high-dimensional space to a low-dimensional space, where \(M < N\). The measurement value \(y\in\mathbb{R}^M\) is obtained through the following formula: y = \Phix; Set \(\Psi\) as the sparse basis matrix, then the signal \(x\) is expressed as: x=\Psi\theta; where \(\theta\) is the sparse representation of the signal in the (\(\Psi\)) domain; It is transformed into solving: \min_{\theta}||\theta||_1\quad\text{s.t.}\quad||y - \Phi\Psi\theta||_2\leq\epsilon where \(||\theta||_1\) is the \(L_1\) norm of \(\theta\) and is used to promote sparsity; \(||y - \Phi\Psi\theta||_2\) is the (\(L_2\)) norm of the measurement error; \(\epsilon\) is a small positive number representing the allowable error range; and the downsampled information acquisition data is obtained; The data evaluation model is used to evaluate the urgency and importance of the data collected by the reduction in mining information. According to the evaluation results, the data is classified into different priorities, including emergency, high priority, medium priority and low priority, and the priority classification results are obtained; The slice manager dynamically configures network slices based on the data priority classification results, as well as the resources and status information of the current 5G network, and allocates corresponding network slices to each priority data, ensuring that urgent and high-priority data obtain more network resources and obtains transmission isolation and secure channels; Medical information collection data is transmitted through a configured transmission isolation security channel. The slice manager monitors the network status and data transmission in real time and dynamically adjusts slice resource allocation as needed; The method of enhancing the medical information collection output group according to the preset generative adversarial network to obtain the medical collection information expansion group includes: Preset a generative adversarial network, including conditional generative adversarial network (cGAN), cycle generative adversarial network (CycleGAN), style transfer GAN; Train the generative adversarial network to generate data similar to real medical information, and obtain a trained generative adversarial network; Processing the output group of medical information collection and converting it into a format corresponding to the generative adversarial network, which includes images and sequence data; The processed output group of medical information collection is used as input data and input into the trained generative adversarial network; And / or in the process of data augmentation using generative adversarial networks, differential privacy is added to ensure that the generated augmented data does not leak the patient's sensitive information; and / or simultaneously inputting a plurality of modalities of medical information collection output groups, including images, medical record texts, and physiological signals, into a generative adversarial network to generate multimodal augmented data; Get the medical collection information expansion group; The method of encrypting and protecting the medical collection information extension group according to quantum key distribution, and encrypting and transmitting the medical collection information extension group by real-time updating and exchanging keys to obtain the medical collection information encryption group includes: Establish quantum communication links and deploy quantum communication equipment, including quantum key distributors and quantum receivers; Using quantum key distribution technology, quantum keys are generated between the communicating parties, and the keys are updated and exchanged in real time through quantum communication links to ensure the freshness and security of the keys; And / or based on the edge computing capabilities of the 5G network, offload part of the computing tasks of the quantum key distribution process to edge nodes to reduce the burden on the core network; A quantum-safe encryption algorithm is used. The encryption algorithm includes the AES encryption algorithm based on quantum keys. The encryption formula is expressed as: C_i=E_{K_i}(P_i); Where: (C_i) represents the ciphertext of the (i)th data group; (E_{K_i}) represents the encryption algorithm using the (i)th round key (K_i); (P_i) represents the (i)th plaintext data group; In the process of quantum key distribution, the BB84 or B92 protocol is used to generate the initial key. The key generation process is: K = QKD(A,B); Where: (K) is the key generated by quantum key distribution; (QKD) represents the quantum key distribution process; (A) and (B) represent the two parties in communication respectively; Obtain the original medical collection information expansion group from the medical system and divide it into data groups (P_i); generate an initial key (K) between the communicating parties through a quantum key distribution process; use a key expansion algorithm to generate round keys (K_i) required for multi-round encryption from the initial key (K); encrypt each data group (P_i) using an encryption algorithm (E_{K_i}) and a corresponding round key (K_i) to obtain a ciphertext (C_i), and form a medical collection information encryption group based on the ciphertext (C_i); The receiving and storing of the encrypted medical collection information encryption group, decrypting and restoring the original medical collection information expansion group, and obtaining the medical collection information analysis result according to the medical collection information expansion group include: The encrypted medical collection information encryption group is received through the 5G network, and the received medical collection information encryption group is verified for integrity. The data of the received medical collection information encryption group is set to (D), and its corresponding hash value is (H(D)). The sender will calculate the hash value (H_{original}(D)) before sending the data and send it together with the data. The integrity verification formula is: [\text{Verification results}=\begin{cases} \text{Pass},&\text{if}H(D)=H_{original}(D)\ \text{Not passed},&\text{otherwise} \end{cases}] Where, (D): received encrypted group data; (H(D)): hash value of received data calculated by the server; (H_{original}(D)): original hash value provided by the sender; Ensure that the data has not been tampered with during transmission. After verification, the encrypted group of medical information collection is securely stored in the server's database; When data processing is required, the corresponding encrypted group of medical collection information is retrieved from the database, and the encrypted group of medical collection information is decrypted using the private key corresponding to the encryption stage to restore the original expanded group of medical collection information; Preprocessing is performed based on the expanded group of medical information collection, and key features are extracted from the preprocessed data using machine learning or deep learning algorithms. Medical information is analyzed based on the extracted features, including disease prediction and health status assessment, to obtain analysis results of the medical information collection; And / or using smart contract technology, after the encrypted group of medical collection information is successfully received and decrypted, the preset data verification and analysis smart contract is automatically triggered, which will automatically perform preliminary data quality assessment, outlier detection and key indicator extraction on the decrypted expanded group of medical collection information, and generate medical collection information analysis results; Based on the analysis results of medical information collection, the smart contract automatically adjusts subsequent data collection strategies or triggers an alarm mechanism.

2. According to the 5G scenario-based medical information remote collection and processing method according to claim 1, it is characterized in that: The task module is deployed at the edge of the 5G network, and a medical information collection output group is obtained based on the medical information collection data combined with the task module, including: Select edge computing nodes for deployment based on the geographical location of the medical institution, 5G network coverage, and data processing requirements; Define the functions of task modules, including data preprocessing, feature extraction, and data analysis; And / or artificial intelligence algorithms are set in the task module, including deep learning and machine learning; Preprocess the received medical information collection data, including denoising and normalization; Using the task module to extract and analyze the preprocessed data, the second medical information collection data and the third medical information collection data are obtained; The second medical information collection data and the third medical information collection data are organized to obtain a medical collection information output group.

3. The method for remote collection and processing of medical information based on 5G scenarios according to claim 1 is characterized in that: Also includes: Outputting the analysis results of the medical information collection in the form of a visual report or a data interface; and / or developing a data visualization platform to present the analysis results of the medical information collection to medical personnel and patients in the form of charts, providing interactive functions and allowing medical personnel to annotate, discuss and share on the platform; and / or enable remote medical consultation and services based on the high bandwidth and low latency characteristics of 5G networks, where patients can communicate with experts in real time through video calls or online chats to obtain professional advice and treatment plans; And / or integrate the smart medical device with the server's database, so that the smart medical device collects the patient's health data in real time and automatically uploads it to the server's database for analysis, providing patients with more comprehensive health management services.

4. According to claim 1, a 5G scenario-based medical information remote collection and processing device is characterized in that: The medical information remote collection and processing device based on the 5G scenario includes: An acquisition module is used to acquire medical information collection data, set a slice manager according to the 5G network slicing technology, and the slice manager is configured to dynamically allocate network resources, adjust the priority and bandwidth allocation of slices according to the urgency and importance of medical data, and build a transmission isolation security channel for the medical information collection data; A task module is used to deploy the task module at the edge of the 5G network, and obtain a medical collection information output group based on the medical information collection data combined with the task module; An enhancement module, used for enhancing the medical information collection output group according to a preset generative adversarial network to obtain an expanded group of medical collection information; An encryption module is used to encrypt and protect the medical collection information extension group according to quantum key distribution, and to encrypt and transmit the medical collection information extension group by real-time updating and exchanging keys to obtain an encrypted medical collection information group; The allocation module is used to receive and store the encrypted medical collection information encryption group, decrypt it to restore the original medical collection information expansion group, and obtain the medical collection information analysis result based on the medical collection information expansion group.

5. According to claim 4, a 5G scenario-based medical information remote collection and processing device is characterized in that: The medical information remote collection and processing device based on the 5G scenario includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory so that the medical information remote collection and processing device based on the 5G scenario executes the medical information remote collection and processing method based on the 5G scenario as described in any one of claims 1-3.

6. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by the processor, the remote collection and processing of medical information based on the 5G scenario as described in any one of claims 1-3 is implemented.

Images