Diagnostic data remote transmission method based on regional remote diagnosis and treatment platform

Abstract

The invention discloses a diagnostic data remote transmission method based on a regional remote diagnosis and treatment platform. The method comprises the following steps: S1, collecting diagnostic data of a patient; s2, preprocessing the acquired diagnosis data; s3, carrying out data transmission by utilizing a short-distance wireless communication technology and a long-distance mobile communication technology; s4, performing data encryption and identity verification by adopting AES and RSA encryption algorithms; s5, after the regional remote diagnosis and treatment platform receives the diagnosis data, decryption and identity verification are carried out on the data; s6, performing image data analysis by using a convolutional neural network, processing character data by using a natural language processing technology, predicting and classifying physiological parameters by using regression analysis and a classification algorithm, and performing fusion analysis on multi-modal data in combination with a deep learning model; and S7, transmitting the analyzed and processed diagnosis result back to a local data terminal through a long-distance mobile communication technology. The system has the advantages of high transmission stability, high safety, high transmission efficiency and high diagnosis accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of remote data transmission, and in particular to a remote diagnosis data transmission method based on a regional remote diagnosis and treatment platform. Background Art

[0002] With the continuous advancement of information technology and medical technology, telemedicine has become an important part of modern medical services. Telemedicine can break geographical restrictions and enable patients to receive high-quality medical services at home, which is especially important for patients in remote areas and with limited mobility. However, diagnostic data faces many technical challenges in the process of remote transmission, including data transmission stability, security, transmission efficiency and diagnostic accuracy.

[0003] In the existing technology, traditional telemedicine data transmission methods mainly rely on a single communication technology and basic encryption measures. These methods have the following shortcomings when facing complex medical data transmission requirements:

[0004] 1. Insufficient transmission stability: Traditional methods usually rely on a single communication technology, such as Wi-Fi or mobile networks. Problems such as unstable signals and transmission interruptions may occur in different transmission environments, and stable data transmission cannot be guaranteed in various scenarios.

[0005] 2. Insufficient data security: Existing telemedicine data transmission methods mostly use basic encryption technologies, such as simple symmetric encryption or asymmetric encryption, which lack multi-level security protection measures and are vulnerable to data leakage and tampering, and cannot fully protect patient privacy and data security.

[0006] 3. Low transmission efficiency: Traditional data transmission methods often lack efficient data preprocessing and compression technology when processing large amounts of medical data, resulting in low data transmission efficiency, occupying a large amount of network bandwidth, increasing transmission delays, and affecting the timeliness and accuracy of diagnostic data.

[0007] 4. Insufficient intelligent analysis capabilities: Existing telemedicine data transmission methods mostly rely on simple data transmission and storage, lack the ability to intelligently analyze and process the transmitted data, and are unable to use advanced artificial intelligence and machine learning technologies for data analysis and diagnostic prediction, affecting the quality and efficiency of telemedicine services.

[0008] Therefore, how to provide a method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform is an urgent problem that technicians in this field need to solve. Summary of the invention

[0009] One object of the present invention is to propose a method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform. The present invention comprehensively applies a variety of communication technologies, data encryption and security mechanisms, efficient data preprocessing technologies and intelligent data analysis and processing technologies, and describes in detail a method for realizing safe, efficient and reliable transmission of diagnostic data in a telemedicine environment. The method has the advantages of high transmission stability, strong security, high transmission efficiency and diagnostic accuracy.

[0010] A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to an embodiment of the present invention is characterized by comprising the following steps:

[0011] S1. Collecting patient diagnostic data through sensors and interfaces configured on medical devices;

[0012] S2. Preprocess the collected diagnostic data, including data cleaning and data compression, to improve data transmission efficiency and reduce network bandwidth occupancy and transmission delay;

[0013] S3. Use short-range wireless communication technology to carry out preliminary data transmission between medical equipment and local data terminals, and use long-range mobile communication technology to transmit data to the regional remote diagnosis and treatment platform;

[0014] S4. During the data transmission process, AES and RSA encryption algorithms are used for data encryption, and two-factor authentication and digital certificate technology are used for identity authentication to improve the security of data transmission;

[0015] S5. After receiving the diagnostic data, the regional remote diagnosis and treatment platform decrypts and authenticates the data and stores the data in a secure database;

[0016] S6. Use convolutional neural networks to analyze image data, use natural language processing technology to process text data, use regression analysis and classification algorithms to predict and classify physiological parameters, and combine deep learning models to perform fusion analysis on multimodal data to provide accurate diagnosis and prediction;

[0017] S7. The analyzed and processed diagnosis results are transmitted back to the local data terminal through long-distance mobile communication technology, and fed back to the medical equipment through short-distance wireless communication technology, thus realizing a closed loop of remote diagnosis and treatment.

[0018] Optionally, the S1 specifically includes:

[0019] S11, collect the patient's physiological parameter data through the multimodal sensor configured on the medical device, and at the same time, multiple physiological parameters P i , and automatically calibrate and synchronize multiple data sources:

[0020]

[0021] Among them, P i is the average value of the ith physiological parameter, S ij is the data value of the i-th physiological parameter at the j-th sampling point, n is the total number of sampling points, and k is the sensor calibration coefficient;

[0022] S12. Medical image data of patients is collected by configuring high-resolution multispectral image sensors on medical equipment. Image sensors can provide clear image data under low light and high-speed motion conditions:

[0023]

[0024] Among them, I k is the original value of the kth image data, I k ' is the standardized value, μ k and σ k are the mean and standard deviation of the kth image data respectively;

[0025] S13. The patient's text data is collected through the intelligent interface module configured on the medical equipment. The interface module supports natural language processing technology, can automatically identify and record the doctor's diagnosis report, medical records and laboratory test results, and can perform real-time speech-to-text and text standardization processing:

[0026]

[0027] Among them, t is a specific word, d is a specific document, and f t,d is the frequency of word t appearing in document d, N is the total number of documents, D is the document set, |{d'∈D:t∈d'}| is the number of documents containing word t;

[0028] S14. Use edge computing-based multi-protocol communication modules to connect sensors and interface modules to local data terminals. These communication modules support 3 protocols and have automatic protocol identification and switching functions:

[0029]

[0030] Among them, R is the data transmission rate, B is the amount of data transmitted, T is the time required for transmission, and P is the packet loss rate that may occur during the transmission process;

[0031] S15. Use dynamic data buffering and verification technology to cache and verify the integrity of real-time data, dynamically adjust the cache size according to network bandwidth and device status, and perform real-time verification of data:

[0032]

[0033] Among them, C is the cache size, R is the data transmission rate, T is the transmission time, N is the number of packets, and ∈ is the cache redundancy factor;

[0034] S16. The collected data is transmitted to the local data terminal in real time through a wireless communication module that supports multi-band communication, and the best communication method is automatically selected according to the environment:

[0035]

[0036] Among them, L is the transmission delay, D is the transmission distance, R is the data transmission rate, λ is the packet arrival rate, and μ is the packet processing rate.

[0037] Optionally, the S2 specifically includes:

[0038] S21. Clean the collected physiological parameter data to remove abnormal values ​​and noise:

[0039] E ij =|S ij -μ i |>k·σ i ;

[0040] Among them, E ij is the abnormal value judgment result of the i-th physiological parameter at the j-th sampling point, S ij is the data value of the ith physiological parameter at the jth sampling point, μ i is the mean value of the ith physiological parameter, σ i is the standard deviation of the ith physiological parameter, k is the set threshold coefficient;

[0041] S22. Preprocessing the collected medical image data, including noise removal and edge enhancement. Gaussian filter is used for noise removal and Sobel operator is used for edge enhancement:

[0042]

[0043] Among them, I k ' is the denoised image data, I k (x+m,y+n) is the original image data, G[m,n] is the Gaussian filter, and σ is the standard deviation of the Gaussian filter;

[0044] S23, cleaning the collected text data:

[0045] SW={w|f(w) <T};

[0046] Among them, SW is the stop word set, w is a specific word, f(w) is the word frequency of word w, and T is the set word frequency threshold;

[0047] S24, using wavelet transform to perform compression processing, and compressing the cleaned physiological parameter data:

[0048]

[0049] Among them, C j is the j-th level wavelet coefficient, x n is the original data, ψ is the wavelet basis function, k is the translation parameter, and N is the number of data points;

[0050] S25, using discrete cosine transform to compress the cleaned medical image data:

[0051]

[0052] Where F(u,v) is the discrete cosine transform coefficient, I(x,y) is the original image data, α(u) and α(v) are normalization coefficients, and N is the size of the image block;

[0053] S26, using Huffman coding to compress the cleaned text data:

[0054]

[0055] Among them, L is the average code length after encoding, p i is the occurrence probability of the ith symbol, and n is the total number of symbols.

[0056] Optionally, the S3 specifically includes:

[0057] S31. Use short-range wireless communication technology to perform preliminary data transmission between medical equipment and local data terminals:

[0058]

[0059] Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission;

[0060] S32. Transmit the preliminary data received by the local data terminal to the regional remote diagnosis and treatment platform through long-distance mobile communication technology:

[0061]

[0062] Among them, R l is the data transmission rate of long-distance mobile communication, B l is the amount of data transmitted, T lis the time required for transmission, P l is the packet loss rate that may occur during transmission;

[0063] S33. During data transmission, a synchronization method based on timestamp is used:

[0064]

[0065] Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet;

[0066] S34, using the automatic retransmission request protocol to retransmit lost or erroneous data packets:

[0067]

[0068] Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted;

[0069] S35. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status:

[0070]

[0071] Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio;

[0072] S36, using a packet data transmission method to split a large data packet into multiple small data packets for transmission:

[0073]

[0074] Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p It is the error rate that may occur during the packet grouping process.

[0075] Optionally, the S4 specifically includes:

[0076] S41. During data transmission, AES and RSA encryption algorithms are used for data encryption:

[0077] C=P⊕EAES (K, IV);

[0078] Among them, C is the encrypted ciphertext, P is the plaintext, and R AES is the AES encryption algorithm, K is the encryption key, IV is the initialization vector, and ⊕ represents the XOR operation;

[0079] S42. Perform RSA encryption on the encrypted data to further enhance the security of data transmission:

[0080] C'=C e n;

[0081] Where C' is the encrypted ciphertext, C is the AES encrypted ciphertext, e is the RSA public key exponent, and n is the RSA modulus.

[0082] S43. Before data transmission, identity authentication is performed using two-factor authentication technology, including static passwords and dynamic verification codes:

[0083] OTP=HMAC(K otp ,T);

[0084] Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K otp is the authentication key, T is the current timestamp;

[0085] S44. Use digital certificate technology to further verify identity:

[0086]

[0087] Among them, Cert sign is the signed digital certificate, H is the hash function, Cert is the digital certificate, d CA is the private key index of the certification authority, n CA is the module of the certification body;

[0088] S45. During data transmission, the transport layer security protocol is used for secure transmission:

[0089] K session =g ab p;

[0090] Among them, K session is the session key, g is the generator, a is the client private key, b is the server private key, and p is the prime modulus;

[0091] S46. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed:

[0092]

[0093] Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, N total is the total number of packets transmitted;

[0094] S47. After the data reaches the regional remote diagnosis and treatment platform, the encrypted data is decrypted. First, the private key is used for RSA decryption:

[0095] C=C' d n;

[0096] Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus;

[0097] S48, then use the AES key to decrypt and restore the original data:

[0098] P=C⊕E AES (K, IV);

[0099] Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, and ⊕ represents the XOR operation.

[0100] Optionally, the S5 specifically includes:

[0101] S51. After receiving the diagnostic data, the regional remote diagnosis and treatment platform first decrypts and authenticates the data:

[0102] C=C' d n;

[0103] Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus;

[0104] S52, then use the AES key to decrypt and restore the original data:

[0105] P=C⊕E AES (K, IV);

[0106] Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, and ⊕ indicates the XOR operation;

[0107] S53, using two-factor authentication technology to verify the user's identity and authenticate the decrypted data:

[0108] OTP=HMAC(K otp ,T);

[0109] Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K opt is the authentication key, T is the current timestamp;

[0110] S54. Use digital certificates to verify user identity:

[0111]

[0112] Among them, V Cert To verify the results, Cert sign is the signed digital certificate, e CA is the public key exponent of the certification authority, n CA is the module of the certification body;

[0113] S55. Store the decrypted and verified data in a secure database:

[0114] D store = {P img ,P text ,P bio};

[0115] Among them, D store is the stored data, P img is the image data, P text For text data, P bio is the physiological parameter data;

[0116] S56. Index and classify the stored data. The indexing process includes assigning a unique identifier ID to each data item:

[0117] ID i =H(P i +T i );

[0118] Among them, ID i is the unique identifier of data item i, H is the hash function, P i is the content of data item i, T i is the timestamp of data item i;

[0119] S57. To ensure data integrity and traceability, back up the stored data:

[0120]

[0121] Among them, F backup is the backup frequency, S data is the data size, R write is the write rate;

[0122] S58. During the data storage process, redundancy technology is used to ensure data reliability. The specific implementation of redundancy technology includes data replication and verification:

[0123]

[0124] Among them, CRC is the cyclic redundancy check code, P i is the data bit, x is the placeholder, and g(x) is the generating polynomial.

[0125] Optionally, the S6 specifically includes:

[0126] S61. Use convolutional neural network to analyze the decrypted image data:

[0127]

[0128] in, is the output after the lth layer of convolution, is the convolution kernel weight of the lth layer, is the input of the l-1th layer, b (l) is the bias of the lth layer, k is the convolution kernel size;

[0129] S62. Use the maximum pooling technique to perform pooling operation on the image data:

[0130]

[0131] in, is the output after pooling at layer l, is the output after the lth layer of convolution, and p is the pooling window size;

[0132] S63, using natural language processing technology to process the decrypted text data, firstly performing word segmentation on the text data:

[0133] W={w1,w2,…,w n};

[0134] Among them, W is the word segmentation result set, w i is the i-th participle, n is the total number of participles;

[0135] S64, then use word embedding technology to represent the word vector of the text data after word segmentation:

[0136]

[0137] Among them, E(w i ) is the word w i The word vector of |D| is the corpus size, For word w i In the document d jThe frequency of occurrence in

[0138] S65. Use regression analysis and classification algorithms to predict and classify the decrypted physiological parameter data:

[0139]

[0140] in, is the predicted value, β0 is the intercept term, β i is the regression coefficient, x i is the independent variable, p is the number of independent variables;

[0141] S66. Use deep learning models to perform fusion analysis on multimodal data:

[0142]

[0143] Among them, O is the output result after fusion, σ is the activation function, α i is the fusion weight, X i is the multimodal input data, and n is the number of input data.

[0144] Optionally, the S7 specifically includes:

[0145] S71. Transmit the analyzed and processed diagnostic results back to the local data terminal via long-distance mobile communication technology:

[0146]

[0147] Among them, R t is the data transmission rate of long-distance mobile communication, B t is the amount of data transmitted, T t is the time required for transmission, P t is the packet loss rate that may occur during transmission;

[0148] S72. During data transmission, a synchronization method based on a timestamp is used:

[0149]

[0150] Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet;

[0151] S73. During data transmission, the automatic retransmission request protocol is used to retransmit lost or erroneous data packets:

[0152]

[0153] Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted;

[0154] S74. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status:

[0155]

[0156] Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio;

[0157] S75, using a packet data transmission method, splitting a large data packet into multiple small data packets for transmission:

[0158]

[0159] Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p is the error rate that may occur during the packet grouping process;

[0160] S76. Feedback the data transmitted back to the local data terminal to the medical device via short-range wireless communication technology:

[0161]

[0162] Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission;

[0163] S77. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed:

[0164]

[0165] Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, N total The total number of packets transmitted.

[0166] The beneficial effects of the present invention are:

[0167] (1) The present invention realizes multi-level transmission of diagnostic data by comprehensively applying multiple communication technologies (such as Wi-Fi, Bluetooth, Zigbee combined with 4G and 5G), ensuring the transmission stability and coverage of data in different scenarios. This multi-level communication method can adapt to different transmission environments, avoiding the signal instability and transmission interruption problems that may be caused by a single communication technology, thereby greatly improving the stability of data transmission.

[0168] (2) The present invention uses advanced encryption algorithms (such as AES, RSA) and identity authentication technologies (such as two-factor authentication, digital certificates) during data transmission, which comprehensively improves the security of data transmission. Through multi-level encryption and identity authentication mechanisms, data leakage and tampering are effectively prevented, ensuring patient privacy and data security.

[0169] (3) The present invention applies efficient data preprocessing technology, including data cleaning and data compression, which improves data transmission efficiency and reduces network bandwidth occupancy and transmission delay. By preprocessing the data, the quality and timeliness of the transmitted data are ensured, thereby improving the accuracy and reliability of remote medical diagnosis.

[0170] (4) The present invention uses artificial intelligence and machine learning technologies (such as convolutional neural networks, natural language processing, regression analysis and classification algorithms, and deep learning models) to intelligently analyze and process data transmitted to the regional remote diagnosis and treatment platform to provide more accurate diagnosis and prediction. Through intelligent data analysis, the quality and efficiency of remote medical services are improved, and more accurate diagnosis results and more timely medical responses are achieved.

[0171] (5) The present invention adopts strict decryption and identity verification steps during data reception and storage to ensure data integrity and traceability. By securely storing and classifying the decrypted and verified data, data security and easy access are ensured, providing a reliable data basis for subsequent diagnostic analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0172] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0173] Figure 1 A schematic diagram of diagnostic data collection and preprocessing of a diagnostic data remote transmission method based on a regional remote diagnosis and treatment platform proposed by the present invention;

[0174] Figure 2 A schematic diagram of data encryption and secure transmission of a diagnostic data remote transmission method based on a regional remote diagnosis and treatment platform proposed by the present invention;

[0175] Figure 3 The present invention provides a schematic diagram of data reception, decryption and storage of a method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform. DETAILED DESCRIPTION

[0176] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0177] refer to Figure 1-Figure 3 A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform, characterized in that it comprises the following steps:

[0178] S1. Collecting patient diagnostic data through sensors and interfaces configured on medical devices;

[0179] In this implementation, S1 specifically includes:

[0180] S11, collect the patient's physiological parameter data through the multimodal sensor configured on the medical device, and at the same time, multiple physiological parameters P i , and automatically calibrate and synchronize multiple data sources:

[0181]

[0182] Among them, P i is the average value of the ith physiological parameter, S ij is the data value of the i-th physiological parameter at the j-th sampling point, n is the total number of sampling points, and k is the sensor calibration coefficient;

[0183] S12. Medical image data of patients is collected by configuring high-resolution multispectral image sensors on medical equipment. Image sensors can provide clear image data under low light and high-speed motion conditions:

[0184]

[0185] Among them, I k is the original value of the kth image data, I k ' is the standardized value, μ k and σ k are the mean and standard deviation of the kth image data respectively;

[0186] S13. The patient's text data is collected through the intelligent interface module configured on the medical equipment. The interface module supports natural language processing technology, can automatically identify and record the doctor's diagnosis report, medical records and laboratory test results, and can perform real-time speech-to-text and text standardization processing:

[0187]

[0188] Among them, t is a specific word, d is a specific document, and f t,d is the frequency of word t appearing in document d, N is the total number of documents, D is the document set, |{d'∈D:t∈d'}| is the number of documents containing word t;

[0189] S14. Use edge computing-based multi-protocol communication modules to connect sensors and interface modules to local data terminals. These communication modules support 3 protocols and have automatic protocol identification and switching functions:

[0190]

[0191] Among them, R is the data transmission rate, B is the amount of data transmitted, T is the time required for transmission, and P is the packet loss rate that may occur during the transmission process;

[0192] S15. Use dynamic data buffering and verification technology to cache and verify the integrity of real-time data, dynamically adjust the cache size according to network bandwidth and device status, and perform real-time verification of data:

[0193]

[0194] Among them, C is the cache size, R is the data transmission rate, T is the transmission time, N is the number of packets, and ∈ is the cache redundancy factor;

[0195] S16. The collected data is transmitted to the local data terminal in real time through a wireless communication module that supports multi-band communication, and the best communication method is automatically selected according to the environment:

[0196]

[0197] Among them, L is the transmission delay, D is the transmission distance, R is the data transmission rate, λ is the packet arrival rate, and μ is the packet processing rate.

[0198] S2. Preprocess the collected diagnostic data, including data cleaning and data compression, to improve data transmission efficiency and reduce network bandwidth occupancy and transmission delay;

[0199] In this implementation, S2 specifically includes:

[0200] S21. Clean the collected physiological parameter data to remove abnormal values ​​and noise:

[0201] E ij =|S ij -μ i |>k·σ i ;

[0202] Among them, E ij is the abnormal value judgment result of the i-th physiological parameter at the j-th sampling point, S ij is the data value of the ith physiological parameter at the jth sampling point, μ i is the mean value of the ith physiological parameter, σ i is the standard deviation of the ith physiological parameter, k is the set threshold coefficient;

[0203] S22. Preprocessing the collected medical image data, including noise removal and edge enhancement. Gaussian filter is used for noise removal and Sobel operator is used for edge enhancement:

[0204]

[0205] Among them, I k ' is the denoised image data, I k (x+m,y+n) is the original image data, G[m,n] is the Gaussian filter, and σ is the standard deviation of the Gaussian filter;

[0206] S23, cleaning the collected text data:

[0207] SW={w|f(w) <T};

[0208] Among them, SW is the stop word set, w is a specific word, f(w) is the word frequency of word w, and T is the set word frequency threshold;

[0209] S24, using wavelet transform to perform compression processing, and compressing the cleaned physiological parameter data:

[0210]

[0211] Among them, C j is the j-th level wavelet coefficient, x n is the original data, ψ is the wavelet basis function, k is the translation parameter, and N is the number of data points;

[0212] S25, using discrete cosine transform to compress the cleaned medical image data:

[0213]

[0214] Where F(u,v) is the discrete cosine transform coefficient, I(x,y) is the original image data, α(u) and α(v) are normalization coefficients, and N is the size of the image block;

[0215] S26, using Huffman coding to compress the cleaned text data:

[0216]

[0217] Among them, L is the average code length after encoding, p i is the occurrence probability of the ith symbol, and n is the total number of symbols.

[0218] S3. Use short-range wireless communication technology to carry out preliminary data transmission between medical equipment and local data terminals, and use long-range mobile communication technology to transmit data to the regional remote diagnosis and treatment platform;

[0219] In this implementation, S3 specifically includes:

[0220] S31. Use short-range wireless communication technology to perform preliminary data transmission between medical equipment and local data terminals:

[0221]

[0222] Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission;

[0223] S32. Transmit the preliminary data received by the local data terminal to the regional remote diagnosis and treatment platform through long-distance mobile communication technology:

[0224]

[0225] Among them, R l is the data transmission rate of long-distance mobile communication, B l is the amount of data transmitted, T l is the time required for transmission, P l is the packet loss rate that may occur during transmission;

[0226] S33. During data transmission, a synchronization method based on timestamp is used:

[0227]

[0228] Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet;

[0229] S34, using the automatic retransmission request protocol to retransmit lost or erroneous data packets:

[0230]

[0231] Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted;

[0232] S35. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status:

[0233]

[0234] Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio;

[0235] S36, using a packet data transmission method to split a large data packet into multiple small data packets for transmission:

[0236]

[0237] Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p It is the error rate that may occur during the packet grouping process.

[0238] S4. During the data transmission process, AES and RSA encryption algorithms are used for data encryption, and two-factor authentication and digital certificate technology are used for identity authentication to improve the security of data transmission;

[0239] In this implementation, S4 specifically includes:

[0240] S41. During data transmission, AES and RSA encryption algorithms are used for data encryption:

[0241] C=P⊕E AES (K, IV);

[0242] Among them, C is the encrypted ciphertext, P is the plaintext, and E AES is the AES encryption algorithm, K is the encryption key, IV is the initialization vector, and ⊕ represents the XOR operation;

[0243] S42. Perform RSA encryption on the encrypted data to further enhance the security of data transmission:

[0244] C'=C e n;

[0245] Where C' is the encrypted ciphertext, C is the AES encrypted ciphertext, e is the RSA public key exponent, and n is the RSA modulus.

[0246] S43. Before data transmission, identity authentication is performed using two-factor authentication technology, including static passwords and dynamic verification codes:

[0247] OTP=HMAC(K otp ,T);

[0248] Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K otp is the authentication key, T is the current timestamp;

[0249] S44. Use digital certificate technology to further verify identity:

[0250]

[0251] Among them, Cert sign is the signed digital certificate, H is the hash function, Cert is the digital certificate, d CA is the private key index of the certification authority, n CA is the module of the certification body;

[0252] S45. During data transmission, the transport layer security protocol is used for secure transmission:

[0253] K session =g ab p;

[0254] Among them, K session is the session key, g is the generator, a is the client private key, b is the server private key, and p is the prime modulus;

[0255] S46. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed:

[0256]

[0257] Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, N total is the total number of packets transmitted;

[0258] S47. After the data reaches the regional remote diagnosis and treatment platform, the encrypted data is decrypted. First, the private key is used for RSA decryption:

[0259] C=C' d n;

[0260] Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus;

[0261] S48, then use the AES key to decrypt and restore the original data:

[0262] P=C⊕E AES (K, IV);

[0263] Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, and ⊕ represents the XOR operation.

[0264] S5. After receiving the diagnostic data, the regional remote diagnosis and treatment platform decrypts and authenticates the data and stores the data in a secure database;

[0265] In this implementation, S5 specifically includes:

[0266] S51. After receiving the diagnostic data, the regional remote diagnosis and treatment platform first decrypts and authenticates the data:

[0267] C=C' d n;

[0268] Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus;

[0269] S52, then use the AES key to decrypt and restore the original data:

[0270] P=C⊕E AES (K, IV);

[0271] Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, and ⊕ indicates the XOR operation;

[0272] S53, using two-factor authentication technology to verify the user's identity and authenticate the decrypted data:

[0273] OTP=RMAC(K otp ,T);

[0274] Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K otp is the authentication key, T is the current timestamp;

[0275] S54. Use digital certificates to verify user identity:

[0276]

[0277] Among them, V Cert To verify the results, Cert sign is the signed digital certificate, e CA is the public key exponent of the certification authority, n CA is the module of the certification body;

[0278] S55. Store the decrypted and verified data in a secure database:

[0279] D store = {P img ,P text ,P bio};

[0280] Among them, D store is the stored data, P img is the image data, P text For text data, P bio is the physiological parameter data;

[0281] S56. Index and classify the stored data. The indexing process includes assigning a unique identifier ID to each data item:

[0282] ID i =H(P i +T i );

[0283] Among them, ID i is the unique identifier of data item i, H is the hash function, P i is the content of data item i, T i is the timestamp of data item i;

[0284] S57. To ensure data integrity and traceability, back up the stored data:

[0285]

[0286] Among them, F backup is the backup frequency, S data is the data size, R write is the write rate;

[0287] S58. During the data storage process, redundancy technology is used to ensure data reliability. The specific implementation of redundancy technology includes data replication and verification:

[0288]

[0289] Among them, CRC is the cyclic redundancy check code, P iis the data bit, x is the placeholder, and g(x) is the generating polynomial.

[0290] S6. Use convolutional neural networks to analyze image data, use natural language processing technology to process text data, use regression analysis and classification algorithms to predict and classify physiological parameters, and combine deep learning models to perform fusion analysis on multimodal data to provide accurate diagnosis and prediction;

[0291] In this implementation, S6 specifically includes:

[0292] S61. Use convolutional neural network to analyze the decrypted image data:

[0293]

[0294] in, is the output after the lth layer of convolution, is the convolution kernel weight of the lth layer, is the input of the l-1th layer, b (l) is the bias of the lth layer, k is the convolution kernel size;

[0295] S62. Use the maximum pooling technique to perform pooling operation on the image data:

[0296]

[0297] in, is the output after pooling at layer l, is the output after the lth layer of convolution, and p is the pooling window size;

[0298] S63, using natural language processing technology to process the decrypted text data, firstly performing word segmentation on the text data:

[0299] W={w1,w2,…,w n};

[0300] Among them, W is the word segmentation result set, w i is the i-th participle, n is the total number of participles;

[0301] S64, then use word embedding technology to represent the word vector of the text data after word segmentation:

[0302]

[0303] Among them, E(w i ) is the word w i The word vector of |D| is the corpus size, For word w i In the document d j The frequency of occurrence in

[0304] S65. Use regression analysis and classification algorithms to predict and classify the decrypted physiological parameter data:

[0305]

[0306] in, is the predicted value, β0 is the intercept term, β i is the regression coefficient, x i is the independent variable, p is the number of independent variables;

[0307] S66. Use deep learning models to perform fusion analysis on multimodal data:

[0308]

[0309] Among them, O is the output result after fusion, σ is the activation function, α i is the fusion weight, X i is the multimodal input data, and n is the number of input data.

[0310] S7. The analyzed and processed diagnosis results are transmitted back to the local data terminal through long-distance mobile communication technology, and fed back to the medical equipment through short-distance wireless communication technology, thus realizing a closed loop of remote diagnosis and treatment.

[0311] In this implementation, S7 specifically includes:

[0312] S71. Transmit the analyzed and processed diagnostic results back to the local data terminal via long-distance mobile communication technology:

[0313]

[0314] Among them, R t is the data transmission rate of long-distance mobile communication, B t is the amount of data transmitted, T t is the time required for transmission, P t is the packet loss rate that may occur during transmission;

[0315] S72. During data transmission, a synchronization method based on a timestamp is used:

[0316]

[0317] Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet;

[0318] S73. During data transmission, the automatic retransmission request protocol is used to retransmit lost or erroneous data packets:

[0319]

[0320] Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted;

[0321] S74. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status:

[0322]

[0323] Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio;

[0324] S75, using a packet data transmission method, splitting a large data packet into multiple small data packets for transmission:

[0325]

[0326] Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p is the error rate that may occur during the packet grouping process;

[0327] S76. Feedback the data transmitted back to the local data terminal to the medical device via short-range wireless communication technology:

[0328]

[0329] Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission;

[0330] S77. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed:

[0331]

[0332] Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, Ntotal The total number of packets transmitted.

[0333] Embodiment 1:

[0334] In order to verify the feasibility of the present invention, the present invention is applied to a telemedicine service platform, aiming to provide high-quality medical services to patients in remote areas. The specific implementation environment is located in the telemedicine center of a large general hospital, which is equipped with advanced medical equipment and data processing facilities to support remote diagnosis and data analysis.

[0335] In a clinic in a remote mountainous area, a patient developed symptoms of heart discomfort and required electrocardiogram (ECG) and blood pressure (BP) monitoring. The clinic was equipped with multimodal sensors and high-resolution image sensors, which transmitted data to a local data terminal via short-range wireless communication technologies such as Wi-Fi and Bluetooth. Subsequently, the data was transmitted to a telemedicine center in the city for analysis and diagnosis via long-range mobile communication technologies such as 4G and 5G.

[0336] First, the clinic collects the patient's physiological parameter data, including ECG and BP, through multimodal sensors. The collected data is transmitted to the local data terminal via Wi-Fi for preliminary processing, including data cleaning and data compression, to improve transmission efficiency. The pre-processed data is transmitted to the telemedicine center via the 4G network. During the data transmission process, the AES encryption algorithm is used for data encryption to ensure the security of the data during transmission. The encrypted data is further protected by RSA encryption, and combined with two-factor authentication and digital certificate technology for identity authentication to prevent data leakage and tampering.

[0337] After receiving the encrypted data, the telemedicine center uses the private key to perform RSA decryption, and then uses the AES key to restore the original data. The decrypted data is analyzed by convolutional neural network (CNN) for image analysis, and natural language processing (NLP) technology is used to process text data. At the same time, regression analysis and classification algorithms are used to predict and classify physiological parameter data, and deep learning models are combined to perform fusion analysis on multimodal data.

[0338] In actual application, the Telemedicine Center tested and analyzed the data of 100 patients, and the results are as follows:

[0339] Table 1 Performance improvement report of telemedicine service platform

[0340] Data Category Before deploying the system After deploying the system Data transmission success rate 85％ 99.2％ Number of data security incidents 5 times / month 0 times Data transmission efficiency 15 minutes / time 10 minutes / time Diagnostic accuracy 88％ 98.5％ Data feedback time 20 minutes / time 5 minutes / time System response speed 10 minutes 2 minutes Data storage reliability 90％ 99.8％

[0341] In a specific application case, a patient was examined in a remote clinic due to sudden heart discomfort. Through the method of the present invention, the collected ECG and BP data were transmitted to the telemedicine center for analysis within 5 minutes. CNN was used to analyze the ECG image, combined with NLP technology to process the patient's medical history records, and regression analysis was used to predict the cardiac risk index. Finally, the telemedicine center fed back the diagnosis results within 10 minutes and recommended that the patient be transferred to another hospital for treatment immediately, successfully avoiding serious cardiac events.

[0342] During the entire implementation process, the system's transmission success rate reached 99.2%, the diagnostic accuracy rate reached 98.5%, the data transmission efficiency increased by about 30%, data security was fully guaranteed, and the patient's medical service experience was significantly improved. It can be seen from these data that the diagnostic data remote transmission method based on the regional remote diagnosis and treatment platform of the present invention not only solves the deficiencies in the prior art, but also significantly improves the overall level and efficiency of remote medical services.

[0343] By implementing the present invention, telemedicine centers can more effectively manage and process large amounts of medical data. The use of multimodal sensors to collect data, as well as efficient data preprocessing and compression technology, makes data transmission more efficient. Compared with traditional methods, data transmission time is significantly reduced and the utilization rate of medical resources is greatly improved. Specifically, in the data preprocessing stage, through data cleaning and compression technology, the average data transmission time is shortened from the original 15 minutes to 10 minutes, and the transmission efficiency is improved by about 30%.

[0344] In terms of data security, the multi-layer encryption and identity authentication mechanism of the present invention significantly improves the security of data transmission. The use of AES and RSA dual encryption algorithms, as well as two-factor authentication and digital certificate technology, ensures the confidentiality and integrity of data during transmission. During the implementation process, no data leakage or tampering incidents occurred, fully protecting the privacy and data security of patients. In addition, the system's real-time monitoring function and automatic retransmission request protocol ensure the integrity and reliability of data transmission, further improving the security performance of the system.

[0345] Through intelligent data analysis and processing technology, the telemedicine center is able to make more accurate diagnoses and predictions. Convolutional neural networks are used to analyze ECG images, natural language processing technology is used to process patient medical history records, regression analysis and classification algorithms are used to predict and classify physiological parameter data, and deep learning models are used to perform fusion analysis on multimodal data. The diagnostic accuracy rate has increased from 88% to 98.5%, significantly improving the reliability and accuracy of the diagnostic results. This improvement not only improves the quality of medical services, but also enhances patients' trust in telemedicine services.

[0346] The system's response speed and feedback time have been significantly improved. In actual applications, the diagnosis results are transmitted back to the local data terminal through long-distance mobile communication technology, and fed back to the medical equipment through short-distance wireless communication technology, realizing a closed loop of remote diagnosis and treatment. The average feedback time has been reduced from 20 minutes to 5 minutes, and the system response speed has been shortened from 10 minutes to 2 minutes, which has greatly improved the response efficiency of medical services, and can provide patients with diagnosis and treatment suggestions in a timely manner, avoiding potential medical risks.

[0347] In addition, the application of data storage and management technology enables the telemedicine center to safely store and manage large amounts of medical data. The integrity and traceability of the data are ensured through decryption and authentication steps. The structured processing and index classification of data storage improves the access speed and management efficiency of data. Throughout the implementation process, the reliability of data storage reached 99.8%, providing a reliable data foundation for subsequent diagnostic analysis.

[0348] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform, characterized in that: The steps include: S1. Collecting patient diagnostic data through sensors and interfaces configured on medical devices; S2. Preprocess the collected diagnostic data, including data cleaning and data compression, to improve data transmission efficiency and reduce network bandwidth occupancy and transmission delay; S3. Use short-range wireless communication technology to carry out preliminary data transmission between medical equipment and local data terminals, and use long-range mobile communication technology to transmit data to the regional remote diagnosis and treatment platform; S4. During data transmission, AES and RSA encryption algorithms are used for data encryption, and two-factor authentication and digital certificate technology are used for identity authentication to improve the security of data transmission; S5. After receiving the diagnostic data, the regional remote diagnosis and treatment platform decrypts and authenticates the data and stores the data in a secure database; S6. Use convolutional neural networks to analyze image data, use natural language processing technology to process text data, use regression analysis and classification algorithms to predict and classify physiological parameters, and combine deep learning models to perform fusion analysis on multimodal data to provide accurate diagnosis and prediction; S7. The analyzed and processed diagnosis results are transmitted back to the local data terminal through long-distance mobile communication technology, and fed back to the medical equipment through short-distance wireless communication technology, thus realizing a closed loop of remote diagnosis and treatment.

2. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 1, characterized in that: The S1 specifically includes: S11, collect the patient's physiological parameter data through the multimodal sensor configured on the medical device, and at the same time, multiple physiological parameters P i , and automatically calibrate and synchronize multiple data sources: Among them, P i is the average value of the ith physiological parameter, S ij is the data value of the i-th physiological parameter at the j-th sampling point, n is the total number of sampling points, and k is the sensor calibration coefficient; S12. Medical image data of patients is collected by configuring high-resolution multispectral image sensors on medical equipment. Image sensors can provide clear image data under low light and high-speed motion conditions: Among them, I k is the original value of the kth image data, I k ' is the standardized value, μ k and σ k are the mean and standard deviation of the kth image data respectively; S13. The patient's text data is collected through the intelligent interface module configured on the medical equipment. The interface module supports natural language processing technology, can automatically identify and record the doctor's diagnosis report, medical records and laboratory test results, and can perform real-time speech-to-text and text standardization processing: Among them, t is a specific word, d is a specific document, and f t,d is the frequency of word t appearing in document d, N is the total number of documents, D is the document set, |{d'∈D:t∈d'}| is the number of documents containing word t; S14. Use edge computing-based multi-protocol communication modules to connect sensors and interface modules to local data terminals. These communication modules support 3 protocols and have automatic protocol identification and switching functions: Among them, R is the data transmission rate, B is the amount of data transmitted, T is the time required for transmission, and P is the packet loss rate that may occur during the transmission process; S15. Use dynamic data buffering and verification technology to cache and verify the integrity of real-time data, dynamically adjust the cache size according to network bandwidth and device status, and perform real-time verification of data: Among them, C is the cache size, R is the data transmission rate, T is the transmission time, N is the number of packets, and ∈ is the cache redundancy factor; S16. The collected data is transmitted to the local data terminal in real time through a wireless communication module that supports multi-band communication, and the best communication method is automatically selected according to the environment: Among them, L is the transmission delay, D is the transmission distance, R is the data transmission rate, λ is the packet arrival rate, and μ is the packet processing rate.

3. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 2, characterized in that: The S2 specifically includes: S21. Clean the collected physiological parameter data to remove abnormal values ​​and noise: E ij =|S ij -m i |>k·s i ; Among them, E ij is the abnormal value judgment result of the i-th physiological parameter at the j-th sampling point, S ij is the data value of the ith physiological parameter at the jth sampling point, μ i is the mean value of the ith physiological parameter, σ i is the standard deviation of the ith physiological parameter, k is the set threshold coefficient; S22. Preprocessing the collected medical image data, including noise removal and edge enhancement. Gaussian filter is used for noise removal and Sobel operator is used for edge enhancement: Among them, I k ' is the denoised image data, I k (x+m,y+n) is the original image data, G[m,n] is the Gaussian filter, and σ is the standard deviation of the Gaussian filter; S23, cleaning the collected text data: SW={w|f(w) <T}; Among them, SW is the stop word set, w is a specific word, f(w) is the word frequency of word w, and T is the set word frequency threshold; S24, using wavelet transform to perform compression processing, and compressing the cleaned physiological parameter data: Among them, C j is the j-th level wavelet coefficient, x n is the original data, ψ is the wavelet basis function, k is the translation parameter, and N is the number of data points; S25, using discrete cosine transform to compress the cleaned medical image data: Where F(u,v) is the discrete cosine transform coefficient, I(x,y) is the original image data, α(u) and α(v) are normalization coefficients, and N is the size of the image block; S26, using Huffmax coding to compress the cleaned text data: Among them, L is the average code length after encoding, p i is the occurrence probability of the ith symbol, and n is the total number of symbols.

4. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 3, characterized in that: The S3 specifically includes: S31. Use short-range wireless communication technology to perform preliminary data transmission between medical equipment and local data terminals: Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission; S32. Transmit the preliminary data received by the local data terminal to the regional remote diagnosis and treatment platform through long-distance mobile communication technology: Among them, R l is the data transmission rate of long-distance mobile communication, B l is the amount of data transmitted, T l is the time required for transmission, P l is the packet loss rate that may occur during transmission; S33. During data transmission, a synchronization method based on timestamp is used: Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet; S34, using the automatic retransmission request protocol to retransmit lost or erroneous data packets: Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted; S35. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status: Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio; S36, using a packet data transmission method to split a large data packet into multiple small data packets for transmission: Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p It is the error rate that may occur during the packet grouping process.

5. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 4, characterized in that: The S4 specifically includes: S41. During data transmission, AES and RSA encryption algorithms are used for data encryption: Among them, C is the encrypted ciphertext, P is the plaintext, and E AES is the AES encryption algorithm, K is the encryption key, IV is the initialization vector, Represents the exclusive OR operation; S42. Perform RSA encryption on the encrypted data to further enhance the security of data transmission: C'=C e n; Where C' is the encrypted ciphertext, C is the AES encrypted ciphertext, e is the RSA public key exponent, and n is the RSA modulus. S43. Before data transmission, identity authentication is performed using two-factor authentication technology, including static passwords and dynamic verification codes: OTP=HMAC(K otp ,T); Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K otp is the authentication key, T is the current timestamp; S44. Use digital certificate technology to further verify identity: Among them, Cert sign is the signed digital certificate, H is the hash function, Cert is the digital certificate, d CA is the private key index of the certification authority, n CA is the module of the certification body; S45. During data transmission, the transport layer security protocol is used for secure transmission: K session =g ab p; Among them, K session is the session key, g is the generator, a is the client private key, b is the server private key, and p is the prime modulus; S46. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed: Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, N total is the total number of packets transmitted; S47. After the data reaches the regional remote diagnosis and treatment platform, the encrypted data is decrypted. First, the private key is used for RSA decryption: C=C' d n; Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus; S48, then use the AES key to decrypt and restore the original data: Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, Represents the exclusive OR operation.

6. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 5, characterized in that: The S5 specifically includes: S51. After receiving the diagnostic data, the regional remote diagnosis and treatment platform first decrypts and authenticates the data: C=C' d n; Where C is the decrypted AES ciphertext, C' is the RSA encrypted ciphertext, d is the RSA private key exponent, and n is the RSA modulus; S52, then use the AES key to decrypt and restore the original data: Among them, P is the decrypted plaintext, C is the ciphertext after AES encryption, and E AES is the AES encryption algorithm, K is the decryption key, IV is the initialization vector, Shows XOR operation; S53, using two-factor authentication technology to verify the user's identity and authenticate the decrypted data: OTP=HMAC(K otp ,T); Among them, OTP is a one-time password, HMAC is a hash message authentication code function, K otp is the authentication key, T is the current timestamp; S54. Use digital certificates to verify user identity: Among them, V Cert To verify the results, Cert sign is the signed digital certificate, e CA is the public key exponent of the certification authority, n CA is the module of the certification body; S55. Store the decrypted and verified data in a secure database: D store ={P img ,P text ,P bio }; Among them, D store is the stored data, P img is the image data, P text For text data, P bio is the physiological parameter data; S56. Index and classify the stored data. The indexing process includes assigning a unique identifier ID to each data item: ID i =H(P i +T i ); Among them, ID i is the unique identifier of data item i, H is the hash function, P i is the content of data item i, T i is the timestamp of data item i; S57. To ensure data integrity and traceability, back up the stored data: Among them, F backup is the backup frequency, S data is the data size, R write is the write rate; S58. During the data storage process, redundancy technology is used to ensure data reliability. The specific implementation of redundancy technology includes data replication and verification: Among them, CRC is the cyclic redundancy check code, P i is the data bit, x is the placeholder, and g(x) is the generating polynomial.

7. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 6, characterized in that: The S6 specifically includes: S61. Use convolutional neural network to analyze the decrypted image data: in, is the output after the lth layer of convolution, is the convolution kernel weight of the lth layer, is the input of the l-1th layer, b (l) is the bias of the lth layer, k is the convolution kernel size; S62. Use the maximum pooling technique to perform pooling operation on the image data: in, is the output after pooling at layer l, is the output after the lth layer of convolution, and p is the pooling window size; S63, using natural language processing technology to process the decrypted text data, firstly performing word segmentation on the text data: In={in1,in2,…,in n }; Among them, W is the word segmentation result set, w i is the i-th participle, n is the total number of participles; S64, then use word embedding technology to represent the word vector of the text data after word segmentation: Among them, E(w i ) is the word w i The word vector of |D| is the corpus size, For word w i In the document d j The frequency of occurrence in S65. Use regression analysis and classification algorithms to predict and classify the decrypted physiological parameter data: in, is the predicted value, β0 is the intercept term, β i is the regression coefficient, x i is the independent variable, p is the number of independent variables; S66. Use deep learning models to perform fusion analysis on multimodal data: Among them, O is the output result after fusion, σ is the activation function, α i is the fusion weight, X i is the multimodal input data, and n is the number of input data.

8. A method for remote transmission of diagnostic data based on a regional remote diagnosis and treatment platform according to claim 7, characterized in that: The S7 specifically includes: S71. Transmit the analyzed and processed diagnostic results back to the local data terminal via long-distance mobile communication technology: Among them, R t is the data transmission rate of long-distance mobile communication, B t is the amount of data transmitted, T t is the time required for transmission, P t is the packet loss rate that may occur during transmission; S72. During data transmission, a synchronization method based on a timestamp is used: Among them, T sync is the timestamp after synchronization, T start is the initial timestamp, Δt is the data transmission delay, δ is the network jitter, and the synchronous transmission of data is achieved through the correction of the timestamp and transmission delay of the data packet; S73. During data transmission, the automatic retransmission request protocol is used to retransmit lost or erroneous data packets: Among them, N r is the number of retransmissions, P t is the total number of packets, P s is the number of packets successfully transmitted; S74. In the process of long-distance mobile communication, adaptive coding and modulation technology is used to adjust the data transmission rate according to the channel status: Among them, R acm is the data transmission rate after adaptive coding modulation, R max is the maximum data transmission rate, BER is the channel bit error rate, and SNR is the signal-to-noise ratio; S75, using a packet data transmission method, splitting a large data packet into multiple small data packets for transmission: Among them, B p is the size of each data packet, B is the total amount of data, N p is the total number of packets, E p is the error rate that may occur during the packet grouping process; S76. Feedback the data transmitted back to the local data terminal to the medical device via short-range wireless communication technology: Among them, R s is the data transmission rate of short-range wireless communication, B s is the amount of data transmitted, T s is the time required for transmission, P s is the packet loss rate that may occur during transmission; S77. During data transmission, real-time monitoring of the transmission status is performed, and alarms and processing of abnormal situations are performed: Among them, S is the transmission success rate, N success is the number of packets successfully transmitted, N total The total number of packets transmitted.

Images