Gastric cancer early screening data synchronization and optimization method and system

Abstract

The invention relates to the technical field of medical data processing, in particular to a stomach cancer early screening data synchronization and optimization method and system. Mapping the gastric cancer early screening data features into discrete codes of a magnetic domain array; triggering directional displacement of the magnetic domain wall by regulating and controlling pulse width and intensity, so that the discrete code is converted into a magnetic domain wall position sequence; importing real-time magnetic resistance change data after magnetic domain wall displacement into a frequency modulation parameter prediction model to obtain a frequency modulation parameter; generating a frequency modulation electromagnetic wave signal by using the frequency modulation parameter, and transmitting a discrete code to a target receiving end based on the frequency modulation electromagnetic wave signal; and decoding the discrete code received by the target receiving end through the relevance between the reverse mapping magnetic domain wall displacement sequence and the coding mode, optimizing the decoded detection data, and synchronizing the decoded detection data to the heterogeneous medical database node. According to the invention, timely and reliable detection data support is provided for doctors and patients, and efficient management and sharing of gastric cancer early screening data are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and particularly to a method and system for synchronizing and optimizing gastric cancer early screening data. Background Art

[0002] In the field of gastric cancer data, the real-time synchronization and optimization of data are crucial for improving the diagnostic efficiency and the treatment effect of patients. However, in the prior art, the transmission and synchronization of gastric cancer early screening data still face many challenges, such as limited data transmission bandwidth, insufficient real-time performance, and difficulty in ensuring data integrity and security. Traditional data transmission methods mostly rely on digital signal processing and radio frequency communication technologies, which have problems such as high energy consumption, large latency, and susceptibility to interference, and are difficult to meet the requirements of high precision, low latency, and high security in medical scenarios. In addition, the data synchronization efficiency between heterogeneous medical database nodes is low, and there is a lack of a unified data verification and optimization mechanism, resulting in doctors and patients being difficult to obtain accurate test results in a timely manner. To solve these problems, there is an urgent need for an innovative data synchronization and optimization method that can break through the limitations of traditional technologies and achieve efficient, secure, and real-time transmission and synchronization of gastric cancer early screening data. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method and system for synchronizing and optimizing gastric cancer early screening data.

[0004] The technical solution adopted by the present invention to achieve the above object is as follows: In a first aspect of the present invention, a method for synchronizing and optimizing gastric cancer early screening data is disclosed, including the following steps: Obtain gastric cancer early screening data, and map the characteristics of the gastric cancer early screening data into discrete encodings of a magnetic domain array; Apply a spin-polarized current pulse to the magnetic domain array, and trigger the directional displacement of magnetic domain walls by regulating the pulse width and intensity, so that the discrete encodings are converted into a magnetic domain wall position sequence; Import the real-time magnetoresistance change data after the displacement of the magnetic domain walls into a frequency modulation parameter prediction model to obtain frequency modulation parameters; Generate a frequency-modulated electromagnetic wave signal by using the frequency modulation parameters, and transmit the discrete encodings to a target receiving end based on the frequency-modulated electromagnetic wave signal; Decode the discrete encodings received by the target receiving end by inversely mapping the correlation between the magnetic domain wall displacement sequence and the coding mode, and synchronize the optimized detected data to heterogeneous medical database nodes.

[0005] Preferably, mapping the characteristics of the gastric cancer early screening data into discrete encodings of a magnetic domain array specifically includes: Extract features from the early gastric cancer screening data collected by the detection device to obtain key pathological features, including tumor marker concentrations, tissue morphology parameters, and nuclear atypia indicators, and quantify each feature into a multi-dimensional feature vector; Allocate magnetic domain units according to the dimensions and weights of the feature vectors. Each magnetic domain unit corresponds to a feature component, and the normalized range of the feature values is represented by the initial position of the magnetic domain wall to form the topological structure of the magnetic domain array; Based on the spatial distribution relationship of the feature vectors, map the correlation between the feature vectors to the adjacency of the magnetic domain wall displacement; Generate a pulse sequence according to the dynamic changes of the feature vectors and in combination with the timing control module of the spin-polarized current pulse. Drive the magnetic domain wall to displace along a preset planned path based on the pulse sequence to form a discrete code corresponding to the feature vector one by one.

[0006] Preferably, trigger the directional displacement of the magnetic domain wall by regulating the pulse width and intensity to convert the discrete code into a magnetic domain wall position sequence. Specifically: Calculate the displacement distance required for each magnetic domain wall according to the initial position and the target position of the magnetic domain wall, and determine the corresponding current pulse parameter range based on the magnetization characteristics of the magnetic domain material; Map the displacement distance required for each magnetic domain wall to a combination of pulse width and intensity to form pulse parameters, ensuring that the pulse energy can overcome the pinning effect of the magnetic domain wall but will not cause unexpected displacement; Generate a displacement sequence according to the priority order of the magnetic domain wall displacement, and control each magnetic domain wall to move to the target position according to the displacement sequence and the pulse parameters; Monitor the displacement state of the magnetic domain wall through the real-time feedback module, and use the output signal of the magnetoresistive sensor to judge whether each magnetic domain wall reaches the target position. If not, dynamically adjust the subsequent pulse parameters; After all magnetic domain wall displacements are completed, generate a magnetic domain wall position sequence corresponding to the discrete code.

[0007] Preferably, monitor the displacement state of the magnetic domain wall through the real-time feedback module, and use the output signal of the magnetoresistive sensor to judge whether each magnetic domain wall reaches the target position. If not, dynamically adjust the subsequent pulse parameters. Specifically: Integrate a magnetoresistive sensor network in the magnetic domain array to collect the magnetic field strength change signals of each magnetic domain wall in real time, and convert the signals into digital displacement position data; Calculate the remaining displacement distance of the magnetic domain wall based on the difference between the target position and the current displacement position data; Generate an adjustment scheme for the pulse parameters according to the remaining displacement distance, including an optimized combination of pulse width, intensity, and application time interval; Execute the adjusted pulse parameters through the pulse generator and synchronously update the monitoring frequency of the magnetoresistive sensor; After the magnetic domain wall reaches the target position, the verification module is triggered to verify the displacement result. If a deviation is found, the remaining displacement distance is recalculated and the adjustment process is restarted until all magnetic domain walls accurately reach the target position.

[0008] Preferably, the steps for constructing the frequency modulation parameter prediction model are as follows: Collect historical magnetoresistance change data and corresponding frequency modulation parameters to construct a training data set; among them, the historical magnetoresistance change data includes the historical magnetoresistance change amount and the magnetoresistance change rate. Each magnetic domain unit in the magnetic domain array is represented as a graph node, and the magnetic domain wall displacement path is represented as an edge. The node features include the magnetoresistance change amount, change rate, and displacement direction, and the edge features include the displacement distance and time interval; complete the construction process of the basic framework of the graph neural network model. Extract the local magnetoresistance change pattern by aggregating the feature information of adjacent nodes, and dynamically adjust the node weights in combination with the attention mechanism to capture the influence of key magnetic domain wall displacements on the overall coding pattern; complete the design process of the graph convolutional layer of the graph neural network model. Input the time series data of the historical magnetoresistance change amount and change rate into the graph neural network to extract the dynamic features in the time dimension, ensuring that the model can capture the trend and fluctuation of the magnetoresistance change; complete the design process of the temporal convolutional layer of the graph neural network model. Fuse the output features of the graph convolutional layer and the temporal convolutional layer, and map the features to the frequency offset and modulation depth through a fully connected network; complete the design process of the frequency modulation parameter prediction layer of the graph neural network model. Train the graph neural network model based on the training data set, adjust the network parameters using an adaptive optimization algorithm, and evaluate the prediction accuracy of the graph neural network model through cross-validation until the prediction accuracy of the graph neural network model reaches the prediction requirement to obtain the frequency modulation parameter prediction model.

[0009] Preferably, import the real-time magnetoresistance change data after the magnetic domain wall displacement into the frequency modulation parameter prediction model to obtain the frequency modulation parameters, specifically: Use the magnetoresistance sensor array to monitor the magnetoresistance value at a preset time interval after the magnetic domain wall displacement in real time, and calculate the real-time magnetoresistance change data based on the magnetoresistance value at a preset time interval after the magnetic domain wall displacement, including the real-time magnetoresistance change amount and the magnetoresistance change rate. Input the real-time magnetoresistance change data into the frequency modulation parameter prediction model to obtain the frequency offset and modulation depth at a preset future moment. Generate the frequency modulation parameters at a preset future moment according to the frequency offset and modulation depth at the preset future moment.

[0010] Preferably, a frequency-modulated electromagnetic wave signal is generated using the frequency modulation parameter, and the discrete coding is transmitted to the target receiving end based on the frequency-modulated electromagnetic wave signal, specifically as follows: Input the frequency modulation parameter into the magnetoelectric coupling antenna, and utilize the inverse magnetoelectric effect of the magnetoelectric composite material to convert the frequency offset and modulation depth into the frequency and amplitude changes of the electromagnetic wave, thereby generating a frequency-modulated electromagnetic wave signal; Through the beamforming technology of the magnetoelectric coupling antenna, the frequency-modulated electromagnetic wave signal is focused and transmitted in a preset direction at a preset future moment, and the transmission discrete coding is sent to the target receiving end in the form of an electromagnetic wave.

[0011] Preferably, by reversing the mapping of the relationship between the magnetic domain wall displacement sequence and the coding pattern, the discrete coding received by the target receiving end is decoded, and the decoded detection data is optimized and then synchronized to the heterogeneous medical database node, specifically as follows: Capture the frequency-modulated electromagnetic wave signal through a magnetoresistive sensor array, and utilize the quantum tunneling effect to convert the frequency and amplitude changes of the electromagnetic wave into an electrical signal; Reverse map the frequency offset and modulation depth in the frequency-modulated electromagnetic wave signal into the magnetoresistance change amount and change rate, and reconstruct the magnetic domain wall displacement sequence in combination with the initial state of the magnetic domain array; Restore the displacement sequence to the original coding pattern according to the relationship between the magnetic domain wall displacement sequence and the discrete coding pattern; Analyze the characteristic components in the original coding pattern into the key pathological features of the early gastric cancer screening data, including the concentration of tumor markers, tissue morphology parameters, and nuclear atypia indicators, and generate structured data; Bind the generated structured data to the patient identity identifier, and after verifying and optimizing the data integrity through the blockchain hash chain, dynamically synchronize it to the heterogeneous medical database node.

[0012] Preferably, bind the generated structured data to the patient identity identifier, and after verifying and optimizing the data integrity through the blockchain hash chain, dynamically synchronize it to the heterogeneous medical database node, specifically as follows: Uniquely bind the decoded early gastric cancer screening data to the patient identity identifier to generate a data-identity association pair, and calculate the unique hash value of the association pair through a hash function; Write the hash value into the blockchain as a transaction record, and utilize the immutability of the distributed ledger to ensure the authenticity and traceability of the data source; Deploy a data verification contract in the blockchain network, verify the data integrity by comparing the hash values, and trigger the data retransmission process if the verification fails; Optimize the compression and indexing of the structured data according to the storage characteristics and query requirements of the heterogeneous medical database node; Allocate the optimized data to the corresponding heterogeneous medical database nodes so that doctors and patients can access the latest test data in a timely manner.

[0013] The second aspect of the present invention discloses a system for synchronizing and optimizing gastric cancer early screening data. The system for synchronizing and optimizing gastric cancer early screening data includes a memory and a processor. A program for the method of synchronizing and optimizing gastric cancer early screening data is stored in the memory. When the program for the method of synchronizing and optimizing gastric cancer early screening data is executed by the processor, the steps of any of the methods of synchronizing and optimizing gastric cancer early screening data are implemented.

[0014] The present invention solves the technical defects in the background art and has the following beneficial effects: By mapping the characteristics of gastric cancer early screening data into discrete encodings of magnetic domain arrays and using spin-polarized current pulses to trigger the directional displacement of magnetic domain walls, the present invention realizes efficient encoding and transmission of data, improves the real-time performance and accuracy of data transmission. At the same time, through the combination of a frequency modulation parameter prediction model and a frequency-modulated electromagnetic wave signal, low-power and high-bandwidth wireless transmission is ensured. In addition, through reverse mapping and decoding technologies, combined with the dynamic synchronization mechanism of heterogeneous medical database nodes, timely and reliable test data support is provided for doctors and patients, realizing the efficient management and sharing of gastric cancer early screening data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 It is an overall method flowchart of a method for synchronizing and optimizing gastric cancer early screening data; Figure 2 It is a partial method flow of a method for synchronizing and optimizing gastric cancer early screening data; Figure 3 It is a system block diagram of a system for synchronizing and optimizing gastric cancer early screening data. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0018] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited by the specific embodiments disclosed below.

[0019] As Figure 1 shown, a method for synchronizing and optimizing gastric cancer early screening data according to a first aspect of the present invention includes the following steps: S102. Obtain gastric cancer early screening data, and map the characteristics of the gastric cancer early screening data to discrete encodings of a magnetic domain array; S104. Apply a spin-polarized current pulse to the magnetic domain array, and trigger the directional displacement of magnetic domain walls by regulating the pulse width and intensity, so that the discrete encodings are converted into a magnetic domain wall position sequence; S106. Import the real-time magnetoresistance change data after the magnetic domain wall displacement into a frequency modulation parameter prediction model to obtain frequency modulation parameters; S108. Generate a frequency-modulated electromagnetic wave signal by using the frequency modulation parameters, and transmit the discrete encodings to a target receiving end based on the frequency-modulated electromagnetic wave signal; S110. Decode the discrete encodings received by the target receiving end by inversely mapping the correlation between the magnetic domain wall displacement sequence and the coding mode, and synchronize the optimized detected data to heterogeneous medical database nodes after decoding.

[0020] It should be noted that the present invention maps the characteristics of gastric cancer early screening data to discrete encodings of a magnetic domain array, and uses a spin-polarized current pulse to trigger the directional displacement of magnetic domain walls, realizing efficient encoding and transmission of data, improving the real-time performance and accuracy of data transmission. At the same time, through the combination of a frequency modulation parameter prediction model and a frequency-modulated electromagnetic wave signal, low-power and high-bandwidth wireless transmission is ensured. In addition, through inverse mapping and decoding techniques, combined with the dynamic synchronization mechanism of heterogeneous medical database nodes, timely and reliable detected data support is provided for doctors and patients, realizing efficient management and sharing of gastric cancer early screening data.

[0021] Preferably, mapping the characteristics of gastric cancer early screening data to discrete encodings of a magnetic domain array, as Figure 2 shown, specifically: S202. Perform feature extraction processing on the gastric cancer early screening data collected by the detection device to obtain key pathological features, including tumor marker concentration, tissue morphology parameters, and nuclear atypia indexes, and quantify each feature into a multi-dimensional feature vector; Exemplarily, real-time image data of gastric tissue is acquired by an endoscopic imaging device, and a computer vision algorithm is used to identify the lesion area and extract tissue morphological parameters, including lesion size, edge regularity, and surface texture features; tumor marker concentration analysis is performed on the lesion area through immunofluorescence detection technology to obtain the expression levels of key indicators such as CEA (carcinoembryonic antigen), CA19-9 (carbohydrate antigen 19-9), and HER2 (human epidermal growth factor receptor 2); karyotype analysis is performed on the lesion cells using a high-power microscope to extract nuclear atypia indicators, including nuclear size, nuclear shape, and chromatin distribution characteristics.

[0022] S204. Magnetic domain units are allocated according to the dimension and weight of the feature vector. Each magnetic domain unit corresponds to a feature component, and the normalized range of the eigenvalue is represented by the initial position of the magnetic domain wall to form the topological structure of the magnetic domain array. S206. Based on the spatial distribution relationship of the feature vectors, the correlation between the feature vectors is mapped to the adjacency of the magnetic domain wall displacement. It should be noted that the key pathological features of the early gastric cancer screening data extracted (such as tumor marker concentration, tissue morphological parameters, and nuclear atypia indicators) are quantified into multi-dimensional feature vectors, where each feature component corresponds to a magnetic domain unit. The spatial position and size of the magnetic domain units are allocated according to the weights of the respective feature components. Feature components with weights higher than the preset weight threshold are allocated to the central region of the magnetic domain array, otherwise to the edge region. The normalized range of the eigenvalue is represented by the initial position of the magnetic domain wall. For example, the normalized value of the tumor marker concentration is mapped to the initial offset of the magnetic domain wall within the magnetic domain unit, and the tissue morphological parameters are mapped to the initial angle of the magnetic domain wall. Finally, based on the spatial distribution relationship of the feature vectors, the topological structure of the magnetic domain array is constructed to ensure that features have adjacent magnetic domain units in the magnetic domain array, providing a basis for subsequent magnetic domain wall displacement path planning.

[0023] S208. According to the dynamic changes of the feature vector and in combination with the timing control module of the spin-polarized current pulse, a pulse sequence is generated, and based on the pulse sequence, the magnetic domain wall is driven to displace along a preset planned path to form a discrete code corresponding one-to-one to the feature vector.

[0024] It should be noted that the dynamic changes of the feature vector refer to the process in which during the early gastric cancer screening, as the detection device monitors and analyzes the gastric tissue in real time, the key pathological features (such as tumor marker concentration, tissue morphological parameters, and nuclear atypia indicators) are updated with changes in time or spatial position. For example, the tumor marker concentration may fluctuate due to the activity of the lesion, the tissue morphological parameters may change due to the expansion or contraction of the lesion edge, and the nuclear atypia indicators may be adjusted due to cell division or apoptosis.

[0025] It should be noted that according to the change of the eigenvector, the timing control module will calculate the position and moving speed of the magnetic domain wall that needs to be moved, then generate a string of "current pulse signals" and send a "movement instruction" to the magnetic domain wall. The width and intensity of these pulse signals will precisely control the displacement of the magnetic domain wall to ensure that the magnetic domain wall moves along the planned path, and finally convert the dynamic change of the eigenvector into a displacement sequence in the magnetic domain array. In this way, the change of the early gastric cancer screening data can be encoded into the magnetic domain array in real time and accurately, providing support for subsequent data transmission and synchronization.

[0026] In summary, this method realizes the efficient compression and structured representation of data by mapping the features of early gastric cancer screening data to the discrete coding of the magnetic domain array. At the same time, it uses the physical characteristics of the magnetic domain wall displacement to dynamically transform the eigenvector into a coding mode, improving the real-time performance and accuracy of data transmission, and laying a foundation for subsequent low-power and high-bandwidth wireless transmission.

[0027] Preferably, by regulating the pulse width and intensity to trigger the directional displacement of the magnetic domain wall, the discrete coding is converted into a magnetic domain wall position sequence, specifically: According to the initial position and target position of the magnetic domain wall, calculate the displacement distance required for each magnetic domain wall, and determine the corresponding current pulse parameter range based on the magnetization characteristics of the magnetic domain material (such as coercivity, magnetic anisotropy constant); Map the displacement distance required for each magnetic domain wall to a combination of pulse width and intensity to form pulse parameters, ensuring that the pulse energy can overcome the pinning effect of the magnetic domain wall but will not cause unexpected displacement; Exemplarily, when the magnetic domain wall needs to move a large distance quickly, for example, from the initial position A to the target position B, the displacement distance is 10 nanometers, a pulse combination of high intensity and short width is used. For example, the pulse intensity is set to 100 milliamperes and the pulse width is 1 nanosecond. The high-energy pulse quickly overcomes the pinning effect of the magnetic domain wall to achieve rapid displacement. When the magnetic domain wall needs to move a small distance precisely, for example, from the initial position C to the target position D, the displacement distance is 2 nanometers, a pulse combination of low intensity and long width is used. For example, the pulse intensity is set to 20 milliamperes and the pulse width is 10 nanoseconds. The low-energy pulse realizes the fine control of the magnetic domain wall to ensure the displacement accuracy.

[0028] Generate a displacement sequence according to the priority order of the magnetic domain wall displacement, and control each magnetic domain wall to move along the target position according to the displacement sequence and pulse parameters; Monitor the displacement state of the magnetic domain wall through the real-time feedback module, and use the output signal of the magnetoresistive sensor to judge whether each magnetic domain wall reaches the target position. If not, dynamically adjust the subsequent pulse parameters; After all magnetic domain wall displacements are completed, generate a magnetic domain wall position sequence corresponding to the discrete coding.

[0029] Among them, the magnetic domain wall position sequence refers to the conversion of the discrete coding pattern of early gastric cancer screening data into the specific position distribution of magnetic domain walls in a magnetic domain array through the directional displacement of magnetic domain walls. The position of each magnetic domain wall corresponds to a characteristic component in the coding pattern, such as tumor marker concentration, tissue morphology parameters, or nuclear atypia index. Its displacement path and final position reflect the dynamic changes of the feature vector. Through this position sequence, the discrete coding pattern can be stored and represented in physical form in the magnetic domain array, providing a basis for subsequent magnetoresistance change detection, frequency modulation electromagnetic wave signal generation, and data transmission.

[0030] In summary, through precise regulation of the width and intensity of the spin-polarized current pulse, this method realizes the directional displacement of magnetic domain walls, efficiently converts discrete coding into magnetic domain wall position sequences, thereby ensuring the accuracy and controllability of magnetic domain wall displacement and avoiding the occurrence of unexpected displacements.

[0031] Preferably, the displacement state of the magnetic domain wall is monitored by a real-time feedback module. The output signal of the magnetoresistive sensor is used to determine whether each magnetic domain wall reaches the target position. If not, the subsequent pulse parameters are dynamically adjusted. Specifically: Integrate a magnetoresistive sensor network in the magnetic domain array to collect the magnetic field intensity change signals of each magnetic domain wall in real time and convert the signals into digital displacement position data; Based on the difference between the target position and the current displacement position data, calculate the remaining displacement distance of the magnetic domain wall; Generate an adjustment scheme for pulse parameters according to the remaining displacement distance, including an optimized combination of pulse width, intensity, and application time interval; Execute the adjusted pulse parameters through a pulse generator and synchronously update the monitoring frequency of the magnetoresistive sensor; After the magnetic domain wall reaches the target position, trigger the verification module to verify the displacement result. If a deviation is found, recalculate the remaining displacement distance and restart the adjustment process until all magnetic domain walls accurately reach the target position.

[0032] It should be noted that based on the difference between the target position and the current displacement position data, the remaining displacement distance of the magnetic domain wall is calculated. For example, the remaining displacement distance is 5 nanometers. According to the remaining displacement distance and the dynamic response characteristics of the magnetic domain material, an optimized combination of pulse parameters is generated. Specifically, for a larger remaining displacement distance (such as 5 nanometers), a pulse combination with high intensity and short width is used. For example, the pulse intensity is set to 80 milliamperes, the pulse width is 2 nanoseconds, and the application time interval is 5 nanoseconds to quickly complete the displacement. For a smaller remaining displacement distance (such as 1 nanometer), a pulse combination with low intensity and long width is used. For example, the pulse intensity is set to 20 milliamperes, the pulse width is 10 nanoseconds, and the application time interval is 20 nanoseconds to achieve precise control. Then, the adjusted pulse parameters are executed by a pulse generator, and the monitoring frequency of the magnetoresistive sensor is synchronously updated to ensure real-time monitoring of the displacement process. Finally, after the magnetic domain wall reaches the target position, the verification module is triggered to verify the displacement result. If a deviation is found, the remaining displacement distance is recalculated and the adjustment process is restarted until all magnetic domain walls accurately reach the target position.

[0033] In summary, this method dynamically monitors the displacement state of the magnetic domain wall through a real-time feedback module and combines the output signal of the magnetoresistive sensor to achieve precise control and real-time adjustment of the magnetic domain wall displacement process.

[0034] Preferably, the steps for constructing the frequency modulation parameter prediction model are as follows: Collect historical magnetoresistance change data and corresponding frequency modulation parameters to construct a training data set. Among them, the historical magnetoresistance change data includes the historical magnetoresistance change amount and the magnetoresistance change rate. Each magnetic domain unit in the magnetic domain array is represented as a graph node, and the magnetic domain wall displacement path is represented as an edge. The node features include the magnetoresistance change amount, change rate, and displacement direction, and the edge features include the displacement distance and time interval. The basic framework construction process of the graph neural network model is completed. Extract the local magnetoresistance change pattern by aggregating the feature information of adjacent nodes, and dynamically adjust the node weights in combination with the attention mechanism to capture the impact of key magnetic domain wall displacements on the overall coding pattern. The graph convolution layer design process of the graph neural network model is completed. It should be noted that in the graph convolutional layer, each magnetic domain unit is taken as a node, and its adjacent nodes are neighbors. Through the message passing mechanism, the feature information of neighbor nodes is aggregated, including the magnetoresistance change amount, change rate, and displacement direction, to form a local magnetoresistance change pattern. The attention mechanism is introduced to calculate the influence weight of each neighbor node on the current node. The weight value is dynamically adjusted based on the correlation of node features and the adjacency of displacement paths to ensure that nodes with high correlation contribute more to the local pattern. Then, the aggregated feature information is combined with the attention weights, and the updated features of the current node are generated through a non-linear activation function to capture the influence of key magnetic domain wall displacements on the overall coding pattern. Finally, the updated node features are output to the next layer to complete the design process of the graph convolutional layer.

[0035] Input the time series data of historical magnetoresistance change amount and change rate into the graph neural network to extract dynamic features in the time dimension, ensuring that the model can capture the trends and fluctuations of magnetoresistance changes; complete the design process of the temporal convolutional layer of the graph neural network model; Fuse the output features of the graph convolutional layer and the temporal convolutional layer, and map the features to the frequency offset and modulation depth through a fully connected network; complete the design process of the frequency modulation parameter prediction layer of the graph neural network model; Train the graph neural network model based on the training data set, adjust the network parameters using an adaptive optimization algorithm, and evaluate the prediction accuracy of the graph neural network model through cross-validation until the prediction accuracy of the graph neural network model meets the prediction requirements to obtain the frequency modulation parameter prediction model.

[0036] In summary, through the construction of a frequency modulation parameter prediction model based on a graph neural network, this method can efficiently capture the local patterns and time dynamic features of magnetoresistance changes, and combined with the attention mechanism and feature fusion technology, it realizes the accurate prediction of frequency offset and modulation depth.

[0037] Preferably, import the real-time magnetoresistance change data after magnetic domain wall displacement into the frequency modulation parameter prediction model to obtain the frequency modulation parameters, specifically: Use a magnetoresistance sensor array to monitor the magnetoresistance value at a preset time interval after magnetic domain wall displacement in real time, and calculate the real-time magnetoresistance change data based on the magnetoresistance value at a preset time interval after magnetic domain wall displacement, including the real-time magnetoresistance change amount and magnetoresistance change rate; Input the real-time magnetoresistance change data into the frequency modulation parameter prediction model to obtain the frequency offset and modulation depth at a preset future moment; Generate the frequency modulation parameters at a preset future moment according to the frequency offset and modulation depth at the preset future moment.

[0038] In summary, by importing the real-time magnetoresistance change data after the magnetic domain wall displacement into the frequency modulation parameter prediction model, this method can dynamically predict the frequency offset and modulation depth at future moments, thereby generating accurate frequency modulation parameters, ensuring the real-time performance and reliability of early gastric cancer screening data during synchronous transmission.

[0039] Preferably, a frequency-modulated electromagnetic wave signal is generated using the frequency modulation parameters, and the discrete coding is transmitted to the target receiving end based on the frequency-modulated electromagnetic wave signal. Specifically: The frequency modulation parameters are input into a magnetoelectric coupling antenna, and the inverse magnetoelectric effect of the magnetoelectric composite material is used to convert the frequency offset and modulation depth into changes in the frequency and amplitude of the electromagnetic wave, generating a frequency-modulated electromagnetic wave signal; Through the beamforming technology of the magnetoelectric coupling antenna, the frequency-modulated electromagnetic wave signal is focused and transmitted in a preset direction at a preset future moment, and the transmission discrete coding is sent to the target receiving end in the form of an electromagnetic wave.

[0040] In summary, by inputting the frequency modulation parameters into a magnetoelectric coupling antenna, using the inverse magnetoelectric effect of the magnetoelectric composite material to generate a frequency-modulated electromagnetic wave signal, and combining the beamforming technology to achieve the directional transmission of the signal, this method can efficiently and accurately transmit the discrete coding to the target receiving end, improving the real-time performance and reliability of data transmission. At the same time, the directional focusing transmission reduces signal interference and energy loss, providing technical support for the real-time synchronization and optimization of early gastric cancer screening data.

[0041] Preferably, by reverse mapping the correlation between the magnetic domain wall displacement sequence and the coding mode, the discrete coding received by the target receiving end is decoded, and the decoded detection data is optimized and synchronized to the heterogeneous medical database node. Specifically: The frequency-modulated electromagnetic wave signal is captured by a magnetoresistive sensor array, and the changes in the frequency and amplitude of the electromagnetic wave are converted into electrical signals using the quantum tunneling effect; The quantum tunneling effect refers to the phenomenon that electrons penetrate a potential barrier with a certain probability through quantum mechanical properties in an energy potential barrier that cannot be crossed in physics. In the present invention, the magnetoresistive sensor utilizes this effect to convert the frequency and amplitude of the electromagnetic wave into electrical signals by monitoring the potential barrier changes caused by the electromagnetic wave signal.

[0042] The frequency offset and modulation depth in the frequency-modulated electromagnetic wave signal are reverse mapped to the magnetoresistance change amount and change rate, and the magnetic domain wall displacement sequence is reconstructed in combination with the initial state of the magnetic domain array; It should be noted that the frequency offset and modulation depth in the frequency-modulated electromagnetic wave signal are extracted by the signal demodulation module, which respectively correspond to the dynamic range of the magnetoresistance change amount and the change rate. Combining the initial state of the magnetic domain array, using the pre-established mapping relationship model, the frequency offset and modulation depth are converted into specific numerical values of the magnetoresistance change amount and the change rate. According to the time series data of the magnetoresistance change amount and the change rate, combined with the initial position and displacement path planning of the magnetic domain wall, the displacement sequence of the magnetic domain wall is gradually reconstructed.

[0043] According to the correlation between the magnetic domain wall displacement sequence and the discrete coding mode, the displacement sequence is restored to the original coding mode; The characteristic components in the original coding mode are parsed into key pathological features of gastric cancer early screening data, including tumor marker concentration, tissue morphology parameters, and nuclear atypia indexes, and structured data is generated; It should be noted that based on the pre-established mapping relationship between the magnetic domain wall displacement sequence and the discrete coding mode, the displacement path and final position of each magnetic domain wall in the displacement sequence are analyzed. According to the corresponding relationship between the displacement path and the position, the displacement state of each magnetic domain wall is mapped to the characteristic components in the discrete coding mode, such as tumor marker concentration, tissue morphology parameters, or nuclear atypia indexes; then, combined with the topological structure of the magnetic domain array, the displacement states of each magnetic domain wall are integrated into a complete discrete coding mode to ensure the correlation and consistency between the characteristic components, realizing the efficient restoration of the displacement sequence to the original coding mode.

[0044] The generated structured data is bound to the patient identity identifier, and after integrity verification and optimization of the data through the blockchain hash chain, it is dynamically synchronized to the heterogeneous medical database nodes.

[0045] In summary, this method realizes the accurate decoding of discrete coding by reverse mapping the correlation between the magnetic domain wall displacement sequence and the coding mode, restores the frequency-modulated electromagnetic wave signal to the key pathological features of gastric cancer early screening data, and combines blockchain technology to ensure the integrity and security of the data, thereby improving the accuracy and transmission efficiency of data decoding. At the same time, through the dynamic synchronization mechanism, real-time data sharing between heterogeneous medical database nodes is realized, providing timely and reliable test result support for doctors and patients.

[0046] Preferably, the generated structured data is bound to the patient identity identifier, and after integrity verification and optimization of the data through the blockchain hash chain, it is dynamically synchronized to the heterogeneous medical database nodes, specifically as follows: The decoded gastric cancer early screening data is uniquely bound to the patient identity identifier to generate a data-identity association pair, and the unique hash value of the association pair is calculated through a hash function; Write the hash value as a transaction record into the blockchain, and utilize the immutability of the distributed ledger to ensure the authenticity and traceability of the data source; Deploy a data verification contract in the blockchain network, verify the integrity of the data by comparing the hash values, and trigger the data retransmission process if the verification fails; Optimize the compression and indexing of structured data according to the storage characteristics and query requirements of heterogeneous medical database nodes; Allocate the optimized data to the corresponding heterogeneous medical database nodes so that doctors and patients can access the latest test data in a timely manner.

[0047] It should be noted that analyze the storage characteristics of heterogeneous medical database nodes. For example, node A supports high-compression ratio storage but has a slow query speed, while node B supports fast query but has limited storage capacity. Classify the structured data according to the query requirements. For example, allocate the tumor marker concentration data with high-frequency queries to node B, and allocate the tissue morphology parameter data with low-frequency queries to node A. Use a data compression algorithm (such as LZ77 or Zstandard) to compress the low-frequency query data to reduce the storage space occupation; finally, dynamically allocate the optimized data to the corresponding database nodes, and evaluate the storage and query performance through a real-time monitoring module to ensure the efficiency and stability of data synchronization.

[0048] In summary, this method binds the structured data with the patient identity identifier, and uses the blockchain hash chain for integrity verification and optimization, ensuring the authenticity, traceability and security of the data source, improving the accuracy and reliability of data synchronization. At the same time, it optimizes the storage and query efficiency of heterogeneous medical database nodes through a dynamic allocation mechanism, provides timely and reliable test data support for doctors and patients, and realizes the efficient management and sharing of early gastric cancer screening data.

[0049] In this embodiment, the method for synchronizing and optimizing the early gastric cancer screening data further includes the following steps: Generate a pair of dynamic entangled particles at the signal transmitter, retain one particle at the transmitter, and transmit the other particle to the receiver through a quantum channel to form an initial link for quantum key distribution; During the transmission of the frequency-modulated electromagnetic wave signal, synchronously bind the polarization state of the dynamic entangled particle pair with the phase information of the electromagnetic wave signal, establish a quantum tunnel for the encoding transmission path through polarization state synchronous detection, and real-time monitor the phase distortion during the signal transmission process; Utilize the quantum entanglement property to transmit the information of the distorted encoding segment from the transmitter to the receiver, and reconstruct the distorted encoding segment at the receiver; Plant quantum error correction codes in the quantum tunnel, and use the quantum error correction codes to correct the phase distortion in real time to improve the stability of signal transmission; A quantum-tunneling-based integrity verification network dynamically adjusts the transmission parameters of frequency-modulated electromagnetic wave signals to optimize the transmission efficiency and fidelity during the penetration of signals through biological tissues.

[0050] In summary, by implanting quantum key distribution and quantum error correction technologies during the transmission stage of frequency-modulated electromagnetic wave signals, this method can monitor and correct phase distortions in real time during signal transmission. At the same time, it reconstructs distorted coding segments through the principle of quantum teleportation, enhancing the stability and fidelity of signal transmission, ensuring the integrity and reliability of early gastric cancer screening data during cross-media transmission, and providing timely and accurate detection data support for doctors and patients.

[0051] In this embodiment, the method for synchronizing and optimizing early gastric cancer screening data further includes the following steps: Real-time monitor the change in the lattice strain field caused by the displacement of magnetic domain walls, and convert the change in the strain field into a magnetostrictive coefficient; Input the magnetostrictive coefficient into the frequency modulation parameter prediction model to dynamically adjust the phase compensation parameter of the electromagnetic wave carrier frequency as a feedback signal. When the change in the lattice strain field is greater than the preset change threshold, the phase compensation amount is increased by a preset amplitude; when the change in the lattice strain field is not greater than the preset change threshold, the phase compensation amount is decreased by a preset amplitude; Determine the difference in tissue dielectric constants based on the change trend of the magnetostrictive coefficient, and eliminate the signal attenuation effect through dynamic adjustment of the phase compensation parameter. For example, when the magnetostrictive coefficient continuously increases, it indicates that the tissue dielectric constant is high, and the phase compensation amount needs to be increased to eliminate the signal attenuation effect; During the generation of frequency-modulated electromagnetic wave signals, combine the adjusted phase compensation parameter with the frequency offset and modulation depth to generate an optimized frequency-modulated electromagnetic wave signal; Verify the signal transmission effect through a real-time feedback mechanism. If it is found that the signal attenuation is not completely eliminated, recalculate the magnetostrictive coefficient and adjust the phase compensation parameter until the signal transmission efficiency and fidelity reach the preset threshold.

[0052] In summary, by real-time monitoring the unidirectional change in the lattice strain caused by the displacement of magnetic domain walls, converting the change in the strain field into a magnetostrictive coefficient, and dynamically adjusting the phase compensation parameter of the electromagnetic wave carrier frequency as a feedback signal, this method can adaptively eliminate the signal attenuation effect caused by differences in tissue dielectric constants.

[0053] Such as Figure 3As shown in the figure, the second aspect of the present invention discloses a system 8 for synchronizing and optimizing gastric cancer early screening data. The system for synchronizing and optimizing gastric cancer early screening data includes a memory 60 and a processor 80. A program for the method of synchronizing and optimizing gastric cancer early screening data is stored in the memory 60. When the program for the method of synchronizing and optimizing gastric cancer early screening data is executed by the processor 80, the steps of any of the methods for synchronizing and optimizing gastric cancer early screening data are implemented.

[0054] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A method for synchronizing and optimizing gastric cancer early screening data, characterized in that: The following steps are involved: Acquire gastric cancer early screening data, and map the gastric cancer early screening data features into discrete codes of the magnetic domain array; Applying spin-polarized current pulses to the magnetic domain array, and triggering the directional displacement of the magnetic domain wall by adjusting the pulse width and intensity, so that the discrete code is converted into a sequence of magnetic domain wall positions; The real-time magnetic resistance change data after the magnetic domain wall displacement is imported into the frequency modulation parameter prediction model to obtain the frequency modulation parameters; Generating a frequency modulated electromagnetic wave signal using the frequency modulation parameters, and transmitting the discrete code to a target receiving end based on the frequency modulated electromagnetic wave signal; By reverse mapping the correlation between the magnetic domain wall displacement sequence and the coding pattern, the discrete code received by the target receiving end is decoded, and the decoded detection data is optimized and synchronized to the heterogeneous medical database node.

2. A method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: The gastric cancer early screening data features are mapped into discrete codes of magnetic domain arrays, specifically: Perform feature extraction on the gastric cancer early screening data collected by the detection equipment to obtain key pathological features, including tumor marker concentrations, tissue morphological parameters, and nuclear atypia indicators, and quantify each feature into a multidimensional feature vector; Magnetic domain units are allocated according to the dimension and weight of the eigenvector, each magnetic domain unit corresponds to a characteristic component, and the normalized range of the characteristic value is represented by the initial position of the magnetic domain wall to form a topological structure of the magnetic domain array; Based on the spatial distribution relationship of the eigenvectors, the correlation between the eigenvectors is mapped to the proximity of the magnetic domain wall displacement; According to the dynamic change of the characteristic vector and in combination with the timing control module of the spin polarized current pulse, a pulse sequence is generated, and based on the pulse sequence, the magnetic domain wall is driven to move along a preset planned path to form a discrete code corresponding to the characteristic vector one by one.

3. The method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: By adjusting the pulse width and intensity to trigger the directional displacement of the magnetic domain wall, the discrete code is converted into a sequence of magnetic domain wall positions, specifically: According to the initial position and target position of the magnetic domain wall, the required displacement distance of each magnetic domain wall is calculated, and the corresponding current pulse parameter range is determined based on the magnetization characteristics of the magnetic domain material; The required displacement distance of each domain wall is mapped to a combination of pulse width and intensity to form pulse parameters, ensuring that the pulse energy can overcome the pinning effect of the domain wall but will not cause unexpected displacement; generating a displacement sequence according to the priority order of magnetic domain wall displacement, and controlling each magnetic domain wall to move along a target position according to the displacement sequence and pulse parameters; The displacement state of the magnetic domain wall is monitored through a real-time feedback module, and the output signal of the magnetoresistive sensor is used to determine whether each magnetic domain wall has reached the target position. If not, the subsequent pulse parameters are dynamically adjusted; After all the domain wall displacements are completed, a sequence of domain wall positions corresponding to the discrete encoding is generated.

4. The method for synchronizing and optimizing gastric cancer early screening data according to claim 3, characterized in that: The displacement state of the magnetic domain wall is monitored through the real-time feedback module, and the output signal of the magnetoresistive sensor is used to determine whether each magnetic domain wall has reached the target position. If not, the subsequent pulse parameters are dynamically adjusted, specifically: A magnetoresistive sensor network is integrated in the magnetic domain array to collect the magnetic field intensity change signal of each magnetic domain wall in real time and convert the signal into digital displacement position data; Calculate the remaining displacement distance of the magnetic domain wall based on the difference between the target position and the current displacement position data; Generate an adjustment scheme of pulse parameters according to the remaining displacement distance, including an optimized combination of pulse width, intensity and application time interval; The pulse generator executes the adjusted pulse parameters and synchronously updates the monitoring frequency of the magnetoresistive sensor; After the magnetic domain wall reaches the target position, the verification module is triggered to verify the displacement result. If a deviation is found, the remaining displacement distance is recalculated and the adjustment process is started again until all the magnetic domain walls accurately reach the target position.

5. The method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: The steps of constructing the frequency modulation parameter prediction model are as follows: Collect historical magnetic resistance change data and corresponding frequency modulation parameters to construct a training data set; wherein the historical magnetic resistance change data includes historical magnetic resistance change amount and magnetic resistance change rate; Each magnetic domain unit in the magnetic domain array is represented as a graph node, and the magnetic domain wall displacement path is represented as an edge. The node features include the magnetic resistance change, change rate and displacement direction, and the edge features include the displacement distance and time interval. This completes the basic framework construction process of the graph neural network model. By aggregating the feature information of adjacent nodes, the local magnetic resistance change pattern is extracted, and the node weights are dynamically adjusted in combination with the attention mechanism to capture the impact of key magnetic domain wall displacement on the overall encoding pattern; the graph convolution layer design process of the graph neural network model is completed; The time series data of historical magnetic resistance changes and change rates are input into the graph neural network to extract dynamic features in the time dimension, ensuring that the model can capture the trend and fluctuation of magnetic resistance changes; the design process of the time series convolution layer of the graph neural network model is completed; The output features of the graph convolution layer and the time series convolution layer are fused, and the features are mapped to frequency offset and modulation depth through a fully connected network; the design process of the frequency modulation parameter prediction layer of the graph neural network model is completed; The graph neural network model is trained based on the training data set, the network parameters are adjusted using an adaptive optimization algorithm, and the prediction accuracy of the graph neural network model is evaluated through cross-validation until the prediction accuracy of the graph neural network model meets the prediction requirements, thereby obtaining a frequency modulation parameter prediction model.

6. The method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: The real-time magnetic resistance change data after the magnetic domain wall displacement is imported into the frequency modulation parameter prediction model to obtain the frequency modulation parameters, specifically: Using a magnetoresistive sensor array to monitor the magnetoresistive value at a preset time interval after the magnetic domain wall is displaced in real time, and calculating the real-time magnetoresistive change data according to the magnetoresistive value at the preset time interval after the magnetic domain wall is displaced, including the real-time magnetoresistive change amount and the magnetoresistive change rate; Input the real-time magnetic resistance change data into the frequency modulation parameter prediction model to obtain the frequency offset and modulation depth at a preset future time; A frequency modulation parameter at the preset future time is generated according to the frequency offset and the modulation depth at the preset future time.

7. The method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: The frequency modulation parameters are used to generate a frequency modulated electromagnetic wave signal, and the discrete code is transmitted to the target receiving end based on the frequency modulated electromagnetic wave signal, specifically: The frequency modulation parameters are input into the magnetoelectric coupling antenna, and the frequency offset and the modulation depth are converted into the frequency and amplitude changes of the electromagnetic wave by using the inverse magnetoelectric effect of the magnetoelectric composite material to generate a frequency modulated electromagnetic wave signal; Through the beamforming technology of the magneto-electric coupling antenna, the frequency-modulated electromagnetic wave signal is focused and transmitted in a preset direction at a preset future time, and the transmission is discretely encoded in the form of electromagnetic waves to the target receiving end.

8. The method for synchronizing and optimizing gastric cancer early screening data according to claim 1, characterized in that: By reverse mapping the correlation between the magnetic domain wall displacement sequence and the coding mode, the discrete code received by the target receiving end is decoded, and the decoded detection data is optimized and synchronized to the heterogeneous medical database node, specifically: Capture frequency-modulated electromagnetic wave signals through a magnetoresistive sensor array, and use the quantum tunneling effect to convert the frequency and amplitude changes of the electromagnetic waves into electrical signals; The frequency offset and modulation depth in the frequency modulated electromagnetic wave signal are reversely mapped into the magnetoresistance change and change rate, and the magnetic domain wall displacement sequence is reconstructed in combination with the initial state of the magnetic domain array; According to the correlation between the magnetic domain wall displacement sequence and the discrete coding pattern, the displacement sequence is restored to the original coding pattern; Parse the feature components in the original coding pattern into key pathological features of gastric cancer early screening data, including tumor marker concentrations, tissue morphological parameters, and nuclear atypia indicators, and generate structured data; The generated structured data is bound to the patient's identity, and after the data integrity is verified and optimized through the blockchain hash chain, it is dynamically synchronized to the heterogeneous medical database nodes.

9. The method for synchronizing and optimizing gastric cancer early screening data according to claim 8, characterized in that: The generated structured data is bound to the patient's identity, and after the data integrity is verified and optimized through the blockchain hash chain, it is dynamically synchronized to the heterogeneous medical database node, specifically: The decoded gastric cancer early screening data is uniquely bound to the patient's identity to generate a data-identity association pair, and a unique hash value of the association pair is calculated through a hash function; Write the hash value as a transaction record into the blockchain, and use the immutability of the distributed ledger to ensure the authenticity and traceability of the data source; Deploy a data verification contract in the blockchain network to verify the integrity of the data by comparing the hash value. If the verification fails, the data retransmission process is triggered; Compress and optimize indexes of structured data based on the storage characteristics and query requirements of heterogeneous medical database nodes; The optimized data is distributed to the corresponding heterogeneous medical database nodes so that doctors and patients can access the latest test data in a timely manner.

10. A system for synchronizing and optimizing gastric cancer early screening data, characterized in that: The synchronization and optimization system for gastric cancer early screening data includes a memory and a processor. The memory stores a synchronization and optimization method program for gastric cancer early screening data. When the synchronization and optimization method program for gastric cancer early screening data is executed by the processor, the steps of the synchronization and optimization method for gastric cancer early screening data as described in any one of claims 1 to 9 are implemented.

Images