Orthopedic disease man-machine interaction system and method based on human body magnetic signals

Abstract

The invention relates to the technical field of medical detection equipment, in particular to an orthopedic disease man-machine interaction system and method based on human body magnetic signals, and the system comprises terminal equipment and a management platform; the terminal equipment comprises a magnetic signal acquisition module, a low-temperature processing module and a magnetic signal filtering module, wherein the magnetic signal acquisition module is used for acquiring magnetic signals around acupuncture points through an optical atomic magnetic sensor; the low-temperature processing module is used for performing low-temperature processing on the periphery of the acupoint area; the magnetic signal filtering module is used for filtering the original magnetic signal data and removing the magnetic signal data of a non-acupoint area; and the management platform is used for extracting the characteristic value of the target magnetic signal data and generating a correlation analysis report between the characteristic value and the orthopedic disease. By combining an optical atomic magnetic force magnetic sensor, low-temperature processing and a non-acupoint magnetic signal filtering technology, noise interference can be filtered out, the reliability of data acquisition is improved, and magnetic information can be conveniently analyzed and converted into a visual effect of traditional Chinese medicine meridians and collaterals.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical detection devices, and more particularly, to an orthopedic disease human-computer interaction system and method based on human magnetic signals. Background Art

[0002] Meridian syndrome differentiation is the key to the diagnosis and treatment of diseases in traditional Chinese medicine. How to explore the relationship between diseases and meridians by mining human meridian magnetic signals? The existing research and application foundation are relatively weak, and a mature theoretical system has not yet been formed. Moreover, the technology for measuring human meridian magnetic signals is currently in its infancy, with significant room for exploration and unknown areas. Currently, the biometric magnetic measurements of human organs, viscera, and tissues have the following drawbacks and deficiencies in terms of technology, overall design, and overall functions: (1) In terms of technology, there are limitations in sensitivity and resolution, as well as deficiencies in environmental noise suppression and anti-interference technology: Although contemporary biometric magnetic measurement technology has achieved certain results, when faced with weak biometric magnetic signals, its sensitivity and resolution still face physical limits and technical bottlenecks, making it difficult to obtain sufficiently detailed and accurate magnetic information in high-precision measurement scenarios, thereby affecting the subsequent data analysis and the depth of scientific research. (2) Biometric magnetic measurement devices are susceptible to external electromagnetic noise, geomagnetic field fluctuations, and other interference factors in the actual operating environment. The existing noise suppression and anti-interference strategies cannot completely eliminate these interferences, resulting in unnecessary noise components being introduced during the data measurement process, reducing the signal-to-noise ratio and reliability of the measurement data. (3) In terms of overall design, there are deficiencies in system integration and modular design, as well as limitations in scalability and compatibility: Currently, some biometric magnetic measurement systems lack high levels of integration and modular consideration in their design, resulting in large system volumes, complex structures, which are not conducive to portable applications and rapid deployment. At the same time, it increases the difficulty and learning cost of user operation. (4) In terms of functions, there are deficiencies in data analysis and mining capabilities, as well as lags in real-time monitoring, dynamic response, and adaptability challenges in specific application scenarios: The massive amounts of data generated by biometric magnetic measurement technology require efficient data analysis and mining technologies to extract valuable information.

[0003] Therefore, those skilled in the art urgently need to find a new technical solution to solve the above problems. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides an orthopedic disease human-computer interaction system and method based on human magnetic signals.

[0005] According to the first aspect of the embodiments of the present disclosure, an orthopedic disease human-computer interaction system based on human magnetic signals is provided. The system includes: a terminal device and a management platform, and data interaction is performed between the terminal device and the management platform;

[0006] The terminal device includes: a magnetic signal acquisition module, a low-temperature processing module, and a magnetic signal filtering module. The low-temperature processing module and the magnetic signal filtering module are disposed inside the magnetic signal acquisition module;

[0007] The magnetic signal acquisition module can be adsorbed in the surrounding area of the acupoint area, and is used to collect the original magnetic signal data of the surrounding area of the acupoint for patients diagnosed with rotator cuff injury, knee arthritis, or osteoporosis through an optical atomic magnetometer;

[0008] The low-temperature processing module, connected to the magnetic signal acquisition module, is used to perform low-temperature processing on the surrounding area of the acupoint area during the acquisition process of the original magnetic signal data;

[0009] The magnetic signal filtering module, connected to the low-temperature processing module, is used to filter the original magnetic signal data through spatial filtering technology, remove the magnetic signal data of non-acupoint areas, obtain target magnetic signal data, and transmit the target magnetic signal data to the management platform;

[0010] The management platform, connected to the magnetic signal filtering module, is used to extract the characteristic values of the target magnetic signal data, and generate a correlation analysis report between the characteristic values of the target magnetic signal data and different orthopedic diseases according to the theory of the flow of qi and blood along the meridians, so as to assist doctors in diagnosing patients.

[0011] Optionally, the magnetic signal acquisition module includes a plurality of cube structures, and the top of the cube structure is made of an adhesive material so that the cube structure can be adsorbed in the surrounding area of the acupoint area.

[0012] Optionally, the terminal device further includes: a processor and a display screen; the processor is used to control the startup of the terminal device, the acquisition and transmission of the original magnetic signal by the magnetic signal acquisition module, and the automatic calibration of the magnetic signal acquisition module;

[0013] The display screen is used to display the prompt of the acquisition time point of the original magnetic signal, the prompt of the acquisition area of the original magnetic signal, and the completion status of the acquisition of the original magnetic signal.

[0014] Optionally, the low-temperature processing module is a semiconductor refrigeration chip, which is used to perform low-temperature processing on the surrounding area of the acupoint area;

[0015] The outside of the low-temperature processing module is wrapped with a heat-insulating material.

[0016] Optionally, the magnetic signal filtering module is used for:

[0017] Perform spatial distribution characteristic analysis on the original magnetic signal data obtained by the magnetic signal acquisition module to obtain the spatial distribution characteristics of the original magnetic signal data;

[0018] According to the spatial distribution characteristics, median filtering and mean filtering of the spatial filtering technology are used to perform spatial smoothing on the original magnetic signal data, so as to remove spatial noise and interference of magnetic signal data in non-acupoint areas, and obtain target magnetic signal data;

[0019] Transmit the target magnetic signal data to the management platform.

[0020] Optionally, before filtering the original magnetic signal data by the spatial filtering technology to remove the magnetic signal data in non-acupoint areas, the magnetic signal filtering module further includes:

[0021] Perform time-domain analysis on the original magnetic signal data to obtain the time-series characteristics of the original magnetic signal data;

[0022] Perform frequency-domain analysis on the original magnetic signal data to obtain the frequency components of the original magnetic signal data;

[0023] According to the time-series characteristics and frequency components of the original magnetic signal data, identify the characteristics of the magnetic signal data in non-acupoint areas in the original magnetic signal data, and take corresponding measures in the time domain and frequency domain to perform smoothing and attenuation processing of non-target frequency components, so as to obtain the original magnetic signal data with non-acupoint area magnetic signal data preliminarily filtered out.

[0024] Optionally, the management platform is used to support problem guidance for magnetic acquisition operations, tracking of patients' conditions, and prompt examinations and follow-up consultations when needed between doctors and patients through text, voice, and video calls.

[0025] Optionally, the management platform is used to receive an automatic calibration instruction from the magnetic signal acquisition module and send the automatic calibration instruction to the terminal device;

[0026] The terminal device controls the magnetic signal acquisition module to start an automatic calibration program according to the automatic calibration instruction;

[0027] The terminal device controls the optical atomic magnetometer to perform preheating;

[0028] The terminal device applies a standard magnetic signal to the optical atomic magnetometer through a built-in standard magnetic field source, so that the optical atomic magnetometer outputs the collected magnetic signal data under the action of the standard magnetic signal;

[0029] The terminal device compares the collected magnetic signal data with the standard magnetic signal, calculates the error, and adjusts the sensitivity and offset of the optical atomic magnetometer according to the comparison result to ensure the accuracy of the calibration result.

[0030] According to the second aspect of the disclosed embodiments of the present invention, a human-computer interaction method for orthopedic diseases based on human magnetic signals is provided, which is applied to a terminal device. The method includes:

[0031] Collect the original magnetic signal data of the surrounding area of the acupoints of patients diagnosed with rotator cuff injury, knee arthritis or osteoporosis through an optical atomic magnetometer sensor;

[0032] During the collection of the original magnetic signal data, perform cryogenic treatment on the surrounding area of the acupoint area;

[0033] Filter the original magnetic signal data through spatial filtering technology, remove the magnetic signal data of non-acupoint areas, obtain the target magnetic signal data, and transmit the target magnetic signal data to the management platform.

[0034] According to the third aspect of the disclosed embodiments of the present invention, a human-computer interaction method for orthopedic diseases based on human magnetic signals is provided, which is applied to a management platform. The method includes:

[0035] Receive the target magnetic signal data from the terminal device and perform real-time analysis on the target magnetic signal data;

[0036] Extract the characteristic values of the target magnetic signal data, and generate a correlation analysis report between the characteristic values of the target magnetic signal data and different orthopedic diseases according to the theory of the flow of qi and blood in the meridians, so as to assist doctors in diagnosing patients.

[0037] In summary, through the technical solutions in the disclosed embodiments of the present invention, the following beneficial effects can be brought:

[0038] (1) Through the progressive design of combining optical atomic magnetometers with intelligent light enhancement, cryogenic treatment, non-acupoint area magnetic signal filtering technology, signal filtering and processing algorithms, electrochemical impedance spectroscopy technology, etc., the magnetic signal changes can be accurately captured, noise interference can be effectively filtered out, and the reliability, accuracy and stability of data collection are greatly improved;

[0039] (2) By deploying a variety of communication interfaces and protocols, it can be compatible with a non-directional system architecture and achieve seamless docking and collaborative work with other intelligent devices;

[0040] (3) By applying technologies such as machine learning and deep learning, the processing, in-depth mining and rapid extraction of valuable information and features from a large amount of magnetic field data can be achieved in a high-timeliness manner, and the efficiency and accuracy of data analysis are significantly improved;

[0041] (4) By adopting encryption strategies in key links such as transmission and storage, the privacy of patients is guaranteed not to be leaked, and the security and uniqueness of data are ensured;

[0042] (5) Through the magnetic signal acquisition technology of meridians, the human body magnetic acquisition system acquires the magnetic signals of the human body into the interaction, and after analyzing the magnetic information, it is converted into the visual effect of traditional Chinese medicine meridians.

[0043] Other features and advantages disclosed in the present invention will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and are used to explain the present disclosure together with the following specific implementation manners, but do not constitute a limitation to the present disclosure. In the drawings:

[0045] Figure 1 is a schematic structural diagram of an orthopedic disease man-machine interaction system based on human body magnetic signals shown according to an exemplary embodiment;

[0046] Figure 2 is according to Figure 1 A schematic structural diagram of a terminal device shown;

[0047] Figure 3 is according to Figure 1 A schematic diagram of the home page of the operating system of the patient side of a terminal device shown;

[0048] Figure 4 is according to Figure 1 A schematic diagram of the magnetic acquisition interface of the acupoint area of the operating terminal device of a rotator cuff injury patient shown;

[0049] Figure 5 is according to Figure 1 A schematic diagram of the magnetic acquisition interface of the acupoint area of the operating terminal device of a knee arthritis patient (I) shown;

[0050] Figure 6 is according to Figure 1 A schematic diagram of the magnetic acquisition interface of the acupoint area of the operating terminal device of a knee arthritis patient (II) shown;

[0051] Figure 7 is according to Figure 1 A schematic diagram of the magnetic acquisition interface of the acupoint area of the operating terminal device of an osteoporosis patient (I) shown;

[0052] Figure 8 is according to Figure 1 A schematic diagram of the magnetic acquisition interface of the acupoint area of the operating terminal device of an osteoporosis patient (II) shown;

[0053] Figure 9 is according to Figure 1 A schematic diagram of the doctor-patient communication interface of the operating system of a rotator cuff injury patient shown;

[0054] Figure 10 is based on Figure 1 a schematic diagram of the meridian magnetic signal - Chenshi Jianjing acupoint data curve for rotator cuff injury shown in

[0055] Figure 11 a flowchart of a human - machine interaction method for orthopedic diseases based on human magnetic signals shown in an exemplary embodiment

[0056] Figure 12 a flowchart of a human - machine interaction method for orthopedic diseases based on human magnetic signals shown in an exemplary embodiment Detailed implementation manners

[0057] The following will explain in detail the specific implementation manners disclosed in the present invention with reference to the accompanying drawings. It should be understood that the specific implementation manners described herein are only for the purpose of illustration and explanation of the present disclosure, and are not used to limit the present disclosure.

[0058] Figure 1 a schematic structural diagram of a human - machine interaction system for orthopedic diseases based on human magnetic signals shown in an exemplary embodiment, as Figure 1 shown, the system includes: a terminal device 110 and a management platform 120, and data interaction is carried out between the terminal device and the management platform; the terminal device 110 includes: a magnetic signal acquisition module 111, a cryogenic treatment module 112, and a magnetic signal filtering module 113, and the cryogenic treatment module 112 and the magnetic signal filtering module 113 are arranged inside the magnetic signal acquisition module 111; the magnetic signal acquisition module 111 can be adsorbed on the surrounding area of the acupoint area, and is used to collect the original magnetic signal data of the surrounding area of the acupoint for patients diagnosed with rotator cuff injury, knee arthritis or osteoporosis through an optical atomic magnetometer; the cryogenic treatment module 112, connected to the magnetic signal acquisition module 111, is used to perform cryogenic treatment on the surrounding area of the acupoint area during the acquisition process of the original magnetic signal data; the magnetic signal filtering module 113, connected to the cryogenic treatment module 112, is used to filter the original magnetic signal data through spatial filtering technology, remove the magnetic signal data of non - acupoint areas, obtain the target magnetic signal data, and transmit the target magnetic signal data to the management platform 120; the management platform 120, connected to the magnetic signal filtering module 113, is used to extract the characteristic values of the target magnetic signal data, and generate a correlation analysis report between the characteristic values of the target magnetic signal data and different orthopedic diseases according to the theory of the flow of qi and blood in meridians at different times, so as to assist doctors in diagnosing patients.

[0059] Exemplarily, in the disclosed embodiments of the present invention, magnetic sensing technology and data processing algorithms are integrated. The original magnetic signal data of the patient is collected by an optical atomic magnetometer, and combined with technologies such as optical enhancement and cryogenic treatment, non-acupoint area magnetic signal filtering technology, signal filtering and processing algorithms, and electrochemical impedance spectroscopy technology, etc., to improve the accuracy and reliability of the collected magnetic signal data. At the same time, the collected magnetic signal data is uploaded to the management platform to realize the interaction between the patient and the doctor. After analyzing the magnetic signal data, the management platform converts the magnetic signal data into a visual effect of traditional Chinese medicine meridians.

[0060] Specifically, the process of collecting magnetic signal data is completed independently by the patient. During the diagnosis and treatment process, patients diagnosed with rotator cuff injury, knee arthritis or osteoporosis will be provided with a portable patient-side terminal device equipped with a magnetic acquisition module. The terminal device uses an ARM Cortex-A embedded processor and integrates a magnetic acquisition operating system that is trimmed and optimized based on the Linux kernel. The portable patient-side terminal device undertakes two main functions: magnetic signal acquisition and magnetic signal processing. The terminal device is responsible for the specific collection work of magnetic signals, preliminary processing and optimization of the magnetic signal data obtained from the magnetic signal acquisition module, transmission of relevant information of the magnetic acquisition signal, automatic calibration, startup of the magnetic signal acquisition module, prompt of the magnetic signal acquisition time point, acupoint area prompt, display of the completion status of magnetic signal acquisition, etc.

[0061] Figure 2 is according to Figure 1 shows a schematic structural diagram of a terminal device, as Figure 2 shown, the terminal device 110 further includes: a processor 114 and a display screen 115; the processor 114 is used to control the startup of the terminal device, the acquisition and transmission of the original magnetic signal by the magnetic signal acquisition module, and the automatic calibration of the magnetic signal acquisition module; the display screen 115 is used to display the prompt of the original magnetic signal acquisition time point, the prompt of the original magnetic signal acquisition area, and the completion status of the original magnetic signal acquisition. The magnetic signal acquisition module 110 includes several cube structures, and the top of the cube structure is made of an adhesive material so that the cube structure can be adsorbed on the surrounding area of the acupoint area.

[0062] For example, a patient can preset the collection time point through a terminal device. When the predetermined magnetic signal collection time point is reached, according to the preset collection plan, the patient is prompted to perform the magnetic signal collection operation through sound and vibration. The magnetic signal collection time point prompting technology real-time prompts the user to perform the magnetic collection operation through the preset time point and trigger conditions. Among them, the prompt information is displayed in the form of text and icons, and the prompt is sent 15 minutes in advance. After receiving the prompt, the patient enters the magnetic signal collection link through the touch screen interface of the terminal device. According to the operation guidance prompt on the touch screen interface of the terminal device, one of the magnetic signal collection modules is removed from the device. The shape of the magnetic signal collection module is a cube that can be adsorbed on the general range of acupoints. During the magnetic signal collection process by the patient, it is not necessary to accurately locate to a specific acupoint, only to locate to the general range of the acupoint.

[0063] The display screen of the terminal device can display the position of the magnetic signal collection module in real time, and use the graphical tool in the IDE (Integrated Development Environment) to display the relative position relationship between the magnetic signal collection module and the acupoint area, so as to help the patient continue to move the position of the magnetic signal collection module according to the position relationship on the display screen to roughly locate it within the acupoint range. After the patient compares with the relative position relationship displayed on the touch screen interface of the terminal device display screen, the final positioning of the magnetic signal collection module is determined and the magnetic signal collection module is buckled.

[0064] It should be noted that the top of the magnetic signal collection module is made of a sticky material and can be adsorbed on the general range of human acupoints. Usually, an adsorption material that can be flexibly adjusted according to the curvature and shape of different parts of the human body is selected, and a sticky material with an adhesive force of ≥5N / cm² is used to ensure that the magnetic collection module is closely attached to the acupoint. A pressure sensor applying a resistance strain gauge is also integrated on the magnetic signal collection module to monitor the contact state between the magnetic signal collection module and the patient's skin in real time, and the accuracy of the pressure sensor is ±0.1N.

[0065] In addition, the magnetic signal collection module in the terminal device uses a standardized digital interface. The digital interface uses high-speed digital communication protocols such as USB, SPI, and I2C, which can support high-speed data transmission to ensure real-time communication between the magnetic collection module and the core processor of the device. The built-in real-time monitoring formula: data transmission rate = communication protocol rate. This communication protocol uses a two-way data transmission mode, which not only allows the operating system core processor to send control instructions to the magnetic signal collection module, but also allows the magnetic signal collection module to feedback real-time status information to the core processor. The two data flows of instruction sending and status feedback ensure the integrity and accuracy of the information. The terminal device is also provided with additional reserved interfaces and expansion slots to support the access of newly added magnetic signal collection modules.

[0066] During the process of collecting magnetic signal data by the magnetic signal acquisition module, the miniaturized optical atomic magnetometer (built inside the top of the magnetic signal acquisition module) is the core component. Through optical pumping and optical magnetic resonance phenomena, it accurately measures tiny magnetic field changes. The miniaturized optical atomic magnetometer is portable and easy to hold, while improving the flexibility and efficiency of measurement. Through micro-nano processing technology, core components such as cesium atomic cells, optical elements, light sources, and detectors are miniaturized and integrated into a handheld module, and full optical measurement is achieved in combination with optical elements to realize high-sensitivity and high-stability magnetic signal measurement, forming an integrated miniaturized sensor.

[0067] During the process of collecting magnetic signal data by the optical atomic magnetometer, high-purity cesium atoms are selected as the sensing medium. Through precise coating technologies such as wax film coating, a protective layer is formed on the inner wall of the cell to reduce the collision relaxation between atoms and the cell wall, and extend the atomic spin coherence time. The size of the cell is optimized to achieve miniaturization while maintaining a sufficient atomic number density. The optical elements include lenses, mirrors, polarizers, etc., which are used for laser collimation, focusing, polarization control, etc. These elements are made by high-precision processing technologies, and their sizes and shapes are precisely calculated to ensure optical performance while achieving miniaturization. The light source uses a semiconductor laser diode as the light source, which has the advantages of small size, low power consumption, and easy modulation. The laser wavelength is precisely selected to match the specific energy level transition of cesium atoms to achieve efficient optical pumping. The purpose of selecting optical elements and light sources is to ensure laser collimation, focusing, polarization control, etc., to achieve efficient interaction between light and cesium atoms, so as to measure the magnetic field. The functions of the optical elements and light sources are to optimize the optical path through high-precision processed optical elements and precisely selected laser wavelengths, and improve the measurement accuracy and sensitivity. The detector selects high-sensitivity photodetectors such as photodiodes and avalanche photodiodes to detect the intensity changes of transmitted light and reflected light. The detector has a fast response speed and low noise, and can accurately reflect the changes in the magnetic field.

[0068] The inside of the sensor adopts a full optical method to measure the magnetic signal through the interaction between laser and cesium atoms. The laser first undergoes collimation and polarization control through a polarizer and a lens, and then irradiates the cesium atomic cell. Inside the cell, the laser interacts with cesium atoms, resulting in the Zeeman splitting of atomic energy levels. The energy difference of the splitting is proportional to the magnetic field strength, which is expressed by the Zeeman effect formula: ΔE = μB * gB, where ΔE is the energy difference of the energy level splitting, μB is the Bohr magneton, g is the Landé factor, and B is the magnetic field strength. The laser frequency matches the transition frequency between the split energy levels of cesium atoms, and the magnetic field strength is deduced by measuring the intensity change of the transmitted light. The relationship between the signal intensity and the magnetic field strength, atomic number density, laser intensity, etc. is described by the signal intensity formula: , where I is the signal intensity, N is the atomic number density, and σ(ω) is the transition cross section related to the magnetic field strength and the laser frequency. is the laser intensity.

[0069] Using micro-nano processing technology, the above core components are miniaturized and integrated into a small handheld module. To achieve long-term stable operation, a temperature control system and an electromagnetic shielding structure are also integrated inside the module. The temperature control system is used to keep the temperature of the gas chamber constant and reduce the influence of temperature fluctuations on the measurement accuracy; the electromagnetic shielding structure is used to isolate external electromagnetic interference and improve the stability of the measurement. During use, calibrations and tests including optical path alignment in optical performance, polarization state calibration, power consumption and stability in electrical performance, and verification of magnetic field measurement accuracy are carried out. These calibrations and tests ensure its performance, namely measurement accuracy and stability.

[0070] The biocompatible electrode is in direct contact with the human acupoints as the magnetic signal acquisition module and is located at the very front end of the magnetic signal acquisition module, flush with the adhesive material. It provides a stable signal acquisition platform for electrochemical impedance spectroscopy technology. Its good biocompatibility ensures the safety and comfort of biological tissues during the magnetic acquisition process. At the same time, its excellent conductivity ensures the accuracy and stability of signal acquisition. By preparing a nano-gold / cellulose nanocomposite as the modification material for the biocompatible electrode, the electrode material of the miniaturized optical atomic magnetometer is optimized. The specific operation is as follows: The nano-gold / cellulose nanocomposite is used as the surface modification material of the electrode to form a uniform and dense modification layer, and the surface roughness of the modified electrode is reduced. The dispersibility of the nano-gold / cellulose nanocomposite: >95%, which helps to improve the uniformity and stability of electrode modification. Through relevant experimental detections: CCK-8 detection and Western Blot experiments, it is shown that the toxicity of nano-gold wrapped with cellulose to cells is significantly reduced, ensuring its good contact with biological tissues and low toxicity, improving the compatibility between the electrode and biological tissues, reducing cell toxicity, reducing the stimulation and damage of the electrode to biological tissues, and ensuring the safety and stability of magnetic signal acquisition. At the same time, as the electrode modification material, the accuracy of spatial filtering in magnetic acquisition is indirectly improved by enhancing the compatibility between the electrode and biological tissues.

[0071] Furthermore, the disclosed embodiments of the present invention also adopt laser and light enhancement technologies, which are integrated with a miniaturized optical atomic magnetic sensor and are located at the front end of the sensor. This technology is used to assist the sensor in working. By precisely regulating laser parameters such as frequency, intensity, and phase, and using a light source with a specific wavelength, the induction and transmission efficiency of magnetic signals are effectively enhanced. Using a tunable light source, near-infrared light with a specific wavelength is radiated to a local area of the human body buckled by the magnetic acquisition module. Through optical filtering, wavelength conversion, etc., the light radiation of this specific wavelength is highlighted and enhanced, and the intensity of the light radiation of this specific wavelength is enhanced, making the light of this wavelength dominant in the total light radiation, thereby enhancing the interaction with human tissues and improving the magnetic signal induction ability. These light waves interact with human tissues to enhance the magnetic signal induction ability. The calculation formula involved: light enhancement factor , where the light enhancement factor is greater than 5 times and the optimal illumination wavelength is 650 nanometers. The change in signal amplitude is monitored through this formula. Using a microprocessor to automatically and precisely modulate and synchronously control the luminous intensity and working mode of the tunable light source, such as continuous light emission and pulsed light emission, to achieve the collaborative work of the light source and the magnetic sensor, ensuring that while the light source emits light of a specific wavelength, the magnetic sensor can accurately receive and process magnetic signals, and improving the overall performance of the magnetic acquisition system. The calculation formula involved: modulation depth is , the synchronization error is ∣tlight−tsensor∣, where the modulation depth: >90%, is the maximum light intensity, is the minimum light intensity, tlight is the light source trigger time, tsensor is the sensor sampling time, is the signal amplitude after illumination, is the signal amplitude before illumination. Using the precise timing function of the microprocessor, precise synchronization of the light source trigger time and the magnetic sensor sampling time is achieved, and the synchronization error is less than 1 μs.

[0072] The low-temperature treatment module in the disclosed embodiments of the present invention is a semiconductor refrigeration chip, which is used to perform low-temperature treatment on the area around the acupoint area; the outside of the low-temperature treatment module is wrapped with a thermal insulation material.

[0073] Exemplarily, the cryogenic treatment module is integrated inside the magnetic signal acquisition module. Each magnetic signal acquisition module contains an independent cryogenic treatment module, which is adjacent to the miniaturized optical atomic magnetometer. During magnetic acquisition, the integrated cryogenic treatment module is used to perform cryogenic treatment on the range where the sensor is buckled to the human body part, which can reduce the interference of thermal noise on magnetic signal detection, and improve the accuracy and efficiency of magnetic signal acquisition by increasing the signal-to-noise ratio and measurement accuracy of the magnetic signal. At the same time, the low-temperature environment can also enhance the performance of the atomic magnetometer, making it more sensitive to the change of magnetic signal. The integrated cryogenic treatment module realizes precise temperature control of the working environment of the magnetic sensor by integrating an efficient semiconductor refrigeration chip and a thermocouple refrigeration device. The intelligent temperature control system monitors the actual ambient temperature of the magnetic sensor in real time and automatically adjusts the refrigeration power of the cryogenic treatment module according to the temperature feedback. Ensure that the sensor operates at the optimal ambient temperature. At the same time, through the setting of thermal insulation materials and heat dissipation, the efficiency and stability of the cryogenic treatment module are improved, thereby improving the accuracy and stability of magnetic signal acquisition. The thermal insulation material and heat dissipation use high-performance thermal insulation materials to wrap the cryogenic treatment module to reduce heat dissipation and improve the refrigeration efficiency. Through the heat dissipation channel, the heat generated during the refrigeration process is discharged in time by means of air convection and heat sink, ensuring the long-term stable operation of the cryogenic treatment module.

[0074] The working principle of the cryogenic treatment module is as follows:

[0075] At room temperature, thermal noise in electronic devices is a factor that cannot be ignored. Thermal noise is caused by the random thermal motion of free electrons inside the conductor, and its magnitude is proportional to the temperature. According to Nyquist's theorem, the power spectral density of thermal noise can be expressed as , where (f) is the noise power spectral density, is the Boltzmann constant, T is the absolute temperature, and B is the measurement bandwidth. It can be seen that reducing the temperature T can effectively reduce thermal noise and increase the signal-to-noise ratio of the signal. The thermal noise is adjusted to a low value through intelligent temperature regulation. Among them, the temperature value and the noise power spectral density reduction ratio function are used to judge the effectiveness of reducing thermal noise by temperature: . In a low-temperature environment, physical properties such as the resistivity and carrier mobility of the sensor material will change, thereby affecting the sensitivity and stability of the sensor. For a magnetic sensor, a low-temperature environment usually can reduce the thermal disturbance inside the material, reduce magnetic noise, and improve the detection sensitivity of the magnetic signal. The improvement of the sensor performance is usually manifested as an increase in sensitivity and a decrease in noise. Sensitivity can be defined as the ratio of the output signal to the input signal, and the decrease in noise can be reflected by the increase in the signal-to-noise ratio SNR. The sensor sensitivity at room temperature is , and the sensor sensitivity at low temperature is , and the sensitivity is measured in real time through the sensitivity increase ratio formula: 。

[0076] Due to the reduction of the noise power at low temperature , the formula for the improvement of the signal-to-noise ratio detected in real time is: , where the signal-to-noise ratio at room temperature is , and the signal-to-noise ratio at low temperature is . The sensor can detect smaller magnetic field changes, which are quantified by the magnetic noise equivalent field MNEF of the sensor. The reduction of the magnetic noise equivalent field: the magnetic noise equivalent field at room temperature is , and the magnetic noise equivalent field at low temperature is , , the formula for the reduction of the magnetic noise equivalent field detected in real time is: . In the low-temperature treatment technology, a semiconductor refrigeration chip is adopted: using the Peltier effect, refrigeration is achieved through current drive. Thermocouple: Using the thermoelectric effect, current is generated under a temperature difference, and refrigeration can be achieved by reverse application. The calculation formula for the refrigeration capacity of the semiconductor refrigeration chip: Q = π·I·T, where Q is the refrigeration capacity, I is the current, and T is the thermoelectric potential of the thermocouple and the temperature coefficient of the refrigeration chip. The calculation formula for power consumption: P = UI, where P is the power consumption, U is the voltage, and I is the current. The intelligent temperature control system adopts the PID control algorithm through the embedded system to ensure that the sensor always operates within the optimal ambient temperature range. Temperature control accuracy: ±0.1°C, temperature response time: <1 second. Thermal insulation materials and heat dissipation design: High-performance aerogel, vacuum insulation panels and other thermal insulation materials are used to wrap the low-temperature treatment module to reduce heat dissipation. The heat dissipation channel uses methods such as forced convection of the fan and heat sink to timely discharge the heat generated during the refrigeration process. Thermal insulation performance: Thermal conductivity <0.01 W / (m·K), heat dissipation efficiency: >90%.

[0077] Furthermore, the magnetic signal filtering module is used for: analyzing the spatial distribution characteristics of the original magnetic signal data obtained by the magnetic signal acquisition module to obtain the spatial distribution characteristics of the original magnetic signal data; according to the spatial distribution characteristics, performing spatial smoothing processing on the original magnetic signal data through median filtering and mean filtering of the spatial filtering technology to remove the interference of spatial noise and non-acupoint area magnetic signal data and obtain the target magnetic signal data; transmitting the target magnetic signal data to the management platform.

[0078] Before filtering the original magnetic signal data through spatial filtering technology to remove the magnetic signal data in non-acupoint areas, the magnetic signal filtering module further includes: performing time-domain analysis on the original magnetic signal data to obtain the time-series characteristics of the original magnetic signal data; performing frequency-domain analysis on the original magnetic signal data to obtain the frequency components of the original magnetic signal data; identifying the characteristics of the magnetic signal data in non-acupoint areas in the original magnetic signal data according to the time-series characteristics and frequency components of the original magnetic signal data, and taking corresponding measures in the time domain and frequency domain to smooth and attenuate the non-target frequency components, so as to obtain the original magnetic signal data with the magnetic signal data in non-acupoint areas preliminarily filtered out.

[0079] Exemplarily, during the data acquisition process, the magnetic signals in non-acupoint areas are automatically identified and filtered out to ensure that the acquired data mainly comes from acupoint areas. In the disclosed embodiments of the present invention, instead of relying on traditional filter design, spatial smoothing processing technologies such as median filtering and mean filtering are adopted to remove spatial noise and magnetic signal interference in non-acupoint areas, thereby improving the spatial consistency of the signals.

[0080] Specifically, analyze the spatial distribution characteristics of the magnetic signals obtained by the magnetic acquisition device (including studying the intensity, direction, and change trend of the magnetic signals at different spatial positions), identify the differences in the spatial distribution between the magnetic signals in acupoint areas and non-acupoint areas, and provide a basis for subsequent spatial filtering processing. According to the spatial distribution characteristics of the magnetic signals, median filtering and mean filtering of the spatial filtering technology are used to perform spatial smoothing processing on the signals, which can effectively remove spatial noise and magnetic signal interference in non-acupoint areas and improve the spatial consistency of the signals.

[0081] Among them, median filtering is to replace the current signal value by taking the median of the signal values in the neighborhood, which helps to remove isolated noise points and outliers of the magnetic signal data in non-acupoint areas. For a given magnetic signal matrix S, represents the magnetic signal value at the spatial position . For each position , consider all the signal values within the window as the buckling part, sort them, and take the median as the filtered signal value Sfiltered . Sfiltered = median{S(i + k, j + l)∣k, l ∈ [− , ]}, where n is the size of the filtering window (assumed to be odd), and median represents the median operation. Mean filtering is to smooth the signal by calculating the average value of the signal values in the neighborhood, which helps to reduce the spatial fluctuation of the signal. Calculate the average value of all the signal values within the window as the filtered signal value. Mean filtering: Sfiltered = S(i + k, j + l), where n is the size of the filtering window. Signal spatial consistency: The spatial consistency of the signal is evaluated by calculating the spatial correlation coefficient of the magnetic signal before and after filtering. The closer the correlation coefficient is to 1, the better the spatial consistency of the signal. The correlation coefficient where and are the average values of the magnetic signals before and after filtering respectively.

[0082] The magnetic acquisition system will preprocess the collected original magnetic signal data through signal filtering and processing algorithms, including steps such as denoising, signal enhancement, signal amplification, feature extraction, and algorithm classification, to improve the quality and interpretability of the signal. Due to the self - adaptability and learning ability of the algorithm, it can continuously optimize the filtering effect, improve the performance and reliability of the system. It avoids the complexity and limitations brought by traditional filters, and avoids problems such as phase distortion and signal attenuation that may be introduced by filters. It provides a more efficient and intelligent solution for the signal processing of magnetic acquisition devices. The specific technical classification and operation methods are as follows:

[0083] Perform time - domain analysis on the original magnetic signal data to capture its time - series characteristics, and then perform frequency - domain analysis on the original magnetic signal data to reveal the frequency components of the signal. Combining these two analyses, identify the characteristics of non - acupoint area magnetic signals, and take corresponding measures in the time - domain and frequency - domain, such as smoothing and attenuating non - target frequency components, to further filter out these interference signals.

[0084] Specifically, the time - domain analysis process includes: calculating the mean μ and variance of the magnetic signal data x(t), which are used to evaluate the overall level and fluctuation degree of the signal. Among them, the signal mean and the variance . Then, according to the waveform characteristics of the signal, such as peak value, valley value, rising edge, falling edge, etc., extract the time - domain feature vector. The frequency - domain analysis process includes: performing Fourier transform on the magnetic signal x(t) to obtain the spectrum X(ω) to reveal the frequency components of the signal. Fuse the time - domain and frequency - domain feature vectors to form a comprehensive feature set for accurately identifying non - acupoint area signals. Based on the comprehensive feature set, in the time - domain, the non - acupoint area signal segments can be smoothed and set to zero; in the frequency - domain, the signal components within a specific frequency range can be attenuated and filtered. Through the joint analysis of the time - domain and frequency - domain, non - acupoint area magnetic signals can be accurately identified and filtered, ensuring that the collected signals mainly originate from the acupoint area. By optimizing the processing strategy, the real - time requirement is met, providing accurate and reliable data support for subsequent medical diagnosis and treatment.

[0085] Furthermore, in magnetic signal processing, machine learning algorithms can help identify and analyze the characteristics of magnetic signals, improving the interpretability of signals after feature extraction and pattern recognition. Machine learning algorithms such as support vector machines and neural networks are used to train and learn magnetic signals. Through training, the algorithm can automatically identify and distinguish magnetic signals in acupoint areas and non-acupoint areas, and filter magnetic signals more intelligently and accurately. Specifically, a large number of sample data containing magnetic signals in acupoint areas and non-acupoint areas are collected to ensure the diversity and representativeness of the data. The data is preprocessed, including denoising and normalization, to improve the training effect of the algorithm. Key features of magnetic signals are extracted in the time domain and frequency domain respectively. Time domain features include the mean, variance, peak value, valley value, rising edge, falling edge, etc. of the signal. Frequency domain features include the spectral distribution and energy spectral density of the signal. A feature vector is formed as the input of the machine learning algorithm. The preprocessed sample data is used to train classification algorithms such as support vector machine SVM, convolutional neural network, recurrent neural network, deep neural network, etc., so that it can learn and identify the feature differences between magnetic signals in acupoint areas and non-acupoint areas. The algorithm parameters are optimized through methods such as cross-validation and grid search to improve the classification performance.

[0086] Embed the trained machine learning algorithm into the magnetic signal acquisition module. Real-time collect the magnetic signal data of the patient and extract the feature vector. Use the algorithm to classify the feature vector and automatically identify the magnetic signals in acupoint areas and non-acupoint areas. Filter and attenuate the magnetic signals in non-acupoint areas and retain the magnetic signals in acupoint areas. The goal of SVM is to maximize the margin between two types of samples by finding a hyperplane. For a given feature vector and the corresponding label , where 1 represents the acupoint area and 0 represents the non-acupoint area, then the optimization problem of SVM can be expressed as: +C i=1 ∑Nξ i,s.t.yi (wTxi + b)≥1−ξi,ξi≥0, where w is the normal vector of the hyperplane, b is the offset, C is the regularization parameter, and ξi is the slack variable.

[0087] It can be understood that a neural network consists of multiple layers of neurons, and each layer of neurons is connected to the next layer through weights and biases. For a given input feature vector x, the output of the neural network can be expressed as: y=f(W L ⋅f(W L−1 ⋅…⋅f(W1⋅x + b1)+b L−1 )+b L ), where W l and b l are the weight matrix and bias vector of the l-th layer respectively, and f is an activation function such as ReLU and sigmoid.

[0088] Real-time noise removal and useful signal enhancement of non-acupoint magnetic signals are achieved through digital signal processing, which can significantly improve data quality and provide accurate and reliable magnetic signal data for subsequent medical analysis. The signal-to-noise ratio should be ≥60 dB, and the signal enhancement multiple should be ≥2 to measure the enhancement effect. The original signal is preprocessed, including removing DC offset, correcting the baseline, etc., to ensure the accuracy of subsequent processing. Methods such as adaptive filtering, spectral subtraction, and wavelet transform in digital signal processing technology are used to filter and enhance the magnetic signal. Adaptive filtering automatically adjusts parameters according to the statistical characteristics of the signal and noise to minimize noise and retain signal details.

[0089] Spectral subtraction enhances the signal by analyzing the spectral characteristics of the signal, estimating and removing the noise spectrum. Wavelet transform uses multi-scale analysis to decompose the signal into sub-signals of different frequency bands, performs threshold processing and enhancement on the sub-signals, and then reconstructs them back into the original signal space.

[0090] Post-processing is performed on the filtered and enhanced signal, such as smoothing processing, peak detection, etc., to further extract signal features and improve data quality. Specifically, for adaptive filtering: w(n + 1)=w(n)+μe(n)x(n),

[0091] where w(n) is the filter weight vector at the nth moment, μ is the learning rate, e(n) is the error signal, and x(n) is the input signal vector. For spectral subtraction: S^(k)=S(k)−αN(k), where S^(k) is the enhanced signal spectrum, S(k) is the original signal spectrum, N(k) is the noise spectrum estimate, and α is the adjustment coefficient. The signal-to-noise ratio SNR = ( ) where Psignal is the signal power and Pnoise is the noise power. It is required that SNR≥60 dB to measure the quality of the enhanced signal. The signal enhancement multiple = where, is the amplitude of the enhanced signal and Aoriginal is the amplitude of the original signal. It is required that the enhancement multiple ≥2 to measure the effect of signal enhancement.

[0092] The electrochemical characteristics of the magnetic acquisition module are monitored in parallel by electrochemical impedance spectroscopy (EIS) technology. By monitoring and analyzing the impedance changes at the interface between the electrode and biological tissue, the changing trend of meridian magnetic signals can be indirectly reflected, providing auxiliary information for signal processing and ensuring the accuracy and reliability of signal acquisition. The specific operations are as follows: The EIS hardware is usually located inside the magnetic acquisition module. By inputting a small-amplitude sinusoidal alternating current signal into the system, the impedance characteristics of the sensing system are detected, including real-time monitoring of the electrochemical changes during the acquisition process of the magnetic acquisition module, such as mass transfer impedance and charge transfer impedance, and analysis of the electrochemical characteristics of the system. Electrochemical parameters such as charge transfer impedance and mass transfer impedance are analyzed, including the real and imaginary parts of the impedance, as well as the analysis of Bode plots and Nyquist plots. Bode plots and Nyquist plots are used to analyze the response of the sensing system to different wavelengths of colored light and magnetic signals, providing direct evidence of the electrochemical characteristics of the sensing system. Feedback is provided for biocompatible electrodes to optimize signal acquisition parameters. The impedance calculation formulas in EIS tests include complex impedance and phase angle: impedance Z = V / I, where V is voltage and I is current. The sensitivity and accuracy of the magnetic signal response are verified through comparative tests, and the response ability and accuracy of the device to biomagnetic signals are verified to optimize the device performance and parameter settings.

[0093] In addition, the customized system architecture within the terminal device supports the characteristics of high stability, low power consumption, strong real-time performance, and easy development and maintenance during the magnetic signal acquisition process. Specifically, an embedded Linux kernel is trimmed and customized to meet the application requirements of the magnetometer sensor. The kernel scheduling algorithm and interrupt handling mechanism are optimized according to the hardware characteristics of the magnetic acquisition module, such as CPU affinity and interrupt response, to improve the utilization efficiency and response speed of the system to hardware resources. Specifically, the CFS (Completely Fair Scheduler) scheduler is used for task scheduling to ensure the high-priority execution of magnetic acquisition tasks. It is achieved through the RT-Preempt patch and priority scheduling. In terms of the RT-Preempt patch, to meet the customized operations of the device combined with the sensors in the magnetic acquisition module: the RT-Preempt patch technology is used to transform the Linux kernel into a real-time operating system to ensure the real-time acquisition and processing of data from the magnetic acquisition module. By modifying the kernel scheduling mechanism, task preemption and priority scheduling are realized, and task latency is reduced. In terms of priority scheduling, to meet the customized operations of the device combined with the magnetic acquisition module: the highest priority is set for the data acquisition, processing, and transmission tasks of the magnetic acquisition module, and the priority inheritance and priority inversion protection mechanisms are adopted to ensure that these critical tasks can still be executed preferentially when the system resources are tense, guaranteeing real-time performance. A cross-compilation toolchain is used to build an Eclipse and Android Studio cross-compilation environment that supports the compilation and debugging of embedded Linux code. This integrated development environment (IDE) provides graphical code editing, debugging, and performance analysis tools. This can ensure that the compiled application can run directly in the operating system of the magnetic acquisition device, improving development efficiency.

[0094] Dynamic Power Management (DPM) and Dynamic Voltage and Frequency Scaling (DVFS) are adopted. In terms of Dynamic Power Management (DPM), to meet the customized operations of the device combined with the sensors in the magnetic acquisition module: system load monitoring technology is used to dynamically adjust the power supply according to the system load and the working state of the magnetic acquisition module, such as turning off unnecessary power rails and reducing the supply voltage of non-critical components, to reduce power consumption. Through the DPM framework, different power states and their switching conditions are defined. In terms of Dynamic Voltage and Frequency Scaling (DVFS), to meet the customized operations of the device combined with the sensors in the magnetic acquisition module: according to the real-time performance requirements of the system, performance monitoring and prediction technologies are adopted to dynamically adjust the voltage and frequency of the CPU and other key components to achieve the best balance between power consumption and performance. Through the DVFS algorithm, appropriate voltage and frequency levels are selected according to the current task load and performance requirements.

[0095] This management platform is used to support the guidance on magnetic acquisition operation problems, the tracking of patients' condition, and the prompt for examinations and follow-up consultations when needed, through text, voice, and video calls between doctors and patients.

[0096] This management platform is used to receive the automatic calibration instruction of the magnetic signal acquisition module and send the automatic calibration instruction to the terminal device; the terminal device controls the magnetic signal acquisition module to start the automatic calibration program according to the automatic calibration instruction; the terminal device controls the optical atomic magnetometer to preheat; the terminal device applies a standard magnetic signal to the optical atomic magnetometer through the built-in standard magnetic field source, so that the optical atomic magnetometer outputs the collected magnetic signal data under the action of the standard magnetic signal; the terminal device compares the collected magnetic signal data with the standard magnetic signal, calculates the error, and adjusts the sensitivity and offset of the optical atomic magnetometer according to the comparison result to ensure the accuracy of the calibration result.

[0097] In addition, since the magnetic signal acquisition module in the terminal device needs to be automatically calibrated before performing magnetic signal acquisition and its related signal processing and control work, medical staff with permission can remotely start the automatic calibration program of the magnetic acquisition module through the management platform, using remote debugging tools such as Android Debug Bridge and SSH. After entering the calibration mode, both doctors and patients can display the calibration progress and prompt information. After calibration starts, the magnetic sensor is first preheated automatically to ensure its stable working state. A standard magnetic signal is applied to the magnetic sensor through the built-in standard magnetic field source. The intensity and direction of the standard magnetic signal should be accurately measured and calibrated in advance to ensure its accuracy. The magnetic sensor outputs magnetic signal data under the action of the standard magnetic signal. The magnetic acquisition system collects these data and compares them with the preset standard value to calculate the error. According to the comparison result, the system automatically adjusts parameters such as the sensitivity and offset of the magnetic sensor to reduce the error. The adjustment process will perform algorithm and iterative calculations to ensure the accuracy of the calibration result. To further improve the calibration accuracy and stability, the system may repeat the above calibration process multiple times. After each calibration, the system will evaluate the calibration effect and continue to adjust the parameters as needed. When the system believes that the calibration result meets the preset accuracy requirements, the automatic calibration process ends. The system will display the calibration completion information and require medical staff with permission to perform simple verification operations such as restarting the measurement magnetic source to ensure the validity of the calibration result.

[0098] In addition, the process, results, and related parameters of the automatic calibration can be recorded in the log file. These log files can be used for subsequent device maintenance, troubleshooting, and performance analysis. The log files of the automatic calibration will be synchronously transmitted to the local server together with the regular data packets and actual magnetic signal data at a later stage.

[0099] The processed magnetic signal data will be packaged into regular data packets for transmission: the metadata includes the acquisition time, patient ID, device ID, etc., and combines the actual magnetic signal data and the log file of automatic calibration.

[0100] A communication connection can be established between the patient-side device and the local server, usually using a reliable transmission protocol such as the TCP / IP protocol. According to the actual deployment environment of the patient's magnetic acquisition device, the communication connection can be made via wireless Wi-Fi or Bluetooth. During the transmission process, the data packets will be encrypted to ensure data security. The configuration server uses the TLS 1.3 protocol and the AES-256 algorithm to encrypt sensitive data. This prevents data from being stolen or tampered with during transmission. The number of encrypted data private keys is , ensuring the security and privacy protection of the data during transmission. Through the data integrity verification and error correction mechanism, checksum and error correction codes are used for integrity verification and error correction during data transmission. The specific algorithms and formulas involving checksum and error correction codes: Cyclic Redundancy Check (CRC). By using checksum and error correction codes, the integrity and accuracy of the data are ensured, further improving the reliability of data transmission. The encrypted data packets are sent to the local server through the communication connection. Data compression is involved during the sending process to reduce the transmission time and bandwidth occupancy. Data reception, processing, and storage: The local server receives the magnetic signal data packets transmitted from the patient side and performs data integrity verification, decryption, and decompression processing. The decrypted data is stored in the file system or database of the server for subsequent analysis and processing. As Figures 3 to 9 shown, it is a schematic diagram of various interface displays of the patient side of the terminal device.

[0101] A communication connection will also be established between the doctor-side magnetic analysis system and the local server, using the TCP / IP protocol and other reliable transmission protocols. The communication connection can be in wired or wireless ways within the local area network. The doctor-side magnetic analysis system sends a data request to the local server. The request includes conditions such as the data range, time period, and patient ID to be queried. The local server retrieves the corresponding magnetic signal data in the storage system according to the received request conditions. The retrieval process involves operations such as database query and file system traversal.

[0102] Data Receiving and Processing Unit: Responsible for receiving the magnetic signal data transmitted from the patient side and performing preliminary processing and integration. It adopts a high-speed analog-to-digital converter ADC, a data preprocessing module, namely a field-programmable gate array FPGA, and a digital signal processor DSP. The high-speed analog-to-digital converter ADC is used to convert the analog magnetic signal into a digital signal, and the field-programmable gate array FPGA and the digital signal processor DSP are used to process and integrate these digital signals in real time. A high-performance computing platform is used to run complex algorithms for real-time analysis of a large amount of magnetic signal data. After obtaining the magnetic signal data from the local server, the high-performance computing platform on the doctor side performs data integration, preprocessing, feature extraction, matching and correlation analysis, and diagnostic determination. It includes a multi-core processor server, a GPU-accelerated computing node, a distributed computing cluster, and a parallel computing framework (such as MapReduce, Spark). This platform uses a multi-core processor server and a GPU-accelerated computing node to provide powerful computing capabilities, and at the same time uses a parallel computing framework to optimize the running efficiency of complex algorithms to achieve real-time analysis of a large amount of magnetic signal data. The storage device is responsible for storing and managing the patient's magnetic signal data and analysis results. It includes solid-state drives (SSDs), high-speed hard drives (HDDs), network-attached storage (NAS), and at the same time uses RAID technology to improve data security and reliability. And data deduplication technology is used to reduce storage space occupancy, and cloud storage is used to achieve remote backup and access of data.

[0103] Construction of the Magnetic Signal Analysis System Software on the Doctor Side: On the high-performance computing platform, specific data integration and preprocessing technologies, feature extraction algorithms, matching and correlation analysis algorithms, and intelligent diagnosis technologies are used for data integration, preprocessing, feature extraction, matching and correlation analysis, and diagnostic determination. According to the characteristics of magnetic signals and the relevance of orthopedic diseases, the extracted feature values can indeed be time-domain feature functions, frequency-domain feature functions, time-domain waveform features, frequency-domain waveform features, the highest frequency value, the lowest frequency value, etc. These feature values can comprehensively describe the characteristics of magnetic signals and establish associations with orthopedic diseases.

[0104] Key features of the magnetic signal are extracted from the preprocessed magnetic signal data by the following methods for subsequent correlation analysis and diagnostic determination.

[0105] Time-domain characteristic function: The time-domain characteristic function describes the law of change of magnetic signals over time and expresses the characteristics of signal changes over time. In the measurement of meridian magnetic signals, it includes the mean value, standard deviation, root mean square value (RMS), peak value, peak-to-peak value, peak factor, skewness, kurtosis, etc. of the signal. These characteristic values can reflect the characteristics of signal fluctuation degree, energy size, peak size, etc. The extracted characteristic values need to be properly processed and analyzed: noise reduction, standardization, etc., to improve the accuracy and reliability of the characteristic values. At the same time, it is also necessary to combine methods such as machine learning and statistical analysis to deeply analyze the correlation between the characteristic values and orthopedic diseases. Specific applications of characteristic values and formulas based on the principles of general signal processing and data analysis: A represents the time-domain characteristic function, which can include multiple specific characteristic values, mean value (A_mean), standard deviation (A_std), peak value (A_peak).

[0106] Specifically, mean value (Mean): , standard deviation (Standard Deviation): Peak value (Peak): , and the unit is nanotesla (nT).

[0107] Frequency-domain characteristic function: The frequency-domain characteristic function describes the characteristics of magnetic signals in the frequency domain. It includes the frequency mean value, frequency center of gravity, root mean square frequency, standard deviation frequency, etc. of the magnetic signal. These characteristic values can reflect the distribution of magnetic signals in the frequency domain, the position of the main frequency band, etc. The extracted characteristic values need to be properly processed and analyzed: noise reduction, standardization, etc., to improve the accuracy and reliability of the characteristic values. At the same time, it is also necessary to combine methods such as machine learning and statistical analysis to deeply analyze the correlation between the characteristic values and orthopedic diseases. Specific applications of characteristic values and formulas based on the principles of general signal processing and data analysis: F represents the frequency-domain characteristic function, which can include, for example, frequency mean value F mean 、frequency center of gravity F center and so on. is the amplitude of the signal at frequency . Frequency mean value (Frequency Mean): i, frequency center of gravity (Frequency Center):

[0108] , the frequency-domain characteristic function is Fourier transform (FT), fast Fourier transform (FFT), and the unit of its result is frequency, F(f), where F represents spectral density, power spectral density, and f represents frequency, and the unit is hertz (Hz).

[0109] Time-domain waveform features: Time-domain waveform features are the waveform features of magnetic signals in the time domain, including the shape, period, phase, etc. of the waveform, which intuitively reflect the variation law and characteristics of the signal. The extracted feature values need to be appropriately processed and analyzed: noise reduction, normalization, etc., to improve the accuracy and reliability of the feature values. At the same time, methods such as machine learning and statistical analysis also need to be combined to deeply analyze the correlation between the feature values and orthopedic diseases. Specific applications of feature values and formulas based on the principles of general signal processing and data analysis: Feature values are usually difficult to represent with a single symbol because they may involve multiple aspects of the waveform, such as period (T), phase (Φ), etc. Period: This usually needs to be estimated through autocorrelation functions and Fourier transforms, and there is no simple formula. Phase: Phase information is usually contained in the imaginary part of the complex signal and is extracted from the real signal through Hilbert transforms. Time-domain waveform features include statistical quantities such as the peak, valley, mean, and variance of the signal, which are directly extracted from the time-domain waveform, and the unit is the same as the signal itself, that is, nanotesla (nT).

[0110] Frequency-domain waveform features: Frequency-domain waveform features are the waveform features of magnetic signals in the frequency domain, including the shape of the spectrum, peak position, etc., which reflect the distribution and variation characteristics of the signal in the frequency domain. The extracted feature values need to be appropriately processed and analyzed: filtering, noise reduction, normalization, etc., to improve the accuracy and reliability of the feature values. At the same time, methods such as machine learning and statistical analysis also need to be combined to deeply analyze the correlation between the feature values and orthopedic diseases. Specific applications of feature values and formulas based on the principles of general signal processing and data analysis:

[0111] Spectral Peak Location: It is found by searching for the maximum value of the spectrum,

[0112] i.e., fpeak ∣X(f)∣.

[0113] Spectral Width: It is estimated by calculating the second moment and fourth moment of the spectrum.

[0114] Frequency-domain waveform features refer to features such as the peak and bandwidth of the spectrum and power spectrum, and the unit is the same as the frequency, that is, hertz (Hz).

[0115] Highest frequency value, lowest frequency value: The highest frequency value and the lowest frequency value respectively represent the highest frequency component and the lowest frequency component in the magnetic signal, reflecting the frequency range and spectral width of the signal. The extracted eigenvalue needs to be processed and analyzed appropriately, such as noise reduction, standardization, etc., to improve the accuracy and reliability of the eigenvalue. At the same time, methods such as machine learning and statistical analysis need to be combined to deeply analyze the correlation between the eigenvalue and orthopedic diseases. Based on the principles of general signal processing and data analysis, the specific application of the eigenvalue and formula: Use f_max to represent the highest frequency value and f_min to represent the lowest frequency value. Among them, the highest frequency value (Maximum Frequency): , the lowest frequency value (Minimum Frequency): .

[0116] Diagnosis and treatment system interface: Integrated into the magnetic analysis system at the doctor's end and runs as an independent module. The high-performance computing platform provides powerful computing capabilities through integrating multi-core processor servers, GPU-accelerated computing nodes, and distributed computing clusters for multi-core processor technology and GPU-accelerated computing. At the same time, parallel computing frameworks such as MapReduce and Spark are used to optimize the running efficiency of complex algorithms to achieve real-time analysis of a large amount of magnetic signal data. Through the development of APIs and database connections, API development technology, database connection technology, and data synchronization mechanism are used to import data such as the basic information, symptoms, diagnosis, and treatment conditions of patients from existing diagnosis and treatment systems and associate them with the results of the magnetic signal analysis system. Although there is no direct corresponding unit for the diagnosis and treatment system interface in terms of hardware, it is closely related to the high-performance computing platform because the import, processing, and correlation analysis of data all require the support of high-performance computing.

[0117] The magnetic analysis system at the medical staff end also has a diagnosis determination link. After processing the collected magnetic signal data through the above steps, the magnetic analysis system at the medical staff end first matches and associates all orthopedic-related symptoms of the patient with the magnetic signal acquisition situation, and all orthopedic-related symptoms of the patient will be imported from another diagnosis and treatment system that records all the basic information, symptoms, diagnosis, and treatment conditions of the patient.

[0118] In the magnetic signal analysis system, the matching and correlation analysis algorithm, combined with the theory of traditional Chinese medicine meridians, establishes a basic correlation analysis model by corresponding eigenvalues to different bone disease types, their related main meridians, acupoints, etc. This model introduces knowledge graph technology to construct an association network between traditional Chinese medicine meridians and bone disease types. A corresponding table is generated according to this model to display the results of the correlation analysis.

[0119] According to the traditional Chinese medicine theory of midnight-noon ebb-flow, acupoint magnetic signals are collected during the seven key daily rest time intervals: Chenshi (07:00 - 09:00), Sishi (09:00 - 11:00), Wushi (11:00 - 13:00), Weishi (13:00 - 15:00), Shenshi (15:00 - 17:00), Youshi (17:00 - 19:00), and Xushi (19:00 - 21:00). Analyze the correlation between the time rhythm of rotator cuff injury, knee arthritis, and osteoporosis and the performance of acupoint magnetic signals.

[0120] The user interface and report generation of the doctor-patient oriented communication platform are shown in Tables 1, 2, and 3 below. The data curve of the meridian magnetic signal of the rotator cuff injury - Jianjing acupoint at Chenshi is as Figure 10 shown.

[0121] Table 1: Meridian magnetic characteristic values of rotator cuff injury at Wushi

[0122]

[0123] Table 2: Meridian magnetic characteristic values of knee arthritis at Wushi

[0124]

[0125] Table 3: Meridian magnetic characteristic values of osteoporosis at Wushi

[0126]

[0127] Through the high-performance computing platform, real-time analysis is performed on a large amount of magnetic signal data by running algorithms. The medical staff user interface includes functional areas such as a text input box, voice / video call buttons, historical message viewing area, and calibration permissions. It displays magnetic detection images, magnetic signal analysis results, and the historical data of patients. It provides a report generation function, allowing medical staff to export detailed diagnostic reports. The doctor-patient oriented communication platform adopts an instant messaging function: an instant messaging module is integrated in the GUI and Web interfaces to provide text, voice, and video communication channels between doctors and patients. The XMPP (Extensible Messaging and Presence Protocol) is used as the instant messaging protocol for doctor-patient communication. Data is transmitted in XML (Extensible Markup Language) format to achieve real-time transmission and reception of text, voice, and video information. It supports the function of offline message storage and synchronization to ensure that both doctors and patients can obtain complete communication records at any time. The message transmission delay < 500ms, and the success rate of offline message synchronization > 99%. The AES (Advanced Encryption Standard) algorithm is used to encrypt instant messaging messages. The patient operation platform decrypts through the corresponding AES decryption algorithm to restore the message content.

[0128] Figure 11 is a flowchart of a human-computer interaction method for orthopedic diseases based on human magnetic signals shown according to an exemplary embodiment, asFigure 11 As shown, applied to a terminal device, the method includes:

[0129] In step 1101, the original magnetic signal data of the area around the acupoint is collected for patients diagnosed with rotator cuff injury, knee arthritis, or osteoporosis through an optical atomic magnetometer sensor.

[0130] In step 1102, during the collection of the original magnetic signal data, the area around the acupoint area is cryogenically treated.

[0131] In step 1103, the original magnetic signal data is filtered through spatial filtering technology to remove the magnetic signal data of non-acupoint areas, obtain the target magnetic signal data, and transmit the target magnetic signal data to the management platform.

[0132] Figure 12 is a flowchart of a human-computer interaction method for orthopedic diseases based on human magnetic signals shown according to an exemplary embodiment. As Figure 12 shown, applied to a management platform, the method includes:

[0133] In step 1201, the target magnetic signal data from the terminal device is received and the target magnetic signal data is analyzed in real time.

[0134] In step 1202, the eigenvalue of the target magnetic signal data is extracted, and according to the theory of the flow of qi and blood along the meridians, a correlation analysis report between the eigenvalue of the target magnetic signal data and different orthopedic diseases is generated to assist doctors in diagnosing patients.

[0135] In summary, the present invention disclosure relates to the technical field of medical detection equipment, and specifically includes a human-computer interaction system and method for orthopedic diseases based on human magnetic signals. The system includes: a terminal device and a management platform; the terminal device includes: a magnetic signal acquisition module, a cryogenic treatment module, and a magnetic signal filtering module. The magnetic signal acquisition module is used to collect the magnetic signals around the acupoint through an optical atomic magnetometer sensor; the cryogenic treatment module is used to perform cryogenic treatment on the area around the acupoint area; the magnetic signal filtering module is used to filter the original magnetic signal data to remove the magnetic signal data of non-acupoint areas; the management platform is used to extract the eigenvalue of the target magnetic signal data and generate a correlation analysis report between the eigenvalue and orthopedic diseases. It can filter out noise interference by combining optical atomic magnetometers, cryogenic treatment, and non-acupoint area magnetic signal filtering technology, improve the reliability of data collection, and facilitate the conversion of magnetic information into a visual effect of traditional Chinese medicine meridians after analysis.

[0136] The preferred embodiments of the present disclosure have been described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0137] In addition, it should be noted that, among the various specific technical features described in the above specific embodiments, they can be combined in any appropriate manner without conflict. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination manners.

[0138] Furthermore, any combination can be made among various different embodiments of the present disclosure, as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

Claims

1. An orthopedic disease human-computer interaction system based on human magnetic signals, characterized in that, The system includes: a terminal device and a management platform, and data interaction is carried out between the terminal device and the management platform; The terminal device includes: a magnetic signal acquisition module, a low-temperature treatment module, and a magnetic signal filtering module, and the low-temperature treatment module and the magnetic signal filtering module are arranged inside the magnetic signal acquisition module; The magnetic signal acquisition module can be adsorbed in the surrounding area of the acupoint area, and is used to collect the original magnetic signal data of the surrounding area of the acupoint for patients diagnosed with rotator cuff injury, knee arthritis or osteoporosis through an optical atomic magnetometer; The low-temperature treatment module, connected to the magnetic signal acquisition module, is used to perform low-temperature treatment on the surrounding area of the acupoint area during the acquisition process of the original magnetic signal data; The magnetic signal filtering module, connected to the low-temperature treatment module, is used to filter the original magnetic signal data through spatial filtering technology, remove the magnetic signal data of non-acupoint areas, obtain target magnetic signal data, and transmit the target magnetic signal data to the management platform; The management platform, connected to the magnetic signal filtering module, is used to extract the characteristic values of the target magnetic signal data, and generate a correlation analysis report between the characteristic values of the target magnetic signal data and different orthopedic diseases according to the theory of the flow of qi and blood along the meridians, so as to assist doctors in diagnosing patients.

2. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, wherein The magnetic signal acquisition module includes several cube structures, and the top end of the cube structure is made of an adhesive material so that the cube structure can be adsorbed in the surrounding area of the acupoint area.

3. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, characterized in that, The terminal device further includes: a processor and a display screen; the processor is used to control the startup of the terminal device, the acquisition and transmission of the original magnetic signal by the magnetic signal acquisition module, and the automatic calibration of the magnetic signal acquisition module; The display screen is used to display the prompt of the acquisition time point of the original magnetic signal, the prompt of the acquisition area of the original magnetic signal, and the completion status of the acquisition of the original magnetic signal.

4. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, wherein, The low-temperature treatment module is a semiconductor refrigeration chip and is used to perform low-temperature treatment on the surrounding area of the acupoint area; The outside of the low-temperature treatment module is wrapped with a heat-insulating material.

5. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, characterized in that, The magnetic signal filtering module is used for: Performing spatial distribution characteristic analysis on the original magnetic signal data obtained by the magnetic signal acquisition module to obtain the spatial distribution characteristics of the original magnetic signal data; According to the spatial distribution characteristics, performing spatial smoothing processing on the original magnetic signal data through median filtering and mean filtering of spatial filtering technology to remove the interference of spatial noise and magnetic signal data of non-acupoint areas and obtain target magnetic signal data; Transmitting the target magnetic signal data to the management platform.

6. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, wherein Before the magnetic signal filtering module filters the original magnetic signal data through spatial filtering technology and removes the magnetic signal data of non-acupoint areas, it further includes: Performing time-domain analysis on the original magnetic signal data to obtain the time series characteristics of the original magnetic signal data; Performing frequency-domain analysis on the original magnetic signal data to obtain the frequency components of the original magnetic signal data; Based on the time series characteristics and frequency components of the original magnetic signal data, identify the characteristics of the magnetic signal data in the non-acupoint area of the original magnetic signal data, and take corresponding measures in the time domain and frequency domain to smooth and attenuate the non-target frequency components, so as to obtain the original magnetic signal data with the magnetic signal data in the non-acupoint area preliminarily filtered out.

7. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, characterized in that, The management platform is used to support the guidance of magnetic acquisition operation problems, the tracking of the patient's condition, and the prompt examination and follow-up visit when needed between doctors and patients through text, voice and video calls.

8. The orthopedic disease human-computer interaction system based on human magnetic signals according to claim 1, wherein The management platform is used to receive the automatic calibration instruction of the magnetic signal acquisition module and send the automatic calibration instruction to the terminal device; The terminal device controls the magnetic signal acquisition module to start the automatic calibration program according to the automatic calibration instruction; The terminal device controls the optical atomic magnetometer to be preheated; The terminal device applies a standard magnetic signal to the optical atomic magnetometer through the built-in standard magnetic field source, so that the optical atomic magnetometer outputs the collected magnetic signal data under the action of the standard magnetic signal; The terminal device compares the collected magnetic signal data with the standard magnetic signal, calculates the error, and adjusts the sensitivity and offset of the optical atomic magnetometer according to the comparison result to ensure the accuracy of the calibration result.

9. A human-computer interaction method for orthopedic diseases based on human magnetic signals, characterized in that, Applied to a terminal device, the method includes: Collect the original magnetic signal data of the area around the acupoints of patients diagnosed with rotator cuff injury, knee arthritis or osteoporosis through an optical atomic magnetometer; During the collection of the original magnetic signal data, perform cryogenic treatment on the area around the acupoint area; Filter the original magnetic signal data through spatial filtering technology, remove the magnetic signal data in the non-acupoint area, obtain the target magnetic signal data, and transmit the target magnetic signal data to the management platform.

10. An orthopedic disease human-computer interaction method based on human magnetic signals, characterized in that, Applied to a management platform, the method includes: Receive the target magnetic signal data from the terminal device and perform real-time analysis on the target magnetic signal data; Extract the characteristic values of the target magnetic signal data, and generate a correlation analysis report between the characteristic values of the target magnetic signal data and different orthopedic diseases according to the theory of meridian flow and infusion, so as to assist doctors in diagnosing patients.

Images