A statistical analysis-based method and system for assessing pilot cellular health status

Abstract

This application relates to the field of pilot health assessment technology, and provides a method and system for assessing pilot cellular health status based on statistical analysis. The method includes: acquiring the pilot's initial physiological information and mission environment information; removing interfering physiological information caused by external interference from the initial physiological information based on the mission environment information to obtain pure physiological information; determining the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in the pure physiological information; determining the pilot's cellular health status information based on the causal relationship and the measured values ​​of the measurement indicators; and determining the pilot's health adjustment strategy based on the pilot's cellular health status information. This approach can improve the accuracy of pilot cellular health status assessment.

Description

Technical Field

[0001] This application relates to the field of pilot health assessment technology, and in particular to a method and system for assessing pilot cellular health status based on statistical analysis. Background Technology

[0002] While existing methods and systems for assessing cellular health perform well in routine flight missions to ensure flight safety and mission success, their assessment capabilities face significant challenges when dealing with novel, high-intensity flight missions. These special missions exert unprecedented and complex physiological effects on pilots, leading to nonlinear and unconventional variations at the cellular level. Furthermore, the data acquisition process is contaminated with significant noise and high-dimensional information, and lacks supporting medical knowledge, making it difficult for traditional assessment methods to accurately identify and interpret potential health risks.

[0003] Specifically, during the execution of new high-intensity missions, the high-intensity maneuvering and complex cockpit environment introduce a large amount of unprecedented noise and artifacts into the physiological data acquisition process. For example, under instantaneous high G-forces, even minor tremors in the pilot's body can cause severe fluctuations in the data from wearable sensors; electromagnetic interference generated by new electronic devices in the cockpit can affect the accuracy of bioelectrical signals (such as electrocardiograms and electroencephalograms); and rapid changes in air pressure and temperature can also interfere with the readings of optical sensors (such as blood oxygen saturation monitors). These noises and artifacts are not randomly distributed but are highly correlated with mission intensity and environmental factors, exhibiting complex non-Gaussian distribution characteristics, resulting in lower accuracy in assessing the pilot's cellular health status. Summary of the Invention

[0004] This application provides a statistical analysis-based method and system for assessing pilot cellular health status, which can improve the accuracy of pilot cellular health status assessment.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a statistical analysis-based method for assessing pilot cellular health status is provided, comprising the following steps: acquiring the pilot's initial physiological information and mission environment information; removing interfering physiological information caused by external interference from the initial physiological information based on the mission environment information to obtain pure physiological information; determining the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in the pure physiological information; the causal relationship is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator; determining the pilot's cellular health status information based on the causal relationship and the measured values ​​of the measurement indicators; and determining the pilot's health adjustment strategy based on the pilot's cellular health status information.

[0006] Furthermore, when the mission environment information includes gravity sensing data and body tremor data, and the initial physiological information includes the initial electrocardiogram signal, the interference physiological information caused by external interference in the initial physiological information is removed based on the mission environment information to obtain pure physiological information. This includes: determining whether the gravity sensing data is greater than a preset gravity sensing data threshold; if so, determining the artifact electrocardiogram signal caused by the pilot's body tremor based on the body tremor data; and removing the artifact electrocardiogram signal from the initial electrocardiogram signal to obtain the pure electrocardiogram signal.

[0007] Furthermore, the gravity sensing data includes gravity G-values. Based on body tremor data, the artifact ECG signal generated by the pilot's body tremor is determined, including: acquiring a preset tremor-ECG signal transfer function and a first preset correspondence; the first preset correspondence includes a one-to-one correspondence between multiple gravity G-value ranges and multiple first adjustment coefficients; using the first adjustment coefficient corresponding to the gravity G-value range in the first preset correspondence as a target first adjustment coefficient; adjusting the parameter values ​​of the target parameters in the preset tremor-ECG signal transfer function according to the target first adjustment coefficient to obtain the target tremor-ECG signal transfer function; inputting the body tremor data into the target tremor-ECG signal transfer function to obtain the artifact ECG signal output by the target tremor-ECG signal transfer function.

[0008] In some preferred embodiments, when the task environment information includes electromagnetic sensing data, removing interfering physiological information caused by external interference from the initial physiological information to obtain pure physiological information includes: inputting the initial physiological information into a preset independent component analysis model to obtain multiple initial sub-physiological information of different frequencies; the preset independent component analysis model is used to divide the initial physiological information into multiple initial sub-physiological information of different frequencies; obtaining a second preset correspondence; the second preset correspondence includes multiple electromagnetic frequency ranges and multiple first frequency ranges; taking the first frequency range corresponding to the electromagnetic frequency range in the electromagnetic sensing data in the second preset correspondence as the interference frequency range; removing the initial sub-physiological information whose frequency falls within the interference frequency range from the multiple initial sub-physiological information to obtain pure physiological information.

[0009] This application also proposes determining the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in pure physiological information, including: for any two measurement indicators among the multiple measurement indicators, determining the convergence cross-mapping score of one measurement indicator relative to the other measurement indicator based on the measured values ​​of the two measurement indicators and a preset convergence cross-mapping model; determining whether the absolute value of the difference between the convergence cross-mapping scores of the two measurement indicators is greater than a preset score threshold; if so, taking the measurement indicator with the larger convergence cross-mapping score as the cause measurement indicator in the causal relationship; taking the measurement indicator with the smaller convergence cross-mapping score as the effect measurement indicator of the cause measurement indicator in the causal relationship; if not, determining that the two measurement indicators do not have a causal relationship.

[0010] Based on this, the measurement index with the larger convergence cross-mapping score among the two measurement indices is designated as the causal measurement index; the measurement index with the smaller convergence cross-mapping score among the two measurement indices is designated as the effect measurement index. This includes: designating the measurement index with the larger convergence cross-mapping score as the initial causal measurement index; designating the measurement index with the smaller convergence cross-mapping score among the two measurement indices as the initial effect measurement index; inputting the measured values ​​of the initial causal measurement index and the initial effect measurement index into a pre-defined permutation test model to obtain the permutation test result output by the pre-defined permutation test model; the pre-defined permutation test model is used to perform permutation tests on the measured values ​​of the initial causal measurement index and the initial effect measurement index; when the permutation test result indicates that the initial causal measurement index and the initial effect measurement index pass the permutation test, it is determined that the two measurement indices have a causal relationship, where the initial causal measurement index is the causal measurement index and the initial effect measurement index is the effect measurement index; when the permutation test result indicates that the initial causal measurement index and the initial effect measurement index fail the permutation test, it is determined that the two measurement indices do not have a causal relationship.

[0011] To improve the scheme, the pilot's cell health status information is determined based on causal relationships and the measured values ​​of measurement indicators, including: obtaining a third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple cell health status information and multiple first information, the first information including multiple target measurement indicators; determining the target first information that includes two measurement indicators with a causal relationship among the multiple first information; when the measured values ​​of the two measurement indicators with a causal relationship exceed the corresponding normal measurement value range, the cell health status information corresponding to the target first information in the third preset correspondence is taken as the pilot's cell health status information.

[0012] As a technological improvement, a pilot's health adjustment strategy is determined based on the pilot's cellular health status information, including: calling a preset health adjustment strategy determination model; the preset health adjustment strategy determination model is used to determine a health adjustment strategy based on the cellular health status information; inputting the pilot's cellular health status information into the preset health adjustment strategy determination model, and using the health adjustment strategy output by the preset health adjustment strategy determination model as the pilot's initial health adjustment strategy; adjusting the pilot's initial health adjustment strategy according to the duration of the pilot's pending task to obtain the pilot's health adjustment strategy.

[0013] As a further improvement, the health adjustment strategy includes an adjustment strategy and adjustment parameters. The initial health adjustment strategy of the pilot is adjusted according to the mission duration of the task to be performed, resulting in the pilot's health adjustment strategy. This includes: obtaining a preset duration coefficient; using the mission duration of the task to be performed and the preset duration coefficient as parameter adjustment coefficients; and adjusting the parameter values ​​of the adjustment parameters in the initial health adjustment strategy of the pilot according to the parameter adjustment coefficients, thus obtaining the pilot's health adjustment strategy.

[0014] Secondly, this application also discloses a pilot cellular health status assessment system based on statistical analysis, comprising: an acquisition device and a processing device; the acquisition device is used to acquire the pilot's initial physiological information and mission environment information; the processing device is used to remove interfering physiological information caused by external interference from the initial physiological information based on the mission environment information to obtain pure physiological information; the processing device is used to determine the causal relationship between multiple measurement indicators based on the measurement values ​​of multiple measurement indicators in the pure physiological information; the causal relationship is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator; the processing device is used to determine the pilot's cellular health status information based on the causal relationship and the measurement values ​​of the measurement indicators; the processing device is used to determine the pilot's health adjustment strategy based on the pilot's cellular health status information.

[0015] Beneficial Effects: This application discloses a statistical analysis-based method for assessing pilot cellular health status. By acquiring the pilot's initial physiological information and mission environment information, and removing interfering physiological information caused by external interference based on the mission environment information, pure physiological information is obtained. This effectively solves the problem of a large amount of noise and artifacts mixed in during the physiological data acquisition process in high-intensity flight missions, ensuring the data quality of subsequent analysis. Based on this, this application determines the causal relationships between multiple measurement indicators in the pure physiological information, overcoming the limitations of traditional statistical methods in handling high-dimensional, high-noise data and inability to reveal nonlinear associations. This provides a new perspective for accurately identifying complex variation patterns at the cellular level.

[0016] Furthermore, this application determines pilots' cellular health status information based on causal relationships and measured values ​​of indicators, effectively addressing the limitations of existing cellular health classification methods in handling complex cellular variation patterns induced by specific missions, thus improving the accuracy and reliability of the assessment. Finally, determining pilots' health adjustment strategies based on their cellular health status information provides practically applicable personalized health intervention strategies, overcoming the shortcomings of existing technologies that cannot provide clear explanations for the specific causes of cellular abnormalities or offer effective intervention strategies. In summary, this application, through a series of innovative technical solutions, comprehensively improves the accuracy, reliability, and practicality of pilot cellular health status assessment, providing strong support for ensuring pilot health and flight safety. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a method for assessing pilot cellular health status based on statistical analysis, provided in this application; Figure 2 A flowchart illustrating yet another statistical analysis-based method for assessing pilot cellular health status provided in this application; Figure 3 A flowchart illustrating yet another statistical analysis-based method for assessing pilot cellular health status provided in this application; Figure 4 This application provides a schematic diagram of the architecture of a pilot cell health status assessment system based on statistical analysis. Detailed Implementation

[0018] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0020] like Figure 1As shown, this application proposes a method for assessing the cellular health status of pilots based on statistical analysis, including the following steps: S101. Obtain the pilot's initial physiological information and mission environment information.

[0021] S102. Based on the task environment information, remove the interfering physiological information caused by external interference from the initial physiological information to obtain pure physiological information.

[0022] S103. Determine the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in pure physiological information.

[0023] Causality is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator.

[0024] S104. Determine the pilot's cellular health status information based on causal relationships and measured values ​​of measurement indicators.

[0025] S105. Determine pilot health adjustment strategies based on pilot's cellular health status information.

[0026] This application acquires the pilot's initial physiological and mission environment information, and then uses the mission environment information to purify the initial physiological information, obtaining pure physiological data. This effectively solves the problem of significant noise and artifacts mixed into physiological data under high-intensity mission environments. Subsequently, based on multiple measurement indicators in the pure physiological data, this application further determines the causal relationships between these indicators, which helps to reveal complex nonlinear correlations at the cellular level. Finally, by combining the causal relationships and the measured values ​​of the indicators, this application can accurately assess the pilot's cellular health status and formulate personalized health adjustment strategies accordingly, thereby overcoming the shortcomings of traditional methods in processing complex data, identifying nonlinear variations, and providing effective intervention strategies.

[0027] To better understand the technical solution proposed in this application, some key terms involved will be explained first.

[0028] "Initial physiological information" refers to raw physiological data collected directly from pilots, which may include various physiological parameters such as electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, blood oxygen saturation, body temperature, and blood pressure. This information forms the basis for assessing a pilot's health status, but in actual collection, it is often subject to interference from various external factors.

[0029] "Mission environment information" refers to the environmental parameters in which a pilot operates during a mission, such as gravity sensor data, body tremor data, electromagnetic sensor data, air pressure, and temperature. This information is crucial for identifying and removing external interference from physiological data.

[0030] "Interference with physiological information" refers to non-physiological components that appear in the original physiological information due to the influence of external environmental factors (such as body tremors, electromagnetic interference, etc.) on the physiological signal acquisition process. Accurately identifying and removing this interference information is the key to obtaining "pure physiological information".

[0031] "Pure physiological information" refers to physiological data that, after being processed to remove external interference, can more accurately reflect the pilot's physiological state.

[0032] "Measurement indicators" refer to specific physiological parameters extracted from pure physiological information, such as heart rate variability, concentration of specific biomarkers, and cell morphology parameters.

[0033] A causal relationship refers to the association between multiple measurement indicators, where a change in one indicator directly or indirectly leads to a change in another. Identifying such causal relationships helps to gain a deeper understanding of the underlying mechanisms of changes in cellular health.

[0034] "Cellular health status information" refers to a comprehensive assessment of a pilot's cellular health status, which may include cell viability, degree of damage, and stress response level.

[0035] "Health adjustment strategy" refers to a personalized health intervention plan developed for pilots based on their cellular health status information, such as adjusting training plans, providing nutritional supplementation recommendations, and adjusting rest plans.

[0036] The method proposed in this application first requires obtaining the pilot's initial physiological information and mission environment information.

[0037] Initial physiological information can be acquired in several ways. For example, wearable sensors, such as smartwatches, heart rate monitors, and EEG caps, can be used to monitor pilots' electrocardiogram signals, blood oxygen saturation, body temperature, skin conductance, and other physiological parameters in real time. These sensors are typically integrated into pilots' personal equipment and can continuously and non-invasively collect data. Another approach is to use implantable or semi-implantable medical devices to acquire deeper physiological data under specific conditions, such as miniature sensors used to monitor specific biomarkers or cell activity.

[0038] The acquisition of mission environmental information is also diverse. For example, environmental sensors integrated into the aircraft or cockpit can acquire gravity sensing data (such as G-forces), body tremor data, electromagnetic sensing data, air pressure, temperature, humidity, and other data. Furthermore, mission parameters such as mission type, mission duration, flight altitude, and maneuver intensity can be obtained through the flight mission management system. This environmental information is collected simultaneously with physiological information, providing context for subsequent interference removal and health assessment.

[0039] After obtaining the initial physiological information and task environment information, this application will remove the interfering physiological information caused by external interference from the initial physiological information based on the task environment information, thereby obtaining pure physiological information.

[0040] For example, when pilots perform high-intensity maneuvers, their bodies may experience severe tremors, leading to artifacts in the electrocardiogram (ECG) signal. In this case, gravity sensor data and body tremor data from the mission environment can be used to identify and remove these artifacts. Specifically, a preset gravity sensor data threshold can be set. When the gravity sensor data (e.g., the G-force) exceeds this threshold, it indicates that the pilot may be experiencing high-intensity maneuvers, increasing the likelihood of body tremors. At this point, the artifact ECG signal caused by body tremors can be estimated based on the body tremor data and a pre-established tremor-ECG signal transfer function. Subsequently, subtracting the estimated artifact ECG signal from the initial ECG signal yields the pure ECG signal.

[0041] For example, in complex cockpit environments, new electronic devices may generate electromagnetic interference, affecting the accuracy of bioelectrical signals. In such cases, electromagnetic sensing data from the mission environment information can be used to identify and remove electromagnetic interference. Specifically, initial physiological information can be input into a pre-defined independent component analysis model, which decomposes the initial physiological information into multiple initial sub-physiological information of different frequencies. Simultaneously, a second pre-defined correspondence is obtained, which includes multiple electromagnetic frequency ranges and multiple first frequency ranges. By analyzing the electromagnetic frequencies in the electromagnetic sensing data, the electromagnetic frequency range in which the information falls is determined, and the corresponding first frequency range is identified as the interference frequency range. Finally, by removing the initial sub-physiological information whose frequencies fall within the interference frequency range, pure physiological information can be obtained.

[0042] After obtaining pure physiological information, this application will determine the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in the pure physiological information.

[0043] For example, for any two measurements in pure physiological information, such as heart rate variability (HRV) and blood oxygen saturation (SpO2), a convergent cross-mapping score can be determined relative to the other measurement based on their measured values ​​and a pre-defined convergent cross-mapping model. Convergent cross-mapping (CCM) is a non-linear time series analysis method used to detect causal relationships between variables in complex systems. By calculating the convergent cross-mapping scores of two measurements, the existence of a causal association between them can be assessed.

[0044] Next, it is determined whether the absolute value of the difference between the convergence cross-mapping scores of the two measurement indicators is greater than a preset score threshold. If the absolute value of the difference is greater than the preset score threshold, the two measurement indicators are considered to have a causal relationship. In this case, the measurement indicator with the larger convergence cross-mapping score is taken as the cause measurement indicator in the causal relationship, and the measurement indicator with the smaller convergence cross-mapping score is taken as the effect measurement indicator of the cause measurement indicator in the causal relationship. If the absolute value of the difference is not greater than the preset score threshold, the two measurement indicators are determined not to have a causal relationship.

[0045] After establishing the causal relationship between the measurement indicators, this application will determine the pilot's cellular health status information based on the causal relationship and the measured values ​​of the measurement indicators.

[0046] Specifically, a third pre-defined correspondence can be established, which includes a one-to-one correspondence between multiple cell health status information and multiple primary information. Each piece of primary information contains multiple target measurement indicators. By analyzing the established causal relationships, two measurement indicators with a causal relationship are identified, and the target primary information containing these two measurement indicators is determined. Subsequently, the measurement values ​​of these two causally related measurement indicators are monitored.

[0047] When the measured values ​​of these two indicators exceed their corresponding normal measurement ranges, the cell health status information corresponding to the first information of the target in the third preset correspondence can be used as the pilot's cell health status information. For example, if a causal relationship is found between heart rate variability (cause indicator) and blood oxygen saturation (effect indicator), and their measured values ​​deviate from the normal range simultaneously, they can be mapped to a specific cell health status, such as "abnormal cell energy metabolism" or "elevated oxidative stress level," according to the preset correspondence.

[0048] Finally, this application will determine the pilot's health adjustment strategy based on the pilot's cellular health status information.

[0049] For example, a pre-defined health adjustment strategy determination model can be invoked, which can determine the corresponding health adjustment strategy based on cellular health status information. By inputting the pilot's cellular health status information into this model, the model will output an initial health adjustment strategy. This initial strategy may include dietary recommendations, exercise programs, and rest schedules. To make the strategy more targeted, this application will also adjust the initial health adjustment strategy according to the duration of the pilot's upcoming mission. For example, if the mission duration is long, it may be necessary to increase rest time, adjust nutritional supplementation plans, or conduct specific anti-fatigue training to ensure the pilot maintains optimal condition during the mission. In this way, the final pilot health adjustment strategy can be obtained.

[0050] The statistical analysis-based pilot cellular health status assessment method proposed in this application works by constructing a closed-loop system from data acquisition to strategy formulation, aiming to solve the assessment challenges of traditional methods in complex and high-intensity flight mission scenarios. First, it lays the foundation for subsequent data processing by acquiring the pilot's initial physiological information and mission environment information. This step is crucial because raw physiological data is often affected by various external factors and cannot be directly used for accurate assessment.

[0051] Subsequently, the core of this application lies in "purifying" the initial physiological information using task environment information, removing interfering physiological information caused by external interference, thereby obtaining pure physiological information. This step is crucial for solving the challenges of high-noise, high-dimensional data. For example, in high-G overload or electromagnetic interference environments, by analyzing gravity sensing data, body tremor data, or electromagnetic sensing data, artifacts or noise components in physiological signals can be accurately identified and removed. This data purification mechanism ensures that the physiological data on which subsequent analysis is based is real and reliable, avoiding the "curse of dimensionality" and information overload problems, allowing effective features to stand out from the noise.

[0052] After obtaining purified physiological information, this application further uses statistical analysis methods to determine the causal relationships among multiple measurement indicators within the purified physiological information. Traditional methods often only focus on the correlation between indicators, neglecting their inherent causal chains. By identifying causal relationships, this application can gain a deeper understanding of the driving factors and transmission pathways of changes at the cellular level. For example, when it is found that a change in one cell metabolic indicator is the "cause" of a change in another cell damage indicator, this causal relationship provides a stronger explanatory power for subsequent health status assessments and also points the way for the formulation of intervention strategies. This revelation of causal relationships effectively solves the problem that traditional methods are unable to explain complex cellular variation patterns.

[0053] Based on established causal relationships and measured values ​​of indicators, this application can accurately determine the cellular health status information of pilots. By combining causal relationships with actual measured values, a more comprehensive and refined assessment of the pilot's cellular health status can be achieved. For example, when multiple causally related indicators simultaneously exceed the normal range, it is possible to more accurately determine whether the pilot has specific cellular dysfunction or damage. This comprehensive assessment method overcomes the shortcomings of traditional methods in identifying complex cellular variation patterns induced by specific tasks, thus improving the accuracy and reliability of the assessment.

[0054] Ultimately, this application determines personalized health adjustment strategies based on the pilot's cellular health status information. This step is the final goal of the entire method and reflects its innovative value. Through precise assessment of cellular health status, the system can provide pilots with personalized intervention plans that have practical guidance. For example, if the assessment results show that the pilot has mitochondrial dysfunction, specific nutritional supplements or training programs can be recommended to improve mitochondrial function. In addition, this application also considers factors such as the duration of the mission to be performed to adjust the strategy, making the health adjustment strategy more adaptable and effective. This solves the problem that traditional methods cannot provide clear explanations and effective intervention strategies.

[0055] In summary, this application, through a series of steps including data cleansing, causal relationship identification, comprehensive evaluation, and personalized strategy formulation, forms an organic whole. This allows the various technical features to work together to solve the technical problems of existing technologies in processing high-noise, high-dimensional data, identifying complex cell mutation patterns, and providing effective intervention strategies. This significantly improves the accuracy, reliability, and practicality of pilot cell health status assessment.

[0056] like Figure 2 As shown, this application further proposes a method for assessing pilot cellular health status based on statistical analysis. When the mission environment information includes gravity sensor data and body tremor data, and the initial physiological information includes initial electrocardiogram signals, the method removes interfering physiological information caused by external interference from the initial physiological information based on the mission environment information to obtain pure physiological information, including: S201. Determine whether the gravity sensing data is greater than the preset gravity sensing data threshold.

[0057] S202. If so, determine the artifact ECG signal caused by the pilot's body tremor based on the body tremor data.

[0058] S203. Remove artifact ECG signals from the initial ECG signal to obtain a pure ECG signal.

[0059] Specifically, mission environment information can be understood as the external environmental conditions in which the pilot operates during a mission. Gravity sensing data refers to data used to measure the force of gravity or acceleration experienced by the pilot, such as the G-value obtained through an accelerometer or gyroscope. Body tremor data refers to data reflecting the pilot's body shaking or vibration, such as signals obtained through electromyography (EMG) sensors or vibration sensors. Initial physiological information can be understood as the pilot's raw, unprocessed physiological data. Initial electrocardiogram (ECG) signals refer to the pilot's raw ECG signals, which may contain artifacts caused by external interference.

[0060] The preset gravity sensor data threshold is a pre-defined value designed to determine whether the gravity sensor data reaches a level that could potentially cause significant body tremors. When the gravity sensor data exceeds this threshold, it indicates that the pilot may be under high G-load or in a state of strenuous activity, at which point the likelihood of body tremors causing artifacts in the electrocardiogram (ECG) signal increases. Artifact ECG signals are interference signals superimposed on the true ECG signal caused by non-cardiac activities such as pilot body tremors. The process of identifying artifact ECG signals aims to accurately quantify and separate these interference components.

[0061] Removing artifacts from the initial electrocardiogram (ECG) signal is typically achieved through signal processing techniques, such as filtering, independent component analysis (ICA), or adaptive noise cancellation, to strip away artifact components from the original signal, resulting in a purer ECG signal. A pure ECG signal refers to an ECG signal that has been processed to remove external interference (especially artifacts caused by body tremors), and it can more accurately reflect the pilot's cardiac physiological activity.

[0062] This application's solution, by introducing the judgment and utilization of gravity sensing data and body tremor data, can more accurately identify and remove external interferences to the initial electrocardiogram (ECG) signal under specific mission conditions. Specifically, when the gravity sensing data exceeds a preset threshold, the system is triggered to identify artifact ECG signals that may be caused by body tremors. This reflects the significant impact of body tremors on physiological signals during high-G or strenuous exercise for pilots. By specifically identifying artifact ECG signals based on body tremor data, interference caused by tremors can be modeled and extracted in a targeted manner, rather than simply performing general filtering. As a result, artifact ECG signals in the initial ECG signal are effectively removed, thereby ensuring higher purity and accuracy of the physiological data upon which subsequent cellular health status assessments depend.

[0063] Through the above technical solution, this application effectively addresses the problem that traditional methods struggle to accurately remove the influence of various external interferences on physiological signals (especially electrocardiogram signals) in complex mission environments. This solution combines gravity sensing data and body tremor data to achieve intelligent identification and targeted removal of specific types of interference (such as artifacts caused by body tremors), significantly improving the quality of pure physiological information. Consequently, the assessment of pilots' cellular health status will be more accurate and reliable, providing a solid data foundation for developing personalized health adjustment strategies, thereby enhancing pilot flight safety and mission execution efficiency.

[0064] This application further proposes a specific method for determining the artifact ECG signal generated by the pilot's body tremor based on body tremor data when the gravity sensing data includes the gravity G value. The accuracy of artifact ECG signal determination is improved by dynamically adjusting the tremor-ECG signal transfer function.

[0065] Specifically, the aforementioned determination of artifact ECG signals caused by pilot tremor based on tremor data includes: Obtain a preset tremor-ECG signal transfer function and a first preset correspondence; the first preset correspondence includes a one-to-one correspondence between multiple gravity G-value ranges and multiple first adjustment coefficients; use the first adjustment coefficient corresponding to the gravity G-value range in the first preset correspondence as the target first adjustment coefficient; adjust the parameter values ​​of the target parameters in the preset tremor-ECG signal transfer function according to the target first adjustment coefficient to obtain the target tremor-ECG signal transfer function; input the body tremor data into the target tremor-ECG signal transfer function to obtain the artifact ECG signal output by the target tremor-ECG signal transfer function.

[0066] Gravity sensing data can be specifically represented as the G-force, which is used to quantify the acceleration or gravitational load experienced by the pilot during flight. The pre-defined tremor-ECG transfer function is a mathematical model or algorithm that describes how body tremor data is transformed into artifact components in the ECG signal. This transfer function is typically constructed based on extensive experimental data and physiological principles to capture the intrinsic relationship between body tremors and ECG artifacts. The first pre-defined correspondence is a pre-established mapping table or function that associates different ranges of G-force with corresponding adjustment coefficients. For example, in low-G-force environments, body tremors may have a smaller impact on the ECG signal, and the corresponding adjustment coefficient will weaken the transfer function's response to tremors; while in high-G-force environments, body tremors may more easily cause significant ECG artifacts, and the corresponding adjustment coefficient will strengthen the transfer function's response to tremors.

[0067] Specifically, the first adjustment coefficient is obtained by searching or calculating from a first preset correspondence based on the current G-force of the pilot. This adjustment coefficient is used to correct one or more target parameters in the preset tremor-ECG signal transfer function. Target parameters can be the transfer function's gain, frequency response characteristics, or time constant, etc. By adjusting these parameters, the transfer function can better adapt to the physiological response characteristics under the current G-force. After adjustment, the resulting target tremor-ECG signal transfer function can more accurately simulate the interference of body tremors on ECG signals under the current gravity environment. Finally, by inputting the real-time acquired body tremor data into this dynamically adjusted target tremor-ECG signal transfer function, a more accurate artifact ECG signal can be output.

[0068] The proposed solution dynamically modifies the tremor-ECG signal transfer function by introducing gravity G-force as an adjustment factor. Specifically, the coupling mechanism and intensity of body tremor to ECG signals may change when pilots experience different gravity G-forces. For example, in a high G-force environment, the tension of body muscles and the state of blood circulation may differ from those in a low G-force environment, resulting in different degrees of ECG artifacts for the same tremor amplitude.

[0069] By acquiring the current gravity G value and determining the corresponding target adjustment coefficient using a first preset correspondence, the target parameters in the preset tremor-ECG signal transfer function can be adaptively adjusted. This adjustment allows the transfer function to better reflect the physiological characteristics under the current gravity environment, thereby more accurately converting body tremor data into artifact ECG signals. This avoids the artifact signal estimation bias that may occur when using a single fixed model under different gravity environments, improving the accuracy of artifact removal.

[0070] Through the above technical solution, this application can dynamically adjust the model parameters used to determine artifact ECG signals based on the actual gravity environment of the pilot. This significantly improves the accuracy of identifying and removing artifacts caused by body tremors from the initial ECG signal. Compared to traditional methods that do not consider the influence of gravity G-forces, this application can more accurately separate pure ECG signals, thereby providing a more reliable physiological data basis for subsequent cellular health status assessment, and thus improving the accuracy and reliability of pilot health status assessment.

[0071] This application further proposes a method for obtaining pure physiological information by analyzing the interference physiological information caused by external interference in the initial physiological information based on the task environment information, when the task environment information includes electromagnetic sensing data. The specific steps of this method include: Initial physiological information is input into a preset independent component analysis model to obtain multiple initial sub-physiological information of different frequencies. The preset independent component analysis model is used to divide the initial physiological information into multiple initial sub-physiological information of different frequencies. A second preset correspondence is obtained. The second preset correspondence includes multiple electromagnetic frequency ranges and multiple first frequency ranges. The first frequency range corresponding to the electromagnetic frequency range in the electromagnetic sensing data in the second preset correspondence is taken as the interference frequency range. Initial sub-physiological information whose frequencies fall within the interference frequency range is removed from the multiple initial sub-physiological information to obtain pure physiological information.

[0072] Specifically, initial physiological information can be understood as raw physiological data obtained from the pilot's body, such as electrocardiogram (ECG), electroencephalogram (EEG), and electromyogram (EMG) signals. Preset independent component analysis (PICA) is a signal processing technique aimed at separating mixed signals into statistically independent non-Gaussian components. In this application, this model is used to decompose the raw initial physiological information into multiple frequency-independent initial sub-physiological information, each representing a component of the original signal within a specific frequency range. For example, this model can decompose a broadband physiological signal into multiple narrowband frequency components, thus facilitating the identification and processing of interference at specific frequencies.

[0073] The second preset correspondence can be understood as a pre-established mapping table or rule set, the purpose of which is to associate the frequency characteristics of detected electromagnetic interference with the frequency ranges that may be affected in physiological signals. This correspondence includes a one-to-one correspondence between multiple electromagnetic frequency ranges and multiple first frequency ranges. For example, when electromagnetic sensing data detects electromagnetic waves within a specific frequency range, this correspondence can indicate in which frequency range of the physiological signal the electromagnetic wave may cause interference. The electromagnetic frequency range refers to the frequency interval of the electromagnetic waves measured by the electromagnetic sensing data, while the first frequency range refers to the frequency interval corresponding to that electromagnetic frequency range that may be affected in the initial sub-physiological information.

[0074] In practical applications, electromagnetic frequencies in electromagnetic sensing data refer to the frequency components of environmental electromagnetic waves detected in real time or periodically by electromagnetic sensors. By matching these electromagnetic frequencies with a second preset correspondence, the interference frequency range corresponding to electromagnetic interference in the current environment can be determined. The interference frequency range is the specific frequency interval that needs to be identified and removed from the initial sub-physiological information. Subsequently, by identifying and removing those initial sub-physiological information whose frequencies fall within this interference frequency range, electromagnetic interference can be effectively stripped from the original physiological signal, thereby obtaining purer physiological information.

[0075] This application's solution addresses the impact of electromagnetic interference on physiological information by introducing an independent component analysis model and a correspondence between electromagnetic sensing data and the frequency of physiological signal interference. Specifically, firstly, by inputting initial physiological information into a pre-defined independent component analysis model, the original physiological signal is decomposed into multiple independent initial sub-physiological information at multiple frequencies. This decomposition allows for the differentiation of signals with different frequency components, laying the foundation for subsequent precise interference removal. Secondly, by acquiring the electromagnetic frequencies from the electromagnetic sensing data and combining them with the second pre-defined correspondence, the interference frequency range in the physiological signal corresponding to electromagnetic interference in the current environment can be accurately identified. It is precisely this precise frequency correspondence that enables the system to specifically locate the specific manifestation of electromagnetic interference in the physiological signal. Finally, by removing the initial sub-physiological information whose frequencies fall within the identified interference frequency range, the electromagnetic interference component can be effectively stripped from the physiological signal, while retaining other undisturbed physiological signal components, thereby obtaining highly pure physiological information.

[0076] Through the above technical solution, this application overcomes the limitations of traditional general denoising methods in handling electromagnetic interference. This solution achieves precise location and effective removal of electromagnetic interference through refined frequency decomposition and interference frequency identification based on electromagnetic sensing data. Consequently, the obtained pure physiological information has a higher signal-to-noise ratio and accuracy, significantly reducing the impact of external electromagnetic interference on the pilot's cellular health status assessment results, thereby improving the reliability and accuracy of the assessment.

[0077] like Figure 3 As shown, this application further proposes the above-mentioned method of determining the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in pure physiological information, including: S301. For any two measurement indicators among multiple measurement indicators, determine the convergence cross-mapping score of one measurement indicator relative to the other measurement indicator based on the measured values ​​of the two measurement indicators and a preset convergence cross-mapping model.

[0078] S302. Determine whether the absolute value of the difference between the convergent cross-mapping scores of the two measurement indicators is greater than the preset score threshold.

[0079] S303. If yes, take the measurement index with the larger convergence cross-mapping score as the cause measurement index in the causal relationship; take the measurement index with the smaller convergence cross-mapping score as the effect measurement index of the cause measurement index in the causal relationship; if no, determine that the two measurement indexes do not have a causal relationship.

[0080] Specifically, the convergent cross-mapping model is a nonlinear causal inference method based on state space reconstruction. This model effectively identifies causal relationships in nonlinear systems and distinguishes between causality and correlation by analyzing the geometric structure of time series data in the reconstructed state space. The convergent cross-mapping score quantifies the predictive power of a measurement indicator's time series data in reconstructing the state space of another measurement indicator; a higher score indicates a stronger causal influence of the first measurement indicator on the second. To determine the convergent cross-mapping score of one measurement indicator relative to another, reconstructed state spaces can be constructed for the time series data of both measurement indicators, and the cross-mapping algorithm can be used to evaluate whether the state space of one measurement indicator can accurately predict the state of the other.

[0081] The preset score threshold is a key parameter used to determine whether a significant causal relationship exists between two measurement indicators. This threshold can be set according to the actual application scenario, data characteristics, and the required confidence level of causal inference. When the absolute value of the difference between the convergent cross-mapping scores of the two measurement indicators is greater than the preset score threshold, it indicates that there is a clear causal direction between them. Specifically, the measurement indicator with the larger score is identified as the causal measurement indicator, while the measurement indicator with the smaller score is identified as the effect measurement indicator, thus clarifying the direction of the causal relationship. Conversely, if the absolute value of the difference is not greater than the preset score threshold, it is considered that there is no significant causal relationship between the two measurement indicators.

[0082] This application's solution overcomes the limitations of traditional correlation analysis in identifying causal relationships in complex physiological data by introducing a convergent cross-mapping model. The convergent cross-mapping model utilizes the geometric characteristics of time-series data in reconstructing the state space to effectively distinguish between correlation and causality, and to identify the causal direction in nonlinear systems. By calculating the convergent cross-mapping score between two measurement indicators and comparing the absolute value of their difference with a preset score threshold, the strength and direction of the causal relationship can be quantified and determined. When the predictive power of one measurement indicator for another is significantly higher than its reverse predictive power, i.e., when the difference in the convergent cross-mapping score is sufficiently large, the measurement indicator with the larger score can be clearly identified as the causal measurement indicator, and the measurement indicator with the smaller score as the effect measurement indicator. This mechanism ensures a more accurate and reliable determination of causal relationships, avoiding causal confusion or directional errors.

[0083] Through the above technical solution, this application provides a more accurate and reliable method for determining causal relationships. Compared to relying solely on correlation analysis, this method can effectively identify causal relationships in nonlinear systems and clearly distinguish the causal direction, thereby avoiding the causal confusion problems that may occur with traditional methods. Therefore, when subsequently determining the cellular health status information of pilots, judgments can be made based on more accurate causal relationships, improving the accuracy and reliability of cellular health status assessment and providing a solid foundation for developing more effective health adjustment strategies.

[0084] This application further proposes a more rigorous causal relationship verification mechanism, which enhances the reliability of causal relationship judgment by introducing a permutation test.

[0085] Specifically, the measurement index with the larger convergence cross-mapping score among the two measurement indices is taken as the cause measurement index; the measurement index with the smaller convergence cross-mapping score among the two measurement indices is taken as the effect measurement index, including: The measurement index with the larger convergence cross-mapping score among the two measurement indices is selected as the initial cause measurement index; the measurement index with the smaller convergence cross-mapping score is selected as the initial effect measurement index. The measured values ​​of the initial cause measurement index and the initial effect measurement index are input into a pre-defined permutation test model to obtain the permutation test result output by the pre-defined permutation test model. The pre-defined permutation test model is used to perform permutation tests on the measured values ​​of the initial cause measurement index and the initial effect measurement index. When the permutation test result indicates that the initial cause measurement index and the initial effect measurement index pass the permutation test, it is determined that the two measurement indices have a causal relationship, where the initial cause measurement index is the cause measurement index and the initial effect measurement index is the effect measurement index. When the permutation test result indicates that the initial cause measurement index and the initial effect measurement index fail the permutation test, it is determined that the two measurement indices do not have a causal relationship.

[0086] Here, "initial cause measurement index" and "initial effect measurement index" refer to the causal roles temporarily determined based on the convergent cross-mapping scores after a preliminary causal assessment. These initial roles need to be verified for significance through further statistical tests. The "presupposition permutation test model" can be understood as a statistical method that aims to assess whether the observed causal relationship is statistically significant by randomly rearranging the data, thereby avoiding misjudging accidental correlations as causal relationships. Specifically, this model constructs a causal relationship strength distribution under the null hypothesis (i.e., no causal relationship) by repeatedly randomly shuffling the time series data of one of the measurement indices and recalculating the causal relationship strength.

[0087] This application's approach employs a permutation test to rigorously verify the initially determined causal relationship statistically. Specifically, after initially determining the initial cause and effect measurement indicators based on convergent cross-mapping scores, their values ​​are input into a pre-defined permutation test model. This model generates a large number of random samples by randomly permuting the data and calculates the causal strength of each sample. By comparing the causal strength observed in the original data with the causal strength distribution of the random samples, the significance of the original causal relationship can be determined. If the permutation test result indicates that the original causal relationship is statistically significant (i.e., passes the permutation test), the causal relationship is confirmed; conversely, if the permutation test result indicates that the original causal relationship is not statistically significant (i.e., fails the permutation test), the two measurement indicators are considered not causally related. This mechanism effectively eliminates the interference of accidental factors in determining causal relationships, making the determined causal relationship more reliable.

[0088] Through the above technical solution, this application can significantly improve the accuracy and robustness of determining the causal relationship between measurement indicators. The introduction of the permutation test ensures that the determination of causality no longer relies solely on the relative magnitude of convergent cross-mapping scores, but undergoes rigorous statistical verification, thus effectively avoiding misjudgments caused by spurious correlations or chance. Therefore, the pilot's cellular health status information determined based on more accurate causal relationships will be more truthful and reliable, leading to more targeted and effective health adjustment strategies for pilots, and contributing to improved pilot health management.

[0089] This application further proposes determining the pilot's cellular health status information based on the aforementioned causal relationship and the measured values ​​of the measurement indicators, including: Obtain a third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple cell health status information and multiple first information, the first information including multiple target measurement indicators; determine the target first information that includes two measurement indicators with a causal relationship among the multiple first information; when the measurement values ​​of the two measurement indicators with a causal relationship exceed the corresponding normal measurement value range, take the cell health status information corresponding to the target first information in the third preset correspondence as the pilot's cell health status information.

[0090] Specifically, the third pre-defined correspondence can be understood as a pre-established knowledge base or rule set that associates specific cell health status information with one or more sets of physiological measurement indicators (i.e., primary information) and their interrelationships (i.e., target measurement indicators). This correspondence can be obtained through expert experience, historical data analysis, or machine learning model training. For example, the third pre-defined correspondence can be a lookup table, a decision tree model, or a neural network model, with inputs being causally related measurement indicators and their values, and outputting the corresponding cell health status information.

[0091] The first information refers to a set of measurements used to characterize a specific cellular health state. Each piece of first information contains multiple target measurements, selected based on their importance in the causal network or their indicativeness of a specific health state. For example, when assessing "cellular fatigue," the first information might include multiple target measurements such as heart rate variability, blood oxygen saturation, and cortisol levels. Target measurements are causally related measurements selected from the first information to assess a specific cellular health state. These measurements are chosen to more accurately reflect potential changes in cellular health. The normal measurement range refers to the expected range of values ​​for each measurement in a healthy state. When the actual measured value of a measurement exceeds this range, it usually indicates a possible physiological abnormality. This range can be derived from statistical analysis of physiological data from a large number of healthy individuals or personalized based on individual pilot baseline data.

[0092] This application's solution, by introducing a third pre-defined correspondence and combining it with the judgment of whether the measured values ​​of causally related indicators exceed the normal range, can systematically and accurately determine the pilot's cellular health status information. Specifically, firstly, by acquiring the pre-defined third pre-defined correspondence, a mapping relationship between cellular health status information and specific combinations of measurement indicators is established, providing a clear basis for subsequent health status assessment. Secondly, after determining the causal relationships between multiple measurement indicators, this solution can identify target first information matching these causally related measurement indicators from the third pre-defined correspondence.

[0093] This process ensures that health status assessments are based on interrelated and physiologically significant indicators, rather than analyzing individual indicators in isolation. Finally, by determining whether the measured values ​​of these causally related indicators simultaneously exceed their corresponding normal ranges, this approach can identify abnormal physiological patterns. Only when these key indicators are simultaneously abnormal is the corresponding cellular health status information used as the pilot's cellular health status information, thus avoiding misjudgments caused by fluctuations in a single indicator or abnormalities in non-key indicators, significantly improving the accuracy and reliability of health status assessments.

[0094] Through the above technical solution, this application provides a more refined and accurate method for assessing pilot cellular health status. This method effectively addresses the ambiguity and uncertainty that may exist in traditional methods when assessing complex physiological states by establishing a clear mapping between cellular health status information and a combination of causally related measurement indicators, combined with rigorous judgment of abnormal measurement values. Therefore, it can more accurately identify potential health risks in pilots, providing a more reliable basis for subsequent health adjustment strategies, thereby improving pilot flight safety and mission execution efficiency.

[0095] This application further proposes an optimization scheme that aims to adjust the initial health adjustment strategy by taking into account the mission duration of the pilot's pending mission, thereby obtaining a more targeted and effective health adjustment strategy.

[0096] Determining pilot health adjustment strategies based on pilot cellular health status information, including: A preset health adjustment strategy determination model is invoked; the preset health adjustment strategy determination model is used to determine the health adjustment strategy based on cell health status information; the pilot's cell health status information is input into the preset health adjustment strategy determination model, and the health adjustment strategy output by the preset health adjustment strategy determination model is used as the pilot's initial health adjustment strategy; the pilot's initial health adjustment strategy is adjusted according to the mission duration of the pilot's pending mission to obtain the pilot's health adjustment strategy.

[0097] Specifically, the pre-set health adjustment strategy determination model can be understood as a pre-trained intelligent model or expert system that contains a large amount of pilot health data, mission types, physiological responses, and the association rules between corresponding health interventions. This model can intelligently infer the most suitable health adjustment strategy based on the input pilot's cellular health status information. For example, this model could be built using machine learning algorithms (such as support vector machines, neural networks, or decision trees), learning from historical data to establish a mapping relationship between cellular health status and health adjustment strategies. Its purpose is to provide a preliminary health intervention suggestion based on the current physiological condition.

[0098] The initial health adjustment strategy for pilots refers to the health intervention plan directly output by the preset health adjustment strategy determination model, which has not yet undergone mission duration adjustment. This strategy may include dietary recommendations, rest schedules, specific training programs, or psychological adjustment methods.

[0099] In practical applications, adjusting a pilot's initial health adjustment strategy based on the duration of the upcoming mission means, after obtaining a preliminary health adjustment strategy, further considering the duration of the upcoming mission. For example, if the mission is short, faster and more focused adjustments may be needed; if the mission is long, a more sustained and comprehensive adjustment plan may be required. This adjustment may involve modifying certain parameters of the strategy, such as adjusting the length of rest periods, the dosage of nutritional supplements, or the intensity of training, to ensure that the adjustment strategy matches the actual needs of the mission.

[0100] This application's solution adjusts the initial health adjustment strategy output by a pre-defined health adjustment strategy determination model by incorporating consideration of the mission duration to be performed by the pilot. Specifically, firstly, the pre-defined health adjustment strategy determination model provides a basic health adjustment suggestion based on the pilot's cellular health status information, tailored to their current physiological condition. Building on this, considering the potential impact of different mission durations on the pilot's physiological and psychological state, the solution further refines the initial strategy according to mission duration. For example, for long-duration missions, it may be necessary to increase the proportion of restorative rest or strengthen anti-fatigue measures; for short-duration, high-intensity missions, it may be necessary to focus on rapid energy replenishment and stress response management. It is precisely this dynamic adjustment based on mission duration that allows the determined health adjustment strategy to more accurately match the mission challenges the pilot will face, thereby improving the effectiveness and practicality of the strategy.

[0101] Through the above technical solution, this application overcomes the limitations of determining health adjustment strategies solely based on cellular health status information. By taking into account the mission duration of the pilot's upcoming tasks, the initial health adjustment strategy is tailored to the specific needs of the pilot, making the final health adjustment strategy more personalized and adaptable. This not only ensures that pilots receive the most appropriate health support when performing missions of varying durations, effectively preventing health risks caused by differences in mission duration, but also significantly improves the accuracy and effectiveness of the health adjustment strategy, thereby better guaranteeing pilot flight safety and mission completion efficiency.

[0102] This application further proposes a health adjustment strategy, including an adjustment strategy and adjustment parameters, and adjusts the parameter values ​​in the initial health adjustment strategy of the pilot according to the mission duration to be performed, so as to obtain a more accurate and effective health adjustment strategy.

[0103] The health adjustment strategy includes adjustment strategies and adjustment parameters. The initial health adjustment strategy is adjusted based on the duration of the pilot's upcoming mission, resulting in the pilot's overall health adjustment strategy, which includes: Obtain the preset duration coefficient; use the task duration of the task to be executed and the preset duration coefficient as parameter adjustment coefficients; adjust the parameter values ​​of the adjustment parameters in the pilot's initial health adjustment strategy according to the parameter adjustment coefficients to obtain the pilot's health adjustment strategy.

[0104] Specifically, a health adjustment strategy can be understood as a set of interventions tailored to the pilot's cellular health status. This includes not only specific adjustment strategies, such as rest, nutritional supplementation, and psychological intervention, but also adjustment parameters related to these strategies, such as rest duration, nutritional intake, and intervention frequency. The values ​​of these adjustment parameters are variable and can be adjusted according to specific circumstances. The preset duration coefficient is a pre-defined value used to quantify the impact of task duration on the adjustment parameters within the health adjustment strategy. This coefficient can be determined based on extensive flight data, physiological studies, or expert experience to reflect the potential impact of different task durations on the pilot's physiological and psychological workload. For example, for tasks requiring prolonged concentration, the preset duration coefficient may be higher to emphasize the importance of rest and recovery.

[0105] In practical applications, combining the task duration of the task to be executed with a preset duration coefficient can generate a parameter adjustment coefficient. This parameter adjustment coefficient is a dynamic value directly related to the task duration, and its purpose is to provide a quantitative basis for subsequent parameter adjustments. For example, the parameter adjustment coefficient can be obtained by multiplying the task duration by the preset duration coefficient, or by calculating it through a more complex functional relationship.

[0106] Furthermore, based on the determined parameter adjustment coefficients, the parameter values ​​in the pilot's initial health adjustment strategy can be adjusted. This means that if the initial health adjustment strategy recommends 8 hours of rest, but the parameter adjustment coefficients indicate a need for increased rest time, the parameter value may be adjusted to 9 hours or longer. This adjustment ensures that the health adjustment strategy can be personalized and finely adapted to the actual duration requirements of the mission.

[0107] This application's solution refines health adjustment strategies into specific strategies and quantifiable adjustment parameters. It introduces a preset duration coefficient combined with mission duration to generate parameter adjustment coefficients, thus addressing the potential lack of specificity and refinement in the initial health adjustment strategies adjusted based on mission duration. Because of the parameterization of the health adjustment strategy, the impact of mission duration on health can be precisely mapped to specific adjustment parameters through the parameter adjustment coefficients. Therefore, the pilot's health adjustment strategy is no longer a general suggestion, but rather a dynamic adjustment of specific parameters related to rest, nutrition, and mental well-being based on the actual mission duration requirements, ensuring the scientific validity and effectiveness of the adjustments.

[0108] Through the above technical solution, this application provides a more refined, personalized, and quantifiable health adjustment strategy. By introducing preset duration coefficients and parameter adjustment coefficients, this strategy allows the impact of mission duration on pilot health to be precisely translated into adjustments to specific parameters within the health adjustment strategy, thereby significantly improving its targeting and effectiveness. This helps to more accurately assess and manage pilots' physiological load and recovery needs under different mission durations, effectively preventing fatigue accumulation and health risks caused by excessively long or intense missions, thus ensuring pilot flight safety and mission execution efficiency.

[0109] This application also discloses a pilot cellular health status assessment system based on statistical analysis, comprising: an acquisition device and a processing device; the acquisition device is used to acquire the pilot's initial physiological information and mission environment information; the processing device is used to remove interfering physiological information caused by external interference from the initial physiological information based on the mission environment information to obtain pure physiological information; the processing device is used to determine the causal relationship between multiple measurement indicators based on the measurement values ​​of multiple measurement indicators in the pure physiological information; the causal relationship is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator; the processing device is used to determine the pilot's cellular health status information based on the causal relationship and the measurement values ​​of the measurement indicators; the processing device is used to determine the pilot's health adjustment strategy based on the pilot's cellular health status information.

[0110] The acquisition device is used to acquire the pilot's initial physiological information and mission environment information. Specifically, the acquisition device can be understood as a combination of one or more sensors. For example, it may include wearable physiological sensors (such as heart rate monitors, pulse oximeters, thermometers, etc.) for collecting initial physiological information, and environmental sensors (such as accelerometers, gyroscopes, electromagnetic field sensors, barometers, etc.) for collecting mission environment information. The specific methods for acquiring initial physiological information and mission environment information have been described in the above embodiments and will not be repeated here. As an optional implementation, the acquisition device can also communicate with the aircraft's internal data bus or external data sources to receive pre-collected or stored physiological and environmental information. The purpose is to provide comprehensive and accurate raw data for subsequent physiological data purification and health status assessment.

[0111] The processing device may be one or more processors, such as a central processing unit, a graphics processing unit, a digital signal processor, or an application-specific integrated circuit, which are configured to execute data processing algorithms.

[0112] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for assessing the health status of a pilot's cells based on statistical analysis, characterized in that, Includes the following steps: Acquire the pilot's initial physiological information and mission environment information; Based on the task environment information, interference physiological information caused by external interference is removed from the initial physiological information to obtain pure physiological information; Determine the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in pure physiological information; Causality is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator; The pilot's cellular health status information is determined based on the causal relationship and the measured values ​​of the measurement indicators; Determine pilot health adjustment strategies based on pilots' cellular health status information.

2. The method for evaluating the cell health status of a pilot based on statistical analysis according to claim 1, characterized in that, When the task environment information includes gravity sensing data and body tremor data, and the initial physiological information includes initial electrocardiogram signals, the interfering physiological information caused by external interference is removed from the initial physiological information based on the task environment information to obtain pure physiological information, including: Determine whether the gravity sensor data is greater than the preset gravity sensor data threshold; If so, determine the artifact ECG signal caused by the pilot's body tremor based on the body tremor data; Artifacts in the initial ECG signal are removed to obtain a clean ECG signal.

3. The method of claim 2, wherein the method further comprises: Gravity sensor data includes the G-force value, and the ECG signal for artifacts caused by pilot tremor is determined based on tremor data, including: Obtain a preset tremor-ECG signal transfer function and a first preset correspondence; the first preset correspondence includes a one-to-one correspondence between multiple gravity G value ranges and multiple first adjustment coefficients; The first adjustment coefficient corresponding to the range of gravity G values ​​in the first preset correspondence is taken as the target first adjustment coefficient. The target parameter values ​​in the preset tremor-ECG signal transfer function are adjusted according to the target first adjustment coefficient to obtain the target tremor-ECG signal transfer function; The body tremor data is input into the target tremor-ECG signal transfer function to obtain the artifact ECG signal output by the target tremor-ECG signal transfer function.

4. The method of claim 1, wherein the method further comprises: When the task environment information includes electromagnetic sensing data, the interfering physiological information caused by external interference is removed from the initial physiological information based on the task environment information to obtain pure physiological information, including: Initial physiological information is input into a preset independent component analysis model to obtain multiple initial sub-physiological information of different frequencies; the preset independent component analysis model is used to divide the initial physiological information into multiple initial sub-physiological information of different frequencies. Obtain a second preset correspondence; the second preset correspondence includes multiple electromagnetic frequency ranges and multiple first frequency ranges; The first frequency range corresponding to the electromagnetic frequency range in the electromagnetic sensing data of the second preset correspondence is taken as the interference frequency range. By removing initial sub-physiological information whose frequencies fall within the interference frequency range from multiple initial sub-physiological information sources, pure physiological information is obtained.

5. The method of claim 1, wherein the method further comprises: Determine the causal relationships between multiple measurement indicators based on the measured values ​​of multiple indicators in pure physiological information, including: For any two measurement indicators among multiple measurement indicators, determine the convergence cross-mapping score of one measurement indicator relative to the other measurement indicator based on the measured values ​​of the two measurement indicators and a preset convergence cross-mapping model. Determine whether the absolute value of the difference between the convergent cross-mapping scores of two measurement indicators is greater than a preset score threshold; If so, the measurement index with the larger convergence cross-mapping score among the two measurement indices shall be the cause measurement index in the causal relationship; the measurement index with the smaller convergence cross-mapping score among the two measurement indices shall be the effect measurement index of the cause measurement index in the causal relationship. If not, then the two measurement indicators are not causally related.

6. The method of claim 5, wherein the method further comprises: The measurement index with the larger convergence cross-mapping score among the two measurement indices is taken as the dependent measurement index. The measurement index with the smaller convergence cross-mapping score among the two measurement indices is taken as the result measurement index, including: The measurement index with the larger convergence cross-mapping score among the two measurement indices is used as the initial cause measurement index. The measurement index with the smaller convergence cross-mapping score among the two measurement indices is used as the initial result measurement index. The measured values ​​of the initial cause measurement index and the initial effect measurement index are input into the preset permutation test model to obtain the permutation test results output by the preset permutation test model; the preset permutation test model is used to perform permutation tests on the measured values ​​of the initial cause measurement index and the initial effect measurement index. When the permutation test results indicate that the initial cause measurement index and the initial effect measurement index pass the permutation test, it is determined that the two measurement indices have a causal relationship, wherein the initial cause measurement index is the cause measurement index and the initial effect measurement index is the effect measurement index. When the permutation test results indicate that the initial cause measurement index and the initial effect measurement index have not passed the permutation test, it is determined that the two measurement indices are not causally related.

7. The method of claim 1, wherein the method further comprises: The pilot's cellular health status information is determined based on the causal relationship and the measured values ​​of the measurement indicators, including: Obtain a third preset correspondence; the third preset correspondence includes a one-to-one correspondence between multiple cell health status information and multiple first information, the first information including multiple target measurement indicators; The target first information is identified as including two measurement indicators that have a causal relationship among multiple first information items; When the measured values ​​of two causally related measurement indicators exceed the corresponding normal measurement range, the cell health status information corresponding to the first information of the target in the third preset correspondence is taken as the pilot's cell health status information.

8. The method of claim 1, wherein the method further comprises: Determining pilot health adjustment strategies based on pilot cellular health status information, including: A preset health adjustment strategy determination model is invoked; the preset health adjustment strategy determination model is used to determine a health adjustment strategy based on cell health status information. The pilot's cellular health status information is input into the preset health adjustment strategy determination model, and the health adjustment strategy output by the preset health adjustment strategy determination model is used as the pilot's initial health adjustment strategy. The pilot's initial health adjustment strategy is adjusted based on the duration of the mission to be performed, resulting in the pilot's health adjustment strategy.

9. The method of claim 8, wherein the method further comprises: The health adjustment strategy includes adjustment strategies and adjustment parameters. The initial health adjustment strategy is adjusted based on the duration of the pilot's upcoming mission, resulting in the pilot's overall health adjustment strategy, which includes: Get the preset duration coefficient; Use the task duration of the task to be executed and the preset duration coefficient as parameter adjustment coefficients; The pilot's health adjustment strategy is obtained by adjusting the parameter values ​​of the adjustment parameters in the initial health adjustment strategy based on the parameter adjustment coefficient.

10. A pilot cellular health status assessment system based on statistical analysis, characterized in that, include: Acquisition device and processing device; Acquisition device, used to acquire the pilot's initial physiological information and mission environment information; The processing device is used to remove interfering physiological information caused by external interference from the initial physiological information based on the task environment information, so as to obtain pure physiological information; A processing device for determining the causal relationship between multiple measurement indicators based on the measured values ​​of multiple measurement indicators in pure physiological information; Causality is used to indicate that one measurement indicator is a causal measurement indicator and another measurement indicator is an effect measurement indicator of the causal measurement indicator; A processing device for determining the pilot's cellular health status information based on the causal relationship and measured values ​​of the measurement indicators; A processing device for determining pilot health adjustment strategies based on pilot cellular health status information.

Images