Intelligent terminal security risk assessment system and method

Abstract

The invention discloses an intelligent terminal security risk assessment system and method, and relates to the technical field of risk assessment, and the method comprises the following steps: continuously collecting meteorological data, geological data and intelligent terminal energy data; wherein the climate data comprises air temperature, wind speed, polar day period duration and polar night period duration; the geological data comprises surface micro-seismic amplitude and ice layer displacement speed; and determining a demarcation point according to the polar day period duration and the polar night period duration, dividing a data time period according to the demarcation point, and increasing the energy storage capacity weight coefficient to a preset value in the polar night period. Calculating the number of remaining extreme night days through a satellite positioning and astronomical calendar method, and enabling energy distribution to have a time dimension dynamic optimization capability; and meanwhile, wind speed correlation analysis is triggered by using data of a light intensity sensor, and a storm precursor signal is captured under a strong light condition in the polar day period, so that the problem of risk assessment lag caused by the fact that the influence of the polar day / polar night period on energy supply and meteorological disasters is not considered in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of risk assessment, and particularly to an intelligent terminal security risk assessment system and method. Background Art

[0002] With the continuous development of operations in extreme environments such as polar scientific research and deep-sea exploration, the stable operation of intelligent terminal devices (such as unmanned monitoring stations, automated scientific research equipment, etc.) faces severe challenges under harsh conditions such as extreme cold, strong winds, and the alternation of polar day and night. Such terminals usually need to work autonomously for a long time, and their security is affected not only by external climate and geological conditions, but also depends on internal energy supply and microbial environment.

[0003] However, during the process of implementing the inventive technical solution in the embodiments of the present application, the inventors found that the above technologies have at least the following technical problems: The prior art fails to establish a dynamic risk assessment mechanism adapted to the polar day / night cycle and cannot adjust risk assessment parameters according to the special polar day / night cycle; there is a lack of a comprehensive risk assessment system for special polar geological conditions (such as ice layer displacement, surface microseisms) and climate factors (such as sudden changes in wind speed). Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent terminal security risk assessment system and method to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the technical solution of the present invention is as follows: In a first aspect, the present invention discloses an intelligent terminal security risk assessment method, including the following steps: Continuously collect meteorological data, geological data, and intelligent terminal energy data at a fixed period; Among them, the meteorological data includes temperature, wind speed, and the duration of polar day and polar night cycles; the geological data includes the amplitude of surface microseisms and the ice layer displacement speed; Determine the demarcation point according to the duration of the polar day and polar night cycles, divide the data time period according to the demarcation point, and increase the energy storage capacity weight coefficient to a preset value during the polar night period; Calculate the temperature difference based on the value of the current fixed period and the value of the previous fixed period of the temperature, input the temperature difference into the constructed cracking prediction model, and output the ice layer cracking probability; Output the predicted value of the ice layer displacement speed according to the ice layer displacement speed and the ice layer cracking probability; Perform standardization processing on the surface microseism amplitude data, and perform vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the foundation stability coefficient; When it is detected that the wind speed exceeds the set threshold and the foundation stability coefficient is lower than the critical value, trigger the shell reinforcement instruction; Calculate the safety risk value of the terminal based on the foundation stability coefficient, the energy data of the intelligent terminal, and the probability of ice layer cracking.

[0006] In a second aspect, the present invention discloses an intelligent terminal safety risk assessment system, which uses the above-mentioned intelligent terminal safety risk assessment method, and includes: A data acquisition module for continuously collecting meteorological data, geological data, and energy data of the intelligent terminal; A data processing module for determining a demarcation point according to the duration of the polar day and polar night cycles, dividing data time periods according to the demarcation point, and increasing the energy storage capacity weight coefficient to a preset value during the polar night period; Calculate the temperature difference based on the value of the current fixed cycle and the value of the previous fixed cycle of the temperature, input the temperature difference into the constructed cracking prediction model, and output the probability of ice layer cracking; Output a predicted value of the ice layer displacement speed according to the ice layer displacement speed and the probability of ice layer cracking; Perform standardization processing on the surface microseismic amplitude data, and perform vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the foundation stability coefficient; An execution module for triggering a shell reinforcement instruction when it is detected that the wind speed exceeds a set threshold and the foundation stability coefficient is lower than a critical value; A risk assessment module for calculating the safety risk value of the terminal according to the foundation stability coefficient, the energy data of the intelligent terminal, and the probability of ice layer cracking.

[0007] Compared with the prior art, the beneficial effects of the present invention are: 1. Calculate the remaining polar night days through satellite positioning and astronomical calendars, enabling the energy distribution to have the ability of dynamic optimization in the time dimension; at the same time, use the light intensity sensor data to trigger the wind speed correlation analysis, and capture the storm precursor signal under strong light conditions during the polar day period, solving the problem of lagging risk assessment in the prior art due to the failure to consider the impact of the polar day / polar night cycle on energy supply and meteorological disasters, and realizing the dynamic optimization of the energy storage strategy and the active defense of storm warning.

[0008] 2. Through the cracking probability model driven by temperature difference, the dynamic correction of displacement speed, and the vector synthesis of multi-source data, the present solution realizes the multi-dimensional collaborative analysis of the ice layer structure change and geological activities, can more accurately capture the early signal of foundation instability, and solves the problem of misjudgment of foundation stability in the prior art due to ignoring the correlation between temperature mutation and geological activities.

[0009] 3. By integrating geographical location data with astronomical calendar information, this solution establishes an energy prediction model driven by the day-night cycle, enabling the charging strategy to actively adapt to the sudden change in light intensity brought about by the alternation of polar day and night. At the same time, the energy utilization efficiency is improved through the intelligent shutdown mechanism of non-core devices, solving the problem of unstable energy supply of intelligent terminals in the polar environment due to the drastic changes in the day-night cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The disclosure of the present invention will be described with reference to the accompanying drawings. It should be understood that the drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In the drawings, the same reference numerals are used to refer to the same components. Among them: Figure 1 is the flowchart of the steps of the present invention; Figure 2 is the functional schematic diagram of the system module provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] It is easy to understand that according to the technical solution of the present invention, without changing the essence of the present invention, those of ordinary skill in the art can propose various structural ways and implementation ways that can be mutually replaced. Therefore, the following detailed embodiments and the accompanying drawings are only exemplary descriptions of the technical solution of the present invention, and should not be regarded as all of the present invention or as a limitation or restriction on the technical solution of the present invention.

[0012] Application Overview: In the prior art, intelligent terminal devices deployed in polar scientific research activities are long-term exposed to extreme climate and geological environments. Traditional risk assessment systems usually use fixed thresholds to judge the operating state of devices. The existing methods do not consider the periodic impact of the polar day-night alternation cycle on energy supply and cannot dynamically adjust the energy storage strategy; at the same time, the lack of correlation analysis between ice layer cracking and changes in foundation stability leads to a lag in risk warning; in addition, the problem of abnormal proliferation of microorganisms inside the device in the low-temperature and high-humidity environment is not included in the assessment system, and there are potential risks of device corrosion and circuit failures.

[0013] To solve the above problems, the inventors found that the risk factors of intelligent terminals in the polar environment have time sensitivity and multi-factor coupling characteristics. First, there is a time correlation between the interruption of energy acquisition during the polar night period and the thermodynamic changes of the ice layer, and a periodic data segmentation mechanism needs to be established; second, the ice layer displacement speed and the cracking probability caused by sudden temperature changes jointly affect the foundation stability, and a dynamic prediction needs to be realized through a thermodynamic model; third, the metabolic activities of microorganisms inside the device have a non-linear relationship with temperature and humidity, and a dynamic monitoring model needs to be established. By integrating meteorological, geological, energy and microbial data, it is necessary to construct a risk assessment framework with multi-dimensional parameter linkage.

[0014] After introducing the basic concept of the present invention, the embodiments of the present invention will be specifically introduced below with reference to the accompanying drawings.

[0015] Embodiment 1: Please refer to Figure 1 , a method for evaluating security risks of intelligent terminals, which is applied to the evaluation of security risks of intelligent terminals in polar unmanned scientific research stations, and includes the following steps: Continuously collect meteorological data, geological data, and intelligent terminal energy data; Among them, the climate data includes temperature, wind speed, and the duration of polar day and polar night cycles; the geological data includes the amplitude of surface microseisms and the ice layer displacement speed; Determine the demarcation point according to the duration of the polar day and polar night cycles, divide the data time period according to the demarcation point, and increase the energy storage capacity weight coefficient to a preset value during the polar night period; Calculate the temperature difference based on the current cycle temperature data and the previous cycle temperature data, input the temperature difference into the constructed ice cracking prediction model, and output the ice layer cracking probability; Output the predicted value of the ice layer displacement speed according to the ice layer displacement speed and the ice layer cracking probability; Standardize the surface microseism amplitude data and perform vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the foundation stability coefficient; When it is detected that the wind speed exceeds the set threshold and the foundation stability coefficient is lower than the critical value, trigger the shell reinforcement instruction; Calculate the security risk value of the terminal according to the foundation stability coefficient, intelligent terminal energy data, and ice layer cracking probability.

[0016] Among them, the demarcation point division refers to dividing the data collection cycle according to the alternation time of polar day and polar night, and specifically can be realized by calculating the threshold of the change in the solar altitude angle using astronomical calendars, which solves the influence of periodic environmental changes on the evaluation model; The temperature difference calculation refers to obtaining the numerical difference between two consecutive temperature monitoring cycles, and specifically can be realized by using the difference calculation method to process the temperature sensor data, which provides a thermodynamic basis for predicting the change of the ice layer structure; The vector synthesis calculation refers to converting the monitoring data of different dimensions into standardized vectors and then performing spatial superposition, and specifically can be realized by using the Z-score standardization combined with the vector projection algorithm, which realizes the integrated evaluation of multi-dimensional geological parameters.

[0017] Specifically, this method obtains environmental cycle data in real time through satellite positioning and light intensity sensors, and automatically increases the energy storage weight during the polar night period to ensure continuous power supply for the device. The temperature difference data is input into a cracking prediction model constructed based on the heat conduction equation, and the output probability value reflects the vulnerability of the ice layer structure. The predicted value of the ice layer displacement speed is obtained by weighted calculation combining real-time monitoring data and cracking probability, accurately reflecting the dynamic changes of the foundation. The standardized microseismic amplitude data and the displacement prediction value are orthogonally vector synthesized to generate a coefficient index reflecting the comprehensive stability state. When the wind speed sensor detects strong wind and the foundation coefficient is lower than the set standard, the electromagnetic locking device is automatically activated to enhance the physical protection of the terminal. Finally, the risk level is calculated through a multi-parameter weighted model, providing a quantitative basis for equipment maintenance.

[0018] Compared with the prior art, the traditional method uses static thresholds to judge risks, while this solution realizes adaptive adjustment of evaluation parameters by dynamically dividing the data cycle; the existing system analyzes geological parameters separately, and this solution establishes a multi-parameter correlation model through vector synthesis; conventional monitoring ignores the influence of microorganisms, and this solution predicts the internal risks of the device through the correlation equation between temperature, humidity and microorganisms. In addition, the existing energy management does not consider the special requirements during the polar night period, and this solution dynamically adjusts the energy storage strategy through the cycle demarcation point.

[0019] Through the above technical solutions, this application realizes the dynamic monitoring and comprehensive evaluation of the risk factors of intelligent terminals in the polar environment, improves the accuracy of foundation stability prediction, and ensures the timely triggering of the protection mechanism under extreme meteorological conditions. At the same time, by integrating the internal microorganism environment monitoring, the internal corrosion risk of the device is effectively prevented, forming an all-round evaluation system covering the external environment and internal state. The periodic data segmentation mechanism solves the problem of insufficient adaptability of traditional methods during the alternation of polar day and polar night, and the vector synthesis algorithm improves the fusion analysis ability of multi-source heterogeneous data.

[0020] This application further proposes that increasing the energy storage capacity weight coefficient to a preset value during the polar night period includes: During the polar night period, the geographical location coordinates of the terminal are obtained through satellite positioning, and the remaining polar night days are calculated in combination with the astronomical calendar; During the polar day period, the solar radiation intensity is monitored by a light intensity sensor. When the solar radiation intensity exceeds 800 W / m² and lasts for 3 hours, wind speed correlation analysis is carried out: If the wind speed reaches 15 m / s during this period and the fluctuation range exceeds 50% of the average value in the previous 24 hours, a storm warning signal is generated and the electromagnetic locking device of the terminal shell is activated 48 hours in advance.

[0021] Among them, satellite positioning refers to the technology of obtaining the longitude and latitude coordinates of the terminal using the Beidou or GPS system, which can be specifically implemented by a multi-band signal receiving module for accurately positioning the geographical location of the terminal; The remaining polar night days refer to the remaining duration of the polar night calculated based on astronomical calendar data combined with the terminal coordinates, which can be specifically implemented through the celestial body orbit algorithm, providing a time benchmark for energy scheduling; The light intensity sensor refers to a photoelectric conversion device used to measure the solar radiation intensity. For example, silicon-based photovoltaic elements are adopted, and when the radiation intensity exceeds 800 W / m², it characterizes the strong light condition during the polar day period; The wind speed correlation analysis refers to an algorithm that compares the current wind speed data with the historical fluctuation values. For example, the moving average method is used to calculate the average value in the previous 24 hours, and when the instantaneous wind speed fluctuation amplitude exceeds 50%, it is determined as an abnormal meteorological event; The electromagnetic locking device refers to a mechanical component that enhances the structural stability of the terminal housing through electromagnetic force. For example, the linkage design of an electromagnetic chuck and a reinforcement frame is adopted to lock the housing joint in advance when a storm warning is triggered.

[0022] Specifically, during the polar night period, the terminal coordinates are obtained in real time through the satellite positioning module, and the remaining polar night days are calculated by combining the pre-stored astronomical calendar data, providing a time basis for the capacity allocation of the energy storage system. During the polar day period, the light intensity sensor continuously monitors the solar radiation intensity. When the detected radiation value exceeds 800 W / m² and lasts for 3 hours, the wind speed data analysis module is activated. This module compares the current wind speed data with the average value in the previous 24 hours. If the wind speed reaches 15 m / s and the fluctuation amplitude exceeds 50% of the average value, it is determined that an extreme storm event is about to occur, and then a warning signal is generated and the electromagnetic locking device is driven to complete the housing reinforcement within 48 hours. Through the correlation analysis of the light intensity and wind speed fluctuation during the polar day period, the early identification and active protection of meteorological disasters are realized.

[0023] Compared with the prior art, the existing risk assessment system does not establish a linkage mechanism between the polar day / polar night cycle, energy management, and meteorological disasters, cannot dynamically adjust the energy storage strategy according to the remaining polar night days, and lacks the correlation analysis of strong light and sudden wind speed changes. This solution calculates the remaining polar night days through satellite positioning and astronomical calendar, enabling the energy distribution to have the ability of dynamic optimization in the time dimension; at the same time, using the light intensity sensor data to trigger the wind speed correlation analysis, capturing the precursor signals of storms under the strong light conditions during the polar day period, significantly improving the warning timeliness compared with the traditional single wind speed threshold alarm method.

[0024] Through the above technical solution, this application solves the problem of lagging risk assessment in the prior art due to the failure to consider the influence of the polar day / polar night cycle on energy supply and meteorological disasters, realizes the dynamic optimization of the energy storage strategy and the active defense of storm warnings, and ensures the operation stability of the terminal device in extreme environments.

[0025] This application further proposes that the calculation of the foundation stability coefficient includes: Calculate the temperature difference based on the current cycle temperature data and the previous cycle temperature data, input the temperature difference into a cracking prediction model constructed based on the principles of thermodynamics, and output the ice layer cracking probability; Based on the ice layer displacement speed and the ice layer cracking probability, calculate the predicted value of the ice layer displacement speed by using probability weighted average; Perform standardization processing on the surface microseismic amplitude data, and conduct vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the foundation stability coefficient.

[0026] Among them, the temperature difference calculation refers to obtaining the temperature data of two consecutive monitoring cycles through temperature sensors and performing difference operations. Specifically, it can be realized by using the difference algorithm or the sliding window mean comparison, and is used to reflect the severity of the ice layer temperature change; The cracking prediction model refers to the mathematical relationship established based on the thermal expansion coefficient and the material fatigue theory. Specifically, it can be realized by using finite element simulation or empirical formula fitting, and is used to quantify the damage probability of the ice layer structure caused by temperature changes, predict the structural damage risk of polar ice layers caused by temperature changes, and provide key parameters for the foundation stability assessment (such as combining with the ice layer displacement speed to correct the displacement prediction value); By analyzing the influence of temperature changes on the ice layer structure, quantify the possibility of ice layer cracking caused by temperature mutations. Specifically, the greater the temperature difference, the more significant the internal thermal stress of the ice layer and the higher the cracking risk; By inputting the current cycle temperature value, the previous cycle temperature value, and the ice layer material parameters, the ice layer cracking probability is output by the cracking prediction model (the value range is [0,1], and the higher the value, the higher the cracking risk); The predicted value of the ice layer displacement speed refers to the dynamic weighted result of combining real-time displacement monitoring data and the cracking probability. Specifically, it can be realized by using linear regression or probability density weighted algorithm, and is used to correct the potential risk of displacement acceleration caused by ice layer cracking; The standardization processing refers to converting the microseismic amplitude data with different dimensions into dimensionless numerical values with a unified scale. Specifically, it can be realized by using Z-score normalization or range method, and is used to eliminate the influence of data scale differences on the synthesis calculation; The vector synthesis calculation refers to vectorially superimposing the standardized microseismic amplitude and the predicted value of the displacement speed in the spatial direction. Specifically, it can be realized by using vector addition or projection decomposition algorithm in the Euclidean space coordinate system, and is used to comprehensively evaluate the stability of the foundation in three-dimensional space.

[0027] Specifically, in the polar environment, the ice layer temperature and geological activities have a decisive impact on the foundation stability of intelligent terminals. By periodically collecting air temperature data, calculating the temperature difference between adjacent periods to reflect the change trend of thermal stress, and inputting it into a cracking prediction model based on thermodynamic principles, such as through the correlation equation between the coefficient of thermal expansion and the ice layer thickness, the cracking probability of the ice layer under the action of temperature difference is output. Subsequently, the ice layer displacement speed monitored in real time is combined with the cracking probability, such as using the probability weighted average or Bayesian inference method, to predict the possible accelerated displacement amount of the ice layer. At the same time, the surface microseismic amplitude data is standardized, such as by removing the dimension difference to make it at the same order of magnitude as the displacement speed prediction value. Finally, the standardized microseismic amplitude data and the displacement speed prediction value are vector synthesized, such as through the vector superposition operation in the space coordinate system, to obtain a comprehensive coefficient reflecting the overall stability of the foundation.

[0028] Compared with the prior art, traditional methods usually only rely on single-sensor data to evaluate the foundation state, such as only analyzing temperature or displacement speed, ignoring the influence of multi-factor coupling on stability. And this solution realizes the multi-dimensional collaborative analysis of ice layer structure changes and geological activities through a cracking probability model driven by temperature difference, dynamic correction of displacement speed, and vector synthesis of multi-source data, and can more accurately capture the early signals of foundation instability.

[0029] Through the above technical solution, this application solves the problem of misjudgment of foundation stability in the prior art caused by ignoring the correlation between temperature mutation and geological activities. By integrating the thermodynamic model and multi-source data synthesis calculation, it can effectively identify the complex foundation risks caused by ice layer cracking and microseismic activities, thereby providing a more reliable basis for the decision-making of the intelligent terminal's shell reinforcement and avoiding equipment overturning or structural damage caused by evaluation deviation.

[0030] This application further proposes that the energy data of the intelligent terminal includes: Before the start of the polar night period, the current longitude and latitude of the intelligent terminal are obtained through polar satellite positioning, and the remaining days are calculated in combination with the polar night cycle data; Obtain the remaining power of the intelligent terminal, and input the remaining days and the remaining power of the intelligent terminal into a pre-constructed calculation model to output the safe operation days; During the polar day period, the daily effective light duration is monitored in real time through a light sensor. When the light duration exceeds 8 hours, the intelligent terminal is charged at the maximum power; when the light duration is less than 4 hours, it switches to the low-power discharge mode and shuts down non-core devices.

[0031] Among them, polar satellite positioning refers to the technology of obtaining the geographical location coordinates of the terminal through the polar orbit satellite system, and specifically can be implemented by using the polar region enhancement module of the Beidou satellite navigation system for accurately positioning the coordinates of the device within the polar circle.

[0032] The remaining days calculation refers to an algorithm for calculating the duration of the polar night based on astronomical calendar data. Specifically, it can be implemented by combining the solar altitude angle model with historical meteorological data, and is used to predict the upcoming polar night duration of the device.

[0033] The calculation model refers to a mathematical relationship that correlates energy supply and operating requirements. Specifically, it can be a linear regression model that integrates the device power consumption curve and the battery capacity attenuation coefficient, and is used to evaluate the sustainable operating ability of the terminal during the polar night.

[0034] The light sensor refers to a photoelectric conversion device that monitors the solar radiation intensity. Specifically, it can be implemented by a silicon photovoltaic cell array combined with a light intensity calibration module, and is used to identify the effective charging period during the polar day.

[0035] Specifically, at the beginning stage of the polar night period, after determining the geographical coordinates of the terminal through satellite positioning, the remaining polar night days are calculated by combining astronomical calendar data. The remaining days and the current remaining battery power of the terminal are input into the calculation model, which outputs the safe days that the terminal can sustainably operate according to the average power consumption of the device and the battery capacity attenuation characteristics. If the safe days are less than the remaining polar night days, the low-power mode is triggered in advance. During the operation stage of the polar day period, the effective light duration is continuously monitored through the light sensor: when the single-day effective light exceeds 8 hours, the maximum power charging mode is activated to quickly replenish energy; when the effective light is less than 4 hours, it automatically switches to the low-power discharge mode and shuts down non-core devices such as the data transmission module, giving priority to ensuring the basic monitoring function.

[0036] Compared with the prior art, traditional energy management methods only make simple estimations based on the remaining battery power, without considering the dynamic impact of the special polar day-night cycle on the energy supply-demand relationship. This solution establishes an energy prediction model driven by the day-night cycle by integrating geographical location data and astronomical calendar information, enabling the charging strategy to actively adapt to the sudden change in light intensity brought about by the alternation of polar day and polar night, and at the same time improving the energy utilization efficiency through the intelligent shutdown mechanism of non-core devices.

[0037] Through the above technical solutions, this application effectively solves the problem of unstable energy supply of intelligent terminals in the polar environment due to the drastic change of the day-night cycle. By accurately matching the remaining days with the device power consumption, it avoids accidental power outages during the polar night; at the same time, it dynamically adjusts the charging power using the light intensity, maximizes the energy reserve on the premise of ensuring the safe operation of the device, and significantly reduces the risk of operation interruption of polar scientific research equipment due to insufficient energy.

[0038] The present application further proposes a method for assessing security risks of intelligent terminals. Specifically, meteorological data, geological data, and energy data of intelligent terminals are continuously collected, including: obtaining internal data of the intelligent terminal, where the internal data includes internal microbial data, temperature data, and humidity data of the terminal; synchronously inputting the humidity data, temperature data, and microbial data into a constructed prediction model, which outputs a prediction curve of microbial proliferation within a specific future time window by establishing a dynamic correlation equation among the three; and judging whether the microbial proliferation data is greater than the safety value according to the prediction curve of microbial proliferation. If so, a cyclic disinfection instruction is initiated.

[0039] Among them, the internal microbial data of the terminal refers to the total number of colonies or the activity parameters of specific corrosive bacterial species in the closed environment of the intelligent terminal, which can be specifically detected by an optical sensor or a bioelectrochemical sensor, and is used to reflect the potential threat of the internal microbial environment of the device to the terminal materials.

[0040] Among them, the dynamic correlation equation refers to a mathematical model established based on the non-linear relationship between humidity, temperature, and microbial proliferation rate, which can be specifically realized by training with a multiple regression algorithm or a neural network model, and is used to quantify the microbial proliferation trend under different temperature and humidity conditions.

[0041] Among them, the cyclic disinfection instruction refers to the operation of sterilizing the inside of the device by triggering an ultraviolet lamp or an ozone generator, which can be specifically realized by using a timed pulse control or a concentration threshold interlock mechanism, and is used to inhibit circuit corrosion or insulation failure caused by excessive microbial reproduction.

[0042] Specifically, in the polar low-temperature environment, condensate may form inside the intelligent terminal housing due to the temperature difference, resulting in an increase in humidity. At the same time, the heat generated by the device operation may cause local temperature fluctuations. By synchronously collecting temperature, humidity, and microbial data, the prediction model can analyze the dynamic relationship among the three. For example, when the temperature is in the range of -10°C to 5°C and the humidity exceeds 70%, the model will predict the exponential proliferation of psychrophilic bacteria. Further, if the proliferation curve output by the model exceeds the preset threshold within the future 72-hour window, the system will automatically initiate a disinfection program, such as releasing short-wave ultraviolet light during the device sleep period and continuously disinfecting for 30 minutes to maintain the microbial concentration within the safe range.

[0043] Compared with the prior art, existing risk assessment systems usually only focus on external environmental parameters and do not consider the problem of abnormal microbial reproduction inside the device under the special polar climate. This solution realizes the active prediction of the internal corrosion risk of the device by establishing a correlation model between temperature, humidity, and microorganisms, making up for the lack of environmental monitoring dimensions in the prior art.

[0044] Through the above technical solutions, this application can effectively identify the risk of circuit corrosion caused by microbial proliferation inside the intelligent terminal. Through the dynamic prediction and automatic disinfection mechanism, it can avoid equipment short - circuit or material degradation problems caused by out - of - control microbial colonies, and significantly improve the long - term operation reliability of intelligent terminals in polar environments.

[0045] This application further proposes that calculating the security risk value of the terminal includes: Inputting the foundation stability coefficient, intelligent terminal energy data, and ice layer cracking probability into a pre - constructed risk assessment model, and outputting the security risk value of the terminal.

[0046] Among them, the foundation stability coefficient is a quantitative index reflecting the stability degree of the surface structure where the intelligent terminal is located. Specifically, it can be achieved through the vector synthesis calculation of the predicted values of surface micro - seismic amplitude and ice layer displacement speed. This index is used to evaluate the comprehensive impact of ice layer displacement and geological activities on the terminal's physical support structure.

[0047] Intelligent terminal energy data is a set of dynamic parameters reflecting the operating state of the device's power supply system. Specifically, it can include parameters such as energy storage capacity, remaining power, charging and discharging power, etc., and is used to evaluate the supporting role of energy supply on the terminal's continuous operation ability in extreme environments.

[0048] The ice layer cracking probability is a numerical value representing the possibility of ice layer structure damage predicted based on temperature changes. Specifically, it can be dynamically predicted by inputting temperature difference data into a thermodynamic model. This parameter is used to identify the sudden risk caused by ice layer rupture to the terminal's foundation.

[0049] Specifically, the foundation stability coefficient forms a multi - dimensional vector through integrating the standardized data of surface micro - seismic amplitude and the predicted value of ice layer displacement speed for synthesis calculation. For example, the Euclidean distance or weighted average algorithm is used to obtain a quantitative result reflecting the comprehensive stability of the foundation. Intelligent terminal energy data evaluates the sustainability of the energy system under extreme lighting conditions by collecting the changes in energy storage capacity and charging and discharging efficiency during the alternation of polar day and polar night, and combining with the remaining operation days prediction model. The ice layer cracking probability constructs a heat conduction equation based on periodic temperature data, predicts the internal stress distribution of the ice layer through continuous temperature difference input, and outputs the cracking risk level. These three types of parameters are synchronously input into the risk assessment model (the risk assessment model is a systematic analysis tool used to identify, quantify, and manage potential risks. Through data, statistical methods, and algorithms, it predicts the possibility of an event occurring and its possible impacts). For example, the multi - factor linear regression or neural network algorithm is used to dynamically generate the security risk value, which is used to characterize the comprehensive probability of the terminal having a failure or being damaged within a specific time period.

[0050] The risk assessment model integrates multi-dimensional risk parameters (foundation stability coefficient, energy data, ice layer cracking probability) to quantify the comprehensive security risks of intelligent terminals in polar environments, achieving risk level classification and dynamic response. By inputting the foundation stability, energy system status, and ice layer structure risk, the model then constructs a multi-layer perceptron. The input layer consists of standardized parameters, and the hidden layer extracts features through a non-linear activation function, and then outputs the security risk value: quantifying the degree of risk (such as in the range of 0 to 1, the higher the value, the higher the risk).

[0051] Compared with the prior art, traditional methods usually only conduct isolated evaluations for single risk factors. For example, only wind speed or power is monitored, without considering the combined effects of geological activities and energy status. This solution constructs a multi-dimensional risk assessment system by integrating three types of dynamic parameters: foundation stability coefficient, energy data, and ice layer cracking probability, which can accurately capture complex risk scenarios in polar environments where sudden temperature changes cause ice layer displacement and insufficient energy supply simultaneously, solving the defect of insufficient identification of cross-risk factors in the prior art.

[0052] Through the above technical solution, this application realizes a comprehensive risk perception of the operating environment of polar intelligent terminals. Especially during the alternation of polar day and polar night, it can simultaneously monitor three key indicators: foundation stability changes, energy system status, and ice layer structure risk, and accurately quantify complex security threats through parameter fusion calculation. This method effectively avoids the problem of lagging protection measures caused by single risk assessment. For example, when ice layer displacement acceleration and insufficient energy storage occur simultaneously, it can trigger dual response strategies of reinforcement and energy allocation in advance to ensure the continuous and stable operation of the terminal in extreme environments.

[0053] This application further proposes that after calculating the security risk value of the terminal, it further includes: After the security risk value is calculated, the current risk level is determined by comparing with a preset grading threshold interval, and the corresponding set control strategy is executed.

[0054] Among them, the security risk value is a quantitative index generated through the comprehensive evaluation of the foundation stability coefficient, intelligent terminal energy data, and ice layer cracking probability. Specifically, it can be realized by using a weighted fusion algorithm and is used to characterize the comprehensive danger degree of the environment and operating state where the terminal is currently located.

[0055] Among them, the grading control strategy refers to triggering different levels of device protection measures according to the preset threshold interval where the security risk value is located. Specifically, it can be realized through a preset instruction mapping table. For example, only the energy distribution mode is adjusted in the low-risk interval, and the physical reinforcement device and emergency disinfection system are activated in the high-risk interval, thereby achieving precise matching of risk response measures.

[0056] Specifically, after the safety risk value is calculated, the system determines the current risk level by comparing it with the preset hierarchical threshold intervals. For example, when the risk value is in the first interval, the energy management strategy is preferentially adjusted to extend the device's battery life; when the risk value jumps to the second interval, the shell reinforcement and microbial disinfection procedures are started simultaneously; if the risk value breaks through the critical value of the third interval, the satellite alarm signal is immediately triggered and non-essential loads are cut off. This hierarchical mechanism can address the problem of equipment corrosion caused by abnormal microbial proliferation during the polar night. When the risk value reaches the corresponding threshold, the cyclic disinfection instruction is immediately started, and at the same time, the shell protection level is dynamically adjusted in combination with the decrease in the ground stability coefficient.

[0057] Compared with the prior art, existing risk assessment systems usually adopt a single threshold to trigger fixed protection measures and cannot dynamically respond to the combined risks of microbial proliferation and energy shortage in the polar environment. In contrast, this solution can match different response measures at different risk stages through a hierarchical control strategy. For example, only local disinfection is started in the initial stage of microbial proliferation to avoid premature energy consumption, and multiple protection actions are executed simultaneously when the risk of ice layer cracking is superimposed.

[0058] Through the above technical solution, this application solves the problems of rigid risk assessment mechanisms in the prior art and the inability to effectively respond to multi-factor coupling risks in special polar environments, achieving an accurate match between device protection measures and real-time risk levels. Especially during the stage of abnormal microbial proliferation, disinfection operations can be implemented in a timely manner to prevent equipment circuits from failing due to corrosion, and at the same time, redundant energy consumption operations are reduced through the hierarchical strategy.

[0059] Embodiment 2: Please refer to Figure 1 , an intelligent terminal safety risk assessment system that uses the above-mentioned intelligent terminal safety risk assessment method, including: a data acquisition module for continuously collecting meteorological data, geological data, and intelligent terminal energy data; A data processing module for determining the demarcation point according to the durations of the polar day and polar night cycles, dividing data time periods according to the demarcation point, and increasing the energy storage capacity weight coefficient to a preset value during the polar night; Calculating the temperature difference based on the current cycle temperature data and the previous cycle temperature data, inputting the temperature difference into the constructed ice layer cracking prediction model, and outputting the ice layer cracking probability; Outputting a predicted value of the ice layer displacement speed based on the ice layer displacement speed and the ice layer cracking probability; Performing standardization processing on the surface microseismic amplitude data and performing vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the ground stability coefficient; An execution module for triggering the shell reinforcement instruction when it is detected that the wind speed exceeds the set threshold and the ground stability coefficient is lower than the critical value; A risk assessment module, configured to calculate a safety risk value of the terminal according to the foundation stability coefficient, the energy data of the intelligent terminal, and the ice layer cracking probability.

[0060] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0061] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent terminal security risk assessment method, which is applied to the intelligent terminal security risk assessment of polar unmanned scientific research stations, is characterized in that: The following steps are involved: Continuously collect meteorological data, geological data, and smart terminal energy data at a fixed period; The meteorological data include temperature, wind speed, and the duration of polar day and polar night cycles; the geological data include surface microseismic amplitude and ice displacement speed; Determine the demarcation point based on the length of the polar day and polar night cycle, divide the data time period based on the demarcation point, and increase the energy storage capacity weight coefficient to the preset value during the polar night period; The temperature difference is calculated based on the temperature value in the current fixed period and the value in the previous fixed period, and the temperature difference is input into the constructed cracking prediction model to output the probability of ice layer cracking; Output the predicted value of ice displacement speed according to ice displacement speed and ice cracking probability; The surface microseismic amplitude data is standardized and vector synthesis is performed with the predicted value of ice layer displacement velocity to obtain the foundation stability coefficient. When it is detected that the wind speed exceeds the set threshold and the foundation stability factor is lower than the critical value, the shell reinforcement instruction is triggered; The safety risk value of the terminal is calculated based on the foundation stability coefficient, smart terminal energy data, and ice cracking probability.

2. The method for evaluating security risks of an intelligent terminal according to claim 1, wherein: The step of increasing the energy storage capacity weight coefficient to a preset value during the polar night period includes: During the polar night period, the geographical location coordinates of the terminal are obtained by satellite positioning, and the number of remaining polar night days is calculated in combination with the astronomical calendar; During the polar day, a light intensity sensor is used to monitor the solar radiation intensity. When the solar radiation intensity exceeds 800W / m² and lasts for 3 hours, a wind speed correlation analysis is performed: If the wind speed reaches 15m / s during this period and the fluctuation exceeds 50% of the average value of the previous 24 hours, a storm warning signal will be generated and the electromagnetic locking device of the terminal casing will be activated 48 hours in advance.

3. The method for evaluating security risks of an intelligent terminal according to claim 1, wherein: The foundation stability coefficient obtained includes: The temperature difference is calculated based on the temperature data of the current period and the temperature data of the previous period, and the temperature difference is input into the cracking prediction model built based on the thermodynamic principle to output the probability of ice layer cracking; According to the ice displacement velocity and ice cracking probability, the predicted value of ice displacement velocity is obtained by probability weighted average calculation; The surface microseismic amplitude data is standardized and vector synthesis is performed with the predicted value of ice layer displacement velocity to obtain the foundation stability coefficient.

4. The method for evaluating security risks of an intelligent terminal according to claim 1, wherein: The smart terminal energy data includes: Before the polar night begins, the current longitude and latitude of the smart terminal is obtained through polar satellite positioning, and the remaining days are calculated in combination with the polar night cycle data; Obtaining the remaining power of the smart terminal, and inputting the remaining days and the remaining power of the smart terminal into a pre-built calculation model to output the number of safe operation days; During the polar day period, the light sensor monitors the daily effective light duration in real time. When the light duration exceeds 8 hours, the smart terminal is charged at maximum power. When the light duration is less than 4 hours, it switches to low-power discharge mode and shuts down non-core devices.

5. The method for evaluating security risks of an intelligent terminal according to claim 1, wherein: The continuous collection of meteorological data, geological data, and smart terminal energy data includes: Acquire internal data of the intelligent terminal, wherein the internal data includes microbial data, temperature data and humidity data inside the terminal; The humidity data, temperature data and microbial data are synchronously input into the constructed prediction model, and the model outputs a prediction curve of microbial proliferation within a specific time window in the future by establishing a dynamic correlation equation among the three; According to the microbial proliferation prediction curve, determine whether the microbial proliferation data is greater than the safety value. If so, initiate a cyclic disinfection and sterilization instruction.

6. The intelligent terminal security risk assessment method according to claim 1, wherein: The calculation of the safety risk value of the terminal includes: Input the foundation stability coefficient, intelligent terminal energy data, and ice layer cracking probability into a pre-constructed risk assessment model to output the safety risk value of the terminal.

7. The method for evaluating security risks of an intelligent terminal according to claim 1, characterized in that: After calculating the safety risk value of the terminal, it further includes: After the safety risk value is calculated, determine the current risk level by comparing with a preset hierarchical threshold interval, and execute the corresponding control strategy.

8. An intelligent terminal security risk assessment system, characterized in that: Using an intelligent terminal safety risk assessment method as described in any one of claims 1 to 7, the intelligent terminal safety risk assessment system includes: A data acquisition module for continuously collecting meteorological data, geological data, and intelligent terminal energy data; A data processing module for determining a demarcation point according to the durations of the polar day and polar night cycles, dividing data time periods according to the demarcation point, and increasing the energy storage capacity weight coefficient to a preset value during the polar night period; Calculate the temperature difference based on the value of the current fixed cycle and the value of the previous fixed cycle of the temperature, input the temperature difference into a constructed cracking prediction model to output the ice layer cracking probability; Output a predicted value of the ice layer displacement speed according to the ice layer displacement speed and the ice layer cracking probability; Perform standardization processing on the surface microseismic amplitude data, and perform vector synthesis calculation with the predicted value of the ice layer displacement speed to obtain the foundation stability coefficient; An execution module for triggering a housing reinforcement instruction when it is detected that the wind speed exceeds a set threshold and the foundation stability coefficient is lower than a critical value; A risk assessment module for calculating the safety risk value of the terminal according to the foundation stability coefficient, intelligent terminal energy data, and ice layer cracking probability.

Images