Grain informatization data security management system

Abstract

The invention relates to the technical field of data management, in particular to a grain informatization data safety management system, which comprises an environment dynamic optimization module, a data management module and a data management module, wherein the environment dynamic optimization module is used for collecting temperature, humidity, gas components and illumination intensity parameters in a grain storage environment, calculating a parameter deviation value of the current environment, and adjusting environment parameters by dynamically evaluating a membership degree; and generating environment optimization adjustment parameters. According to the invention, by collecting multiple parameters such as temperature and humidity, gas components, illumination intensity and the like in the grain storage environment and based on dynamic comparison and deviation value calculation of monitoring data, the accuracy and adaptability of environmental data are improved. And the deviation condition of the environmental parameters is dynamically evaluated, so that the storage condition can be adjusted in time, and the potential influence of the uncertainty and fluctuation of the storage environment on the food safety is reduced. The abnormal points of the environmental data are analyzed, and the fluctuation rule and the dynamic characteristics are extracted, so that potential problems can be quickly identified, abnormal characteristic indexes are generated, and a basis is provided for subsequent processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a food information data security management system. Background Art

[0002] The field of data management technology focuses on the collection, storage, processing, analysis and maintenance of data to ensure the security, integrity, availability and controllability of data. This field covers technologies such as database technology, data warehouse, data governance, data security, data privacy protection and data lifecycle management. Its goal is to enable enterprises and organizations to extract the maximum value from data through effective data management technologies and strategies, while preventing risks such as data leakage, tampering and loss.

[0003] Among them, the food information data security management system is to improve the security, management efficiency and decision-making support capabilities of food data through information technology. Its main uses include achieving real-time collection and monitoring of food data, strengthening the security management of food storage and circulation information, improving data sharing efficiency, and providing data support for decision-making in the food supply chain.

[0004] Existing technologies do not fully capture the dynamic changes of multi-dimensional environmental parameters in data collection and monitoring, and can only provide static data records. It is difficult to reflect the dynamic changes of the storage environment in a timely manner, resulting in insufficient ability to predict potential risks in the storage environment. The analysis of abnormal data relies on a single indicator to judge, ignoring the dynamic characteristics of the correlation between data, which may lead to risks that are not fully revealed. In terms of data storage, it fails to optimize different types of data in a layered manner, which easily leads to problems such as low data storage efficiency and insufficient management of key data. In addition, the analysis of storage environment change trends and the prediction of abnormal risks are relatively weak, and there is a lack of in-depth assessment of long-term safety risks. These deficiencies will make it difficult for storage management to respond to environmental issues in a timely and efficient manner, which may cause food spoilage or safety problems. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a food information data security management system.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A food information data security management system comprises:

[0007] The environment dynamic optimization module collects the temperature, humidity, gas composition and light intensity parameters in the grain storage environment, calculates the parameter deviation value of the current environment, adjusts the environmental parameters through dynamic evaluation of membership, and generates environmental optimization adjustment parameters;

[0008] The environmental anomaly detection module calls the environmental optimization adjustment parameters, analyzes the fluctuation rules between the parameters, screens the monitoring point data that exceeds the safety threshold, and extracts the associated dynamic change characteristics of the monitoring point data to generate environmental anomaly characteristic indicators;

[0009] The data hierarchical storage module divides the parameters in the grain storage environment into environmental regulation related data and environmental anomaly related data, groups and stores the environmental regulation related data, matches and analyzes the environmental anomaly related data with the environmental anomaly characteristic indicators, and generates hierarchical environmental data storage results;

[0010] The environmental prediction and control module performs trend analysis on the time series of the environmental control related data and the abnormal related data in the hierarchical environmental data storage results, extracts the key nodes in the trend changes, and predicts whether the current abnormal characteristics will continue to affect storage safety based on the key nodes, so as to obtain the food data safety management results.

[0011] As a further solution of the present invention, the step of obtaining the parameter deviation value of the current environment is specifically as follows:

[0012] Collect the temperature, humidity, gas concentration and light intensity data in the grain storage environment in real time and convert them into continuous change curves, compare and analyze the continuous change curves, record their change values, and generate parameter change data record sets;

[0013] For the parameter change data record set, the formula is used:

[0014]

[0015] Calculate the deviation value P of the i-th parameter i , get the parameter deviation data of the current environment;

[0016] Among them, X m is the current monitoring value, X s is the target setting value, α i is the dynamic adjustment coefficient.

[0017] As a further solution of the present invention, the step of obtaining the environment optimization adjustment parameters is specifically as follows:

[0018] For the parameter deviation data of the current environment, the formula is used:

[0019]

[0020] Calculate the membership μ of the i-th parameter i , get parameter membership data;

[0021] Among them, β is the sensitivity coefficient, γ is the expected target value, and e represents the exponential with e as the base;

[0022] Based on the parameter membership data and in combination with the deviation value of the parameter, the adjustment priority is dynamically evaluated and analyzed, the environmental parameters are adjusted, and the environmental optimization adjustment parameters are generated.

[0023] As a further solution of the present invention, the step of obtaining the monitoring point data that exceeds the safety threshold is specifically as follows:

[0024] Based on the environmental optimization adjustment parameters, the fluctuation patterns of the environmental parameters at the monitoring points are analyzed, and the trend of parameter changes is identified by comparing all the collected data with the current values, and abnormal fluctuations are marked to generate fluctuation pattern analysis results;

[0025] Based on the analysis results of the fluctuation law, the formula is adopted:

[0026] ΔP j =|P j -P safe |

[0027] Calculate the difference ΔP at monitoring point j j , get the comparison result between the monitoring point and the safety boundary;

[0028] Among them, P j is the environmental parameter value of monitoring point j, P safe It is the preset safety boundary value.

[0029] As a further solution of the present invention, the step of obtaining the environmental abnormality characteristic index is specifically as follows:

[0030] Based on the comparison results between the monitoring points and the safety boundary, for the monitoring point data exceeding the safety threshold, the fluctuation amplitude and dynamic change characteristics of the monitoring point are extracted, and the fluctuation pattern of the data is identified through time series analysis to obtain the dynamic change analysis results of the monitoring point data;

[0031] Based on the dynamic change analysis results of the monitoring point data, the monitoring point data is weighted, key dynamic features are extracted, and environmental abnormality feature indicators are generated.

[0032] As a further solution of the present invention, the step of obtaining the hierarchical environment data storage result is specifically:

[0033] Based on the parameters in the grain storage environment, the grain storage environment is divided into environmental control related data and environmental abnormality related data, and the environmental control related data is grouped and stored by time period or type to establish grouped stored environmental data;

[0034] Based on the environmental data stored in the groups, the environmental anomaly associated data and the environmental anomaly characteristic indicators are matched and analyzed, and the abnormal data are classified according to the characteristics and impact degree, so as to generate a hierarchical environmental data storage result.

[0035] As a further solution of the present invention, the step of obtaining the key nodes in the extraction trend change is specifically:

[0036] Based on the hierarchical environmental data storage results, the trend of the time series of environmental regulation related data is analyzed to identify the continuous environmental change risks and obtain the environmental regulation trend analysis results;

[0037] Based on the environmental regulation trend analysis results, by locating turning points in the data and identifying the moments of change through differential sequences, key nodes in the trend change are extracted to obtain key node analysis results.

[0038] As a further solution of the present invention, the steps for obtaining the food data safety management results are specifically as follows:

[0039] Based on the key node analysis results, analyze the frequency of abnormal data in each time period, perform fluctuation analysis on the number of abnormalities, obtain the proportion of abnormal data in each time period, extract the distribution law of abnormal data on the time axis, and obtain the density change trend of abnormal data;

[0040] Based on the density change trend of the abnormal data, the formula is adopted:

[0041]

[0042] Calculate the risk index R continuity , predict whether the current abnormal characteristics will continue to affect storage safety, and obtain the results of food data safety management;

[0043] Where H is the total number of key nodes, ΔF i′,h is the variation range of the i′th type parameter at the hth key node, T is the total time length of the monitoring period, and W is the risk weight.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, by collecting multiple parameters such as temperature and humidity, gas composition and light intensity in the grain storage environment, and based on the dynamic comparison and deviation value calculation of the monitoring data, the accuracy and adaptability of the environmental data are improved. Dynamic evaluation of the deviation of environmental parameters can adjust the storage conditions in time, reducing the uncertainty and potential impact of fluctuations in the storage environment on food security. Analysis of abnormal points in environmental data can quickly identify potential problems and generate abnormal characteristic indicators by extracting fluctuation patterns and dynamic characteristics, providing a basis for subsequent processing. Through hierarchical storage and classification analysis, different types of data are processed in a refined manner, which not only improves the efficiency of data storage, but also ensures the targeted management of abnormal data. Based on trend analysis and key node extraction, combined with the distribution density and frequency evaluation of abnormal data, the ability to predict the continuous impact of abnormalities is realized, the monitoring and management of storage safety is strengthened, not only the precise regulation of the storage environment is realized, but also the intelligence of grain management is improved through comprehensive analysis of multidimensional data, and the data decision support capability is significantly enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a system flow chart of the present invention;

[0047] Figure 2 A flow chart for calculating parameter deviation values ​​of the current environment for the present invention;

[0048] Figure 3 Obtaining the flow chart of environmental optimization adjustment parameters for the present invention;

[0049] Figure 4 A data flow chart for screening monitoring points exceeding a safety threshold for the present invention;

[0050] Figure 5 A flow chart for obtaining environmental anomaly characteristic indicators for the present invention;

[0051] Figure 6 A flowchart of the present invention for obtaining the hierarchical environment data storage result;

[0052] Figure 7 A flowchart of the key nodes in the trend change extracted by the present invention;

[0053] Figure 8 The present invention is a flow chart for obtaining food data safety management results. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0056] See also Figure 1 , a food information data security management system includes:

[0057] The environment dynamic optimization module collects the temperature, humidity, gas composition and light intensity parameters in the grain storage environment, compares the monitored temperature change values, humidity change values, light intensity values ​​and gas concentration change values, calculates the parameter deviation value of the current environment, adjusts the environmental parameters through dynamic evaluation of membership, and generates environmental optimization adjustment parameters;

[0058] The environmental anomaly detection module calls the environmental optimization adjustment parameters, analyzes the fluctuation patterns between the parameters, and screens the monitoring point data that exceeds the safety threshold by calculating the difference between the parameter monitoring point and the safety boundary. It also extracts the associated dynamic change characteristics of the monitoring point data to generate environmental anomaly characteristic indicators.

[0059] The data hierarchical storage module divides the parameters in the grain storage environment into environmental control related data and environmental anomaly related data, groups and stores the environmental control related data, matches and analyzes the environmental anomaly related data with environmental anomaly characteristic indicators, and generates hierarchical environmental data storage results;

[0060] The environmental prediction and control module performs trend analysis on the time series of environmental control-related data and abnormal-related data in the hierarchical environmental data storage results, extracts key nodes in trend changes, analyzes the distribution density and frequency of abnormal-related data, and predicts whether the current abnormal characteristics will continue to affect storage safety based on key nodes, thereby obtaining food data safety management results;

[0061] Environmental optimization and adjustment parameters include the dynamic adjustment range of ambient temperature, the target value range of humidity, and the optimized ratio of gas concentration. Environmental abnormality characteristic indicators include the abnormality type classification of monitoring points, the time span and fluctuation trend of deviation values, and the density distribution information of related characteristics. The layered environmental data storage results include the priority storage location of environmental control data, the independent partition identification of abnormal data, and the storage association labels of each group of data. The food data safety management results include the time series prediction values ​​of key parameters in the future storage environment, the risk warning values ​​of potential abnormal points, and the environmental priority regulation within the storage area.

[0062] See also Figure 2 , the specific steps for calculating the parameter deviation value of the current environment are:

[0063] Collect the temperature, humidity, gas concentration and light intensity data in the grain storage environment in real time and convert them into continuous change curves, compare and analyze the continuous change curves, record their change values, and generate parameter change data record sets;

[0064] The temperature, humidity, gas concentration and light intensity data are collected in real time through sensor equipment installed in the grain storage environment. The temperature parameters are collected and recorded once every hour, and the humidity data are summarized through the hourly average value. The gas concentration monitoring records the concentration value of the current period at a fixed sampling frequency, and the light intensity is collected by the light intensity value recorded by the sensor. The historical data change curves of the monitored temperature, humidity and gas concentration are compared and analyzed through MATLAB, and their changes are recorded and the daily maximum and minimum values ​​are marked, finally forming a set of change data records for each parameter.

[0065] For the parameter change data record set, the formula is used:

[0066]

[0067] Calculate the deviation value P of the i-th parameter i , get the parameter deviation data of the current environment;

[0068] Among them, X m is the current monitoring value, which refers to the value collected by the sensor in the grain storage environment in real time, such as the temperature value collected by the temperature sensor, the humidity value collected by the humidity sensor, etc., obtained through the environmental monitoring equipment, X s is the target setting value, which refers to the environmental parameter value determined according to the recommended standard or management target of grain storage environment. i It is a dynamic adjustment coefficient used to correct the deviation value and reflect the characteristics of historical fluctuations of the monitoring value. It is obtained by normalizing the standard deviation of the data. The calculation formula is: σ is the standard deviation of the data, and the dynamic adjustment coefficient α is introduced i, can correct the deviation value calculation according to the historical fluctuation characteristics, enhance the fault tolerance to data fluctuations, and thus improve the flexibility and reliability of calculation.

[0069] For example, if X m The temperature is 25.3℃, the humidity is 65%, the light intensity is 800lx, the gas concentration is 400ppm, and X s The target temperature is 23°C, the target humidity is 60%, the target light intensity is 750lx, the target gas concentration is 350ppm, and the temperature adjustment coefficient is set to 0.05.

[0070] Temperature deviation:

[0071]

[0072] Humidity deviation:

[0073]

[0074] Light intensity deviation:

[0075]

[0076] Gas concentration deviation:

[0077]

[0078] The calculation results show that the current temperature deviation value is 15%, humidity is 20.3%, light intensity is 21.7%, and gas concentration is 24.3%.

[0079] See also Figure 3 , the specific steps for obtaining the environmental optimization adjustment parameters are:

[0080] For the parameter deviation data of the current environment, the formula is used:

[0081]

[0082] Calculate the membership μ of the i-th parameter i , get parameter membership data;

[0083] Among them, β is the sensitivity coefficient, which reflects the response speed of the membership change to the deviation value change. Specifically, the larger the β is, the more sensitive the membership change is. When the deviation value is small, the change of the membership will be more obvious, and the smaller the β is, the more gradual the change of the membership will be. For some environmental parameters (such as temperature, humidity, etc.), when the change amplitude is large, a larger β may be required to more sensitively respond to environmental changes in the actual monitoring process. For control systems that require rapid response, β can be set larger; and for control systems that are not very sensitive to fluctuations, β can be appropriately reduced. Through regression analysis of historical data, Observe the impact of different sensitivity values ​​on the membership and control effect, and determine the appropriate β value. Assume that in a certain grain storage environment, the sensitivity of the temperature deviation value is higher, because a slight change in temperature may have a greater impact on the quality of grain storage. Therefore, the sensitivity coefficient β can be set to 2, which means that for each unit deviation value, the change in membership will be more drastic. For the humidity parameter, a more conservative sensitivity coefficient of 1.5 is set so that the adjustment of humidity will not be too drastic. γ is the expected target value, reflecting the center point of the membership curve, and is set with reference to industry standards. e is an exponential function, which represents an exponential operation with e as the base.

[0084] For example, if the monitoring data in the grain storage environment is: temperature deviation value P T =15%, humidity deviation value P H =5%, light intensity deviation value P L =10%, gas concentration deviation value P G =20%, according to the sensitivity coefficient β=2.0 and the center deviation value γ=0.10 (i.e., the target deviation value of 10%), the membership degree of each environmental parameter can be calculated.

[0085] Membership calculation of temperature:

[0086] P T -γ=0.15-0.1=0.05

[0087]

[0088] Membership calculation of humidity:

[0089] P H -γ=0.05-0.1=-0.05

[0090]

[0091] Membership calculation of light intensity:

[0092] P L -γ=0.1-0.1=0

[0093]

[0094] Membership calculation of gas concentration:

[0095] P G -γ=0.2-0.1=0.1

[0096]

[0097] The results show that the temperature membership: μ T ≈0.525, humidity membership: μ H ≈0.475, light intensity membership: μ L ≈0.5, gas concentration membership: μ G ≈0.550.

[0098] Based on parameter membership data and combined with parameter deviation values, dynamically evaluate and analyze adjustment priorities, adjust environmental parameters, and generate environmental optimization adjustment parameters;

[0099] The various parameters of the grain storage environment, including temperature and humidity, gas concentration and light intensity, all have preset standard values, and data is collected in real time through monitoring equipment. In order to ensure the stability of the grain storage environment, the deviation values ​​of all parameters will be calculated and converted into membership, which is used to determine the adjustment priority. The membership value range is 0 to 1, where 0 means that it does not meet the standard at all, 1 means that it meets the standard completely, and the value between the two reflects the degree of deviation of the parameter from the standard. For example, the membership of temperature is 0.525, which means that the deviation value of this parameter is in the medium range, that is, the deviation degree of temperature is not serious, but it still needs to be adjusted appropriately to ensure that the temperature environment is maintained within the appropriate range. The membership of humidity is 0.475, and the deviation value is small, which means that the priority of humidity adjustment is low, but it still needs to be slightly adjusted according to the real-time monitoring data to increase or decrease the moisture supply. The membership of light intensity is 0.5, which means that the light intensity is close to the target value, so there is no need for major adjustments, and only the operating status of the existing lighting equipment needs to be maintained. The membership degree of gas concentration is 0.550, indicating that the parameter deviates greatly, so it is necessary to adjust the ventilation or adsorption equipment first to reduce the concentration of harmful gases and ensure that the environmental gas composition is within a safe range. Through these dynamic evaluation results, the corresponding environmental optimization adjustment parameters are generated to accurately control the operating parameters of the equipment, ensure that the grain storage environment meets safety standards, and avoid the negative impact of environmental parameters on grain quality.

[0100] See also Figure 4 ,The specific steps for obtaining the monitoring point data that exceeds the safety threshold are:

[0101] Based on the environment optimization adjustment parameters, analyze the fluctuation patterns of environmental parameters at each monitoring point, identify the trend of parameter changes by comparing all collected data with the current values, mark abnormal fluctuations, and generate fluctuation pattern analysis results;

[0102] First, historical environmental data of multiple monitoring points, such as temperature and humidity, gas concentration, and light intensity, are obtained, and the data is preliminarily cleaned to remove missing values ​​and outliers. Subsequently, the data is tested for volatility through time series analysis. Common methods include using Excel, MATLAB, or the Pandas library in Python for data smoothing, eliminating short-term fluctuations through moving average or exponential smoothing, and retaining long-term trends. Next, statistical methods are used to analyze the volatility characteristics of each parameter. By calculating the fluctuation amplitude, variance, and standard deviation of each parameter within a certain time period, these statistics can effectively reflect the intensity of the fluctuation of the parameter value. For example, the larger the standard deviation of temperature change, the more drastic the temperature fluctuation, and there may be a higher environmental risk. For each monitoring point, by calculating the fluctuation amplitude of each environmental parameter, the fluctuation differences between different monitoring points can be further understood. In addition, covariance and correlation analysis methods can also be used to evaluate the relationship between different environmental parameters. By calculating the correlation coefficient between temperature and humidity, it is determined whether there is a strong linkage between them. These parameters may affect other environmental factors and thus affect the stability of the entire environment. The calculation process is implemented through MATLAB, R language or Python's SciPy library, which assists in analyzing which parameters have the strongest volatility and which parameters need to be adjusted in a coordinated manner.

[0103] Based on the results of fluctuation law analysis, the formula is adopted:

[0104] ΔP j =|P j -P safe |

[0105] Calculate the difference ΔP at monitoring point j j , get the comparison result between the monitoring point and the safety boundary;

[0106] Among them, P j is the actual environmental parameter value of monitoring point j, for example, it can be temperature, humidity, gas concentration, etc., which is collected in real time by sensors or monitoring equipment. safe It is a preset safety boundary value, indicating the maximum or minimum safety value allowed for the environmental parameter. The setting of the safety boundary is usually determined through historical data analysis, expert experience or regulatory standards. For example, the safety temperature boundary of a certain area may be set at 18°C ​​to 28°C. If the temperature exceeds this range, it indicates that there may be an abnormal situation.

[0107] Taking temperature as an example, if the temperature P at a certain monitoring pointj is 30℃, and the safety temperature boundary P safe is 25°C, the calculated difference is:

[0108] ΔP=|30-25|=5℃

[0109] The difference indicates that the temperature deviates from the safety boundary by 5°C, which may indicate that there is an abnormality in the environment of the monitoring point, and the temperature exceeds the safety range, and corresponding adjustment measures need to be taken. By analyzing the difference of the monitoring points, it can be determined which monitoring points have environmental parameters that exceed the preset safety range. These points that exceed the safety boundary will serve as alarm points and further trigger the environmental anomaly handling program. In actual applications, the changes in these differences can be monitored through real-time data streams to ensure rapid response and intervention.

[0110] See also Figure 5 ,The specific steps for obtaining environmental anomaly characteristic indicators are:

[0111] Based on the comparison results between the monitoring points and the safety boundary, for the monitoring point data that exceeds the safety threshold, the fluctuation amplitude and dynamic change characteristics of the monitoring points are extracted, and the fluctuation pattern of the data is identified through time series analysis to obtain the dynamic change analysis results of the monitoring point data;

[0112] For monitoring point data that exceeds the safety threshold, it is necessary to first identify which monitoring points have data that exceeds the preset safety threshold range. Then, based on these data points, the time series change characteristics of the monitoring point data are analyzed. Common analysis methods include obtaining dynamic characteristics such as the fluctuation amplitude and change trend of the monitoring point data. For example, by analyzing the fluctuations of the monitoring point data in different time periods, it is possible to identify whether there are large fluctuations or sudden changes, which may be caused by environmental abnormalities. Furthermore, data cleaning and filtering techniques can be used to remove irrelevant noise, retain key fluctuation information, and ensure the accuracy of the analysis. Finally, the change characteristics of these data are compared with the normal fluctuation range to confirm which monitoring points belong to the abnormal range.

[0113] Based on the dynamic change analysis results of the monitoring point data, the monitoring point data is weighted, key dynamic features are extracted, and environmental abnormality feature indicators are generated;

[0114] For each monitoring point, extract key dynamic features such as fluctuation amplitude and change rate. These features can be obtained by calculating the maximum change amplitude and average change rate of data points within a certain period of time through data analysis tools (such as Excel, MATLAB, etc.). Next, these features are weighted. The basis for weighting is the importance of different features to the overall anomaly detection results. This weight can be set based on historical data, expert experience, or model-based analysis results. For example, if the fluctuation amplitude has a greater impact on the anomaly detection results, a higher weight is assigned to the fluctuation amplitude; if changes with a slower rate of change may also cause anomalies, the rate of change is given a corresponding weight.

[0115] See also Figure 6 , the specific steps for obtaining the hierarchical environment data storage results are:

[0116] Based on the parameters in the grain storage environment, the grain storage environment is divided into environmental control related data and environmental abnormality related data, and the environmental control related data is grouped and stored by time period or type to establish grouped stored environmental data;

[0117] The parameters in the grain storage environment are divided into environmental control-related data and environmental abnormality-related data, and the environmental control-related data are grouped and stored. This step first involves classifying the data according to the nature of the parameters. Environmental control-related data refers to those parameters that directly affect the storage status of grain, such as temperature, humidity, light, airflow rate, etc. These data need to be collected in real time and stored in groups in chronological order. In order to ensure the efficiency of storage and the convenience of subsequent processing, a database management system (such as MySQL, SQLite, etc.) can be used to group these data by time period, date or environmental parameter type. For example, temperature and humidity data can be stored in the same group, while airflow rate is stored separately. During the storage of these data, the original data needs to be cleaned according to the acquisition frequency and accuracy, and outliers or missing values ​​need to be removed or missing values ​​corrected to ensure the accuracy and validity of subsequent data. After each group of data is stored, the database system will mark the timestamp of each group of data and provide a retrieval interface to support users to query and analyze according to different environmental conditions.

[0118] Based on the environmental data stored in groups, the matching analysis of environmental anomaly correlation data and environmental anomaly characteristic indicators is performed, and the abnormal data is classified according to the characteristics and impact degree, and the hierarchical environmental data storage results are generated;

[0119] The environmental anomaly correlation data and environmental anomaly characteristic indicators are matched and analyzed. In this step, the identified abnormal data and the corresponding characteristic indicators (such as temperature and humidity beyond the normal range) will be associated and analyzed. First, by analyzing the time, value and other information of each data point, the relationship between the abnormal data and the storage environment is found. Environmental abnormality characteristic indicators such as high temperature and low humidity represent potential risks in grain storage. Based on these characteristic indicators, the abnormal data is compared with its characteristic values ​​to determine the abnormal nature and impact of the data. Specifically, the abnormal data can be divided into different levels, such as minor abnormalities and severe abnormalities, according to the strength of its association with the characteristic indicators. Through this hierarchical division, different response measures can be taken for different abnormal states to generate hierarchical environmental data storage results. The results are displayed in the form of a data table, and each abnormal data will be marked with the abnormal level to which it belongs, and the relevant environmental characteristic values ​​are attached.

[0120] See also Figure 7 , the specific steps for extracting the key nodes in the trend change are:

[0121] Based on the hierarchical environmental data storage results, analyze the trend of the time series of environmental regulation-related data, identify the continuous environmental change risks, and obtain the environmental regulation trend analysis results;

[0122] When conducting trend analysis, the time series of environmental regulation-related data are first cleaned and prepared to ensure the continuity and validity of the data. Data cleaning usually involves removing invalid data, filling missing values, and removing outliers. The processed data are arranged in chronological order to form a stable time series, and then smoothing techniques (such as sliding average) are used to reduce the interference of short-term fluctuations. The core purpose of trend analysis is to extract long-term change trends while ignoring cyclical or short-term fluctuations, helping to identify potential long-term environmental change impacts. In this process, it is necessary to compare and verify the long-term trend of the data to analyze whether there is an obvious upward or downward trend. For example, if the mutation points in certain cyclical changes are analyzed, it is necessary to check whether these fluctuations are caused by external factors (such as sudden weather changes). Ultimately, trend analysis will help discover potential risk changes in the grain storage environment and provide data support for subsequent risk management and safety warnings.

[0123] Based on the results of environmental regulation trend analysis, by locating the turning points in the data and identifying the moments of change through differential sequences, the key nodes in the trend change are extracted and the key node analysis results are obtained;

[0124] When extracting key nodes in trend changes, it is necessary to locate turning points that have an important impact on environmental regulation through detailed analysis of time series. These key nodes are usually when the data fluctuates violently, or when there are obvious changes before and after a specific time point. In order to accurately extract key nodes, the rate of change of the data can be calculated first to identify the time point when the mutation occurs, and then the nodes with large changes can be selected as key nodes. In order to further improve the accuracy, signal processing methods can be used, such as calculating differential sequences to identify the mutation moments in the sequence. By analyzing these nodes, the key periods of environmental changes can be better captured, providing an important reference for anomaly detection and risk assessment in grain storage environments. For example, if the temperature and humidity fluctuate greatly during a period of time, it can be judged as a key node that may affect grain storage safety. Through data processing and analysis of these nodes, timely warnings can be made for potential risks in grain storage.

[0125] See also Figure 8 , the specific steps for obtaining food data safety management results are:

[0126] Based on the key node analysis results, analyze the frequency of abnormal data in each time period, perform fluctuation analysis on the number of abnormalities, obtain the proportion of abnormal data in each time period, extract the distribution law of abnormal data on the time axis, and obtain the density change trend of abnormal data;

[0127] SPSS statistical software is used to obtain the frequency of abnormal data in each time period, the total amount of abnormal data in a cycle is recorded, the data analysis module is called to obtain the fluctuation of the number of abnormalities in different time periods, and the proportion of abnormal data in each time unit is obtained. MATLAB is used to extract the distribution law of abnormal data on the time axis, and the data processing program is used to output the density change trend of abnormal data in different time periods, and the increase and decrease of abnormal data per unit time are obtained. The spectrum analysis module is called to obtain the time change characteristics of abnormal data, and the spatial data analysis software is used to extract the spatial distribution of abnormal data in the storage environment, and the proportion of abnormal data in different storage areas is obtained. The spatial distribution density of abnormal data is called, and the spatial distribution law of abnormal data in the storage environment is obtained through GIS software. The data mining program is used to extract the density change characteristics of abnormal data in different storage areas. The spatial accumulation analysis module is used to obtain the accumulation of abnormal data in the unit space, and the density and frequency distribution characteristics of abnormal related data are obtained.

[0128] Based on the density change trend of abnormal data, the formula is used:

[0129]

[0130] Calculate the risk index R continuity, predict whether the current abnormal characteristics will continue to affect storage safety, and obtain the results of food data safety management;

[0131] Where H is the total number of key nodes, which is obtained from the results of time series analysis, for example, by extracting important fluctuation points from the differential sequence, ΔF i′,h is the change amplitude of the i′th type parameter at the hth key node, indicating the significant change of the monitoring data before and after the key node time, obtained by the difference formula: ΔF i′,h =|F i′,h,t+1 -F i′,h,t |, F i′,h,t is the parameter value before the critical node time point, F i′,h,t+1 It is the parameter value after the key node time point. The data comes from the real-time monitoring equipment of the storage environment, such as the environmental data recorded by the temperature and humidity sensor. t+1 represents the monitoring time after the key node time point, t represents the monitoring time before the key node time point, T is the total time length of the monitoring cycle, which is usually obtained directly through the monitoring plan or time range. W is the risk weight, which is used to adjust the impact of different abnormal characteristics on storage safety. The weight can be determined based on historical data or expert evaluation. For example, the weight is higher when the temperature and humidity fluctuation weight is higher.

[0132] For example, within a 30-day monitoring period (T=30 days), three key nodes were extracted:

[0133] The first key node (temperature) change range ΔF T′,1 =|F T′,1,t+1 -F T′,1,t |=|33-28|=5, weight W=0.9, change range of the second key node (humidity) ΔF H′,2 =|F H′,2,t+1 -F H′,2,t |=

[0134] |70-65|=5, weight W=0.8, the change range of the third key node (gas concentration) ΔF C′,3 =

[0135] |F C′,3,t+1 -F C′,3,t |=|400-350|=50, weight W=0.7.

[0136] Substituting into the formula:

[0137]

[0138] The results show that the calculated risk index R continuity =1.6, risk index R continuityIt is an indicator derived from the change range of key nodes, monitoring cycle and risk weight, and is used to evaluate the continuous impact of abnormal characteristics on the storage environment. Based on historical data and expert experience, the following reference range can be defined: R continuity <0.5: low risk, the abnormal characteristics have little impact on storage safety, and no intervention measures are required; 0.5≤R continuity <1.0: Medium risk. Abnormal characteristics may have a certain impact on storage safety. It is recommended to monitor abnormal change trends. continuity ≥1.0: High risk, abnormal characteristics have a significant impact on storage safety, and immediate intervention measures are required. continuity =1.6, which is in the high risk range. This indicates that the abnormal characteristics in the current environment are highly persistent and may affect the stability and safety of the grain storage environment. If the change in key parameters (such as temperature, humidity or gas concentration) exceeds the set threshold and is not alleviated in the next monitoring cycle, the abnormal characteristics may continue to affect storage safety.

[0139] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A food information data security management system, characterized in that: The system comprises: The environment dynamic optimization module collects the temperature, humidity, gas composition and light intensity parameters in the grain storage environment, calculates the parameter deviation value of the current environment, adjusts the environmental parameters through dynamic evaluation of membership, and generates environmental optimization adjustment parameters; The environmental anomaly detection module calls the environmental optimization adjustment parameters, analyzes the fluctuation rules between the parameters, screens the monitoring point data that exceeds the safety threshold, and extracts the associated dynamic change characteristics of the monitoring point data to generate environmental anomaly characteristic indicators; The data hierarchical storage module divides the parameters in the grain storage environment into environmental regulation related data and environmental anomaly related data, groups and stores the environmental regulation related data, matches and analyzes the environmental anomaly related data with the environmental anomaly characteristic indicators, and generates hierarchical environmental data storage results; The environmental prediction and control module performs trend analysis on the time series of the environmental control related data and the abnormal related data in the hierarchical environmental data storage results, extracts the key nodes in the trend changes, and predicts whether the current abnormal characteristics will continue to affect storage safety based on the key nodes, so as to obtain the food data safety management results.

2. The food information data security management system according to claim 1 is characterized in that: The step of obtaining the parameter deviation value of the current environment is specifically as follows: Collect the temperature, humidity, gas concentration and light intensity data in the grain storage environment in real time and convert them into continuous change curves, compare and analyze the continuous change curves, record their change values, and generate parameter change data record sets; For the parameter change data record set, the formula is used: Calculate the deviation value P of the i-th parameter i , get the parameter deviation data of the current environment; Among them, X m is the current monitoring value, X s is the target setting value, α i is the dynamic adjustment coefficient.

3. The food information data security management system according to claim 2 is characterized in that: The steps for obtaining the environment optimization adjustment parameters are specifically as follows: For the parameter deviation data of the current environment, the formula is used: Calculate the membership μ of the i-th parameter i , get parameter membership data; Among them, β is the sensitivity coefficient, γ is the expected target value, and e represents the exponential with e as the base; Based on the parameter membership data and in combination with the deviation value of the parameter, the adjustment priority is dynamically evaluated and analyzed, the environmental parameters are adjusted, and the environmental optimization adjustment parameters are generated.

4. The food information data security management system according to claim 3 is characterized in that: The steps of obtaining the monitoring point data that exceeds the safety threshold by screening are specifically as follows: Based on the environmental optimization adjustment parameters, the fluctuation patterns of the environmental parameters at the monitoring points are analyzed, and the trend of parameter changes is identified by comparing all the collected data with the current values, and abnormal fluctuations are marked to generate fluctuation pattern analysis results; Based on the analysis results of the fluctuation law, the formula is adopted: ΔP j =|P j -P safe | Calculate the difference ΔP at monitoring point j j , get the comparison result between the monitoring point and the safety boundary; Among them, P j is the environmental parameter value of monitoring point j, P safe It is the preset safety boundary value.

5. The food information data security management system according to claim 4 is characterized in that: The steps for obtaining the environmental abnormality characteristic index are specifically as follows: Based on the comparison results between the monitoring points and the safety boundary, for the monitoring point data exceeding the safety threshold, the fluctuation amplitude and dynamic change characteristics of the monitoring point are extracted, and the fluctuation pattern of the data is identified through time series analysis to obtain the dynamic change analysis results of the monitoring point data; Based on the dynamic change analysis results of the monitoring point data, the monitoring point data is weighted, key dynamic features are extracted, and environmental abnormality feature indicators are generated.

6. The food information data security management system according to claim 5 is characterized in that: The steps for obtaining the hierarchical environment data storage result are specifically as follows: Based on the parameters in the grain storage environment, the grain storage environment is divided into environmental control related data and environmental abnormality related data, and the environmental control related data is grouped and stored by time period or type to establish grouped stored environmental data; Based on the environmental data stored in the groups, the environmental anomaly associated data and the environmental anomaly characteristic indicators are matched and analyzed, and the abnormal data are classified according to the characteristics and impact degree, so as to generate a hierarchical environmental data storage result.

7. The food information data security management system according to claim 6 is characterized in that: The steps of obtaining the key nodes in the extraction trend change are specifically as follows: Based on the hierarchical environmental data storage results, the trend of the time series of environmental regulation related data is analyzed to identify the continuous environmental change risks and obtain the environmental regulation trend analysis results; Based on the environmental regulation trend analysis results, by locating turning points in the data and identifying the moments of change through differential sequences, key nodes in the trend change are extracted to obtain key node analysis results.

8. The food information data security management system according to claim 7 is characterized in that: The specific steps for obtaining the food data safety management results are: Based on the key node analysis results, analyze the frequency of abnormal data in each time period, perform fluctuation analysis on the number of abnormalities, obtain the proportion of abnormal data in each time period, extract the distribution law of abnormal data on the time axis, and obtain the density change trend of abnormal data; Based on the density change trend of the abnormal data, the formula is adopted: Calculate the risk index R continuity , predict whether the current abnormal characteristics will continue to affect storage safety, and obtain the results of food data safety management; Where H is the total number of key nodes, ΔF i′,h is the variation range of the i′th type parameter at the hth key node, T is the total time length of the monitoring period, and W is the risk weight.

Images