Data analysis methods, devices, equipment, media and products based on artificial intelligence

Abstract

The present invention discloses a data analysis method, device, equipment, medium and product based on artificial intelligence, which collects surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment; according to the multi-source data set, an environmental anomaly analysis value is calculated; when the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold, it is determined that the current environment is abnormal; according to the environmental anomaly analysis value, an environmental anomaly magnitude value is calculated; according to the environmental anomaly magnitude value, the abnormal level of the current environment is determined. By adopting the present invention, multi-source data can be collected and integrated in real time, complex environmental changes can be accurately reflected, and the accuracy and efficiency of monitoring environmental anomalies can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to an artificial intelligence-based data analysis method, device, equipment, medium and product. Background Art

[0002] In the field of environmental anomaly monitoring, artificial intelligence-based data analysis methods generate core indicators that can characterize environmental status through the collection, integration and calculation of multi-source data. This technology uses the powerful analytical capabilities of machine learning and intelligent algorithms to accurately identify environmental anomalies, predict trends and evaluate levels, and achieve real-time early warning through an intelligent feedback mechanism, providing a scientific basis for environmental management and decision-making.

[0003] In the current practice of air quality monitoring and environmental anomaly analysis, traditional methods have many defects. For example, the data source is single and difficult to integrate in real time, which cannot accurately reflect complex environmental changes. In addition, traditional analysis methods often rely on manual judgment and lack intelligent early warning mechanisms, making it difficult to respond quickly to sudden environmental events. These shortcomings significantly reduce the effectiveness of environmental monitoring systems and limit the accuracy of data-driven decision-making. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a data analysis method, device, equipment, medium and product based on artificial intelligence, which can collect multi-source data and integrate them in real time, accurately reflect complex environmental changes, and improve the accuracy and efficiency of monitoring environmental abnormalities.

[0005] To achieve the above objectives, an embodiment of the present invention provides a data analysis method based on artificial intelligence, comprising:

[0006] Collecting surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment;

[0007] Calculating an environmental anomaly analysis value according to the multi-source data set; wherein the environmental anomaly analysis value is used for environmental anomaly analysis;

[0008] When the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold, it is determined that the current environment is abnormal;

[0009] When it is determined that the current environment is abnormal, the environmental abnormality magnitude value is calculated according to the environmental abnormality analysis value; wherein the environmental abnormality magnitude value is used to characterize the degree of environmental abnormality;

[0010] The abnormality level of the current environment is determined according to the environmental abnormality magnitude value.

[0011] As an improvement of the above solution, the step of calculating the environmental anomaly analysis value according to the multi-source data set includes:

[0012] Calculate a first reference coefficient and a first correction coefficient according to the first data set; wherein the first reference coefficient is used to characterize the air quality condition, and the first correction coefficient is used to characterize the physical state of the atmosphere;

[0013] Calculating a second reference coefficient and a second correction coefficient according to the second data set; wherein the second reference coefficient is used to characterize daily meteorological conditions, and the second correction coefficient is used to characterize the impact of a specific meteorological event;

[0014] Calculating a third reference coefficient and a third correction coefficient according to the third data set; wherein the third reference coefficient is used to characterize the impact of human activities, and the third correction coefficient is used to characterize the impact of urban planning;

[0015] The environmental anomaly analysis value HJX is calculated by the following calculation formula:

[0016]

[0017] Among them, d1, d2, and d3 are preset weight values, S1 is the first reference coefficient, S2 is the second reference coefficient, S3 is the third reference coefficient, X1 is the first correction coefficient, X2 is the second correction coefficient, and X3 is the third correction coefficient.

[0018] As an improvement of the above solution, the first data set includes PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index;

[0019] The calculating a first reference coefficient and a first correction coefficient according to the first data set includes:

[0020] According to the PM2.5 concentration, NO2 concentration, and O3 concentration, the first reference coefficient S1 is calculated by the following calculation formula:

[0021]

[0022] According to the air pressure value and the atmospheric stability index, the first correction coefficient X1 is calculated by the following calculation formula:

[0023]

[0024] in, , , , , They are PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index at the nth sampling point in the data sequence; , , , , They are PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index at the n-1th sampling point in the data sequence;

[0025] The second data set includes temperature, humidity, wind speed, solar radiation intensity, and precipitation;

[0026] The step of calculating a second reference coefficient and a second correction coefficient according to the second data set includes:

[0027] According to temperature, humidity and wind speed, the second reference coefficient S2 is calculated by the following calculation formula:

[0028]

[0029] According to the solar radiation intensity and precipitation, the second correction coefficient X2 is calculated by the following calculation formula:

[0030]

[0031] in, , , , , are the temperature, humidity, wind speed, solar radiation intensity, and precipitation of the nth sampling point in the data sequence; , , , , are the temperature, humidity, wind speed, solar radiation intensity, and precipitation of the n-1th sampling point in the data sequence;

[0032] The third data set includes traffic flow, industrial emissions, energy consumption, urban population density, and road traffic condition index;

[0033] The calculating a third reference coefficient and a third correction coefficient according to the third data set includes:

[0034] According to traffic flow, industrial emissions, and energy consumption, the third reference coefficient S3 is calculated by the following calculation formula:

[0035]

[0036] According to the urban population density and the road traffic condition index, the third correction coefficient X3 is calculated by the following calculation formula:

[0037]

[0038] in, , , , , They are the traffic flow, industrial emissions, energy consumption, urban population density, and road traffic condition index of the nth sampling point in the data sequence; , , , , They are the traffic flow, industrial emissions, energy consumption, urban population density and road condition index of the n-1th sampling point in the data sequence respectively; a1, a2, a3, b1, b2, b3, c1, c2 and c3 are the preset weight values.

[0039] As an improvement of the above solution, the step of calculating the environmental anomaly magnitude value according to the environmental anomaly analysis value includes:

[0040] According to the environmental anomaly analysis value HJX, the environmental anomaly magnitude value HYJ is calculated by the following calculation formula:

[0041]

[0042] Wherein, Y is the preset environmental abnormality threshold.

[0043] As an improvement of the above solution, the step of determining the abnormality level of the current environment according to the abnormality magnitude value of the environment includes:

[0044] When satisfied When the current environment is determined to be a level 1 abnormality;

[0045] When satisfied When the current environment is determined to be a secondary abnormality;

[0046] When satisfied , it is determined that the current environment is a level three abnormality; wherein, the higher the abnormality level, the greater the degree of environmental abnormality, R1 and R2 are preset abnormality level thresholds, R2>R1.

[0047] As an improvement of the above solution, after determining the abnormality level of the current environment according to the environmental abnormality magnitude value, the method further includes:

[0048] According to the abnormality level, corresponding protective measures are determined and executed; wherein the protective measures include increasing the frequency of collecting the surrounding environment data, issuing early warning information and initiating environmental governance measures for the target area.

[0049] The embodiment of the present invention further provides a data analysis device based on artificial intelligence, comprising:

[0050] An environmental data collection module is used to collect surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment;

[0051] An abnormality analysis value calculation module, used to calculate an environmental abnormality analysis value according to the multi-source data set; wherein the environmental abnormality analysis value is used for environmental abnormality analysis;

[0052] An environmental anomaly analysis module, used to determine that an abnormality exists in the current environment when the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold;

[0053] An abnormal magnitude value calculation module, used for calculating the environmental abnormal magnitude value according to the environmental abnormality analysis value when it is determined that the current environment is abnormal; wherein the environmental abnormal magnitude value is used to characterize the degree of environmental abnormality;

[0054] The environment anomaly level determination module is used to determine the anomaly level of the current environment according to the environment anomaly magnitude value.

[0055] An embodiment of the present invention also provides an artificial intelligence-based data analysis device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the artificial intelligence-based data analysis method as described in any one of the above.

[0056] An embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the artificial intelligence-based data analysis methods described above.

[0057] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, the artificial intelligence-based data analysis method as described in any one of the above is implemented.

[0058] Compared with the prior art, the artificial intelligence-based data analysis method, device, equipment, medium and product disclosed in the present invention have achieved significant improvements in multi-source data fusion, analysis depth, real-time and automation level compared to traditional environmental monitoring methods. By introducing artificial intelligence technology, it does not rely on manual judgment, can dynamically integrate multi-dimensional data, and form a unified multi-source data set with multiple different types of parameters, and quickly generate quantitative indicators and early warning information. Compared with the traditional single-dimensional environmental monitoring method, this multi-dimensional collection method solves the information gap problem caused by data isolation in traditional data collection methods, greatly improves the comprehensiveness of the data, ensures that the monitoring data can better reflect the complexity and diversity of the environment, and avoids the delay and one-sidedness problems in traditional methods. It not only improves the accuracy and efficiency of environmental monitoring, but also provides multi-angle information support for subsequent analysis, enhances the decision-making support capability of environmental management, and helps to respond to environmental problems earlier and more accurately, and reduce their impact on society and ecosystems. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flowchart of a data analysis method based on artificial intelligence provided by an embodiment of the present invention;

[0060] Figure 2 is a structural schematic diagram of an artificial intelligence-based data analysis device provided by an embodiment of the present invention;

[0061] Figure 3 It is a structural schematic diagram of an artificial intelligence-based data analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0064] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0065] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0066] See also Figure 1 , is a flow chart of a data analysis method based on artificial intelligence provided by an embodiment of the present invention. The embodiment of the present invention provides a data analysis method based on artificial intelligence, which is specifically performed by the following steps S11 to S15:

[0067] S11, collecting surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment;

[0068] S12. Calculating an environmental anomaly analysis value according to the multi-source data set; wherein the environmental anomaly analysis value is used for environmental anomaly analysis;

[0069] S13, when the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold, it is determined that the current environment is abnormal;

[0070] S14, when it is determined that the current environment is abnormal, calculating the environmental abnormality magnitude value according to the environmental abnormality analysis value; wherein the environmental abnormality magnitude value is used to characterize the degree of environmental abnormality;

[0071] S15. Determine the abnormality level of the current environment according to the environmental abnormality magnitude value.

[0072] In the embodiment of the present invention, the surrounding environment data is collected by the environment data collection module to generate a multi-source data set. The environment data collection module includes multiple data collection units, each of which is used to collect data of a data type to form a corresponding data set.

[0073] Specifically, the environmental data acquisition module includes a first data acquisition unit, a second data acquisition unit and a third data acquisition unit. The first data acquisition unit is used to collect atmospheric environment data to form a first data set. The second data acquisition unit is used to collect meteorological condition data to form a second data set. The third data acquisition unit is used to collect data on the impact of human activities on the environment to form a third data set. The above multiple data sets form the multi-source data set.

[0074] The first, second, and third data sets cover key indicators in different fields such as air quality, meteorological conditions, and human activities, respectively. This detailed classification ensures that the data can be processed in a targeted manner as needed. For example, the first data set can be used for air quality analysis, the second data set for meteorological conditions analysis, and the third data set to reflect the impact of human factors on the environment. In this way, the data in each field can be processed specifically according to its characteristics, improving the accuracy of the overall analysis. Integrating different types of data into a unified data framework by timestamp allows the system to easily perform multi-dimensional data fusion in the subsequent analysis stage. In this way, the system can simultaneously analyze the interactions between different fields, thereby providing richer information support for the accurate identification and prediction of environmental anomalies.

[0075] Preferably, after collecting the surrounding environment data, the method further includes:

[0076] The environmental data is preprocessed; wherein the preprocessing includes data cleaning, data sorting and dimensionless conversion.

[0077] Specifically, data cleaning operations include using deletion, interpolation or model prediction methods to deal with missing values; deleting duplicates; using deletion, replacement and conversion methods to deal with outliers; removing noise data, etc. Data sorting operations include data integration, data transformation, data reduction, etc. Data integration is to merge environmental data from different data sources into a unified data set; data transformation is to transform the data to make it more suitable for subsequent analysis or modeling; data reduction is to reduce the size and complexity of the data set through methods such as feature selection and dimensionality reduction, and improve processing efficiency and model performance. The dimensionless operation effectively eliminates the dimensional differences between different types of data, so that data from different sources can be compared and integrated under the same analysis framework. Through this processing, the calculation errors caused by inconsistent dimensions are reduced, ensuring the accuracy of the analysis results.

[0078] Furthermore, based on the multi-source data set, an environmental anomaly analysis value HJX is obtained through comprehensive analysis and integrated calculation. The environmental anomaly analysis value HJX is used to perform environmental anomaly analysis. The larger the value of the environmental anomaly analysis value, the more abnormal the environment.

[0079] Specifically, an environmental anomaly threshold value Y is pre-set as a critical value for determining whether the environment is normal or abnormal, and the size relationship between the environmental anomaly analysis value HJX and the environmental anomaly threshold value Y is compared. When the environmental anomaly analysis value HJX is greater than or equal to the preset environmental anomaly threshold value Y, that is, HJX ≥ Y, it is determined that the current environment is abnormal. When it is determined that the current environment is abnormal, the environmental anomaly magnitude value HYJ is calculated according to the environmental anomaly analysis value HJX; the environmental anomaly magnitude value HYJ is used to characterize the degree of environmental anomaly. The larger the value of the environmental anomaly magnitude value HYJ, the more obvious the degree of environmental anomaly. Furthermore, according to the environmental anomaly magnitude value HYJ, the abnormality level of the current environment is determined. The higher the abnormality level, the more obvious the degree of environmental anomaly.

[0080] By adopting the technical means of the embodiments of the present invention, compared with traditional environmental monitoring methods, the embodiments of the present invention have achieved significant improvements in multi-source data fusion, analysis depth, real-time and automation level. By introducing artificial intelligence technology, the method can dynamically integrate multi-dimensional data, and form a unified multi-source data set of multiple different types of parameters, and quickly generate quantitative indicators and early warning information. Compared with the traditional single-dimensional environmental monitoring method, this multi-dimensional collection method solves the information gap problem caused by data isolation in traditional data collection methods, greatly improves the comprehensiveness of the data, ensures that the monitoring data can better reflect the complexity and diversity of the environment, and avoids the delay and one-sidedness problems in traditional methods. It not only improves the accuracy and efficiency of environmental monitoring, but also provides multi-angle information support for subsequent analysis, enhances the decision-making support capability of environmental management, and helps to respond to environmental problems earlier and more accurately, and reduce their impact on society and ecosystems.

[0081] As a preferred implementation, the embodiment of the present invention is further implemented on the basis of the above embodiment, wherein the first data set includes PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value and atmospheric stability index. These parameters mainly reflect the chemical and physical state of the atmosphere, so the first data set can be regarded as an atmospheric environment data set, through which the air quality and atmospheric state can be evaluated.

[0082] Among them, PM2.5 concentration is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0083] The NO2 concentration is recorded according to the sampling point timestamp as , , ,..., ;

[0084] The O3 concentration is recorded according to the sampling point timestamp as , , ,..., ;

[0085] The air pressure values ​​are recorded according to the sampling point timestamps as , , ,..., ;

[0086] The atmospheric stability index is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0087] The second data set includes temperature, humidity, wind speed, solar radiation intensity and precipitation. These parameters mainly describe the characteristics of climate and weather, so the second data set can be regarded as a meteorological condition data set. These data come from meteorological observation stations, environmental monitoring stations and other institutions, and are used to study climate change, provide weather forecasts, etc.

[0088] Among them, the temperature is recorded as , , ,..., ;

[0089] Humidity is recorded as , , ,..., ;

[0090] The wind speed is recorded as , , ,..., ;

[0091] The solar radiation intensity is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0092] The precipitation is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0093] The third data set includes collected traffic flow, industrial emissions, energy consumption, urban population density and road traffic condition index. These parameters are mainly related to human activities and environmental impacts, so the third data set can be regarded as a data set of human activities on the environment. These data may come from traffic management departments, industrial departments, energy departments, urban planning departments and other institutions, and are used to study the impact of human activities on the environment and formulate environmental protection policies.

[0094] Among them, the traffic flow is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0095] Industrial emissions are recorded according to the sampling point timestamps as , , ,..., ;

[0096] The energy consumption is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0097] The urban population density is recorded as follows according to the sampling point timestamp: , , ,..., ;

[0098] The road condition index is recorded as follows according to the sampling point timestamp: , , ,..., .

[0099] The PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, atmospheric stability index, collection temperature, humidity, wind speed, solar radiation intensity, precipitation, traffic flow, industrial emissions, energy consumption, urban population density and road traffic condition index constitute a multi-source data set.

[0100] By using the technical means of the embodiments of the present invention, all parameters are recorded and sorted according to timestamps during the sorting process of each data set. The advantage of this is that it can provide data support in the time dimension for subsequent dynamic analysis, so that environmental changes and trends can be accurately tracked and predicted. Through time serialization processing, the system can reflect the laws of environmental changes over time, providing a more timely reference for timely warning and decision-making.

[0101] As a preferred implementation, the embodiment of the present invention is further implemented on the basis of the above embodiment, step S12, that is, calculating the environmental anomaly analysis value according to the multi-source data set, includes steps S121 to S124:

[0102] S121. Calculate a first reference coefficient and a first correction coefficient according to the first data set; wherein the first reference coefficient is used to characterize air quality conditions, and the first correction coefficient is used to characterize atmospheric physical conditions;

[0103] S122. Calculate a second reference coefficient and a second correction coefficient according to the second data set; wherein the second reference coefficient is used to characterize daily meteorological conditions, and the second correction coefficient is used to characterize the impact of a specific meteorological event;

[0104] S123. Calculate a third reference coefficient and a third correction coefficient according to the third data set; wherein the third reference coefficient is used to characterize the impact of human activities, and the third correction coefficient is used to characterize the impact of urban planning;

[0105] S124. Calculate the environmental anomaly analysis value HJX by the following calculation formula:

[0106]

[0107] Among them, d1, d2, and d3 are preset weight values, S1 is the first reference coefficient, S2 is the second reference coefficient, S3 is the third reference coefficient, X1 is the first correction coefficient, X2 is the second correction coefficient, and X3 is the third correction coefficient.

[0108] In an embodiment of the present invention, the data in the first data set are divided into two categories, one is data reflecting air quality conditions, and the other is data reflecting the physical state of the atmosphere. Then, based on these two categories of data in the first data set, a first reference coefficient S1 for characterizing the air quality conditions and a first correction coefficient X1 for characterizing the physical state of the atmosphere are calculated respectively.

[0109] Similarly, the data in the second data set are divided into two categories, one is data reflecting daily meteorological conditions, and the other is data reflecting the impact of specific meteorological events. Then, based on these two categories of data in the second data set, a second reference coefficient S2 for characterizing daily meteorological conditions and a second correction coefficient X2 for characterizing the impact of specific meteorological events are calculated respectively.

[0110] Similarly, the data in the third data set are divided into two categories, one is data reflecting the impact of human activities, and the other is data reflecting the impact of urban planning. Then, based on these two types of data in the third data set, a third reference coefficient S3 for characterizing the impact of human activities and a third correction coefficient X3 for characterizing the impact of urban planning are calculated respectively.

[0111] Furthermore, the logarithmic function and weighted average method are used to calculate the environmental anomaly analysis value HJX. HJX is a comprehensive calculation result based on the reference coefficient S and the correction coefficient X. It can reflect the comprehensive impact of environmental factors, meteorological conditions and human activities on environmental quality, and is used to evaluate environmental anomalies.

[0112] Specifically, HJX calculates the logarithm of S1×X1, S2×X2, S3×X3 and multiplies them by the corresponding weight values ​​d1, d2, d3 to obtain the final environmental anomaly analysis value. This value can reflect the overall changes in environmental quality and is used to determine whether there are environmental anomalies or potential environmental risks.

[0113] It should be noted that the values ​​of weights d1, d2, and d3 are adjusted and set by the user and are not specifically limited here.

[0114] Furthermore, by comparing the environmental anomaly analysis value HJX with the preset environmental anomaly threshold Y, it is possible to accurately determine whether the current environment is abnormal. If the environmental anomaly analysis value HJX is less than Y, it indicates that there is no abnormality in the environment; if HJX is greater than or equal to Y, it indicates that there is an abnormality. This judgment method has high sensitivity and accuracy, can quickly identify the occurrence of environmental anomalies, and provide a basis for subsequent treatment measures in a timely manner. Compared with the traditional fixed threshold method, this comparison mechanism based on dynamic calculation can more finely identify subtle environmental changes, improving the timeliness and effectiveness of early warning.

[0115] By adopting the technical means of the embodiments of the present invention, multi-dimensional data are integrated into a comprehensive indicator using complex algorithms to achieve quantitative characterization of environmental conditions. The calculation of the environmental anomaly analysis value HJX not only takes into account the changes in various types of data, but also integrates the interactions between multiple factors. The advantage of this process is that a large amount of complex data is simplified into an easy-to-understand and scientifically credible indicator, providing a convenient tool for quickly judging and analyzing environmental anomalies. By combining multi-dimensional data for calculation, the ability to identify environmental anomalies is improved and the risk of missed reports and false reports is reduced.

[0116] Moreover, based on the evaluation results of the environmental anomaly analysis value HJX, it is possible to effectively evaluate whether the environment is abnormal, provide a scientific basis for the decision-making of relevant departments, and help formulate more reasonable and effective environmental protection policies and measures to deal with the impact of different factors on air quality. By regularly monitoring and analyzing the environmental anomaly analysis value HJX, it is possible to timely discover the changing trends and potential problems of environmental quality, which is helpful to promote the in-depth development of environmental protection work, improve the efficiency and effectiveness of environmental governance, and promote the continuous improvement of environmental quality.

[0117] Preferably, step S121, that is, calculating the first reference coefficient and the first correction coefficient according to the first data set, includes:

[0118] According to the PM2.5 concentration, NO2 concentration, and O3 concentration, the first reference coefficient S1 is calculated by the following calculation formula:

[0119]

[0120] According to the air pressure value and the atmospheric stability index, the first correction coefficient X1 is calculated by the following calculation formula:

[0121]

[0122] in, , , , , They are PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index at the nth sampling point in the data sequence; , , , , They are respectively the PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index of the n-1th sampling point in the data sequence.

[0123] Specifically, PM2.5 concentration, NO2 concentration, and O3 concentration are common air quality indicators that can reflect the concentration level of pollutants in the atmosphere and are important parameters for assessing air quality. Air pressure and atmospheric stability index reflect the physical state of the atmosphere, and these parameters have an important impact on the diffusion and deposition of pollutants.

[0124] The first reference coefficient S1 is obtained by calculating the relative changes in PM2.5, NO2, and O3 concentrations (using a logarithmic function) and multiplying them by the corresponding weight values, which is a comprehensive indicator reflecting changes in air quality. The first correction coefficient X1 takes into account the impact of air pressure and atmospheric stability index on air quality changes. By calculating their relative relationship (using a ratio method) and multiplying them by the weight value, a comprehensive indicator reflecting changes in the physical state of the atmosphere is obtained.

[0125] The environmental anomaly analysis value HJX combines the two coefficients S1 and X1 and is obtained by calculating their product (or logarithmic product and weighting). It can comprehensively consider the impact of changes in air quality and changes in the physical state of the atmosphere on environmental quality, thereby more comprehensively evaluating environmental anomalies.

[0126] Preferably, step S122, that is, calculating the second reference coefficient and the second correction coefficient according to the second data set, includes:

[0127] According to temperature, humidity and wind speed, the second reference coefficient S2 is calculated by the following calculation formula:

[0128]

[0129] According to the solar radiation intensity and precipitation, the second correction coefficient X2 is calculated by the following calculation formula:

[0130]

[0131] in, , , , , are the temperature, humidity, wind speed, solar radiation intensity, and precipitation of the nth sampling point in the data sequence; , , , , They are the temperature, humidity, wind speed, solar radiation intensity and precipitation of the n-1th sampling point in the data sequence respectively.

[0132] Specifically, temperature, humidity, and wind speed are common meteorological conditions, which are important factors affecting the diffusion, chemical reaction rate, and deposition process of atmospheric pollutants. For example, high temperature can accelerate certain chemical reactions, while humidity may affect the solubility and deposition efficiency of pollutants, and wind speed directly affects the diffusion rate and range of pollutants.

[0133] The second reference coefficient S2 is obtained by calculating the relative changes of these meteorological conditions (such as using a logarithmic function), which is a comprehensive indicator reflecting the potential impact of meteorological conditions on air quality. This indicator can capture the corresponding changes in air quality that may occur when meteorological conditions change.

[0134] Solar radiation intensity and precipitation are key factors affecting photochemical reactions, pollutant deposition, and atmospheric stability in the atmosphere. Solar radiation can drive photochemical reactions and produce secondary pollutants, while precipitation can directly remove pollutants from the atmosphere.

[0135] The second correction factor X2 is obtained by calculating the relative relationship between solar radiation intensity and precipitation or their direct impact on air quality changes. It is a correction factor X2 that reflects the characteristics of air quality changes under specific meteorological conditions. This coefficient can reveal the specific change pattern that air quality may present under specific weather conditions.

[0136] The calculation of the environmental anomaly analysis value HJX combines the two coefficients S2 and X2. By calculating their product (or logarithmic product and weighting), it comprehensively considers the impact of meteorological conditions and specific weather events on air quality, and can more comprehensively evaluate the overall status of environmental quality.

[0137] Preferably, step S123, that is, calculating a third reference coefficient and a third correction coefficient according to the third data set, includes:

[0138] According to traffic flow, industrial emissions, and energy consumption, the third reference coefficient S3 is calculated by the following calculation formula:

[0139]

[0140] According to the urban population density and the road traffic condition index, the third correction coefficient X3 is calculated by the following calculation formula:

[0141]

[0142] in, , , , , They are the traffic flow, industrial emissions, energy consumption, urban population density, and road traffic condition index of the nth sampling point in the data sequence; , , , , are the traffic flow, industrial emissions, energy consumption, urban population density and road condition index of the n-1th sampling point in the data sequence respectively, and a1, a2, a3, b1, b2, b3, c1, c2 and c3 are the preset weight values.

[0143] Specifically, traffic flow is an important indicator for measuring the level of urban traffic activity and one of the main factors affecting urban air quality. The exhaust gas emitted by traffic contains a large amount of pollutants, such as particulate matter, nitrogen oxides, etc., which have a direct impact on air quality. Industrial emissions are one of the main sources of environmental pollution, including waste gas, wastewater, solid waste, etc. Among them, pollutants in industrial waste gas have a particularly significant impact on air quality. Energy consumption is closely related to environmental pollution. Emissions generated during energy consumption, such as sulfur dioxide and nitrogen oxides generated by coal burning, will have a negative impact on air quality.

[0144] By comprehensively considering traffic flow, industrial emissions and energy consumption, the third reference coefficient S3 reflecting the impact of human activities on air quality can be calculated.

[0145] Urban population density is an important indicator to measure the density of urban population distribution. In areas with high population density, traffic activities are frequent and industrial emissions are relatively concentrated, which has a greater impact on air quality. The road traffic condition index reflects the condition of urban transportation infrastructure and the efficiency of traffic operation. Roads with good traffic conditions can reduce traffic congestion and thus reduce traffic emissions; otherwise, it may aggravate air pollution.

[0146] By comprehensively considering the urban population density and road traffic condition index, the third correction coefficient X3 can be calculated to reflect the impact of urban planning and traffic conditions on air quality.

[0147] The environmental anomaly analysis value HJX combines the two coefficients S3 and X3. By calculating their product (or weighted processing according to specific circumstances), we can obtain the environmental anomaly analysis value HJX that reflects the overall changes in environmental quality. It integrates the impact of human activities, urban planning and traffic conditions on air quality, and can more comprehensively evaluate the overall status of environmental quality.

[0148] In the embodiment of the present invention, by comparing and calculating the current value in the data sequence with the value at the previous moment, the change trend of the data can be effectively captured. This time-series calculation enhances the dynamic response capability of the system, can quickly respond to changes in environmental parameters, and adjust abnormal analysis results in a timely manner. Compared with traditional static analysis methods, this can provide more timely data feedback.

[0149] By combining the reference coefficient and the correction coefficient, the environmental anomaly analysis value HJX can be calculated more accurately. The reference coefficient reflects the rate of change of various environmental data, while the correction coefficient corrects the relationship between these changing factors and other environmental conditions. Combining these two types of coefficients can more accurately reflect small changes in the environment, thereby improving the ability to detect potential environmental anomalies. This is crucial to improving the accuracy of the environmental early warning system.

[0150] The calculation formulas of reference coefficients S1, S2, and S3 all use logarithmic functions and weighted average methods. Logarithmic functions can reflect the percentage or relative change of data changes, which are often used in environmental science to evaluate changes in pollutant concentrations, changes in meteorological conditions, etc. Weighted average takes into account the relative importance of different factors on the environment. By adjusting the weight values ​​a1, a2, a3, b1, b2, b3, c1, c2, and c3, the degree of impact of different data points on the overall environment can be reflected.

[0151] Specifically, S1, S2, and S3 calculated the relative changes in environmental factors such as PM2.5 concentration, NO2 concentration, and O3 concentration, meteorological conditions such as temperature, humidity, and wind speed, and human activity factors such as traffic flow and industrial emissions, and obtained the final reference coefficients through weighted average. These reference coefficients can reflect the comprehensive impact of environmental factors, meteorological conditions, and human activities on changes in environmental quality.

[0152] The calculation formula of the correction coefficients X1, X2, and X3 uses the ratio and weighted average method. The ratio method can reflect the relative relationship between two data points, which is often used in environmental science to evaluate the interaction or impact between different environmental factors. The weighted average also takes into account the relative importance of different factors on the overall environmental impact.

[0153] Specifically, X1, X2, and X3 respectively calculated the relative relationship between environmental factors such as air pressure and atmospheric stability index and urban meteorological conditions such as solar radiation intensity and precipitation, as well as human activity factors such as urban population density and road conditions, and obtained the final correction coefficient through weighted average. These correction coefficients can reflect the interaction or influence between different environmental factors and correct the reference coefficients to improve the accuracy of environmental anomaly analysis.

[0154] In traditional environmental monitoring, a certain type of data is often emphasized, while the mutual influence between different environmental factors is ignored. By adopting the technical means of the embodiment of the present invention, by comprehensively considering multiple factors affecting air quality, the actual changes in environmental quality can be more accurately reflected, which helps to reduce the errors caused by single factor evaluation and improve the accuracy of analysis. In combination with multiple reference coefficients and multiple correction coefficients, the multi-faceted influence of air quality indicators, atmospheric physical state parameters, meteorological conditions, weather events, human activities, urban planning and traffic conditions on air quality can be fully considered, and the fusion between different data is realized, which enhances the adaptability of the system to complex environmental changes. For example, comprehensive analysis of multi-dimensional data such as traffic flow, meteorological data and pollutant concentration can more accurately reveal the potential correlation between them, thereby improving the ability of anomaly detection. Based on the calculation results of the environmental anomaly analysis value HJX, the system can optimize each type of data through weight adjustment and provide a more sensitive early warning signal. This calculation method not only improves the analysis accuracy, but also greatly optimizes the response speed and accuracy of the early warning system. Compared with the traditional fixed threshold method, this method based on dynamic calculation of data changes can respond to changes in environmental status in real time, issue early warnings in time, and help decision makers make more accurate judgments and countermeasures.

[0155] As a preferred implementation, the embodiment of the present invention is further implemented on the basis of the above embodiment, step S14, that is, calculating the environmental anomaly magnitude value according to the environmental anomaly analysis value, includes:

[0156] According to the environmental anomaly analysis value HJX, the environmental anomaly magnitude value HYJ is calculated by the following calculation formula:

[0157]

[0158] Wherein, Y is the preset environmental abnormality threshold.

[0159] In the embodiment of the present invention, the environmental anomaly level is further determined by calculating the environmental anomaly magnitude coefficient HYJ. The calculation formula of HYJ is based on the ratio of HJX to the threshold value Y, which quantifies the degree of anomaly and ensures that the level division of environmental anomalies is more scientific and reasonable. By setting different anomaly magnitudes, more detailed anomaly information can be provided to decision makers, making it easier to take corresponding countermeasures. This refined level division system is more accurate than the traditional simple "abnormal / no abnormal" judgment method and can provide more in-depth abnormality analysis.

[0160] As a preferred implementation, the embodiment of the present invention is further implemented on the basis of the above embodiment, wherein the determining the abnormality level of the current environment according to the environmental abnormality magnitude value includes:

[0161] When satisfied When the current environment is determined to be a level 1 abnormality;

[0162] When satisfied When the current environment is determined to be a secondary abnormality;

[0163] When satisfied , it is determined that the current environment is a level three abnormality; wherein, the higher the abnormality level, the greater the degree of environmental abnormality, R1 and R2 are preset abnormality level thresholds, R2>R1.

[0164] Preferably, R2=125%×R1.

[0165] In an embodiment of the present invention, a grading system for the magnitude of environmental anomalies provides a hierarchical basis for emergency response. When HYJ≤R1, it indicates a level 1 anomaly, reminding the user that the environment is in a relatively mild abnormal state; and when HYJ>R1×125%, it indicates a level 3 anomaly, reminding the user that the environmental anomaly is more serious. This hierarchical response mechanism is more flexible than the traditional binary judgment of whether there is an abnormality or not, and can take different levels of response measures according to the severity of the anomaly. This grading mechanism can greatly improve the accuracy and timeliness of emergency response, and help various environmental management systems to better formulate emergency plans and processing procedures.

[0166] By calculating and classifying the environmental anomaly magnitude coefficient HYJ, the system can be provided with continuous dynamic feedback to ensure that the environmental monitoring system can track and adjust the analysis results in real time. Especially in the case of rapid environmental changes, the system's high responsiveness can be ensured to quickly identify abnormal changes. This dynamic feedback mechanism not only increases the timeliness of the analysis, but also improves the accuracy of the monitoring system and its sensitivity to abnormal changes.

[0167] The setting method of comparing the environmental anomaly analysis value HJX with the preset environmental anomaly threshold Y can flexibly adjust the threshold Y according to the needs of different regions and different environmental conditions. This flexibility enables the system to optimize analysis and judgment in different scenarios, thereby improving the applicability of environmental anomaly detection. Compared with traditional methods, AI-based data analysis methods not only rely on threshold settings, but can also adapt to different changes in the environment through dynamic adjustments, further improving the accuracy of the system.

[0168] Based on the comparison results of the two-level data analysis, the system can issue warning signals of different intensities according to different abnormal levels. Through hierarchical abnormality analysis and precise abnormality classification, more detailed warning output can be achieved, helping decision makers to judge the severity of environmental conditions more quickly and make corresponding emergency responses. This detailed abnormality warning mechanism is particularly important in complex environments and helps improve the efficiency and accuracy of responding to environmental abnormalities.

[0169] As a preferred implementation, the embodiment of the present invention is further implemented on the basis of the above embodiment. In step S15, that is, after determining the abnormal level of the current environment according to the abnormal level value of the environment, the method further includes step S16:

[0170] S16. Determine and execute corresponding protective measures according to the abnormality level; wherein the protective measures include increasing the frequency of collecting the surrounding environment data, issuing early warning information and initiating environmental governance measures for the target area.

[0171] Preferably, when the abnormality level is a first-level abnormality, the protective measures include: increasing the frequency of collecting the surrounding environment data to a first sampling frequency, issuing a first warning message, and initiating a first environmental governance measure;

[0172] When the abnormality level is a level 2 abnormality, the protective measures include: increasing the frequency of collecting the surrounding environment data to a second sampling frequency, issuing a second warning message, and initiating a second environmental governance measure;

[0173] When the abnormality level is level three, the protective measures include: increasing the frequency of collecting the surrounding environment data to a third sampling frequency, issuing a third warning information, and initiating a third environmental governance measure;

[0174] The third sampling frequency is greater than the second sampling frequency, and the second sampling frequency is greater than the first sampling frequency;

[0175] The first environmental governance measure includes: increasing the number of road sweeping times and controlling traffic flow in the target area;

[0176] The second environmental governance measures include: restricting industrial emissions in the target area, controlling traffic flow and activating air purification systems;

[0177] The third environmental governance measure includes: temporarily closing some high-polluting enterprises in the target area, restricting industrial emissions and traffic flow, and starting an air purification system.

[0178] Specifically, when an environmental anomaly is found to be a level one anomaly, it is necessary to increase the sampling frequency of relevant monitoring indicators, especially those closely related to air quality and meteorological conditions, and issue a preliminary warning to remind relevant management departments and the public to pay attention to environmental changes and the potential impact of air quality on health. In local areas, environmental governance measures should be initiated, including strengthening road cleaning and controlling traffic flow.

[0179] When an environmental anomaly is found to be a Level 2 anomaly, the frequency of collecting environmental monitoring data will be increased, especially focusing on data related to pollution diffusion, such as atmospheric stability and wind speed, so as to more accurately predict the trend of pollution diffusion and initiate more stringent environmental protection measures, including limiting factory emissions, limiting traffic flow, and activating air purification systems, and issuing stricter health recommendations, including reducing outdoor activities and strengthening protective measures for high-risk groups;

[0180] When the third-level environmental anomaly is found, a comprehensive emergency response mechanism will be activated, the coordinated work of environmental protection departments, meteorological departments, and public security departments will be strengthened, and strict emission control measures will be implemented, including the temporary closure of some high-pollution enterprises, restrictions on industrial emissions, and strict restrictions on traffic flow. Health warnings and protective measures for the society will be strengthened, large-scale air purification and cleaning operations will be implemented, environmental monitoring data will be tracked in real time, and emergency plans will be adjusted dynamically to ensure that the effects are fully verified.

[0181] See also Figure 2 , is a schematic diagram of the structure of an artificial intelligence-based data analysis device provided in an embodiment of the present invention. The embodiment of the present invention further provides an artificial intelligence-based data analysis device 10, including:

[0182] The environmental data collection module 11 is used to collect surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment;

[0183] The abnormal analysis value calculation module 12 is used to calculate the environmental abnormality analysis value according to the multi-source data set; wherein the environmental abnormality analysis value is used for environmental abnormality analysis;

[0184] The environment anomaly analysis module 13 is used to determine that the current environment is abnormal when the environment anomaly analysis value is greater than or equal to a preset environment anomaly threshold;

[0185] The abnormal magnitude value calculation module 14 is used to calculate the environmental abnormal magnitude value according to the environmental abnormality analysis value when it is determined that the current environment is abnormal; wherein the environmental abnormal magnitude value is used to characterize the degree of environmental abnormality;

[0186] The environment abnormality level determination module 15 is used to determine the abnormality level of the current environment according to the environment abnormality magnitude value.

[0187] Preferably, the device 10 further comprises:

[0188] The protective measures execution module is used to determine and execute corresponding protective measures according to the abnormality level; wherein the protective measures include increasing the frequency of collecting the surrounding environment data, issuing early warning information and initiating environmental governance measures for the target area.

[0189] It should be noted that the artificial intelligence-based data analysis device provided in an embodiment of the present invention is used to execute all the process steps of an artificial intelligence-based data analysis method in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be elaborated on herein.

[0190] See also Figure 3 , is a structural diagram of an artificial intelligence-based data analysis device provided in an embodiment of the present invention. An embodiment of the present invention also provides an artificial intelligence-based data analysis device 20, including a processor 21, a memory 22, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the artificial intelligence-based data analysis method as described in any one of the above embodiments.

[0191] An embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the artificial intelligence-based data analysis method as described in any one of the above embodiments.

[0192] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, the artificial intelligence-based data analysis method as described in any one of the above embodiments is implemented.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0194] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A data analysis method based on artificial intelligence, characterized in that: include: Collecting surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment; Calculating an environmental anomaly analysis value according to the multi-source data set; wherein the environmental anomaly analysis value is used for environmental anomaly analysis; When the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold, it is determined that the current environment is abnormal; When it is determined that the current environment is abnormal, the environmental abnormality magnitude value is calculated according to the environmental abnormality analysis value; wherein the environmental abnormality magnitude value is used to characterize the degree of environmental abnormality; Determining the abnormality level of the current environment according to the environmental abnormality magnitude value; The step of calculating the environmental anomaly analysis value according to the multi-source data set includes: Calculate a first reference coefficient and a first correction coefficient according to the first data set; wherein the first reference coefficient is used to characterize the air quality condition, and the first correction coefficient is used to characterize the physical state of the atmosphere; Calculating a second reference coefficient and a second correction coefficient according to the second data set; wherein the second reference coefficient is used to characterize daily meteorological conditions, and the second correction coefficient is used to characterize the impact of a specific meteorological event; Calculating a third reference coefficient and a third correction coefficient according to the third data set; wherein the third reference coefficient is used to characterize the impact of human activities, and the third correction coefficient is used to characterize the impact of urban planning; The environmental anomaly analysis value HJX is calculated by the following calculation formula: Among them, d1, d2, and d3 are preset weight values, S1 is the first reference coefficient, S2 is the second reference coefficient, S3 is the third reference coefficient, X1 is the first correction coefficient, X2 is the second correction coefficient, and X3 is the third correction coefficient.

2. The artificial intelligence-based data analysis method according to claim 1, characterized in that: The first data set includes PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index; The calculating a first reference coefficient and a first correction coefficient according to the first data set includes: According to the PM2.5 concentration, NO2 concentration, and O3 concentration, the first reference coefficient S1 is calculated by the following calculation formula: According to the air pressure value and the atmospheric stability index, the first correction coefficient X1 is calculated by the following calculation formula: in, , , , , They are PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index at the nth sampling point in the data sequence; , , , , They are PM2.5 concentration, NO2 concentration, O3 concentration, air pressure value, and atmospheric stability index at the n-1th sampling point in the data sequence; The second data set includes temperature, humidity, wind speed, solar radiation intensity, and precipitation; The step of calculating a second reference coefficient and a second correction coefficient according to the second data set includes: According to temperature, humidity and wind speed, the second reference coefficient S2 is calculated by the following calculation formula: According to the solar radiation intensity and precipitation, the second correction coefficient X2 is calculated by the following calculation formula: in, , , , , are the temperature, humidity, wind speed, solar radiation intensity, and precipitation of the nth sampling point in the data sequence; , , , , are the temperature, humidity, wind speed, solar radiation intensity, and precipitation of the n-1th sampling point in the data sequence; The third data set includes traffic flow, industrial emissions, energy consumption, urban population density, and road traffic condition index; The calculating a third reference coefficient and a third correction coefficient according to the third data set includes: According to traffic flow, industrial emissions, and energy consumption, the third reference coefficient S3 is calculated by the following calculation formula: According to the urban population density and the road traffic condition index, the third correction coefficient X3 is calculated by the following calculation formula: in, , , , , They are the traffic flow, industrial emissions, energy consumption, urban population density, and road traffic condition index of the nth sampling point in the data sequence; , , , , They are the traffic flow, industrial emissions, energy consumption, urban population density and road condition index of the n-1th sampling point in the data sequence respectively; a1, a2, a3, b1, b2, b3, c1, c2 and c3 are the preset weight values.

3. The artificial intelligence-based data analysis method according to claim 1, characterized in that: The calculating of the environmental anomaly magnitude value according to the environmental anomaly analysis value comprises: According to the environmental anomaly analysis value HJX, the environmental anomaly magnitude value HYJ is calculated by the following calculation formula: Wherein, Y is the preset environmental abnormality threshold.

4. The artificial intelligence-based data analysis method according to claim 3, characterized in that: The determining the abnormality level of the current environment according to the environmental abnormality magnitude value includes: When satisfied When the current environment is determined to be a level 1 abnormality; When satisfied When the current environment is determined to be a secondary abnormality; When satisfied , it is determined that the current environment is a level three abnormality; wherein, the higher the abnormality level, the greater the degree of environmental abnormality, R1 and R2 are preset abnormality level thresholds, R2>R1.

5. The artificial intelligence-based data analysis method according to any one of claims 1 to 4, characterized in that: After determining the abnormality level of the current environment according to the environmental abnormality magnitude value, the method further includes: According to the abnormality level, corresponding protective measures are determined and executed; wherein the protective measures include increasing the frequency of collecting the surrounding environment data, issuing early warning information and initiating environmental governance measures for the target area.

6. A data analysis device based on artificial intelligence, characterized in that: include: An environmental data collection module is used to collect surrounding environment data to form a multi-source data set; wherein the multi-source data set includes a first data set, a second data set and a third data set, the first data set includes atmospheric environment data, the second data set includes meteorological condition data, and the third data set includes data on the impact of human activities on the environment; An abnormality analysis value calculation module, used to calculate an environmental abnormality analysis value according to the multi-source data set; wherein the environmental abnormality analysis value is used for environmental abnormality analysis; An environmental anomaly analysis module, used to determine that an abnormality exists in the current environment when the environmental anomaly analysis value is greater than or equal to a preset environmental anomaly threshold; An abnormal magnitude value calculation module, used for calculating the environmental abnormal magnitude value according to the environmental abnormality analysis value when it is determined that the current environment is abnormal; wherein the environmental abnormal magnitude value is used to characterize the degree of environmental abnormality; An environment anomaly level determination module, used to determine the anomaly level of the current environment according to the environment anomaly magnitude value; The abnormal analysis numerical calculation module is specifically used for: Calculate a first reference coefficient and a first correction coefficient according to the first data set; wherein the first reference coefficient is used to characterize the air quality condition, and the first correction coefficient is used to characterize the physical state of the atmosphere; Calculating a second reference coefficient and a second correction coefficient according to the second data set; wherein the second reference coefficient is used to characterize daily meteorological conditions, and the second correction coefficient is used to characterize the impact of a specific meteorological event; Calculating a third reference coefficient and a third correction coefficient according to the third data set; wherein the third reference coefficient is used to characterize the impact of human activities, and the third correction coefficient is used to characterize the impact of urban planning; The environmental anomaly analysis value HJX is calculated by the following calculation formula: Among them, d1, d2, and d3 are preset weight values, S1 is the first reference coefficient, S2 is the second reference coefficient, S3 is the third reference coefficient, X1 is the first correction coefficient, X2 is the second correction coefficient, and X3 is the third correction coefficient.

7. A data analysis device based on artificial intelligence, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the artificial intelligence-based data analysis method as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the artificial intelligence-based data analysis method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product comprises a computer program or computer instructions, and when the computer program or the computer instructions are executed by a processor, the artificial intelligence-based data analysis method as described in any one of claims 1 to 5 is implemented.

Images