Smart city environment supervision system

Abstract

The invention discloses a smart city environment supervision system, and particularly relates to the technical field of environment supervision. A data conversion delay coefficient, a data conversion loss coefficient, a data noise interference coefficient and a data precision loss coefficient are respectively obtained and calculated through a conversion delay response module, an information loss response module, a noise interference response module and a precision loss response module, and conversion delay and information loss in data format conversion are timely found; the method solves the problems of noise interference and precision loss, constructs a data conversion hidden danger evaluation model, generates a data conversion hidden danger evaluation index, evaluates format conversion hidden dangers in a data format conversion process, and guarantees that the system can always maintain the accuracy and timeliness of data in an environment crisis emergency response process. Decision errors and response delay caused by inaccurate or delayed data are avoided, early warning can be automatically given out and corresponding decisions can be made based on a hidden danger assessment result, and whether a system needs to adjust a data processing flow or carry out emergency repair or not is indicated.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental supervision, and more specifically, to a smart city environmental supervision system. Background Art

[0002] With the acceleration of the urbanization process, environmental crises (such as large-scale air pollution, flood disasters, etc.) have become major issues affecting the sustainable development of cities and the quality of life of residents. To effectively address these environmental crises, smart city environmental supervision systems have emerged. Such systems integrate real-time data from different sources (such as air quality monitoring, weather forecasting, traffic flow, social media information, etc.), and use advanced data analysis and artificial intelligence technologies to provide real-time monitoring, early warning, and decision-making support for environmental changes, aiming to achieve cross-departmental collaboration, timely response, and precise governance. However, smart city environmental supervision systems usually involve multiple heterogeneous data sources, including environmental sensors, meteorological satellites, traffic monitoring devices, etc. These data sources use different formats and protocols, and there are problems such as inconsistent data structures and different collection frequencies. The process of data format conversion and integration is complex. If not handled properly, it may lead to data loss or misreading, affecting the accuracy of information. Especially in disaster response, real-time and accuracy are particularly crucial. Therefore, potential hazards (such as conversion delays, data loss, noise interference, etc.) during the data format conversion process, if not detected in time, may cause decision-makers to respond based on incorrect or incomplete data, delay emergency actions, and even miss key intervention opportunities. This leads to obstacles in cross-departmental collaboration and information sharing, resulting in waste of resources or insufficient crisis response in some areas, thus exacerbating the consequences of disasters. Especially in the face of environmental crises, rapid response and efficient collaboration are the keys to reducing disaster losses. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a smart city environmental supervision system to solve the problems raised in the above background art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A smart city environmental supervision system includes a conversion delay response module, an information loss response module, a noise interference response module, an accuracy loss response module, a comprehensive evaluation module, and a warning decision module;

[0006] The conversion delay response module is used to obtain the data conversion delay information during the data format conversion process, and obtain the data conversion delay coefficient according to the data conversion delay information;

[0007] The information loss response module is used to obtain the data conversion loss information during the data format conversion process, and obtain the data conversion loss coefficient according to the data conversion loss information;

[0008] A noise interference response module, which is used to obtain the data noise interference information in the data format conversion process and obtain the data noise interference coefficient according to the data noise interference information;

[0009] An accuracy loss response module, which is used to obtain the data accuracy loss information in the data format conversion process and obtain the data accuracy loss coefficient according to the accuracy loss information;

[0010] A comprehensive evaluation module, which is used to construct a data conversion hidden danger evaluation model according to the data conversion delay coefficient, the data conversion loss coefficient, the data noise interference coefficient, and the data accuracy loss coefficient, generate a data conversion hidden danger evaluation index, and evaluate the format conversion hidden danger in the data format conversion process;

[0011] An early warning decision-making module, which is used to make an early warning decision on the conversion format hidden danger of the current data format conversion according to the evaluation result of the format conversion hidden danger.

[0012] In a preferred embodiment, by obtaining the data conversion delay information in the data format conversion process, analyzing the data conversion delay situation in the data format conversion process, and obtaining the data conversion delay coefficient, the data conversion delay degree in the data format conversion process is measured;

[0013] The acquisition logic of the data conversion delay coefficient is as follows:

[0014] The timestamp mechanism is adopted to record the time points of each stage of the data format conversion, including the data format conversion start timestamp Tconverts and the data format conversion end timestamp Ttransmite, and the data conversion delay Ty is calculated. The expression is as follows where Tsagnao is the expected data format conversion time; obtain the set of delay data {Ty i} = {Ty 1 , Ty 2 ,..., Ty I} within the time window T, where Ty i represents the data conversion delay of the i-th data type for data format conversion, i ∈ {1, 2,..., I}, and I is a positive integer;

[0015] Calculate the average data conversion delay μy within the time window T. The expression is as follows

[0016] Calculate the standard deviation σy of the data conversion within the time window T. The expression is as follows

[0017] Calculate the data conversion delay coefficient Dlc. The expression is as follows Where k represents the preset proportional coefficient of the data conversion standard deviation, which is used to reflect the importance of data conversion delay fluctuations, and Threshold represents the maximum allowable delay value.

[0018] In a preferred embodiment, by obtaining the data conversion loss information during the data format conversion process, analyzing the data conversion loss situation during the data format conversion process, and obtaining the data conversion loss coefficient, to measure the data conversion loss degree during the data format conversion process;

[0019] The acquisition logic of the data conversion loss coefficient is as follows:

[0020] Obtain the original data volume Dtotal of each data point before data format conversion and the converted data volume Dlost of each data point after data format conversion within the time window T, and calculate the data conversion loss ratio Lv. The expression is as follows Where Dlost j represents the converted data volume of the jth data point, and Dtotal j represents the original data volume of the jth data point, j ∈ {1, 2,..., J}, and J is a positive integer; calculate the data loss influence range Where FW is the data loss influence range, and α j represents the influence coefficient of the jth data point on environmental monitoring and emergency decision-making;

[0021] Calculate the loss timeliness coefficient Tloss. The expression is as follows Where δ(t n ) represents the time weighting function, tcurent represents the current time, and t n represents the loss time of the nth data point, n ∈ {1, 2,..., N}, and N is a positive integer;

[0022] Calculate the data conversion loss coefficient Sjz. The expression is as follows Sjz = Lv * (a 1 * FW + a 2 * Tloss).

[0023] In a preferred embodiment, by obtaining the data noise interference information during the data format conversion process, analyzing the data noise interference situation during the data format conversion process, and obtaining the data noise interference coefficient, to measure the data noise interference degree during the data format conversion process;

[0024] The acquisition logic of the data noise interference coefficient is as follows:

[0025] Obtain the data after format conversion and perform wavelet transform on the data after format conversion. Specifically, as follows Where Wx(a,b) represents the wavelet coefficients of the data after format conversion at scale a and position b. is the complex conjugate of the wavelet basis function, x(t) is the data after format conversion, and the energy E(a,b) of the wavelet coefficient at scale a and position b is calculated. The expression is as follows: E(a,b) = |W(a,b)| 2 ; Compare the energy at different scales with the preset scale threshold and energy threshold. If the scale a is less than or equal to the scale threshold and the energy is greater than the energy threshold, then add up the energy to obtain the data noise interference coefficient Zsx.

[0026] In a preferred embodiment, by acquiring data precision loss information of the data format conversion process, analyzing the data precision loss of the data format conversion process, and acquiring a data precision loss coefficient, the degree of data precision loss of the data format conversion process is measured;

[0027] The logic for obtaining the data precision loss coefficient is as follows:

[0028] Get the original data set before format conversion Doriginal = {d g}={d 1 ,d 1 ,...,d G} and the converted data set Dconvert = {d ' g}={d' 1 ,d' 1 ,...,d' G}, where d g represents the data point in the g-th original data set, d' g Represents the data point in the data set after the g-th format conversion;

[0029] Calculate the entropy of the original data set H(Doriginal), the expression is as follows Where P(d g ) is the data point d g The probability of appearing in the original dataset Doriginal;

[0030] Calculate the entropy H(Dconvert) of the data set after format conversion. The expression is as follows Where P(d' g ) is the data point d' g The probability of appearing in the dataset Dconvert after format conversion;

[0031] Calculate the joint entropy H(Doriginal,Dconvert), the expression is as follows where P(d g , d' g ) is the probability that each pair of data points appears simultaneously in the two datasets;

[0032] Calculate the mutual information I(Doriginal, Dconvert), and the expression is as follows: I(Doriginal, Dconvert) = H(Doriginal) + H(Dconvert) - H(Doriginal, Dconvert);

[0033] Calculate the data precision loss coefficient Jds, and the expression is as follows

[0034] In a preferred embodiment, construct a data conversion hidden danger assessment model based on the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, and generate a data conversion hidden danger assessment index Efinal. The formula on which the model is based is as follows In the formula, w 1 , w 2 , w 3 , w 4 respectively represent the preset proportional coefficients of the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, and w 1 , w 2 , w 3 , w 4 are all greater than 0.

[0035] In a preferred embodiment, compare the data conversion hidden danger assessment index with the preset data conversion hidden danger assessment index threshold to make a warning decision on the conversion format hidden danger of the current data format conversion, as follows:

[0036] If the data conversion hidden danger assessment index is greater than or equal to the data conversion hidden danger assessment index threshold, it indicates that there are relatively large hidden dangers in the current data format conversion process, and the system should immediately trigger a warning to generate a warning signal; if the data conversion hidden danger assessment index is less than or equal to the data conversion hidden danger assessment index threshold, it indicates that the hidden dangers in the data format conversion process are within an acceptable range, and there is no need to generate a warning signal.

[0037] The technical effects and advantages of the present invention:

[0038] 1. The present invention respectively obtains the calculation data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient through the conversion delay response module, information loss response module, noise interference response module, and precision loss response module, timely discovers problems such as conversion delay, information loss, noise interference, and precision loss in data format conversion, constructs a data conversion hidden danger evaluation model, generates a data conversion hidden danger evaluation index, evaluates the format conversion hidden danger in the data format conversion process, ensures that the system can always maintain the accuracy and timeliness of data during the environmental crisis emergency response process, avoids decision-making mistakes and response delays caused by inaccurate or delayed data, and based on the hidden danger evaluation results, can automatically issue early warnings and make corresponding decisions to indicate whether the system needs to adjust the data processing process or perform emergency repairs. This timely and intelligent early warning mechanism effectively improves the emergency response ability of the system. Especially when an environmental disaster occurs, it can quickly and accurately trigger emergency response measures, minimizing the impact of the environmental crisis on the city and residents. Brief Description of the Drawings

[0039] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0040] Figure 1 It is the flowchart of the system of the embodiment of the present invention. Detailed Embodiments

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment: The present invention provides a smart city environmental supervision system as Figure 1 shown, including a conversion delay response module, an information loss response module, a noise interference response module, a precision loss response module, a comprehensive evaluation module, and a warning decision module;

[0043] The conversion delay response module is used to obtain the data conversion delay information in the data format conversion process and obtain the data conversion delay coefficient according to the data conversion delay information;

[0044] The information loss response module is used to obtain the data conversion loss information in the data format conversion process and obtain the data conversion loss coefficient according to the data conversion loss information;

[0045] The noise interference response module is used to obtain the data noise interference information during the data format conversion process, and obtain the data noise interference coefficient according to the data noise interference information;

[0046] The precision loss response module is used to obtain the data precision loss information during the data format conversion process, and obtain the data precision loss coefficient according to the precision loss information;

[0047] The comprehensive evaluation module is used to construct a data conversion hidden danger evaluation model according to the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, generate a data conversion hidden danger evaluation index, and evaluate the format conversion hidden danger during the data format conversion process;

[0048] The early warning decision-making module is used to make an early warning decision on the conversion format hidden danger of the current data format conversion according to the evaluation result of the format conversion hidden danger;

[0049] The conversion delay response module is used to obtain the data conversion delay information during the data format conversion process, and obtain the data conversion delay coefficient according to the data conversion delay information;

[0050] The data conversion delay coefficient is used to measure the impact of the delay that occurs during the data format conversion on the real-time performance of the system. Especially in the emergency response to environmental crises, the timeliness of data is crucial because delayed data may prevent decision-makers from obtaining the latest environmental information in a timely manner, thereby missing key intervention opportunities, delaying emergency actions, and even potentially rendering response measures ineffective or exacerbating the impact of the crisis. The potential impacts of data conversion delays are as follows:

[0051] Missing key intervention opportunities: In environmental crises such as air pollution or flood disasters, monitoring data must reflect the changing trends in real time. For example, if air quality monitoring data is delayed by several minutes or hours, changes in pollution sources may have occurred, and response measures may no longer be implementable in a timely manner. Data delays can cause decision-makers to miss the optimal timing for emergency evacuation or pollution control, thus affecting the health and safety of the public.

[0052] Affecting resource allocation and cross-departmental collaboration: Different departments (such as emergency management, transportation, fire protection, etc.) rely on real-time environmental data to formulate response plans. Data conversion delays may cause a time lag in information acquisition for each department, thereby affecting multi-department coordination and resource allocation. For example, delayed traffic flow data may lead to incorrect evacuation route planning and miss the optimal evacuation window.

[0053] Misleading decision-making and emergency response: Emergency responses in environmental crises usually rely on data-driven decision-making. If the data is delayed, it may lead to decisions being made based on incomplete or outdated information. For example, dispatching rescue resources based on outdated meteorological data may result in ineffective responses or resource waste.

[0054] Affect the speed of post-disaster assessment and restoration: After an environmental disaster, rapid post-disaster assessment is crucial for recovery and reconstruction. Delays in data conversion reduce the timeliness of post-disaster assessment, further slowing down the restoration process and increasing economic losses.

[0055] The data conversion delay coefficient provides a quantitative delay metric for the system, enabling accurate assessment of the delay in each data source during the conversion process and rapid identification of delay risks in a real-time environment. This assessment helps identify bottlenecks that may affect the system's response speed, early warning of potential format conversion delay problems, and prevention of these problems from magnifying during an environmental crisis, thus affecting real-time decision-making and emergency response. To help optimize the entire data processing flow, the system can reduce unnecessary format conversion steps through automated adjustment, adopt more efficient data transmission and processing methods, and enhance the overall response speed of the system. In cases where data sources are complex and formats are inconsistent, timely assessment and optimization of delays, avoiding redundant processing links and excessive data conversion, not only improve the efficiency of the data stream but also reduce the risk of potential data loss and information misreading. The assessment of the data conversion delay coefficient helps promote the effectiveness of cross-departmental coordination and information sharing. Since different departments rely on different data sources for decision-making, the accumulation of delays may lead to information lag, thereby affecting resource scheduling and emergency response. By evaluating the delay impact of each link, real-time data sharing can be achieved during multi-departmental collaboration, ensuring that all departments can obtain the latest and complete environmental data within the same time frame, thereby enhancing the accuracy of decision-making and the coordination of responses. Especially in the event of a disaster, rapid data sharing and decision-making response are the keys to mitigating the impact of the disaster and protecting public safety.

[0056] Therefore, by obtaining data conversion delay information during the data format conversion process, analyzing the data conversion delay situation during the data format conversion process, and obtaining the data conversion delay coefficient, the degree of data conversion delay during the data format conversion process is measured;

[0057] The acquisition logic of the data conversion delay coefficient is as follows:

[0058] Adopt a timestamp mechanism to record the time points of each stage of data format conversion, including the start timestamp Tconverts of data format conversion and the end timestamp Ttransmite of data format conversion, and calculate the data conversion delay Ty. The expression is as follows where Tsagnao is the expected data format conversion time; obtain the set of delay data {Ty within the time window T i} = {Ty 1 , Ty 2 ,..., Ty I}, where Ty iDenote the data conversion latency for the i-th data type to perform data format conversion, where i ∈ {1, 2, ..., I} and I is a positive integer;

[0059] It should be noted that the data type is determined according to the actual data types collected by the smart city environmental supervision system, such as CSV, JSON, etc.;

[0060] Calculate the average data conversion latency μy within the time window T, and the expression is as follows

[0061] Calculate the standard deviation σy of data conversion within the time window T, and the expression is as follows

[0062] Calculate the data conversion latency coefficient Dlc, and the expression is as follows Where k represents the preset proportional coefficient of the data conversion standard deviation, which is used to reflect the importance of the data conversion latency fluctuation, and Threshold represents the maximum allowable latency value;

[0063] It should be noted that the preset proportional coefficient of the data conversion standard deviation is set according to the actual situation. For example, the expert weighting method is adopted, that is, relevant experts are invited to determine the preset proportional coefficient of the data conversion standard deviation through professional opinion surveys and comprehensive evaluations;

[0064] The information loss response module is used to obtain the data conversion loss information during the data format conversion process and obtain the data conversion loss coefficient according to the data conversion loss information;

[0065] The data conversion loss coefficient is used to measure the severity of data loss during the data format conversion process. Data loss usually leads to the absence of key information in the system, affecting the quality of decision-making for environmental crisis response and even potentially resulting in missed intervention opportunities. By calculating the data conversion loss coefficient, it is possible to effectively identify and quantify the potential impact of the lost data on the system during the data conversion process, and then optimize the data processing flow and emergency response capabilities. By comprehensively considering the ratio of lost data and its impact on decision-making, the data conversion loss coefficient not only reveals the severity of data loss but also helps the system evaluate the scope of the impact of the lost data, thus taking targeted measures. Specifically, the data conversion loss coefficient can reflect the negative impact of the lost data on environmental monitoring and disaster response decision-making, ensuring that decision-makers can timely adjust data collection and conversion strategies to prevent decision-making errors or response delays caused by the loss of key information. The larger the data conversion loss coefficient, the more severe the amount of data lost and the impact of the lost data on the system during the data format conversion process. This means that the system may lose key monitoring information or environmental change data, thus affecting the timely response and decision-making for environmental crises, delaying emergency treatment measures, and even potentially leading to incorrect decisions or resource waste. In severe cases, it may even exacerbate the consequences of the disaster. On the contrary, the smaller the data conversion loss coefficient, the lower the degree of data loss, the data conversion process in the system is relatively stable, the amount of lost data is small, and the impact on overall monitoring and emergency response is small. This means that the integrity and accuracy of the data are relatively high, which can effectively support environmental monitoring, real-time early warning, and decision-making support, reduce potential risks caused by data loss, and thus ensure more efficient cross-departmental collaboration and resource allocation, improving the timeliness and accuracy of emergency response.

[0066] Therefore, by obtaining the data conversion loss information during the data format conversion process, analyzing the data conversion loss situation during the data format conversion process, and obtaining the data conversion loss coefficient, the degree of data conversion loss during the data format conversion process is measured;

[0067] The acquisition logic of the data conversion loss coefficient is as follows:

[0068] Within the time window T, obtain the original data volume Dtotal of each data point before data format conversion and the converted data volume Dlost of each data point after data format conversion, and calculate the data conversion loss ratio Lv. The expression is as follows where Dlost j represents the converted data volume of the jth data point, and Dtotal j represents the original data volume of the jth data point, j ∈ {1, 2,..., J}, and J is a positive integer; calculate the data loss impact scope where FW is the data loss impact scope, and α jIndicates the influence coefficient of the j-th data point on environmental monitoring and emergency decision-making;

[0069] It should be noted that the influence coefficient is used to measure the importance of data points for environmental monitoring and emergency decision-making, and its value range is [0, 1]. The larger the value, the more important the data point is for decision-making, and it can be set according to the importance of the data source;

[0070] Calculate the loss of timeliness coefficient Tloss, and the expression is as follows where δ(t n ) represents the time weighting function, tcurent represents the current time, t n represents the loss time of the n-th data point, n ∈ {1, 2,..., N}, and N is a positive integer;

[0071] Calculate the data conversion loss coefficient Sjz, and the expression is as follows Sjz = Lv * (a 1 * FW + a 2 * Tloss);

[0072] It should be noted that before calculating the data conversion loss coefficient, it is necessary to ensure that the data conversion loss ratio, the data loss influence range, and the loss of timeliness coefficient have all been normalized. Common normalization methods include Min-Max normalization, Z-Score standardization, etc.; a 1 、a 2 are set according to the actual situation. For example, the expert weighting method is adopted, that is, experts in related fields are invited to determine the preset proportional coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0073] The noise interference response module is used to obtain the data noise interference information during the data format conversion process, and obtain the data noise interference coefficient according to the data noise interference information;

[0074] The data noise interference coefficient is used to measure the impact of external interferences (such as electromagnetic interference, environmental noise, etc.) on the data quality and reliability during the data format conversion process. During the data conversion process, data may be distorted, in error, or lost due to external interferences, affecting the accuracy of system decision-making. Especially in the smart city environmental supervision system involving real-time monitoring and emergency response, the accuracy and accuracy of data are crucial. Therefore, the noise interference coefficient becomes an important parameter for evaluating the stability and effectiveness of the data conversion process. The data noise interference coefficient reflects the impact of external environmental factors (such as electromagnetic interference, environmental noise, etc.) on the data format conversion process. When the noise interference coefficient is high, it indicates that the data may be distorted or in error to a large extent during the conversion process, which will lead to a decline in data quality and further affect the accuracy of system decision-making.

[0075] Therefore, by obtaining the data noise interference information during the data format conversion process, analyzing the data noise interference situation during the data format conversion process, and obtaining the data noise interference coefficient, the data noise interference degree during the data format conversion process is measured;

[0076] The acquisition logic of the data noise interference coefficient is as follows:

[0077] Obtain the data after format conversion and perform wavelet transform on the data after format conversion, specifically as follows where Wx(a, b) represents the wavelet coefficient of the data after format conversion at scale a and position b, is the complex conjugate of the wavelet basis function, x(t) is the data after format conversion, calculate the energy E(a, b) of the wavelet coefficient at scale a and position b, and the expression is as follows E(a, b) = |W(a, b)| 2 ; Compare the energies at different scales with the preset scale threshold and energy threshold. If the scale a is less than or equal to the scale threshold and the energy is greater than the energy threshold, then accumulate and calculate its energy to obtain the data noise interference coefficient Zsx;

[0078] In wavelet transform, the scale controls the stretching degree of the wavelet basis function. The smaller the scale, the higher the time (or space) resolution of the wavelet function, that is, the stronger the local analysis ability. Energy represents the local change degree of the signal at this scale.

[0079] Therefore, the smaller the scale and the greater the energy, usually indicating that the signal has a strong local change at this scale, may be noise or fast-changing signal components. Specifically:

[0080] The smaller the scale: means that the wavelet function has a higher degree of localization in time or space, and can capture more subtle signal changes, especially the fast-changing signal part. The small scale corresponds to the high-frequency part in the signal.

[0081] The greater the energy: means that at this scale, the signal changes violently, usually noise or high-frequency components. Large energy indicates that there are large fluctuations or irregularities at this scale.

[0082] The precision loss response module is used to obtain the data precision loss information during the data format conversion process and obtain the data precision loss coefficient according to the precision loss information;

[0083] The data precision loss coefficient is used to measure the degree of data precision decline caused by conversion operations, data scaling, or other factors during the data format conversion process. Precision loss may affect the accuracy of data analysis and decision-making. Especially in environmental monitoring and emergency response systems, precision loss will affect the timely perception of environmental changes and the effectiveness of decision-making. The data precision loss coefficient reflects the potential data quality problems that may be caused by the precision decline during the data format conversion process. Evaluating this coefficient can help the system identify potential risks at an early stage, especially during the environmental crisis emergency response process. By quantifying the precision loss and assessing its potential hazards, the system can more accurately judge the risks of data inaccuracy or decision-making errors that may be caused during the conversion process, thereby providing more reliable information support in aspects such as environmental monitoring, disaster response, and resource allocation. When the data precision loss coefficient is relatively high, it indicates that the precision loss during the data conversion process is relatively serious. The system should detect and respond in a timely manner to avoid incorrect decisions caused by the loss of precision. This is particularly important for cross-departmental cooperation. Ensuring that the data used by each department is consistent and accurate can reduce communication barriers caused by information errors and promote more timely and effective emergency response and pollution control measures.

[0084] Therefore, by obtaining the data precision loss information during the data format conversion process, analyzing the data precision loss situation during the data format conversion process, and obtaining the data precision loss coefficient, the degree of data precision loss during the data format conversion process can be measured;

[0085] The acquisition logic of the data precision loss coefficient is as follows:

[0086] Obtain the original data set Doriginal before format conversion = {d g} = {d 1 , d 1 ,..., d G} and the data set Dconvert after format conversion = {d' g} = {d' 1 , d' 1 ,..., d' G}, where d g represents the data point in the g-th original data set, and d' g represents the data point in the g-th data set after format conversion;

[0087] Calculate the entropy H(Doriginal) of the original data set, and the expression is as follows where P(d g ) is the probability that the data point d g appears in the original data set Doriginal;

[0088] Calculate the entropy H(Dconvert) of the dataset after format conversion, and the expression is as follows where P(d' g ) is the probability that the data point d' g appears in the dataset Dconvert after format conversion;

[0089] Calculate the joint entropy H(Doriginal,Dconvert), and the expression is as follows where P(d g ,d' g ) is the probability that each pair of data points appears simultaneously in the two datasets;

[0090] Calculate the mutual information I(Doriginal,Dconvert), and the expression is as follows I(Doriginal,Dconvert) = H(Doriginal) + H(Dconvert) - H(Doriginal,Dconvert);

[0091] Calculate the data precision loss coefficient Jds, and the expression is as follows

[0092] A comprehensive evaluation module is used to construct a data conversion hidden danger evaluation model based on the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, generate a data conversion hidden danger evaluation index, and evaluate the format conversion hidden danger in the data format conversion process;

[0093] Construct a data conversion hidden danger evaluation model based on the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, and generate a data conversion hidden danger evaluation index Efinal. The formula on which the model is based is as follows In the formula, w 1 , w 2 , w 3 , w 4 respectively represent the preset proportional coefficients of the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, and w 1 , w 2 , w 3 , w 4 are all greater than 0;

[0094] It should be noted that before constructing the data conversion hidden danger evaluation model, it is necessary to ensure that the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient have all been normalized. Common normalization methods include Min-Max normalization, Z-Score standardization, etc.; w 1 , w2 、w 3 、w 4 Set it according to the actual situation. For example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0095] It can be seen from the above calculation expression that the larger the data conversion delay coefficient, the larger the data conversion loss coefficient, the larger the data noise interference coefficient, and the larger the data precision loss coefficient, the larger the data conversion hidden danger assessment index, which means that the system has a large data conversion problem, which may cause data distortion, delay, loss and other phenomena, affecting the quality of information sharing and the accuracy of decision-making. On the contrary, the smaller the data conversion delay coefficient, the smaller the data conversion loss coefficient, the smaller the data noise interference coefficient, and the smaller the data precision loss coefficient, the smaller the data conversion hidden danger assessment index, which represents the superiority of the system data quality, indicating that the system has a strong response capability in environmental crises, efficient response, and optimized resource utilization, which plays a vital role in ensuring the sustainable development and safety management of smart cities;

[0096] An early warning decision module is used to make early warning decisions on conversion format risks of current data format conversion according to the evaluation results of format conversion risks;

[0097] The data conversion hidden danger assessment index is compared with the preset data conversion hidden danger assessment index threshold, and a warning decision is made on the conversion format hidden danger of the current data format conversion, as follows:

[0098] If the data conversion hidden danger assessment index is greater than or equal to the data conversion hidden danger assessment index threshold, it indicates that there are major hidden dangers in the current data format conversion process, and the system should immediately trigger an early warning and generate an early warning signal. At this time, the quality problems of the data conversion process may cause distortion or delay of the basic data that key decisions rely on, affecting the effectiveness of the entire emergency response process; if the data conversion hidden danger assessment index is less than or equal to the data conversion hidden danger assessment index threshold, it indicates that the hidden dangers in the data format conversion process are within an acceptable range, and there is no need to generate an early warning signal. The current data format conversion process has no significant delay, loss, noise interference or accuracy loss problems, and data processing and conversion can continue according to the predetermined process to support subsequent environmental monitoring and decision analysis.

[0099] The present invention respectively obtains the calculation data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient through a conversion delay response module, an information loss response module, a noise interference response module, and a precision loss response module, timely discovers problems such as conversion delay, information loss, noise interference, and precision loss in data format conversion, constructs a data conversion hidden danger assessment model, generates a data conversion hidden danger assessment index, evaluates the format conversion hidden danger in the data format conversion process, ensures that the system can always maintain the accuracy and timeliness of data during the environmental crisis emergency response process, avoids decision-making mistakes and response delays caused by inaccurate or delayed data, and based on the hidden danger assessment results, can automatically issue a warning and make corresponding decisions to indicate whether the system needs to adjust the data processing process or perform emergency repairs. This timely and intelligent warning mechanism effectively improves the emergency response ability of the system. Especially when an environmental disaster occurs, it can quickly and accurately trigger emergency response measures, minimizing the impact of the environmental crisis on the city and residents.

[0100] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0101] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0102] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not indicate the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0103] If the above function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0104] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart city environmental monitoring system, characterized by: It includes a conversion delay response module, an information loss response module, a noise interference response module, an accuracy loss response module, a comprehensive evaluation module, and an early warning decision module; A conversion delay response module, used to obtain data conversion delay information of a data format conversion process, and obtain a data conversion delay coefficient according to the data conversion delay information; An information loss response module is used to obtain data conversion loss information in the data format conversion process and obtain a data conversion loss coefficient according to the data conversion loss information; A noise interference response module is used to obtain data noise interference information during the data format conversion process, and obtain a data noise interference coefficient according to the data noise interference information; The precision loss response module is used to obtain the data precision loss information in the data format conversion process and obtain the data precision loss coefficient according to the precision loss information; A comprehensive assessment module is used to construct a data conversion hidden danger assessment model based on a data conversion delay coefficient, a data conversion loss coefficient, a data noise interference coefficient, and a data precision loss coefficient, generate a data conversion hidden danger assessment index, and assess the format conversion hidden dangers in the data format conversion process; The early warning decision module is used to make early warning decisions on conversion format risks of the current data format conversion according to the evaluation results of the format conversion risks.

2. A smart city environmental monitoring system according to claim 1, characterized in that: By acquiring data conversion delay information of the data format conversion process, analyzing the data conversion delay of the data format conversion process, and acquiring a data conversion delay coefficient, the degree of data conversion delay of the data format conversion process is measured; The logic for obtaining the data conversion delay coefficient is as follows: The timestamp mechanism is used to record the time points of each stage of data format conversion, including the start timestamp Tconverts and end timestamp Ttransmite of data format conversion, and the data conversion delay Ty is calculated. The expression is as follows Where Tsagnao is the expected data format conversion time; Get the delayed data set in the time window T {Ty i }={Ty1,Ty2,...,Ty I }, where Ty i represents the data conversion delay for data format conversion of the i-th data type, i∈{1,2,...,I}, where I is a positive integer; Calculate the average data conversion delay μy within the time window T, the expression is as follows Calculate the data conversion standard deviation σy within the time window T, the expression is as follows Calculate the data conversion delay coefficient Dlc, the expression is as follows Wherein k represents a preset proportional coefficient of the data conversion standard deviation, which is used to reflect the importance of data conversion delay fluctuation, and Threshold represents the maximum allowable delay value.

3. A smart city environmental monitoring system according to claim 1, characterized in that: By acquiring data conversion loss information in the data format conversion process, analyzing the data conversion loss situation in the data format conversion process, and acquiring a data conversion loss coefficient, the degree of data conversion loss in the data format conversion process is measured; The logic for obtaining the data conversion loss coefficient is as follows: Obtain the original data volume Dtotal of each data point before data format conversion and the converted data volume Dlost of each data point after data format conversion within the time window T, and calculate the data conversion loss ratio Lv. The expression is as follows: Dlost j Indicates the amount of data after the jth data point is converted, Dtotal j Represents the original data volume of the jth data point, j∈{1,2,...,J}, J is a positive integer; calculate the impact range of data loss Where FW is the impact range of data loss, α j Represents the influence coefficient of the jth data point on environmental monitoring and emergency decision-making; Calculate the loss time coefficient Tloss, the expression is as follows Where δ(t n ) represents the time weighting function, tcurent represents the current time, t n represents the loss time of the nth data point, n∈{1,2,...,N}, N is a positive integer; Calculate the data conversion loss coefficient Sjz, the expression is as follows Sjz = Lv*(a1*FW+a2*Tloss).

4. A smart city environment monitoring system according to claim 1, characterized in that: By acquiring the data noise interference information of the data format conversion process, analyzing the data noise interference situation of the data format conversion process, and obtaining the data noise interference coefficient, the degree of data noise interference in the data format conversion process is measured; The logic for obtaining the data noise interference coefficient is as follows: Get the data after format conversion and perform wavelet transform on the data after format conversion, as follows Where Wx(a,b) represents the wavelet coefficients of the data after format conversion at scale a and position b. is the complex conjugate of the wavelet basis function, x(t) is the data after format conversion, and the energy E(a,b) of the wavelet coefficient at scale a and position b is calculated. The expression is as follows: E(a,b) = |W(a,b)| 2 ; Compare the energy at different scales with the preset scale threshold and energy threshold. If the scale a is less than or equal to the scale threshold and the energy is greater than the energy threshold, then add up the energy to obtain the data noise interference coefficient Zsx.

5. The smart city environment monitoring system according to claim 1 is characterized in that: By obtaining the data precision loss information of the data format conversion process, analyzing the data precision loss of the data format conversion process, and obtaining the data precision loss coefficient, the degree of data precision loss of the data format conversion process is measured; The logic for obtaining the data precision loss coefficient is as follows: Get the original data set before format conversion Doriginal = {d g }={d1,d1,...,d G } and the converted data set Dconvert = {d ' g }={d'1,d'1,...,d' G }, where d g represents the data point in the g-th original data set, d' g Represents the data point in the data set after the g-th format conversion; Calculate the entropy of the original data set H(Doriginal), the expression is as follows Where P(d g ) is the data point d g The probability of appearing in the original dataset Doriginal; Calculate the entropy H(Dconvert) of the data set after format conversion. The expression is as follows Where P(d' g ) is the data point d' g The probability of appearing in the dataset Dconvert after format conversion; Calculate the joint entropy H(Doriginal,Dconvert), the expression is as follows Where P(d g ,d' g ) is the probability that each pair of data points appears in both data sets; Calculate the mutual information I(Doriginal,Dconvert), which is expressed as follows: I(Doriginal,Dconvert) = H(Doriginal) + H(Dconvert) - H(Doriginal,Dconvert); Calculate the data precision loss coefficient Jds, the expression is as follows 6. A smart city environment monitoring system according to claim 1, characterized in that: According to the data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data accuracy loss coefficient, a data conversion hidden danger assessment model is constructed to generate the data conversion hidden danger assessment index Efinal. The formula based on the model is as follows: Wherein w1, w2, w3, and w4 represent preset proportional coefficients of data conversion delay coefficient, data conversion loss coefficient, data noise interference coefficient, and data precision loss coefficient, respectively, and w1, w2, w3, and w4 are all greater than 0.

7. A smart city environment monitoring system according to claim 6, characterized in that: The data conversion hidden danger assessment index is compared with the preset data conversion hidden danger assessment index threshold, and a warning decision is made on the conversion format hidden danger of the current data format conversion, as follows: If the data conversion hidden danger assessment index is greater than or equal to the data conversion hidden danger assessment index threshold, it indicates that there are major hidden dangers in the current data format conversion process, and the system should immediately trigger an early warning and generate an early warning signal; if the data conversion hidden danger assessment index is less than or equal to the data conversion hidden danger assessment index threshold, it indicates that the hidden dangers in the data format conversion process are within an acceptable range and there is no need to generate an early warning signal.

Images