A water source key risk substance sample intelligent detection method and system

Abstract

The present application relates to the field of water source detection, and more particularly to a water source key risk sample intelligent detection method and system, which obtains sample detection data of the water source in real time; determines whether the sample detection data of the water source meets an abnormal condition; when the water source meets the abnormal condition, analyzes the sample detection data, identifies a target risk parameter and a sample position according to the sample detection data, generates risk data based on the target risk parameter and the sample position, and sends the risk data to a management end; when the water source does not meet the abnormal condition, extracts a target feature of the sample detection data; predicts a water quality change trend of the water source based on the target feature; determines whether the water quality meets an early warning condition according to a prediction result; when the water quality meets the early warning condition, generates a water quality treatment strategy and early warning information based on the prediction result, and sends the water quality treatment strategy and the early warning information to the management end. Through multi-dimensional risk assessment, errors caused by sensor limitations are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water source detection, in particular to a water source key risk substance sample intelligent detection method and system. BACKGROUND

[0002] In the process of monitoring and analyzing key pollutants that may harm water quality and water ecology in water sources (such as rivers, lakes, reservoirs, etc.). The purpose is to sample and detect potential pollutants existing in the water source environment. These pollutants may be introduced into the water body by industrial, agricultural, domestic sewage and other discharge sources, or naturally occurring harmful substances in the water body.

[0003] In the prior art, the water quality monitoring method relies on sensors to directly measure whether the content of risk substances (such as heavy metals, chemical pollutants, dissolved oxygen, etc.) in the water source exceeds the standard. Although this method can obtain water quality data in real time, due to the influence of environmental conditions (such as temperature, pH value, water flow rate, precipitation, etc.) on the concentration of pollutants in the water source, the sensor is easily affected by errors, interference or reaction lag, and the sensor detection result often has certain errors. For example, the concentration of some pollutants may fluctuate rapidly or show a gradual change trend in a short time, and the sensor often cannot capture these subtle changes in time. For another example, when extreme weather events occur, temperature, humidity, rainfall and other environmental characteristics may change dramatically in a very short time, which may cause instantaneous fluctuations in water quality parameters, causing the water source detection data to exceed the fixed threshold in a short time, but this does not necessarily mean that the water quality of the water source is abnormal, but is caused by environmental disturbance. If the detection model only relies on a fixed threshold without effectively identifying and adapting to these extreme environmental changes, it may cause false positives or false negatives.

[0004] Therefore, the prior art has defects and needs to be improved. SUMMARY

[0005] In order to solve one or several problems in the prior art, the main purpose of the present application is to provide a water source key risk substance sample intelligent detection method and system.

[0006] In order to achieve the above-mentioned purpose of the application, the present application provides a water source key risk substance sample intelligent detection method, which comprises:

[0007] real-time acquisition of sample detection data of the water source;

[0008] determining whether the sample detection data of the water source meets the abnormal condition;

[0009] When the water source meets the abnormal condition, the sample detection data is parsed, a target risk parameter and a sample position are identified according to the sample detection data, and risk data is generated based on the target risk parameter and the sample position and sent to a management end;

[0010] When the water source does not meet the abnormal condition, a target feature of the sample detection data is extracted;

[0011] The target feature is used to predict a water quality change trend of the water source;

[0012] It is judged whether the water quality meets an early warning condition according to a prediction result;

[0013] When the water quality meets the early warning condition, a water quality treatment strategy and early warning information are generated based on the prediction result and sent to the management end.

[0014] The embodiment of the application further provides a water source key risk sample intelligent detection system, comprising:

[0015] An acquisition module is configured to acquire sample detection data of a water source in real time;

[0016] A judgment module is configured to judge whether the sample detection data of the water source meets an abnormal condition;

[0017] A parsing module is configured to parse the sample detection data when the water source meets the abnormal condition, identify a target risk parameter and a sample position according to the sample detection data, generate risk data based on the target risk parameter and the sample position, and send the risk data to a management end;

[0018] An extraction module is configured to extract a target feature of the sample detection data when the water source does not meet the abnormal condition;

[0019] A prediction module is configured to predict a water quality change trend of the water source according to the target feature;

[0020] A second judgment module is configured to judge whether the water quality meets an early warning condition according to a prediction result;

[0021] A sending module is configured to generate a water quality treatment strategy and early warning information based on the prediction result and send the water quality treatment strategy and the early warning information to the management end when the water quality meets the early warning condition.

[0022] The application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of the preceding embodiments when executing the computer program.

[0023] The application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method according to any one of the preceding embodiments when executed by a processor.

[0024] The water source key risk substance sample intelligent detection method and system of the embodiments of the present application can not only detect the current water quality state, but also predict the future water quality trend through real-time monitoring and data analysis. This forward-looking judgment enables the system to identify potential water quality problems in advance, avoiding the possible reaction lag in traditional monitoring methods, thereby providing more accurate risk assessment and early warning information for managers. By extracting features from sample data and combining historical data and environmental factors, a prediction model of water quality changes can be generated in real time. This prediction capability significantly improves the response speed of the monitoring system, enabling managers to take action in advance and effectively reduce the risk of pollutant concentration fluctuations. By integrating multiple data sources (such as water sample detection results, environmental factor data, etc.), multi-dimensional risk assessment is achieved. This data fusion approach avoids the limitations of a single sensor due to environmental interference or technical limitations, providing a more comprehensive and accurate reflection of the true water quality of the water source, reducing errors caused by sensor limitations. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 FIG. 1 is a flowchart of the water source key risk substance sample intelligent detection method of an embodiment of the present application;

[0026] Figure 2 FIG. 1 is a flowchart of the water source key risk substance sample intelligent detection method of an embodiment of the present application;

[0027] Figure 3 FIG. 2 is a structural schematic block diagram of the water source key risk substance sample intelligent detection system of an embodiment of the present application;

[0028] Figure 4 FIG. 3 is a structural schematic block diagram of the computer device of an embodiment of the present application.

[0029] The implementation of the purpose of the present application, functional characteristics and advantages will be further described with reference to the drawings. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the present application more clear, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0031] Referring to Figure 1 , the present application provides a water source key risk substance sample intelligent detection method, which comprises:

[0032] S1, real-time acquisition of sample detection data of the water source;

[0033] S2, judging whether the sample detection data of the water source meets an abnormal condition;

[0034] S3, when the water source meets the abnormal condition, analyzing the sample detection data, identifying a target risk parameter and a sample position according to the sample detection data, and generating risk data based on the target risk parameter and the sample position and sending the risk data to a management end;

[0035] S4, when the water source does not meet the abnormal condition, extracting a target feature of the sample detection data;

[0036] S5, predicting a water quality change trend of the water source according to the target feature;

[0037] S6, judging whether the water quality meets an early warning condition according to the prediction result;

[0038] S7, when the water quality meets the early warning condition, generating a water quality treatment strategy and early warning information based on the prediction result and sending the water quality treatment strategy and the early warning information to the management end.

[0039] As described in steps S1-S3 above, the water source can be continuously monitored by sensors, sampling devices, or remote monitoring systems to collect water quality sample data in real time. These data typically include physical-chemical parameters such as pH, dissolved oxygen, turbidity, temperature, chemical oxygen demand (COD), ammonia nitrogen, etc. This real-time monitoring can be achieved through various technologies such as sensor networks, Internet of Things (IoT) devices. By analyzing the real-time collected water quality data, it can be determined whether the water quality deviates from the normal range. For example, statistical analysis methods, machine learning algorithms or threshold judgments can be used to identify whether there are abnormal conditions such as pollution, excessive concentration of pollutants, etc. Abnormal conditions may include excessive concentration of pollutants, sudden changes in water quality, or sudden events (such as release of upstream pollution sources). By identifying abnormal conditions in real time, potential pollution threats can be detected in advance, and emergency response measures can be taken in a timely manner. The accuracy of the abnormal condition judgment will directly affect the reliability of the system, avoiding frequent false alarms. The detection data is analyzed to identify key parameters related to water quality changes, such as specific pollutants, heavy metals, toxic chemicals, etc. These key parameters can be dissolved oxygen, chemical oxygen demand (COD), nitrogen and phosphorus concentrations, etc. In addition, spatial location information of the water source is also needed to identify pollution sources at different locations to more accurately determine the degree of pollution of the water source. By identifying specific risk parameters and sample locations, the area where the pollution source is located can be determined, facilitating rapid response. After identifying the risk parameters, targeted emergency response measures can be developed, rather than a simple "one-size-fits-all" approach, but different handling measures according to the type and location of the pollution source. Through accurate identification of target risk parameters and locations, the severity of pollution can be effectively evaluated, improving decision-making quality. For example, according to the different types of pollutants, physical, chemical or biological treatment methods can be taken to help develop more appropriate treatment strategies. Based on the target risk parameters and sample locations identified in the above steps, comprehensive risk data is generated. Risk data typically includes information such as pollution source type, concentration, and pollution area, and is sent to the management end through a data transmission system. Risk data can be presented to water quality monitoring managers in the form of charts, reports, etc., helping them understand the current water quality risk level.

[0040] As described in steps S4-S7 above, when the water quality data does not show obvious abnormalities, the system extracts target features (such as the historical trends of various water quality indicators) through data analysis methods (such as machine learning prediction models, time series analysis, etc.), and predicts the water quality trends based on these features. The prediction model can be based on historical data, weather changes, seasonal factors, etc., combined with feature data to predict the future water quality trends. Based on the prediction results of the previous step, it is determined whether the future water quality change will reach the warning threshold. The warning conditions may include the water quality indicators reaching the set dangerous level (such as the concentration of a specific pollutant exceeding the standard). The warning algorithm may combine historical data, trend prediction and warning threshold to calculate whether the warning condition is met using a rule engine or model. By automatically determining whether the warning condition is met based on the prediction results, intelligent management can be achieved, reducing human judgment errors. By predicting whether the water quality reaches the warning condition, measures can be taken to prevent water pollution before the concentration of pollutants increases. Automatic judgment and warning can improve the adaptive ability of the system and reduce human intervention. When the water quality meets the warning condition, the system generates corresponding water quality treatment strategies based on the water quality prediction results and notifies the management end through warning information. The water quality treatment strategies may include dosing, adjusting water flow, starting pollution source control equipment, etc. According to the type of water quality problem and the prediction, appropriate water quality treatment strategies are developed to minimize water pollution. Through real-time feedback of warning information, management personnel can quickly understand the problem and take prompt measures.

[0041] As described above, by collecting the behavior data and environmental data of poultry in the orchard. This real-time nature ensures that the breeding personnel can obtain accurate information at any time, which helps to quickly discover any potential problems. Ensures that poultry health problems can be discovered at the earliest stage, avoiding delays. Continuous high-frequency data collection improves the accuracy of monitoring, which helps to accurately determine the behavior and physiological state of poultry. When the behavior or physiological data of poultry deviates from the normal range, it can be automatically judged and marked as abnormal behavior. This process combines the data of the poultry itself and environmental factors, and can efficiently and accurately identify health or environmental problems. It can timely discover poultry abnormalities and prevent problems from spreading, such as disease transmission or environmental stress. Reduces the subjective judgment errors of breeding personnel, and relies on data-driven automated judgment for greater reliability. Comprehensive analysis is conducted in combination with environmental data (such as temperature, humidity, light, etc.) to infer the root cause of abnormal behavior. This multi-dimensional data fusion capability significantly improves the adaptability of the system to complex situations. Avoids misjudgment that may be caused by a single data source, ensuring the accuracy of the abnormal behavior analysis results. For example, natural behavior changes caused by environmental changes are no longer misjudged as health problems. Through comprehensive analysis, the system can learn from itself and improve the accuracy of abnormal behavior identification, gradually optimizing the monitoring model. After confirming the cause of the abnormal behavior, the system can automatically generate targeted response strategies.

[0042] Reference Figure 2 In one embodiment, after the step of determining whether the sample detection data of the water source meets the abnormal conditions, and before the step of determining when the water source meets the abnormal conditions, the method further includes:

[0043] S31. Obtain environmental data of the sample location and extract environmental features from the environmental data, wherein the environmental features include temperature features, humidity features, wind speed features and rainfall features.

[0044] S32. Construct an error analysis model, input the environmental features and sample detection data into the error analysis model, evaluate the interference coefficient of the environmental features on the sample detection data within a specific time period through the error analysis model, and output the evaluation result. The interference coefficient is used to evaluate the magnitude of the deviation of water quality parameters from normal values ​​caused by environmental features.

[0045] S33. Based on the evaluation results, the detection threshold is adjusted using the interference coefficient to obtain the adjusted detection threshold;

[0046] S34. Based on the adjusted detection threshold, determine whether the water source meets the abnormal conditions;

[0047] S35. When the sample detection data is greater than the adjusted detection threshold, it is determined that the sample detection data of the water source meets the abnormal conditions.

[0048] As described above, temperature is a key factor affecting water quality parameters. For example, increased temperature increases the rate of dissolved oxygen consumption and accelerates chemical reaction rates, leading to changes in some water quality indicators. Temperature changes also affect the activity of microorganisms in the water, thus impacting water quality. Some water quality testing equipment is highly sensitive to temperature, so readings may deviate under different temperature conditions. Ignoring the impact of temperature on water quality may lead to misinterpretations of certain indicators. For example, water at higher temperatures may show lower dissolved oxygen levels, but this low value is actually caused by temperature and does not necessarily indicate water quality deterioration. By inputting temperature data as an environmental characteristic into an error analysis model, its interference coefficient on water quality data can be assessed. By dynamically adjusting the detection threshold, errors caused by temperature changes can be corrected, ensuring more accurate water quality monitoring. Air humidity has a direct impact on water evaporation, precipitation, and water level changes. Humidity changes typically cause fluctuations in water flow and level, thus affecting the stability of water quality monitoring data. For example, when air humidity is high, the evaporation rate of water sources is low, which may lead to changes in the concentration of nutrients in the water. Furthermore, excessively high or low humidity can lead to instability in the performance of water quality monitoring instruments, thus affecting the accuracy of test results. Changes in humidity can significantly impact water quality parameters in the short term; for example, under high humidity conditions, changes in water quality indicators may be misjudged as water quality anomalies. By using humidity as an input feature, error analysis models can identify potential errors caused by humidity changes and calculate the corresponding interference coefficients. By adjusting the detection threshold, the interference of humidity changes on water quality monitoring can be eliminated, reducing misjudgments. Wind speed has a direct impact on water surface fluctuations, water flow velocity, and evaporation processes, especially in open water bodies. Changes in wind speed may affect water quality parameters such as oxygen solubility and suspended solids concentration. For example, high wind speeds may cause pollutants in the water to float to the surface, thus affecting water quality monitoring data. Changes in wind speed may also interfere with the stability of monitoring equipment (such as buoys and sensors), leading to deviations in the collected data. High wind speeds may cause large water surface fluctuations, thus affecting the stability and measurement accuracy of water quality sensors. If the influence of wind speed is ignored, water quality changes caused by wind speed may be misjudged as water quality anomalies. By inputting wind speed characteristics, the error analysis model can assess the impact of wind speed changes on water quality testing and calculate the interference coefficient. This process helps to dynamically adjust the detection threshold, ensuring that the influence of wind speed on water quality testing results is properly handled, thereby improving monitoring accuracy. The impact of rainfall on water quality: Rainfall directly affects the quality of water sources. Heavy rainfall can bring external pollutants (such as sediment, chemicals, etc.), causing rapid changes in water quality, especially in a short period. For example, excessive rainfall washes away groundwater, bringing a large amount of pollutants, and water quality parameters such as suspended solids concentration and chemical oxygen demand may rise rapidly. Rainfall causes changes in water flow and the erosion of pollutants, which may lead to significant fluctuations in water quality testing data in the short term.If these factors are not considered after rainfall, fluctuations in water quality data may be mistakenly interpreted as water quality anomalies. The role of rainfall in error adjustment: By inputting rainfall data, the error analysis model can identify the short-term impact of rainfall on water quality, calculate the interference coefficient, and then determine whether water quality is abnormal based on the adjusted detection threshold. This helps ensure that the water quality monitoring system can correctly identify water quality changes after rainfall and avoid misjudgments. The core objective of the error analysis model is to quantify the impact of various environmental characteristics on water quality detection data. By combining environmental characteristics (temperature, humidity, wind speed, rainfall) with sample detection data, the model can calculate the interference coefficient of each environmental characteristic on the detection data. The interference coefficient measures the magnitude of the deviation of environmental changes from normal water quality parameters. For example, an increase in temperature may lead to lower dissolved oxygen levels; the model can quantify this change as an interference coefficient. By evaluating the interference coefficient of environmental characteristics, the error analysis model can dynamically adjust the water quality detection threshold. With the adjusted threshold, the system can more accurately identify water quality anomalies and avoid misjudgments caused by environmental factors. For example, if the wind speed is high, the system can raise the threshold to eliminate the influence of wind speed changes and ensure that the judgment of water quality is more reliable.

[0049] In one embodiment, the method for predicting the water quality change trend of a water source based on the target features includes:

[0050] Acquire historical sample detection data and corresponding historical environmental data, and extract target features from the historical sample detection data;

[0051] Time series analysis is performed on the target features and historical environmental data to identify the impact parameters and lag characteristics of the historical environmental data on the target features;

[0052] Obtain future environmental forecast data;

[0053] Acquire the current sample detection data, input the current sample detection data, influencing parameters, lag characteristics and environmental prediction data into a preset trend prediction model, predict the water quality change trend under future environmental conditions through the trend prediction model, and output the prediction results.

[0054] Based on the output results, the predicted trend of water quality change is obtained.

[0055] As mentioned above, historical sample data contains information on the changes in water quality indicators (such as dissolved oxygen, chemical oxygen demand, and suspended solids concentration) over time. Extracting target features from this data can help understand the long-term trends and current state of water quality. Historical data provides trend lines and fluctuation patterns for model building, revealing past water quality changes. By using these target features, models can perform pattern recognition on water quality changes, thereby more accurately predicting future water quality trends. Historical data can capture the seasonality and periodicity in water quality changes, helping models distinguish between normal and abnormal fluctuations. Environmental factors (such as temperature, humidity, precipitation, and wind speed) have a significant impact on water quality changes. For example, rainfall may lead to increased water pollution, and temperature changes may affect dissolved oxygen levels in water bodies. Analyzing these historical environmental data can identify which environmental features are significantly correlated with water quality changes and reveal the lag effect between environmental changes and water quality indicators (i.e., the impact of environmental changes on water quality may be delayed). The relationship between environmental factors and water quality may not be immediate. Changes in certain environmental features (such as increased rainfall) may take some time to significantly affect water quality. Therefore, identifying these lag effects allows models to predict water quality changes more accurately, rather than relying solely on current environmental data. Time series analysis, by modeling the trends, seasonality, and periodicity of historical data, helps us understand how environmental data changes over time and thus predict its impact on water quality. Lag characteristics refer to the potential impact of past changes in environmental data on current water quality; time series analysis helps identify the time span and patterns of this impact. By capturing lag effects, time series analysis helps models predict future water quality changes more accurately. For example, identifying the impact of rainfall over the past week on future water quality can improve the accuracy of water quality trend predictions and avoid ignoring the delayed effects of environmental factors. Obtaining future environmental forecast data is crucial for incorporating upcoming environmental changes into water quality trend predictions. For example, information such as future temperature and precipitation provided by weather forecasts helps models understand impending environmental changes and adjust their predictions of water quality changes accordingly. Future environmental conditions are key inputs to predictive models, helping them identify the potential impacts of short-term environmental fluctuations on water quality. By combining future environmental data, models can make advance predictions about water quality changes. Combining environmental data with future predictions can provide valuable information for water quality management and emergency response, improving the timeliness and scientific rigor of decision-making. Current sample testing data represents the true state of water quality at the present moment, reflecting the immediate water quality status of the water source. Using this data as model input ensures that the prediction results more accurately reflect the actual water quality conditions and allows for reasonable inferences about future water quality changes when combined with other factors (such as environmental data and lag characteristics). Current testing data provides immediate feedback on water quality, helping the model compare and adjust prediction results, ensuring that water quality trends reflect the actual situation.As an immediate input, it effectively corrects prediction errors based on historical data. The model integrates historical data, environmental prediction data, and current water quality data to comprehensively analyze the impact of various factors on water quality changes. Through training and optimization, the model can identify complex causal relationships and predict water quality trends under specific future environmental conditions. Using a pre-set trend prediction model, it can maintain accuracy in predicting water quality changes even under dynamic environmental conditions. This approach avoids the limitations of traditional static models, can cope with complex natural environmental fluctuations, and improves the reliability of water quality monitoring systems.

[0056] In one embodiment, the method for determining whether the water quality meets the early warning conditions based on the prediction results includes:

[0057] Obtain the predicted trend of water quality changes;

[0058] Calculate the magnitude of change in the target characteristics based on the described water quality change trend;

[0059] Based on the magnitude of the change, determine whether the magnitude of the change in the target feature is within a preset range;

[0060] When the change in the target characteristic exceeds the preset range, the water quality is determined to meet the warning conditions.

[0061] When the change range of the target feature is within a preset range, the rate of change of the target feature is calculated;

[0062] Based on the rate of change, determine whether the rate of change of the target feature is within a preset rate range;

[0063] When the rate of change of the target feature exceeds the preset rate range, the water quality change trend is determined to meet the warning conditions.

[0064] As mentioned above, predicting future water quality trends (such as the rise and fall of indicators like dissolved oxygen, pH, and chemical oxygen demand) provides the foundation for early warning systems. Water quality trends are typically predicted based on historical data, environmental data, and current monitoring data, using time series analysis, regression models, or machine learning methods. The predicted water quality trend reflects the expected trajectory of water quality over a future period. By predicting these trends, it's possible to anticipate the risk of water quality deterioration. Trend prediction helps identify potential water quality anomalies, prevent possible pollution or environmental disasters, and allow for proactive measures to ensure the health and safety of water bodies. Predicting water quality trends provides a forward-looking perspective for early warning systems. If certain water quality indicators are predicted to exceed standards or deteriorate, warnings can be issued in advance, allowing for monitoring or intervention. Through predicting future water quality changes, water quality management departments can make more scientific and rational decisions based on data, addressing not only current water quality issues but also potential water quality risks. The magnitude of change refers to the maximum fluctuation range of a specific water quality indicator (target characteristic) within the prediction period. For example, a large fluctuation in a water quality indicator may indicate water instability or an increased risk of pollution. This step assesses the severity of water quality changes by calculating the maximum range of variation for water quality indicators (such as dissolved oxygen concentration and pH value). Amplitude calculation helps identify abnormal fluctuations in water quality. When the amplitude of water quality changes exceeds a preset range, it signifies a potential drastic change in water quality, indicating a possible risk of pollution or other environmental hazards. Amplitude measurement is a crucial indicator of whether water quality is abnormal. If the amplitude of water quality changes exceeds a preset threshold, it indicates a drastic fluctuation in water quality, which is usually a signal of pollution or changes in environmental conditions. At this point, the system will issue an early warning, reminding management personnel to take timely measures. Amplitude calculation allows for quantitative analysis of water quality fluctuations, helping decision-makers determine whether further investigation and treatment are needed, avoiding missing potential water quality crises. This step determines whether the water quality change is within an acceptable range by judging the amplitude. The preset amplitude range is set based on historical data experience and represents the fluctuation range of water quality under normal changing conditions. If the amplitude of a certain indicator exceeds this range, it indicates an abnormality in water quality. The preset range helps distinguish between normal and abnormal fluctuations. In the natural environment, water quality may experience normal fluctuations (such as seasonal variations). However, if these fluctuations exceed the normal range, it may indicate pollution or other unforeseen events. By comparing the magnitude of these changes with preset ranges, it is possible to effectively determine whether abnormal changes in water quality exist and to promptly identify potential water pollution or other anomalies. This helps prevent environmental disasters and avoid health and ecological risks caused by water quality deterioration. The rate of change refers to how quickly a water quality indicator (target characteristic) changes per unit of time. Rapid changes may indicate rapid deterioration of water quality, such as a rapid increase in chemical oxygen demand (COD) or a sharp decrease in dissolved oxygen.Calculating the rate of change allows for a more precise assessment of water quality dynamics. Some water quality changes may be temporary or slow-moving, but certain extreme pollution events or sudden environmental changes can lead to rapid deterioration. Calculating the rate of change helps distinguish between slow and rapid changes, enabling timely identification of rapid anomalies. It facilitates the detection of rapid water quality changes, especially during sudden pollution events or under extreme weather conditions. Monitoring the rate of water quality change allows for rapid response and timely warnings, preventing major environmental accidents. This step compares the calculated rate of change with a preset rate range to determine if the water quality change is within a reasonable range. Preset rate ranges are typically based on experience, historical data, and environmental characteristics. A rate exceeding the range indicates an abnormal change in water quality, potentially requiring appropriate control measures. Setting a rate range helps distinguish between normal water quality changes (such as slow fluctuations in seasonal variations) and abnormal changes (such as sudden pollution or environmental changes). By combining characteristics such as the trend, magnitude, and rate of water quality change, the final determination is whether the water quality meets the warning criteria. If the magnitude or rate of change exceeds the preset range, the water quality is deemed abnormal, meeting the warning criteria. Relying solely on a single characteristic may not fully reflect the true state of water quality. Comprehensive assessment helps avoid inaccurate early warnings caused by a single factor, ensuring a more efficient and reliable water quality management system.

[0065] In one embodiment, the method further includes:

[0066] Acquire historical sample detection data and corresponding historical environmental data, and extract target features from the historical sample detection data;

[0067] Time series analysis is performed on the target features and historical environmental data to identify the change patterns of the target features under different historical environmental data conditions;

[0068] Based on the identification results, a frequency analysis model is constructed to analyze the change patterns under different environmental data conditions, and the frequency of abnormal judgment of the sample detection data is determined according to the change patterns.

[0069] Acquire current environmental data, input the current environmental data into the frequency analysis model, and output the frequency of abnormal judgment of the sample detection data under the current environmental data conditions through the frequency analysis model.

[0070] As mentioned above, historical sample detection data consists of the detection results of certain key indicators or signals, which may be sampled values ​​from certain devices, sensors, or systems. These data contain information about the state of the system or device at different points in time. Historical environmental data refers to the external environmental conditions at the time these historical sample detection data were collected. These environmental conditions may affect the performance of the sample detection data, including factors such as temperature, humidity, pressure, and light. Different environmental conditions may lead to significant differences in the performance of the detection data; therefore, combining environmental data helps to capture such changes. By combining historical sample and environmental data, the system can construct a comprehensive view of the target features, providing an accurate foundation for subsequent analysis and modeling. Target features can refer to key indicators that can reveal data anomalies or specific patterns. For example, statistical characteristics such as the mean, variance, maximum, minimum, and trend of the detection data, or certain complex frequency domain features (such as frequency components, power spectrum, etc.). These features can usually be extracted using statistical methods, signal processing techniques (such as Fourier transform, wavelet transform, etc.), or machine learning algorithms. By extracting target features, the most critical information can be extracted from complex data, reducing data redundancy and focusing on the parts that best reflect system anomalies. The selection and extraction of target features are crucial to model accuracy, as these features determine the capabilities of subsequent analysis and prediction. Extracted features help us identify behavioral patterns in sample data and provide more concise and representative data input for subsequent analysis. Time series analysis models the patterns of data changes over time to identify regularities and trends. In this case, time series analysis can reveal how target features fluctuate over time under different environmental conditions. Under multiple environmental conditions, the changes in target features may exhibit different patterns. Time series analysis can identify these patterns, providing a useful basis for modeling. The changing patterns of target features may differ under different environmental conditions; time series analysis helps to uncover the time dependencies hidden in the data and capture the dynamic characteristics of the system over time. By identifying change patterns, more accurate anomaly detection can be made under different environmental conditions. Through time series analysis, we can understand the dynamic change patterns under different environmental conditions, thus providing strong support for subsequent anomaly detection and frequency analysis. Frequency analysis typically refers to analyzing the frequency components of a signal to identify frequency patterns within the signal. In this case, the frequency analysis model will attempt to find the frequency distribution of sample detection data under different environmental conditions based on the identified change patterns. This model can be constructed using frequency domain analysis methods such as Fourier transform and wavelet transform, or using machine learning methods such as clustering algorithms and regression analysis. The frequency distribution of data under environmental conditions can provide additional information. Through frequency analysis, periodic changes or sudden fluctuations in the data can be detected, which is particularly important for anomaly detection.If the frequency of target features varies significantly under different environments, frequency analysis models can help identify abnormal and normal patterns, thereby improving the accuracy of the judgment. Frequency analysis models can reveal periodic or regular changes in data, providing additional evidence for anomaly detection and contributing to improved model accuracy. Real-time collected environmental data represents the current external environmental conditions, such as temperature and humidity. Inputting this current environmental data into a pre-trained frequency analysis model predicts the anomaly detection frequency of sample detection data under the current environmental conditions. The anomaly detection frequency output by the frequency analysis model refers to the probability or likelihood that the sample detection data is abnormal under the current environmental conditions. By inputting real-time environmental data into the model, dynamic anomaly detection results can be obtained. The advantage of this method is its ability to adapt to different environmental changes, monitor data anomalies in real time, and react promptly.

[0071] In one embodiment, after the step of generating a water quality treatment strategy and sending early warning information based on the prediction results to the management terminal, the method further includes:

[0072] Obtain water source sample testing data after water quality treatment strategies are implemented;

[0073] Based on the time series, the water source sample test data after the water quality treatment strategy is compared with the initial water source sample test data to extract the change parameters of the target risk parameters;

[0074] Based on the changes in the target risk parameters, determine whether the water treatment strategy meets the replacement conditions;

[0075] If the changing parameter is less than the preset changing threshold, then the water treatment strategy is determined to meet the replacement condition.

[0076] As mentioned above, water source sample testing data refers to water quality testing data collected after the application of water treatment strategies. This data typically includes various water quality indicators, such as pH, turbidity, dissolved oxygen, bacterial content, and chemical oxygen demand (COD). Water treatment strategies are usually designed to improve water quality issues, such as removing harmful substances and adjusting the pH of the water. Obtaining post-treatment data refers to re-testing the water source after the implementation of a specific treatment plan to obtain these indicator data for subsequent analysis. Time series analysis identifies trends and patterns by comparing data changes at different time points. In this step, water source sample data before and after treatment are compared. Initial water source sample data refers to the raw water quality data before any treatment was implemented. Post-treatment sample data refers to water quality data from the same or similar time period after water treatment. Target risk parameters refer to key factors in water quality indicators, such as pH, dissolved oxygen, heavy metal content, and pathogenic microorganism content, all of which directly affect water safety and drinking water health standards. By comparing initial source water data with treated data, specific changes are extracted, which typically indicate improvement or deterioration in water quality. Change parameters are the changes in certain key water quality indicators in the sample data before and after treatment. For example, a decrease in certain indicators indicates good water quality treatment, while a increase may indicate a problem. If the change parameters do not reach preset standards or thresholds, the water quality treatment strategy may need to be changed. For example, if the concentration of certain pollutants remains high after treatment, or if certain important water quality indicators do not change significantly, the current treatment strategy may be ineffective or have limited effect. Monitoring changes in water quality indicators helps determine the effectiveness of the current treatment strategy. If the target risk parameter does not change significantly after water quality treatment, the water quality improvement is not significant, and the strategy may need to be adjusted. If the change parameter is less than the threshold, the water quality improvement is not significant, and the treatment strategy may need to be adjusted or changed. These thresholds can be set based on water quality safety standards, actual water quality improvement needs, or historical experience. The thresholds must be set scientifically and reasonably to ensure that problems in water quality treatment can be detected in a timely manner.

[0077] In one embodiment, before the step of determining whether the sample test data of the water source meets the abnormal conditions, the method further includes:

[0078] Identify the target risk parameters of the sample detection data;

[0079] The target risk parameters are classified, and overlapping signals are detected for each type of target risk object.

[0080] Based on the results of the overlapping signal detection, it is determined whether the target risk object contains any interfering elements;

[0081] When the target risk object is accompanied by interfering factors, the type of the interfering factors is identified;

[0082] Based on the type of interfering substance, the overlapping signals are separated, and the content of the interfering substance is inferred based on the signal of the interfering substance;

[0083] Compensation parameters for the target risk substance are generated based on the content of interfering substances.

[0084] The content of the target risk substance is adjusted based on the compensation parameters.

[0085] As mentioned above, target risk parameter identification involves determining which water quality indicators in water quality sample testing data are critical and potentially risky. For example, heavy metals, bacterial content, and chemical oxygen demand (COD) are likely target risk parameters requiring special attention. Identifying target risk parameters is the first step in data analysis, helping to focus on the most critical indicators and thus concentrate efforts on in-depth analysis and processing of these parameters. By accurately identifying target risk parameters, the system can process water quality monitoring data in a targeted manner, ensuring attention is paid to key indicators that may pose threats to water quality safety and human health. Target risk parameters are categorized according to their characteristics. For example, some indicators may be related to toxic chemicals, while others may be related to microorganisms or physical properties (such as turbidity). During measurement, signals from certain risk substances may overlap, leading to data confusion. For example, certain chemicals or microorganisms may simultaneously affect the same water quality parameter. Overlapping signals can lead to data misunderstanding or misjudgment; therefore, it is necessary to identify and analyze such mixed signals by detecting overlapping signals to ensure data accuracy. Overlap signal detection improves the precision of data analysis, avoids interference between different substances, and ensures the correct identification and analysis of target risk substances. By detecting overlapping signals, the system can determine whether other substances (interference agents) affect the detection of the target risk substance. These interference agents may cause the signal reading to deviate from the true value. In actual measurements, other chemical substances or physical factors in the environment may interfere with the detection of the target substance. Therefore, identifying and distinguishing interference agents is crucial to ensuring the accuracy of measurement results. Identifying interference agents can help eliminate error sources, thereby improving the reliability and accuracy of detection results. After confirming the presence of interference agents, the next step is to determine the specific type of interference agent. For example, certain organic compounds or minerals may affect the detection of heavy metals. Different types of interference agents may have different effects on the signal, and identifying the type of interference agent can provide necessary information for subsequent signal separation and compensation. Identifying the type of interference agent can help pinpoint the root cause of the problem and provide effective guidance for subsequent processing and correction. Once the interference agent and its type are identified, the next step is to separate the interference signal from the target signal using specific algorithms or signal processing techniques. Methods may include frequency analysis, filtering, and other techniques. By combining the separated interference signal with certain mathematical models and experimental data, the content of the interference agent can be estimated. Signal separation and content estimation help to accurately assess the true content of the target risk substance and avoid the influence of interference agents on the data. This allows for a more accurate recovery of the actual content of the target risk substance. By separating the interference signal and inferring the content of the interference substance, the original data can be accurately corrected, ensuring that the estimated content of the target risk substance is closer to the true value. Once the content of the interference substance is inferred, compensation parameters can be generated based on this information to correct the content of the target risk substance.The presence of interfering substances may lead to underestimation or overestimation of the measured values ​​of target risk substances. Therefore, compensation is needed based on the concentration of interfering substances to ensure that the final data accurately reflects the water quality. By generating compensation parameters, measurement errors caused by interfering substances can be effectively corrected, improving the accuracy of the test results. The compensation parameters are applied to correct the concentration of target risk substances to offset the influence of interfering substances.

[0086] As mentioned above, real-time monitoring and data analysis not only detect the current water quality status but also predict future water quality trends. This forward-looking judgment allows the system to identify potential water quality problems in advance, avoiding the potential reaction lag in traditional monitoring methods, thus providing managers with more accurate risk assessment and early warning information. By extracting features from sample data and combining them with historical data and environmental factors, predictive models of water quality changes can be generated in real time. This predictive capability significantly improves the response speed of the monitoring system, enabling managers to take proactive measures and effectively reduce the risks caused by fluctuations in pollutant concentrations. By integrating multiple data sources (such as water quality sample test results and environmental factor data), multi-dimensional risk assessment is achieved. This data fusion approach avoids the limitations of single sensors due to environmental interference or technological constraints, and can more comprehensively and accurately reflect the true water quality status of the water source, reducing errors caused by sensor limitations.

[0087] Reference Figure 3 This application also provides an intelligent detection system for key risk substances samples in water sources, including:

[0088] Module 1 is used to acquire sample test data of water sources in real time;

[0089] The first judgment module 2 is used to determine whether the sample detection data of the water source meets the abnormal conditions;

[0090] The parsing module 3 is used to parse the sample detection data when the water source meets the abnormal conditions, identify the target risk parameters and sample location based on the sample detection data, and generate risk data based on the target risk parameters and sample location and send it to the management terminal.

[0091] Extraction module 4 is used to extract target features from the sample detection data when the water source does not meet the abnormal conditions;

[0092] Prediction module 5 is used to predict the water quality change trend of the water source based on the target features;

[0093] The second judgment module 6 is used to determine whether the water quality meets the early warning conditions based on the prediction results.

[0094] The sending module 7 is used to generate a water quality treatment strategy and early warning information based on the prediction results and send them to the management terminal when the water quality meets the early warning conditions.

[0095] As described above, it is understood that each component of the intelligent detection system for key risk materials in water sources proposed in this application can realize the function of any of the intelligent detection methods for key risk materials in water sources as described above, and the specific structure will not be described in detail.

[0096] Reference Figure 4 This application also provides a computer device, which may be a server, and its internal structure may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores monitoring data and other data. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an intelligent detection method for key risk samples in water sources.

[0097] The processor described above executes the intelligent detection method for key risk materials samples in water sources, including: acquiring sample detection data of the water source in real time; determining whether the sample detection data of the water source meets abnormal conditions; when the water source meets abnormal conditions, parsing the sample detection data, identifying target risk parameters and sample locations based on the sample detection data, generating risk data based on the target risk parameters and sample locations, and sending it to the management terminal; when the water source does not meet abnormal conditions, extracting target features from the sample detection data; predicting the water quality change trend of the water source based on the target features; determining whether the water quality meets the early warning conditions based on the prediction results; when the water quality meets the early warning conditions, generating a water quality treatment strategy and early warning information based on the prediction results and sending it to the management terminal.

[0098] One embodiment of this application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements an intelligent detection method for key risk samples in water sources, including the following steps: acquiring sample detection data of the water source in real time; determining whether the sample detection data of the water source meets abnormal conditions; when the water source meets abnormal conditions, parsing the sample detection data, identifying target risk parameters and sample locations based on the sample detection data, generating risk data based on the target risk parameters and sample locations, and sending it to a management terminal; when the water source does not meet abnormal conditions, extracting target features from the sample detection data; predicting the water quality change trend of the water source based on the target features; determining whether the water quality meets early warning conditions based on the prediction results; when the water quality meets early warning conditions, generating a water quality treatment strategy and early warning information based on the prediction results and sending it to a management terminal.

[0099] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0100] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0101] The above description is only a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural changes made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for intelligent detection of key risk substances in water source areas, characterized in that, The method includes: Real-time acquisition of water source sample testing data; Determine whether the sample test data of the water source meets the abnormal conditions; When the water source meets the abnormal conditions, the sample detection data is analyzed, the target risk parameters and sample location are identified based on the sample detection data, and risk data is generated based on the target risk parameters and sample location and sent to the management terminal. When the water source does not meet the abnormal conditions, the target features of the sample detection data are extracted; Predict the water quality change trend of the water source based on the target characteristics; Determine whether the water quality meets the early warning conditions based on the prediction results; When the water quality meets the early warning conditions, a water quality treatment strategy and early warning information are generated based on the prediction results and sent to the management terminal. After the step of determining whether the sample detection data of the water source meets the abnormal conditions, and before the step of determining when the water source meets the abnormal conditions, the method further includes: acquiring environmental data of the sample location, extracting environmental features from the environmental data, wherein the environmental features include temperature features, humidity features, wind speed features, and rainfall features; constructing an error analysis model, inputting the environmental features and sample detection data into the error analysis model, evaluating the interference coefficient of the environmental features on the sample detection data within a specific time period through the error analysis model, and outputting the evaluation result, wherein the interference coefficient is used to evaluate the magnitude of the deviation of water quality parameters from normal values ​​caused by the environmental features; adjusting the detection threshold based on the evaluation result using the interference coefficient to obtain the adjusted detection threshold; determining whether the water source meets the abnormal conditions based on the adjusted detection threshold; and determining that the sample detection data of the water source meets the abnormal conditions when the sample detection data is greater than the adjusted detection threshold. Before the step of determining whether the sample detection data of the water source meets the abnormal conditions, the method further includes: identifying the target risk parameters of the sample detection data; identifying the types of the target risk parameters and performing overlap signal detection for each type of target risk substance; determining whether there are interfering substances in the target risk substance based on the result of the overlap signal detection; identifying the type of interfering substance when there are interfering substances in the target risk substance; separating the overlap signal based on the type of interfering substance and inferring the content of interfering substance based on the signal of the interfering substance; generating compensation parameters for the target risk substance based on the content of the interfering substance; and adjusting the content of the target risk substance based on the compensation parameters.

2. The intelligent detection method for key risk samples in water source areas according to claim 1, characterized in that, The method for predicting the water quality change trend of the water source based on the target features includes: Acquire historical sample detection data and corresponding historical environmental data, and extract target features from the historical sample detection data; Time series analysis is performed on the target features and historical environmental data to identify the impact parameters and lag characteristics of the historical environmental data on the target features; Obtain future environmental forecast data; Acquire the current sample detection data, input the current sample detection data, influencing parameters, lag characteristics and environmental prediction data into a preset trend prediction model, predict the water quality change trend under future environmental conditions through the trend prediction model, and output the prediction results. Based on the output results, the predicted trend of water quality change is obtained.

3. The intelligent detection method for key risk samples in water source areas according to claim 2, characterized in that, The method for determining whether the water quality meets the early warning conditions based on the prediction results includes: Obtain the predicted trend of water quality changes; Calculate the magnitude of change in the target characteristics based on the described water quality change trend; Based on the magnitude of the change, determine whether the magnitude of the change in the target feature is within a preset range; When the change in the target characteristic exceeds the preset range, the water quality is determined to meet the warning conditions. When the change range of the target feature is within a preset range, the rate of change of the target feature is calculated; Based on the rate of change, determine whether the rate of change of the target feature is within a preset rate range; When the rate of change of the target feature exceeds the preset rate range, the water quality change trend is determined to meet the warning conditions.

4. The intelligent detection method for key risk samples in water source areas according to claim 2, characterized in that, The method further includes: Acquire historical sample detection data and corresponding historical environmental data, and extract target features from the historical sample detection data; Time series analysis is performed on the target features and historical environmental data to identify the change patterns of the target features under different historical environmental data conditions; Based on the identification results, a frequency analysis model is constructed to analyze the change patterns under different environmental data conditions, and the frequency of abnormal judgment of the sample detection data is determined according to the change patterns. Acquire current environmental data, input the current environmental data into the frequency analysis model, and output the frequency of abnormal judgment of the sample detection data under the current environmental data conditions through the frequency analysis model.

5. The intelligent detection method for key risk samples in water source areas according to claim 1, characterized in that, After the step of generating a water quality treatment strategy and sending early warning information based on the prediction results to the management terminal, the method further includes: Obtain water source sample testing data after water quality treatment strategies are implemented; Based on the time series, the water source sample test data after the water quality treatment strategy is compared with the initial water source sample test data to extract the change parameters of the target risk parameters; Based on the changes in the target risk parameters, determine whether the water treatment strategy meets the replacement conditions; If the changing parameter is less than the preset changing threshold, then the water treatment strategy is determined to meet the replacement condition.

6. An intelligent detection system for key risk substances in water sources, used in the method described in any one of claims 1-5, characterized in that, include: The acquisition module is used to acquire sample test data of water sources in real time; The first judgment module is used to determine whether the sample test data of the water source meets the abnormal conditions; The analysis module is used to analyze the sample detection data when the water source meets the abnormal conditions, identify the target risk parameters and sample location based on the sample detection data, and generate risk data based on the target risk parameters and sample location and send it to the management terminal. The extraction module is used to extract target features from the sample detection data when the water source does not meet the abnormal conditions. The prediction module is used to predict the water quality change trend of the water source based on the target features; The second judgment module is used to determine whether the water quality meets the early warning conditions based on the prediction results. The sending module is used to generate a water quality treatment strategy and early warning information based on the prediction results and send them to the management terminal when the water quality meets the early warning conditions.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images