Water affairs intelligent alarm method and device based on water affairs big model

Abstract

The present invention relates to the technical field of Internet of Things, and discloses a water affairs intelligent alarm method and device based on a water affairs big model, the method comprising: constructing an IOT sensor group of a water treatment component, calculating the real-time coefficient of the IOT sensor group, and when the real-time coefficient meets the preset standard real-time coefficient, collecting the water output index data of the water treatment component corresponding to the water output index; constructing a sequence state curve of the water output index; using a trained water affairs early warning model to analyze the sequence index analysis value of the water output index, and based on the sequence index analysis value, constructing a state analysis curve of the water output index; fitting the sequence state curve and the state analysis curve to obtain an index state curve, calculating the index abnormality coefficient of the index state curve, and constructing an abnormal early warning report of a water affairs scene based on the index abnormality coefficient; constructing a multimodal alarm strategy for the abnormal early warning report, and executing an intelligent alarm for a water affairs scene. The present invention can improve the intelligent alarm effect for a water affairs scene.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a water affairs intelligent alarm method and device based on a water affairs big model. Background Art

[0002] Smart water alarm is a process of alarming water anomalies that integrates Internet of Things (IoT) technology, data analysis, machine learning, and communication technology, aiming to improve the efficiency and safety of water management.

[0003] At present, water affairs intelligent alarm mainly realizes intelligent alarm by collecting water affairs data of water affairs scenes in real time, analyzing the water discharge indicators of water affairs scenes through water affairs data, and comparing the water discharge indicators with the preset standard water discharge indicator thresholds. This method does not make full use of the hidden information such as seasonal patterns and trend changes of water discharge indicators in historical data, and misses the opportunity to improve the prediction accuracy through historical data analysis, which leads to the inaccuracy of water affairs intelligent alarm for water affairs scenes. Summary of the invention

[0004] The present invention provides a water affairs intelligent alarm method and device based on a water affairs big model, the main purpose of which is to improve the intelligent alarm effect on water affairs scenes.

[0005] To achieve the above object, the present invention provides a water affairs intelligent alarm method based on a water affairs big model, comprising:

[0006] Acquire a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate a real-time coefficient of the IOT sensor group, and when the real-time coefficient meets a preset standard real-time coefficient, collect water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group;

[0007] Based on the water output index data, construct a sequence state curve of the water output index;

[0008] Based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, and based on the sequence index analysis value, a state analysis curve of the water output index is constructed;

[0009] Fitting the sequence state curve and the state analysis curve to obtain an indicator state curve, and based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, calculating the indicator abnormality coefficient of the indicator state curve, and constructing an abnormal warning report of the water affairs scene based on the indicator abnormality coefficient;

[0010] A multimodal alarm strategy for the abnormal warning report is constructed, and the multimodal alarm strategy is used to execute intelligent alarm for the water affairs scenario.

[0011] Optionally, the IOT sensor group for constructing the water treatment component includes:

[0012] Analyzing monitoring requirements of the water treatment components;

[0013] According to the monitoring requirements, configure the target sensor of the water treatment component;

[0014] Based on the component characteristics corresponding to the water treatment component, construct a network layout of the target sensor;

[0015] Based on the network layout, an IOT sensor group of the water treatment component is constructed.

[0016] Optionally, the calculating the real-time coefficient of the IOT sensor group includes:

[0017] Determining a data path of the IOT sensor group;

[0018] Based on the data path, analyzing the response time of the IOT sensor group, wherein the response time includes data collection time, data transmission time, data processing time and data display time;

[0019] Based on the response time, the real-time coefficient of the IOT sensor group is calculated using the following formula:

[0020] ;

[0021] in, Represents the real-time coefficient of the IOT sensor group, Indicates the number of sensors in the IOT sensor group, Indicates the IOT sensor group The data collection time of each sensor, Indicates the IOT sensor group The data transmission time of each sensor, Indicates the IOT sensor group The data processing time of each sensor is Indicates the IOT sensor group The data display time of each sensor, Indicates the IOT sensor group The user expected response time of each sensor.

[0022] Optionally, constructing a sequence state curve of the water output index based on the water output index data includes:

[0023] Preprocessing the water outlet index data to obtain preprocessed index data;

[0024] Serializing the preprocessing indicator data to obtain sequence indicator data, and determining the time node of the sequence indicator data;

[0025] Based on the sequence indicator data, marking the node indicator concentration of the time node;

[0026] The time nodes and the node indicator concentrations are used to construct a sequence state curve of the water output indicator.

[0027] Optionally, analyzing the sequence indicator analysis value of the water output indicator based on the sequence state curve and the water output indicator data using a trained water affairs early warning model includes:

[0028] Performing a stationarity test on the sequence index data corresponding to the water discharge index data to obtain data stationarity, wherein the stationarity test includes trend test, seasonal test and unit root test;

[0029] When the data stability does not meet the preset standard stability, performing differential processing on the sequence index data to obtain stable index data;

[0030] Extracting the time series characteristics of the stable index data and marking the prediction starting point of the sequence state curve;

[0031] Determine the model order of the water affairs early warning model, wherein the model order includes autoregressive order, difference order, and sliding average order. Based on the time series characteristics, the prediction starting point, and the model order, use the water affairs early warning model to analyze the sequence indicator analysis value of the water output indicator.

[0032] Optionally, performing a stability test on the sequence indicator data corresponding to the water output indicator data to obtain data stability includes:

[0033] Constructing a time series graph of the sequence indicator data;

[0034] Based on the time series graph, marking the observed values ​​of the sequence indicator data;

[0035] Based on the observed values, the data slope of the sequence index data is calculated using the following formula:

[0036] ;

[0037] in, represents the data slope of the series indicator data, Indicates the sequence index data The observed value of data points, Indicates the sequence index data The observed value of data points, The number of data points representing the series indicator data;

[0038] Based on the time series graph, calculating the seasonal kurtosis of the sequence indicator data;

[0039] Identifying the unit root of the sequence indicator data;

[0040] The data stationarity of the sequence indicator data is determined based on the data slope, the seasonal kurtosis and the unit root.

[0041] Optionally, the calculating the indicator abnormality coefficient of the indicator status curve based on the scene status corresponding to the water service scene includes:

[0042] Based on the scene state corresponding to the water affairs scene, determine the ideal value of the water output indicator corresponding to the water affairs scene;

[0043] Based on the ideal value of the indicator and the indicator state curve, constructing an indicator error curve of the water affairs scenario;

[0044] identifying curve fluctuations of the indicator error curve;

[0045] The fluctuation coefficient of the curve fluctuation is calculated, and based on the fluctuation coefficient, the indicator abnormality coefficient of the indicator error curve is determined.

[0046] Optionally, the calculating the fluctuation coefficient of the curve fluctuation includes:

[0047] Identifying the fluctuation amplitude and fluctuation duration of the curve fluctuation;

[0048] Based on the fluctuation amplitude and the fluctuation duration, the fluctuation coefficient of the curve fluctuation is calculated using the following formula:

[0049] ;

[0050] in, The coefficient of fluctuation represents the fluctuation of the curve, represents the fluctuation amplitude of the curve fluctuation pair, Indicates the error curve of the corresponding indicator of curve fluctuation, Indicates the angular frequency of the curve fluctuation corresponding to the indicator error curve, Indicates the peak value of the fluctuation corresponding to the fluctuation amplitude of the curve. Indicates the fluctuation valley value of the curve fluctuation corresponding to the fluctuation amplitude, Indicates the fluctuation duration of the curve fluctuation in the indicator error curve corresponding to the curve fluctuation.

[0051] Optionally, the multi-modal alarm strategy for constructing the abnormal warning report includes:

[0052] Analyze the scenario requirements of the abnormal warning report corresponding to the water affairs scenario;

[0053] Based on the scenario requirements, analyzing the warning emergency coefficient of the abnormal warning report;

[0054] Locking the warning object of the abnormal warning report and constructing a warning method for the warning object;

[0055] Based on the warning urgency coefficient, the warning object and the warning method, a multimodal alarm strategy for the abnormal warning report is constructed.

[0056] In order to solve the above problems, the present invention also provides a water affairs intelligent alarm device based on a water affairs big model, the system comprising:

[0057] An index data acquisition module is used to obtain a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate a real-time coefficient of the IOT sensor group, and when the real-time coefficient meets a preset standard real-time coefficient, collect water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group;

[0058] A state curve construction module, used to construct a sequence state curve of the water output index based on the water output index data;

[0059] An analysis curve construction module is used to analyze the sequence indicator analysis value of the water output indicator based on the sequence state curve and the water output indicator data using a trained water affairs early warning model, and to construct a state analysis curve of the water output indicator based on the sequence indicator analysis value;

[0060] An early warning report construction module is used to fit the sequence state curve and the state analysis curve to obtain an indicator state curve, calculate an indicator abnormality coefficient of the indicator state curve based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, and construct an abnormal early warning report for the water affairs scene based on the indicator abnormality coefficient;

[0061] The intelligent alarm module is used to construct a multimodal alarm strategy for the abnormal warning report and use the multimodal alarm strategy to execute intelligent alarm for the water service scenario.

[0062] The present invention can improve the automation level and efficiency of water treatment by constructing an IOT sensor group of the water treatment component; the present invention evaluates the response speed and efficiency of the system by calculating the real-time coefficient of the IOT sensor group; the embodiment of the present invention can improve the reliability of data collection and analysis by collecting the water output index data of the water treatment component corresponding to the water output index based on the IOT sensor group when the real-time coefficient meets the preset standard real-time coefficient, thereby improving the performance and safety of the water treatment system; the embodiment of the present invention constructs a sequence state curve of the water output index based on the water output index data, which can be used as a basis for subsequent water output index analysis. Furthermore, the present invention constructs a sequence state curve based on the sequence index analysis value. The state analysis curve of the water output index can intuitively display the prediction results of the model for the water output index. The accuracy of the prediction of the water output index is improved by constructing the state analysis curve based on the analysis of historical data. Furthermore, the present invention can connect the water output index state collected by the sensor and the predicted water output index state by fitting the sequence state curve and the state analysis curve to obtain the index state curve, so as to obtain a more comprehensive water output index analysis and improve the monitoring effect of water quality. Finally, the embodiment of the present invention can ensure that relevant personnel can be quickly notified in a variety of ways when an abnormal situation occurs by constructing a multi-modal alarm strategy for the abnormal warning report, thereby improving the response speed and efficiency. Therefore, the water affairs intelligent alarm method and device based on the water affairs big model proposed in the present invention can improve the intelligent alarm effect of water affairs scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic flow chart of a water affairs intelligent alarm method based on a water affairs big model provided in one embodiment of the present invention;

[0064] Figure 2 A functional module diagram of a water affairs intelligent alarm device based on a water affairs big model provided by an embodiment of the present invention;

[0065] Figure 3 A schematic diagram of the structure of an electronic device of a water affairs intelligent alarm device based on a water affairs large model provided by an embodiment of the present invention;

[0066] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0068] The embodiment of the present application provides a water affairs intelligent alarm method based on a water affairs big model. The execution subject of the water affairs intelligent alarm method based on the water affairs big model includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the water affairs intelligent alarm method based on the water affairs big model can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0069] Reference Figure 1 FIG. 1 is a flow chart of a water affairs intelligent alarm method based on a water affairs big model provided by an embodiment of the present invention. In this embodiment, the water affairs intelligent alarm method based on a water affairs big model includes:

[0070] S1. Acquire the water treatment components of the water service scenario, construct an IOT sensor group of the water treatment components, calculate the real-time coefficient of the IOT sensor group, and when the real-time coefficient meets the preset standard real-time coefficient, collect the water output index data corresponding to the water output index of the water treatment components based on the IOT sensor group.

[0071] It should be explained that the water treatment components in the water affairs scenario refer to equipment and systems used to treat and improve water quality. These components usually function in sewage treatment plants, drinking water treatment plants or other water treatment facilities to ensure that the effluent meets environmental protection standards or is suitable for specific purposes.

[0072] Exemplarily, the water treatment components can be pretreatment components: these components are used for preliminary treatment of incoming water to remove large particles and suspended matter, and common pretreatment components include grids, screens, grit chambers and other components; they can also be primary treatment components: primary treatment aims to remove settleable solid matter, and common components include sedimentation tanks, clarification tanks, flotation equipment and other components; they can also be secondary treatment components: secondary treatment further removes organic matter and microorganisms in the water, and these components may include biological filters, aeration tanks in activated sludge methods, membrane bioreactors (MBRs) and other components; they can also be advanced treatment components: used to treat difficult-to-degrade organic matter and specific pollutants, which may include ozone oxidation, ultraviolet disinfection, activated carbon adsorption, ion exchange and other components; they can also be sludge treatment components: these components are used to treat sludge generated during water treatment, including sludge concentration, sludge stabilization, sludge drying and other components.

[0073] The present invention can improve the automation level and efficiency of water treatment by constructing the IOT sensor group of the water treatment component. Wherein, the IOT sensor group refers to a series of sensor devices connected to the Internet of Things, which are deployed in a specific environment to collect and transmit data.

[0074] In detail, the IOT sensor group for constructing the water treatment component includes:

[0075] Analyzing monitoring requirements of the water treatment components;

[0076] According to the monitoring requirements, configure the target sensor of the water treatment component;

[0077] Based on the component characteristics corresponding to the water treatment component, construct a network layout of the target sensor;

[0078] Based on the network layout, an IOT sensor group of the water treatment component is constructed.

[0079] Among them, the monitoring requirements refer to the target requirements for monitoring water treatment components, including the parameters that need to be monitored (such as pH value, dissolved oxygen, turbidity, chemical oxygen demand COD, ammonia nitrogen, total phosphorus, etc.), monitoring frequency, data accuracy and other requirements, and the target sensor refers to the selection of appropriate sensors according to the requirements. The sensor should have good waterproof performance, stability, anti-interference ability and a long service life. Commonly used sensors include water quality sensors (such as pH sensors, turbidity sensors, conductivity sensors), flow sensors, pressure sensors, liquid level sensors and other sensors. The network layout refers to the physical connection method between each device in the network. The component characteristics refer to the specific characteristics or functions of the water treatment component during the design and operation process, such as location, structure, function and other characteristics.

[0080] In an optional embodiment of the present invention, the network layout of the target sensor needs to ensure that each sensor can effectively cover its monitoring area. At the same time, the network structure for data transmission is planned, and wired or wireless communication methods such as Wi-Fi, LoRa, NB-IoT, etc. can be selected.

[0081] Furthermore, the present invention evaluates the response speed and efficiency of the system by calculating the real-time coefficient of the IOT sensor group, wherein the real-time coefficient refers to the real-time degree of sensor data collection and transmission.

[0082] In detail, the calculating of the real-time coefficient of the IOT sensor group includes:

[0083] Determining a data path of the IOT sensor group;

[0084] Based on the data path, analyzing the response time of the IOT sensor group, wherein the response time includes data collection time, data transmission time, data processing time and data display time;

[0085] Based on the response time, the real-time coefficient of the IOT sensor group is calculated using the following formula:

[0086] ;

[0087] in, Represents the real-time coefficient of the IOT sensor group, Indicates the number of sensors in the IOT sensor group, Indicates the IOT sensor group The data collection time of each sensor, Indicates the IOT sensor group The data transmission time of each sensor, Indicates the IOT sensor group The data processing time of each sensor is Indicates the IOT sensor group The data display time of each sensor, Indicates the IOT sensor group The user expected response time of each sensor.

[0088] Among them, the data path refers to the key steps from sensor data collection to user receiving data, which usually includes data collection, data transmission, data processing and data display. The data collection time is the time from the sensor starting to collect data to the data being completely collected. The data transmission time is the time from the completion of data collection to the arrival of data at the receiving end. The data processing time is the time from the arrival of data at the receiving end to the completion of data processing. The data display time is the time from the completion of data processing to the time when the user can see the processing results. The user expected response time refers to the user's subjective expectation of the time required for the system to complete the data path operation.

[0089] Optionally, the embodiment of the present invention can improve data collection and analysis reliability by collecting water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group when the real-time coefficient meets the preset standard real-time coefficient, thereby improving the performance and safety of the water treatment system.

[0090] In detail, the standard real-time coefficient refers to a target value for evaluating the real-time performance of the sensor according to the specific application scenario and user needs. The effluent index includes key indicators such as COD, ammonia nitrogen, total nitrogen, total phosphorus and SS, and the effluent index data refers to the values ​​of key water quality parameters collected by the IoT sensor group. These index data include the concentration values ​​of key parameters such as chemical oxygen demand (COD), ammonia nitrogen, total nitrogen, total phosphorus and suspended solids (SS).

[0091] S2. Constructing a sequence state curve of the water output index based on the water output index data.

[0092] In the embodiment of the present invention, based on the water output index data, a sequence state curve of the water output index is constructed, which can be used as a basis for subsequent water output index analysis. The sequence state curve refers to a state curve indicating that the water output index changes over time.

[0093] In detail, the step of constructing a sequence state curve of the water output index based on the water output index data includes:

[0094] Preprocessing the water outlet index data to obtain preprocessed index data;

[0095] Serializing the preprocessing indicator data to obtain sequence indicator data, and determining the time node of the sequence indicator data;

[0096] Based on the sequence indicator data, marking the node indicator concentration of the time node;

[0097] The time nodes and the node indicator concentrations are used to construct a sequence state curve of the water output indicator.

[0098] Among them, the pre-processed index data refers to the cleaning and pre-processing of the effluent index data, including removing outliers, filling missing values, standardization and other operations to ensure the quality and consistency of the data, the sequence index data refers to the data set after the pre-processed index data is arranged in time, the time node refers to the time point used to construct the curve, and the node index concentration refers to the effluent index concentration value corresponding to the time node. For example, time nodes: 00:00, 00:10, 00:20, …, 00:50, node index concentration: COD concentration: 10, 11, 12, …, 15, ammonia nitrogen concentration: 2, 2.1, 2.2, …, 2.5, total nitrogen concentration: 5, 5.1, 5.2, …, 5.5, total phosphorus concentration: 0.5, 0.51,0.52, …, 0.55, SS concentration: 100, 101, 102, …, 105.

[0099] Furthermore, the construction of the sequence state curve of the effluent index by using the time nodes and the node index concentrations can be achieved by using a chart tool or a programming language (such as Python, R, etc.).

[0100] S3. Based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, and based on the sequence index analysis value, a state analysis curve of the water output index is constructed.

[0101] In the embodiment of the present invention, the sequence index analysis value refers to the state value of the water output index predicted by the water affairs early warning model over time, and the water affairs early warning model is pre-constructed by the time series analysis model.

[0102] It should be explained that the time series analysis model is a statistical model specifically used to analyze time series data. They can help us understand and predict the changing trend of data over time. In the present invention, the autoregressive integrated moving average model (ARIMA) of the time series analysis model is more suitable for time series data with seasonality and trend, which improves the accuracy of data analysis.

[0103] In detail, the analyzing the sequence indicator analysis value of the water output indicator based on the sequence state curve and the water output indicator data using the trained water affairs early warning model includes:

[0104] Performing a stationarity test on the sequence index data corresponding to the water discharge index data to obtain data stationarity, wherein the stationarity test includes trend test, seasonal test and unit root test;

[0105] When the data stability does not meet the preset standard stability, performing differential processing on the sequence index data to obtain stable index data;

[0106] Extracting the time series characteristics of the stable index data and marking the prediction starting point of the sequence state curve;

[0107] Determine the model order of the water affairs early warning model, wherein the model order includes autoregressive order, difference order, and sliding average order. Based on the time series characteristics, the prediction starting point, and the model order, use the water affairs early warning model to analyze the sequence indicator analysis value of the water output indicator.

[0108] The data stability refers to the degree of stability of the data. Specifically, the trend detection is to observe the time series graph of the sequence indicator data to see whether there is a trend of increasing or decreasing over time.

[0109] The seasonality detection: observe the time series graph of the sequence indicator data to check whether there is periodic fluctuation, such as monthly, quarterly or annual cycle.

[0110] The unit root test: a unit root test is used to determine whether the time series of the sequence indicator data has a unit root, that is, whether it is non-stationary.

[0111] The stable index data refers to the data set obtained after the sequence index data is processed smoothly, the time series characteristics refer to the law and pattern of data changes over time, the prediction starting point refers to the starting time point used to predict future trends in time series analysis, which is generally the last time node on the curve, and the autoregressive order, the difference order and the sliding average order are three key parameters used to build a water affairs early warning model. They represent the order of the autoregressive term, the difference term and the sliding average term in the model, respectively, wherein the autoregressive term refers to the influence of the previous value of the time series data itself on the current value, the difference term is a technology used to stabilize the time series, and the sliding average term refers to the influence of the lagged value of the error term (or residual) of the time series data on the current error term.

[0112] Further, in an optional embodiment of the present invention, the step of performing a stationarity test on the sequence index data corresponding to the water output index data to obtain data stationarity includes:

[0113] Constructing a time series graph of the sequence indicator data;

[0114] Based on the time series graph, marking the observed values ​​of the sequence indicator data;

[0115] Based on the observed values, the data slope of the sequence index data is calculated using the following formula:

[0116] ;

[0117] in, represents the data slope of the series indicator data, Indicates the sequence index data The observed value of data points, Indicates the sequence index data The observed value of data points, The number of data points representing the series indicator data;

[0118] Based on the time series graph, calculating the seasonal kurtosis of the sequence indicator data;

[0119] Identifying the unit root of the sequence indicator data;

[0120] The data stationarity of the sequence indicator data is determined based on the data slope, the seasonal kurtosis and the unit root.

[0121] It should be explained that the time series graph refers to a graphical tool used to visualize the changing trend of time series data over time, the observed value refers to the data value of the sequence indicator data, such as ammonia nitrogen concentration, total nitrogen concentration, etc., the data slope refers to the rate of change of the data point on the time axis, the seasonal kurtosis refers to the sharpness of seasonal fluctuations, and the unit root refers to a characteristic of time series data, that is, its mean and variance change over time.

[0122] Furthermore, the seasonal kurtosis can be used to quantify the presence and strength of seasonality using seasonal strength tests (such as seasonal skewness tests, seasonal kurtosis tests, etc.).

[0123] The unit root can be tested by ADF test, KPSS test, etc.

[0124] Furthermore, in the process of determining the data stationarity of the sequence indicator data based on the data slope, the seasonal kurtosis and the unit root, when the data slope, the seasonal kurtosis and the unit root show that the data slope does not change significantly, the seasonal kurtosis fluctuates slightly, and the unit root ADF test p-value is greater than 0.05, it can be judged that the data is stable and the data stationarity is marked as 0; otherwise, when the data slope changes significantly, the seasonal kurtosis fluctuates greatly, and the unit root ADF test p-value is less than 0.05, it can be judged that the data is unstable and the data stationarity is marked as 1.

[0125] The present invention constructs the state analysis curve of the water discharge index based on the sequence index analysis value, which can intuitively display the prediction result of the model on the water discharge index. Wherein, the state analysis curve refers to the state curve of the constructed water discharge index prediction value changing with time.

[0126] It should be noted that the construction principle of the state analysis curve is the same as the construction principle of the sequence state curve, which will not be described in detail here.

[0127] S4. Fit the sequence state curve and the state analysis curve to obtain an indicator state curve. Based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, calculate the indicator abnormality coefficient of the indicator state curve. Based on the indicator abnormality coefficient, construct an abnormal warning report for the water affairs scene.

[0128] The present invention obtains an index state curve by fitting the sequence state curve and the state analysis curve, and can connect the water outlet index state collected by the sensor and the predicted water outlet index state, so as to obtain a more comprehensive water outlet index analysis and improve the monitoring effect of water quality. Among them, the index state curve refers to the curve after the sequence state curve and the state analysis curve are integrated into the same coordinate axis.

[0129] In detail, the fitting of the sequence state curve and the state analysis curve can be performed by aligning the time axes of the two curves, and then drawing the sequence state curve and the state analysis curve on the same coordinate axis, distinguishing them by different curve states, for example, the sequence state curve is a smooth curve and the state analysis curve is a dotted curve.

[0130] Optionally, the embodiment of the present invention can further monitor water quality abnormalities by calculating the index abnormality coefficient of the index status curve based on the scene state corresponding to the water service scene, wherein the index abnormality coefficient refers to the abnormal degree of the water output index in the curve.

[0131] In detail, the calculation of the indicator abnormality coefficient of the indicator status curve based on the scene status corresponding to the water service scene includes:

[0132] Based on the scene state corresponding to the water affairs scene, determine the ideal value of the water output indicator corresponding to the water affairs scene;

[0133] Based on the ideal value of the indicator and the indicator state curve, constructing an indicator error curve of the water affairs scenario;

[0134] identifying curve fluctuations of the indicator error curve;

[0135] The fluctuation coefficient of the curve fluctuation is calculated, and based on the fluctuation coefficient, the indicator abnormality coefficient of the indicator error curve is determined.

[0136] Among them, the ideal value of the indicator refers to the ideal state in which the water discharge indicator meets the standard in the scene state corresponding to the historical scene state and the future scene state, the indicator error curve refers to the state curve of the indicator error changing with time, the curve fluctuation refers to the area where there is fluctuation in the indicator error curve, and the fluctuation coefficient refers to the degree of fluctuation of the curve fluctuation.

[0137] Furthermore, in an optional embodiment of the present invention, the indicator error curve of the water service scenario is constructed based on the ideal indicator value and the indicator status curve by calculating the indicator concentration difference between the ideal indicator value and the node indicator concentration at the corresponding time nodes of the indicator status curve, and constructing the curve through the indicator difference and the time nodes.

[0138] For example, at time node 1: the difference in index concentration is 60 mg / L, the ideal index value is 50 mg / L, and the difference in index concentration is 10 mg / L

[0139] Time node 2: indicator concentration difference 55 mg / L, indicator ideal value 50 mg / L, indicator concentration difference 5 mg / L

[0140] Time node 3: indicator concentration difference 50 mg / L, indicator ideal value 50 mg / L, indicator concentration difference 0 mg / L

[0141] Time node 4: The indicator concentration difference is 45 mg / L, the indicator ideal value is 50 mg / L, and the indicator concentration difference is -5 mg / L.

[0142] In another optional embodiment of the present invention, the calculating of the fluctuation coefficient of the curve fluctuation includes:

[0143] Identifying the fluctuation amplitude and fluctuation duration of the curve fluctuation;

[0144] Based on the fluctuation amplitude and the fluctuation duration, the fluctuation coefficient of the curve fluctuation is calculated using the following formula:

[0145] ;

[0146] in, The coefficient of fluctuation represents the fluctuation of the curve, represents the fluctuation amplitude of the curve fluctuation pair, Indicates the error curve of the corresponding indicator of the curve fluctuation, Indicates the angular frequency of the curve fluctuation corresponding to the indicator error curve, Indicates the peak value of the fluctuation corresponding to the fluctuation amplitude of the curve. Indicates the fluctuation valley value of the curve fluctuation corresponding to the fluctuation amplitude, Indicates the fluctuation duration of the curve fluctuation in the indicator error curve corresponding to the curve fluctuation.

[0147] The present invention constructs an abnormal warning report for the water affairs scenario based on the indicator abnormality coefficient, including: setting an abnormal threshold, triggering an alarm when the indicator abnormality coefficient exceeds the abnormal threshold, and constructing an abnormal warning report, including information such as the time point when the abnormal coefficient exceeds the threshold, the indicator name, and the abnormal value.

[0148] S 5. Construct a multimodal alarm strategy for the abnormal warning report, and use the multimodal alarm strategy to execute intelligent alarm for the water affairs scenario.

[0149] The embodiment of the present invention can ensure that relevant personnel can be quickly notified in multiple ways when an abnormal situation occurs by constructing a multi-modal alarm strategy for the abnormal warning report, thereby improving the response speed and efficiency. The multi-modal alarm strategy refers to multiple alarm strategies constructed according to different scenario requirements, such as using voice or telephone warnings for more urgent situations, and using text messages or email warnings for less urgent situations.

[0150] In detail, the multi-modal alarm strategy for constructing the abnormal warning report includes:

[0151] Analyze the scenario requirements of the abnormal warning report corresponding to the water affairs scenario;

[0152] Based on the scenario requirements, analyzing the warning emergency coefficient of the abnormal warning report;

[0153] Locking the warning object of the abnormal warning report and constructing a warning method for the warning object;

[0154] Based on the warning urgency coefficient, the warning object and the warning method, a multimodal alarm strategy for the abnormal warning report is constructed.

[0155] Among them, the scenario requirements refer to the specific requirements of the water affairs scenario, including monitoring indicators, alarm conditions, response time, etc. The warning emergency coefficient refers to the urgency of the abnormal warning report requiring an alert. The warning object refers to the relevant personnel who need to be warned. The warning methods include SMS, e-mail, telephone, voice notification, mobile application push, etc.

[0156] Finally, the embodiment of the present invention utilizes the multimodal alarm strategy to execute intelligent alarm for the water service scenario, which can prevent problems from occurring by adjusting the treatment process in advance or increasing the monitoring frequency, thereby improving the early warning effect for the water service scenario.

[0157] The present invention can improve the automation level and efficiency of water treatment by constructing an IOT sensor group of the water treatment component; the present invention evaluates the response speed and efficiency of the system by calculating the real-time coefficient of the IOT sensor group; the embodiment of the present invention can improve the reliability of data collection and analysis by collecting the water output index data of the water treatment component corresponding to the water output index based on the IOT sensor group when the real-time coefficient meets the preset standard real-time coefficient, thereby improving the performance and safety of the water treatment system; the embodiment of the present invention constructs a sequence state curve of the water output index based on the water output index data, which can be used as a basis for subsequent water output index analysis. Furthermore, the present invention constructs a sequence state curve based on the sequence index analysis value. The state analysis curve of the water output index can intuitively display the prediction results of the model for the water output index. The accuracy of the prediction of the water output index is improved by constructing the state analysis curve based on the analysis of historical data. Furthermore, the present invention can connect the water output index state collected by the sensor and the predicted water output index state by fitting the sequence state curve and the state analysis curve to obtain the index state curve, so as to obtain a more comprehensive water output index analysis and improve the monitoring effect of water quality. Finally, the embodiment of the present invention can ensure that relevant personnel can be quickly notified in a variety of ways when an abnormal situation occurs by constructing a multi-modal alarm strategy for the abnormal warning report, thereby improving the response speed and efficiency. Therefore, the water affairs intelligent alarm method and device based on the water affairs big model proposed in the present invention can improve the intelligent alarm effect of water affairs scenes.

[0158] like Figure 2 1 is a functional module diagram of a water affairs intelligent alarm device based on a water affairs big model provided by an embodiment of the present invention.

[0159] The water affairs intelligent alarm device 200 based on the water affairs big model of the present invention can be installed in an electronic device. According to the functions to be implemented, the water affairs intelligent alarm device 200 based on the water affairs big model can include an indicator data acquisition module 201, a state curve construction module 202, an analysis curve construction module 203, an early warning report construction module 204 and an intelligent alarm module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0160] In this embodiment, the functions of each module / unit are as follows:

[0161] The index data acquisition module 201 is used to obtain the water treatment components of the water service scene, build the IOT sensor group of the water treatment components, calculate the real-time coefficient of the IOT sensor group, and when the real-time coefficient meets the preset standard real-time coefficient, collect the water output index data of the water treatment components corresponding to the water output index based on the IOT sensor group;

[0162] The state curve construction module 202 is used to construct a sequence state curve of the water output index based on the water output index data;

[0163] The analysis curve construction module 203 is used to analyze the sequence indicator analysis value of the water output indicator based on the sequence state curve and the water output indicator data using the trained water affairs early warning model, and construct the state analysis curve of the water output indicator based on the sequence indicator analysis value;

[0164] The warning report construction module 204 is used to fit the sequence state curve and the state analysis curve to obtain an indicator state curve, calculate the indicator abnormality coefficient of the indicator state curve based on the scene state corresponding to the water service scene, wherein the scene state includes the historical scene state and the future scene state, and construct an abnormal warning report for the water service scene based on the indicator abnormality coefficient;

[0165] The intelligent alarm module 205 is used to construct a multi-modal alarm strategy for the abnormal warning report, and use the multi-modal alarm strategy to execute intelligent alarm for the water service scenario.

[0166] In detail, the modules described in the water affairs intelligent alarm device 200 based on the water affairs big model described in the embodiment of the present invention adopt the same technical means as the water affairs intelligent alarm method based on the water affairs big model described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0167] An embodiment of the present invention provides an electronic device for implementing a water affairs intelligent alarm method based on a water affairs big model.

[0168] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a water affairs intelligent alarm method program based on a water affairs big model.

[0169] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory (for example, executing a water affairs intelligent alarm program based on a water affairs big model, etc.), and calling data stored in the memory.

[0170] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit and an external storage device of the electronic device. The memory can not only be used to store application software and various types of data installed in the electronic device, such as the code of the water affairs intelligent alarm program based on the water affairs big model, but also can be used to temporarily store data that has been output or is to be output.

[0171] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0172] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0173] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0174] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0175] The water affairs intelligent alarm program based on the water affairs big model stored in the memory of the electronic device is a combination of multiple instructions. When running in the processor, it can achieve:

[0176] Acquire a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate a real-time coefficient of the IOT sensor group, and when the real-time coefficient meets a preset standard real-time coefficient, collect water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group;

[0177] Based on the water output index data, construct a sequence state curve of the water output index;

[0178] Based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, and based on the sequence index analysis value, a state analysis curve of the water output index is constructed;

[0179] Fitting the sequence state curve and the state analysis curve to obtain an indicator state curve, and based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, calculating the indicator abnormality coefficient of the indicator state curve, and constructing an abnormal warning report of the water affairs scene based on the indicator abnormality coefficient;

[0180] A multimodal alarm strategy for the abnormal warning report is constructed, and the multimodal alarm strategy is used to execute intelligent alarm for the water affairs scenario.

[0181] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0182] Furthermore, if the module / unit integrated in the electronic device 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. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0183] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0184] Acquire a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate a real-time coefficient of the IOT sensor group, and when the real-time coefficient meets a preset standard real-time coefficient, collect water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group;

[0185] Based on the water output index data, construct a sequence state curve of the water output index;

[0186] Based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, and based on the sequence index analysis value, a state analysis curve of the water output index is constructed;

[0187] Fitting the sequence state curve and the state analysis curve to obtain an indicator state curve, and based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, calculating the indicator abnormality coefficient of the indicator state curve, and constructing an abnormal warning report of the water affairs scene based on the indicator abnormality coefficient;

[0188] A multimodal alarm strategy for the abnormal warning report is constructed, and the multimodal alarm strategy is used to execute intelligent alarm for the water affairs scenario.

[0189] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0190] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0191] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0192] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0193] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0194] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0195] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0196] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A water affairs intelligent alarm method based on a water affairs big model, characterized in that: The method comprises: Acquire a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate the real-time coefficient of the IOT sensor group, and when the real-time coefficient meets the preset standard real-time coefficient, collect the water output index data of the water treatment component corresponding to the water output index based on the IOT sensor group, wherein the calculation of the real-time coefficient of the IOT sensor group includes: determining the data path of the IOT sensor group, and based on the data path, analyzing the response time of the IOT sensor group, wherein the response time includes data collection time, data transmission time, data processing time and data display time, and based on the response time, the real-time coefficient of the IOT sensor group is calculated using the following formula: ； in, Represents the real-time coefficient of the IOT sensor group, Indicates the number of sensors in the IOT sensor group, Indicates the IOT sensor group The data collection time of each sensor, Indicates the IOT sensor group The data transmission time of each sensor, Indicates the IOT sensor group The data processing time of each sensor is Indicates the IOT sensor group The data display time of each sensor, Indicates the IOT sensor group The user's expected response time for each sensor; Based on the water output index data, construct a sequence state curve of the water output index; Based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, and based on the sequence index analysis value, a state analysis curve of the water output index is constructed, wherein, based on the sequence state curve and the water output index data, the sequence index analysis value of the water output index is analyzed using a trained water affairs early warning model, including: performing a stationarity test on the sequence index data corresponding to the water output index data to obtain data stationarity, wherein the stationarity test includes trend detection, seasonality detection and unit root detection, and when the data stationarity does not meet the preset standard stationarity, performing differential processing on the sequence index data to obtain stationarity index data , extract the time series characteristics of the stable index data, and mark the prediction starting point of the sequence state curve, determine the model order of the water affairs early warning model, wherein the model order includes autoregressive order, difference order, and sliding average order, and analyze the sequence index analysis value of the water discharge index based on the time series characteristics, the prediction starting point and the model order using the water affairs early warning model, wherein the stationarity detection of the sequence index data corresponding to the water discharge index data to obtain the data stationarity includes: constructing a time series graph of the sequence index data, marking the observed values ​​of the sequence index data based on the time series graph, and calculating the data slope of the sequence index data based on the observed values ​​using the following formula: ； in, represents the data slope of the series indicator data, Indicates the sequence index data The observed value of data points, Indicates the sequence index data The observed value of data points, Representing the number of data points of the sequence indicator data, calculating the seasonal kurtosis of the sequence indicator data based on the time series graph, identifying the unit root of the sequence indicator data, and determining the data stationarity of the sequence indicator data based on the data slope, the seasonal kurtosis and the unit root; The sequence state curve and the state analysis curve are fitted to obtain an indicator state curve, and based on the scene state corresponding to the water affairs scenario, wherein the scene state includes a historical scene state and a future scene state, an indicator abnormality coefficient of the indicator state curve is calculated, and based on the indicator abnormality coefficient, an abnormal warning report of the water affairs scenario is constructed, wherein the calculation of the indicator abnormality coefficient of the indicator state curve based on the scene state corresponding to the water affairs scenario includes: determining an indicator ideal value of the water discharge indicator corresponding to the water affairs scenario based on the scene state corresponding to the water affairs scenario, constructing an indicator error curve of the water affairs scenario based on the indicator ideal value and the indicator state curve, identifying curve fluctuations of the indicator error curve, calculating the fluctuation coefficient of the curve fluctuations, and determining the indicator abnormality coefficient of the indicator error curve based on the fluctuation coefficient, wherein the calculation of the fluctuation coefficient of the curve fluctuation includes: identifying the fluctuation amplitude and fluctuation duration of the curve fluctuation; and calculating the fluctuation coefficient of the curve fluctuation based on the fluctuation amplitude and the fluctuation duration using the following formula: ； in, The coefficient of fluctuation represents the fluctuation of the curve, represents the fluctuation amplitude of the curve fluctuation pair, Indicates the error curve of the corresponding indicator of curve fluctuation, Indicates the angular frequency of the curve fluctuation corresponding to the indicator error curve, Indicates the peak value of the fluctuation corresponding to the fluctuation amplitude of the curve. Indicates the fluctuation valley value of the curve fluctuation corresponding to the fluctuation amplitude, Indicates the fluctuation duration of the curve fluctuation in the indicator error curve corresponding to the curve fluctuation; A multimodal alarm strategy for the abnormal warning report is constructed, and the multimodal alarm strategy is used to execute intelligent alarm for the water affairs scenario.

2. The water affairs intelligent alarm method based on the water affairs big model as claimed in claim 1 is characterized in that: The IOT sensor group for constructing the water treatment component includes: Analyzing monitoring requirements of the water treatment components; According to the monitoring requirements, configure the target sensor of the water treatment component; Based on the component characteristics corresponding to the water treatment component, construct a network layout of the target sensor; Based on the network layout, an IOT sensor group of the water treatment component is constructed.

3. The water affairs intelligent alarm method based on the water affairs big model as claimed in claim 2 is characterized in that: The step of constructing a sequence state curve of the water output index based on the water output index data includes: Preprocessing the water outlet index data to obtain preprocessed index data; Serializing the preprocessing indicator data to obtain sequence indicator data, and determining the time node of the sequence indicator data; Based on the sequence indicator data, marking the node indicator concentration of the time node; The time nodes and the node indicator concentrations are used to construct a sequence state curve of the water output indicator.

4. The water affairs intelligent alarm method based on the water affairs big model as claimed in claim 3 is characterized in that: The multi-modal alarm strategy for constructing the abnormal warning report includes: Analyze the scenario requirements of the abnormal warning report corresponding to the water affairs scenario; Based on the scenario requirements, analyzing the warning emergency coefficient of the abnormal warning report; Locking the warning object of the abnormal warning report and constructing a warning method for the warning object; Based on the warning urgency coefficient, the warning object and the warning method, a multimodal alarm strategy for the abnormal warning report is constructed.

5. A water affairs intelligent alarm device based on a water affairs big model, characterized in that: The device is used to execute the water affairs intelligent alarm method based on the water affairs big model as described in any one of claims 1 to 4, and comprises: An index data acquisition module is used to obtain a water treatment component of a water service scenario, construct an IOT sensor group of the water treatment component, calculate a real-time coefficient of the IOT sensor group, and when the real-time coefficient meets a preset standard real-time coefficient, collect water output index data corresponding to the water output index of the water treatment component based on the IOT sensor group; A state curve construction module, used to construct a sequence state curve of the water output index based on the water output index data; An analysis curve construction module is used to analyze the sequence indicator analysis value of the water output indicator based on the sequence state curve and the water output indicator data using a trained water affairs early warning model, and to construct a state analysis curve of the water output indicator based on the sequence indicator analysis value; An early warning report construction module is used to fit the sequence state curve and the state analysis curve to obtain an indicator state curve, calculate an indicator abnormality coefficient of the indicator state curve based on the scene state corresponding to the water affairs scene, wherein the scene state includes a historical scene state and a future scene state, and construct an abnormal early warning report for the water affairs scene based on the indicator abnormality coefficient; The intelligent alarm module is used to construct a multimodal alarm strategy for the abnormal warning report and use the multimodal alarm strategy to execute intelligent alarm for the water service scenario.

Images