Remote monitoring and data analysis method and system based on ATP fluorescence detection and Internet of Things

Abstract

The invention provides a remote monitoring and data analysis method and system based on ATP fluorescence detection and the Internet of Things. The method comprises the following steps: collecting original detection data generated by an ATP fluorescence detection sensor to obtain stable processed detection data with a high signal-to-noise ratio; the comprehensive detection data is efficiently transmitted to a cloud data center through the Internet of Things technology, and the safely transmitted comprehensive detection data is generated; comprehensively analyzing the detection data, identifying a change mode of the biological pollution level, and generating an alarm notification record; constructing a biological pollution prediction model, and generating a biological pollution prediction report; the ATP fluorescence detection frequency setting of each monitoring point is adjusted, the detection frequency of the monitoring points which are predicted and displayed as high-risk areas is increased, the detection frequency of the monitoring points which are predicted and displayed as low-risk areas is reduced, and an optimized monitoring strategy is generated, so that the response speed and the resource utilization efficiency of the monitoring system are improved. According to the technical scheme provided by the invention, the real-time performance, the accuracy and the response efficiency of biological pollution monitoring are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of environmental monitoring and data analysis, and in particular to a remote monitoring and data analysis method and system based on ATP fluorescence detection and the Internet of Things. Background Art

[0002] In the fields of environmental monitoring, food safety, and public health, rapid and accurate detection and early warning of biological contamination are crucial. With the development of Internet of Things technology, adenosine triphosphate (ATP) fluorescence detection sensors can be used to monitor the activity of microorganisms in the environment in real time. This technology can provide instant data feedback, helping managers respond quickly and reduce the occurrence and impact of contamination incidents.

[0003] There are currently a variety of technical means on the market for monitoring biological contamination, such as traditional laboratory testing methods, chemical indicators, etc. In recent years, solutions that combine ATP fluorescence detection technology and IoT platforms have gradually emerged. These systems usually include a sensor network deployed on-site to collect raw data; cloud computing services that are responsible for storing and processing large amounts of data; and advanced data analysis algorithms to identify potential risk patterns and generate alarm notifications. In addition, some advanced applications also integrate machine learning models to improve prediction accuracy and automation levels.

[0004] Although the existing method of combining ATP fluorescence detection with the Internet of Things has solved the problem of real-time monitoring to a certain extent, there are still some challenges. First, the original detection data is often interfered by noise, and direct use may lead to inaccurate analysis results. Secondly, many current systems lack effective data preprocessing mechanisms and cannot guarantee the security and integrity of information transmission. Furthermore, although some systems have introduced time series analysis or simple statistical methods for data analysis, their predictive capabilities are limited when faced with complex and changeable actual scenarios, and it is difficult to effectively respond to emergencies. Finally, in terms of alarm response, existing systems often use fixed threshold settings, lack flexibility, and cannot dynamically adjust alarm levels and response strategies according to actual conditions, resulting in unreasonable resource allocation. Summary of the invention

[0005] The embodiment of the present application provides a remote monitoring and data analysis method and system based on ATP fluorescence detection and the Internet of Things, which is used to solve the problems of low real-time, accuracy and response efficiency of biological contamination monitoring in the prior art.

[0006] In a first aspect, the present application embodiment provides a remote monitoring and data analysis method based on ATP fluorescence detection and the Internet of Things, comprising:

[0007] Collecting the original detection data generated by the ATP fluorescence detection sensor, the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and performing real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio;

[0008] Based on the processed detection data, the processed detection data is efficiently transmitted to the cloud data center via the Internet of Things technology, and together with the stored historical detection data, the comprehensive detection data after secure transmission is generated;

[0009] A time series analysis algorithm is used to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data to identify the change pattern of the biological contamination level. When the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data, a multi-level alarm response system is activated. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records;

[0010] Based on the alarm notification records, historical detection data and environmental parameters in the securely transmitted comprehensive detection data, combined with real-time detection data, a machine learning algorithm is used to construct a biological contamination prediction model to generate a biological contamination prediction report;

[0011] By using the biological contamination prediction report and combining it with the problem area information reflected in the alarm notification record, the ATP fluorescence detection frequency setting of each monitoring point is adjusted, the detection frequency is increased for monitoring points predicted to be high-risk areas, and the detection frequency is reduced for low-risk areas, and an optimized monitoring strategy is generated to improve the response speed and resource utilization efficiency of the monitoring system.

[0012] Optionally, the detection data is comprehensively analyzed by combining the environmental parameters in the securely transmitted comprehensive detection data using a time series analysis algorithm to identify the change pattern of the biological contamination level. When the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data, a multi-level alarm response system is activated. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records, including:

[0013] Using a time series analysis algorithm to analyze the fluorescence intensity values ​​and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extract key indicators reflecting the biological contamination level and their changing trends over time, and obtain a time series analysis result of the biological contamination level;

[0014] Based on the time series analysis results of the biological contamination level, compared with the stored historical detection data, a statistical method is used to dynamically adjust the preset warning threshold to obtain a dynamic warning threshold that adapts to the changes in the biological contamination level under different environmental conditions;

[0015] According to the dynamic warning threshold, the time series analysis result of the biological contamination level is monitored, and when the detected fluorescence intensity value exceeds the dynamic warning threshold, a multi-level alarm response mechanism is immediately activated to obtain an alarm trigger signal;

[0016] Based on the alarm trigger signal, the alarm level is automatically determined according to the severity of the alarm, and the most appropriate communication channel is selected to send customized alarm information including the alarm level, specific pollution location, cause analysis and preliminary recommended response measures to the preset management personnel or emergency team, and an alarm notification record is generated.

[0017] Optionally, the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are analyzed by using a time series analysis algorithm, key indicators reflecting the biological contamination level and their changing trends over time are extracted, and the time series analysis results of the biological contamination level are obtained, including:

[0018] Using time series decomposition technology, the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are decomposed and processed to separate the three components of long-term trend, seasonal fluctuation and random fluctuation, and obtain preliminary decomposition results;

[0019] Based on the preliminary decomposition results, a statistical regression analysis method is applied to identify the main environmental factors that affect the change of fluorescence intensity values, a mathematical model between the fluorescence intensity values ​​and environmental parameters is established, and an environmental factor influence model is obtained;

[0020] Using the environmental factor impact model, combined with the long-term trend and seasonal fluctuations in the preliminary decomposition results, the biological contamination level is predicted, key indicators reflecting the biological contamination level are extracted, including average fluorescence intensity and fluorescence intensity change rate, and a key indicator set is generated;

[0021] According to the key indicator set, the changing trend of the biological contamination level over time is analyzed, the rising, falling or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated.

[0022] Optionally, the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are analyzed by using a time series analysis algorithm, key indicators reflecting the biological contamination level and their changing trends over time are extracted, and the time series analysis results of the biological contamination level are obtained, including:

[0023] By using the time series decomposition technology, the fluorescence intensity value F(t) and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are decomposed and processed, and the three components of the long-term trend T(t), seasonal fluctuation S(t) and random fluctuation R(t) are separated to obtain a preliminary decomposition result, namely, F(t)=T(t)+S(t)+R(t), wherein t represents time, F(t) represents the fluorescence intensity value, which represents the fluorescence intensity at time t; T(t) represents the long-term trend, which represents the long-term change trend of the fluorescence intensity value; S(t) represents the seasonal fluctuation, which represents the periodic change of the fluorescence intensity value; R(t) represents the random fluctuation, which represents the random change part of the fluorescence intensity value;

[0024] Based on the preliminary decomposition results, statistical regression analysis was applied to identify the main environmental factors affecting the changes in fluorescence intensity values. i (t), establish the fluorescence intensity value F(t) and the environmental parameter E i (t) The nonlinear mathematical model between the two factors is as follows:

[0025]

[0026] Among them: E i (t) represents the environmental parameter, which represents the i-th environmental parameter at time t; β0 is the intercept term, β i , γ i and δ i are the linear, quadratic and cubic regression coefficients of the i-th environmental parameter, α1 and α2 are the regression coefficients of the long-term trend and seasonal fluctuation, n is the number of environmental parameters, ∈ is the error term, and the environmental factor impact model is obtained;

[0027] The environmental factor impact model is used to predict the biological contamination level in combination with the long-term trend T(t) and seasonal fluctuation S(t) in the preliminary decomposition results, and key indicators reflecting the biological contamination level are extracted:

[0028] The mean fluorescence intensity was calculated using the following formula:

[0029]

[0030] The fluorescence intensity change rate ΔF(t) was calculated using the following formula:

[0031]

[0032] Wherein, Δt represents the time interval, which indicates the time interval for calculating the rate of change of fluorescence intensity;

[0033] Weighted moving average fluorescence intensity WMA (F(t)):

[0034]

[0035] Among them, w i is the weight, k is the time window length; i represents the index within the time window;

[0036] The exponentially smoothed fluorescence intensity ES(F(t)) was calculated using the following formula:

[0037] ES(F(t))=αF(t)+(1-α)ES(F(t-1))

[0038] Among them, α is a smoothing factor, which usually takes a value between 0 and 1; generate a set of key indicators;

[0039] According to the key indicator set, the changing trend of the biological contamination level over time is analyzed, the rising, falling or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated.

[0040] Optionally, the environmental parameters in the alarm notification records, historical detection data and the integrated detection data after secure transmission are combined with real-time detection data, and a machine learning algorithm is used to construct a biological contamination prediction model to generate a biological contamination prediction report, including:

[0041] Collect and preprocess alarm notification records, historical test data, environmental parameters in securely transmitted comprehensive test data, and real-time test data to obtain high-quality data sets;

[0042] Based on high-quality data sets, feature selection and transformation are performed to determine the key features that affect biological pollution prediction, and some features are transformed or encoded as necessary to obtain feature data after feature selection and transformation;

[0043] Using the feature data after feature selection and transformation, support vector machine is selected as the machine learning algorithm to build a biological contamination prediction model. At the same time, appropriate kernel functions are selected and related parameters are adjusted to optimize model performance.

[0044] Based on the constructed biological contamination prediction model, the model is trained and verified using the cross-validation method to ensure that the model has good generalization ability and prediction accuracy, and the optimized biological contamination prediction model is obtained;

[0045] The optimized biological contamination prediction model is used to predict new or future data and generate a detailed biological contamination prediction report, which includes the predicted time range, prediction results, potential high-risk areas and corresponding recommended measures.

[0046] Optionally, the feature data after feature selection and conversion is used to select a support vector machine as a machine learning algorithm to construct a biological contamination prediction model, and a suitable kernel function is selected to optimize the model performance, including:

[0047] Using the feature data after feature selection and transformation, the support vector machine is selected as the machine learning algorithm to model the biological pollution prediction task and obtain a preliminary vector machine model;

[0048] According to the requirements of the biological contamination prediction task, a suitable kernel function is selected for the vector machine model, and the selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, so as to obtain a vector machine model with strong nonlinear mapping ability to optimize model performance;

[0049] The penalty parameters and kernel function parameters are adjusted by using a preliminary vector machine model. The adjustment process uses a parameter optimization method to find the best parameter combination within a predefined parameter range to obtain an optimized parameter combination.

[0050] Optionally, the feature data after feature selection and conversion is used to select a support vector machine as a machine learning algorithm to construct a biological contamination prediction model, and a suitable kernel function is selected to optimize the model performance, including:

[0051] Using the feature data after feature selection and transformation, the support vector machine is selected as the machine learning algorithm to model the biological pollution prediction task and obtain a preliminary vector machine model;

[0052] The basic form of the vector machine model f(x) is expressed as:

[0053]

[0054] Where N represents the number of support vectors, α i is the Lagrange multiplier, y i is the label of each support vector (+1 or -1), K(x, x i ) is the kernel function, b is the bias term;

[0055] According to the requirements of the biological pollution prediction task, a suitable kernel function is selected for the vector machine model. The selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, and a vector machine model with strong nonlinear mapping ability is obtained; commonly used kernel functions include linear kernel, polynomial kernel and radial basis function kernel; the mathematical expression of the basis function kernel K(x, x i )for:

[0056] K(x,x i )=exp(-γ∥xx i∥ 2 )

[0057] Among them, γ is the kernel function parameter, ∥xx i ∥ represents the Euclidean distance between two vectors.

[0058] Optionally, the biological contamination prediction report is used in combination with the problem area information reflected in the alarm notification record to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, to generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system, including:

[0059] Using the prediction results, prediction confidence and potential impact analysis in the biological contamination prediction report, the future biological contamination risk of each monitoring point is evaluated to obtain the risk area assessment result;

[0060] Based on the risk area assessment results, combined with the problem area information reflected in the alarm notification record, the actual pollution risk level of each monitoring point is comprehensively analyzed to generate a risk assessment report for each monitoring point;

[0061] According to the risk assessment report of each monitoring point, for monitoring points predicted to be high-risk areas, the detection frequency is increased by adjusting the ATP fluorescence detection frequency setting to ensure that biological contamination events can be discovered and responded to in a timely manner, and a monitoring strategy for high-risk areas is generated;

[0062] For monitoring points predicted to be low-risk areas, based on the risk assessment reports of the monitoring points, the detection frequency is appropriately reduced to reduce resource waste, improve the operating efficiency of the monitoring system, and generate monitoring strategies for low-risk areas;

[0063] The monitoring strategies for the high-risk areas and the low-risk areas are integrated to form a comprehensive and optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system and ensure effective monitoring and management of biological contamination.

[0064] Optionally, the processed detection data is efficiently transmitted to a cloud data center via the Internet of Things technology, and together with the stored historical detection data, generates comprehensive detection data after secure transmission, including:

[0065] Using the processed detection data to form a structured detection data packet, thereby obtaining a structured detection data packet;

[0066] Based on the structured detection data packet, the detection data packet is encrypted using the security encryption protocol in the Internet of Things technology to ensure the security of the data during transmission, prevent the data from being stolen or tampered with, and generate an encrypted detection data packet;

[0067] The encrypted detection data packet is efficiently transmitted to the cloud data center through the Internet of Things network, and data compression technology is used to reduce the amount of data transmission during the transmission process. At the same time, error control technology is used to ensure the integrity of data transmission, so as to obtain the detection data after secure transmission;

[0068] In the cloud data center, the securely transmitted detection data is integrated with the stored historical detection data to ensure the consistency and continuity of the new and old data, and to generate the securely transmitted comprehensive detection data.

[0069] In a second aspect, the present application embodiment provides a remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things, including:

[0070] A collection and processing module is used to collect the original detection data generated by the ATP fluorescence detection sensor, wherein the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and to perform real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio;

[0071] A transmission module, used to efficiently transmit the processed detection data to a cloud data center via the Internet of Things technology, and generate comprehensive detection data after secure transmission together with the stored historical detection data;

[0072] An analysis activation module is used to use a time series analysis algorithm to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data, identify the change pattern of the biological contamination level, and activate a multi-level alarm response system when the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records;

[0073] A construction module is used to construct a biological contamination prediction model using a machine learning algorithm based on the environmental parameters in the alarm notification record, historical detection data and the comprehensive detection data after secure transmission, combined with real-time detection data, to generate a biological contamination prediction report;

[0074] The adjustment generation module is used to use the biological contamination prediction report, combined with the problem area information reflected in the alarm notification record, to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, and generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system.

[0075] In the embodiment of the present application, the original detection data generated by the ATP fluorescence detection sensor is collected, the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and the original detection data is subjected to real-time denoising processing to obtain stable processed detection data with a high signal-to-noise ratio; based on the processed detection data, it is efficiently transmitted to a cloud data center via the Internet of Things technology, and together with the stored historical detection data, the comprehensive detection data after safe transmission is generated; the detection data is comprehensively analyzed using a time series analysis algorithm in combination with the environmental parameters in the comprehensive detection data after safe transmission to identify the change pattern of the biological contamination level, and when the detection data exceeds a preset threshold value dynamically adjusted based on the historical detection data, a multi-level alarm response system is activated, and the multi-level alarm The alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records; based on the alarm notification records, historical detection data and environmental parameters in the comprehensive detection data after secure transmission, combined with real-time detection data, a machine learning algorithm is used to build a biological contamination prediction model to generate a biological contamination prediction report; using the biological contamination prediction report, combined with the problem area information reflected in the alarm notification record, the ATP fluorescence detection frequency setting of each monitoring point is adjusted, the detection frequency is increased for monitoring points predicted to be high-risk areas, and the detection frequency is reduced for low-risk areas, and an optimized monitoring strategy is generated to improve the response speed and resource utilization efficiency of the monitoring system.

[0076] The technical solution of this application has the following beneficial effects:

[0077] The embodiments of the present application improve the real-time, accuracy and response efficiency of biological contamination monitoring by combining ATP fluorescence detection with Internet of Things technology, while optimizing the monitoring strategy and improving resource utilization efficiency.

[0078] Furthermore, the embodiments of the present application enhance the sensitivity and adaptability of the biological contamination monitoring system through time series analysis and dynamic adjustment of warning thresholds, ensure the timeliness and accuracy of alarm information, and thus effectively improve the early warning capability for biological contamination incidents.

[0079] Furthermore, the embodiment of the present application improves the prediction accuracy of future biological contamination trends by using a machine learning algorithm to construct a biological contamination prediction model, generates a detailed prediction report, provides a scientific basis for decision makers, and helps to take effective prevention and control measures in advance.

[0080] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0082] Figure 1 A flowchart of a remote monitoring and data analysis method based on ATP fluorescence detection and the Internet of Things provided in an embodiment of the present application;

[0083] Figure 2 A schematic diagram of the structure of a remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things provided in an embodiment of the present application;

[0084] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0085] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0086] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0087] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0088] Figure 1 A flowchart of a remote monitoring and data analysis method based on ATP fluorescence detection and the Internet of Things is provided for the embodiment of the present application, such as Figure 1 As shown, the method includes:

[0089] 101. Collecting raw detection data generated by the ATP fluorescence detection sensor, wherein the raw detection data includes a fluorescence intensity value and its accompanying environmental parameters, and performing real-time denoising processing on the raw detection data to obtain stable processed detection data with a high signal-to-noise ratio;

[0090] In this step, the fluorescence detection sensor is able to measure the content of adenosine triphosphate in the water sample. ATP is the energy source of all living cells and its presence indicates biological activity. The raw detection data includes the fluorescence intensity value and its accompanying environmental parameters, which are used to evaluate the activity of microorganisms in the water.

[0091] First, ATP fluorescence detection sensors are installed at water quality monitoring points to collect the fluorescence signals and environmental parameters of water samples in real time. Second, in order to improve data quality, the collected data is subjected to real-time denoising, such as using filters to remove noise, to ensure that the data used in subsequent analysis is stable and has a high signal-to-noise ratio.

[0092] In this application example, it is assumed that in a city water supply system, ATP fluorescence detection sensors are deployed at multiple key nodes. These sensors automatically collect water samples once an hour and record the fluorescence intensity value as well as environmental parameters such as water temperature and pH value. Through the real-time denoising algorithm, the noise caused by equipment vibration or external interference is eliminated to obtain purer data.

[0093] 102. Based on the processed detection data, the processed detection data is efficiently transmitted to a cloud data center via the Internet of Things technology, and together with the stored historical detection data, comprehensive detection data after secure transmission is generated;

[0094] In this step, the processed test data is transmitted to the cloud data center through the Internet of Things technology and stored together with the historical test data to form a comprehensive test data set. This step ensures the secure transmission and centralized management of data.

[0095] First, IoT technologies, such as LoRaWAN, NB-IoT and other low-power wide area network technologies, are used to transmit the processed detection data from the on-site sensors to the cloud server. Secondly, encryption technology is used during data transmission to ensure security.

[0096] In the example of this application, in the above-mentioned urban water supply system, each ATP fluorescence detection sensor sends the processed data to the cloud data center through the built-in LoRaWAN module. The cloud server receives and stores this data, and combines it with the historical data of the past few months to form a complete water quality monitoring database.

[0097] Optionally, the processed detection data in step 102 is efficiently transmitted to a cloud data center via the Internet of Things technology, and together with the stored historical detection data, generates comprehensive detection data after secure transmission, including: using the processed detection data to form a structured detection data packet to obtain a structured detection data packet; based on the structured detection data packet, using the security encryption protocol in the Internet of Things technology to encrypt the detection data packet to ensure the security of the data during transmission and prevent the data from being stolen or tampered with, and generate an encrypted detection data packet; efficiently transmitting the encrypted detection data packet to the cloud data center via the Internet of Things network, using data compression technology to reduce the amount of data transmission during transmission, and using error control technology to ensure the integrity of data transmission, to obtain the detection data after secure transmission; in the cloud data center, integrating the securely transmitted detection data with the stored historical detection data to ensure the consistency and continuity of the new and old data, and generating comprehensive detection data after secure transmission.

[0098] In this step, structured detection data packets refer to the organization of processed detection data in a certain format and structure to facilitate subsequent data processing and analysis. Security encryption protocols are technical means used to protect data from being stolen or tampered with during transmission, ensuring data security. Data compression technology can reduce the amount of data transmission and improve transmission efficiency. Error control technology ensures the integrity of data transmission through checksums and other methods to prevent data loss or damage. These technologies work together to ensure that the data transmission process from sensors to cloud data centers is both efficient and secure.

[0099] First, the processed detection data is used to form a structured detection data packet for easy transmission and processing. Then, the detection data packet is encrypted using the security encryption protocol in the Internet of Things technology to ensure the security of the data during transmission. Next, the encrypted detection data packet is efficiently transmitted to the cloud data center through the Internet of Things network. During the transmission process, data compression technology is used to reduce the amount of data transmission, and error control technology is used to ensure the integrity of data transmission. Finally, in the cloud data center, the securely transmitted detection data is integrated with the stored historical detection data to ensure the consistency and continuity of the new and old data, and generate comprehensive detection data after secure transmission.

[0100] In an embodiment of the present application, in a water quality monitoring project of a city water supply system, ATP fluorescence detection sensors are deployed at multiple key nodes. These sensors automatically collect the fluorescence intensity value and environmental parameters of the water sample once an hour, and perform denoising in real time. The processed data is organized into structured data packets, each of which contains a timestamp, a sensor ID, a fluorescence intensity value, and environmental parameters. Next, the data packet is encrypted using the Advanced Encryption Standard encryption algorithm to ensure the security of the data during transmission. The encrypted data packet is efficiently transmitted to the cloud data center via the LoRaWAN network. During the transmission process, GZIP compression technology is used to reduce the amount of data transmission, and cyclic redundancy check technology is used to ensure the integrity of data transmission. After arriving at the cloud data center, the system integrates the newly received data with the historical data, updates the records in the database, and ensures the consistency and continuity of the data. This not only improves the security and efficiency of data transmission, but also provides a reliable basis for subsequent data analysis and prediction.

[0101] 103. Perform a comprehensive analysis of the detection data by combining the environmental parameters in the securely transmitted comprehensive detection data using a time series analysis algorithm to identify the change pattern of the biological contamination level, and activate a multi-level alarm response system when the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records;

[0102] In this step, time series analysis algorithms are used to identify trends and patterns in data over time, which combined with environmental parameters can more accurately assess changes in biological contamination levels. When the detection data exceeds the dynamically adjusted preset threshold, a multi-level alarm response system is triggered.

[0103] First, the time series analysis method is used to analyze the changing trend of the fluorescence intensity value over time. Combined with environmental parameters such as temperature and pH value, the warning threshold is dynamically adjusted. Once the detection data exceeds the threshold, the multi-level alarm response system is immediately activated to send an alarm message to the management personnel.

[0104] In the example of this application, in the water quality monitoring system, first, through time series analysis, it is found that the fluorescence intensity value of a certain area has increased significantly in the past week. Combined with the analysis of environmental parameters, it is determined that this is due to increased microbial activity. Secondly, when the fluorescence intensity value exceeds the threshold value dynamically adjusted according to historical data, the system automatically triggers an alarm and notifies relevant managers via SMS and email.

[0105] Optionally, the time series analysis algorithm in step 103 is used to comprehensively analyze the detection data in combination with the environmental parameters in the comprehensive detection data after the secure transmission, and the change pattern of the biological contamination level is identified. When the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data, a multi-level alarm response system is activated. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records, including: using a time series analysis algorithm to analyze the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extracting key indicators reflecting the biological contamination level and its change trend over time, and obtaining a time series analysis result of the biological contamination level. The method comprises the following steps: based on the time series analysis result of the biological contamination level, comparing it with the stored historical detection data, dynamically adjusting the preset warning threshold value by using statistical methods, and obtaining a dynamic warning threshold value adapted to the change of the biological contamination level under different environmental conditions; monitoring the time series analysis result of the biological contamination level according to the dynamic warning threshold value, and immediately starting a multi-level alarm response mechanism when the detected fluorescence intensity value exceeds the dynamic warning threshold value to obtain an alarm trigger signal; based on the alarm trigger signal, automatically determining the alarm level according to the severity of the alarm, selecting the most appropriate communication channel to send customized alarm information including the alarm level, specific contamination location, cause analysis, and preliminary recommended response measures to the preset management personnel or emergency response team, and generating an alarm notification record.

[0106] Optionally, the step 103 of using a time series analysis algorithm to analyze the fluorescence intensity values ​​and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extracting key indicators reflecting the biological contamination level and their changing trends over time, and obtaining a time series analysis result of the biological contamination level includes: using a time series decomposition technique to decompose the fluorescence intensity values ​​and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, separating the three components of long-term trend, seasonal fluctuation and random fluctuation, and obtaining a preliminary decomposition result; based on the preliminary decomposition result, applying a statistical regression analysis method to identify the main environmental factors affecting the change of the fluorescence intensity value, establishing a mathematical model between the fluorescence intensity value and the environmental parameters, and obtaining an environmental factor influence model; using the environmental factor influence model, combined with the long-term trend and seasonal fluctuation in the preliminary decomposition result, predicting the biological contamination level, extracting key indicators reflecting the biological contamination level, including the average fluorescence intensity and the fluorescence intensity change rate, and generating a key indicator set; according to the key indicator set, analyzing the changing trend of the biological contamination level over time, identifying the rising, falling or stable state of the biological contamination level, and generating a time series analysis result of the biological contamination level.

[0107] In this step, the time series analysis algorithm is a statistical method used to analyze and predict data that changes over time. In water quality testing, time series analysis can be used to identify the changing trends of fluorescence intensity values ​​and their accompanying environmental parameters over time. Key indicators include average fluorescence intensity and fluorescence intensity change rate, which reflect the changes in biological contamination levels. Time series decomposition technology decomposes data into three components: long-term trends, seasonal fluctuations, and random fluctuations, which helps to understand the changing patterns of data more accurately. Statistical regression analysis methods are used to establish a mathematical model between fluorescence intensity values ​​and environmental parameters, further revealing the impact of environmental factors on fluorescence intensity.

[0108] Firstly, the fluorescence intensity values ​​and the accompanying environmental parameters in the comprehensive detection data after secure transmission are decomposed by time series decomposition technology, and the three components of long-term trend, seasonal fluctuation and random fluctuation are separated to obtain preliminary decomposition results. Then, the statistical regression analysis method is applied to identify the main environmental factors affecting the change of fluorescence intensity values, and a mathematical model between fluorescence intensity values ​​and environmental parameters is established. Then, the model is used to predict the biological contamination level in combination with the long-term trend and seasonal fluctuation in the preliminary decomposition results, and the key indicators reflecting the biological contamination level are extracted to generate a key indicator set. According to the key indicator set, the change trend of the biological contamination level over time is analyzed, the rise, fall or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated. Based on these analysis results, compared with the stored historical detection data, the preset warning threshold is dynamically adjusted by using statistical methods to obtain the dynamic warning threshold adapted to the change of biological contamination level under different environmental conditions. When the detected fluorescence intensity value exceeds the dynamic warning threshold, the multi-level alarm response mechanism is immediately activated to generate an alarm trigger signal. Finally, the alarm level is automatically determined according to the severity of the alarm, and the most appropriate communication channel is selected to send customized alarm information containing the alarm level, specific pollution location, cause analysis, and preliminary recommended response measures to the preset management personnel or emergency team, and an alarm notification record is generated.

[0109] In an embodiment of the present application, in a water quality monitoring project of a city water supply system, ATP fluorescence detection sensors are deployed at multiple key nodes to automatically collect the fluorescence intensity value and environmental parameters of a water sample once every hour. These data are transmitted to the cloud data center after processing. In the cloud, the fluorescence intensity value and its accompanying environmental parameters are decomposed using time series decomposition technology to separate the three components of long-term trend, seasonal fluctuation and random fluctuation. For example, it is found through decomposition that in summer, due to the increase in temperature, the fluorescence intensity value has obvious seasonal fluctuations.

[0110] Next, we applied statistical regression analysis to identify temperature as the main environmental factor affecting the change in fluorescence intensity values, and established a mathematical model between fluorescence intensity values ​​and temperature. This model was used to combine long-term trends and seasonal fluctuations to predict future fluorescence intensity values ​​and extract key indicators such as average fluorescence intensity and fluorescence intensity change rate. Based on these key indicators, we analyzed the trend of biological contamination levels over time and identified that biological contamination levels in certain areas tended to increase.

[0111] Based on these analysis results, the preset warning thresholds are dynamically adjusted in comparison with historical data. For example, during high temperatures in summer, the warning thresholds are appropriately increased to adapt to higher natural background fluorescence levels. When the fluorescence intensity value in a certain area exceeds the dynamic warning threshold, the multi-level alarm response mechanism is immediately activated. The system automatically determines the alarm level based on the severity of the alarm and selects the most appropriate communication channel to send the alarm information to the preset manager or emergency team. The alarm information includes the alarm level, specific contamination location, cause analysis, and preliminary recommended response measures. In this way, managers can take quick action to prevent further deterioration of biological contamination incidents.

[0112] The present application takes into account that in water quality testing, the fluorescence intensity value F(t) is a key indicator for assessing the level of biological contamination in water bodies. The fluorescence intensity value is affected by a variety of environmental factors, such as temperature, pH value, etc. Through time series analysis, the fluorescence intensity value can be decomposed into long-term trends T(t), seasonal fluctuations S(t) and random fluctuations R(t), so as to better understand the change pattern of the data. Furthermore, by establishing a nonlinear mathematical model between the fluorescence intensity value and the environmental parameters, the future fluorescence intensity value can be predicted and the key indicators reflecting the level of biological contamination can be extracted.

[0113] Optionally, the time series analysis algorithm in step 103 is used to analyze the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extract key indicators reflecting the biological contamination level and their changing trends over time, and obtain the time series analysis results of the biological contamination level, including:

[0114] By using the time series decomposition technology, the fluorescence intensity value F(t) and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are decomposed and processed, and the three components of the long-term trend T(t), seasonal fluctuation S(t) and random fluctuation R(t) are separated to obtain a preliminary decomposition result, namely, F(t)=T(t)+S(t)+R(t), wherein t represents time, F(t) represents the fluorescence intensity value, which represents the fluorescence intensity at time t; T(t) represents the long-term trend, which represents the long-term change trend of the fluorescence intensity value; S(t) represents the seasonal fluctuation, which represents the periodic change of the fluorescence intensity value; R(t) represents the random fluctuation, which represents the random change part of the fluorescence intensity value;

[0115] Based on the preliminary decomposition results, statistical regression analysis was applied to identify the main environmental factors affecting the changes in fluorescence intensity values. i (t), establish the fluorescence intensity value F(t) and the environmental parameter E i (t) The nonlinear mathematical model between the two factors is as follows:

[0116]

[0117] Among them: E i (t) represents the environmental parameter, which represents the i-th environmental parameter at time t; β0 is the intercept term, β i , γ i and δ i are the linear, quadratic and cubic regression coefficients of the i-th environmental parameter, α1 and α2 are the regression coefficients of the long-term trend and seasonal fluctuation, n is the number of environmental parameters, ∈ is the error term, and the environmental factor impact model is obtained;

[0118] The environmental factor impact model is used to predict the biological contamination level in combination with the long-term trend T(t) and seasonal fluctuation S(t) in the preliminary decomposition results, and key indicators reflecting the biological contamination level are extracted:

[0119] The mean fluorescence intensity was calculated using the following formula:

[0120]

[0121] The fluorescence intensity change rate ΔF(t) was calculated using the following formula:

[0122]

[0123] Wherein, Δt represents the time interval, which indicates the time interval for calculating the rate of change of fluorescence intensity;

[0124] Weighted moving average fluorescence intensity WMA (F(t)):

[0125]

[0126] Among them, w i is the weight, k is the time window length; i represents the index within the time window;

[0127] The exponentially smoothed fluorescence intensity ES(F(t)) was calculated using the following formula:

[0128] ES(F(t))=αF(t)+(1-α)ES(F(t-1))

[0129] Among them, α is a smoothing factor, which usually takes a value between 0 and 1; generate a set of key indicators;

[0130] According to the key indicator set, the changing trend of the biological contamination level over time is analyzed, the rising, falling or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated.

[0131] Decomposing the fluorescence intensity values ​​into long-term trends, seasonal fluctuations, and random fluctuations helps to separate the change patterns on different time scales. By identifying the main environmental factors that affect the fluorescence intensity values ​​and establishing a nonlinear mathematical model, the change pattern of the fluorescence intensity values ​​can be described more accurately. By calculating the average fluorescence intensity, the rate of change of fluorescence intensity, the weighted moving average fluorescence intensity, and the exponentially smoothed fluorescence intensity, key indicators reflecting the level of biological contamination can be extracted for trend analysis.

[0132] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0133] In the fluorescence intensity value formula F(t), β i E i (t) This sub-item represents the environmental parameter E i (t) linear effect on the fluorescence intensity value F(t), capturing the basic effect of environmental factors; γ i E i (t) 2 This sub-item represents the environmental parameter E i (t) has a quadratic nonlinear effect on the fluorescence intensity value F(t), capturing the nonlinear effect of environmental factors; δ i E i (t) 3 This sub-item represents the environmental parameter E i The third nonlinear influence of the long-term trend T(t) on the fluorescence intensity value F(t) is used to further capture more complex nonlinear effects. The sub-item α1T(t) represents the influence of the long-term trend T(t) on the fluorescence intensity value F(t), which captures the long-term change trend of the data. The sub-item α2S(t) represents the influence of the seasonal fluctuation S(t) on the fluorescence intensity value F(t), which captures the periodic change of the data.

[0134] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0135] In the fluorescence intensity change rate formula ΔF(t), the sub-item F(t-Δt) represents the fluorescence intensity value at the previous time point (t-Δt) and is used to calculate the change rate of the fluorescence intensity.

[0136] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0137] In the weighted moving average fluorescence intensity formula WMA(F(t)), This sub-item represents the sum of weighted fluorescence intensity values ​​within the time window and is used to calculate the weighted moving average fluorescence intensity to smooth short-term fluctuations.

[0138] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0139] In the exponential smoothing fluorescence intensity formula ES(F(t), the sub-item αF(t) represents the weighted part of the fluorescence intensity value F(t) at the current time point t, which is used for exponential smoothing to reflect the impact of the latest data; the sub-item (1-α)ES(F(t-1)) represents the weighted part of the exponential smoothing fluorescence intensity value at the previous time point t-1, which is used for exponential smoothing to reflect the impact of historical data.

[0140] The following is a brief introduction to how to obtain the parameters of the formula:

[0141] Among them, the fluorescence intensity value F(t) is collected in real time by the ATP fluorescence detection sensor; the environmental parameter E i (t) is collected in real time by sensors or other monitoring equipment, such as temperature, pH value, etc.; long-term trend T(t), seasonal fluctuation S(t) and random fluctuation R(t): extracted from the fluorescence intensity value by time series decomposition technology; regression coefficients β0, β i , γ i , δ i , α1, α2: obtained by fitting through statistical regression analysis methods (such as multivariate regression); weight w i Determined by experience or optimization algorithm; the smoothing factor α usually takes a value between 0 and 1, and the specific value is adjusted according to actual conditions.

[0142] Assume that in a water quality monitoring project for a city water supply system, there are the following data:

[0143] The fluorescence intensity value F(t) is the data collected every hour;

[0144] Environmental parameters E1(t) is temperature, E2(t) is pH value;

[0145] Time interval Δt = 1 hour;

[0146] Weight w i =1(simple moving average);

[0147] Smoothing factor α = 0.5;

[0148] Here is an example of the data:

[0149] Time t Fluorescence intensity F(t) <![CDATA[Temperature E1(t)]]> <![CDATA[pH value E2(t)]]> 1 10 20 7.2 2 12 22 7.1 3 14 24 7.0 4 16 25 6.9 5 18 26 6.8

[0150] Here is the time series breakdown:

[0151] Assume that we can get the following through STL decomposition:

[0152] Long-term trend T(t) = [10, 10, 10, 10, 10]

[0153] Seasonal fluctuation S(t) = [0, 1, 2, 3, 4]

[0154] Random fluctuation R(t) = [0, 1, 2, 3, 4]

[0155] The following is the environmental factor impact model:

[0156] Assume that through regression analysis:

[0157] β0=8;

[0158] β1=0.5, γ1=0.01, δ1=0.001;

[0159] β2=0.3, γ2=0.005, δ2=0.0005;

[0160] α1=0.1, α2=0.2;

[0161] The following are the key metric calculations:

[0162] Mean fluorescence intensity

[0163]

[0164] Fluorescence intensity change rate ΔF(t):

[0165]

[0166] The following is the weighted moving average fluorescence intensity WMA (F(t)):

[0167]

[0168] The following is the exponentially smoothed fluorescence intensity ES(F(t)):

[0169] ES(F(1))=10

[0170] ES(F(2))=0.5·12+(1-0.5)·10=11

[0171] ES(F(3))=0.5·14+(1-0.5)·11=12.5

[0172] ES(F(4))=0.5·16+(1-0.5)·12.5=14.25

[0173] ES(F(5))=0.5·18+(1-0.5)·14.25=16.125

[0174] Mean fluorescence intensity It means that the average level of fluorescence intensity during this period is 14.

[0175] The fluorescence intensity change rate ΔF(t)=2 means that the fluorescence intensity increases by 2 units per hour, indicating that the biological contamination level is gradually increasing.

[0176] The weighted moving average fluorescence intensity WMA(F(t)) and the exponentially smoothed fluorescence intensity ES(F(t)) both showed a trend of gradual increase in fluorescence intensity over time, which further confirmed the increase in the level of biological contamination.

[0177] From the above calculations, it can be concluded that the level of biological contamination in the area has been on an upward trend during this period, and it is necessary to pay close attention and take appropriate measures.

[0178] 104. Based on the alarm notification records, historical detection data and environmental parameters in the securely transmitted comprehensive detection data, combined with real-time detection data, a machine learning algorithm is used to construct a biological contamination prediction model to generate a biological contamination prediction report;

[0179] In this step, a biocontamination prediction model is constructed based on existing data and real-time data using machine learning algorithms to generate a biocontamination prediction report. This model can help predict possible biocontamination events in the future.

[0180] First, collect alarm notification records, historical detection data, environmental parameters, and real-time detection data for preprocessing and feature selection. Second, select a suitable machine learning algorithm and train the model. Use the cross-validation method to optimize model performance, and then use the optimized model to predict future data.

[0181] In this application example, it is assumed that in the water quality monitoring system, alarm notification records, historical detection data and environmental parameters for the past year are collected. By preprocessing and feature selection of these data, a vector machine algorithm is used to build a biological contamination prediction model. After cross-validation and tuning, the model is used to predict possible biological contamination events in the next month and generate a detailed prediction report.

[0182] Optionally, the method of constructing a biological contamination prediction model based on the alarm notification records, historical detection data and the environmental parameters in the integrated detection data after secure transmission, combined with real-time detection data, and using a machine learning algorithm in step 104 to generate a biological contamination prediction report includes: collecting and preprocessing the alarm notification records, historical detection data, the environmental parameters in the integrated detection data after secure transmission, and real-time detection data to obtain a high-quality data set; performing feature selection and conversion based on the high-quality data set to determine the key features that affect the biological contamination prediction, and performing necessary conversion or encoding on some features to obtain feature data after feature selection and conversion; using the feature data after feature selection and conversion, selecting a support vector machine as a machine learning algorithm to construct a biological contamination prediction model, and selecting a suitable kernel function and adjusting relevant parameters to optimize model performance; based on the constructed biological contamination prediction model, using a cross-validation method to train and verify the model to ensure that the model has good generalization ability and prediction accuracy, and obtain an optimized biological contamination prediction model; using the optimized biological contamination prediction model to predict new or future data and generate a detailed biological contamination prediction report, the content of which includes the predicted time range, prediction results, potential high-risk areas and corresponding recommended measures.

[0183] Optionally, the step 104 uses the feature data after feature selection and conversion, selects a support vector machine as a machine learning algorithm, constructs a biological contamination prediction model, and selects a suitable kernel function to optimize model performance, including: using the feature data after feature selection and conversion, selecting a support vector machine as a machine learning algorithm, modeling the biological contamination prediction task, and obtaining a preliminary vector machine model; according to the requirements of the biological contamination prediction task, selecting a suitable kernel function for the vector machine model, the selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, and obtaining a vector machine model with strong nonlinear mapping ability to optimize model performance; using the preliminary vector machine model, adjusting the penalty parameters and the kernel function parameters, the adjustment process uses a parameter optimization method to find the best parameter combination within a predefined parameter range to obtain an optimized parameter combination.

[0184] In this step, the alarm notification record contains past biological contamination events and their handling. The historical detection data includes past fluorescence intensity values ​​and environmental parameters. The comprehensive detection data after secure transmission is processed and integrated current data. These data are used to build a biological contamination prediction model to predict possible biological contamination events in the future. Feature selection and transformation refers to extracting the most helpful features for the prediction task from the original data, and performing necessary transformations or encoding to improve model performance. Support vector machine is a commonly used machine learning algorithm. By selecting a suitable kernel function, it can effectively handle nonlinear problems and optimize model performance.

[0185] First, collect alarm notification records, historical detection data, environmental parameters in the integrated detection data after secure transmission, and real-time detection data, and perform preprocessing to obtain a high-quality data set. Then, based on the high-quality data set, perform feature selection and transformation, determine the key features that affect the prediction of biological contamination, and perform necessary transformation or encoding on some features to obtain feature data after feature selection and transformation. Next, using the feature data after feature selection and transformation, select support vector machine as the machine learning algorithm to build a preliminary vector machine model. According to the requirements of the biological contamination prediction task, select a suitable kernel function to optimize the nonlinear mapping ability and generalization ability of the model. Subsequently, use the cross-validation method to train and verify the model to ensure that the model has good generalization ability and prediction accuracy, and obtain the optimized biological contamination prediction model. Finally, use the optimized biological contamination prediction model to predict new or future data and generate a detailed biological contamination prediction report, which includes the predicted time range, prediction results, potential high-risk areas, and corresponding recommended measures.

[0186] In an embodiment of the present application, in a water quality monitoring project of a city water supply system, ATP fluorescence detection sensors are deployed at multiple key nodes to automatically collect the fluorescence intensity value and environmental parameters of water samples once an hour. These data are processed and transmitted to the cloud data center. In the cloud, the system collects alarm notification records, historical detection data, environmental parameters in the comprehensive detection data after secure transmission, and real-time detection data for the past year, and performs preprocessing to remove noise and outliers to obtain a high-quality data set.

[0187] Next, feature selection and transformation are performed to determine the key features that affect the prediction of biological contamination, such as fluorescence intensity, temperature, pH value, etc. Some continuous features are standardized, and categorical features are encoded with one-hot encoding to obtain feature data after feature selection and transformation.

[0188] Using these characteristic data, support vector machine is selected as the machine learning algorithm to build a preliminary vector machine model. According to the requirements of the biological pollution prediction task, radial basis function kernel is selected because radial basis function kernel performs well in dealing with nonlinear problems and can provide strong nonlinear mapping and generalization capabilities. Through the grid search method, the best parameter combination is found within the predefined parameter range to optimize the model performance.

[0189] The model was trained and validated using the 5-fold cross-validation method to ensure that the model had good generalization ability and prediction accuracy on unseen data. Finally, an optimized biological contamination prediction model was obtained.

[0190] The optimized biocontamination prediction model is used to predict new or future data and generate a detailed biocontamination prediction report. The report includes the predicted time range, prediction results, potential high-risk areas and corresponding recommended measures. In this way, managers can take measures in advance based on the prediction report to effectively prevent and control the occurrence of biocontamination incidents.

[0191] This application considers that support vector machines are a powerful supervised learning algorithm, particularly suitable for classification and regression tasks. In biological contamination prediction, support vector machines distinguish between different classes of data points by constructing a decision boundary. The kernel function is a key component of the support vector machine, which allows the model to find nonlinear decision boundaries in high-dimensional space, thereby improving the generalization ability of the model.

[0192] Optionally, the step 104 uses the feature data after feature selection and conversion, selects a support vector machine as a machine learning algorithm, constructs a biological contamination prediction model, and selects a suitable kernel function to optimize the model performance, including:

[0193] Using the feature data after feature selection and transformation, the support vector machine is selected as the machine learning algorithm to model the biological pollution prediction task and obtain a preliminary vector machine model;

[0194] The basic form of the vector machine model f(x) is expressed as:

[0195]

[0196] Where N represents the number of support vectors, α i is the Lagrange multiplier, y i is the label of each support vector (+1 or -1), K(x, x i ) is the kernel function, b is the bias term;

[0197] According to the requirements of the biological pollution prediction task, a suitable kernel function is selected for the vector machine model. The selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, and a vector machine model with strong nonlinear mapping ability is obtained; commonly used kernel functions include linear kernel, polynomial kernel and radial basis function kernel; the mathematical expression of the basis function kernel K(x, x i )for:

[0198] K(x,x i )=exp(-γ∥xx i ∥ 2 )

[0199] Among them, γ is the kernel function parameter, ∥xx i ∥ represents the Euclidean distance between two vectors.

[0200] Support vector machines achieve good classification performance by selecting the optimal hyperplane to maximize the interval between different categories. The kernel function maps the original feature space to a high-dimensional space, making it easier to find a linearly separable decision boundary in the high-dimensional space. Commonly used kernel functions include linear kernels, polynomial kernels, and radial basis function kernels.

[0201] The following is a brief introduction to how to obtain the parameters of the formula:

[0202] Among them, the number of support vectors N is automatically determined through the training process; the Lagrange multiplier α i Obtained by solving the optimization problem; label y i Directly obtained from the training data set; kernel function K(x, x i ) Select the appropriate kernel function type according to the requirements and optimize the parameters through cross-validation; the bias term b is obtained by solving the optimization problem; the kernel function parameter γ is optimized and selected through methods such as cross-validation.

[0203] Assume that in a water quality monitoring project for a city water supply system, there are the following data:

[0204] The characteristic data X include light intensity value, temperature, pH value and so on.

[0205] The label data Y indicates whether biological contamination occurs (+1 indicates contamination, -1 indicates no contamination).

[0206] Here is an example of the data:

[0207] Fluorescence intensity temperature pH Label 10 20 7.2 -1 12 22 7.1 -1 14 24 7.0 +1 16 25 6.9 +1 18 26 6.8 +1

[0208] Feature selection and transformation:

[0209] Assume that after feature selection and transformation, fluorescence intensity, temperature and pH value are retained as features.

[0210] Support vector machine was used for modeling, and radial basis function kernel was selected.

[0211] Train the support vector machine model:

[0212] Assume that the following parameters are obtained through training:

[0213] Number of support vectors N = 3

[0214] Lagrange multipliers α1 = 0.5, α2 = 0.2, α3 = 0.3

[0215] Label y1 = -1, y2 = -1, y3 = +1

[0216] Kernel function parameter γ = 0.1

[0217] Bias term b = -1.5

[0218] Support Vector Machine Model:

[0219] f(x)=0.5·(-1)·exp(-0.1·∥x-x1∥ 2 )+0.2·(-1)·exp(-0.1·∥x-x2∥ 2 )

[0220] +0.3·(+1)·exp(-0.1·∥x-x3∥ 2 )-1.5

[0221] Predict a new data point:

[0222] Suppose there is a new data point x = [15, 23, 7.1], calculate its predicted value:

[0223] Support vector x1 = [10, 20, 7.2];

[0224] Support vector x2 = [12, 22, 7.1];

[0225] Support vector x3 = [14, 24, 7.0];

[0226] Calculate the Euclidean distance:

[0227]

[0228] Calculate the kernel function value:

[0229] K(x, x1) = exp(-0.1·5.83 2 )=exp(-3.3989)≈0.033

[0230] K(x, x2) = exp(-0.1·3.16 2)=exp(-0.9986)≈0.367

[0231] K(x, x3) = exp(-0.1·1.42 2 )=exp(-0.2016)≈0.817

[0232] Calculate the predicted value:

[0233] f(x)=0.5·(-1)·0.033+0.2·(-1)·0.367+0.3·(+1)·0.817-1.5

[0234] f(x)=-0.0165-0.0734+0.2451-1.5

[0235] f(x)≈-1.3448

[0236] The predicted value f(x)≈-1.3448. Since the predicted value is a negative number, according to the classification rules of the support vector machine, this data point is predicted to be free of biological contamination (labeled as -1).

[0237] Through the above calculations, it can be concluded that under the given characteristic data, the new data point x = [15, 23, 7.1] is predicted to be free of biological contamination. This indicates that the current water quality conditions have not yet reached the threshold of biological contamination, but continuous monitoring is still required to ensure water quality safety.

[0238] 105. Utilize the biological contamination prediction report and the problem area information reflected in the alarm notification record to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, and generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system.

[0239] In this step, the detection frequency of each monitoring point is adjusted according to the biological contamination prediction report and alarm notification records. The detection frequency is increased in high-risk areas and reduced in low-risk areas, thereby optimizing the monitoring strategy and improving the system's response speed and resource utilization efficiency.

[0240] First, based on the biological contamination prediction report, determine which areas are high-risk areas. Second, for these areas, increase the frequency of ATP fluorescence detection; for low-risk areas, appropriately reduce the detection frequency. This can more reasonably allocate detection resources and improve the overall efficiency of the system.

[0241] In the present application example, in the water quality monitoring system, according to the forecast report, several areas are found to have a higher risk of biological contamination in the future. Therefore, the ATP fluorescence detection frequency in these areas is increased from once an hour to once every half an hour. For other low-risk areas, the detection frequency is reduced from once an hour to once every two hours. This adjustment not only improves the response speed to potential pollution incidents, but also optimizes the resource allocation of the entire system.

[0242] Optionally, the use of the biological contamination prediction report in step 105, combined with the problem area information reflected in the alarm notification record, adjusts the ATP fluorescence detection frequency setting of each monitoring point, increases the detection frequency for monitoring points predicted to be high-risk areas, and reduces the detection frequency for low-risk areas, to generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system, including: using the prediction results, prediction confidence and potential impact analysis in the biological contamination prediction report to evaluate the future biological contamination risk of each monitoring point to obtain a risk area assessment result; based on the risk area assessment result, combined with the problem area information reflected in the alarm notification record, comprehensively analyze the actual contamination risk level of each monitoring point to generate each risk assessment reports for monitoring points; based on the risk assessment reports of the monitoring points, for monitoring points predicted to be high-risk areas, by adjusting the ATP fluorescence detection frequency setting, increasing the detection frequency, ensuring timely detection and response to biological contamination incidents, and generating monitoring strategies for high-risk areas; for monitoring points predicted to be low-risk areas, also based on the risk assessment reports of the monitoring points, appropriately reducing the detection frequency to reduce resource waste, improve the operating efficiency of the monitoring system, and generate monitoring strategies for low-risk areas; integrating the monitoring strategies for high-risk areas and low-risk areas to form a comprehensive and optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system, and ensure effective monitoring and management of biological contamination.

[0243] In this step, the biocontamination prediction report includes prediction results, prediction confidence, and potential impact analysis, which are used to evaluate the biocontamination risk of each monitoring point in the future. The alarm notification record contains past biocontamination incidents and their handling, reflecting the information of the actual problem area. The risk assessment report combines the prediction results and historical data to determine the actual contamination risk level of each monitoring point. By adjusting the ATP fluorescence detection frequency setting, the monitoring density in high-risk areas can be increased to ensure timely detection and response to biocontamination incidents, while reducing the detection frequency in low-risk areas to save resources and improve the overall efficiency of the monitoring system.

[0244] First, the prediction results, prediction confidence and potential impact analysis in the biological contamination prediction report are used to evaluate the future biological contamination risk of each monitoring point and obtain the risk area assessment results. Then, based on these risk area assessment results, combined with the problem area information reflected in the alarm notification record, the actual contamination risk level of each monitoring point is comprehensively analyzed to generate a risk assessment report for each monitoring point. According to the risk assessment report, for monitoring points predicted to be high-risk areas, the detection frequency is increased by adjusting the ATP fluorescence detection frequency setting to ensure that biological contamination events can be discovered and responded to in a timely manner, and a monitoring strategy for high-risk areas is generated. For monitoring points predicted to be low-risk areas, the detection frequency is appropriately reduced to reduce resource waste, improve the operating efficiency of the monitoring system, and generate a monitoring strategy for low-risk areas. Finally, the monitoring strategies for high-risk areas and low-risk areas are integrated to form a comprehensive and optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system and ensure effective monitoring and management of biological contamination.

[0245] In an embodiment of the present application, in a water quality monitoring project of a city water supply system, ATP fluorescence detection sensors are deployed at multiple key nodes to automatically collect the fluorescence intensity value and environmental parameters of water samples once an hour. The system generates a biological contamination prediction report, which includes the prediction results, prediction confidence and potential impact analysis of each monitoring point in the next week. For example, the prediction report shows that certain areas have a higher risk of biological contamination in the next week, while other areas have a lower risk.

[0246] Based on these prediction results, combined with the problem area information reflected in the alarm notification records of the past year, the system comprehensively analyzes the actual pollution risk level of each monitoring point and generates a risk assessment report for each monitoring point. For example, an area has experienced multiple biological contamination incidents in the past year, and the prediction results show that the area will still have a high risk in the next week, so it is marked as a high-risk area.

[0247] Figure 2 A schematic diagram of the structure of a remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things is provided for the embodiment of the present application, such as Figure 2 As shown, the system includes:

[0248] The collection and processing module 21 is used to collect the original detection data generated by the ATP fluorescence detection sensor, wherein the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and perform real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio;

[0249] The transmission module 22 is used to efficiently transmit the processed detection data to the cloud data center via the Internet of Things technology, and generate comprehensive detection data after secure transmission together with the stored historical detection data;

[0250] An analysis activation module 23 is used to use a time series analysis algorithm to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data, identify the change pattern of the biological contamination level, and activate a multi-level alarm response system when the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data. The multi-level alarm response system can select a suitable communication channel according to different levels of alarm types to send customized alarm information to designated managers and generate an alarm notification record;

[0251] A construction module 24 is used to construct a biological contamination prediction model using a machine learning algorithm based on the alarm notification record, the historical detection data and the environmental parameters in the comprehensive detection data after the secure transmission, combined with the real-time detection data, to generate a biological contamination prediction report;

[0252] The adjustment generation module 25 is used to use the biological contamination prediction report, combined with the problem area information reflected in the alarm notification record, to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, and generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system.

[0253] Figure 2 The remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things can be performed Figure 1 The implementation principle and technical effect of the remote monitoring and data analysis method based on ATP fluorescence detection and the Internet of Things described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0254] In one possible design, Figure 2 The remote monitoring and data analysis system based on ATP fluorescence detection and the Internet of Things of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0255] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0256] The processing component 32 is used to: collect the original detection data generated by the ATP fluorescence detection sensor, the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and perform real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio; based on the processed detection data, efficiently transmit it to the cloud data center via the Internet of Things technology, and generate comprehensive detection data after safe transmission together with the stored historical detection data; use a time series analysis algorithm to perform a comprehensive analysis on the detection data in combination with the environmental parameters in the comprehensive detection data after safe transmission to identify the change pattern of the biological contamination level, and when the detection data exceeds a preset threshold value dynamically adjusted based on the historical detection data, activate a multi-level alarm response system, the multi-level alarm response system The alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records; based on the alarm notification records, historical detection data and environmental parameters in the comprehensive detection data after secure transmission, combined with real-time detection data, a machine learning algorithm is used to build a biological contamination prediction model to generate a biological contamination prediction report; using the biological contamination prediction report, combined with the problem area information reflected in the alarm notification record, the ATP fluorescence detection frequency setting of each monitoring point is adjusted, the detection frequency is increased for monitoring points predicted to be high-risk areas, and the detection frequency is reduced for low-risk areas, and an optimized monitoring strategy is generated to improve the response speed and resource utilization efficiency of the monitoring system.

[0257] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital data processors (DSPs), digital data processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0258] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0259] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0260] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0261] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0262] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0263] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a remote monitoring and data analysis method based on ATP fluorescence detection and the Internet of Things.

[0264] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0265] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0266] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0267] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things, characterized in that: include: Collecting the original detection data generated by the ATP fluorescence detection sensor, the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and performing real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio; Based on the processed detection data, the processed detection data is efficiently transmitted to the cloud data center via the Internet of Things technology, and together with the stored historical detection data, the comprehensive detection data after secure transmission is generated; A time series analysis algorithm is used to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data to identify the change pattern of the biological contamination level. When the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data, a multi-level alarm response system is activated. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records; Based on the alarm notification records, historical detection data and environmental parameters in the securely transmitted comprehensive detection data, combined with real-time detection data, a machine learning algorithm is used to construct a biological contamination prediction model to generate a biological contamination prediction report; By using the biological contamination prediction report and combining it with the problem area information reflected in the alarm notification record, the ATP fluorescence detection frequency setting of each monitoring point is adjusted, the detection frequency is increased for monitoring points predicted to be high-risk areas, and the detection frequency is reduced for low-risk areas, and an optimized monitoring strategy is generated to improve the response speed and resource utilization efficiency of the monitoring system.

2. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 1, characterized in that: The time series analysis algorithm is used to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data to identify the change pattern of the biological contamination level. When the detection data exceeds the preset threshold value dynamically adjusted based on the historical detection data, the multi-level alarm response system is activated. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records, including: Using a time series analysis algorithm to analyze the fluorescence intensity values ​​and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extract key indicators reflecting the biological contamination level and their changing trends over time, and obtain a time series analysis result of the biological contamination level; Based on the time series analysis results of the biological contamination level, compared with the stored historical detection data, a statistical method is used to dynamically adjust the preset warning threshold to obtain a dynamic warning threshold that adapts to the changes in the biological contamination level under different environmental conditions; According to the dynamic warning threshold, the time series analysis result of the biological contamination level is monitored, and when the detected fluorescence intensity value exceeds the dynamic warning threshold, a multi-level alarm response mechanism is immediately activated to obtain an alarm trigger signal; Based on the alarm trigger signal, the alarm level is automatically determined according to the severity of the alarm, and the most appropriate communication channel is selected to send customized alarm information including the alarm level, specific pollution location, cause analysis and preliminary recommended response measures to the preset management personnel or emergency team, and an alarm notification record is generated.

3. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 2 is characterized in that: The time series analysis algorithm is used to analyze the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extract the key indicators reflecting the biological contamination level and its changing trend over time, and obtain the time series analysis results of the biological contamination level, including: Using time series decomposition technology, the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are decomposed and processed to separate the three components of long-term trend, seasonal fluctuation and random fluctuation, and obtain preliminary decomposition results; Based on the preliminary decomposition results, a statistical regression analysis method is applied to identify the main environmental factors that affect the change of fluorescence intensity values, a mathematical model between the fluorescence intensity values ​​and environmental parameters is established, and an environmental factor influence model is obtained; Using the environmental factor impact model, combined with the long-term trend and seasonal fluctuations in the preliminary decomposition results, the biological contamination level is predicted, key indicators reflecting the biological contamination level are extracted, including average fluorescence intensity and fluorescence intensity change rate, and a key indicator set is generated; According to the key indicator set, the changing trend of the biological contamination level over time is analyzed, the rising, falling or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated.

4. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 3 is characterized in that: The time series analysis algorithm is used to analyze the fluorescence intensity value and the accompanying environmental parameters in the comprehensive detection data after the secure transmission, extract the key indicators reflecting the biological contamination level and its changing trend over time, and obtain the time series analysis results of the biological contamination level, including: By using the time series decomposition technology, the fluorescence intensity value F(t) and the accompanying environmental parameters in the comprehensive detection data after the secure transmission are decomposed and processed, and the three components of the long-term trend T(t), seasonal fluctuation S(t) and random fluctuation R(t) are separated to obtain a preliminary decomposition result, namely, F(t)=T(t)+S(t)+R(t), wherein t represents time, F(t) represents the fluorescence intensity value, which represents the fluorescence intensity at time t; T(t) represents the long-term trend, which represents the long-term change trend of the fluorescence intensity value; S(t) represents the seasonal fluctuation, which represents the periodic change of the fluorescence intensity value; R(t) represents the random fluctuation, which represents the random change part of the fluorescence intensity value; Based on the preliminary decomposition results, statistical regression analysis was applied to identify the main environmental factors affecting the changes in fluorescence intensity values. i (t), establish the fluorescence intensity value F(t) and the environmental parameter E i (t) The nonlinear mathematical model between the two factors is as follows: Among them: E i (t) represents the environmental parameter, which represents the i-th environmental parameter at time t; β0 is the intercept term, β i , γ i and δ i are the linear, quadratic and cubic regression coefficients of the i-th environmental parameter, α1 and α2 are the regression coefficients of the long-term trend and seasonal fluctuation, n is the number of environmental parameters, ∈ is the error term, and the environmental factor impact model is obtained; The environmental factor impact model is used to predict the biological contamination level in combination with the long-term trend T(t) and seasonal fluctuation S(t) in the preliminary decomposition results, and key indicators reflecting the biological contamination level are extracted: The mean fluorescence intensity was calculated using the following formula: The fluorescence intensity change rate ΔF(t) was calculated using the following formula: Wherein, Δt represents the time interval, which indicates the time interval for calculating the rate of change of fluorescence intensity; Weighted moving average fluorescence intensity WMA (F(t)): Among them, w i is the weight, k is the time window length; i represents the index within the time window; The exponentially smoothed fluorescence intensity ES(F(t)) was calculated using the following formula: ES(F(t))=αF(t)+(1-α)ES(F(t-1)) Among them, α is a smoothing factor, which usually takes a value between 0 and 1; generate a set of key indicators; According to the key indicator set, the changing trend of the biological contamination level over time is analyzed, the rising, falling or stable state of the biological contamination level is identified, and the time series analysis results of the biological contamination level are generated.

5. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 1, characterized in that: The method of constructing a biological contamination prediction model based on the alarm notification record, historical detection data and environmental parameters in the comprehensive detection data after secure transmission, combined with real-time detection data, using a machine learning algorithm to generate a biological contamination prediction report includes: Collect and preprocess alarm notification records, historical test data, environmental parameters in securely transmitted comprehensive test data, and real-time test data to obtain high-quality data sets; Based on high-quality data sets, feature selection and transformation are performed to determine the key features that affect biological pollution prediction, and some features are transformed or encoded as necessary to obtain feature data after feature selection and transformation; Using the feature data after feature selection and transformation, support vector machine is selected as the machine learning algorithm to build a biological contamination prediction model. At the same time, appropriate kernel functions are selected and related parameters are adjusted to optimize model performance. Based on the constructed biological contamination prediction model, the model is trained and verified using the cross-validation method to ensure that the model has good generalization ability and prediction accuracy, and the optimized biological contamination prediction model is obtained; The optimized biological contamination prediction model is used to predict new or future data and generate a detailed biological contamination prediction report, which includes the predicted time range, prediction results, potential high-risk areas and corresponding recommended measures.

6. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 5, characterized in that: The method uses the feature data after feature selection and conversion, selects support vector machine as the machine learning algorithm, constructs a biological contamination prediction model, and selects a suitable kernel function to optimize the model performance, including: Using the feature data after feature selection and transformation, the support vector machine is selected as the machine learning algorithm to model the biological pollution prediction task and obtain a preliminary vector machine model; According to the requirements of the biological contamination prediction task, a suitable kernel function is selected for the vector machine model, and the selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, so as to obtain a vector machine model with strong nonlinear mapping ability to optimize model performance; The penalty parameters and kernel function parameters are adjusted by using a preliminary vector machine model. The adjustment process uses a parameter optimization method to find the best parameter combination within a predefined parameter range to obtain an optimized parameter combination.

7. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 6, characterized in that: The method uses the feature data after feature selection and conversion, selects support vector machine as the machine learning algorithm, constructs a biological contamination prediction model, and selects a suitable kernel function to optimize the model performance, including: Using the feature data after feature selection and transformation, the support vector machine is selected as the machine learning algorithm to model the biological pollution prediction task and obtain a preliminary vector machine model; The basic form of the vector machine model f(x) is expressed as: Where N represents the number of support vectors, α i is the Lagrange multiplier, y i is the label of each support vector (+1 or -1), K(x, x i ) is the kernel function, b is the bias term; According to the requirements of the biological pollution prediction task, a suitable kernel function is selected for the vector machine model. The selection of the kernel function is based on the nonlinear mapping ability and generalization ability of the model, and a vector machine model with strong nonlinear mapping ability is obtained; commonly used kernel functions include linear kernel, polynomial kernel and radial basis function kernel; the mathematical expression of the basis function kernel K(x, x i )for: K(x,x i )=exp(-γ∥x-x i ∥ 2 ) Among them, γ is the kernel function parameter, ∥xx i ∥ represents the Euclidean distance between two vectors.

8. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 1, characterized in that: The biological contamination prediction report is used in combination with the problem area information reflected in the alarm notification record to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, to generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system, including: Using the prediction results, prediction confidence and potential impact analysis in the biological contamination prediction report, the future biological contamination risk of each monitoring point is evaluated to obtain the risk area assessment result; Based on the risk area assessment results, combined with the problem area information reflected in the alarm notification record, the actual pollution risk level of each monitoring point is comprehensively analyzed to generate a risk assessment report for each monitoring point; According to the risk assessment report of each monitoring point, for monitoring points predicted to be high-risk areas, the detection frequency is increased by adjusting the ATP fluorescence detection frequency setting to ensure that biological contamination events can be discovered and responded to in a timely manner, and a monitoring strategy for high-risk areas is generated; For monitoring points predicted to be low-risk areas, based on the risk assessment reports of the monitoring points, the detection frequency is appropriately reduced to reduce resource waste, improve the operating efficiency of the monitoring system, and generate monitoring strategies for low-risk areas; The monitoring strategies for the high-risk areas and the low-risk areas are integrated to form a comprehensive and optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system and ensure effective monitoring and management of biological contamination.

9. The remote monitoring and data analysis method based on ATP fluorescence detection and Internet of Things according to claim 1, characterized in that: The processed detection data is efficiently transmitted to the cloud data center via the Internet of Things technology, and together with the stored historical detection data, generates comprehensive detection data after secure transmission, including: Using the processed detection data to form a structured detection data packet, thereby obtaining a structured detection data packet; Based on the structured detection data packet, the detection data packet is encrypted using the security encryption protocol in the Internet of Things technology to ensure the security of the data during transmission, prevent the data from being stolen or tampered with, and generate an encrypted detection data packet; The encrypted detection data packet is efficiently transmitted to the cloud data center through the Internet of Things network, and data compression technology is used to reduce the amount of data transmission during the transmission process. At the same time, error control technology is used to ensure the integrity of data transmission, so as to obtain the detection data after secure transmission; In the cloud data center, the securely transmitted detection data is integrated with the stored historical detection data to ensure the consistency and continuity of the new and old data, and to generate securely transmitted comprehensive detection data.

10. A remote monitoring and data analysis system based on ATP fluorescence detection and Internet of Things, characterized in that: include: A collection and processing module is used to collect the original detection data generated by the ATP fluorescence detection sensor, wherein the original detection data includes the fluorescence intensity value and its accompanying environmental parameters, and to perform real-time denoising on the original detection data to obtain stable processed detection data with a high signal-to-noise ratio; A transmission module, used to efficiently transmit the processed detection data to a cloud data center via the Internet of Things technology, and generate comprehensive detection data after secure transmission together with the stored historical detection data; An analysis activation module is used to use a time series analysis algorithm to comprehensively analyze the detection data in combination with the environmental parameters in the securely transmitted comprehensive detection data, identify the change pattern of the biological contamination level, and activate a multi-level alarm response system when the detection data exceeds a preset threshold value dynamically adjusted based on historical detection data. The multi-level alarm response system can select appropriate communication channels according to different levels of alarm types to send customized alarm information to designated managers and generate alarm notification records; A construction module is used to construct a biological contamination prediction model using a machine learning algorithm based on the environmental parameters in the alarm notification record, historical detection data and the comprehensive detection data after secure transmission, combined with real-time detection data, to generate a biological contamination prediction report; The adjustment generation module is used to use the biological contamination prediction report, combined with the problem area information reflected in the alarm notification record, to adjust the ATP fluorescence detection frequency setting of each monitoring point, increase the detection frequency for monitoring points predicted to be high-risk areas, and reduce the detection frequency for low-risk areas, and generate an optimized monitoring strategy to improve the response speed and resource utilization efficiency of the monitoring system.

Images