Intelligent Acquisition Management Method for Water Service Data Based on Machine Learning

Abstract

The present invention relates to the technical field of water management, and particularly to an intelligent acquisition management method for water service data based on machine learning. The method includes the following steps: S1: Collect the devices and equipment locations for collecting water service data, obtain the water service data and perform preprocessing to determine the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data; S2: According to the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data, reserve a dynamically adjustable position range for the devices and equipment for collecting water service data. The present invention ensures quality and consistency through data preprocessing, analyzes the relationship between the device location and data accuracy using the Transformer model to identify the optimal location; predicts the optimal location and optimizes device control using the LSTM model; constructs a dynamic adjustment sequence to improve accuracy; predicts risks and adjusts the location using the RNN model to form a closed-loop optimization management, realizing intelligent and efficient data acquisition management.

Description

Technical Field

[0001] The present invention relates to the technical field of water management, and particularly to an intelligent acquisition and management method for water service data based on machine learning. Background Art

[0002] The intelligent acquisition and management method for water service data covers multiple aspects such as data acquisition, transmission, storage, processing, analysis, and visualization, aiming to improve the accuracy of data and management efficiency through intelligent means. The advantages of the existing intelligent acquisition and management method for water service data lie in the efficient and accurate acquisition and real-time analysis of data through automated and intelligent technologies, enhancing the comprehensiveness of monitoring and management efficiency. However, in lakes, sensors at fixed positions cannot capture the dynamic changes in water quality (such as changes in water flow velocity and dissolved oxygen levels), especially during high-flow periods or emergencies (such as algal blooms), resulting in data distortion and decision-making lags, affecting the response speed and management effect of the system.

[0003] The advantages of the intelligent acquisition and management method for water service data based on machine learning lie in its ability to automatically identify and predict water quality change patterns through machine learning technologies, thereby improving the accuracy of data acquisition and the scientific nature of management decisions. However, there are also challenges in ensuring the objectivity and accuracy of water service data in the acquisition method based on machine learning. The adaptability of the model is poor, and it cannot capture the real changes in water quality in a timely manner when facing complex and variable hydrological conditions, resulting in data distortion. In addition, fixed-position sensors are difficult to reflect dynamic changes, especially during high-flow periods or emergencies, affecting the comprehensiveness and accuracy of data, thus reducing the response speed of the system and the reliability of decision-making.

[0004] Therefore, the research of this solution is of great necessity and practical significance for solving the above problems and further optimizing the intelligent acquisition and management method for water service data based on machine learning. Summary of the Invention

[0005] In order to overcome the disadvantage of poor adaptability of the intelligent acquisition of water service data, the present invention provides an intelligent acquisition and management method for water service data based on machine learning.

[0006] The technical implementation solution of the present invention is as follows: The intelligent acquisition and management method for water service data based on machine learning includes the following steps:

[0007] S1: Collect the devices and equipment positions for collecting water service data, obtain the water service data for preprocessing, and determine the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data;

[0008] S2: According to the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data, reserve a dynamic adjustment position range for the devices and equipment for collecting water service data and perform optimized control;

[0009] S3: Classify the collected water utility data and use the classified data for risk prediction;

[0010] S4: Determine the final intelligent acquisition management method for water utility data according to the prediction results.

[0011] Preferably, the device and equipment positions for collecting water utility data are collected, the water utility data is obtained and preprocessed, and the relationship between the device and equipment for collecting water utility data and the accuracy of water utility data is determined, including: the preprocessing includes cleaning and standardizing the data; for the water body stratification phenomenon, the data changes at different depth levels are collected; the initial collection position of the device and equipment for collecting water utility data is defined as the first position, and the water utility data collected under the first position is defined as the first data; the first position includes the positions of all devices and equipment for collecting water utility data in the water utility data collection area, and the first data includes all water utility data collected under the first position of all devices and equipment for collecting water utility data in the water utility data collection area; for the water body stratification phenomenon, the accuracy of the water utility data under the first position is analyzed; the water utility data includes parameters reflecting the water body stratification phenomenon.

[0012] Preferably, the accuracy analysis of the first data under the first position for water utility data includes: for the influence of the water body stratification phenomenon, taking the process positions of the device and equipment for collecting water utility data reaching the first position as position comparison data, and recording the position changes recorded at different depth levels; and recording the external environmental parameters; at the same time, paying attention to the different water quality conditions experienced by the device and equipment when moving between different depth levels; taking the water utility data collected during the process of the device and equipment for collecting water utility data reaching the first position as the collected data comparison data; obtaining the position comparison data training set and the collected data comparison data training set, constructing a Transformer model, inputting the training set data into the Transformer model, and introducing a feature engineering specifically designed for the water body stratification phenomenon to obtain a trained Transformer model. The model is specially optimized to adapt to the water body stratification phenomenon and can effectively capture the data characteristics at different depth levels; using the Transformer model to analyze the position comparison data and the collected data comparison data, not only evaluating the data accuracy at different depth levels, but also aiming at the influence of water body stratification on the data collection and transmission process, so as to obtain the relationship between the device and equipment for collecting water utility data and the accuracy of water utility data.

[0013] Preferably, based on the relationship between the devices and equipment for collecting water service data and the accuracy of water service data, a dynamic adjustment position range is reserved for the devices and equipment for collecting water service data, and optimization control is performed, including: obtaining the relationship between the devices and equipment for collecting water service data and the accuracy of water service data, sorting them according to the level of accuracy, taking the position with the highest accuracy as the first preferred position, aiming at the influence of water body stratification phenomenon, combining the positions of the collecting devices and equipment and the accuracy of the collected data in the process of analyzing the relationship between the devices and equipment for collecting water service data and the accuracy of water service data into a sequence, constructing an LSTM model, obtaining sequence training set data, inputting the training set data into the LSTM model, obtaining a trained LSTM model, using the trained LSTM model to obtain the optimal position after the first position of the water service data, and defining it as the second preferred position; taking the distance length between the first preferred position and the second preferred position as the dynamic adjustment position range, and performing optimization control based on the dynamic adjustment position range.

[0014] Preferably, the optimization control based on the dynamic adjustment position range includes: obtaining all the first positions of the devices and equipment for collecting water service data, taking the first position as the center, obtaining the collection areas of the water service collection devices and equipment within the dynamic adjustment range, and defining them as the effective collection area and the farthest collection area; considering the influence of different depth levels, obtaining the effective collection area and the farthest collection area of all the water service collection devices and equipment under the dynamic adjustment range, taking the intersection of the effective collection areas of all the devices and equipment for collecting water service data as the shortest adjustment distance, and taking the intersection of the farthest collection areas as the longest adjustment distance. When the devices and equipment for collecting water service data are at the shortest adjustment distance, adjust their positions within the dynamic adjustment range. When the devices and equipment for collecting water service data are at the longest adjustment distance, shrink the collection areas of the devices and equipment; and constructing a dynamic adjustment sequence for the devices and equipment for collecting water service data.

[0015] Preferably, constructing a dynamic adjustment sequence for the devices and equipment for collecting water service data includes: obtaining the first position within the collection area as the static sequence, obtaining the dynamically adjusted positions within the collection area as the dynamic sequence, aiming at the data changes at different depth levels, obtaining the static sequence data training set and the dynamic sequence data training set, constructing a virtual adjustment model, inputting the training set data into the virtual adjustment model, obtaining a trained virtual adjustment model, using the virtual adjustment model to obtain the adjustment amount of the devices and equipment during the process of collecting water service data at the first position, and then making adjustments.

[0016] Preferably, in the process of obtaining the adjustment amount of the device and equipment for collecting water service data at the first position by using the virtual adjustment model and then making adjustments, the following steps are included: constructing a plane rectangular coordinate system with the collection area as the center point, the water flow direction as the X-axis, and the direction perpendicular to the X-axis horizontally as the Y-axis; the static sequence includes fixed points, the first position, and data collection accuracy, and the dynamic sequence includes fixed points, a dynamic adjustment range, and data collection accuracy. The fixed points include, but are not limited to, the data receiving points of the devices and equipment for collecting water service data or the positions where the fixtures for towing and fixing the devices and equipment for collecting water service data are located; calibrating static points (the points where the first position is located) and dynamic points (the points within the dynamic adjustment range) in the plane rectangular coordinate system to form a first sequence (including the static sequence and the dynamic sequence), calculating the distances from the fixed points to the first position and the maximum adjustment range through the Euclidean distance formula, and updating the first sequence to form a second sequence (a fusion sequence, adding the static sequence to the dynamic sequence). The second sequence includes the minimum distance and the maximum distance, the first position, and data collection accuracy, and considers the data changes at different depth levels; then segmenting according to the water service data collection barrier medium to generate a distance adjustment sequence and a data collection sequence.

[0017] Preferably, the second sequence includes the minimum distance and the maximum distance, the first position, and data collection accuracy. Then, segmenting according to the water service data collection barrier medium to generate a distance adjustment sequence and a data collection sequence includes: the barrier medium includes, but is not limited to, network propagation barriers and material propagation barriers. For the data changes at different depth levels, traverse the distance adjustment sequence and the data collection sequence to generate a set of effective distance adjustment parameters and a set of effective data collection parameters, obtain the intersection of the set of effective distance adjustment parameters and the set of effective data collection parameters, and use the distance amount that needs to be adjusted during the process of obtaining the intersection as the adjustment amount for adjustment.

[0018] Preferably, classifying the collected water service data and using the classified data for risk prediction includes: obtaining the fluctuation period and the stable period of the water service data in the collection area, extracting the influencing factors for water service data collection during the fluctuation period and the stable period, evaluating the changes of the influencing factors at different depth levels, introducing a weight mechanism to dynamically adjust the weights according to the importance of the data for the influence of the water body stratification phenomenon on different depth levels, classifying the adjustment data of the water service data collection devices and equipment during the stable period as safe adjustment data, classifying the influencing factors of the water service data collection during the fluctuation period as dangerous adjustment data, constructing an RNN model, obtaining a training set of dangerous adjustment data, inputting the training set data into the RNN model, and introducing a feature selection mechanism optimized for the water body stratification phenomenon to obtain a trained RNN model, and using the RNN model to make further adjustments to the devices and equipment for collecting water service data.

[0019] Preferably, the method for intelligently collecting and managing water service data determined according to the prediction result includes: obtaining the first positions of devices and equipment during the water service data collection process and their positions during the dynamic adjustment process, and simultaneously obtaining the water service data, forming a cycle for the whole process and continuously optimizing it, and outputting the optimized method for intelligently collecting and managing water service data.

[0020] Beneficial effects: Through preprocessing, dynamic adjustment and optimization, risk prediction and closed-loop management, the present invention significantly improves the objectivity and accuracy of water service data collection:

[0021] 1. Data quality guarantee: Data cleaning and standardization are carried out in the preprocessing stage to ensure data consistency and reliability, reduce noise interference, and are especially applicable to complex and changeable lake environments.

[0022] 2. Intelligent position optimization: Based on the relationship between the device position and data accuracy, the best collection position is automatically identified and the dynamic adjustment range is adjusted to ensure that each collection point provides the most representative data, enhancing stability and representativeness, especially in the case of frequent water flow changes.

[0023] 3. Real-time precise control: A dynamic adjustment sequence is constructed, the system predicts and executes the best adjustment amount, realizes real-time precise control, improves flexibility and response speed, and ensures accurate and timely data under different hydrological conditions.

[0024] 4. Risk foresight and prevention: Potential risks (such as algal blooms) are identified in advance through classification and risk prediction, and the strategy is adjusted to avoid the influence of uncertain factors, improving the predictability and response ability of the system.

[0025] 5. Closed-loop optimization management: The whole process constitutes a closed-loop management, continuously optimizing the method to ensure long-term high efficiency and accuracy, and realizing intelligent management of the whole process. Description of the drawings

[0026] Figure 1 It is a flowchart of the method for intelligently collecting and managing water service data based on machine learning of the present invention;

[0027] Figure 2 It is a schematic diagram of the process for determining the dynamic adjustment range of the present invention. Detailed implementation manners

[0028] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] Intelligent acquisition management method for water service data based on machine learning, such as Figure 1 shown, including the following steps:

[0030] S1: Collect the locations of the devices and equipment for collecting water service data, obtain the water service data for preprocessing, and determine the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data;

[0031] S2: According to the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data, reserve a dynamic adjustment position range for the devices and equipment for collecting water service data and perform optimized control;

[0032] S3: Classify the collected water service data and use the classified data for risk prediction;

[0033] S4: Determine the final intelligent acquisition management method for water service data according to the prediction results.

[0034] Collect the locations of the devices and equipment for collecting water service data, obtain the water service data for preprocessing, and determine the relationship between the devices and equipment for collecting water service data and the accuracy of the water service data, including: the preprocessing includes cleaning and standardizing the data; for the water body stratification phenomenon, collect the data changes at different depth levels; define the initial collection position of the devices and equipment for collecting water service data as the first position, and define the water service data collected at the first position as the first data; the first position includes the locations of all the devices and equipment for collecting water service data in the water service data collection area, and the first data includes all the water service data collected at the first position of all the devices and equipment for collecting water service data in the water service data collection area; for the water body stratification phenomenon, perform water service data accuracy analysis on the first data at the first position; the water service data includes parameters reflecting the water body stratification phenomenon.

[0035] For further illustration, assume that there are 10 buoys in a lake for collecting water service data. Record the locations of these 10 buoys in sequence and define them as the first position. At the same time, obtain the water service data collected by the 10 buoys at the first position. It should be noted that during the entire collection process, other water service data (such as temperature, dissolved oxygen, pH value) remains consistent, and only the water body stratification phenomenon changes.

[0036] Conduct water service data accuracy analysis on the first data at the first position, including: regarding the influence of water body stratification phenomenon, using the process positions of the devices and equipment for collecting water service data when reaching the first position as position comparison data, recording the position changes at different depth levels; and recording external environmental parameters; meanwhile, paying attention to the different water quality conditions experienced by the devices and equipment when moving between different depth levels; using the water service data collected during the process of the devices and equipment for collecting water service data reaching the first position as the collected data comparison data; obtaining the position comparison data training set and the collected data comparison data training set, constructing a Transformer model, inputting the training set data into the Transformer model, and introducing feature engineering specifically designed for the water body stratification phenomenon to obtain a trained Transformer model. The model is specially optimized to adapt to the water body stratification phenomenon and can effectively capture the data characteristics at different depth levels; using the Transformer model to analyze the position comparison data and the collected data comparison data, not only evaluating the data accuracy at different depth levels, but also aiming at the influence of water body stratification on the data collection and transmission process, so as to obtain the relationship between the devices and equipment for collecting water service data and the water service data accuracy.

[0037] For further illustration, assume that there are 10 buoys used to collect lake water service data, record N positions of the 10 buoys from the starting position of the fixed buoy to the first position as the position comparison data, and use the water service data collected by the 10 buoys during the process of reaching the first position as the collected data comparison data; the position comparison data is used to compare with the first position, and the collected data comparison data is used to compare with the data collected during the process from the fixed point to the first position; the external environmental parameters include temperature and water flow velocity.

[0038] According to the relationship between the devices and equipment for collecting water service data and the water service data accuracy, reserve a dynamic adjustment position range for the devices and equipment for collecting water service data and conduct optimized control, including: obtaining the relationship between the devices and equipment for collecting water service data and the water service data accuracy, sorting them according to the level of accuracy, taking the position with the highest accuracy as the first preferred position, regarding the influence of the water body stratification phenomenon, combining the positions of the collection devices and equipment and the accuracy of the collected data during the process of analyzing the relationship between the devices and equipment for collecting water service data and the water service data accuracy into a sequence, constructing an LSTM model, obtaining the sequence training set data, inputting the training set data into the LSTM model, obtaining a trained LSTM model, using the trained LSTM model to obtain the optimal position after the first position of the water service data and defining it as the second preferred position; using the distance length between the first preferred position and the second preferred position as the dynamic adjustment position range and conducting optimized control based on the dynamic adjustment position range.

[0039] For further illustration, still assuming a lake scenario, the first preferred position is the optimal position during the process from the fixed point to the first position, that is, the position with the highest accuracy of water service data collection. The second preferred position is the optimal position other than the first position obtained through the analysis of the buoy's process from the fixed point to the first position by the LSTM model. For example, assume that the cable of the buoy is released by a total of 10 meters starting from the fixed point, and the first preferred position is assumed to be at 8 meters. Then, the second preferred position after the analysis by the LSTM model is at 12 meters (assumed value). The dynamic adjustment position range is 8 - 10 meters, that is, the cable retraction range is 0 - 2 meters and the release range is 0 - 2 meters.

[0040] Based on the dynamic adjustment position range for optimization control, it includes: obtaining all the first positions where water service data is collected, taking the first position as the center, obtaining the collection areas of water service collection devices and equipment within the dynamic adjustment range, and defining them as the effective collection area and the farthest collection area; considering the influence of different depth levels, obtaining the effective collection area and the farthest collection area of all water service collection devices and equipment under the dynamic adjustment range, taking the intersection of the effective collection areas of all devices and equipment collecting water service data as the shortest adjustment distance, and taking the intersection of the farthest collection areas as the longest adjustment distance. When the devices and equipment collecting water service data are at the shortest adjustment distance, adjust their positions within the dynamic adjustment range. When the devices and equipment collecting water service data are at the longest adjustment distance, shrink the collection areas of the devices and equipment; and construct a dynamic adjustment sequence for the devices and equipment collecting water service data.

[0041] For further illustration, still taking the lake scenario as an example, the effective collection area is the effectiveness of the buoy in collecting water service data. That is, assume that the buoy collects water service data within the dynamic adjustment range of 8 - 12 meters. However, if the water flow suddenly speeds up or there are other obstacles such as floating branches or waterweeds at 8 meters or 12 meters, resulting in inaccurate collection of some water service data by the buoy, then this area is the farthest collection area; otherwise, it is the effective collection area. For ease of understanding, assume that 8 - 12 meters is the dynamic adjustment range, 8 - 8.5 and 11.5 - 12 are the farthest adjustment distances, and 8.5 - 11.5 is the effective adjustment distance. The intersection of the effective collection areas of all devices and equipment collecting water service data being taken as the shortest adjustment distance means that, assuming the data collected by buoy A is within the effective collection range of 8.5 - 11.5, and the data collected by buoy B is within the effective collection range of 8.5 - 11.5. If the collected data is the same and both are valid data, then the cable retraction or release range of buoy A and buoy B is 0, or the farthest adjustment distance within the effective collection range. Taking the intersection of the farthest collection areas as the longest adjustment distance means that if the farthest collection distances of buoy A and buoy B are 8 - 12, and if there are identical data in the collected data, then adjust according to the effective adjustment distance in the longest distance of the dynamic adjustment distance.

[0042] Build a dynamic adjustment sequence for devices and equipment for collecting water service data, including: obtaining a first position within the collection area as a static sequence, obtaining a dynamically adjustable position within the collection area as a dynamic sequence, obtaining a static sequence data training set and a dynamic sequence data training set for data changes at different depth levels, building a virtual adjustment model, inputting the training set data into the virtual adjustment model to obtain a trained virtual adjustment model, using the virtual adjustment model to obtain the adjustment amount of the device and equipment during the process of collecting water service data at the first position, and then making adjustments.

[0043] Using the virtual adjustment model to obtain the adjustment amount of the device and equipment during the process of collecting water service data at the first position, and then making adjustments, including: constructing a plane rectangular coordinate system with the center of the collection area as the center point, the water flow direction as the X-axis, and the direction perpendicular to the X-axis horizontally as the Y-axis; the static sequence includes fixed points, the first position, and data collection accuracy, the dynamic sequence includes fixed points, a dynamically adjustable range, and data collection accuracy, and the fixed points include but are not limited to the data receiving points of the devices and equipment for collecting water service data or the positions where the fixtures for towing and fixing the devices and equipment for collecting water service data are located; calibrating static points (the points where the first position is located) and dynamic points (the points within the dynamically adjustable range) in the plane rectangular coordinate system to form a first sequence (including the static sequence and the dynamic sequence), calculating the distances from the fixed points to the first position and the maximum adjustment range through the Euclidean distance formula, and updating the first sequence to form a second sequence (a fusion sequence, adding the static sequence to the dynamic sequence), the second sequence includes the minimum distance and the maximum distance, the first position, and data collection accuracy, and considering data changes at different depth levels; then segmenting according to the water service data collection barrier medium to generate a distance adjustment sequence and a data collection sequence.

[0044] For further illustration, taking a lake as an example, assume there are three buoys for collecting water service data. With the center of the collection area as the center of the lake center, that is, in the whole lake, with the lake center point as the center, the first sequence includes a static sequence, [A((0, 0), 10, high), B((1, 1), 10, medium), C((2, 2), 10, medium)], and a dynamic sequence [A((0, 0), 8 - 12, high), B((1, 1), 8 - 12, medium), C((2, 2), 8 - 12, medium)], and the second sequence, [A(8, 12, 10, high), B(8, 12, 10, medium), C(8, 12, 10, medium)].

[0045] The second sequence includes the minimum distance and the maximum distance, the first position, and the data acquisition accuracy. Then, it is segmented according to the water service data acquisition barrier medium to generate a distance adjustment sequence and a data acquisition sequence, including: The barrier medium includes, but is not limited to, network propagation barriers and material propagation barriers. For data changes at different depth levels, traverse the distance adjustment sequence and the data acquisition sequence to generate a set of effective distance adjustment parameters and a set of effective data acquisition parameters, obtain the intersection of the set of effective distance adjustment parameters and the set of effective data acquisition parameters, and use the amount of distance that needs to be adjusted during the process of obtaining the intersection as the adjustment amount for adjustment.

[0046] To further illustrate, taking the lake scenario as an example, assume there are 10 buoys in the lake. The second sequence is [A(8, 12, 10, high), B(8, 12, 10, medium), C(8, 12, 10, medium), D(8, 12, 10, medium), E(8, 12, 10, high), F(8, 12, 10, high), G(8, 12, 10, medium), H(8, 12, 10, high), I(8, 12, 10, low), J(8, 12, 10, high)]. Extract the distance sequence and the data acquisition accuracy sequence in the second sequence, that is, the distance adjustment sequence [A(8, 12), B(8, 12), C(8, 12), D(8, 12), E(8, 12), F(8, 12), G(8, 12), H(8, 12), I(8, 12), J(8, 12)], and the data acquisition sequence [A(high), B(medium), C(medium), D(medium), E(high), F(high), G(medium), H(high), I(low), J(high)]. After generating the set of effective distance adjustment parameters and the set of effective data acquisition parameters, there will be positions that do not meet the data acquisition requirements in the distance adjustment sequence and the data acquisition sequence. After taking the intersection of the generated set of effective distance adjustment parameters and the set of effective data acquisition parameters, first, the buoys that do not need to be adjusted are excluded, and then the buoys that need to be adjusted are adjusted.

[0047] Classify the collected water service data and use the classified data for risk prediction, including: Obtain the fluctuation period and the stable period of the water service data in the acquisition area, and extract the influencing factors of water service data acquisition during the fluctuation period and the stable period. Evaluate the changes in the influencing factors at different depth levels. For the influence of the water body stratification phenomenon on different depth levels, introduce a weight mechanism to dynamically adjust the weights according to the importance of the data. Classify the adjustment data of the water service data acquisition devices and equipment during the stable period as safe adjustment data, and classify the influencing factors of water service data acquisition during the fluctuation period as dangerous adjustment data. Build an RNN model to obtain a training set of dangerous adjustment data. Input the training set data into the RNN model, and introduce a feature selection mechanism optimized for the water body stratification phenomenon to obtain a trained RNN model. Use the RNN model to adjust the devices and equipment for collecting water service data again.

[0048] Further explanation is that by classifying the collected water service data and using the classified data for risk prediction, the data characteristics of the fluctuation period and the stable period are effectively distinguished, the influencing factors are identified, and the data in the stable period is adjusted and classified as safe adjustment data, and the data in the fluctuation period is adjusted and classified as dangerous adjustment data. The RNN model is used to predict future dangerous adjustment data, potential risks are identified in advance, and the device position is adjusted accordingly to improve the accuracy and security of data collection. For example, in a lake, by analyzing the data of water quality fluctuations during the high temperature in summer and the stable water quality in winter, influencing factors such as algae reproduction are identified, and the buoy position is adjusted accordingly to avoid high-risk areas, thus ensuring the reliability and efficiency of data collection.

[0049] Determine the final intelligent acquisition management method for water service data according to the prediction results, including: obtaining the first position of the devices and equipment during the water service data acquisition process and the position during the dynamic adjustment process, and simultaneously obtaining the water service data, forming a cycle for the whole process and continuously optimizing it, and outputting the optimized intelligent acquisition management method for water service data.

[0050] Further explanation is that by determining the final intelligent acquisition management method for water service data according to the prediction results, obtaining the initial position of the device during the acquisition process and its dynamic adjustment position, and synchronously obtaining the water service data, the whole process is constructed into a closed-loop system, continuously optimized, and finally the optimized intelligent acquisition management method is output. For example, in a lake, by recording the data of the buoy at different positions and dynamically adjusting the buoy position according to the prediction results, a closed-loop management process is formed, and the position of the buoy and the data acquisition strategy are continuously optimized to ensure the efficiency and accuracy of data collection.

[0051] The above has introduced this application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for intelligent collection and management of water affairs data based on machine learning, characterized in that: The following steps are involved: S1: Collect the locations of devices and equipment for collecting water service data and obtain water service data for pre-processing to determine the relationship between the devices and equipment for collecting water service data and the accuracy of water service data; The initial collection position of the device or equipment for collecting water affairs data is defined as the first position, and the water affairs data collected at the first position is defined as the first data; the first position includes the positions of all devices or equipment for collecting water affairs data in the water affairs data collection area, and the first data includes all water affairs data collected at the first position of all devices or equipment for collecting water affairs data in the water affairs data collection area; in view of the water body stratification phenomenon, the accuracy of the water affairs data is analyzed for the first data at the first position; the water affairs data includes parameters reflecting the water body stratification phenomenon; S2: Based on the relationship between the devices and equipment for collecting water affairs data and the accuracy of water affairs data, dynamically adjust the position range for the devices and equipment for collecting water affairs data, and perform optimization control; S3: Classify the collected water affairs data and use the classified data to make risk predictions; S4: Determine the final intelligent collection and management method of water affairs data based on the prediction results; The water affairs data accuracy analysis of the first data at the first position includes: targeting the influence of water body stratification phenomenon, taking the process position of the device and equipment for collecting water affairs data to reach the first position as position comparison data, and recording the position changes at different depth levels; and recording external environmental parameters; paying attention to the different water quality conditions experienced by the device and equipment when moving between different depth levels; taking the water affairs data collected in the process of the device and equipment for collecting water affairs data reaching the first position as collection data comparison data; obtaining a position comparison data training set and a collection data comparison data training set, constructing a Transformer model, inputting the training set data into the Transformer model, and introducing feature engineering designed specifically for the water body stratification phenomenon to obtain a trained Transformer model, which is specially optimized to adapt to the water body stratification phenomenon and can effectively capture data features at different depth levels; using the Transformer model to analyze the position comparison data and the collection data comparison data, not only evaluating the data accuracy at different depth levels, but also targeting the influence of water body stratification on the data collection and transmission process, thereby obtaining the relationship between the device and equipment for collecting water affairs data and the accuracy of water affairs data; The method reserves a dynamic adjustment position range for the devices and equipment for collecting water data and performs optimization control based on the relationship between the devices and equipment for collecting water data and the accuracy of the water data, and performs optimization control, including: obtaining the relationship between the devices and equipment for collecting water data and the accuracy of the water data, and sorting them according to the accuracy, taking the position with the highest accuracy as the first preferred position, and in view of the influence of the water body stratification phenomenon, combining the positions of the collecting devices and equipment in the process of analyzing the relationship between the devices and equipment for collecting water data and the accuracy of the water data and the accuracy of the collected data into a sequence, constructing an LSTM model, obtaining sequence training set data, inputting the training set data into the LSTM model, obtaining a trained LSTM model, and using the trained LSTM model to obtain the optimal position after the first position of the water data, and defining it as the second preferred position; taking the distance between the first preferred position and the second preferred position as the dynamic adjustment position range, and performing optimization control based on the dynamic adjustment position range; The method classifies the collected water affairs data and uses the classified data for risk prediction, including: obtaining the fluctuation period and stable period of the water affairs data in the collection area, and extracting the influencing factors of water affairs data collection in the fluctuation period and stable period, evaluating the changes of the influencing factors at different depth levels, introducing a weight mechanism to dynamically adjust the weights according to the importance of the data in view of the impact of water body stratification on different depth levels, classifying the adjustment data of the water affairs data collection devices and equipment in the stable period as safe adjustment data, and classifying the water affairs data collection factors in the fluctuation period as dangerous adjustment data, constructing an RNN model, obtaining a training set of dangerous adjustment data, inputting the training set data into the RNN model, and introducing a feature selection mechanism optimized for the water body stratification phenomenon to obtain a trained RNN model, and using the RNN model to adjust the devices and equipment for collecting water affairs data again.

2. The method for intelligent collection and management of water affairs data based on machine learning according to claim 1, characterized in that: The device and equipment locations for collecting water affairs data are obtained and the water affairs data is pre-processed to determine the relationship between the device and equipment for collecting water affairs data and the accuracy of water affairs data, including: the pre-processing includes cleaning and standardizing the data; in view of the water body stratification phenomenon, data changes at different depth levels are collected.

3. The method for intelligent collection and management of water affairs data based on machine learning according to claim 1, characterized in that: The optimization control based on the dynamic adjustment position range includes: obtaining the first position of all water affairs data collection, taking the first position as the center, obtaining the collection area of ​​the water affairs collection devices and equipment within the dynamic adjustment range, and defining them as the effective collection area and the farthest collection area; considering the influence of different depth levels, obtaining the effective collection area and the farthest collection area of ​​all water affairs collection devices and equipment within the dynamic adjustment range, taking the intersection of the effective collection areas of all devices and equipment collecting water affairs data as the shortest adjustment distance, and taking the intersection of the farthest collection areas as the longest adjustment distance, adjusting the position of the device and equipment collecting water affairs data within the dynamic adjustment range when the device and equipment collecting water affairs data is at the shortest adjustment distance, and shrinking the collection area of ​​the device and equipment when the device and equipment collecting water affairs data is at the longest adjustment distance; and constructing a dynamic adjustment sequence for the device and equipment collecting water affairs data.

4. The method for intelligent collection and management of water affairs data based on machine learning as claimed in claim 3, characterized in that: The method of constructing a dynamic adjustment sequence for devices and equipment that collect water data includes: obtaining the first position in the collection area as a static sequence, obtaining the dynamically adjusted position in the collection area as a dynamic sequence, obtaining a static sequence data training set and a dynamic sequence data training set for data changes at different depth levels, constructing a virtual adjustment model, inputting the training set data into the virtual adjustment model to obtain a trained virtual adjustment model, and using the virtual adjustment model to obtain the adjustment amount of the device or equipment in the process of collecting water data at the first position, and then making adjustments.

5. The method for intelligent collection and management of water affairs data based on machine learning as claimed in claim 4, characterized in that: The method of using a virtual adjustment model to obtain the adjustment amount of the device or equipment in the process of collecting water affairs data at the first position, and then adjusting the device or equipment, includes: constructing a plane rectangular coordinate system with the collection area as the center point, the water flow direction as the X-axis, and the horizontal direction perpendicular to the X-axis as the Y-axis; the static sequence includes a fixed point, a first position, and data collection accuracy, and the dynamic sequence includes a fixed point, a dynamic adjustment range, and data collection accuracy. The fixed point includes but is not limited to the data receiving point of the device or equipment for collecting water affairs data or the position of the fixed object used to tow and fix the device or equipment for collecting water affairs data; calibrating the static point (the point at the first position) and the dynamic point (the point within the dynamic adjustment range) in the plane rectangular coordinate system to form a first sequence (including a static sequence and a dynamic sequence), calculating the distance from the fixed point to the first position and the maximum adjustment range by the Euclidean distance formula, and updating the first sequence to form a second sequence (a fusion sequence, adding the static sequence to the dynamic sequence), the second sequence includes the minimum distance value and the maximum distance value, the first position, the data collection accuracy, and considering the data changes at different depth levels; then segmenting the water affairs data collection barrier medium to generate a distance adjustment sequence and a data collection sequence.

6. The method for intelligent collection and management of water affairs data based on machine learning as claimed in claim 5, characterized in that: The second sequence includes the minimum distance and the maximum distance, the first position, and the data collection accuracy, and then is segmented according to the water affairs data collection barrier medium to generate a distance adjustment sequence and a data collection sequence, including: the barrier medium includes but is not limited to network transmission barriers and material transmission barriers, and for data changes at different depth levels, the distance adjustment sequence and the data collection sequence are traversed to generate a distance effective adjustment parameter set and a data effective collection parameter set, and the intersection of the distance effective adjustment parameter set and the data effective collection parameter set is obtained, and the distance amount that needs to be adjusted in the process of obtaining the intersection is adjusted as the adjustment amount.

7. The method for intelligent collection and management of water affairs data based on machine learning according to claim 1, characterized in that: The method for determining the final intelligent collection and management method for water affairs data based on the prediction results includes: obtaining the first position of the device and equipment in the water affairs data collection process and the position in the dynamic adjustment process, and simultaneously obtaining the water affairs data, looping the entire process and continuously optimizing it, and outputting the optimized intelligent collection and management method for water affairs data.

Images