Underground water data intelligent processing system based on cloud platform

Abstract

The invention relates to the technical field of data processing, in particular to an underground water data intelligent processing system based on a cloud platform, and the system comprises a data optimization processing module, a reference information extraction module, an underground water abnormity monitoring module and a data processing adjustment module. According to the invention, the groundwater data is received and analyzed in real time, the historical average value and the standard deviation of each detection point are calculated, the data reference of the groundwater is identified, the deviation is identified in time by comparing the groundwater data with the set reference, and the abnormal coverage of the groundwater is determined by comprehensively evaluating the duration of the data deviation, the number of projects and the abnormal coverage. According to the method, the sensitivity and accuracy of anomaly detection are improved, the frequency and strategy of data processing are automatically adjusted according to data fluctuation and anomaly records, resource allocation is optimized, unnecessary data processing burden is reduced, a more flexible and accurate management mode is provided by a dynamic adjustment mechanism, the sudden water quality problem can be more effectively solved, and the water quality detection efficiency is improved. The processing efficiency is improved; and the possibility of false alarm is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a groundwater data intelligent processing system based on a cloud platform. Background Art

[0002] The field of data processing technology involves the use of computer hardware and software resources to process input data to obtain useful information or make decisions. This field includes data input, verification, storage, retrieval and output. Data processing technology can be applied to a variety of data forms, such as text, images, audio and video data. Data processing technology enables enterprises and organizations to extract valuable insights and information from raw data to support decision making.

[0003] Among them, the groundwater data intelligent processing system is a technical system used to manage and analyze groundwater resource data. Its main uses include monitoring water quality, predicting water resource changes, evaluating utilization strategies, and conducting environmental impact analysis. The system is usually used to predict water demand, detect pollution sources, and optimize water resource allocation. Through intelligent processing and analysis, the system can help government agencies, environmental organizations, and water resource management companies improve water efficiency, reduce waste, and protect the water environment.

[0004] Traditional processing systems rely on periodic data updates and batch processing, and lack the ability to process data in real time and adjust dynamically. This results in data processing being slow to respond to rapidly changing environmental conditions, and being unable to adjust strategies in time to respond to emergencies. For example, traditional systems are unable to quickly identify drastic changes in water quality caused by abnormal rainfall, and miss the best time to process. Fixed data processing frequencies can lead to a waste of resources, such as maintaining high-frequency monitoring and analysis when data changes little, increasing operating costs without corresponding benefits, limiting the efficiency and effectiveness of water resource management, and exacerbating environmental risks and management costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a groundwater data intelligent processing system based on a cloud platform.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a groundwater data intelligent processing system based on a cloud platform, the system comprising:

[0007] The data optimization processing module collects groundwater data through sensors based on the target groundwater detection points, standardizes the data, unifies the data range, and removes outliers to obtain optimized groundwater data;

[0008] The benchmark information extraction module receives data through a cloud server based on the optimized groundwater data, extracts groundwater data records of differentiated time periods, calculates the historical average value of groundwater data in differentiated time periods, calculates the standard deviation of groundwater data in corresponding time periods, identifies the normal range of groundwater data, and obtains groundwater benchmark information;

[0009] The groundwater anomaly monitoring module compares the current groundwater data with the groundwater benchmark based on the groundwater benchmark information, evaluates the data deviation, and evaluates the degree of groundwater anomaly in combination with the deviation duration, the number of deviation items and the anomaly coverage, implements the corresponding groundwater anomaly warning, and obtains the groundwater anomaly monitoring results;

[0010] The data processing adjustment module is based on the groundwater anomaly monitoring results and groundwater benchmark information, evaluates the fluctuation degree of groundwater data according to the standard deviation of groundwater data at differentiated detection points, and adjusts the cloud server's receiving and processing frequency of detection point data in combination with the abnormal records of the detection points to obtain data processing adjustment results.

[0011] The present invention is improved in that the steps of obtaining the optimized groundwater data are:

[0012] Based on the target groundwater detection point, the groundwater data is automatically collected through sensors. The groundwater data includes water temperature data, water level data, water quality data and pH value data;

[0013] Based on the groundwater data, the formula:

[0014]

[0015] Calculate the scaled standard groundwater data, where X new is the scaled standard groundwater data point, X represents the original groundwater data point, min(X) represents the minimum value in the groundwater data, max(X) represents the maximum value in the groundwater data, S X represents the scaling factor;

[0016] The scaled standard groundwater data is compared with a preset outlier threshold, and data points outside the outlier threshold are removed to obtain optimized groundwater data.

[0017] The present invention is improved in that the method for calculating the historical average value of groundwater data in the differentiated time period is:

[0018] Based on the optimized groundwater data, extract historical groundwater data for a target period to obtain average value associated data;

[0019] Based on the average value associated data, by the formula:

[0020]

[0021] Calculate the average value for the target period Get the average groundwater data information for the target period, where X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period.

[0022] The present invention is improved in that the step of obtaining the groundwater benchmark information is:

[0023] Based on the average groundwater data information of the target period, according to the average value of the target period, the formula is:

[0024]

[0025] Calculate the standard deviation of the target period, where X σ is the standard deviation of the target period, X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period;

[0026] Based on the standard deviation of the target period, the normal range of groundwater data is set as Get groundwater baseline information.

[0027] The present invention is improved in that the method for evaluating data deviation is:

[0028] Based on the groundwater benchmark information, extract the average value and the standard deviation of the target period, and extract the current groundwater data to obtain deviation-related data;

[0029] Based on the deviation correlation data, through the formula:

[0030]

[0031] Calculate the deviation index and obtain the data deviation analysis results, where P represents the deviation index and X current Current groundwater data, X σ is the standard deviation of the target period, is the average value of the target period, b P is the coefficient of the baseline of the translation deviation index, c P is the logarithmic magnification factor, d P The smoothing parameter is calculated logarithmically.

[0032] The present invention is improved in that the steps of obtaining the abnormal groundwater monitoring results are:

[0033] Based on the data deviation analysis result, the deviation index is compared with the preset deviation threshold, the groundwater index whose deviation index exceeds the deviation threshold is recorded, and the deviation duration and deviation existence range are recorded to obtain abnormal correlation data;

[0034] Based on the abnormal correlation data, the formula:

[0035]

[0036] Calculate the degree of groundwater anomaly, where P j,f is the fth deviation index of the jth indicator, is the weight of the jth indicator, A j is the jth indicator deviation coverage, T j,f is the duration of the fth deviation of the jth indicator, k E is the logarithmic adjustment coefficient, E is the degree of groundwater anomaly, J is the total number of groundwater indicators, and F j is the number of times the deviation of the jth indicator exceeds the deviation threshold;

[0037] Based on the degree of groundwater anomaly, it is compared with the preset anomaly standard, and the corresponding groundwater anomaly warning is implemented to obtain the groundwater anomaly monitoring result.

[0038] The present invention is improved in that the method for evaluating the fluctuation degree of groundwater data is:

[0039] Based on the groundwater benchmark information, extract the standard deviation of the target period and the length of the target period to obtain fluctuation correlation data;

[0040] Based on the fluctuation correlation data, the formula:

[0041]

[0042] Calculate the data fluctuation index B during the target period to obtain the fluctuation evaluation result of groundwater data, where X σ is the standard deviation of the target period, T B is the target period length, c B is the logarithmic coefficient, d B is the offset, s B is the time adjustment parameter, and B is the data fluctuation index of the target period.

[0043] The present invention is improved in that the step of obtaining the data processing adjustment result is:

[0044] Based on the groundwater data fluctuation assessment results and groundwater anomaly monitoring results, extract the detection records of the target detection points, count the number of groundwater anomalies at the detection points, and obtain the basic receiving and processing frequency of the data to obtain frequency adjustment associated data;

[0045] The associated data is adjusted based on the frequency, by the formula:

[0046]

[0047] Calculate the data receiving and processing frequency after the target period is adjusted to obtain the data processing adjustment result, where Z is the data receiving and processing frequency after the target period is adjusted, B is the data fluctuation index of the target period, and N Z is the number of historical anomalies of the detection point, Z0 is the basic receiving and processing frequency, a Z is the weight coefficient of the volatility index, b Z is the weight coefficient of the number of historical anomalies.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, by real-time receiving and analyzing groundwater data, calculating the historical average and standard deviation of each detection point, identifying the data benchmark of groundwater, and timely identifying deviations by comparing the groundwater data with the set benchmark, the sensitivity and accuracy of anomaly detection are improved by comprehensively evaluating the duration of data deviations, the number of items and the coverage of anomalies, and the frequency and strategy of data processing are automatically adjusted according to data fluctuations and abnormal records, thereby optimizing resource allocation and reducing unnecessary data processing burden. The dynamic adjustment mechanism provides a more flexible and accurate management method, which can more effectively respond to sudden water quality problems, improve processing efficiency and reduce the possibility of false alarms, ensure the flexibility and adaptability of data processing, improve the overall effect of groundwater management, and achieve efficient resource utilization and minimization of environmental risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 A flow chart for obtaining optimized groundwater data for the present invention;

[0052] Figure 3 A flow chart for calculating the historical average of groundwater data for differentiated time periods for the present invention;

[0053] Figure 4 A flow chart for obtaining groundwater benchmark information for the present invention;

[0054] Figure 5 Flowchart for evaluating data bias for the present invention;

[0055] Figure 6 A flow chart for obtaining groundwater anomaly monitoring results in the present invention;

[0056] Figure 7 A flow chart for evaluating the degree of fluctuation of groundwater data for the present invention;

[0057] Figure 8 The present invention is a flow chart for obtaining data processing adjustment results. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0060] See also Figure 1 The present invention provides a technical solution: a groundwater data intelligent processing system based on a cloud platform, the system comprising:

[0061] The data optimization processing module collects groundwater data through sensors based on the target groundwater detection points, standardizes the data, unifies the data range, and removes outliers to obtain optimized groundwater data;

[0062] The benchmark information extraction module receives data through the cloud server based on the optimized groundwater data, extracts groundwater data records of differentiated time periods, calculates the historical average value of groundwater data in differentiated time periods, and calculates the standard deviation of groundwater data in corresponding time periods, identifies the normal range of groundwater data, and obtains groundwater benchmark information;

[0063] The groundwater anomaly monitoring module compares the current groundwater data with the groundwater benchmark based on the groundwater benchmark information, evaluates the data deviation, and evaluates the degree of groundwater anomaly based on the deviation duration, number of deviation items and anomaly coverage, implements the corresponding groundwater anomaly warning, and obtains the groundwater anomaly monitoring results;

[0064] The data processing adjustment module evaluates the fluctuation of groundwater data based on the groundwater anomaly monitoring results and groundwater benchmark information, according to the standard deviation of groundwater data at differentiated detection points, and adjusts the frequency of receiving and processing the detection point data by the cloud server in combination with the abnormal records of the detection points to obtain the data processing adjustment results;

[0065] The optimized groundwater data include optimized water temperature data, water level height, water quality data and pH value data; the groundwater benchmark information include water temperature benchmark data, water level benchmark data, water quality benchmark data and pH value benchmark data; the groundwater abnormal monitoring results include data deviation amplitude, deviation duration and abnormality level; the data processing adjustment results include adjusted data collection and analysis frequency and data storage capacity.

[0066] See also Figure 2 , the steps for obtaining the optimized groundwater data are:

[0067] Based on the target groundwater detection point, the groundwater data is automatically collected through sensors. The groundwater data includes water temperature data, water level data, water quality data and pH value data;

[0068] Based on groundwater data, the formula:

[0069]

[0070] Calculate the scaled standard groundwater data, where X new is the scaled standard groundwater data point, X represents the original groundwater data point, min(X) represents the minimum value in the groundwater data, max(X) represents the maximum value in the groundwater data, S X represents the scaling factor;

[0071] Based on the scaled standard groundwater data, it is compared with the preset outlier threshold, and the data points outside the outlier threshold are removed to obtain the optimized groundwater data.

[0072] formula:

[0073]

[0074] The meaning and acquisition method of parameters:

[0075] X is the original groundwater data point, which is automatically collected by sensors placed at the groundwater monitoring points.

[0076] min(X) and max(X) are the minimum and maximum values ​​of all groundwater data, respectively. The values ​​are usually preset according to the requirements or the minimum and maximum values ​​in the historical data.

[0077] S XIt is a user-defined scaling factor used to adjust the scale of the data so that the normalized data falls within a specific numerical range, such as 0 to 100. The coefficient is set according to the specific data analysis requirements to adapt to different analysis environments.

[0078] Calculation example:

[0079] The set of groundwater data points X collected within a certain period of time is set to {20, 55, 75, 90}, and the data needs to be standardized. And min(X)=20, max(X)=90 are set.

[0080] Set the scaling factor S X =100, calculate the standardized X new , taking the data point X=75 as an example for calculation:

[0081]

[0082] The calculated result 78.57 represents the standardized data value. This data processing helps researchers better compare and analyze water quality data at different time points or different monitoring points, thereby effectively conducting trend analysis and quality control.

[0083] See also Figure 3 , the method to calculate the historical average of groundwater data in differentiated periods is:

[0084] Based on the optimized groundwater data, the historical groundwater data of the target period is extracted to obtain the average value related data;

[0085] Based on the mean value correlation data, through the formula:

[0086]

[0087] Calculate the average value for the target period Get the average groundwater data information for the target period, where X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period.

[0088] formula:

[0089]

[0090] Parameter meaning and acquisition method

[0091] X i represents the i-th data point in the target period. The data is automatically collected by sensors at the groundwater monitoring station and transmitted to the cloud server through the network.

[0092] n is the total number of data points in the target period. The value is obtained by counting all valid data points in a specific period. The valid data includes data records that have been preliminarily screened and have excluded abnormal or damaged data records.

[0093] Calculation Example

[0094] Suppose there are three data points {70, 85, 90} between 10 and 11 o'clock every day. To calculate the average of these three data points, follow these steps:

[0095] Add up all the data points:

[0096] Apply the mean formula:

[0097] The calculated average It indicates the average level of groundwater quality during this specific period of time.

[0098] See also Figure 4 , the steps to obtain groundwater benchmark information are:

[0099] Based on the average groundwater data information during the target period, according to the average value of the target period, the formula is:

[0100]

[0101] Calculate the standard deviation of the target period, where X σ is the standard deviation of the target period, X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period;

[0102] Based on the standard deviation of the target period, the normal range of groundwater data is set as Get groundwater baseline information.

[0103] formula:

[0104]

[0105] The meaning and acquisition method of parameters:

[0106] X i represents the i-th data point in the target period. The data is automatically collected by sensors at the groundwater monitoring station and transmitted to the cloud server through the network.

[0107] n is the total number of data points in the target period. The value is obtained by counting all valid data points in a specific period. The valid data includes data records that have been preliminarily screened and have excluded abnormal or damaged data records.

[0108] is the average value of the target period, calculated in the previous step.

[0109] Calculation example:

[0110] Set three data points {60, 70, 90} in the target period and the known average value

[0111] Compute the square of the deviation of each data point from the mean:

[0112] (60-73.33) 2 =178.0889

[0113] (70-73.33) 2 =11.0889

[0114] (90-73.33) 2 =278.0889

[0115] Compute the sum of the squares of these differences:

[0116]

[0117] Taking the square root gives the standard deviation:

[0118]

[0119] Result X σ ≈12.48 represents the fluctuation of the dispersion of the data relative to the mean value during this period. A smaller standard deviation means that the data points are relatively concentrated near the mean value, while a larger standard deviation means that the data points are more dispersed. This calculation helps to understand and evaluate the stability of groundwater data.

[0120] See also Figure 5 , the method to evaluate data bias is:

[0121] Based on the groundwater benchmark information, the mean value and standard deviation of the target period are extracted, and the current groundwater data are extracted to obtain the deviation-related data;

[0122] Based on the deviation correlation data, through the formula:

[0123]

[0124] Calculate the deviation index and obtain the data deviation analysis results, where P represents the deviation index and X current Current groundwater data, X σ is the standard deviation of the target period, is the average value of the target period, b P is the coefficient of the baseline of the translation deviation index, cP is the logarithmic amplification factor, d P The smoothing parameter is calculated logarithmically.

[0125] formula:

[0126]

[0127] The meaning and acquisition method of parameters:

[0128] X current : The currently observed groundwater data points are collected in real time by groundwater quality monitoring sensors.

[0129] X σ is the standard deviation of the target period, is the average value of the target period, calculated by the previous steps.

[0130] b P 、c P ,d P :Adjustment coefficient, used to calibrate the sensitivity and stability of the deviation index. The coefficient is set according to the actual monitoring needs and the characteristics of historical data to ensure that the deviation index can effectively reflect the deviation between current data and historical data.

[0131] Calculation Example

[0132] Set the current data point X current =150mg / L, average value Standard Deviation X σ =20mg / L, the coefficient is set to b P =5, c P =2,d P =1.

[0133] The calculation process is as follows:

[0134] Calculate the absolute deviation of the current data point from the historical mean:

[0135]

[0136] Calculate the deviation index P:

[0137]

[0138] The calculation result P=4.84 represents the deviation index of the current data point relative to the historical data. By introducing the adjustment coefficient, this result takes into account the size of the current data point, so that the deviation index can more sensitively reflect its deviation when the data point is larger.

[0139] See also Figure 6 , the steps to obtain the abnormal groundwater monitoring results are:

[0140] Based on the data deviation analysis results, the deviation index is compared with the preset deviation threshold, and the groundwater indicators whose deviation index exceeds the deviation threshold are recorded, and the deviation duration and deviation existence range are recorded to obtain abnormal correlation data;

[0141] Based on abnormal correlation data, through the formula:

[0142]

[0143] Calculate the degree of groundwater anomaly, where P j,f is the fth deviation index of the jth indicator, is the weight of the jth indicator, A j is the jth indicator deviation coverage, T j,f is the duration of the fth deviation of the jth indicator, k E is the logarithmic adjustment coefficient, E is the degree of groundwater anomaly, J is the total number of groundwater indicators, and F j is the number of times the deviation of the jth indicator exceeds the deviation threshold;

[0144] Based on the degree of groundwater abnormality, it is compared with the preset abnormality standard, and the corresponding groundwater abnormality warning is implemented to obtain the groundwater abnormality monitoring results.

[0145] formula:

[0146]

[0147] Parameter meaning and acquisition method

[0148] P j,f : The f-th deviation index of the j-th indicator, calculated in the previous way.

[0149] The weight of the jth indicator reflects the importance of the indicator in the overall water quality assessment. This weight is determined based on expert evaluation or impact analysis of historical data.

[0150] A j : The geographical scope covered by the deviation indicates the actual geographical area affected by the deviation, which is inferred from the geographic information system or related environmental database by analyzing the geographical location of the detection points where the anomalies exist.

[0151] T j,f is the duration of the f-th deviation of the j-th indicator, calculated based on the timestamp recorded by the monitoring system.

[0152] k E : Logarithmic adjustment coefficient, used to ensure the stability and adaptability of logarithmic operations. This coefficient is set based on previous experiments and error analysis.

[0153] Calculation example:

[0154] Set the parameters as follows

[0155] Total number of indicators J = 2: set as chemical oxygen demand (COD) and ammonia nitrogen (NH3-N), F COD =3, F NH3-N =3: Each indicator has three deviations, weight: Deviation index: P COD,1 =1.2, P COD,2 =1.3, P COD,3 =1.4, P NH3-N,1 =1.5, P NH3-N,2 =1.6, P NH3-N,3 =1.7. Duration: T COD,1 = 2 hours, T COD,1 = 3 hours, T COD,1 = 4 hours, T NH3-N,1 = 2 hours, T NH3-N,2 = 3 hours, T NH3-N,3 = 4 hours. Geographical range: A COD =100m2, A NH3-N =150m2. Adjustment coefficient: k E =1.05.

[0156] Calculate the weighted deviation index for each indicator at each time point:

[0157] For COD:

[0158]

[0159] log(k E ·A COD )=log(1.05·100)=log(105)≈2.02

[0160] For NH3-N:

[0161]

[0162] log(k E ·A NH3-N )=log(1.05·150)=log(157.5)≈2.197

[0163] Calculate the abnormality degree E:

[0164]

[0165] The calculation result E = 27.25312, which represents the overall abnormality after considering the weighted deviation index of different indicators at multiple time points and the logarithmic adjustment of the geographical range covered by the deviation of each indicator. The numerical value can be used to evaluate the overall abnormal state of groundwater. A higher value indicates that there may be significant quality problems in groundwater.

[0166] See also Figure 7 , the method to assess the volatility of groundwater data is:

[0167] Based on the groundwater benchmark information, the standard deviation of the target period is extracted, and the length of the target period is extracted to obtain the fluctuation correlation data;

[0168] Based on the fluctuation correlation data, the formula is:

[0169]

[0170] Calculate the data fluctuation index B during the target period to obtain the fluctuation evaluation result of groundwater data, where X σ is the standard deviation of the target period, T B is the target period length, c B is the logarithmic coefficient, d B is the offset, s B is the time adjustment parameter, and B is the data fluctuation index of the target period.

[0171] formula:

[0172]

[0173] The meaning and acquisition method of parameters:

[0174] X σ : The standard deviation of the target period, calculated by the previous step.

[0175] T B : Target period length, which indicates the length of the time period considered in the standard deviation calculation process.

[0176] c B : A coefficient used to enhance the influence of small standard deviations in the evaluation. The sensitivity of the model to small fluctuations is adjusted by enlarging the value of the standard deviation.

[0177] d B : Offset, used to ensure that the input of the logarithmic function in the formula is always positive when the standard deviation is small or close to zero, to prevent calculation errors.

[0178] s B : Time adjustment parameter, added to the time length, used to adjust the calculation results so that high fluctuations in a short period of time will not excessively amplify the degree of fluctuation.

[0179] Calculation example:

[0180] Set the following parameters: X σ =2.5mg / L (standard deviation), T B = 10 minutes (time period length), c B =1.2(coefficient), d B =0.5(offset),s B =2 (time adjustment parameter).

[0181] Compute the value inside a logarithmic function:

[0182] c B ·X σ +d B =1.2×2.5+0.5=3+0.5=3.5

[0183] Compute logarithms:

[0184] log(3.5)≈0.5441

[0185] Calculate the value of the denominator:

[0186] T B +s B =10+2=12

[0187] Calculate the volatility B:

[0188]

[0189] The calculated result is B = 0.213, which indicates the degree of fluctuation of groundwater data in a given 10-minute time period. The lower B value indicates that the variability of the data is relatively small within this time period.

[0190] See also Figure 8 , the steps to obtain the data processing and adjustment results are:

[0191] Based on the groundwater data fluctuation assessment results and groundwater anomaly monitoring results, the detection records of the target detection points are extracted, the number of groundwater anomalies at the detection points is counted, and the basic receiving and processing frequency of the data is obtained to obtain the frequency adjustment associated data;

[0192] Adjust the correlation data based on frequency, through the formula:

[0193]

[0194] Calculate the data receiving and processing frequency after the target period is adjusted to obtain the data processing adjustment result, where Z is the data receiving and processing frequency after the target period is adjusted, B is the data fluctuation index of the target period, and N Zis the number of historical anomalies of the detection point, Z0 is the basic receiving and processing frequency, a Z is the weight coefficient of the volatility index, b Z is the weight coefficient of the number of historical anomalies.

[0195] formula:

[0196]

[0197] Parameter meaning and acquisition method

[0198] B: Data fluctuation index of the target period, which is the quantitative value of the data fluctuation degree of the detection point target period, calculated through the previous steps.

[0199] N Z : The number of historical anomalies of the detection point, which indicates the total number of groundwater anomaly events recorded at the detection point during the monitoring period, is obtained from the database.

[0200] Z0: Basic receiving and processing frequency, which is the standard frequency of the current cloud server processing the data of the detection point, and is set and predetermined by the system administrator or the system.

[0201] a Z : Weight coefficient of the volatility index, which is used to adjust the contribution of the volatility level (through its square root) to the frequency adjustment. This coefficient is set based on historical data analysis or system performance requirements.

[0202] b Z : The weight coefficient of the number of historical abnormalities is used to smooth its impact on frequency adjustment by applying a logarithmic form. This coefficient is also determined based on system analysis or monitoring requirements.

[0203] Calculation Example

[0204] The following parameter values ​​are set for calculation: B = 4.0 (indicating a higher degree of fluctuation), N Z =10 (the detection point had 10 abnormalities during the monitoring period), Z0 = 5Hz (the basic data receiving frequency is 5 times per second), a Z =0.3 (volatility weight coefficient), b Z =0.2 (abnormality frequency weight coefficient).

[0205] Calculate the contribution of volatility:

[0206]

[0207] Calculate the contribution of the anomaly history:

[0208]

[0209] Calculate the adjusted receive frequency:

[0210] Z=5·(1+0.6+0.20828)=5·1.80828=9.0414

[0211] The calculation result Z = 9.0414 Hz, indicating that after considering the degree of fluctuation and abnormal history, the frequency of data reception and processing at the detection point should be increased from 5 times per second to about 9 times per second. This adjustment helps the cloud server receive and process data from this detection point more frequently to cope with higher data fluctuations and abnormal activities, ensuring the timeliness and accuracy of data processing.

[0212] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The intelligent groundwater data processing system based on cloud platform is characterized by: The system comprises: The data optimization processing module collects groundwater data through sensors based on the target groundwater detection points, standardizes the data, unifies the data range, and removes outliers to obtain optimized groundwater data; The benchmark information extraction module receives data through a cloud server based on the optimized groundwater data, extracts groundwater data records of differentiated time periods, calculates the historical average value of groundwater data in differentiated time periods, calculates the standard deviation of groundwater data in corresponding time periods, identifies the normal range of groundwater data, and obtains groundwater benchmark information; The groundwater anomaly monitoring module compares the current groundwater data with the groundwater benchmark based on the groundwater benchmark information, evaluates the data deviation, and evaluates the degree of groundwater anomaly in combination with the deviation duration, the number of deviation items and the anomaly coverage, implements the corresponding groundwater anomaly warning, and obtains the groundwater anomaly monitoring results; The data processing adjustment module is based on the groundwater anomaly monitoring results and groundwater benchmark information, evaluates the fluctuation degree of groundwater data according to the standard deviation of groundwater data at differentiated detection points, and adjusts the cloud server's receiving and processing frequency of detection point data in combination with the abnormal records of the detection points to obtain data processing adjustment results.

2. The cloud platform-based groundwater data intelligent processing system according to claim 1 is characterized in that: The steps for obtaining the optimized groundwater data are as follows: Based on the target groundwater detection point, the groundwater data is automatically collected through sensors. The groundwater data includes water temperature data, water level data, water quality data and pH value data; Based on the groundwater data, the formula: Calculate the scaled standard groundwater data, where X new is the scaled standard groundwater data point, X represents the original groundwater data point, min(X) represents the minimum value in the groundwater data, max(X) represents the maximum value in the groundwater data, S X represents the scaling factor; The scaled standard groundwater data is compared with a preset outlier threshold, and data points outside the outlier threshold are removed to obtain optimized groundwater data.

3. The cloud platform-based groundwater data intelligent processing system according to claim 1 is characterized in that: The method for calculating the historical average value of groundwater data in differentiated periods is: Based on the optimized groundwater data, extract historical groundwater data for a target period to obtain average value associated data; Based on the average value associated data, by the formula: Calculate the average value for the target period Get the average groundwater data information for the target period, where X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period.

4. The cloud platform-based groundwater data intelligent processing system according to claim 3 is characterized in that: The steps for obtaining the groundwater benchmark information are: Based on the average groundwater data information of the target period, according to the average value of the target period, the formula is: Calculate the standard deviation of the target period, where X σ is the standard deviation of the target period, X i represents the i-th data point in the target period, n represents the total number of data points in the target period, is the average value of the target period; Based on the standard deviation of the target period, the normal range of groundwater data is set as Get groundwater baseline information.

5. The cloud platform-based groundwater data intelligent processing system according to claim 1 is characterized in that: The method for evaluating data deviation is: Based on the groundwater benchmark information, extract the average value and the standard deviation of the target period, and extract the current groundwater data to obtain deviation-related data; Based on the deviation correlation data, through the formula: Calculate the deviation index and obtain the data deviation analysis results, where P represents the deviation index and X current Current groundwater data, X σ is the standard deviation of the target period, is the average value of the target period, b P is the coefficient of the baseline of the translation deviation index, c P is the logarithmic magnification factor, d P The smoothing parameter is calculated logarithmically.

6. The cloud platform-based groundwater data intelligent processing system according to claim 5 is characterized in that: The steps for obtaining the abnormal groundwater monitoring results are as follows: Based on the data deviation analysis result, the deviation index is compared with the preset deviation threshold, the groundwater index whose deviation index exceeds the deviation threshold is recorded, and the deviation duration and deviation existence range are recorded to obtain abnormal correlation data; Based on the abnormal correlation data, the formula: Calculate the degree of groundwater anomaly, where P j,f is the fth deviation index of the jth indicator, is the weight of the jth indicator, A j is the jth indicator deviation coverage, T j,f is the duration of the fth deviation of the jth indicator, k E is the logarithmic adjustment coefficient, E is the degree of groundwater anomaly, J is the total number of groundwater indicators, and F j is the number of times the deviation of the jth indicator exceeds the deviation threshold; Based on the degree of groundwater anomaly, it is compared with the preset anomaly standard, and the corresponding groundwater anomaly warning is implemented to obtain the groundwater anomaly monitoring result.

7. The cloud platform-based groundwater data intelligent processing system according to claim 1 is characterized in that: The method for evaluating the fluctuation degree of groundwater data is: Based on the groundwater benchmark information, extract the standard deviation of the target period and the length of the target period to obtain fluctuation correlation data; Based on the fluctuation correlation data, the formula: Calculate the data fluctuation index B during the target period to obtain the fluctuation evaluation result of groundwater data, where X σ is the standard deviation of the target period, T B is the target period length, c B is the logarithmic coefficient, d B is the offset, s B is the time adjustment parameter, and B is the data fluctuation index of the target period.

8. The cloud platform-based groundwater data intelligent processing system according to claim 7 is characterized in that: The steps of obtaining the data processing adjustment result are: Based on the groundwater data fluctuation assessment results and groundwater anomaly monitoring results, extract the detection records of the target detection points, count the number of groundwater anomalies at the detection points, and obtain the basic receiving and processing frequency of the data to obtain frequency adjustment associated data; The associated data is adjusted based on the frequency, by the formula: Calculate the data receiving and processing frequency after the target period is adjusted to obtain the data processing adjustment result, where Z is the data receiving and processing frequency after the target period is adjusted, B is the data fluctuation index of the target period, and N Z is the number of historical anomalies of the detection point, Z0 is the basic receiving and processing frequency, a Z is the weight coefficient of the volatility index, b Z is the weight coefficient of the number of historical anomalies.

Images