A data classification and evaluation method for sewage monitoring based on big data

Abstract

The present invention discloses a data classification and evaluation method for sewage monitoring based on big data, which relates to the field of data processing technology. The data classification and evaluation method for sewage monitoring based on big data includes the following steps: dividing the total sewage monitoring area; performing concentration threshold comparative analysis on the original data; performing a second classification adjustment based on the second comparative analysis result; and performing a third classification adjustment based on the third comparative analysis result. The present invention performs a first classification evaluation and a second classification evaluation on different data collection points based on the early warning results; performs a second classification adjustment based on the second comparative analysis result; and performs a third classification adjustment based on the third comparative analysis result, thereby achieving the effect of improving the accuracy of the classification and evaluation processing of the original data of sewage monitoring, and solving the problem of insufficient accuracy of the classification and evaluation processing of the original data of sewage monitoring based on big data in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data classification and evaluation method for sewage monitoring based on big data. Background Art

[0002] As the problem becomes increasingly serious, the use and preparation of sewage not only violates the law but also poses a serious threat to personal health and social security. To effectively combat crime and protect public safety, and to actively explore new monitoring and prevention methods, a big data-based sewage monitoring data classification and evaluation method has emerged.

[0003] The existing big data-based sewage monitoring data classification and evaluation is achieved through the following methods: sewage sampling technology, which collects sewage samples from sewage treatment plants or specific areas; chemical analysis technology, which uses high-performance liquid chromatography, mass spectrometry and other chemical analysis technologies to detect the components in sewage; big data analysis technology, which uses a big data platform to store, process and analyze the detection data to achieve data classification and evaluation.

[0004] For example, the invention patent with publication number CN119046858A discloses a poison monitoring system, which includes: a data acquisition model, a data preprocessing model, a poison analysis model, an anomaly analysis model, and a data display model. In the poison analysis model, the data analysis layer uses a clustering method to obtain the input data of each indicator of the indicator layer. The indicator layer analyzes each indicator based on the input data to obtain the output data of each indicator. The comprehensive evaluation layer is used to conduct a comprehensive analysis of the output data of each indicator, the weight of each indicator, and the preprocessed data to obtain a comprehensive evaluation result. The anomaly analysis model is used to analyze the output data and preprocessed data of each indicator in the poison analysis model to obtain an anomaly analysis report. The data display model visually displays the comprehensive evaluation results and the anomaly analysis report.

[0005] For example, the invention patent with publication number CN111339172A discloses a real-time visualization monitoring method for abuse, which includes: collecting influent samples based on sewage epidemiological principles and analyzing concentration information; establishing a per capita abuse model to calculate the per capita abuse quantity, and constructing a prevalence model for such substances based on the continuous collection and measurement of sewage samples and metabolites, combined with the abuse frequency and abuse dose survey results, so as to predict the number of abusers, prevalence and total amount of abuse in real time and establish a large database; reading information in the large database, importing the data source into the visualization system, performing ETL processing on the data source to form a data warehouse, and visually expressing the data in the form of multiple components on the web interface through front-end integration analysis.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] While existing technologies for sewage toxicity testing have made significant progress in data detection, they lack a systematic analysis and early warning mechanism during the data collection and preliminary analysis stages. Furthermore, the classification and assessment generation process often relies on manual labor, which is not only inefficient but also difficult to ensure the consistency and accuracy of the classification and assessment. This leads to insufficient accuracy in the classification and assessment processing of raw data from sewage monitoring based on big data. Summary of the Invention

[0008] The embodiments of the present application solve the problem of insufficient accuracy of classification, evaluation and processing of original data of sewage monitoring based on big data in the prior art by providing a data classification and evaluation method for sewage monitoring based on big data, thereby achieving the effect of improving the accuracy of classification, evaluation and processing of original data of sewage monitoring.

[0009] An embodiment of the present application provides a data classification and evaluation method for sewage monitoring based on big data, comprising the following steps: dividing the total sewage monitoring area to obtain different sewage monitoring sub-areas, and obtaining the original data at the data collection points in the sewage monitoring sub-areas from a database; performing a concentration threshold comparative analysis on the original data, issuing an early warning based on the concentration threshold comparative analysis results, and performing a first classification evaluation and a second classification evaluation on different data collection points based on the early warning results; performing a first comparative analysis based on the first classification evaluation result, performing a first classification adjustment based on the first comparative analysis result, performing a second comparative analysis based on the second classification evaluation result, and performing a second classification adjustment based on the second comparative analysis result; obtaining a comprehensive classification evaluation result based on the first classification evaluation result and the second classification evaluation result, performing a third comparative analysis based on the comprehensive classification evaluation result, and performing a third classification adjustment based on the third comparative analysis result.

[0010] Furthermore, the early warning based on the comparative analysis results of the concentration thresholds specifically includes: classifying the original data according to predefined data categories to obtain original data under different categories; if the original data under different categories are equal to or greater than the corresponding concentration thresholds, the data collection points in the corresponding sewage monitoring sub-area are recorded as first-level early warning points and relevant personnel are notified; if the original data under different categories are less than the corresponding concentration thresholds, the data collection points in the corresponding sewage monitoring sub-area are recorded as second-level early warning points.

[0011] Furthermore, the first classification evaluation and the second classification evaluation are performed on different data collection points according to the early warning results, specifically including: obtaining the medical waste data under the corresponding data collection point through the medical waste database of the sewage monitoring sub-area, and performing the first classification evaluation based on the original data and medical waste data under the data collection point; if the data collection point is recorded as a secondary early warning point, performing the second classification evaluation based on the original data under the data collection point.

[0012] Furthermore, the first classification evaluation is performed based on the original data and medical waste data at the data collection points, specifically including: numbering the data collection points in sequence, numbering the types of medical waste in the medical waste data in sequence, and numbering the monitoring time periods corresponding to the original data in sequence; directly extracting medical concentration data, concentration detection threshold, standard temperature of sewage, and standard pH value of sewage from the medical waste database of the sewage monitoring sub-area; collecting and extracting from the temperature collection device the sewage temperature of different monitoring time periods for different types of medical waste at different data collection points; collecting and extracting from the pH collection device the pH value of sewage of different monitoring time periods for different types of medical waste at different data collection points; and comprehensively analyzing the medical concentration data, concentration detection threshold, standard temperature of sewage, standard pH value of sewage, sewage temperature of different monitoring time periods for different types of medical waste at different data collection points, and pH value of sewage of different monitoring time periods for different types of medical waste at different data collection points to obtain a concentration correction value.

[0013] Furthermore, the first classification adjustment is performed based on the first comparative analysis result, specifically including: if the concentration correction value of the first-level warning point is equal to or greater than the concentration correction threshold, the corresponding first-level warning point is recorded as a special-level warning point and relevant personnel are notified to conduct on-site inspections of the sewage monitoring sub-area where the special-level warning point is located; if the concentration correction value of the first-level warning point is less than the concentration correction threshold, the corresponding first-level warning point is still recorded as a first-level warning point and the original data collection frequency of the corresponding first-level warning point is increased; if the concentration correction value of the second-level warning point is equal to or greater than the concentration correction threshold, the corresponding second-level warning point is recorded as a first-level warning point and the original data collection frequency of the corresponding second-level warning point is increased and the original data of the corresponding second-level warning point is processed by a local anomaly factor detection algorithm; if the concentration correction value of the second-level warning point is less than the concentration correction threshold, the corresponding second-level warning point is recorded as a third-level warning point, and the original data of the corresponding third-level warning point is cleaned for similarity through a fuzzy matching algorithm.

[0014] Furthermore, the first classification adjustment based on the first comparative analysis result also includes: counting the number of first-level warning points, second-level warning points and third-level points in the sewage monitoring sub-area; if the number of first-level warning points in the sewage monitoring sub-area is equal to or greater than the first-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as special-level warning points; if the number of first-level warning points in the sewage monitoring sub-area is less than the first-level warning point number threshold, no adjustment is made; if the number of second-level warning points in the sewage monitoring sub-area is equal to or greater than the second-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as first-level warning points; if the number of second-level warning points in the sewage monitoring sub-area is less than the second-level warning point number threshold, no adjustment is made; if the number of third-level warning points in the sewage monitoring sub-area is equal to or greater than the third-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as second-level warning points; if the number of third-level warning points in the sewage monitoring sub-area is less than the third-level warning point number threshold, no adjustment is made.

[0015] Furthermore, the second classification evaluation is performed based on the original data at the data collection point, specifically including: directly extracting the sewage flow standard value, rainfall standard value and concentration standard value from the medical waste database of the sewage monitoring sub-area; collecting and extracting the concentrations of different types and different monitoring time periods at different secondary warning points from the intelligent flow statistics equipment; collecting and extracting the sewage flow and rainfall in different monitoring time periods at different secondary warning points from the intelligent flow statistics equipment; comprehensively analyzing the sewage flow standard value, rainfall standard value, concentration standard value, the concentrations of different types and different monitoring time periods at different secondary warning points, and the sewage flow and rainfall in different monitoring time periods at different secondary warning points to obtain the concentration mutation degree value.

[0016] Furthermore, the second classification adjustment is performed based on the second comparative analysis result, specifically including: if the concentration mutation degree value of the second-level warning point is equal to or greater than the concentration mutation degree threshold, the corresponding second-level warning point is recorded as a first-level warning point and the original data collection frequency of the corresponding first-level warning point is increased and relevant personnel are notified to perform data cleaning on the original data of the corresponding first-level warning point; if the concentration mutation degree value of the second-level warning point is less than the concentration mutation degree threshold, the corresponding second-level warning point is still recorded as a second-level warning point.

[0017] Furthermore, the comprehensive classification evaluation result is obtained based on the first classification evaluation result and the second classification evaluation result, specifically including: obtaining a comprehensive evaluation value of the concentration data of the secondary warning point based on a comprehensive analysis of the concentration correction value and the concentration mutation degree value of the secondary warning point, which is used to quantitatively evaluate the comprehensive level of the concentration data monitoring quality; numbering the secondary warning points in sequence, Indicates the number of the second-level warning point. , Indicates the total number of secondary warning point numbers; the specific comprehensive analysis formula is as follows: ; Indicates the The comprehensive evaluation value of the concentration data of each data collection point is used to quantify the comprehensive evaluation value of the concentration data affected by the interference of concentration monitoring; Indicates the The concentration correction value of each data collection point is used to quantify the relative negative degree of interference in concentration monitoring; Indicates the The concentration mutation degree value of each secondary warning point is used to quantify the relative level value of the concentration monitoring mutation degree; Indicates the The correction factor of the dissolved oxygen content in sewage at the second-level warning point is used to quantify the relative level value of the concentration monitoring mutation degree. Indicates the The weight factor of the concentration correction value of each secondary warning point for the comprehensive evaluation value of the concentration data, Indicates the The concentration mutation degree value of each secondary warning point is the weight factor of the comprehensive evaluation value of concentration data.

[0018] Furthermore, the third classification adjustment is performed based on the third comparative analysis result, specifically including: if the comprehensive evaluation value of the concentration data of the second-level warning point is less than the comprehensive evaluation threshold of the concentration data, the original data of the corresponding second-level warning point is cleaned by a standard score algorithm; if the comprehensive evaluation value of the concentration data of the second-level warning point is equal to or greater than the comprehensive evaluation threshold of the concentration data, the corresponding second-level warning point is recorded as a first-level warning point and the original data collection frequency of the corresponding second-level warning point is increased; the special warning points, first-level warning points, second-level warning points and third-level warning points in all data collection points under the sewage monitoring sub-area are used to generate a classified and labeled electronic map report through a report generation model.

[0019] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0020] 1. According to the early warning results, the first classification evaluation and the second classification evaluation are performed on different data collection points respectively; the second classification adjustment is performed according to the second comparative analysis results; and the third classification adjustment is performed according to the third comparative analysis results, thereby achieving the effect of improving the accuracy of the classification evaluation processing of the original data of sewage monitoring, and solving the problem of insufficient accuracy of the classification evaluation processing of the original data of sewage monitoring based on big data in the existing technology.

[0021] 2. Perform a first comparative analysis based on the results of the first classification evaluation, and perform a first classification adjustment based on the results of the first comparative analysis. By considering multiple interference factors, the actual concentration can be more accurately reflected, false alarms and missed alarms can be reduced, and the impact of environmental factors such as temperature and pH on the detection can be considered, so that the test results are more in line with the actual environmental conditions, thereby achieving the real-time nature of data classification evaluation.

[0022] 3. Based on the first classification evaluation results and the second classification evaluation results, a comprehensive classification evaluation result is obtained. A third comparative analysis is performed based on the comprehensive classification evaluation result. Based on the third comparative analysis result, a third classification adjustment is performed. By comprehensively analyzing the concentration correction value and the mutation degree value, the monitoring quality of the concentration data can be evaluated more comprehensively, thereby quantitatively evaluating the quality level of concentration data monitoring, providing an objective and operational basis for decision-making, and thus ensuring the reliability of the original data. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Flowchart of the data classification and evaluation method for sewage monitoring based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application solve the problem of insufficient accuracy of classification and evaluation processing of original data of sewage monitoring based on big data in the prior art by providing a data classification and evaluation method for sewage monitoring based on big data. The first classification evaluation and the second classification evaluation are performed on different data collection points according to the early warning results; the second classification adjustment is performed according to the second comparative analysis results; and the third classification adjustment is performed according to the third comparative analysis results, thereby achieving the effect of improving the accuracy of classification and evaluation processing of original data of sewage monitoring.

[0025] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0026] like Figure 1As shown, it is a flow chart of the data classification and evaluation method for sewage monitoring based on big data provided in an embodiment of the present application, and the method includes the following steps: dividing the total sewage monitoring area to obtain different sewage monitoring sub-areas, and obtaining the original data of the data collection points in the sewage monitoring sub-areas from the database; performing concentration threshold comparative analysis on the original data, issuing an early warning based on the concentration threshold comparative analysis results, and performing a first classification evaluation and a second classification evaluation on different data collection points according to the early warning results; performing a first comparative analysis based on the first classification evaluation result, performing a first classification adjustment based on the first comparative analysis result, performing a second comparative analysis based on the second classification evaluation result, and performing a second classification adjustment based on the second comparative analysis result; obtaining a comprehensive classification evaluation result based on the first classification evaluation result and the second classification evaluation result, performing a third comparative analysis based on the comprehensive classification evaluation result, and performing a third classification adjustment based on the third comparative analysis result.

[0027] In this embodiment, the overall sewage monitoring area division rules are independently set by relevant personnel.

[0028] The original data has been collected and stored in the database, and the original data is one-to-one or many-to-one with the data collection points in the sewage monitoring sub-area, that is, one data collection point in a sewage monitoring sub-area corresponds to at least one original data.

[0029] Furthermore, an early warning is issued based on the results of the comparative analysis of concentration thresholds, specifically including: classifying the original data according to predefined data categories to obtain original data under different categories; if the original data under different categories are equal to or greater than the corresponding concentration threshold, the data collection point in the corresponding sewage monitoring sub-area is recorded as a first-level early warning point and the relevant personnel are notified; if the original data under different categories are less than the corresponding concentration threshold, the data collection point in the corresponding sewage monitoring sub-area is recorded as a second-level early warning point.

[0030] In this embodiment, the corresponding concentration threshold refers to different concentration thresholds corresponding to different categories, and the concentration threshold can be directly extracted from a database.

[0031] The concentration threshold is usually calculated in nanograms per liter (ng / L), which can sensitively capture ultra-trace metabolites in sewage.

[0032] It can count and analyze the detection frequency and concentration of various drugs and their metabolites in detail, thereby providing accurate and targeted guidance for drug control personnel.

[0033] Furthermore, according to the early warning results, different data collection points are respectively subjected to first classification evaluation and second classification evaluation, specifically including: obtaining the medical waste data under the corresponding data collection point through the medical waste database of the sewage monitoring sub-area, and performing the first classification evaluation based on the original data and medical waste data under the data collection point; if the data collection point is recorded as a secondary early warning point, performing the second classification evaluation based on the original data under the data collection point.

[0034] In this embodiment, the medical waste data refers to special labeled data that is manually set to interfere with monitoring, specifically referring to component data in medical waste that may be misjudged as components and their metabolites.

[0035] Furthermore, a first classification assessment is performed based on the original data and medical waste data at the data collection points, specifically including: numbering the data collection points in sequence, numbering the types of medical waste in the medical waste data in sequence, and numbering the monitoring time periods corresponding to the original data in sequence; directly extracting medical concentration data, concentration detection thresholds, standard sewage temperatures, and standard pH values ​​of sewage from the medical waste database of the sewage monitoring sub-area; extracting from the temperature collection device the sewage temperatures of different monitoring time periods for different types of medical waste at different data collection points; extracting from the pH collection device the pH values ​​of sewage of different monitoring time periods for different types of medical waste at different data collection points; and comprehensively analyzing the medical concentration data, concentration detection thresholds, standard sewage temperatures, standard sewage pH values, sewage temperatures of different monitoring time periods for different types of medical waste at different data collection points, and pH values ​​of sewage of different monitoring time periods for different types of medical waste at different data collection points to obtain concentration correction values.

[0036] In this embodiment, the components of medical waste that may be misidentified as components and their metabolites may be misidentified as components and their metabolites, such as analgesics, such as morphine and fentanyl, which are used for clinical analgesia, but their metabolites may be similar to metabolites; sedatives, such as benzodiazepines (such as diazepam) and barbiturates, which are used to treat anxiety and insomnia, may have their metabolites misidentified; antidepressants, such as selective serotonin reuptake inhibitors (SSRIs), may have metabolites similar to certain metabolites; chemical Disinfectants, including chlorine-containing disinfectants such as sodium hypochlorite, may produce ketamine-like metabolites; drug metabolites, including antibiotic metabolites: metabolites of certain antibiotics may be misidentified as metabolites; antiepileptic drug metabolites, such as metabolites of phenytoin sodium; anesthetics such as ether and halothane, used for clinical anesthesia, may produce metabolites that are misidentified; solvents such as acetone and ethyl acetate, used for laboratory or medical equipment cleaning, may produce metabolites similar to metabolites; and radiopharmaceuticals used for diagnosis or treatment may produce metabolites that are misidentified. Medical waste data includes the above types of data, collected by intelligent monitoring equipment at the same data collection points as the original data.

[0037] Number the data collection points in sequence. Indicates the number of the data collection point. , Indicates the total number of data collection points.

[0038] Number the types of medical waste in the medical waste data in sequence. A number indicating the type of medical waste, , Indicates the total number of medical waste types. It should be noted that the medical waste types only include data that have an impact on the test results.

[0039] The monitoring time periods corresponding to the original data are numbered in sequence. Indicates the number of the monitoring time period, , Indicates the total number of monitoring time periods.

[0040] Indicates the The concentration correction value of each data collection point is used to quantify the relative negative degree of interference in concentration monitoring. The larger the concentration correction value, the higher the actual concentration relative to the collected detection value. The smaller the concentration correction value, the lower the actual concentration relative to the collected detection value.

[0041] ;

[0042] Represents a natural constant.

[0043] Indicates the The first data collection point The first monitoring period The concentration values ​​in the raw data corresponding to each medical waste type. The raw data actually collected includes the medical concentration data for the corresponding medical waste type. For example, the collected concentration of pethidine may be 190 ng / L. Of these, 190 ng / L is the raw data, and 140 ng / L is collected from medical waste, so 140 ng / L is the medical waste data.

[0044] Therefore, the smaller the difference between the concentration value and the medical concentration data, the greater the interference of the medical concentration data on the concentration value, which makes the actual concentration higher than the collected detection value, and thus makes the concentration correction value larger.

[0045] Indicates the The first data collection point The first monitoring period The medical concentration data of each medical waste type is directly extracted from the medical waste database of the sewage monitoring sub-area.

[0046] Indicates the The concentration detection threshold for each type of medical waste is directly extracted from the medical waste database of the sewage monitoring sub-area. It means that when the concentration is lower than this detection threshold, the corresponding collection equipment will not be able to detect and obtain valid data.

[0047] Indicates the The first data collection point The first monitoring period The sewage temperature of each type of medical waste is collected and extracted from the temperature collection equipment.

[0048] Indicates the The standard sewage temperature for each type of medical waste is directly extracted from the medical waste database of the sewage monitoring sub-area.

[0049] Through laboratory temperature-controlled experiments, we measure solubility and degradation rates at different temperatures and develop a temperature-concentration curve. The median solubility point in the temperature-concentration curve is used as the standard wastewater temperature. Generally, lower temperatures correspond to slower degradation rates and higher sample concentrations. Higher temperatures generally correspond to faster degradation rates. If excessive concentrations are still detected at high temperatures, this indicates a more serious condition.

[0050] Indicates the The first data collection point The first monitoring period The pH value of sewage of each type of medical waste is collected and extracted from the pH value collection equipment.

[0051] Indicates the The standard pH value of sewage for each type of medical waste is directly extracted from the medical waste database of the sewage monitoring sub-area.

[0052] Some substances are unstable under alkaline conditions and may decompose, resulting in low test concentrations. Increased pH values ​​may cause molecules to convert to other forms, affecting detection. Some substances are unstable under acidic conditions and may decompose, resulting in low test concentrations. Decreased pH values ​​may cause molecules to convert to other forms, affecting detection. Through laboratory experiments to control pH values, stability and conversion at different pH values ​​are measured, and a pH-concentration curve is established. The minimum solubility point in the pH-concentration curve is used as the standard pH value for wastewater.

[0053] The larger the ratio of sewage temperature to sewage standard temperature, the faster the relative degradation rate of concentration, so the higher the actual concentration is relative to the collected test value; the larger the relative difference between sewage pH value and sewage standard pH value, the faster the relative degradation rate of concentration, so the higher the actual concentration is relative to the collected test value.

[0054] Represents the sewage temperature correction factor, which is directly extracted from the medical waste database of the sewage monitoring sub-area.

[0055] It represents the pH correction factor of sewage, which is directly extracted from the medical waste database of the sewage monitoring sub-area.

[0056] The sewage temperature correction factor and the sewage pH correction factor respectively represent the correction levels of the relative impact of the ambient temperature corresponding to the corresponding data collection time on the sewage temperature and the sewage pH.

[0057] The sewage temperature correction factor and the sewage pH correction factor are directly obtained from the AC test instrument database through a pre-set mapping relationship. For example, a mapping set is constructed to identify the real-time sewage temperature and sewage pH data collection time and their corresponding sewage temperature correction factor and sewage pH correction factor. The real-time sewage temperature and sewage pH data collection time are input into the mapping set to obtain the corresponding sewage temperature correction factor and sewage pH correction factor. The mapping relationship is a one-to-one or many-to-one relationship. Different seasonal changes or day and night temperature differences may affect both sewage temperature and pH value, thereby affecting detection. Therefore, the data collection time of sewage temperature and sewage pH needs to be taken into consideration.

[0058] Furthermore, a first classification adjustment is performed based on the first comparative analysis result, specifically including: if the concentration correction value of the first-level warning point is equal to or greater than the concentration correction threshold, the corresponding first-level warning point is recorded as a special-level warning point and relevant personnel are notified to conduct on-site inspections of the sewage monitoring sub-area where the special-level warning point is located; if the concentration correction value of the first-level warning point is less than the concentration correction threshold, the corresponding first-level warning point is still recorded as a first-level warning point and the original data collection frequency of the corresponding first-level warning point is increased; if the concentration correction value of the second-level warning point is equal to or greater than the concentration correction threshold, the corresponding second-level warning point is recorded as a first-level warning point and the original data collection frequency of the corresponding second-level warning point is increased, and the original data of the corresponding second-level warning point is processed by a local anomaly factor detection algorithm; if the concentration correction value of the second-level warning point is less than the concentration correction threshold, the corresponding second-level warning point is recorded as a third-level warning point, and the original data of the corresponding third-level warning point is cleaned for similar data through a fuzzy matching algorithm.

[0059] In this embodiment, if the concentration correction value of the first-level warning point is equal to or greater than the concentration correction threshold, it means that the actual concentration is higher than the detected concentration, and if the detected concentration exceeds the threshold, it means that the actual toxicity is more serious, so it is necessary to record the corresponding first-level warning point as a special warning point and notify relevant personnel to conduct on-site inspections of the sewage monitoring sub-area where the special warning point is located.

[0060] If the concentration correction value of the first-level warning point is less than the concentration correction threshold, it means that the actual concentration may exceed the threshold. Due to the influence of the collection frequency and other factors, the concentration at the time of collection does not exceed the threshold. Therefore, the corresponding first-level warning point needs to be recorded as a first-level warning point and the original data collection frequency of the corresponding first-level warning point needs to be increased.

[0061] If the concentration correction value of the secondary warning point is equal to or greater than the concentration correction threshold, the corresponding secondary warning point will be recorded as a primary warning point and the raw data collection frequency of the corresponding secondary warning point will be increased. The raw data of the corresponding secondary warning point will be processed by the local anomaly factor detection algorithm. It should be noted that at this time, it is necessary to rule out whether the judgment of the warning point is wrong due to data anomalies, and the local anomaly factor detection algorithm needs to be processed. The local anomaly factor is an algorithm for anomaly detection. It identifies outliers by considering the local density of data points. The specific example steps are as follows: data cleaning, removing obvious erroneous data, such as negative values ​​or values ​​outside a reasonable range; selecting features related to concentration, such as time, location, detection method, etc.; standardization, standardizing the data so that different features have the same scale; manually selecting a suitable neighbor The domain size k is usually determined based on experience or through cross-validation; a distance metric is manually selected, such as Euclidean distance or Manhattan distance; for each original data point, its distance to the kth neighbor is calculated, called the k-distance; for each original data point, its reachable distance to all neighbors is calculated; based on the reachable distance, the local reachable density of each data point is calculated; for each original data point, its LOF value is calculated, which is the average of the ratio of its local reachable density to the local reachable density of its neighbors; the higher the LOF value, the more likely the point is an outlier relative to its neighbors; based on the distribution of LOF values, an anomaly threshold is set, and points with LOF values ​​greater than 1 are usually selected as potential outliers; points with LOF values ​​exceeding the threshold are identified as outliers; the identified outliers are manually determined to determine whether they are real anomalies or data errors.

[0062] If the concentration correction value of the second-level warning point is less than the concentration correction threshold, the corresponding second-level warning point will be recorded as a third-level warning point, and the original data of the corresponding third-level warning point will be cleaned with a fuzzy matching algorithm for similar data. The example steps of using a fuzzy matching algorithm (such as Levenshtein distance) to detect and clean similar data are as follows: convert the text to a unified format, such as converting all to lowercase; Levenshtein distance, calculate the minimum number of editing operations (insertion, deletion, replacement) required to convert one string into another; apply the selected fuzzy matching algorithm to each pair of text records to calculate the similarity score between them; score interpretation, the lower the score, the more similar the two strings are; set a similarity score threshold according to actual needs, and text pairs below the threshold are considered similar; filter similar records, and mark text pairs with similarity scores below the threshold as similar records; for identified similar records, choose to merge or delete as needed.

[0063] It should be noted that when the drug situation is serious, the special warning point is the highest, followed by the first warning point, then the second warning point, and the third warning point is the lowest.

[0064] Furthermore, the first classification adjustment is performed based on the first comparative analysis result, and also includes: counting the number of first-level warning points, second-level warning points and third-level points in the sewage monitoring sub-area; if the number of first-level warning points in the sewage monitoring sub-area is equal to or greater than the first-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as special-level warning points; if the number of first-level warning points in the sewage monitoring sub-area is less than the first-level warning point number threshold, no adjustment is made; if the number of second-level warning points in the sewage monitoring sub-area is equal to or greater than the second-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as first-level warning points; if the number of second-level warning points in the sewage monitoring sub-area is less than the second-level warning point number threshold, no adjustment is made; if the number of third-level warning points in the sewage monitoring sub-area is equal to or greater than the third-level warning point number threshold, all points in the corresponding sewage monitoring sub-area are recorded as second-level warning points; if the number of third-level warning points in the sewage monitoring sub-area is less than the third-level warning point number threshold, no adjustment is made.

[0065] In this embodiment, in actual testing conditions, hospital wastewater must undergo strict treatment before it can be discharged. For example, after hospital wastewater is treated and discharged into a municipal sewage treatment plant, the residual chlorine index of the treated water is 2 to 8 mg / L; after hospital wastewater is treated and not discharged into a municipal sewage treatment plant, the residual chlorine index of the treated water is 3 to 10 mg / L; after infectious disease hospital wastewater is treated, the residual cyanide index is 6.5 to 10 mg / L, and it must undergo two chlorine disinfection treatments. However, there may not be specific corresponding treatments for medical waste that is easily confused with data, which can easily lead to misjudgment. Due to the crisscrossing of urban underground pipelines, if multiple collection points detect serious toxicity, then the actual toxicity will inevitably be more serious, and the classification assessment level of the point will need to be adjusted upward.

[0066] Furthermore, a second classification evaluation is performed based on the original data at the data collection points, specifically including: directly extracting the sewage flow standard value, rainfall standard value and concentration standard value from the medical waste database of the sewage monitoring sub-area; collecting and extracting the concentrations of different types and different monitoring time periods at different secondary warning points from the intelligent flow statistics equipment; collecting and extracting the sewage flow and rainfall in different monitoring time periods at different secondary warning points from the intelligent flow statistics equipment; comprehensively analyzing the sewage flow standard value, rainfall standard value, concentration standard value, the concentrations of different types and different monitoring time periods at different secondary warning points, and the sewage flow and rainfall in different monitoring time periods at different secondary warning points to obtain the concentration mutation degree value.

[0067] In this embodiment, the second-level warning points are numbered in sequence. Indicates the number of the second-level warning point. , Indicates the total number of second-level warning points.

[0068] Number the types of raw data in the medical waste data in sequence. Indicates the type number, , Indicates the total number of types.

[0069] The monitoring time periods corresponding to the original data are numbered in sequence. Indicates the number of the monitoring time period, , Indicates the total number of monitoring time periods.

[0070] Indicates the The concentration mutation degree value of each secondary warning point is used to quantify the relative level value of the concentration monitoring mutation degree. The larger the concentration mutation degree value, the higher the actual concentration mutation over a period of time, and the smaller the concentration mutation degree value, the lower the actual concentration mutation over a period of time.

[0071] When wastewater flow increases, it is diluted, resulting in a lower detected concentration. Furthermore, increased flow may increase wastewater agitation, affecting distribution and further lowering the detected concentration. When wastewater flow decreases, the concentration is relatively high, resulting in a higher detected concentration. Reduced flow may cause sedimentation, affecting the accuracy of test results.

[0072] Similarly, rainfall dilutes pollutants in sewage, resulting in lower detected concentrations. At the same time, rainfall may bring in surface pollutants, interfering with detection. When rainfall decreases, concentrations are relatively high, and the detected concentration is biased higher.

[0073] Increasing the flow rate will dilute the wastewater, resulting in lower concentrations. Increasing the flow rate may also increase wastewater agitation and affect distribution.

[0074] ;

[0075] Indicates the The second-level warning point Types of The maximum concentration during the monitoring period.

[0076] Indicates the The second-level warning point Types of The minimum concentration during the monitoring period.

[0077] Indicates the The concentration standard values ​​of various types are directly extracted from the medical waste database of the sewage monitoring sub-area.

[0078] Indicates the The second-level warning point Types of The maximum sewage flow rate during a monitoring period.

[0079] Indicates the The second-level warning point Types of The minimum sewage flow rate during a monitoring period.

[0080] Indicates the The sewage flow standard value and concentration standard value of each secondary warning point are directly extracted from the medical waste database of the sewage monitoring sub-area.

[0081] Represents the correction factor for sewage flow rate, with a value range of (0, 1). This correction factor is directly extracted from the medical waste database for the sewage monitoring sub-area. For example, a mapping set is constructed between the real-time sewage flow rate and its corresponding correction factor. Inputting the real-time sewage flow rate into the mapping set yields a corresponding mapping set of correction factors for sewage flow rate. The mapping relationship is one-to-one or many-to-one. Increased flow rate and flow rate dilute the wastewater, resulting in a lower detected concentration. Increased flow rate may increase sewage agitation, affecting distribution and causing a lower detected concentration. Reduced flow rate and flow rate result in a relatively high concentration and a higher detected concentration. Slower flow rate may cause sedimentation, affecting detection. Furthermore, at the same flow rate, different flow rates result in different degrees of dilution.

[0082] Indicates the The second-level warning point The maximum rainfall during the monitoring period.

[0083] Indicates the The second-level warning point The standard rainfall value for each monitoring period is directly extracted from the medical waste database for the sewage monitoring sub-area. This standard rainfall value indicates that rainfall above a certain value will not affect statistical accuracy. For example, it corresponds to 5 percent of the historical average sewage flow at the Level 2 warning point. Increased rainfall dilutes sewage, reducing its concentration. At the same time, rainfall may introduce surface pollutants, interfering with detection. Rain gauges are installed to record rainfall and perform correlation analysis with concentration data.

[0084] Furthermore, a second classification adjustment is performed based on the second comparative analysis result, specifically including: if the concentration mutation degree value of the second-level warning point is equal to or greater than the concentration mutation degree threshold, the corresponding second-level warning point is recorded as a first-level warning point, the original data collection frequency of the corresponding first-level warning point is increased, and relevant personnel are notified to perform data cleaning on the original data of the corresponding first-level warning point; if the concentration mutation degree value of the second-level warning point is less than the concentration mutation degree threshold, the corresponding second-level warning point is still recorded as a second-level warning point.

[0085] In this embodiment, if the concentration mutation degree value of the second-level warning point is equal to or greater than the concentration mutation degree threshold, it means that the data fluctuation at this point is large. It may be a monitoring point with a large flow rate in an underground sewage pipe, or it may be a monitoring point located in many hospitals and chemical plants. It is necessary to increase the raw data collection frequency of the corresponding first-level warning point and notify relevant personnel to perform data cleaning on the raw data of the corresponding first-level warning point.

[0086] Furthermore, a comprehensive classification evaluation result is obtained based on the first classification evaluation result and the second classification evaluation result, specifically including: obtaining a comprehensive evaluation value of the concentration data of the second-level warning point based on a comprehensive analysis of the concentration correction value and the concentration mutation degree value of the second-level warning point, which is used to quantitatively evaluate the comprehensive level of the concentration data monitoring quality; numbering the second-level warning points in sequence, Indicates the number of the second-level warning point. , Indicates the total number of secondary warning point numbers; the specific comprehensive analysis formula is as follows: ; Indicates the The comprehensive evaluation value of the concentration data of each data collection point is used to quantify the comprehensive evaluation value of the concentration data affected by the interference of concentration monitoring; Indicates the The concentration correction value of each data collection point is used to quantify the relative negative degree of interference in concentration monitoring; Indicates the The concentration mutation degree value of each secondary warning point is used to quantify the relative level value of the concentration monitoring mutation degree; Indicates the The correction factor of the dissolved oxygen content in sewage at the second-level warning point is used to quantify the relative level value of the concentration monitoring mutation degree. Indicates the The weight factor of the concentration correction value of each secondary warning point for the comprehensive evaluation value of the concentration data, Indicates the The concentration mutation degree value of each secondary warning point is the weight factor of the comprehensive evaluation value of concentration data.

[0087] In this embodiment, the data collection points include the second-level warning points, and the above parameters of the second-level warning points are evaluated again to obtain the first The concentration correction value of each data collection point.

[0088] Indicates the The sewage dissolved oxygen content impact correction factor for each secondary warning point is calculated, with a value range of (1, 2). The sewage dissolved oxygen content impact correction factor is directly extracted from the medical waste database of the sewage monitoring sub-area. For example, a mapping set of real-time sewage dissolved oxygen content and its corresponding sewage dissolved oxygen content impact correction factor is constructed. The real-time sewage dissolved oxygen content is input into the mapping set to obtain a mapping set of corresponding sewage dissolved oxygen content impact correction factors. The mapping relationship is a one-to-one or many-to-one relationship. Dissolved oxygen can participate in redox reactions, which may change certain chemical forms and thus affect its detection accuracy. Dissolved oxygen is an important substance for microbial growth and metabolism. High dissolved oxygen levels may promote microbial degradation and reduce its concentration; low dissolved oxygen levels may weaken microbial activity and reduce degradation.

[0089] The weighting factors for the concentration correction value and the concentration mutation degree value on the comprehensive assessment of concentration data are directly extracted from the medical waste database of the sewage monitoring sub-area. Different parameters have varying degrees of influence on the quality of concentration data monitoring. For example, the concentration correction value and the concentration mutation degree value are both important indicators, but their impact on the final assessment results may differ. The weighting factors can reflect this difference in importance. For example, the concentration mutation degree value may be very sensitive to short-term concentration changes, while the concentration correction value may be more sensitive to long-term changes. The weighting factors can reflect this difference in sensitivity. This allows for more accurate interpretation of the impact of the comprehensive assessment of concentration data. For example, a mapping set is constructed between the duration of the monitoring period and its corresponding weighting factors for the concentration correction value and the concentration mutation degree value. The duration of the monitoring period is input into the mapping set to obtain the corresponding weighting factors for the concentration correction value and the concentration mutation degree value. The mapping relationship is either one-to-one or many-to-one.

[0090] Furthermore, a third classification adjustment is performed based on the third comparative analysis result, specifically including: if the comprehensive evaluation value of the concentration data of the second-level warning point is less than the comprehensive evaluation threshold of the concentration data, the original data of the corresponding second-level warning point is cleaned by the standard score algorithm; if the comprehensive evaluation value of the concentration data of the second-level warning point is equal to or greater than the comprehensive evaluation threshold of the concentration data, the corresponding second-level warning point is recorded as a first-level warning point and the original data collection frequency of the corresponding second-level warning point is increased; all the data collection points under the sewage monitoring sub-area, including the special warning points, first-level warning points, second-level warning points and third-level warning points, are classified and annotated into an electronic map report through the report generation model.

[0091] In this embodiment, if the comprehensive evaluation value of the concentration data of the secondary warning point is less than the comprehensive evaluation threshold of the concentration data, the original data of the corresponding secondary warning point is cleaned by the standard score algorithm. The Z-score (standard score) is a statistic that measures the degree of deviation of a single data point from the average value of the data set. In data analysis and statistics, Z-score is often used to standardize data, identify outliers, and compare values ​​between different data sets. Explanation of Z-score, a Z-score of 0 indicates that the data point is exactly equal to the average value. A Z-score greater than 0 indicates that the data point is higher than the average value. A Z-score less than 0 indicates that the data point is lower than the average value. The larger the absolute value of the Z-score, the farther the data point is from the average value, and it may be an outlier. Outlier detection: It is generally believed that data points with an absolute value of Z-score greater than 3 may be outliers (according to the 3σ principle).

[0092] The report generation model utilizes advanced LLM (Large Language Model) technology to automatically generate detailed, scientific wastewater monitoring and analysis reports based on the output of the data analysis model and the early warning model. This model not only improves the efficiency of report generation but also ensures the accuracy and depth of the report content, providing strong decision-making support for drug control efforts.

[0093] The electronic map report refers to an electronic map that marks the special warning points, first-level warning points, second-level warning points and third-level warning points in the corresponding sewage monitoring sub-areas.

[0094] Application of the Large Language Model (LLM): The report generation model uses the LLM as its core generation engine. LLM possesses powerful natural language processing and deep learning capabilities, enabling it to understand and generate complex text content. By training the LLM model to familiarize it with specialized terminology, analysis methods, and report formats in the field of sewage monitoring, it can accurately translate the output of the data analysis and early warning models into professional monitoring and analysis reports.

[0095] Detailed Report: The generated sewage monitoring and analysis report is comprehensive, covering all analytical dimensions of the data analysis and early warning models. The report first outlines the background, purpose, and importance of the monitoring project, then presents detailed data analysis results, including key indicators such as target substance detection, abuse, and major abuse trends. The report also highlights findings from the early warning model, such as new abuse warnings, abuse warnings for inhalation, and cross-abuse warnings, providing emergency response recommendations for relevant departments.

[0096] Data Visualization and Charting: To enhance report readability and intuitiveness, the report generation model leverages the text generation capabilities of the LLM model and combines it with data visualization technology to generate a rich set of charts and graphs. These charts, including but not limited to bar charts, line charts, pie charts, and maps, can intuitively display key information such as the geographic distribution of abuse, temporal trends, and correlations between different types of abuse. These charts provide a more intuitive understanding of the current status and trends of abuse, providing strong support for the development of targeted drug control strategies.

[0097] Conclusions and Recommendations: When generating a report, the report generation model automatically extracts conclusions and recommendations based on the output of the data analysis model and the early warning model. The conclusion section summarizes the main findings of the monitoring project, including key information such as the main types of abuse, severity, and geographical distribution.

[0098] Customized Report Generation: To meet the needs and preferences of diverse users, the report generation model also provides customized report generation. Users can select report content, format, chart type, and even customize key information such as the report title and summary. This customized report generation feature allows users to more flexibly obtain the monitoring and analysis reports they need, improving work efficiency and decision-making effectiveness.

[0099] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0104] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention is intended to include such modifications and variations.

Claims

1. A data classification and evaluation method for sewage monitoring based on big data, characterized in that: The following steps are involved: Divide the total sewage monitoring area into different sewage monitoring sub-areas, and obtain the original data of the data collection points in the sewage monitoring sub-areas from the database; Conduct a comparative analysis of concentration thresholds on the original data, issue an early warning based on the results of the comparative analysis, and conduct first-class and second-class evaluations on different data collection points based on the early warning results; Perform a first comparative analysis based on the first classification evaluation result, perform a first classification adjustment based on the first comparative analysis result, perform a second comparative analysis based on the second classification evaluation result, and perform a second classification adjustment based on the second comparative analysis result; Obtaining a comprehensive classification evaluation result based on the first classification evaluation result and the second classification evaluation result, conducting a third comparative analysis based on the comprehensive classification evaluation result, and conducting a third classification adjustment based on the third comparative analysis result; The concentration correction value is obtained according to the first classification assessment. The specific method of obtaining the concentration correction value is as follows: ； in, Indicates the The concentration correction value of each data collection point is used to quantify the relative negative degree of interference in concentration monitoring. represents a natural constant, Indicates the number of the data collection point. , Indicates the total number of data collection points. A number indicating the type of medical waste, , The total number of numbers indicating the types of medical waste, Indicates the number of the monitoring time period, , Indicates the total number of monitoring time periods. Indicates the The first data collection point The first monitoring period The concentration value in the original data corresponding to each type of medical waste, Indicates the The first data collection point The first monitoring period Medical concentration data for each medical waste type, Indicates the Concentration detection thresholds for each type of medical waste, Indicates the The first data collection point The first monitoring period The wastewater temperature of each medical waste type, Indicates the Standard wastewater temperature for each type of medical waste, Indicates the The first data collection point The first monitoring period The pH value of sewage of each type of medical waste is collected and extracted from the pH value collection equipment. Indicates the The standard pH value of sewage for each type of medical waste is directly extracted from the medical waste database of the sewage monitoring sub-area. represents the sewage temperature correction factor, Indicates the correction factor of sewage pH value; A second classification assessment is performed based on the original data at the data collection points, including: comprehensive analysis of the sewage flow standard value, rainfall standard value, concentration standard value, concentrations of different types in different monitoring time periods at different secondary warning points, and sewage flow and rainfall in different monitoring time periods at different secondary warning points to obtain the concentration mutation degree value.

2. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The early warning based on the concentration threshold comparison analysis results specifically includes: Classify the original data according to predefined data categories to obtain original data under different categories; If the raw data under different categories is equal to or greater than the corresponding concentration threshold, the data collection point in the corresponding sewage monitoring sub-area will be recorded as a first-level warning point and relevant personnel will be notified; If the original data under different categories is less than the corresponding concentration threshold, the data collection point in the corresponding sewage monitoring sub-area will be recorded as a secondary warning point.

3. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The first classification evaluation and the second classification evaluation are respectively performed on different data collection points according to the early warning results, specifically including: Obtain medical waste data at corresponding data collection points through the medical waste database of the sewage monitoring sub-area, and perform a first classification assessment based on the original data and medical waste data at the data collection points; If the data collection point is recorded as a secondary warning point, a second classification assessment will be performed based on the original data at the data collection point.

4. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 3, characterized in that: The first classification assessment based on the original data and medical waste data at the data collection points specifically includes: The data collection points are numbered in sequence, the types of medical waste in the medical waste data are numbered in sequence, and the monitoring time periods corresponding to the original data are numbered in sequence; Directly extract medical concentration data, concentration detection threshold, sewage standard temperature and sewage standard pH value from the medical waste database of the sewage monitoring sub-area; The sewage temperature of different types of medical waste at different data collection points and different monitoring time periods is collected and extracted from the temperature collection equipment; The pH value of sewage of different types of medical waste at different data collection points and different monitoring time periods is collected and extracted from the pH value collection equipment; The concentration correction value is obtained by comprehensively analyzing the medical concentration data, concentration detection threshold, standard temperature of sewage, standard pH value of sewage, sewage temperature of different monitoring time periods for different types of medical waste at different data collection points, and pH value of sewage of different monitoring time periods for different types of medical waste at different data collection points.

5. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The performing the first classification adjustment according to the first comparative analysis result specifically includes: If the concentration correction value of the first-level warning point is equal to or greater than the concentration correction threshold, the corresponding first-level warning point will be recorded as a special-level warning point and relevant personnel will be notified to conduct on-site inspections of the sewage monitoring sub-area where the special-level warning point is located; If the concentration correction value of the first-level warning point is less than the concentration correction threshold, the corresponding first-level warning point will still be recorded as a first-level warning point and the raw data collection frequency of the corresponding first-level warning point will be increased; If the concentration correction value of the second-level warning point is equal to or greater than the concentration correction threshold, the corresponding second-level warning point will be recorded as a first-level warning point, the raw data collection frequency of the corresponding second-level warning point will be increased, and the raw data of the corresponding second-level warning point will be processed by the local anomaly factor detection algorithm; If the concentration correction value of the second-level warning point is less than the concentration correction threshold, the corresponding second-level warning point will be recorded as a third-level warning point, and the original data of the corresponding third-level warning point will be cleaned for similar data using a fuzzy matching algorithm.

6. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The performing the first classification adjustment according to the first comparative analysis result further includes: Count the number of first-level warning points, second-level warning points, and third-level warning points in the sewage monitoring sub-area; If the number of first-level warning points in the sewage monitoring sub-area is equal to or greater than the first-level warning point number threshold, all points in the corresponding sewage monitoring sub-area will be recorded as special-level warning points; If the number of first-level warning points in the sewage monitoring sub-area is less than the first-level warning point number threshold, no adjustment will be made; If the number of second-level warning points in the sewage monitoring sub-area is equal to or greater than the second-level warning point number threshold, all points in the corresponding sewage monitoring sub-area will be recorded as first-level warning points; If the number of secondary warning points in the sewage monitoring sub-area is less than the threshold for the number of secondary warning points, no adjustment will be made; If the number of third-level warning points in the sewage monitoring sub-area is equal to or greater than the third-level warning point number threshold, all points in the corresponding sewage monitoring sub-area will be recorded as second-level warning points; If the number of third-level warning points in the sewage monitoring sub-area is less than the third-level warning point number threshold, no adjustment will be made.

7. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 3, characterized in that: The second classification evaluation based on the original data at the data collection point specifically includes: The sewage flow standard value, rainfall standard value and concentration standard value are directly extracted from the medical waste database of the sewage monitoring sub-area; The concentrations of different types and different monitoring time periods at different secondary warning points are collected and extracted from the intelligent flow statistics equipment; The sewage flow and rainfall at different monitoring time periods at different secondary warning points are collected and extracted from the intelligent flow statistics equipment; A comprehensive analysis is conducted on the standard values ​​of sewage flow, rainfall, concentration, concentrations of different types in different monitoring time periods at different secondary warning points, and sewage flow and rainfall in different monitoring time periods at different secondary warning points to obtain the concentration mutation degree value.

8. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The performing the second classification adjustment according to the second comparative analysis result specifically includes: If the concentration mutation degree value of the second-level warning point is equal to or greater than the concentration mutation degree threshold, the corresponding second-level warning point will be recorded as a first-level warning point, the raw data collection frequency of the corresponding first-level warning point will be increased, and relevant personnel will be notified to clean the raw data of the corresponding first-level warning point; If the concentration mutation degree value of the second-level warning point is less than the concentration mutation degree threshold, the corresponding second-level warning point will still be recorded as a second-level warning point.

9. The data classification and evaluation method for sewage monitoring based on big data as claimed in claim 1, characterized in that: The comprehensive classification evaluation result obtained according to the first classification evaluation result and the second classification evaluation result specifically includes: The comprehensive evaluation value of the concentration data at the second-level warning point is obtained by comprehensive analysis of the concentration correction value and concentration mutation degree value at the second-level warning point, which is used to quantitatively evaluate the comprehensive level of concentration data monitoring quality; Number the secondary warning points in sequence. Indicates the number of the second-level warning point. , Indicates the total number of secondary warning points; The specific comprehensive analysis formula is as follows: ； Indicates the The comprehensive evaluation value of the concentration data of each data collection point is used to quantify the comprehensive evaluation value of the concentration data affected by the interference of concentration monitoring; Indicates the The concentration correction value of each data collection point is used to quantify the relative negative degree of interference in concentration monitoring; Indicates the The concentration mutation degree value of each secondary warning point is used to quantify the relative level value of the concentration monitoring mutation degree; Indicates the The correction factor for the dissolved oxygen content in sewage at each secondary warning point is used to quantify the relative level of concentration monitoring mutation; Indicates the The weight factor of the concentration correction value of each secondary warning point for the comprehensive evaluation value of the concentration data, Indicates the The concentration mutation degree value of each secondary warning point is the weight factor of the comprehensive evaluation value of concentration data.

10. The data classification and evaluation method for sewage monitoring based on big data according to claim 1, characterized in that: The performing of the third classification adjustment according to the third comparative analysis result specifically includes: If the comprehensive evaluation value of the concentration data at the secondary warning point is less than the comprehensive evaluation threshold of the concentration data, the raw data of the corresponding secondary warning point will be cleaned using the standard score algorithm; If the comprehensive evaluation value of the concentration data at the second-level warning point is equal to or greater than the comprehensive evaluation threshold of the concentration data, the corresponding second-level warning point will be recorded as a first-level warning point and the raw data collection frequency of the corresponding second-level warning point will be increased; The special warning points, first-level warning points, second-level warning points and third-level warning points in all data collection points under the sewage monitoring sub-area are used to generate a classified and labeled electronic map report through the report generation model.

Images