Method and system for supervising information of sewage draining exit entering sea based on rule engine

Abstract

The invention discloses a method and a system for supervising sewage draining exit information entering sea based on a rule engine, and relates to the technical field of marine ecological environment supervision. The method comprises the following steps: acquiring multi-source data, and carrying out standardization processing and abnormal value detection to obtain preprocessed data; constructing a rule engine based on the preprocessed data; wherein the rule engine comprises a space time sequence rule optimization model, an association logic rule optimization model and a composite rule judgment model; and utilizing the rule engine to carry out potential environmental influence prediction on future sewage draining exit information, triggering early warning information of a corresponding level when a prediction result exceeds a set threshold value, and pushing the early warning information to a responsibility subject and a supervision department. According to the invention, multi-dimensional rule judgment and intelligent dynamic supervision of the sea sewage draining exit data can be realized by fusing related rules related to sea sewage draining exit supervision work, and powerful technical support is provided for marine ecological environment protection.

Description

Technical Field

[0001] This invention relates to the field of marine ecological environment supervision technology, and in particular to a method and system for supervising information on sewage outfalls into the sea based on a rule engine. Background Technology

[0002] There are many problems that urgently need to be solved in the current supervision of sewage outlets. Although some regions have carried out the construction of sewage outlet informatization and built relevant supervision platforms, these platforms have promoted the transformation of sewage outlet management from the traditional manpower and paper document mode to the informatization mode to a certain extent. However, the current supervision technology still has obvious shortcomings, mainly reflected in the following aspects: (1) Data silo problem: local supervision systems are built independently, data is difficult to share, and a unified national supervision system cannot be formed. (2) Single rule judgment: traditional systems lack the ability to judge composite rules and have difficulty in handling complex correlation analysis of spatial and temporal dimensions. (3) Low supervision efficiency: manual review process is cumbersome and lacks an automated rule verification mechanism. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for monitoring information on sewage outfalls into the sea based on a rule engine, aiming to solve or improve at least one of the aforementioned technical problems.

[0004] To achieve the above objectives, the present invention provides the following solution: A rule-based method for monitoring information on sewage discharge outlets into the sea, comprising: Acquire multi-source data; the multi-source data includes filing data, law enforcement supervision data, and environmental thematic data captured through regulatory systems or applications; The multi-source data is standardized and outlier detected to obtain preprocessed data; A rule engine is constructed based on the preprocessed data; the rule engine includes a spatial-temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial-temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance constraint rules; the association logic rule optimization model consists of multi-dimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm. The rule engine is used to predict the potential environmental impact of future sewage outfalls into the sea. When the prediction results exceed the set threshold, a corresponding level of early warning information is triggered and the early warning information is pushed to the responsible parties and regulatory departments.

[0005] Optionally, the filing data includes basic information on sewage outlets and the responsible entities; the law enforcement and supervision data includes monitoring reports and law enforcement records; and the environmental thematic data includes marine functional zoning data and distribution data of ecologically sensitive areas.

[0006] Optionally, the standardization and outlier detection of the multi-source data to obtain preprocessed data specifically includes: The multi-source data is processed to have a unified dimension, and the data format is unified to JSON or XML; Outlier identification is performed on the uniformly processed data based on the interquartile range (IQR) algorithm. Data exceeding the outlier threshold is identified as outliers and removed to obtain preprocessed data. The outlier threshold includes a lower limit Q1−1.5×IQR and an upper limit Q3+1.5×IQR, where IQR represents the interquartile range, Q1 is the first quartile (representing the value at 25% of the data), and Q3 is the third quartile (representing the value at 75% of the data).

[0007] Optionally, the multidimensional association rules include association rules between pollutant concentration and changes in surrounding water quality.

[0008] Optionally, the spatial weighted time series model modifies traditional time series analysis by introducing a spatial distance decay coefficient, specifically expressed as follows: in, This indicates the corrected pollutant concentration monitoring value. The space influences the weight. Indicates the spatial distance between the sewage outlet and the sensitive area. This indicates the current pollutant concentration value. This indicates the pollutant concentration value monitored in the previous time period; The time-series pattern mining algorithm employs an improved FP-Growth algorithm, embedding time window constraints: in, This indicates the frequency with which events X and Y occur simultaneously within a time window. Indicates the time window Δ T Within, the number of times event X and event Y occur simultaneously. This indicates the total number of monitoring times within the time window. σ Δ represents the statistical quantity. T Indicates the length of the time window. This represents the minimum support threshold; The distance restriction rule is expressed as follows: Where P is the coordinate of the sewage outlet, S is the coordinate of the ecologically sensitive area, and D is the coordinate of the ecologically sensitive area. max This is the maximum permissible distance.

[0009] Optionally, the multidimensional association rule is represented as: in, To improve the rule level, Let X be the probability that events X and Y occur simultaneously. and Let X and Y be the probabilities of events occurring individually. These are the weighting coefficients; The causal reasoning model is expressed as follows: in, This represents the probability that event Y will be abnormal after event X occurs. This represents the probability of event X occurring when event Y is abnormal. λ Δ represents the time decay coefficient. t This represents the time difference between event X and event Y.

[0010] Optionally, the rule fusion algorithm adopts the DS evidence theory, expressed as: in, This represents the confidence level of the composite rule regarding the occurrence of event A. This represents the basic probability allocation of spatial temporal rules for the occurrence of event A. B represents the basic probability allocation of the association logic rule for the occurrence of event A, and B represents other possible events besides the occurrence of event A. The anomaly detection threshold optimization algorithm is expressed as follows: in, Threshold t This indicates a dynamically adjusted warning threshold. μ This represents the average of historical monitoring data. k Indicates the warning coefficient. σ t This represents the standard deviation of the monitoring data for the current time period. t This indicates the system uptime.

[0011] Optionally, the step of using the rule engine to predict the potential environmental impact of future sewage discharge outlets into the sea, and triggering a corresponding level of early warning information when the prediction result exceeds a set threshold, and pushing the early warning information to the responsible entity and regulatory department, specifically includes: The current multi-source data is used to predict the probability of abnormal events through spatial temporal rule optimization model and association logic rule optimization model, respectively, to obtain spatiotemporal anomaly prediction results and logical anomaly prediction results. The spatiotemporal anomaly prediction results and the logical anomaly prediction results are input into the composite rule judgment model for judgment, and the rule fusion algorithm is optimized using dynamically adjusted early warning thresholds to obtain the potential environmental impact prediction results that fuse spatial temporal sequence and related logic. When the prediction result exceeds the set threshold, the corresponding level of early warning information is triggered and the early warning information is pushed to the responsible entity and regulatory department to trigger the corresponding handling process.

[0012] This invention also provides a rule-based system for monitoring information on sewage discharge outlets into the sea, comprising: The data acquisition unit is used to acquire multi-source data, including filing data, law enforcement supervision data, and environmental thematic data captured through the regulatory system or application APP. The data preprocessing unit is used to perform standardization processing and outlier detection on the multi-source data to obtain preprocessed data. A rule building unit is used to build a rule engine based on the preprocessed data; the rule engine includes a spatial-temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial-temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance constraint rules; the association logic rule optimization model consists of multi-dimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm. The regulatory application unit is used to use the rule engine to predict the potential environmental impact of future sewage discharge outlets into the sea. When the prediction result exceeds the set threshold, it triggers the corresponding level of early warning information and pushes the early warning information to the responsible entity and regulatory department.

[0013] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: This invention discloses a method and system for monitoring information on sewage discharge outlets into the sea based on a rule engine. The method includes acquiring multi-source data, including registration data, law enforcement supervision data, and environmental thematic data captured through a monitoring system or application APP; standardizing and detecting outliers in the multi-source data to obtain preprocessed data; constructing a rule engine based on the preprocessed data; the rule engine includes a spatial-temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial-temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance constraint rules; the association logic rule optimization model consists of multi-dimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm; and using the rule engine to predict the potential environmental impact of future sewage discharge outlet information into the sea, triggering a corresponding level of early warning information when the prediction result exceeds a set threshold, and pushing the early warning information to the responsible entity and regulatory department. This invention can integrate relevant rules involved in the supervision of sewage outfalls into the sea, enabling multi-dimensional rule-based judgment and intelligent dynamic supervision of sewage outfall data, thus providing strong technical support for marine ecological environment protection. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart of the method for monitoring information on sewage discharge outlets into the sea based on a rule engine, as described in this invention. Figure 2 This is a flowchart of the initial filing process in this embodiment; Figure 3 This is a flowchart of the filing information change process in this embodiment; Figure 4 This is a flowchart of the self-monitoring process in this embodiment; Figure 5 This is a flowchart of the monitoring and supervision process in this embodiment; Figure 6 This is a flowchart of the law enforcement inspection process in this embodiment; Figure 7 This is a flowchart of the supervision and inspection process in this embodiment. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] The purpose of this invention is to provide a method and system for monitoring information on sewage outfalls into the sea based on a rule engine, aiming to solve or improve at least one of the aforementioned technical problems.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] like Figure 1 As shown, this invention provides a method for monitoring information on sewage discharge outlets into the sea based on a rule engine, including: Step 100: Obtain multi-source data; the multi-source data includes filing data, law enforcement supervision data, and environmental thematic data captured through the regulatory system or application APP.

[0020] Step 200: Standardize and detect outliers in the multi-source data to obtain preprocessed data.

[0021] Step 300: Construct a rule engine based on the preprocessed data; the rule engine includes a spatial temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance restriction rules; the association logic rule optimization model consists of multidimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm.

[0022] Step 400: Use the rule engine to predict the potential environmental impact of future sewage outfalls into the sea. When the prediction results exceed the set threshold, trigger the corresponding level of early warning information and push the early warning information to the responsible entity and regulatory department.

[0023] As a specific implementation method, step 100 involves: accessing a multi-source data acquisition interface and integrating registration data, law enforcement supervision data, and environmental thematic data through a regulatory system or APP. The registration data includes basic information about the discharge outlet and the responsible entity; the law enforcement supervision data includes monitoring reports and enforcement records; and the environmental thematic data includes marine functional zoning data and data on the distribution of ecologically sensitive areas.

[0024] As a specific implementation method, step 200 involves: standardizing and detecting outliers in the multi-source data to obtain preprocessed data. The data preprocessing process includes cleaning, standardizing, and detecting outliers in the collected data to ensure data quality. Specific methods employed include: The multi-source data is processed to have a unified dimension, and the data format is standardized to JSON or XML. Outlier identification is performed on the standardized data based on the interquartile range (IQR) algorithm. Data exceeding the outlier threshold are identified as outliers and removed, resulting in preprocessed data. The outlier threshold includes a lower limit Q1 − 1.5 × IQR and an upper limit Q3 + 1.5 × IQR, where IQR represents the interquartile range, Q1 is the first quartile (representing the value at 25% of the data), and Q3 is the third quartile (representing the value at 75% of the data).

[0025] As a specific implementation method, step 300 specifically involves: constructing a rule engine, which includes the following rule base: Spatial rule base: Stores rules related to geographical location, such as distance restrictions between sewage outlets and marine ecologically sensitive areas (mangroves, coral reefs, etc.), and verification of the selected sea area of ​​the sewage outlet with the entered latitude and longitude.

[0026] Time-series rule base: Define rules related to monitoring time and monitoring frequency. For example, according to the "HJ 1387-2024" standard, dynamically verify the frequency of monitoring data submission. Key management sewage outlets need to submit a full indicator monitoring report once per quarter.

[0027] Association rule base: Establish association rules between pollutant concentration and changes in surrounding water quality, such as the association model between COD concentration and seawater eutrophication.

[0028] Logical rule base: Establishes rules for event occurrence, as well as rules for user permissions, data viewing, and approval processes. For example, responsible entities can only view data from their own unit and data they created; accounts with city-level permissions can view submitted data within their own jurisdiction, as well as data they saved; accounts with provincial-level permissions can view submitted data within their province, and provincial departments can confirm the data, but this does not affect the data filing process; river basin bureau accounts can view data from provinces within their river basin; and oceanographic department accounts can view all submitted data.

[0029] Based on the above rule base, a spatial temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model are constructed respectively.

[0030] The spatial temporal rule optimization model includes: The spatially weighted time series model, by introducing a spatial distance decay coefficient, corrects traditional time series analysis, and is specifically expressed as follows: in, This indicates the corrected pollutant concentration monitoring value. The space influences the weight. Indicates the spatial distance between the sewage outlet and the sensitive area. This indicates the current pollutant concentration value. This indicates the pollutant concentration value monitored in the previous time period.

[0031] The time series pattern mining algorithm employs an improved FP-Growth algorithm, embedding time window constraints: in, This indicates the frequency with which events X and Y occur simultaneously within a time window. Indicates the time window Δ T Within, the number of times event X and event Y occur simultaneously. This indicates the total number of monitoring times within the time window. σ Δ represents the statistical quantity. T Indicates the length of the time window. This represents the minimum support threshold.

[0032] The distance restriction rule is expressed as follows: Where P is the coordinate of the sewage outlet, S is the coordinate of the ecologically sensitive area, and D is the coordinate of the ecologically sensitive area. max This is the maximum permissible distance.

[0033] The association logic rule optimization model includes: Multidimensional association rules are specifically expressed as follows: in, To improve the rule level, Let X be the probability that events X and Y occur simultaneously. and Let X and Y be the probabilities of events occurring individually. These are the weighting coefficients.

[0034] The causal reasoning model is specifically represented as follows: in, This represents the probability that event Y will be abnormal after event X occurs. This represents the probability of event X occurring when event Y is abnormal. λ Δ represents the time decay coefficient. t This represents the time difference between event X and event Y.

[0035] This composite rule-based judgment model includes: The rule fusion algorithm, employing the DS evidence theory, is specifically expressed as follows: in, This represents the confidence level of the composite rule regarding the occurrence of event A. This represents the basic probability allocation of spatial temporal rules for the occurrence of event A. B represents the basic probability allocation of the association logic rule for the occurrence of event A, and B represents other possible events besides event A.

[0036] The anomaly detection threshold optimization algorithm is specifically expressed as follows: in, Threshold t This indicates a dynamically adjusted warning threshold. μ This represents the average of historical monitoring data. k Indicates the warning coefficient. σ t This represents the standard deviation of the monitoring data for the current time period. t This indicates the system uptime.

[0037] As one specific implementation method, step 400 specifically includes: The current multi-source data is used to predict the probability of abnormal events through a spatial-temporal rule optimization model and an association logic rule optimization model, respectively, to obtain spatiotemporal anomaly prediction results and logical anomaly prediction results. The spatiotemporal anomaly prediction results and the logical anomaly prediction results are input into the composite rule judgment model for judgment, and the rule fusion algorithm is optimized using a dynamically adjusted warning threshold to obtain the potential environmental impact prediction results that fuse spatial-temporal and association logic. When the prediction result exceeds the set threshold, the corresponding level of warning information is triggered, and the warning information is pushed to the responsible entity and regulatory department to trigger the corresponding handling process.

[0038] Based on the above technical solution, the following embodiments are provided.

[0039] In practical applications, the steps described above are executed in the system through the data aggregation layer, rule engine layer, data fusion layer, and application service layer.

[0040] The system comprises several layers: data collection at the data aggregation layer; rule base and processing model construction at the rule engine layer; data fusion analysis of various rule bases and processed data at the data fusion layer; and finally, the application service layer reflecting the regulatory results. For example, it provides real-time status monitoring, rule-based early warning, and statistical analysis of discharge outlets through ledger management; initial registration, registration modification, and registration cancellation for discharge outlet responsible parties or construction units through registration settings; dynamic supervision supporting the standardized construction and self-monitoring of discharge outlet responsible parties or construction units, as well as the supervision, monitoring, enforcement, and inspection operations of regulatory departments at all levels; connection to mobile enforcement terminals supporting on-site data collection, rule verification, and enforcement recording, achieving offline data synchronization; and a data visualization system that visualizes the distribution of discharge outlets, rule execution results, and environmental impact analysis.

[0041] In addition, the following rules are set for uploading multi-source data: Rule engine-driven filing: A workflow state machine is built into the rule engine layer. When an enterprise submits a filing application, it automatically matches the rule of "responsible entity submits → municipal department reviews". The task allocation logic is triggered through the Drools engine to push the approval task to the local ecological and environmental department. When the review is approved, the engine generates a unique filing number according to the coding rules and updates the status to "filed". The entire process verifies the permissions of the approval nodes and the compliance of the process through the rule base, realizing a closed loop of "application-allocation-feedback".

[0042] The rule engine-driven multi-source data fusion architecture uses the filing code as the key to link a spatial database (WGS84 coordinates) and a business database (emission concentration, etc.), employing a "main table + appendix table" structure: the main table stores structured filing information, while the appendix tables index unstructured documents such as demonstration reports. The engine executes the monitoring frequency rules of the "Technical Guidelines for Monitoring and Supervision of Sewage Outfalls into Rivers and Seas" (HJ 1387-2024) in real time, automatically checks the data submission cycle, triggers early warning rules for overdue data submissions, and verifies the consistency between the sea area coordinates and the reported information.

[0043] The rules engine supports dynamic code generation rules: The engine integrates GB / T2260 administrative division codes and sewage discharge type codes (such as "GY" for industrial sewage outlets), generating codes according to an 18-digit rule: the first 6 digits are the administrative division code + the 7th digit is the management type identifier (Z-key / J-simplified) + the last 11 digits are the year and month serial number. During generation, the spatial verification rules in the "Technical Solution.doc" are triggered, and the ST_Distance function verifies whether the coordinates are within the selected sea area. The uniqueness of the code is guaranteed by the engine's built-in conflict detection rules, ensuring the traceability of administrative divisions and the identification of business types.

[0044] In the aforementioned system, the initial filing process is as follows: Figure 2 As shown, the responsible entity / construction unit logs into the system interface, registers an account, fills in the responsible entity information through the registered account, and then logs back into the system for the initial filing. Data query and display functions are opened according to the "city-level / district-level" permission rules, including the setting of new or historical sewage outlets, allowing for further targeted management. The filing cancellation process is similar to the initial filing process; simply click "cancel" in the required options.

[0045] In general management, fill out the General Management Registration Form for Sewage Outlets Discharging into the Sea and upload relevant supporting documents. In simplified management, fill out the Simplified Management Registration Form for Sewage Outlets Discharging into the Sea and upload relevant supporting documents. In key management, fill out the Key Management Registration Form for Sewage Outlets Discharging into the Sea and upload relevant supporting documents. Then, start the rule engine to verify the data materials uploaded for each of the above management types. After completion, click the save, submit, or close button.

[0046] The process for changing filing information is as follows: Figure 3 As shown, the responsible party / construction unit logs into the system interface, registers an account, fills in the responsible party information through the registered account, and then logs back into the system to make the filing change. The subsequent process is the same as the relevant steps for the initial filing.

[0047] Self-monitoring process as follows Figure 4 As shown, the responsible entity / construction unit logs into the system interface, registers an account, and completes the registration of the responsible entity information. Then, they log back into the system to register key sewage outlets and large-scale, contiguous sewage outlets from marine aquaculture. Key sewage outlets are monitored via real-time flow meter interfaces, while large-scale, contiguous sewage outlets from marine aquaculture are monitored via monitoring reports. The above materials are then uploaded to the regulatory system for rule engine verification to obtain the self-monitoring results.

[0048] Supervision and monitoring process such as Figure 5 As shown, after the provincial level formulates a monitoring plan and submits it to the system, the municipal level implements monitoring according to the monitoring plan, fills in the monitoring information, submits the monitoring results, and uses the rule engine to verify them to obtain the supervision and monitoring results.

[0049] Law enforcement inspection process as follows Figure 6 As shown, the city-level authorities formulate an enforcement inspection plan, submit it to the system, conduct enforcement inspections, fill in relevant information, submit inspection results, use a rule engine to verify, and punish the responsible parties if violations are confirmed. For problems found, rectification and handling are carried out as required, ultimately forming the enforcement inspection results.

[0050] Supervision and inspection process as follows Figure 7As shown, the river basin bureau formulates a supervision and inspection plan, submits it to the system, conducts supervision and inspection, fills in relevant information, submits the inspection results, uses a rule engine for verification, and if problems are found, it urges and follows up on the rectification of the problems.

[0051] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0052] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for monitoring information on sewage discharge outlets into the sea based on a rule engine, characterized in that, include: Acquire multi-source data; the multi-source data includes filing data, law enforcement supervision data, and environmental thematic data captured through regulatory systems or applications; The multi-source data is standardized and outlier detected to obtain preprocessed data; A rule engine is constructed based on the preprocessed data; the rule engine includes a spatial-temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial-temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance constraint rules; the association logic rule optimization model consists of multi-dimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm. The rule engine is used to predict the potential environmental impact of future sewage outfalls into the sea. When the prediction results exceed the set threshold, a corresponding level of early warning information is triggered and the early warning information is pushed to the responsible parties and regulatory departments.

2. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The filing data includes basic information on sewage outlets and the responsible entities; the law enforcement and supervision data includes monitoring reports and law enforcement records; and the environmental thematic data includes marine functional zoning data and distribution data of ecologically sensitive areas.

3. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The standardization and outlier detection of the multi-source data to obtain preprocessed data specifically includes: The multi-source data is processed to have a unified dimension, and the data format is unified to JSON or XML; Outlier identification is performed on the uniformly processed data based on the interquartile range (IQR) algorithm. Data exceeding the outlier threshold is identified as outliers and removed to obtain preprocessed data. The outlier threshold includes a lower limit Q1−1.5×IQR and an upper limit Q3+1.5×IQR, where IQR represents the interquartile range, Q1 is the first quartile (representing the value at 25% of the data), and Q3 is the third quartile (representing the value at 75% of the data).

4. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The multidimensional association rules include association rules between pollutant concentration and changes in surrounding water quality.

5. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The spatial weighted time series model introduces a spatial distance attenuation coefficient to correct traditional time series analysis, specifically as follows: in, This indicates the corrected pollutant concentration monitoring value. The space influences the weight. Indicates the spatial distance between the sewage outlet and the sensitive area. This indicates the current pollutant concentration value. This indicates the pollutant concentration value monitored in the previous time period; The time-series pattern mining algorithm employs an improved FP-Growth algorithm, embedding time window constraints: in, This indicates the frequency with which events X and Y occur simultaneously within a time window. Indicates the time window Δ T Within, the number of times event X and event Y occur simultaneously. This indicates the total number of monitoring times within the time window. σ Δ represents the statistical quantity. T Indicates the length of the time window. This represents the minimum support threshold; The distance restriction rule is expressed as follows: Where P is the coordinate of the sewage outlet, S is the coordinate of the ecologically sensitive area, and D is the coordinate of the ecologically sensitive area. max This is the maximum permissible distance.

6. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The multidimensional association rule is represented as follows: in, To improve the rule level, Let X be the probability that events X and Y occur simultaneously. and Let X and Y be the probabilities of events occurring individually. These are the weighting coefficients; The causal reasoning model is expressed as follows: in, This represents the probability that event Y will be abnormal after event X occurs. This represents the probability of event X occurring when event Y is abnormal. λ Δ represents the time decay coefficient. t This represents the time difference between event X and event Y.

7. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The rule fusion algorithm adopts the DS evidence theory and is expressed as follows: in, This represents the confidence level of the composite rule regarding the occurrence of event A. This represents the basic probability allocation of spatial temporal rules for the occurrence of event A. B represents the basic probability allocation of the association logic rule for the occurrence of event A, and B represents other possible events besides the occurrence of event A. The anomaly detection threshold optimization algorithm is expressed as follows: in, Threshold t This indicates a dynamically adjusted warning threshold. μ This represents the average of historical monitoring data. k Indicates the warning coefficient. σ t This represents the standard deviation of the monitoring data for the current time period. t This indicates the system uptime.

8. The method for monitoring information on sewage discharge outlets into the sea based on a rule engine according to claim 1, characterized in that, The process of using the rule engine to predict the potential environmental impact of future sewage outfalls into the sea, triggering a corresponding level of early warning information when the prediction result exceeds a set threshold, and pushing the early warning information to the responsible parties and regulatory departments, specifically includes: The current multi-source data is used to predict the probability of abnormal events through spatial temporal rule optimization model and association logic rule optimization model, respectively, to obtain spatiotemporal anomaly prediction results and logical anomaly prediction results. The spatiotemporal anomaly prediction results and the logical anomaly prediction results are input into the composite rule judgment model for judgment, and the rule fusion algorithm is optimized using dynamically adjusted early warning thresholds to obtain the potential environmental impact prediction results that fuse spatial temporal sequence and related logic. When the prediction result exceeds the set threshold, the corresponding level of early warning information is triggered and the early warning information is pushed to the responsible entity and regulatory department to trigger the corresponding handling process.

9. A rule-based system for monitoring information on sewage discharge outlets into the sea, characterized in that, include: The data acquisition unit is used to acquire multi-source data, including filing data, law enforcement supervision data, and environmental thematic data captured through the regulatory system or application APP. The data preprocessing unit is used to perform standardization processing and outlier detection on the multi-source data to obtain preprocessed data. A rule building unit is used to build a rule engine based on the preprocessed data; the rule engine includes a spatial-temporal rule optimization model, an association logic rule optimization model, and a composite rule judgment model; the spatial-temporal rule optimization model consists of a spatial weighted temporal model, a temporal pattern mining algorithm, and distance constraint rules; the association logic rule optimization model consists of multi-dimensional association rules and a causal reasoning model; the composite rule judgment model consists of a rule fusion algorithm and an anomaly identification threshold optimization algorithm. The regulatory application unit is used to use the rule engine to predict the potential environmental impact of future sewage discharge outlets into the sea. When the prediction result exceeds the set threshold, it triggers the corresponding level of early warning information and pushes the early warning information to the responsible entity and regulatory department.

Images