Method and device for enhancing water affairs knowledge using large models
By acquiring and analyzing sewage data, building a water knowledge graph and sewage data analysis model, the problem of insufficient intelligence and automation level of water management in the existing technology is solved, and more efficient water resource management and water knowledge enhancement is achieved.
Patent Information
- Application Number
- CN202411090594.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing methods for enhancing water knowledge are difficult to effectively process and analyze large amounts of sewage data, resulting in insufficient intelligence and automation of water management, and the inability to fully improve the understanding of water conservancy field and enhance the water knowledge.
By obtaining the water enhancement needs of drainage scenarios to be enhanced, collecting and isomerizing sewage data, determining the map schema, building a water knowledge graph and sewage data analysis model, analyzing water pollution status, establishing a water pollution balance and environmental impact model, and providing data-driven decision support.
It has improved the in-depth insight and prediction capabilities of water management's decision-making process, optimized water resource management, enhanced resource utilization efficiency in water business scenarios, and improved the enhancement effect of water business knowledge.
Smart Images

Figure CN118626659B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer science, and in particular to a method and device for enhancing water affairs knowledge by using a large model. Background Art
[0002] Enhancing water knowledge mainly involves using large-scale deep learning models to improve the intelligence level of the water industry. These large models play an important role in processing large amounts of sewage data, predicting water resource demand, and optimizing the operation of water facilities.
[0003] At present, water affairs knowledge is mainly enhanced by collecting water-related data, including water resources, water quality, water demand, meteorological information, etc., and storing and managing them. The professional knowledge and skills of water industry staff are improved through seminars, training courses, workshops, etc. Compared with this method, the use of large model technology can process and analyze large amounts of data, provide data-driven decision support, realize the intelligence and automation of water affairs management, reduce manual intervention, improve work efficiency, and enhance the understanding of the model in the field of water conservancy, thereby improving the enhancement effect of water affairs knowledge. Summary of the invention
[0004] The present invention provides a method and device for enhancing water affairs knowledge using a large model, the main purpose of which is to enhance the understanding of the model in the field of water conservancy and improve the enhancement effect of water affairs knowledge in water affairs scenarios.
[0005] To achieve the above object, the present invention provides a method for enhancing water affairs knowledge using a large model, comprising:
[0006] Acquire water conservancy enhancement requirements for the drainage scene to be enhanced, collect sewage data of the drainage scene to be enhanced based on the water conservancy enhancement requirements, perform isomorphism processing on the sewage data, and obtain water conservancy sewage data;
[0007] Determine a graph schema of the water and sewage data, and construct a water knowledge graph of the water and sewage data based on the graph schema;
[0008] Identifying water service characteristics of the water service and sewage data, and establishing a sewage data analysis model for the water service and sewage data based on the water service characteristics;
[0009] Based on the water affairs sewage data, the water pollution state of the drainage scene to be enhanced is analyzed using the sewage data analysis model, and based on the water affairs knowledge graph and the water pollution state, a water pollution balance model and a water pollution environmental impact model of the drainage scene to be enhanced are constructed;
[0010] Based on the water pollution balance model and the water pollution environmental impact model, the water pollution solution of the drainage scenario to be enhanced is analyzed, and the water affairs knowledge enhancement of the drainage scenario to be enhanced is performed based on the water affairs knowledge graph and the water pollution solution.
[0011] Optionally, the collecting sewage data of the drainage scene to be enhanced based on the water affairs enhancement demand includes:
[0012] Analyze the demand characteristics of the water service enhancement demand;
[0013] Based on the demand characteristics, determining an enhanced data source for the drainage scenario to be enhanced;
[0014] Analyzing the acquisition method of the enhanced data source;
[0015] configuring data acquisition components of the acquisition method and determining optimal arrangement points of the data acquisition components;
[0016] Based on the optimal arrangement point, the data acquisition component is used to collect sewage data of the drainage scene to be enhanced.
[0017] Optionally, determining a schema of the water and sewage data includes:
[0018] Identify the data entity of the water and sewage data;
[0019] defining an entity tag of the data entity;
[0020] Based on the entity labels, relationship modeling is performed on the data entities to obtain entity relationships;
[0021] Based on the entity relationship, define the graph node type and graph edge type of the water and sewage data;
[0022] Based on the graph node type and the graph edge type, a graph schema of the water and sewage data is constructed.
[0023] Optionally, performing relationship modeling on the data entities to obtain entity relationships includes:
[0024] Constructing a relational CRF model of the data entity;
[0025] Calculating the model parameters of the relational CRF model using a preset likelihood function;
[0026] Among them, the likelihood function is:
[0027] ;
[0028] in, Represents model parameters The likelihood function of Represents a data entity, Relationship labels representing data entities, represents the model parameters of the CRF model, Represents the data entity in a given data entity and model parameters The probability of getting the relationship label under
[0029] Based on the model parameters, the entity relations of the data entities are extracted using the relational CRF model.
[0030] Optionally, constructing a water affairs knowledge graph of the water affairs and sewage data based on the graph schema includes:
[0031] Mapping the water and sewage data into the graph schema to obtain a mapping result;
[0032] Based on the mapping result, construct an entity relationship diagram of the water and sewage data;
[0033] Integrate the entity attribute information of the data entity corresponding to the water and sewage data into the entity relationship diagram to obtain an attribute entity relationship diagram;
[0034] Calculating data consistency of the attribute entity relationship diagram;
[0035] The attribute entity relationship diagram is optimized through the data consistency to obtain a water affairs knowledge graph.
[0036] Optionally, the analyzing the water pollution state of the drainage scene to be enhanced by using the sewage data analysis model based on the water service sewage data includes:
[0037] Serializing the water and sewage data to obtain serial sewage data;
[0038] Identifying dependencies between the water service characteristics corresponding to the sequence sewage data;
[0039] Based on the dependency, analyzing the sewage operation graph of the drainage scenario to be enhanced using the sewage data analysis model;
[0040] Based on the sewage operation map, the water pollution state of the drainage scene to be enhanced is determined.
[0041] Optionally, constructing a water pollution balance model and a water pollution environmental impact model of the drainage scenario to be enhanced based on the water affairs knowledge graph and the water pollution status includes:
[0042] Based on the water pollution state, analyzing the water pollution balance mechanism of the drainage scenario to be enhanced;
[0043] Constructing an optimization target for the water pollution balance mechanism;
[0044] Based on the optimization objective, determining an optimization function of the water pollution balance mechanism;
[0045] By means of the optimization function, a water pollution balance model of the drainage scenario to be enhanced is established;
[0046] Based on the water affairs knowledge graph, analyzing the water pollution environmental impact factors of the drainage scenario to be enhanced;
[0047] Collecting sequence factor data of the water pollution environmental impact factors;
[0048] Based on the sequence factor data, analyzing the influence relationship of the water pollution environment influencing factor on the water pollution state corresponding to the drainage scene to be enhanced;
[0049] Based on the impact relationship, a water pollution environment impact model of the drainage scenario to be enhanced is constructed.
[0050] Optionally, the analyzing, based on the sequence factor data, the influence relationship of the water pollution environment influencing factor on the water pollution state corresponding to the drainage scene to be enhanced includes:
[0051] Identify the data feature vector and water pollution status label of the sequence factor data;
[0052] Based on the data feature vector and the water pollution state label, the influence relationship function of the water pollution environment impact factor on the water pollution state corresponding to the drainage scene to be enhanced is constructed using the following formula;
[0053] ;
[0054] in, represents the predicted water pollution status value, The factor eigenvector representing the environmental impact factor of water pollution, The first data feature vectors, represents the Lagrange multiplier, Represents the sequence factor data The water pollution status label corresponding to the data feature vector, represents the kernel function, represents the bias term, represents the number of data feature vectors;
[0055] Based on the influence relationship function, the influence relationship of the water pollution environment influence factor on the water pollution state corresponding to the drainage scene to be enhanced is analyzed.
[0056] Optionally, the analyzing the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model includes:
[0057] Based on a preset state expectation value, analyzing the state loss value of the drainage scenario to be enhanced;
[0058] Identifying constraints of the drainage scenario to be enhanced;
[0059] Based on the state loss value, the constraint conditions and the water pollution environmental impact model, construct a water pollution integrated module for the drainage scenario to be enhanced;
[0060] Calculating water resource configuration parameters of the water pollution integrated module using the optimization function corresponding to the water pollution balance model;
[0061] Based on the water resource configuration parameters, a water pollution solution for the drainage scenario to be enhanced is constructed.
[0062] In order to solve the above problems, the present invention further provides a device for enhancing water affairs knowledge by using a large model, the device comprising:
[0063] A sewage data processing module is used to obtain water affairs enhancement requirements for drainage scenarios to be enhanced, collect sewage data for the drainage scenarios to be enhanced based on the water affairs enhancement requirements, and perform isomorphism processing on the sewage data to obtain water affairs sewage data;
[0064] A knowledge graph construction module, used to determine the graph schema of the water and sewage data, and to construct a water knowledge graph of the water and sewage data based on the graph schema;
[0065] An analysis model building module, used to identify the water service characteristics of the water service and sewage data, and to establish a sewage data analysis model for the water service and sewage data based on the water service characteristics;
[0066] A supply and demand status analysis module, used to analyze the water pollution status of the drainage scenario to be enhanced based on the water affairs sewage data and the sewage data analysis model, and to construct a water pollution balance model and a water pollution environmental impact model for the drainage scenario to be enhanced based on the water affairs knowledge graph and the water pollution status;
[0067] A water affairs knowledge enhancement module is used to analyze the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model, and to perform water affairs knowledge enhancement of the drainage scenario to be enhanced based on the water affairs knowledge graph and the water pollution solution.
[0068] The present invention obtains water sewage data by isomorphizing the sewage data, so that the data has a unified data format, structure, unit and scope, and provides support for subsequent water management and decision-making; the present invention can determine an accurate and comprehensive graph schema by determining the graph schema of the water sewage data, which is used to construct a water knowledge graph; the present invention constructs a water knowledge graph of the water sewage data based on the graph schema to support the decision-making process of water management and provide deeper insights and prediction capabilities; further, based on the water characteristics, the present invention establishes a sewage data analysis model for the water sewage data to perform a detailed analysis of the sewage data; further, based on the water sewage data, the present invention uses the sewage data analysis model to analyze the water pollution status of the drainage scene to be enhanced, which can provide support for water resource management and optimization; finally, based on the water pollution balance model and the water pollution environmental impact model, the present invention analyzes the water pollution solution of the drainage scene to be enhanced, which can improve the resource utilization efficiency of the water scene, thereby improving the knowledge enhancement of the water scene. Therefore, the method and device for enhancing water affairs knowledge using a large model proposed in the present invention can enhance the model's understanding in the field of water conservancy and improve the effect of enhancing water affairs knowledge in water affairs scenarios. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] Figure 1 A flow chart of a method for enhancing water affairs knowledge by using a large model provided by an embodiment of the present invention;
[0070] Figure 2 A functional module diagram of a device for enhancing water affairs knowledge using a large model provided by an embodiment of the present invention;
[0071] Figure 3 A schematic diagram of the structure of an electronic device of an apparatus for enhancing water affairs knowledge using a large model provided by an embodiment of the present invention;
[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0074] The embodiment of the present application provides a method for enhancing water affairs knowledge using a large model. The execution subject of the method for enhancing water affairs knowledge using a large model includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for enhancing water affairs knowledge using a large model can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.
[0075] Reference Figure 1 FIG. 1 is a flow chart of a method for enhancing water affairs knowledge by using a large model according to an embodiment of the present invention. In this embodiment, the method for enhancing water affairs knowledge by using a large model includes:
[0076] S1. Obtain water conservancy enhancement requirements for the drainage scenario to be enhanced, collect sewage data for the drainage scenario to be enhanced based on the water conservancy enhancement requirements, perform isomorphism processing on the sewage data, and obtain water conservancy sewage data.
[0077] It should be explained that the drainage scene to be enhanced may be a sewage purification plant, and the water enhancement requirements refer to specific requirements that must be met in order to improve the performance of the drainage system and meet water management challenges, such as the enhancement of sewage data processing and analysis capabilities, and the reduction of flood and overflow risks in extreme rainfall events. The sewage data includes information such as water quality, flow, flow rate, and pollutant concentration of sewage in the drainage scene.
[0078] The present invention performs isomorphic processing on the sewage data to obtain water affairs sewage data, which can have a unified data format, structure, unit and range, and provide support for subsequent water affairs management and decision-making. The water affairs sewage data refers to a data set after the sewage data is cleaned, format converted, and other operations are performed.
[0079] In detail, based on the water affairs enhancement demand, collecting sewage data of the drainage scene to be enhanced includes:
[0080] Analyze the demand characteristics of the water service enhancement demand;
[0081] Based on the demand characteristics, determining an enhanced data source for the drainage scenario to be enhanced;
[0082] Analyzing the acquisition method of the enhanced data source;
[0083] configuring data acquisition components of the acquisition method and determining optimal arrangement points of the data acquisition components;
[0084] Based on the optimal arrangement point, the data acquisition component is used to collect sewage data of the drainage scene to be enhanced.
[0085] Among them, the demand characteristics refer to the specific attributes of water conservancy enhanced demand, including data type, accuracy requirement, time frequency, coverage, etc. The enhanced data source refers to additional data used to collect and enhance sewage data, including historical data, real-time data, predicted data, simulation data, etc. The acquisition method refers to the strategy and method for obtaining data from the enhanced data source, including automatic collection, manual reporting, third-party purchase, public data sets, etc. The data acquisition component refers to the component for obtaining the enhanced data source, including sensing equipment, data crawling components and other components. The optimal layout point refers to the placement location of the data acquisition component. The optimal layout point can be on the water conservancy equipment or in the data repository.
[0086] Furthermore, the determination of the optimal arrangement point of the data acquisition component may be determined according to demand characteristics and characteristics of the enhanced data source.
[0087] Furthermore, the sewage data is homogenized to obtain water sewage data which can be processed by homogenous CSV, JSON and other tools.
[0088] S2. Determine the graph schema of the water and sewage data, and construct a water knowledge graph of the water and sewage data based on the graph schema.
[0089] The present invention can determine an accurate and comprehensive graph schema for constructing a water affairs knowledge graph by determining the graph schema of the water affairs and sewage data, wherein the graph schema refers to the core component of the knowledge graph, which describes the structure of entities and their relationships in the water affairs and sewage data.
[0090] It should be explained that the graph schema is a blueprint or template for building a knowledge graph, which defines the data structure and relationships; while the water affairs knowledge graph is an actual data set built based on the graph schema, which contains specific information and knowledge in the water affairs field. The graph schema is abstract, while the water affairs knowledge graph is concrete, and it forms a useful knowledge base by filling in actual data.
[0091] In detail, the determining of the schema of the water and sewage data includes:
[0092] Identify the data entity of the water and sewage data;
[0093] defining an entity tag of the data entity;
[0094] Based on the entity labels, relationship modeling is performed on the data entities to obtain entity relationships;
[0095] Based on the entity relationship, define the graph node type and graph edge type of the water and sewage data;
[0096] Based on the graph node type and the graph edge type, a graph schema of the water and sewage data is constructed.
[0097] The data entity refers to an object with independent meaning and characteristics in water and sewage data, such as an outfall, a river, a water quality monitoring station, a pollutant, etc. The entity label refers to an identifier for classifying and identifying an entity, usually including the name, type, and attributes of the entity. For example, an outfall entity may be labeled as "outfall 1", "industrial wastewater outfall", etc. The entity relationship refers to the relationship between entities, such as the discharge relationship between an outfall and a river, the monitoring relationship between a pollutant and a water quality monitoring station, etc. The graph node type refers to the definition of the node type (such as a water quality monitoring station, an outfall, a pollutant, etc.) and edge type (such as a discharge relationship, a monitoring relationship, etc.) in the graph according to the entity relationship.
[0098] Furthermore, performing relationship modeling on the data entities to obtain entity relationships includes:
[0099] Constructing a relational CRF model of the data entity;
[0100] Calculating the model parameters of the relational CRF model using a preset likelihood function;
[0101] Among them, the likelihood function is:
[0102] ;
[0103] in, Represents model parameters The likelihood function of Represents a data entity, Relationship labels representing data entities, represents the model parameters of the CRF model, Represents the data entity in a given data entity and model parameters The probability of getting the relationship label under
[0104] Based on the model parameters, the entity relations of the data entities are extracted using the relational CRF model.
[0105] The relational CRF model refers to a model based on conditional random fields (CRF) for identifying relations between entities in text. The model parameters refer to parameters that need to be learned in the relational CRF model. These parameters determine how the model processes and predicts sequence data, including relations between entities. The relational labels refer to the types of relations between entities in a given input text. These labels are usually discrete and represent specific relations between entities, such as "located in", "belonging to", "influence", etc.
[0106] Furthermore, the data entity identifying the water and sewage data may be extracted by natural language processing (NLP) technology or a data mining algorithm.
[0107] Optionally, the present invention constructs a water affairs knowledge graph of the water affairs and sewage data based on the graph schema to support the decision-making process of water affairs management and provide deeper insights and prediction capabilities. The water affairs knowledge graph refers to a structured knowledge base used to represent entities, relationships and attributes in the water affairs field.
[0108] In detail, the water affairs knowledge graph of the water affairs and sewage data is constructed based on the graph schema, including:
[0109] Mapping the water and sewage data into the graph schema to obtain a mapping result;
[0110] Based on the mapping result, construct an entity relationship diagram of the water and sewage data;
[0111] Integrate the entity attribute information of the data entity corresponding to the water and sewage data into the entity relationship diagram to obtain an attribute entity relationship diagram;
[0112] Calculating data consistency of the attribute entity relationship diagram;
[0113] The attribute entity relationship diagram is optimized through the data consistency to obtain a water affairs knowledge graph.
[0114] Among them, the mapping result is a specific representation of entities, relationships and attributes in the knowledge graph, the entity relationship diagram is a graphical representation of entities and their relationships in the knowledge graph, the entities are nodes in the graph, and the relationships are edges connecting the entities, the attribute entity relationship diagram refers to a graphical representation of entities and their attributes in the knowledge graph, and the data consistency refers to the consistency relationship between the various parts of the data.
[0115] Furthermore, the mapping of the water and sewage data to the graph schema can be performed through data integration tools such as Apache NiFi, Apache Spark, etc. for automated data mapping, and the calculation of the data consistency of the attribute entity relationship diagram can be performed through tools such as Alation, Trifacta, etc., and data repair can be performed through Informatica, IBM DataStage, etc.
[0116] S3. Identify the water service characteristics of the water service sewage data, and establish a sewage data analysis model for the water service sewage data based on the water service characteristics.
[0117] It should be explained that the water service characteristics refer to the key features or attributes contained in the sewage data, including water quality characteristics, water quantity characteristics, facility characteristics, user characteristics, environmental characteristics, and economic characteristics.
[0118] Based on the water service characteristics, the present invention establishes a sewage data analysis model for the water service sewage data to perform detailed analysis on the sewage data. The sewage data analysis model refers to a model for performing water resource analysis on the water service sewage data.
[0119] In detail, the construction of the sewage data analysis model includes model architecture and algorithm selection. The model architecture should be able to effectively capture the relationships and dependencies between water service characteristics and be trained through a large amount of sewage data.
[0120] S4. Based on the water affairs sewage data, the sewage data analysis model is used to analyze the water pollution status of the drainage scenario to be enhanced, and based on the water affairs knowledge graph and the water pollution status, a water pollution balance model and a water pollution environmental impact model of the drainage scenario to be enhanced are constructed.
[0121] The present invention is based on the water service sewage data and uses the sewage data analysis model to analyze the water pollution state of the drainage scene to be enhanced to provide support for water resource management and optimization. The water pollution state refers to the evaluation and monitoring of the degree of water pollution and the types and concentrations of pollutants.
[0122] In detail, the analyzing the water pollution state of the drainage scene to be enhanced based on the water service sewage data and using the sewage data analysis model includes:
[0123] Serializing the water and sewage data to obtain serial sewage data;
[0124] Identifying dependencies between the water service characteristics corresponding to the sequence sewage data;
[0125] Based on the dependency, analyzing the sewage operation graph of the drainage scenario to be enhanced using the sewage data analysis model;
[0126] Based on the sewage operation map, the water pollution state of the drainage scene to be enhanced is determined.
[0127] Among them, the water service characteristics refer to various characteristics related to the water service system, including water quality, water temperature, water flow rate, dissolved oxygen content, pollutant concentration and other indicators. The dependency relationship refers to the relationship and influence between water service characteristics. For example, an increase in pollutant concentration may lead to a decrease in dissolved oxygen content, or an increase in water temperature may affect the biodegradation rate of certain pollutants. The sewage operation map refers to the one obtained by analyzing sewage data, which shows the change patterns and relationships of various water service characteristics in the sewage system over time or other variables. It can be used to describe the dynamic behavior and response characteristics of the sewage system.
[0128] Based on the water affairs knowledge graph and the water pollution status, the present invention constructs the water pollution balance model and water pollution environmental impact model of the drainage scene to be enhanced, which can provide a basis for later water pollution treatment. Among them, the water pollution balance model refers to a model for allocating water pollution to the water affairs scene, and the water pollution environmental impact model refers to a model that simulates the impact of different environments on the water pollution status of the water affairs scene.
[0129] In detail, the water pollution balance model and the water pollution environmental impact model of the drainage scenario to be enhanced are constructed based on the water affairs knowledge graph and the water pollution status, including:
[0130] Based on the water pollution state, analyzing the water pollution balance mechanism of the drainage scenario to be enhanced;
[0131] Constructing an optimization target for the water pollution balance mechanism;
[0132] Based on the optimization objective, determining an optimization function of the water pollution balance mechanism;
[0133] By means of the optimization function, a water pollution balance model of the drainage scenario to be enhanced is established;
[0134] Based on the water affairs knowledge graph, analyzing the water pollution environmental impact factors of the drainage scenario to be enhanced;
[0135] Collecting sequence factor data of the water pollution environmental impact factors;
[0136] Based on the sequence factor data, analyzing the influence relationship of the water pollution environment influencing factor on the water pollution state corresponding to the drainage scene to be enhanced;
[0137] Based on the impact relationship, a water pollution environment impact model of the drainage scenario to be enhanced is constructed.
[0138] Among them, the water pollution balance mechanism refers to the relationship between the interaction and mutual restriction between various factors in the water pollution system, and how these relationships lead to the balance or stability of the pollution state. It includes the source, migration path, transformation process and removal mechanism of pollutants, etc. The optimization target refers to the specific goal or standard that is hoped to be achieved in the process of improving the water pollution state. This may include goals such as reducing pollutant concentration, improving water quality, reducing environmental impact, and improving sewage treatment efficiency. The optimization function refers to a mathematical function used to describe how to achieve the optimization goal by adjusting and optimizing system parameters. In the sewage system, this may involve issues such as pollutant treatment efficiency, cost-benefit analysis, and resource allocation. The water pollution environmental influencing factors refer to various environmental factors that affect the water pollution state, such as rainfall, temperature, soil type, water flow rate, biodiversity and other factors. The sequence factor data refers to factor data that changes over time or other variables, such as daily rainfall, monthly water quality monitoring data and other data, and the impact relationship refers to the interaction relationship between water pollution environmental influencing factors and water pollution states.
[0139] Furthermore, based on the optimization target, the optimization function of the water pollution balance mechanism is determined by selecting a suitable nonlinear programming algorithm to construct it.
[0140] Furthermore, the analyzing, based on the sequence factor data, the influence relationship of the water pollution environment influencing factor on the water pollution state corresponding to the drainage scene to be enhanced includes:
[0141] Identify the data feature vector and water pollution status label of the sequence factor data;
[0142] Based on the data feature vector and the water pollution state label, the influence relationship function of the water pollution environment impact factor on the water pollution state corresponding to the drainage scene to be enhanced is constructed using the following formula;
[0143] ;
[0144] in, represents the predicted water pollution status value, The factor eigenvector representing the environmental impact factor of water pollution, The first data feature vector, represents the Lagrange multiplier, Represents the sequence factor data The water pollution status label corresponding to the data feature vector, represents the kernel function, represents the bias term, represents the number of data feature vectors;
[0145] Based on the influence relationship function, the influence relationship of the water pollution environment influence factor on the water pollution state corresponding to the drainage scene to be enhanced is analyzed.
[0146] It should be explained that the water pollution state value refers to the specific measurement or evaluation result of the water pollution state, which is usually a numerical value representing the degree or quality of water pollution. The factor feature vector refers to the vector describing the environmental impact factor of water pollution, which contains the size or attributes of multiple impact factors. The Lagrange multiplier is a multiplier used to solve the optimization problem. They are used to construct the Lagrange function in the Lagrange multiplier method. The water pollution state label refers to the classification or labeling of the water pollution state, which is usually a discrete numerical value or category label used to indicate different states or levels of water pollution. For example, the label can be "clean", "lightly polluted", "moderately polluted" or "severely polluted". The kernel function is used to calculate the similarity between feature vectors. It maps the feature vectors in the low-dimensional space to the high-dimensional space so that it is easier to find the optimal segmentation hyperplane. Commonly used kernel functions include linear kernels, polynomial kernels, radial basis function (RBF) kernels, etc. The bias term refers to a parameter in the regression model, which represents the offset of the decision function.
[0147] S5. Based on the water pollution balance model and the water pollution environmental impact model, analyze the water pollution solution of the drainage scenario to be enhanced, and perform water knowledge enhancement of the drainage scenario to be enhanced based on the water knowledge graph and the water pollution solution.
[0148] The present invention analyzes the water pollution solution of the drainage scene to be enhanced based on the water pollution balance model and the water pollution environmental impact model, which can improve the water quality of the water affairs scene, thereby improving the knowledge enhancement of the water affairs scene. The water pollution solution refers to a strategy for optimizing water pollution in the drainage scene to be enhanced.
[0149] In detail, the analyzing the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model includes:
[0150] Based on a preset state expectation value, analyzing the state loss value of the drainage scenario to be enhanced;
[0151] Identifying constraints of the drainage scenario to be enhanced;
[0152] Based on the state loss value, the constraint conditions and the water pollution environmental impact model, construct a water pollution integrated module for the drainage scenario to be enhanced;
[0153] Calculating water resource configuration parameters of the water pollution integrated module using the optimization function corresponding to the water pollution balance model;
[0154] Based on the water resource configuration parameters, a water pollution solution for the drainage scenario to be enhanced is constructed.
[0155] Among them, the state loss value refers to the difference between the actual water pollution state and the preset state expectation value, the constraint condition refers to the restrictions or rules that must be followed in water pollution control and management, such as laws and regulations, environmental protection standards, water resource utilization upper limit and other conditions, and the water pollution integrated module refers to a module that comprehensively considers multiple factors such as water pollution environmental impact model, state loss analysis, and constraint conditions. This module is used to build a comprehensive solution to achieve effective control and management of water pollution, and the water resource configuration parameters refer to the specific parameters of water resource configuration calculated by the optimization function in the water pollution integrated module, such as pollutant treatment efficiency, water resource allocation ratio, optimal sewage discharge, etc.
[0156] Furthermore, the construction of the water pollution integrated module for the drainage scenario to be enhanced can be achieved through tools such as WaterGEMS and MIKE; the calculation of the water resource configuration parameters of the water pollution integrated module using the corresponding optimization function of the water pollution balance model can be achieved through optimization algorithms such as genetic algorithms and particle swarm optimization.
[0157] Finally, the present invention performs water knowledge enhancement of the drainage scenario to be enhanced based on the water knowledge graph and the water pollution solution, which can fully understand the effects of the water knowledge graph and the water pollution solution in the drainage scenario to be enhanced, and provide a basis for continuous improvement and optimization.
[0158] The present invention obtains water sewage data by isomorphizing the sewage data, so that the data has a unified data format, structure, unit and scope, and provides support for subsequent water management and decision-making; the present invention can determine an accurate and comprehensive graph schema by determining the graph schema of the water sewage data, which is used to construct a water knowledge graph; the present invention constructs a water knowledge graph of the water sewage data based on the graph schema to support the decision-making process of water management and provide deeper insights and prediction capabilities; further, based on the water characteristics, the present invention establishes a sewage data analysis model for the water sewage data to perform a detailed analysis of the sewage data; further, based on the water sewage data, the present invention uses the sewage data analysis model to analyze the water pollution status of the drainage scene to be enhanced, which can provide support for water resource management and optimization; finally, based on the water pollution balance model and the water pollution environmental impact model, the present invention analyzes the water pollution solution of the drainage scene to be enhanced, which can improve the resource utilization efficiency of the water scene, thereby improving the knowledge enhancement of the water scene. Therefore, the method of enhancing water affairs knowledge using a large model proposed in the present invention can enhance the model's understanding in the field of water conservancy and improve the effect of enhancing water affairs knowledge in water affairs scenarios.
[0159] like Figure 2 , which is a functional module diagram of a device for enhancing water affairs knowledge using a large model provided by an embodiment of the present invention.
[0160] The device 200 for enhancing water affairs knowledge using a large model of the present invention can be installed in an electronic device. According to the functions implemented, the device 200 for enhancing water affairs knowledge using a large model can include a sewage data processing module 201, a knowledge graph construction module 202, an analysis model construction module 203, a supply and demand status analysis module 204 and a water affairs knowledge enhancement module 205. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0161] In this embodiment, the functions of each module / unit are as follows:
[0162] The sewage data processing module 201 is used to obtain the water affairs enhancement demand of the drainage scene to be enhanced, collect the sewage data of the drainage scene to be enhanced based on the water affairs enhancement demand, and perform isomorphism processing on the sewage data to obtain water affairs sewage data;
[0163] The knowledge graph construction module 202 is used to determine the graph schema of the water and sewage data, and to construct a water knowledge graph of the water and sewage data based on the graph schema;
[0164] The analysis model building module 203 is used to identify the water service characteristics of the water service and sewage data, and to establish a sewage data analysis model for the water service and sewage data based on the water service characteristics;
[0165] The supply and demand status analysis module 204 is used to analyze the water pollution status of the drainage scenario to be enhanced based on the water service sewage data and the sewage data analysis model, and to construct a water pollution balance model and a water pollution environmental impact model of the drainage scenario to be enhanced based on the water service knowledge graph and the water pollution status;
[0166] The water affairs knowledge enhancement module 205 is used to analyze the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model, and perform water affairs knowledge enhancement of the drainage scenario to be enhanced based on the water affairs knowledge graph and the water pollution solution.
[0167] In detail, each module described in the device 200 for enhancing water affairs knowledge using a large model in the embodiment of the present invention adopts the same technical means as the method for enhancing water affairs knowledge using a large model described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.
[0168] An embodiment of the present invention provides an electronic device for implementing a method for enhancing water affairs knowledge by using a large model.
[0169] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a method program for enhancing water affairs knowledge using a large model.
[0170] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory (for example, executing programs for enhancing water affairs knowledge using large models, etc.), and calling data stored in the memory.
[0171] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code of a program based on the use of a large model to enhance water affairs knowledge, but also to temporarily store data that has been output or is to be output.
[0172] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.
[0173] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.
[0174] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
[0175] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0176] The program for enhancing water affairs knowledge by using a large model stored in the memory of the electronic device is a combination of multiple instructions, and when executed in the processor, the following can be achieved:
[0177] Acquire water conservancy enhancement requirements for the drainage scene to be enhanced, collect sewage data of the drainage scene to be enhanced based on the water conservancy enhancement requirements, perform isomorphism processing on the sewage data, and obtain water conservancy sewage data;
[0178] Determine a graph schema of the water and sewage data, and construct a water knowledge graph of the water and sewage data based on the graph schema;
[0179] Identifying water service characteristics of the water service and sewage data, and establishing a sewage data analysis model for the water service and sewage data based on the water service characteristics;
[0180] Based on the water affairs sewage data, the water pollution state of the drainage scene to be enhanced is analyzed using the sewage data analysis model, and based on the water affairs knowledge graph and the water pollution state, a water pollution balance model and a water pollution environmental impact model of the drainage scene to be enhanced are constructed;
[0181] Based on the water pollution balance model and the water pollution environmental impact model, the water pollution solution of the drainage scenario to be enhanced is analyzed, and the water affairs knowledge enhancement of the drainage scenario to be enhanced is performed based on the water affairs knowledge graph and the water pollution solution.
[0182] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.
[0183] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0184] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:
[0185] Acquire water conservancy enhancement requirements for the drainage scene to be enhanced, collect sewage data of the drainage scene to be enhanced based on the water conservancy enhancement requirements, perform isomorphism processing on the sewage data, and obtain water conservancy sewage data;
[0186] Determine a graph schema of the water and sewage data, and construct a water knowledge graph of the water and sewage data based on the graph schema;
[0187] Identifying water service characteristics of the water service and sewage data, and establishing a sewage data analysis model for the water service and sewage data based on the water service characteristics;
[0188] Based on the water affairs sewage data, the water pollution state of the drainage scene to be enhanced is analyzed using the sewage data analysis model, and based on the water affairs knowledge graph and the water pollution state, a water pollution balance model and a water pollution environmental impact model of the drainage scene to be enhanced are constructed;
[0189] Based on the water pollution balance model and the water pollution environmental impact model, the water pollution solution of the drainage scenario to be enhanced is analyzed, and the water affairs knowledge enhancement of the drainage scenario to be enhanced is performed based on the water affairs knowledge graph and the water pollution solution.
[0190] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0191] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0192] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0193] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0194] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0195] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0196] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.
[0197] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for enhancing water affairs knowledge using a large model, characterized in that: The method comprises: Acquire water affairs enhancement requirements of a drainage scene to be enhanced, wherein the drainage scene to be enhanced is a sewage purification plant, and the water affairs enhancement requirements refer to specific requirements that must be met in order to improve the performance of the drainage system and meet water management challenges. Based on the water affairs enhancement requirements, collect sewage data of the drainage scene to be enhanced, perform isomorphism processing on the sewage data, and obtain water affairs sewage data; Determine a graph schema of the water and sewage data, and construct a water knowledge graph of the water and sewage data based on the graph schema; Identifying water service characteristics of the water service and sewage data, and establishing a sewage data analysis model for the water service and sewage data based on the water service characteristics; Based on the water affairs sewage data, the water pollution state of the drainage scene to be enhanced is analyzed using the sewage data analysis model; based on the water pollution state, the water pollution balance mechanism of the drainage scene to be enhanced is analyzed, and an optimization target of the water pollution balance mechanism is constructed; based on the optimization target, an optimization function of the water pollution balance mechanism is determined; through the optimization function, a water pollution balance model of the drainage scene to be enhanced is established; based on the water affairs knowledge graph, the water pollution environmental influencing factors of the drainage scene to be enhanced are analyzed; the sequence factor data of the water pollution environmental influencing factors are collected; the data feature vectors and water pollution state labels of the sequence factor data are identified; based on the data feature vectors and the water pollution state labels, the following formula is used to construct an influence relationship function of the water pollution environmental influencing factors on the water pollution state corresponding to the drainage scene to be enhanced; ; in, represents the predicted water pollution status value, The factor eigenvector representing the environmental impact factor of water pollution, The first data feature vectors, represents the Lagrange multiplier, Represents the sequence factor data The water pollution status label corresponding to the data feature vector, represents the kernel function, represents the bias term, represents the number of data feature vectors, based on the influence relationship function, analyzes the influence relationship of the water pollution environmental impact factor on the water pollution state corresponding to the drainage scene to be enhanced, and based on the influence relationship, constructs the water pollution environmental impact model of the drainage scene to be enhanced, wherein the water pollution balance model refers to a model for water pollution distribution for water affairs scenes, the water pollution environmental impact model refers to a model for simulating the influence of different environments on the water pollution state of water affairs scenes, the water pollution balance mechanism refers to the relationship between the interaction and mutual restriction between various factors in the water pollution system, which includes the source, migration path, transformation process and removal mechanism of pollutants, the optimization target refers to the specific goal or standard that is expected to be achieved in the process of improving the water pollution state, which includes reducing the concentration of pollutants, improving water quality, reducing environmental impact, and improving sewage treatment efficiency, the optimization function refers to a mathematical function used to describe how to achieve the optimization target by adjusting and optimizing system parameters, in the sewage system, this involves pollutant treatment efficiency, cost-benefit analysis, and resource allocation issues, the water pollution environmental impact factor refers to various environmental factors that affect the water pollution state, including rainfall, temperature, soil type, water flow rate, and biodiversity; Based on the water pollution balance model and the water pollution environmental impact model, the water pollution solution of the drainage scenario to be enhanced is analyzed, and the water affairs knowledge enhancement of the drainage scenario to be enhanced is performed based on the water affairs knowledge graph and the water pollution solution.
2. The method for enhancing water affairs knowledge using a large model as claimed in claim 1, characterized in that: The collecting of sewage data of the drainage scene to be enhanced based on the water affairs enhancement demand includes: Analyze the demand characteristics of the water service enhancement demand; Based on the demand characteristics, determining the enhanced data source of the drainage scenario to be enhanced, wherein the enhanced data source refers to additional data used to collect and enhance sewage data, including historical data, real-time data, predicted data, and simulated data; Analyzing the acquisition method of the enhanced data source; configuring data acquisition components of the acquisition method and determining optimal arrangement points of the data acquisition components; Based on the optimal arrangement point, the data acquisition component is used to collect sewage data of the drainage scene to be enhanced.
3. The method for enhancing water affairs knowledge using a large model as claimed in claim 2, characterized in that: The step of determining the schema of the water and sewage data includes: Identify the data entity of the water and sewage data; defining an entity tag of the data entity; Based on the entity labels, relationship modeling is performed on the data entities to obtain entity relationships; Based on the entity relationship, define the graph node type and graph edge type of the water and sewage data; Based on the graph node type and the graph edge type, a graph schema of the water and sewage data is constructed.
4. The method for enhancing water affairs knowledge using a large model as claimed in claim 3, characterized in that: The performing relationship modeling on the data entities to obtain entity relationships includes: Constructing a relational CRF model of the data entity; Calculating the model parameters of the relational CRF model using a preset likelihood function; Among them, the likelihood function is: ; in, Represents model parameters The likelihood function of Represents a data entity, Relationship labels representing data entities, represents the model parameters of the CRF model, Represents the data entity in a given data entity and model parameters The probability of getting the relationship label under Based on the model parameters, the entity relations of the data entities are extracted using the relational CRF model.
5. The method for enhancing water affairs knowledge using a large model as claimed in claim 4, characterized in that: The step of constructing a water affairs knowledge graph of the water affairs and sewage data based on the graph schema includes: Mapping the water and sewage data into the graph schema to obtain a mapping result; Based on the mapping result, construct an entity relationship diagram of the water and sewage data; Integrate the entity attribute information of the data entity corresponding to the water and sewage data into the entity relationship diagram to obtain an attribute entity relationship diagram; Calculating data consistency of the attribute entity relationship diagram; The attribute entity relationship diagram is optimized through the data consistency to obtain a water affairs knowledge graph.
6. The method for enhancing water affairs knowledge using a large model as claimed in claim 5, characterized in that: The analyzing the water pollution state of the drainage scene to be enhanced based on the water service sewage data and using the sewage data analysis model includes: Serializing the water and sewage data to obtain serial sewage data; Identify the dependency relationship between the water service characteristics corresponding to the serial sewage data, wherein the water service characteristics refer to various characteristics related to the water service system, including water quality, water temperature, water flow rate, dissolved oxygen content, and pollutant concentration, and the dependency relationship refers to the mutual relationship and influence between the water service characteristics; Based on the dependency, the sewage data analysis model is used to analyze the sewage operation map of the drainage scenario to be enhanced, wherein the sewage operation map is obtained by analyzing the sewage data, and shows the change rules and relationships of various water service characteristics in the sewage system over time or other variables; Based on the sewage operation map, the water pollution state of the drainage scene to be enhanced is determined.
7. The method for enhancing water affairs knowledge using a large model as claimed in claim 6, characterized in that: The analyzing the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model includes: Based on a preset state expectation value, analyzing the state loss value of the drainage scenario to be enhanced; Identifying constraints of the drainage scenario to be enhanced; Based on the state loss value, the constraint condition and the water pollution environmental impact model, construct a water pollution integrated module for the drainage scenario to be enhanced, wherein the water pollution integrated module refers to a module that comprehensively considers multiple factors such as the water pollution environmental impact model, the state loss analysis and the constraint condition; Calculating water resource configuration parameters of the water pollution integrated module using the optimization function corresponding to the water pollution balance model; Based on the water resource configuration parameters, a water pollution solution for the drainage scenario to be enhanced is constructed.
8. A device for enhancing water affairs knowledge using a large model, characterized in that: The device is used to execute the method for enhancing water affairs knowledge by using a large model as claimed in any one of claims 1 to 7, comprising: A sewage data processing module is used to obtain water affairs enhancement requirements of the drainage scene to be enhanced, wherein the drainage scene to be enhanced is a sewage purification plant, and the water affairs enhancement requirements refer to specific requirements that must be met in order to improve the performance of the drainage system and meet water management challenges. Based on the water affairs enhancement requirements, sewage data of the drainage scene to be enhanced is collected, and the sewage data is homogeneously processed to obtain water affairs sewage data; A knowledge graph construction module, used to determine the graph schema of the water and sewage data, and to construct a water knowledge graph of the water and sewage data based on the graph schema; An analysis model building module, used to identify the water service characteristics of the water service and sewage data, and to establish a sewage data analysis model for the water service and sewage data based on the water service characteristics; A supply and demand status analysis module is used to analyze the water pollution status of the drainage scene to be enhanced based on the water affairs sewage data and the sewage data analysis model, analyze the water pollution balance mechanism of the drainage scene to be enhanced based on the water pollution status, construct an optimization target of the water pollution balance mechanism, determine the optimization function of the water pollution balance mechanism based on the optimization target, establish a water pollution balance model for the drainage scene to be enhanced through the optimization function, analyze the water pollution environmental influencing factors of the drainage scene to be enhanced based on the water affairs knowledge graph, collect the sequence factor data of the water pollution environmental influencing factors, identify the data feature vector and the water pollution status label of the sequence factor data, and construct the influence relationship function of the water pollution environmental influencing factors on the water pollution status corresponding to the drainage scene to be enhanced based on the data feature vector and the water pollution status label using the following formula; ; in, represents the predicted water pollution status value, The factor eigenvector representing the environmental impact factor of water pollution, The first data feature vectors, represents the Lagrange multiplier, Represents the sequence factor data The water pollution status label corresponding to the data feature vector, represents the kernel function, represents the bias term, represents the number of data feature vectors, based on the influence relationship function, analyzes the influence relationship of the water pollution environmental impact factor on the water pollution state corresponding to the drainage scene to be enhanced, and based on the influence relationship, constructs the water pollution environmental impact model of the drainage scene to be enhanced, wherein the water pollution balance model refers to a model for water pollution distribution for water affairs scenes, the water pollution environmental impact model refers to a model for simulating the influence of different environments on the water pollution state of water affairs scenes, the water pollution balance mechanism refers to the relationship between the interaction and mutual restriction between various factors in the water pollution system, which includes the source, migration path, transformation process and removal mechanism of pollutants, the optimization target refers to the specific goal or standard that is expected to be achieved in the process of improving the water pollution state, which includes reducing the concentration of pollutants, improving water quality, reducing environmental impact, and improving sewage treatment efficiency, the optimization function refers to a mathematical function used to describe how to achieve the optimization target by adjusting and optimizing system parameters, in the sewage system, this involves pollutant treatment efficiency, cost-benefit analysis, and resource allocation issues, the water pollution environmental impact factor refers to various environmental factors that affect the water pollution state, including rainfall, temperature, soil type, water flow rate, and biodiversity; A water affairs knowledge enhancement module is used to analyze the water pollution solution of the drainage scenario to be enhanced based on the water pollution balance model and the water pollution environmental impact model, and to perform water affairs knowledge enhancement of the drainage scenario to be enhanced based on the water affairs knowledge graph and the water pollution solution.
Citation Information
Patent Citations
Miner illegal behavior knowledge extraction method based on entity and relation joint learning
CN114239574A
Knowledge graph method for identifying water environment pollution
CN114547322A
Entity relation joint extraction method based on entity-to-attention mechanism
CN115062109A
Management and control method and system based on intelligent sewage treatment cloud platform
CN118429139A
Dynamic multi-objective particle swarm optimization-based optimal control method for wastewater treatment process
US20200385286A1
