Sewage plant multivariate heterogeneous data warehouse construction method and system

Abstract

The invention discloses a sewage plant multivariate heterogeneous data warehouse construction method and system, and relates to the technical field of sewage plant monitoring, and the method comprises the steps: analyzing the field arrangement of a sewage plant, constructing a structure expression model comprising process blocks and equipment nodes, and mapping the actual layout; constructing a sewage plant knowledge graph, and marking process blocks and equipment nodes in the structural representation model based on knowledge interpretation content to form a first model mapping structure; performing content analysis on the heterogeneous data, extracting key factors and mapping the key factors to a structure expression model to form a second model mapping structure; and based on the second model mapping structure, adapting to the first model mapping structure, determining the information mapping logic of the heterogeneous data, and performing classified storage according to the knowledge graph logic. According to the method, integration and accurate mapping of heterogeneous data are realized through the structure model and the knowledge graph, the problems of data islands and insufficient relevance are solved, the data management and operation efficiency of a sewage treatment plant is improved, and the method is suitable for an intelligent sewage treatment scene.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment plant monitoring, and in particular to a method and system for constructing a multi-source heterogeneous data warehouse for a sewage treatment plant. Background Art

[0002] With the rapid development of the sewage treatment industry and the continuous improvement of environmental protection requirements, the operation and management of sewage treatment plants are moving towards the direction of intelligence and refinement. Sewage treatment plants involve multiple data sources, including equipment operation status, process parameters, maintenance records, material consumption, personnel management, standards and specifications, video monitoring data, and patrol record data, etc. These data have significant multi-source heterogeneous characteristics, manifested as inconsistent data formats (such as structured data, semi-structured data, video streams, etc.), scattered sources (such as sensors, monitoring devices, manual records, etc.), and complex storage structures. This heterogeneity makes it difficult to effectively integrate data, resulting in the phenomenon of data islands, which seriously restricts the improvement of the operation efficiency of sewage treatment plants and the accuracy of decision-making support.

[0003] Traditional data management methods, such as relational databases or simple file storage systems, are difficult to meet the integration and analysis requirements of multi-source heterogeneous data in sewage treatment plants. First, the physical layout and process flow of sewage treatment plants have a high degree of spatial and logical relevance, and data analysis needs to correspond to the actual scenarios of process blocks, equipment nodes, video monitoring, and patrol records. For example, video monitoring data needs to be associated with specific equipment or process areas, and patrol record data needs to be matched with equipment operation status and time series, while traditional methods lack an effective mapping mechanism. Second, a large amount of redundant information is contained in the massive heterogeneous data. How to accurately extract key factors (such as abnormal operation status, abnormal patrol points, etc.) from it and associate them with the operation scenarios of sewage treatment plants is the key challenge for realizing data-driven optimization. In addition, the operation environment of sewage treatment plants is highly dynamic (such as equipment updates, process adjustments, changes in monitoring points, etc.), and traditional data warehouses lack sufficient adaptability and intelligent analysis capabilities, making it difficult to meet the real-time and dynamic management requirements. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for constructing a data warehouse for intelligent planning of multi-source heterogeneous data in a sewage treatment plant.

[0005] The present invention discloses a method for constructing a multi-source heterogeneous data warehouse for a sewage treatment plant, including: Step S100, analyzing the on-site layout of the sewage treatment plant to construct a sewage treatment plant structure representation model, where the sewage treatment plant structure representation model includes several process blocks, each process block includes several equipment nodes, and the relative positions between process blocks and the relative positions between equipment nodes are mapped to the on-site layout of the sewage treatment plant; Step S200, a knowledge graph is constructed for the sewage treatment plant. For each information mapping logic in the knowledge graph, corresponding knowledge explanation content is set. Based on the knowledge explanation content, the process blocks and equipment nodes in the sewage treatment plant structure performance model are marked to form a first model mapping structure; Step S300, perform content analysis on the heterogeneous data to determine the key factors in each heterogeneous data, and analyze the key factors to determine the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model, forming a second model mapping structure; Step S400, based on the first model mapping structure adapted to the second model mapping structure of the heterogeneous data, determine the information mapping logic corresponding to the heterogeneous data, and classify and store the heterogeneous data according to the information mapping logic of the knowledge graph.

[0006] In some embodiments disclosed by the present invention, the method for constructing a knowledge graph for a sewage treatment plant includes: Step S201, determine the knowledge keywords of the sewage treatment plant, including process block keywords, equipment keywords, parameter keywords, time keywords, space keywords, operation and maintenance record keywords, material keywords, personnel keywords, and standard keywords; Step S202, construct the logical relationships between the knowledge keywords, and based on the logical relationships, sequentially connect the corresponding knowledge keywords to obtain the graph framework of the knowledge graph; Step S203, classify the preset knowledge explanation content based on the knowledge keywords and logical relationships mapped by the graph framework, and combine the knowledge explanation content and the graph framework.

[0007] In some embodiments disclosed by the present invention, the method for marking the process blocks and equipment nodes in the sewage treatment plant structure performance model to form a first model mapping structure includes: Step S204, perform keyword analysis on the knowledge explanation content, extract the process block keywords and equipment node keywords, and mark the process blocks and equipment nodes in the sewage treatment plant structure performance model based on the process block keywords and equipment node keywords; Step S205, perform event impact weight analysis on the process blocks or equipment nodes in the knowledge explanation content, sort the process block keywords and equipment node keywords based on the magnitude order of the event impact weights, and perform vector line connection on the marked process blocks and equipment nodes in the sewage structure performance model based on the sorting results to obtain a first model mapping structure.

[0008] In some embodiments disclosed by the present invention, the method for performing content analysis on heterogeneous data to determine the key factors in each heterogeneous data includes: In step S301, a factor extraction template is set for each type of heterogeneous data. A number of factor types are set on the factor extraction template, and a factor parameter section sequence is set for each factor type. In step S302, the key factors of the historical heterogeneous data are marked, and the factor parameters of each key factor are determined to obtain a number of historical key factor parameter groups. In step S303, based on the conformity of the key factor types as the classification condition, different historical key factor parameter groups are classified, and centralized feature analysis is performed on the historical key factor parameter groups in each category. Based on the analysis results, a number of factor parameter section array templates are constructed. The factor parameter section array template includes a number of content factor types, each content factor type corresponds to a number of factor parameter section sequences. The factor parameter section sequence includes a number of factor parameter sections connected in size order, and the factor parameter sections to be concerned are marked. In step S304, the content factors in the heterogeneous data are identified, and the content factors are compared with different factor parameter section array templates to determine the factor parameter section array template that is completely mapped and adapted, and it is recognized as the reference factor parameter section array template. In step S305, the factor types and the factor parameter sections to be concerned in the reference factor parameter section array template are recognized as the key factors of the heterogeneous data.

[0009] In some embodiments disclosed in the present invention, the method for performing centralized feature analysis on the historical key factor parameter groups in each category includes: In step S3031, the historical key factor parameters of the same category in the historical key factor parameter group are extracted, and the historical key factor parameters are sorted in order. The historical key factor parameter clusters aggregated in the sequence are respectively determined, and the average value in each historical key factor parameter cluster is calculated and recorded as the key factor parameter to be concerned. In step S3032, the number of factor parameters and the factor parameter span in the historical key factor parameter cluster are analyzed, the quantity density between the number of factor parameters and the factor parameter span is calculated, and based on the preset density interval to which the quantity density belongs, the extension section length of the factor parameter section corresponding to the historical key factor parameter cluster is determined. In step S3033, the factor parameter sections corresponding to different types of historical key factor parameter clusters are randomly combined to obtain a number of initial factor parameter section array templates. In step S3034, the historical key factor parameter group is mapped and compared with the initial factor parameter section array template to determine the mapping matching performance. Based on the mapping matching performance, the initial factor parameter section array template is sorted, and the first several initial factor parameter section array templates in the order are selected as the applied factor parameter section array template.

[0010] In some embodiments disclosed by the present invention, the method for determining the mapping coincidence performance by performing mapping comparison between the historical key factor parameter group and the initial factor parameter section array template includes: Step S30341: Determine the section center value of each type of factor parameter section in the initial factor parameter section array template, and calculate the factor parameter difference value between the corresponding historical key factor parameter in the historical key factor parameter group and the section center value; Step S30342: Determine the factor type matching ratio between the initial factor parameter section array template and the historical key factor parameter group, and combine the factor parameter difference values of each factor type to determine the mapping coincidence sub-parameters between the initial factor parameter section array template and a single historical key factor parameter group; Step S30343: Randomly select several mapping coincidence sub-parameters greater than or equal to a preset value, and calculate their average value to obtain the mapping coincidence degree.

[0011] In some embodiments disclosed by the present invention, the method for analyzing key factors and determining the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model includes: Step S306: Establish a key factor - block and equipment mapping table, which includes several key factor types. Each key factor type corresponds to a key factor parameter section. Each key factor type and key factor parameter section correspond to several process blocks and equipment nodes, and there is an order relationship between the process blocks and equipment nodes; Step S307: Substitute the determined key factors into the key factor - block and equipment mapping table to determine the process blocks and equipment nodes mapped in the sewage structure performance model. Based on the order relationship between the determined process blocks and equipment nodes, vector - line connect the process blocks and equipment nodes mapped in the sewage structure performance model.

[0012] In some embodiments disclosed by the present invention, the method for determining that the second model mapping structure is adapted to the first model mapping structure includes: Step S401: Respectively determine the envelope blocks of the first model mapping structure and the second model mapping structure on the sewage treatment plant structure performance model, denoted as the first envelope block and the second envelope block. Analyze the intersection volume between the first envelope block and the second envelope block, and determine the sum of the volumes of the first envelope block and the second envelope block, denoted as the total block volume. Calculate the volume ratio of the intersection volume to the total block volume; Step S402: Compare the line coincidence ratio of the vector lines that coincide in the first model mapping structure and the second model mapping structure, and combine the volume ratio to determine the adaptation degree of the first model mapping structure and the second model mapping structure.

[0013] In some embodiments disclosed by the present invention, a system for constructing a multi - heterogeneous data warehouse of a sewage treatment plant is also disclosed, which is characterized by including: A first module, configured to analyze the on - site layout of the sewage treatment plant and construct a structural performance model of the sewage treatment plant. The structural performance model of the sewage treatment plant includes several process blocks, each process block includes several equipment nodes, and the relative positions between the process blocks and the relative positions between the equipment nodes are mapped to the on - site layout of the sewage treatment plant; A second module, configured to construct a knowledge graph for the sewage treatment plant, and for each information mapping logic in the knowledge graph, knowledge explanation content is correspondingly set. Based on the knowledge explanation content, the process blocks and equipment nodes in the structural performance model of the sewage treatment plant are marked to form a first model mapping structure; A third module, configured to perform content analysis on heterogeneous data, determine the key factors in each heterogeneous data, and analyze the key factors to determine the process blocks and equipment nodes mapped in the structural performance model of the sewage treatment plant, forming a second model mapping structure; A fourth module, configured to determine the information mapping logic corresponding to the heterogeneous data based on the adaptation of the first model mapping structure to the second model mapping structure of the heterogeneous data, and classify and store the heterogeneous data according to the information mapping logic of the knowledge graph.

[0014] The present invention discloses a method and system for constructing a multi - heterogeneous data warehouse of a sewage treatment plant, relating to the technical field of sewage treatment plant monitoring. It includes analyzing the on - site layout of the sewage treatment plant, constructing a structural performance model including process blocks and equipment nodes, and mapping the actual layout; constructing a knowledge graph of the sewage treatment plant, marking the process blocks and equipment nodes in the structural performance model based on the knowledge explanation content to form a first model mapping structure; performing content analysis on heterogeneous data, extracting key factors and mapping them to the structural performance model to form a second model mapping structure; based on the adaptation of the second model mapping structure to the first model mapping structure, determining the information mapping logic of the heterogeneous data, and classifying and storing according to the knowledge graph logic. This method realizes the integration and accurate mapping of heterogeneous data through the structural model and the knowledge graph, solves the problems of data islands and insufficient relevance, improves the data management and operation efficiency of the sewage treatment plant, and is applicable to intelligent sewage treatment scenarios.

[0015] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments. Brief Description of the Drawings

[0016] Figure 1 It is a method step diagram of a method for constructing a multi - heterogeneous data warehouse of a sewage treatment plant disclosed in an embodiment of the present invention. Detailed Embodiments

[0017] The technical solutions of the present invention will be further described below with reference to the drawings and embodiments.

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings and specific embodiments. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and should not be construed as limiting the protection scope of the present invention. Those skilled in the art can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and defined, the technical terms used in the present invention should have the ordinary meaning understood by those skilled in the art of the present invention.

[0019] Embodiment:

[0020] The object of the present invention is to provide a method and system for constructing a data warehouse for intelligent planning of multi-source heterogeneous data in a sewage treatment plant.

[0021] The present invention discloses a method for constructing a multi-source heterogeneous data warehouse in a sewage treatment plant. Refer to Figure 1 , including: Step S100, analyze the on-site layout of the sewage treatment plant to construct a sewage treatment plant structure representation model. The sewage treatment plant structure representation model includes several process blocks, each process block includes several equipment nodes, and the relative positions between the process blocks and the relative positions between the equipment nodes are mapped to the on-site layout of the sewage treatment plant.

[0022] Step S100 constructs a structural representation model through in-depth analysis of the on-site layout of the sewage treatment plant, providing a spatial and structured foundation for the extraction of key factors and the mapping of heterogeneous data, and ensuring the accurate association of data with the actual physical layout and process flow. The operation and management of a sewage treatment plant highly depend on the characteristics of its physical layout and process flow, and key factors (such as abnormal equipment operation, process parameter deviation, abnormal events in video monitoring, and fault descriptions in patrol records) are often directly related to specific process blocks or equipment nodes. Therefore, this step first conducts a systematic investigation of the on-site layout of the sewage treatment plant, collecting the spatial distribution, functional division of each process block (such as pretreatment area, biochemical treatment area, advanced treatment area), and the specific positions and connection relationships of equipment nodes (such as pumps, valves, aerators) within each process block. This information is transformed into a structural representation model through digital modeling technology, in which the relative positions between process blocks and equipment nodes are mapped one-to-one with the actual on-site layout. For example, a biochemical treatment block may contain multiple equipment nodes (such as agitators and dissolved oxygen sensors), and their spatial relationships reflect the functional dependencies in the process flow, such as the pipeline connection between the agitator and the downstream filtration equipment. This mapping not only preserves the authenticity of the physical layout but also lays a foundation for the spatial association of key factors. For example, abnormal events in video monitoring (such as pipeline blockages) need to be located to specific process blocks or equipment nodes, and fault descriptions in patrol records may be related to the operating status of a certain equipment. By constructing a structural representation model, the system can associate key factors (such as equipment anomalies or process deviations) with physical locations, avoiding the analysis difficulties caused by the lack of spatial context in traditional data management. In addition, this model has dynamic scalability and can adapt to the actual changes in the sewage treatment plant (such as new equipment addition or process adjustment), ensuring the continuous effectiveness of key factor mapping. For example, when a new aeration device is added to the biochemical treatment block, the model can update its node positions and association relationships to support the subsequent analysis of key factors (such as abnormal equipment operation). This model-based method effectively solves the problem of the disconnection between key factors and the physical layout, providing a unified structural framework for the semantic tagging of the subsequent knowledge graph and the accurate mapping of heterogeneous data, thereby enhancing the data-driven management ability of the sewage treatment plant.

[0023] In step S200, a knowledge graph is constructed for the sewage treatment plant. For each information mapping logic in the knowledge graph, corresponding knowledge explanation content is set, and based on the knowledge explanation content, the process blocks and equipment nodes in the structural representation model of the sewage treatment plant are marked to form a first model mapping structure.

[0024] Step S200 builds a knowledge graph of the sewage treatment plant and semantically tags the structural performance model based on the knowledge interpretation content to form a first model mapping structure, providing a logical basis for the semantic association of key factors and the intelligent analysis of heterogeneous data. The operation of a sewage treatment plant involves complex process and equipment interactions, and key factors (such as abnormal equipment operation, process parameter deviation, abnormal events in video monitoring, and fault descriptions in patrol records) need to be accurately corresponded to the process flow and the functional semantics of the equipment. As a graph-structured knowledge representation method, a knowledge graph describes entities and their relationships through nodes and edges, and can effectively integrate the operation knowledge of the sewage treatment plant. First, the system determines the knowledge keywords related to the sewage treatment plant, including process blocks, equipment, parameters, time, space, operation and maintenance records, video monitoring events, patrol faults, etc., and constructs the logical relationships between these keywords. For example, a process block may have an "include" relationship with a specific piece of equipment, an equipment has a "monitor" relationship with operation parameters, and an abnormal event in video monitoring may have an "association" relationship with a fault description in patrol records. These logical relationships are structurally connected through the graph framework to form a knowledge graph, where each information mapping logic corresponds to specific knowledge interpretation content (such as the working parameter range of the equipment, the functional description of the process block, and the characteristics of abnormal events). Based on this, the system semantically tags the process block and equipment nodes in the structural performance model of step S100, mapping the semantic information of the knowledge graph onto the physical structure. For example, a biochemical treatment block may be tagged as "anaerobic treatment", and the equipment nodes it contains are tagged as "anaerobic reactors", and are associated with operation parameters (such as dissolved oxygen concentration) and key factors (such as equipment anomalies or fault images in video monitoring). This tagging process combines the physical structure with the semantic context to form a first model mapping structure, enabling key factors (such as process parameter deviation or patrol fault description) to be systematically analyzed based on the logical relationships of the knowledge graph. For example, the description of "insufficient aeration" in the patrol record can be associated through the knowledge graph with the operation parameters of the aeration equipment and the abnormal images in video monitoring, avoiding the problem of information isolation. In addition, the dynamic update ability of the knowledge graph enables it to adapt to the operation changes of the sewage treatment plant (such as adding monitoring points or process adjustments), ensuring the continuity and accuracy of key factor analysis. Through this step, the system lays a foundation for the semantic management of key factors and the integration of heterogeneous data, significantly improving the intelligent level of data analysis.

[0025] In step S300, content analysis is performed on the heterogeneous data to determine the key factors in each piece of heterogeneous data, and the key factors are analyzed to determine the process blocks and equipment nodes mapped in the structural performance model of the sewage treatment plant, forming a second model mapping structure.

[0026] Step S300 extracts key factors (such as abnormal equipment operation, process parameter deviation, abnormal events in video surveillance, and fault descriptions in patrol inspection records) through content analysis of heterogeneous data and maps them to the structural representation model to form the second model mapping structure, achieving an accurate association between key factors and physical layout and process flow. The sources of heterogeneous data in a sewage treatment plant are extensive, including equipment sensor data, video surveillance streams, patrol inspection records, process parameters, etc. These data are significantly different in format and content, and key factors are often hidden in a large amount of information. This step first uses a factor extraction template to perform structured analysis on heterogeneous data. The template defines the types of key factors (such as abnormal events, parameter deviations, fault descriptions) and their parameter section sequences (such as parameter ranges, event times). For example, for video surveillance data, the key factor may be an abnormal event (such as an equipment failure image or pipeline blockage); for patrol inspection records, the key factor may be a fault description (such as "motor overheating") or the patrol time. Subsequently, the system accurately extracts key factors through historical data analysis and the factor parameter section array template and determines their mapping positions in the structural representation model. For example, a "pipeline blockage" event in a video surveillance may be mapped to a specific pipeline equipment node in the pretreatment block, while a description of "insufficient aeration" in the patrol inspection record may be mapped to the aerator node in the biochemical treatment block. This mapping process forms the second model mapping structure through the association of key factors with process blocks and equipment nodes, not only retaining the original content of the data but also enhancing the spatial and process context of key factors. For example, the parameter data of abnormal equipment operation can be mapped and located to specific equipment for subsequent fault diagnosis; abnormal events in video surveillance can be cross-validated with the fault descriptions in patrol inspection records to improve the reliability of analysis. Compared with traditional data analysis methods, this step significantly improves the accuracy and efficiency of key factor extraction through templatization and historical data analysis, solving the problem of the association between heterogeneous data and process flow. In addition, this step supports dynamic updates. When new types of key factors (such as abnormalities captured by newly added monitoring equipment) appear, the system can adjust the template and mapping rules to ensure the adaptability of analysis. By forming the second model mapping structure, the system provides a reliable basis for the systematic management of key factors and subsequent data classification storage, laying a technical foundation for the intelligent operation optimization of the sewage treatment plant.

[0027] Step S400 determines the information mapping logic corresponding to the heterogeneous data based on the first model mapping structure adapted to the second model mapping structure of the heterogeneous data, and classifies and stores the heterogeneous data according to the information mapping logic of the knowledge graph.

[0028] Step S400 determines the information mapping logic of key factors (such as abnormal device operation, process parameter deviation, abnormal events in video monitoring, and fault descriptions in patrol inspection records) by adapting the second model mapping structure to the first model mapping structure, and classifies and stores heterogeneous data according to the logic of the knowledge graph to construct an efficient and semantic data warehouse. The heterogeneous data of the sewage treatment plant has been mapped to form the second model mapping structure through key factors in step S300, but these data still need to be integrated with the semantic logic of the knowledge graph to achieve systematic storage and intelligent analysis. This step first evaluates the adaptability of the second model mapping structure (based on heterogeneous data and key factors) to the first model mapping structure (based on knowledge graph tags), and calculates the adaptability by analyzing the cross-sectional volume of the envelope blocks and the coincidence ratio of the vector lines of the two. For example, an "equipment failure" event in video monitoring may be mapped and adapted to the "fault diagnosis" logic related to the equipment in the knowledge graph, while the description of "parameter exceeding the standard" in the patrol inspection record may be adapted to the "process anomaly" logic. Based on this adaptation, the system determines the information mapping logic corresponding to the key factors and classifies and stores the heterogeneous data according to the structure of the knowledge graph. For example, abnormal device operation data is stored in the "device status" category, abnormal events in video monitoring are stored in the "monitoring events" category, and fault descriptions in patrol inspection records are stored in the "operation and maintenance records" category. This classified storage not only improves the data retrieval efficiency but also realizes the systematic organization of key factors through the semantic relationships of the knowledge graph, enabling subsequent analysis to quickly locate relevant process blocks or device nodes. For example, when querying abnormal events in a certain process block, the system can simultaneously retrieve relevant video monitoring data and patrol inspection records, improving the comprehensiveness of the analysis. In addition, this step supports the scalability of the data warehouse through a dynamic adaptation mechanism. When new data types (such as data from newly added monitoring devices) or key factors (such as new fault modes) are introduced into the sewage treatment plant, the system can update the mapping logic and storage structure to ensure continuous applicability. Compared with traditional data warehouses, this step solves the complexity and lack of intelligence in the classified storage of heterogeneous data through the semantic integration of key factors and model adaptation, provides an efficient and unified data management platform for the operation optimization of sewage treatment plants, and significantly improves the decision-making support ability based on key factors.

[0029] In some embodiments disclosed in the present invention, the method for constructing a knowledge graph for a sewage treatment plant includes: Step S201, determining the knowledge keywords of the sewage treatment plant, including process block keywords, equipment keywords, parameter keywords, time keywords, space keywords, operation and maintenance record keywords, material keywords, personnel keywords, and standard keywords.

[0030] Step S202: Construct the logical relationships between the knowledge keywords, and based on the logical relationships, sequentially connect the corresponding knowledge keywords to obtain the graph framework of the knowledge graph.

[0031] Step S203: Classify the preset knowledge explanation content based on the knowledge keywords and logical relationships mapped by the graph framework, and combine the knowledge explanation content and the graph framework.

[0032] In some embodiments disclosed by the present invention, the method for marking process blocks and equipment nodes in the sewage treatment plant structure performance model to form the first model mapping structure includes: Step S204: Analyze the keywords in the knowledge explanation content, extract the process block keywords and equipment node keywords, and based on the process block keywords and equipment node keywords, mark the process blocks and equipment nodes in the sewage treatment plant structure performance model; Step S205: Analyze the event impact weights of the process blocks or equipment nodes in the knowledge explanation content, sort the process block keywords and equipment node keywords based on the magnitude order of the event impact weights, and based on the sorting results, perform vector line connection on the marked process blocks and equipment nodes in the sewage structure performance model to obtain the first model mapping structure.

[0033] Step S205 analyzes the event impact weights of process blocks or equipment nodes in the knowledge explanation content, adjusts the priorities of keywords based on the weight ranking, and forms the first model mapping structure by connecting the marked process blocks and equipment nodes with vector lines, providing dynamic and structured support for the systematic association of key factors (such as abnormal equipment operation, process parameter deviation, abnormal events in video monitoring, and fault descriptions in patrol inspection records) and the intelligent integration of heterogeneous data. In the operation of a sewage treatment plant, different process blocks and equipment nodes have different degrees of influence on key factors. For example, the "aerator" equipment may have a much greater impact on the "dissolved oxygen concentration deviation" than other equipment, while the "pretreatment" block has a more significant impact on the "pipe blockage" event. This step first conducts a quantitative analysis of the event impacts in the knowledge explanation content, evaluating the association strength between each process block and equipment node and the events related to key factors. For example, by analyzing historical data and the knowledge explanation content, the system may determine that the weight of the "aerator" associated with the "dissolved oxygen abnormality" event is higher than that of the "pump" because the former directly affects the biochemical treatment effect. Similarly, the "pipe blockage event in video monitoring" may have a higher weight for the "pretreatment" block, and the "motor overheating fault in patrol inspection records" may be related to the weight of a specific equipment node (such as the "motor"). Based on these weights, the system sorts the keywords of process blocks and equipment nodes, and the keywords with higher priorities (such as the "aerator" or "pretreatment" closely related to key factors) are placed at the front. Subsequently, according to the sorting results, the system connects the marked process blocks and equipment nodes with vector lines in the structure performance model to generate the first model mapping structure. These vector lines not only represent physical or process connections (such as pipe connections) but also reflect the priorities and logical relationships of event impacts. For example, a "biochemical treatment" block may be connected to the "aerator" through a high-weight vector line and further connected to the "dissolved oxygen concentration" parameter node, forming a mapping path reflecting the key factor of "dissolved oxygen concentration deviation". This structured mapping enables key factors to be systematically represented and analyzed in the model. For example, when analyzing "pipe blockage", the system can quickly locate the "pretreatment" block and its associated video monitoring and patrol inspection data through vector lines. Compared with traditional data association methods, this step solves the problem of difficult quantification and association of the influence degrees of key factors through weight analysis and vector line connection. In addition, this step supports dynamic adjustment. When the operation scenario of the sewage treatment plant changes (such as new equipment addition or fault modes), the system can re-analyze the event impact weights and update the mapping structure to ensure the accuracy and adaptability of key factor analysis. The formation of the first model mapping structure not only provides a semantic and priority basis for the subsequent adaptation and classified storage of heterogeneous data but also significantly improves the intelligent level of the data warehouse in the sewage treatment plant, providing strong technical support for operation optimization and decision-making support.

[0034] In some embodiments disclosed by the present invention, the method for performing content analysis on heterogeneous data to determine key factors in each piece of heterogeneous data includes: Step S301: For each type of heterogeneous data, a factor extraction template is set. A number of factor types are set on the factor extraction template, and a factor parameter section sequence is set for each factor type.

[0035] By setting a factor extraction template for each type of heterogeneous data in Step S301, the factor types and their parameter section sequences are defined, providing a structured framework for the accurate extraction of key factors (such as equipment operation anomalies, process parameter deviations, abnormal events in video surveillance, and fault descriptions in patrol records), ensuring that heterogeneous data can be systematically analyzed and associated with the operation scenarios of the sewage treatment plant. The sources of heterogeneous data in the sewage treatment plant are diverse, including equipment sensor data, video surveillance streams, patrol records, process parameters, etc. The formats and contents of these data vary significantly, and key factors are often hidden in complex information. To effectively extract these key factors, this step first designs a dedicated factor extraction template according to the type of heterogeneous data (such as structured sensor data, semi-structured patrol records, and unstructured video surveillance data). Each template contains a number of factor types, such as "equipment status" (corresponding to equipment operation anomalies), "process parameters" (corresponding to parameter deviations), "abnormal events" (corresponding to anomalies in video surveillance), and "fault descriptions" (corresponding to patrol records). Each factor type further defines a factor parameter section sequence, that is, the quantization range or feature description of the key factor. For example, for the "process parameter" type, the parameter section sequence may include the normal range of dissolved oxygen concentration (such as 2 - 4 mg / L) and the abnormal range (such as < 1 mg / L); for the "abnormal event" type, the parameter section may include the features of abnormal images in video surveillance (such as "pipe blockage" or "equipment jitter"). The design of these templates is based on the operation characteristics of the sewage treatment plant, historical data analysis, and industry standards to ensure that the diversity of key factors can be covered. For example, the "motor overheating" fault description in the patrol record may be defined as a specific parameter section of the "fault description" factor type, which is directly related to equipment operation anomalies. By setting the factor extraction template, the system provides a standardized reference framework for the extraction of key factors, avoiding the extraction difficulties caused by data heterogeneity in traditional data analysis. In addition, the template is scalable and can be updated according to new data types (such as data from newly added monitoring equipment) or key factors (such as new fault modes) in the sewage treatment plant. This structured templating method not only improves the efficiency and accuracy of key factor extraction but also lays a foundation for subsequent historical data analysis and factor classification, ensuring that key factors can be accurately associated with the process flow and equipment nodes, providing key support for the intelligent construction of the sewage treatment plant data warehouse.

[0036] Step S302: Mark the key factors of the heterogeneous data in the historical records, and determine the factor parameters of each key factor to obtain a number of historical key factor parameter groups.

[0037] Step S303: Using the conformity of the key factor types as the classification condition, classify the different historical key factor parameter groups, conduct a centralized feature analysis on the historical key factor parameter groups in each category, and based on the analysis results, construct a number of factor parameter section array templates. The factor parameter section array template includes a number of content factor types, each content factor type corresponds to a number of factor parameter section sequences, the factor parameter section sequence includes a number of factor parameter sections connected in size order, and mark the factor parameter sections that need to be concerned.

[0038] Step S303 classifies the historical key factor parameter groups based on the conformity of the key factor types, conducts centralized feature analysis on each category, constructs a factor parameter section array template, and provides a dynamic and standardized reference framework for the accurate identification of key factors (such as equipment operation anomalies, process parameter deviations, abnormal events in video surveillance, and fault descriptions in patrol records) and the systematic mapping of heterogeneous data. The operation data of the sewage treatment plant is complex and variable, and the characteristics of key factors may vary in different scenarios. For example, the thresholds of "process parameter deviations" are different in different process blocks, and the characteristics of "abnormal events in video surveillance" vary depending on the equipment type. This step first classifies the historical key factor parameter groups generated in step S302 using the key factor types (such as "equipment status", "abnormal events", "fault descriptions") as the classification conditions. For example, the "dissolved oxygen concentration deviation" parameter group is classified into the "process parameter" category, the "pipe blockage image" parameter group is classified into the "abnormal event" category, and the "motor overheating" parameter group is classified into the "fault description" category. Subsequently, the system conducts centralized feature analysis on the parameter groups in each category, extracts the statistical characteristics and distribution laws of the key factors. For example, by analyzing the parameter groups in the "process parameter" category, the system may determine the common abnormal sections of the dissolved oxygen concentration (such as <1mg / L or >6mg / L); by analyzing the parameter groups in the "abnormal event" category, the system may identify the typical characteristics of pipe blockage images (such as image gray-scale changes). Based on these analysis results, the system constructs a factor parameter section array template. Each template contains several content factor types, and each type corresponds to a group of factor parameter section sequences (such as numerically consecutive value ranges or feature descriptions in ascending order), and marks the sections that need attention. For example, a "process parameter" template may contain a section sequence of the "dissolved oxygen concentration" type (0-1mg / L, 1-4mg / L, 4-6mg / L), where 0-1mg / L is marked as the section that needs attention, indicating a high-risk deviation; an "abnormal event" template may contain an image feature sequence of the "pipe blockage" type, where a specific gray-scale range is marked as the section that needs attention. These templates not only summarize the characteristic laws of key factors but also provide a standardized comparison basis for factor extraction from new data. Compared with traditional data analysis methods, this step solves the problems of scattered key factor characteristics and difficulty in standardization through classification and feature analysis. In addition, the template supports dynamic optimization. When the operation environment of the sewage treatment plant changes (such as new equipment addition or fault modes), the system can update the template based on new historical data to ensure the accuracy of key factor identification. These factor parameter section array templates provide core support for subsequent factor comparison and key factor determination, promoting the intelligent construction of the data warehouse and data-driven decision-making for the operation optimization of the sewage treatment plant.

[0039] Step S304: Identify the content factors in the heterogeneous data, compare the content factors with different factor parameter section array templates, determine the factor parameter section array templates that are completely mapped and adapted, and identify them as the reference factor parameter section array templates.

[0040] Step S305: Identify the factor types in the reference factor parameter section array template and the factor parameter sections to be concerned about as the key factors of the heterogeneous data.

[0041] In some embodiments disclosed by the present invention, the method for performing centralized feature analysis on the historical key factor parameter groups in each category includes: Step S3031: Extract the historical key factor parameters of the same category in the historical key factor parameter group, sort the historical key factor parameters in order, determine the clusters of historical key factor parameters aggregated in the sequence respectively, and calculate the average value in each cluster of historical key factor parameters, which is denoted as the key factor parameter to be concerned about.

[0042] Step S3032: Analyze the number of factor parameters and the factor parameter span in the historical key factor parameter cluster, calculate the quantity density between the number of factor parameters and the factor parameter span, and determine the extension section length of the factor parameter section corresponding to the historical key factor parameter cluster based on the preset density interval to which the quantity density belongs.

[0043] Step S3033: Randomly combine the factor parameter sections corresponding to different types of historical key factor parameter clusters to obtain several initial factor parameter section array templates.

[0044] Step S3034: Perform a mapping comparison between the historical key factor parameter group and the initial factor parameter section array templates, determine the mapping matching performance, and based on the mapping matching performance, sort the initial factor parameter section array templates and select the first several initial factor parameter section array templates as the applied factor parameter section array templates.

[0045] In some embodiments disclosed by the present invention, the method for performing a mapping comparison between the historical key factor parameter group and the initial factor parameter section array templates to determine the mapping matching performance includes: Step S30341: Determine the section center value of each type of factor parameter section in the initial factor parameter section array template, and calculate the factor parameter difference value between the corresponding historical key factor parameter in the historical key factor parameter group and the section center value.

[0046] Step S30342: Determine the matching ratio of the initial factor parameter section array template to the factor types of the historical key factor parameter groups, and in combination with the factor parameter difference values of each factor type, determine the mapping matching sub-parameters between the initial factor parameter section array template and a single historical key factor parameter group.

[0047] Step S30343: Randomly select several mapping matching sub-parameters greater than or equal to the preset value, and calculate their average value to obtain the mapping matching degree.

[0048] 。

[0049] Among them, W is the mapping occurrence degree, is the preset maximum factor parameter difference value, is the i-th factor parameter difference value between the initial factor parameter section array template and the historical key factor parameter group, is the effective judgment function of the factor parameter difference value. If the i-th factor parameter difference value is less than or equal to the of the corresponding factor parameter section, then output 1, otherwise output 0. is the number of factor types that match between the initial factor parameter section array template and the historical key factor parameter group, is the number of factor types in the initial factor parameter section array template, is the number of factor types in the historical key factor parameter group. L is the adjustment coefficient of the factor type matching ratio, and b is the adjustment constant of the factor type matching ratio.

[0050] In some embodiments disclosed in the present invention, the method for analyzing key factors and determining the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model includes: Step S306: Establish a key factor - block and equipment mapping table. The key factor - block and equipment mapping table includes several key factor types, and each key factor type corresponds to a key factor parameter section. Each key factor type and key factor parameter section correspond to several process blocks and equipment nodes, and there is an order relationship between the process blocks and equipment nodes.

[0051] Step S307: Substitute the determined key factors into the key factor - block and equipment mapping table to determine the process blocks and equipment nodes mapped in the sewage structure performance model, and based on the order relationship between the determined process blocks and equipment nodes, perform vector line connection on the process blocks and equipment nodes mapped in the sewage structure performance model.

[0052] In some embodiments disclosed in the present invention, the method for determining that the second model mapping structure is adapted to the first model mapping structure includes: Step S401: respectively determine the envelope blocks of the first model mapping structure and the second model mapping structure on the sewage treatment plant structure performance model, denoted as the first envelope block and the second envelope block, analyze the intersection volume between the first envelope block and the second envelope block, and determine the sum of the volumes of the first envelope block and the second envelope block, denoted as the total block volume, and calculate the volume ratio of the intersection volume to the total block volume.

[0053] Step S402: compare the line coincidence ratio of the vector lines in the first model mapping structure and the second model mapping structure, and combine the volume ratio to determine the adaptation degree of the first model mapping structure and the second model mapping structure.

[0054] 。

[0055] Where S is the adaptation degree, is the intersection volume of the first envelope block and the second envelope block, is the volume of the first envelope block, is the volume of the second envelope block, is the number of vector lines of the first model mapping structure, is the number of vector lines of the second model mapping structure, is the number of coincident vector lines, is the intersection volume influence weight, is the vector line coincidence influence weight.

[0056] In some embodiments disclosed by the present invention, a sewage treatment plant multi-source heterogeneous data warehouse construction system is also disclosed, which is characterized by including: The first module is used to analyze the on-site layout of the sewage treatment plant and construct a sewage treatment plant structure performance model. The sewage treatment plant structure performance model includes several process blocks, each process block includes several equipment nodes, and the relative positions between the process blocks and the relative positions between the equipment nodes are mapped to the on-site layout of the sewage treatment plant.

[0057] The second module is used to construct a knowledge graph for the sewage treatment plant, and for each information mapping logic in the knowledge graph, knowledge explanation content is correspondingly set, and based on the knowledge explanation content, the process blocks and equipment nodes in the sewage treatment plant structure performance model are marked to form the first model mapping structure.

[0058] The third module is used to perform content analysis on heterogeneous data, determine the key factors in each heterogeneous data, and analyze the key factors to determine the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model to form the second model mapping structure.

[0059] The fourth module is used to determine the information mapping logic corresponding to the heterogeneous data based on the adaptation of the first model mapping structure by the second model mapping structure of the heterogeneous data, and classify and store the heterogeneous data according to the information mapping logic of the knowledge graph.

[0060] The present invention discloses a method and system for constructing a multi-source heterogeneous data warehouse in a sewage treatment plant, which relates to the technical field of sewage treatment plant monitoring. It includes analyzing the on-site layout of the sewage treatment plant, constructing a structural representation model containing process blocks and equipment nodes, and mapping the actual layout; constructing a knowledge graph of the sewage treatment plant, and marking the process blocks and equipment nodes in the structural representation model based on the knowledge interpretation content to form a first model mapping structure; performing content analysis on the heterogeneous data, extracting key factors and mapping them to the structural representation model to form a second model mapping structure; adapting the first model mapping structure based on the second model mapping structure, determining the information mapping logic of the heterogeneous data, and classifying and storing it according to the knowledge graph logic. This method realizes the integration and precise mapping of heterogeneous data through the structural model and the knowledge graph, solves the problems of data islands and insufficient relevance, improves the data management and operation efficiency of the sewage treatment plant, and is applicable to intelligent sewage treatment scenarios.

[0061] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant, characterized in that, Including: Step S100: Analyze the on-site layout of the sewage treatment plant and construct a structural performance model of the sewage treatment plant. The structural performance model of the sewage treatment plant includes several process blocks, each process block includes several equipment nodes, and the relative positions between the process blocks and the relative positions between the equipment nodes are mapped to the on-site layout of the sewage treatment plant; Step S200: Construct a knowledge graph for the sewage treatment plant. For each information mapping logic in the knowledge graph, corresponding knowledge explanation content is set, and based on the knowledge explanation content, the process blocks and equipment nodes in the structural performance model of the sewage treatment plant are marked to form a first model mapping structure; Step S300: Analyze the content of heterogeneous data, determine the key factors in each heterogeneous data, and analyze the key factors to determine the process blocks and equipment nodes mapped in the structural performance model of the sewage treatment plant to form a second model mapping structure; Step S400: Based on the first model mapping structure adapted to the second model mapping structure of the heterogeneous data, determine the information mapping logic corresponding to the heterogeneous data, and classify and store the heterogeneous data according to the information mapping logic of the knowledge graph.

2. The method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 1, wherein, The method for constructing a knowledge graph for the sewage treatment plant includes: Step S201: Determine the knowledge keywords of the sewage treatment plant, including process block keywords, equipment keywords, parameter keywords, time keywords, space keywords, operation and maintenance record keywords, material keywords, personnel keywords, and standard keywords; Step S202: Construct the logical relationship between the knowledge keywords, and based on the logical relationship, sequentially connect the corresponding knowledge keywords to obtain the graph framework of the knowledge graph; Step S203: Classify the preset knowledge explanation content based on the knowledge keywords and logical relationships mapped by the graph framework, and combine the knowledge explanation content and the graph framework.

3. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 2, characterized in that, The method for marking the process blocks and equipment nodes in the structural performance model of the sewage treatment plant to form a first model mapping structure includes: Step S204: Analyze the keywords of the knowledge explanation content, extract the process block keywords and equipment node keywords, and based on the process block keywords and equipment node keywords, mark the process blocks and equipment nodes in the structural performance model of the sewage treatment plant; Step S205: Analyze the event impact weights of the process blocks or equipment nodes in the knowledge explanation content, sort the process block keywords and equipment node keywords based on the magnitude of the event impact weights, and based on the sorting results, perform vector line connection on the marked process blocks and equipment nodes in the sewage structure performance model to obtain the first model mapping structure.

4. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 3, characterized in that, The method for analyzing the content of heterogeneous data to determine the key factors in each heterogeneous data includes: Step S301: For each type of heterogeneous data, a factor extraction template is set. The factor extraction template is set with several factor types, and each factor type is set with a factor parameter section sequence; Step S302: Mark the key factors of the historical heterogeneous data and determine the factor parameters of each key factor to obtain several historical key factor parameter groups; Step S303: Based on the compliance of the key factor types as the classification condition, classify different historical key factor parameter groups, conduct centralized feature analysis on the historical key factor parameter groups in each category, and based on the analysis results, construct several factor parameter section array templates. The factor parameter section array template includes several content factor types, each content factor type corresponds to several factor parameter section sequences, the factor parameter section sequence includes several factor parameter sections connected in size order, and mark the factor parameter sections that need to be concerned; Step S304: Identify the content factors in the heterogeneous data, compare the content factors with different factor parameter section array templates, determine the factor parameter section array template that is completely mapped and adapted, and recognize it as the reference factor parameter section array template; Step S305: Recognize the factor types and the factor parameter sections that need to be concerned in the reference factor parameter section array template as the key factors of the heterogeneous data.

5. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 4, characterized in that, The method for conducting centralized feature analysis on the historical key factor parameter groups in each category includes: Step S3031: Extract the historical key factor parameters of the same category in the historical key factor parameter group, sort the historical key factor parameters in order, determine the historical key factor parameter clusters aggregated in the sequence respectively, and calculate the average value in each historical key factor parameter cluster, denoted as the key factor parameter to be concerned; Step S3032: Analyze the number of factor parameters and the factor parameter span in the historical key factor parameter cluster, calculate the quantity density between the number of factor parameters and the factor parameter span, and determine the extension section length of the factor parameter section corresponding to the historical key factor parameter cluster based on the preset density interval where the quantity density belongs; Step S3033: Randomly combine the factor parameter sections corresponding to different types of historical key factor parameter clusters to obtain several initial factor parameter section array templates; Step S3034: Conduct mapping comparison between the historical key factor parameter group and the initial factor parameter section array template, determine the mapping matching performance, sort the initial factor parameter section array template based on the mapping matching performance, and select the first several initial factor parameter section array templates as the applied factor parameter section array templates.

6. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 5, characterized in that, The method for conducting mapping comparison between the historical key factor parameter group and the initial factor parameter section array template to determine the mapping matching performance includes: Step S30341: Determine the section center value of each type of factor parameter section in the initial factor parameter section array template, and calculate the factor parameter difference value between the corresponding historical key factor parameter in the historical key factor parameter group and the section center value; Step S30342: Determine the factor type compliance ratio between the initial factor parameter section array template and the historical key factor parameter group, and combine the factor parameter difference values of each factor type to determine the mapping matching sub-parameters between the initial factor parameter section array template and a single historical key factor parameter group. Step S30343: Randomly select a number of mapping matching sub-parameters greater than or equal to the preset value, and calculate their average value to obtain the mapping matching degree.

7. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 1, characterized in that, The method for analyzing key factors and determining the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model includes: Step S306: Establish a key factor~block and equipment mapping table. The key factor~block and equipment mapping table includes several key factor types, and each key factor type corresponds to a key factor parameter section. Each key factor type and key factor parameter section correspond to several process blocks and equipment nodes, and there is an order relationship between the process blocks and equipment nodes. Step S307: Substitute the determined key factors into the key factor~block and equipment mapping table to determine the process blocks and equipment nodes mapped in the sewage structure performance model. Based on the order relationship between the determined process blocks and equipment nodes, vector line connections are made for the process blocks and equipment nodes mapped in the sewage structure performance model.

8. A method for constructing a multi - heterogeneous data warehouse in a sewage treatment plant according to claim 1, characterized in that The method for determining that the second model mapping structure is adapted to the first model mapping structure includes: Step S401: Respectively determine the envelope blocks of the first model mapping structure and the second model mapping structure on the sewage treatment plant structure performance model, denoted as the first envelope block and the second envelope block. Analyze the intersection volume between the first envelope block and the second envelope block, and determine the sum of the volumes of the first envelope block and the second envelope block, denoted as the total block volume. Calculate the volume ratio of the intersection volume to the total block volume. Step S402: Compare the line coincidence ratio of the vector lines that coincide in the first model mapping structure and the second model mapping structure, and combine the volume ratio to determine the adaptation degree of the first model mapping structure and the second model mapping structure.

9. A system for constructing a multi - heterogeneous data warehouse in a sewage treatment plant, characterized in that, Including: The first module is used to analyze the on-site layout of the sewage treatment plant and construct a sewage treatment plant structure performance model. The sewage treatment plant structure performance model includes several process blocks, each process block includes several equipment nodes, and the relative positions between the process blocks and the relative positions between the equipment nodes are mapped to the on-site layout of the sewage treatment plant. The second module is used to construct a knowledge graph for the sewage treatment plant. For each information mapping logic in the knowledge graph, corresponding knowledge explanation content is set, and based on the knowledge explanation content, the process blocks and equipment nodes in the sewage treatment plant structure performance model are marked to form the first model mapping structure. The third module is used to perform content analysis on heterogeneous data, determine the key factors in each heterogeneous data, and analyze the key factors to determine the process blocks and equipment nodes mapped in the sewage treatment plant structure performance model to form the second model mapping structure. The fourth module is used to determine the information mapping logic corresponding to the heterogeneous data based on the adaptation of the second model mapping structure of the heterogeneous data to the first model mapping structure, and classify and store the heterogeneous data according to the information mapping logic of the knowledge graph.

Images