A water affair data governance system and method

Abstract

The present application relates to the technical field of water management, and particularly relates to a water data management system and method. The method comprises the following steps: firstly, obtaining multi-source water data in a business system, and performing object processing on the multi-source water data to construct corresponding water objects; then, determining a reference water object with the highest correlation degree in the water objects as an object management base point; then, vectorizing attributes of each water object, and judging the similarity of the attributes with the definition of the management base point; performing attribute fusion and supplement on the water objects judged as similar according to a preset business rule to form a standard water object; finally, writing the standard water object back to a water data service platform to realize unified view and standardized management of multi-source water data. Through objectization, multi-source fusion and correlation analysis, the present application realizes standardized, intelligent and visualized unified management of water data, and provides reliable support for scientific decision-making.

Description

Technical Field

[0001] This invention relates to the field of water management technology, and in particular to a water data governance system and method. Background Technology

[0002] With the advancement of smart water management, business systems such as water supply and drainage operation, pipeline management, and metering monitoring continuously generate a large amount of multi-source water data. Due to differences in data models, attribute definitions, coding rules, and business semantics among different business systems, the same actual water entity often exists repeatedly in multiple systems, which can easily lead to data redundancy, inconsistent definitions, and semantic conflicts, affecting data sharing and integrated application.

[0003] Existing water data governance methods are mostly table- or field-centric, relying primarily on manually configured rules or static master data models for field alignment and data merging. They lack a systematic characterization of water entities themselves and their business relationships, particularly failing to reflect the unique characteristics of the water sector, such as pipeline structure and flow transmission. In object selection and governance, master objects or fixed references are typically pre-specified, resulting in insufficient flexibility and adaptability. Furthermore, existing technologies for water data similarity identification are often based on single attributes or simple matching logic, failing to uniformly represent the multidimensional attributes of water objects. This easily leads to incorrect object merging or inaccurate attribute supplementation, making it difficult to form a stable and consistent data view and hindering further improvements in water data governance effectiveness. Summary of the Invention

[0004] Therefore, it is necessary to provide a water data governance system and method to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, a water resources data governance method is provided, the method comprising the following steps: Step S1: Obtain multi-source water data from the business system and objectify the multi-source water data to construct water objects corresponding to actual water entities; Step S2: Identify the benchmark water objects from the water objects and use the benchmark water objects as the basis for object governance; Step S3: Vectorize the attribute information of each water object and determine the similarity of the definition of each water object relative to the object governance baseline; Step S4: For water affairs objects that are similar to the object governance baseline, perform attribute fusion and supplementation based on the object governance baseline according to the preset business rules to form a standard water affairs object; Step S5: Write the standard water affairs objects back to the water affairs data service platform to obtain a unified view of water affairs data.

[0006] This invention provides a water data governance system for executing the water data governance method described above. The water data governance system includes: The objectification module is used to acquire multi-source water data from the business system and perform objectification processing on the multi-source water data to construct water objects corresponding to actual water entities; The benchmark module is used to identify benchmark water objects from water objects and to use benchmark water objects as the basis for object governance. The similarity comparison module is used to vectorize the attribute information of each water object and determine the similarity of the definition of each water object relative to the object governance baseline. The supplementary module is used to perform attribute fusion and supplementation based on the object governance baseline for water objects that are similar to the object governance baseline, according to preset business rules, to form a standard water object; The visualization module is used to write back standard water affairs objects to the water affairs data service platform to obtain a unified view of water affairs data.

[0007] The present invention has the following beneficial effects: First, by objectifying multi-source water data and using benchmark water objects as the governance basis, the attributes of similar water objects are merged and supplemented to form standardized water objects. This processing method eliminates problems such as differences in data sources, inconsistent formats, and information redundancy, and achieves the unification of water data across different systems and sources, providing a reliable data foundation for subsequent data analysis, management, and application.

[0008] Second, by constructing a set of relationships between water-related objects and analyzing the interaction between them based on pipeline structure, flow direction, and spatial proximity, the degree of correlation between water-related objects can be scientifically confirmed. This not only improves the intelligence level of the water data governance process but also enables precise characterization of the connections between objects in complex water systems, providing an effective reference for object governance and avoiding the inefficient governance model based on traditional manual rules or simple matching.

[0009] Third, after completing the construction of standard water affairs objects, they are written back to the water affairs data service platform to generate a water affairs knowledge graph, realizing a unified and visualized display of multi-source water affairs data. This effect enables managers to intuitively understand the overall structure of the water affairs system, the relationships between objects, and key attributes, providing clear data support for water affairs scheduling, pipeline network operation and maintenance, and business decisions, significantly improving the refinement, scientific nature, and operability of water affairs management. Attached Figure Description

[0010] Figure 1 A flowchart illustrating the steps of a water data governance method; Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S2. Figure 3 This is a unified view of a water data governance method proposed in this application; Figure 4 This is a functional module diagram of a water data management system according to this application; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0011] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0012] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0013] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0014] To achieve the above objectives, please refer to Figures 1 to 4 A water resources data governance method, the method comprising the following steps: Step S1: Obtain multi-source water data from the business system and objectify the multi-source water data to construct water objects corresponding to actual water entities; In one embodiment, multi-source water data is first obtained from multiple business systems related to water management. These business systems include at least one or more of the following: a water supply operation system, a drainage dispatching system, a water quality monitoring system, a water level monitoring system, and an equipment operation and maintenance management system. The multi-source water data may include, but is not limited to, pipeline operation status data, water quantity and pressure data, water level change data, water quality index data, equipment operating condition data, and corresponding time and spatial location information.

[0015] When acquiring multi-source water data, data from different business systems are uniformly accessed and processed. Specifically, the timestamps, spatial identifiers, and data types of data from each business system are standardized to ensure that data from different sources are alignable in both time and spatial dimensions, thus providing a foundation for subsequent data association and object-oriented processing.

[0016] After data access is completed, preliminary cleaning processing is performed on the multi-source water data. The cleaning process includes identifying and processing outliers, missing values, and duplicate data. For example, data that is obviously outside the reasonable range is removed, data that is missing for a short period of time is reasonably supplemented, and duplicate records at the same time and in the same location are merged to ensure the integrity and consistency of the multi-source water data.

[0017] Subsequently, based on the actual management objects of water affairs operations, the cleaned multi-source water affairs data is objectified. During the objectification process, the types of water affairs objects are first predefined. These objects include at least one or more of the following: water source objects, pipeline network objects, pumping station objects, valve objects, monitoring point objects, and water-using unit objects. Each type of water affairs object corresponds to a specific physical or management entity in the actual water affairs system.

[0018] During object-oriented processing, related data are aggregated into the same water affairs object based on spatial location information, equipment identification information, or business code information in multi-source water affairs data. For example, water pressure data, flow data, and operation and maintenance records corresponding to the same pipe section are uniformly aggregated into the data attributes of the pipe network object; water quality data and water level data collected from the same monitoring point are aggregated into the data attributes of the monitoring point object.

[0019] In some embodiments, for each constructed water utility object, object attribute information is further assigned to it. The object attribute information includes basic attributes, operational attributes, and historical state attributes. The basic attributes describe the fixed characteristics of the water utility object, the operational attributes describe the operational state of the water utility object at the current moment, and the historical state attributes record the state changes of the water utility object over historical periods.

[0020] Step S2: Identify the benchmark water objects from the water objects and use the benchmark water objects as the basis for object governance; In one embodiment, after the water objects are constructed, the set of water objects is traversed and analyzed to determine at least one baseline water object.

[0021] When determining the benchmark water utility objects, the first step is to assess the business relevance of each object. Business relevance reflects the core nature of a particular water utility object within the overall water system. The assessment criteria include at least the number of other water utility objects associated with that object, the frequency of data interactions, and its critical position within the water supply or drainage process. Water utility objects with higher business relevance are prioritized as candidate benchmark water utility objects.

[0022] In some embodiments, the data stability of water-related objects is also analyzed. Data stability is used to characterize the completeness and continuity of data collection for water-related objects within a continuous time period. Specifically, the data missingness, abnormal fluctuations, and update time consistency of each water-related object within a preset time window are statistically analyzed. Water-related objects with good data continuity and low abnormality rates are given higher priority as benchmark water-related objects.

[0023] Simultaneously, the spatial representativeness of water-related objects is assessed. Spatial representativeness measures whether a water-related object is located in a representative spatial position within the water system, such as main pipelines, key pumping stations, important water source nodes, or core monitoring sections. Water-related objects located in key spatial positions are more conducive to reflecting the overall water system operation status and therefore have a higher weight in the selection of benchmark water-related objects.

[0024] After considering factors such as comprehensive business relevance, data stability, and spatial representativeness, at least one water object is selected from the set of water objects as a baseline water object. This baseline water object is marked as a governance benchmark and a unique governance identifier is established in the system for subsequent object association, data calibration, and governance rule mapping.

[0025] In some embodiments, when the water system is large in scale or has a complex business structure, multiple baseline water objects can be identified, each corresponding to a different business subdomain or spatial subregion. For example, in a water supply system, the main water supply network object can be selected as the baseline water object, and in a drainage system, the key drainage trunk line object can be selected as the baseline water object, thereby forming multiple object governance baselines, which are used for data governance within their respective subsystems.

[0026] After determining the baseline water management point, the relationships between other water management objects and the baseline water management object are uniformly calibrated using the benchmark water management object as a reference. This calibration process includes time alignment calibration, spatial relationship calibration, and business process relationship calibration, so that subsequent data processing, status analysis, and risk assessment of each water management object can all be carried out around the baseline water management point.

[0027] Step S3: Vectorize the attribute information of each water object and determine the similarity of the definition of each water object relative to the object governance baseline; In one embodiment, after determining the governance baseline, attribute information extraction processing is performed on each water object in the water object set. The attribute information includes at least the basic attributes, operational attributes, and business attributes of the water object, wherein the basic attributes are used to characterize the type, region, and physical location characteristics of the water object, the operational attributes are used to characterize the state change characteristics of the water object during operation, and the business attributes are used to characterize the functional role of the water object in the water business process.

[0028] After extracting the attribute information, the attribute information of each water utility object is standardized. This standardization process includes field alignment, unit unification, and outlier correction for attribute information from different sources and in different formats, ensuring that the attribute information of each water utility object is consistent at both the semantic and structural levels, thus providing a unified data foundation for subsequent vectorized representation.

[0029] After completing the attribute information standardization process, the attribute information of each water resource object is mapped to a corresponding attribute vector. Specifically, the various attributes of the water resource object are arranged according to a preset attribute dimension order, and the attribute values ​​are converted into comparable numerical or hierarchical forms, thereby forming an attribute vector representation that can comprehensively characterize the features of the water resource object. In this way, the transformation of water resource objects from semantic description to structured feature representation is realized.

[0030] Simultaneously, the same attribute extraction and vectorization processing is performed on the benchmark water objects corresponding to the object governance benchmark to obtain the benchmark attribute vector. The benchmark attribute vector is used as a reference vector to define similarity judgment, and is used to measure the degree of similarity between other water objects and the object governance benchmark at the attribute level.

[0031] In some embodiments, by performing a dimension-by-dimensional comparative analysis of the attribute vectors of each water utility object and the baseline attribute vector, the similarity between each water utility object and the baseline governance object in terms of functional characteristics, operational status, and business positioning is assessed. Water utility objects with a high degree of similarity typically have consistency or high correlation with the baseline water utility object in terms of business functions or operational characteristics.

[0032] When defining similarity criteria, an attribute weight adjustment mechanism can be introduced. For core attributes that have a significant impact on water operations, their influence in similarity criteria is increased; for auxiliary attributes that have a smaller impact on overall operations, their influence is decreased, thereby making the similarity criteria results more consistent with the actual characteristics of water operations.

[0033] In some embodiments, water objects are divided into multiple similarity level intervals based on their definitional similarity to the governance baseline. For example, water objects that are highly consistent with the governance baseline in terms of function and operational characteristics are classified as highly similar objects, water objects with some consistent attributes but different operational states are classified as moderately similar objects, and water objects with significant attribute differences are classified as lowly similar objects.

[0034] Step S4: For water affairs objects that are similar to the object governance baseline, perform attribute fusion and supplementation based on the object governance baseline according to the preset business rules to form a standard water affairs object; In one embodiment, a set of water objects that are similar to the governance baseline is first selected. The selection is based on the definition similarity discrimination results of the previous step, and water objects with high similarity and moderate similarity are included in the candidate set for subsequent attribute fusion and supplementation operations.

[0035] For each object in the candidate water affairs object set, its attribute vector is extracted, including basic attributes, operational attributes, and business attributes. Each attribute is compared with the corresponding attribute of the object's governance baseline to determine whether the attribute value is complete, whether there are outliers, whether it conforms to business specifications, and whether it needs to be corrected or supplemented based on the baseline attribute.

[0036] For missing or abnormal attributes, supplementation and correction are performed according to preset business rules. Business rules may include: for missing basic attributes, priority is given to using the corresponding attribute of the object governance baseline to complete them; for abnormal runtime attributes, a reasonable value range is obtained through historical runtime data statistics, and adjustments are made with reference to the baseline attribute; for missing or incomplete business attributes, unified assignment or mapping is performed to supplement them based on the baseline attribute and business process logic.

[0037] When performing attribute fusion, if multiple similar water affairs objects have conflicting attributes, priority rules or weighted fusion methods can be used to handle the situation. Priority rules are set according to the importance of attributes or historical accuracy to ensure that key attributes are based on the object's governance baseline attributes. Weighted fusion methods, on the other hand, comprehensively consider the credibility of attributes of each object to achieve a smooth transition and reasonable value selection.

[0038] For water affairs objects that have completed attribute fusion and supplementation, a consistency check is performed. The check includes whether the attribute values ​​conform to business specifications, whether the attribute differences from the object's governance baseline are within the allowable range, and whether there are any logical conflicts or abnormal combinations. After passing the check, a standard water affairs object is generated, ensuring that its attribute expression is consistent, complete, and can be directly used for subsequent governance operations.

[0039] In some embodiments, the resulting standard water object may also be attached with attribute tag information to identify the attribute source, fusion process records, and credibility level. This additional information can be used for subsequent data traceability, anomaly analysis, and risk assessment.

[0040] Step S5: Write the standard water affairs objects back to the water affairs data service platform to obtain a unified view of water affairs data.

[0041] In one embodiment, the generated standard water affairs object is written back to the water affairs data service platform via a data interface or service call. During the write-back process, the system first performs format conversion on the standard water affairs object to make it conform to the platform's unified data storage specifications, including field names, data types, timestamp formats, and unique identifier generation rules.

[0042] The written-back data undergoes integrity and consistency checks to ensure that each water utility data entry has a unique identifier and all fields are complete, preventing data anomalies caused by duplicate writes or missing fields. Additionally, version information or change logs can be generated for critical attribute fields to track the update history of standard water utility objects.

[0043] During the write-back process, the platform can automatically establish indexes and relationships based on the attribute information of standard water objects to support subsequent data queries, statistical analysis, and visualization. The mapping relationship between standard water objects and original water data can also be retained for data traceability and discrepancy analysis.

[0044] After the write-back is completed, the water data service platform generates a unified view of water data. In this unified view, the data of each water object has been standardized, integrated, and verified, and the attribute information is complete and consistent, which can be directly used for water governance decision-making, risk analysis, resource scheduling, and intelligent management applications.

[0045] In some embodiments, to improve data availability and access efficiency, the platform can cache the unified view or generate a multidimensional index, while attaching data quality identifiers, including data credibility, update frequency, and anomaly correction records, to support rapid access and dynamic monitoring by business systems.

[0046] In another embodiment, reference can be made to Figure 3The unified management interface for water supply facility objects, as shown, writes back the standardized water objects, processed through the aforementioned steps, to the water data service platform to construct a unified view of water data. Specifically, the water data service platform uses "water supply facility objects" as the overall object overview unit, centrally displaying and summarizing the written-back standard water objects. This includes: a total of 1248 objects, 45 associated attribute fields, and 4 object subtypes, with each subtype including at least water plants, booster stations, water storage facilities, and water meters. The platform further generates an object distribution view based on object type, displaying the quantity composition of different water supply facility objects in the system; for example, 12 water plant objects, 45 booster station objects, 89 water storage facility objects, and 1102 water meter objects. Through the above-mentioned write-back and visualization aggregation, water supply facility data scattered across multiple business systems are transformed into a unified water data view with consistent structure and semantics under the same interface, thus providing a standardized data foundation for subsequent water object analysis, operation monitoring, and decision-making applications.

[0047] As an example of the present invention, reference is made to... Figure 2 As shown, in this example, step S2 includes: Step S21: Obtain the object attributes of each water object and the relationship information between the object attributes; Step S22: Based on the relationship information, identify the water object that has the highest degree of association with other water objects among the water objects; Step S23: Identify the water utility object with the highest degree of correlation as the benchmark water utility object; Step S24: Starting with the benchmark water object, establish object governance reference relationships for other water objects, and determine the benchmark water object as the object governance base point.

[0048] In one embodiment, multi-source attribute data of each water object is acquired through a water data service platform. This includes basic attributes (such as pool number "P001", capacity 500 cubic meters, geographical coordinates longitude 123.45°E, latitude 34.56°N), operational attributes (such as flow rate 30 cubic meters / hour, water quality indicators pH value 7.2, pressure value 0.5MPa), and business attributes (such as pipeline number "N01", monitoring point number "M12", and upstream and downstream numbers "P002" and "P003"). Simultaneously, information on the relationships between water objects is collected, including upstream and downstream flow direction relationships, pipeline connection relationships, and scheduling dependencies. The data is then organized into structured tables for subsequent processing.

[0049] Subsequently, the correlation strength between each water object and other objects is calculated: for example, the flow share of pool "P001" with downstream pool "P002" is 80%, and with pool "P003" it is 20%. Combining the upstream and downstream connection weights, the comprehensive correlation score is 0.85. All water objects are then ranked by score. The pool with the highest score and complete attributes ("P001" in this example) is identified as the benchmark water object, serving as the core reference for object governance.

[0050] Starting with the baseline water management object "P001", a reference chain is established according to the upstream and downstream flow direction: such as "P001→P002→P004", and the reference object number of each water management object is marked. For pipeline scheduling dependent objects, such as "P003" depending on the water supply of "P001", a dependency chain is established. In the system, "P001" is marked as the object governance baseline, and the remaining objects are treated as a set of governance objects. This reference relationship is used for subsequent attribute fusion and anomaly analysis. For example, the flow and pressure data of "P002" are compared with the data of "P001", and missing values ​​are automatically supplemented or outliers are adjusted, thereby generating a unified water management data view to ensure that governance operations are feasible and logically clear.

[0051] Preferred methods for obtaining the degree of association of water-related objects include: Based on the association information between the attributes of water affairs objects, a set of association relationships for water affairs objects is formed; For any water-related object, count the frequency of its occurrence as a related object in the association set, and filter the first set of water-related objects based on the frequency of occurrence; The degree of association between water-related objects is determined by the degree of interaction and influence among the first set of water-related objects.

[0052] In one embodiment, the attributes of each water object and the relationships between attributes are organized. For example, the upstream and downstream objects of water tank "P001" are "P002" and "P003", the pipeline node "N01" connects water tanks "P001" and "P004", and the monitoring point "M12" is associated with "P001", forming a preliminary set of relationships. This set is represented by a table or graph structure, and each record contains the starting point object, the ending point object, and the relationship type (such as flow dependency, scheduling dependency, or monitoring dependency).

[0053] Subsequently, for any target water object (e.g., "P001"), count the number of times it appears as a related object in the association set. For example, "P001" appears 3 times in the flow dependency relationship and 2 times in the scheduling dependency relationship, for a total of 5 times. Filter out the objects with higher frequency of occurrence to form the first water object set (in this example, it includes "P002", "P003", and "P004").

[0054] Next, the interaction effects between objects within the first water affairs object set are analyzed. For example, the upstream and downstream flow ratios, pipeline connection weights, and scheduling dependency strengths are calculated, and these values ​​are combined as an interaction effect index between objects. Based on this interaction effect index, the correlation degree of the target water affairs object "P001" is quantified. For example, the interaction effect degree between "P001" and "P002" is 0.8, with "P003" it is 0.6, and with "P004" it is 0.3. Therefore, the overall correlation degree of "P001" is relatively high, around 0.7.

[0055] Preferably, the degree of association between water objects is determined by the degree of interaction between the first set of water objects, including: Based on the geographic spatial distance between the first set of water objects, the water objects are divided into a second set of water objects according to the pipeline network structure and flow direction. Each set contains water objects that are directly connected in the pipeline network. The number of direct pipe connections between the second set of water affairs objects is counted, and the response magnitude of flow changes between the second set of water affairs objects is calculated. The interaction values ​​between the second set of water-related objects are determined based on the weighted results of pipeline connections and flow responses; The degree of correlation between water-related objects is determined by using interaction impact values.

[0056] In one embodiment, a geospatial and pipeline network structure analysis is performed on a first set of water-related objects. For example, assume the first set of water-related objects includes water tanks “P001”, “P002”, and “P003” and pumping stations “N01” and “N02”. Based on the pipeline network structure and flow direction, the water-related objects within the set are divided into a second set of water-related objects, where objects within each set are directly connected in the pipeline network. Assume the division results are set A (P001, N01) and set B (P002, P003, N02).

[0057] Next, the number of direct pipe connections between set A and set B is counted. Assuming set A and set B are directly connected by two pipes, the number of pipe connections is 2. Then, the response amplitude of each set to changes in flow rate is monitored. For example, when the water flow in set A increases by 10 m³ / h, and the water flow in set B changes by 7 m³ / h, the flow response amplitude is 0.7.

[0058] Then, the number of pipe connections and the flow response magnitude are weighted and calculated. For example, the weight can be set to 0.6 for flow response and 0.4 for the number of pipe connections, thus obtaining the interaction value between set A and set B. Assume the weighted interaction value is 0.74.

[0059] Finally, the degree of correlation between the target water objects is comprehensively confirmed based on the interaction values ​​between the sets of secondary water objects. For example, if the interaction value between set A and set B to which "P001" belongs is 0.74, then "P001" has a high degree of correlation, providing a reliable basis for the subsequent selection of benchmark water objects and object management.

[0060] Preferably, based on the geographic spatial distance between the first set of water affairs objects, the water affairs objects are divided into a second set of water affairs objects according to the pipeline network structure and flow direction, including: Based on the geographic spatial distance between the first set of water affairs objects, the spatial proximity between the first set of water affairs objects is determined; Extract the pipeline connection relationships of water affairs objects, and identify the object pairs directly connected by pipelines through the pipeline connection relationships; The flow direction among the first water level object sets is determined based on the network topology between object pairs. The first water level object set is divided by the flow direction to obtain the second water affairs object set.

[0061] In one embodiment, it is assumed that the first set of water objects includes several pools and pumping stations, such as pools "P001", "P002", and "P003" and pumping stations "N01" and "N02". First, the spatial distance between each object is calculated based on its geographical coordinates to obtain the spatial proximity between the objects. For example, if the distance between "P001" and "N01" is 50 meters and the distance between "P002" and "N02" is 80 meters, then objects that are close to each other can be preferentially grouped into the same set.

[0062] Next, the pipe network connection relationships of the water objects are extracted, and the directly connected object pairs are identified by analyzing the pipe connection information. For example, "P001" is directly connected to "N01" through pipe D1, and "P002" is connected to "N02" through pipe D2. Based on these object pairs, the pipe network topology is constructed, and the upstream and downstream relationships of each object in the pipe network are confirmed by combining the flow direction of water in the pipe network.

[0063] Then, based on the flow direction, the first set of water-related objects is divided into several sets of second-level water-related objects. For example, "P001" and "N01" form set A, and "P002", "P003" and "N02" form set B. The objects within each set are directly connected in the pipe network and have the same flow direction. This division ensures that the water-related objects within the same set have logical continuity in terms of pipe network structure and flow direction, providing an accurate basis for subsequent correlation analysis and selection of benchmark water-related objects.

[0064] Preferably, determining the flow direction among the first water level object sets based on the pipeline topology between object pairs includes: Confirm the pipeline topology based on the pipeline connection relationships; Based on the object pair, obtain the corresponding pipeline node identifier and adjacent pipeline node information, and confirm the node connection relationship based on the pipeline node identifier and adjacent pipeline node information. The direct flow relationship between the first water level object set was confirmed by the pipeline network topology and node connection relationship. The direction of flow between objects at the first water level is determined by the direct flow relationship.

[0065] In one embodiment, it is assumed that the first set of water objects includes water tanks “P001”, “P002”, and “P003”, and pumping stations “N01” and “N02”. First, the network node identifiers corresponding to each water object are obtained using the network design diagram or real-time monitoring data. For example, the node ID corresponding to “P001” is N100, and the node ID corresponding to “N01” is N200. Then, the neighboring node information of each node is extracted. For example, the downstream node of node N100 is N200, and the upstream node is none (i.e., the source node).

[0066] Based on the aforementioned node identifiers and adjacent node information, a pipeline network topology is established, forming a connection diagram of each node. For example, a unidirectional connection is formed from N100 to N200, and another unidirectional connection is formed from N200 to N300. By analyzing the pipeline network topology, the direct flow relationships between the first set of water-related objects can be confirmed. For instance, there is a direct flow between "P001" and "N01," while "P002" and "N01" flow indirectly through "N02."

[0067] Finally, the flow direction of objects within the set is determined using direct flow relationships. For example, if water flows from node N100 to N200, the flow direction of the corresponding object "P001" points to "N01"; if water flows from N300 to N400, the flow direction of the corresponding object "P003" points to "N02". This method accurately determines the upstream and downstream relationships and flow directions of each object within the first water-related object set, providing a basis for subsequent water-related object set partitioning and correlation analysis.

[0068] Preferably, determining the flow direction among the first water level object sets using direct flow relationships includes: The flow direction range of each first water level object set is identified by using direct flow relationships, including unidirectional flow, bidirectional flow, or undetermined flow direction; The instantaneous flow rate between the first water level object set is extracted based on the flow direction range to calculate the flow rate difference; The flow difference is compared with a preset flow threshold. When the flow difference is greater than or equal to the flow threshold, the first flow direction is obtained; when the flow difference is less than the flow threshold, the second flow direction is obtained. The flow direction between the first water level object set is identified by the first flow direction and the second flow direction.

[0069] In one embodiment, it is assumed that the first set of water objects includes pump stations "N01" and "N02" and water tanks "P001" and "P002". First, based on the established direct flow relationship, the flow direction range of each set of first water objects is identified. For example, pump station "N01" is connected downstream to water tank "P001", where the flow direction is unidirectional; pump station "N02" is connected to water tank "P002", but bidirectional flow occurs when there are fluctuations in the upstream and downstream water levels, so it is marked as bidirectional flow or undetermined flow direction.

[0070] Subsequently, instantaneous flow data between the object sets is acquired using flow sensors or a SCADA system. For example, the instantaneous flow rate from pump station "N01" to water tank "P001" is 5.2 cubic meters per second, and the instantaneous return flow rate from water tank "P001" is 0.1 cubic meters per second. Based on this instantaneous flow data, the flow difference is calculated, which is the downstream flow rate minus the upstream flow rate. In this example, the flow difference is 5.1 cubic meters per second.

[0071] Next, the flow difference is compared with a preset flow threshold, for example, a flow threshold of 1.0 cubic meters per second. When the flow difference is greater than or equal to the flow threshold, the flow direction between the sets is confirmed as the "first flow direction", that is, the mainstream direction is downward; when the flow difference is less than the flow threshold, it is determined as the "second flow direction", that is, the mainstream direction is not obvious or there is a reverse flow.

[0072] Finally, by combining the first and second flow directions mentioned above, the final flow direction among the first set of water resources objects is identified. For example, if the flow difference between "N01-P001" is greater than a threshold, the flow direction is determined to be downstream; if the flow difference between "N02-P002" is less than a threshold, the flow direction is determined to be undetermined. In this way, the flow direction among objects within the first set of water resources objects can be accurately determined, providing a basis for subsequent water resources object set division and correlation analysis.

[0073] Preferably, step S3 includes the following steps: Step S31: Vectorize the attribute information of each water object and its governance baseline to obtain the water object vector and the governance baseline vector; Step S32: Determine the degree of similarity between each water object based on the cosine similarity between the water object vector and the object governance baseline vector; Step S33: Compare the similarity of each water object with the preset similarity threshold to confirm the definition similarity of each water object relative to the object governance baseline.

[0074] In one embodiment, it is assumed that there are five water-related objects in a certain area, namely "Pump Station A", "Pump Station B", "Water Pool C", "Water Pipe D" and "Water Valve E", and "Pump Station A" has been confirmed as the object management base point through step S2.

[0075] In step S31, the attribute information of each water object is vectorized, including flow capacity, pipe diameter, water level, historical dispatch frequency, etc. For example, the attribute vector of "Pump Station A" is [500, 200, 10, 15], the attribute vector of "Pump Station B" is [480, 180, 9, 12], the attribute vector of "Water Pool C" is [300, 150, 8, 10], and so on. At the same time, the attributes of the object governance base point "Pump Station A" are also vectorized to form the governance base point vector.

[0076] In step S32, based on the vectorized attribute information, the cosine similarity between each water object vector and the governance baseline vector is calculated. For example, the cosine similarity between "Pump Station B" and "Pump Station A" is 0.96, between "Water Pool C" and "Pump Station A" is 0.82, between "Water Pipe D" and "Pump Station A" is 0.75, and between "Water Valve E" and "Pump Station A" is 0.60. The closer the cosine similarity is to 1, the more similar the attribute features are.

[0077] In step S33, the calculated cosine similarity is compared with a preset similarity threshold, for example, a threshold of 0.8. Based on this, it can be determined that "Pump Station B" and "Water Pool C" are similar to the target governance base point "Pump Station A," meeting the defined similarity criteria; while "Water Pipe D" and "Water Valve E" have similarities below the threshold and do not belong to the scope of similar water affairs objects. Finally, the judgment result is used as the basis for subsequent attribute fusion and standardization processing, forming a candidate set of standard water affairs objects.

[0078] Preferably, step S32 further includes: Using the water affairs object corresponding to the object governance baseline as the reference object, extract its attribute information for object governance to form an object governance baseline vector; For water objects that are not subject to the governance baseline, extract the attribute information corresponding to the object governance baseline vector to form a water object vector with a unified representation dimension. Using the object governance baseline vector as the directional reference for similarity calculation, the directional alignment process is performed on the vectors of each water affairs object to obtain the aligned water affairs object vectors. Calculate the cosine similarity between each water affairs object vector and the object governance baseline vector; Based on cosine similarity, the degree of similarity between each water resource object and the object governance baseline is confirmed.

[0079] In one embodiment, it is assumed that there are five water-related objects in the area: “Pump Station A”, “Pump Station B”, “Water Pool C”, “Water Pipe D” and “Water Valve E”, where “Pump Station A” has been identified as the object governance base point.

[0080] First, taking the target governance base point "Pump Station A" as the reference object, extract its attribute information for target governance, such as flow capacity, pipe diameter, water level and historical scheduling frequency, to form the target governance base point vector [500, 200, 10, 15].

[0081] Subsequently, attribute information corresponding to the object governance baseline vectors is extracted for other water objects that are not object governance baselines, and all vectors are ensured to have a unified representation dimension. For example, the attribute vector of "Pump Station B" is [480, 180, 9, 12], the attribute vector of "Water Pool C" is [300, 150, 8, 10], and so on.

[0082] Next, using the object governance baseline vector as the directional benchmark, the vectors of each water affairs object are aligned to ensure that the vector representations can be compared for similarity under the same dimension and direction. For example, if there are differences in attribute order, units, or dimensions, the vectors of non-object governance baselines will be normalized or their units converted to maintain consistency with the baseline vector. Then, based on the aligned vectors, the cosine similarity of each water object vector with respect to the object governance baseline vector is calculated. For example, the cosine similarity between "Pump Station B" and "Pump Station A" is 0.96, the cosine similarity between "Water Pool C" and "Water Pipe D" is 0.82, the cosine similarity between "Water Pipe D" and "Water Valve E" is 0.75, and the cosine similarity between "Water Valve E" and "Water Valve E" is 0.60.

[0083] Finally, based on the calculated cosine similarity, the degree of similarity between each water-related object and the object's governance baseline is confirmed. The closer the cosine similarity is to 1, the more similar the attribute features are, thus providing a basis for subsequent attribute fusion and standardization processing. For example, "Pump Station B" and "Water Pool C" are determined to be similar to the object's governance baseline, while "Water Pipe D" and "Water Valve E" have a lower degree of similarity.

[0084] Of particular importance is that, based on the geographic spatial distance between the first set of water affairs objects, the spatial proximity between the first set of water affairs objects is determined to include: Extract the geographic coordinates and boundary information of each water object in the first water object set; Calculate the spatial distance between each water-related object based on geographical coordinates and boundary information; The spatial distances between various water-related objects are spatially proximity mapped to obtain the spatial proximity strength of the first water-related object. Confirm the spatial proximity between the first water object sets by using the spatial proximity strength of the first water objects.

[0085] In an embodiment, it is assumed that the first water object set includes "pump station A", "pool B", "water valve C" and "water pipe D". First, extract the geographic coordinates (latitude and longitude or plane projection coordinates) and boundary information (such as the polygonal boundary of the service coverage area) of each water object. For example, the coordinates of "pump station A" are (120.15, 30.25), with a coverage radius of 500 meters; the coordinates of "pool B" are (120.16, 30.26), with a coverage radius of 300 meters, and so on.

[0086] Subsequently, based on the geographic coordinates and boundary information of each water object, calculate the spatial distance between every two water objects in the set. For example, the Euclidean distance or geographic distance formula is used to calculate that the center distance between "pump station A" and "pool B" is about 150 meters, and the distance between "pump station A" and "water valve C" is 230 meters.

[0087] Next, perform spatial proximity mapping on the spatial distances between various water objects. The specific method is: set a distance threshold range, map object pairs with closer distances to higher spatial proximity strength, and map object pairs with farther distances to lower proximity strength. For example, the proximity strength of an object pair with a distance less than 200 meters is 1.0, 0.7 for 200 to 400 meters, 0.4 for 400 to 600 meters, and so on.

[0088] Finally, combined with the spatial proximity strength, count the average proximity strength of all object pairs in the first water object set, which is used as the overall spatial proximity index of the first water object set. For example, the average spatial proximity strength in this set is 0.82, indicating that the internal spatial distribution of the object set is relatively compact. This spatial proximity is used for subsequent division of the second water object set according to the pipe network structure and flow direction.

[0089] It is particularly important that performing spatial proximity mapping on the spatial distances between various water objects includes: Based on the preset spatial proximity mapping rules, convert the spatial distances between various water objects into corresponding spatial proximity strength values; With the first water object as the center, collect the spatial proximity strength corresponding to it and other water objects, and form the spatial proximity strength of the first water object, wherein the preset spatial proximity mapping rules are specifically as follows: According to the spatial distance D between water objects, map the spatial distance to a standardized spatial proximity strength value S, wherein the mapping rule satisfies: when D≤50m, the spatial proximity strength S is 1; when 50m<D≤200m, the spatial proximity strength S adopts a linear decreasing value; when D>200m, the spatial proximity strength S is 0.

[0090] In one embodiment, multiple water-related objects within an urban area are used as the first set of water-related objects. These water-related objects include stormwater inspection wells, pipe section nodes, pumping stations, and small-scale water storage facilities. First, the geographic coordinate information corresponding to each water-related object is read from the water-related basic database, and its spatial boundary range is obtained by combining the object type. Point objects are represented by their center coordinates, while linear or area objects are spatially located based on their boundary outlines.

[0091] Based on this, for any two water objects in the first set of water objects, the actual spatial distance between the objects is calculated based on their geographic coordinates and boundary information. This distance can be determined using planar distance measurement or the shortest boundary distance in a projected coordinate system. After completing the distance calculation for all pairs of objects, a set of spatial distances between water objects is obtained.

[0092] Subsequently, the aforementioned spatial distances are transformed according to a preset spatial proximity mapping rule. Specifically, when the spatial distance between two water-related objects is relatively close, they are considered to have a strong spatial correlation and are assigned a high spatial proximity strength; when the spatial distance is in the medium range, their spatial correlation is considered to gradually weaken with increasing distance, and the corresponding spatial proximity strength decreases accordingly; when the spatial distance exceeds the preset maximum influence range, they are considered to have no direct spatial correlation, and their spatial proximity strength is set to the lowest value. Through this mapping rule, different spatial distances can be uniformly converted into standardized spatial proximity strength values.

[0093] Furthermore, taking a certain water object as the first water object as the center, the spatial proximity intensity of it and other water objects in the set of the first water objects is collected and summarized to form the spatial proximity intensity result of the first water object, which is used to characterize its proximity to surrounding water objects in the spatial dimension.

[0094] For example, in a certain implementation scenario, a storm drain inspection well is selected as the first water management object. Three other water management objects exist around it. One is relatively close to the inspection well and is mapped to the highest spatial proximity intensity; another is at a medium distance and its spatial proximity intensity is correspondingly lower; the third is relatively far away and is determined to have no spatial proximity relationship. By aggregating these spatial proximity intensities, the spatial proximity between the storm drain inspection well and surrounding water management objects can be intuitively reflected, providing a foundation for subsequent water management object correlation analysis and governance decisions.

[0095] like Figure 4 The diagram shown is a functional block diagram of a water data management system provided in an embodiment of the present invention.

[0096] The water data management system 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the water data management system 100 may include an objectification module 101, a benchmark module 102, a similarity comparison module 103, a supplementary module 104, and a visualization module 105. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0097] The objectification module 101 is used to acquire multi-source water data from the business system and perform objectification processing on the multi-source water data to construct water objects corresponding to actual water entities. The benchmark module 102 is used to determine benchmark water objects from water objects and to use benchmark water objects as the basis for object governance. The similarity comparison module 103 is used to vectorize the attribute information of each water object and determine the definition similarity of each water object relative to the object governance base point; The supplementary module 104 is used to perform attribute fusion and supplementation based on the object governance baseline for water objects that are similar to the object governance baseline, according to preset business rules, to form a standard water object; The visualization module 105 is used to write back standard water affairs objects to the water affairs data service platform to obtain a unified view of water affairs data.

[0098] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0099] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for water resources data governance, characterized in that, Includes the following steps: Step S1: Obtain multi-source water data from the business system and objectify the multi-source water data to construct water objects corresponding to actual water entities; Step S2: Determine the benchmark water management object from the water management objects, and use the benchmark water management object as the basis for object governance; wherein, step S2 includes the following steps: Step S21: Obtain the object attributes of each water object and the relationship information between the object attributes; Step S22: Based on the relationship information, identify the water object that has the highest degree of association with other water objects among the water objects; Step S23: Identify the water utility object with the highest degree of correlation as the benchmark water utility object; Step S24: Starting with the benchmark water resource object, establish object governance reference relationships for other water resource objects, and determine the benchmark water resource object as the object governance base point; wherein, the method for obtaining the degree of association of water resource objects includes: Based on the association information between the attributes of water affairs objects, a set of association relationships for water affairs objects is formed; For any water-related object, count the frequency of its occurrence as a related object in the association set, and filter the first set of water-related objects based on the frequency of occurrence; The degree of association between water-related objects is determined by the degree of interaction and influence among the first set of water-related objects; wherein, determining the degree of association between water-related objects by the degree of interaction and influence among the first set of water-related objects includes: Based on the geographic spatial distance between the first set of water objects, the water objects are divided into a second set of water objects according to the pipeline network structure and flow direction. Each set contains water objects that are directly connected in the pipeline network. The number of direct pipe connections between the second set of water affairs objects is counted, and the response magnitude of flow changes between the second set of water affairs objects is calculated. The interaction values ​​between the second set of water-related objects are determined based on the weighted results of pipeline connections and flow responses; Use interaction values ​​to determine the degree of correlation between water-related objects; Step S3: Vectorize the attribute information of each water resource object and determine the similarity of each water resource object's definition relative to the object's governance baseline; Step S3 includes the following steps: Step S31: Vectorize the attribute information of each water object and its governance baseline to obtain the water object vector and the governance baseline vector; Step S32: Determine the degree of similarity between each water object based on the cosine similarity between the water object vector and the object governance baseline vector; Step S33: Compare the similarity of each water object with the preset similarity threshold to confirm the definitional similarity of each water object relative to the object governance baseline; Step S4: For water affairs objects that are similar to the object governance baseline, perform attribute fusion and supplementation based on the object governance baseline according to the preset business rules to form a standard water affairs object; Step S5: Write the standard water affairs objects back to the water affairs data service platform to obtain a unified view of water affairs data.

2. The water data governance method according to claim 1, characterized in that, Based on the geographic spatial distance between the first set of water resources objects, the water resources objects are divided into a second set of water resources objects according to the pipeline network structure and flow direction, including: Based on the geographic spatial distance between the first set of water affairs objects, the spatial proximity between the first set of water affairs objects is determined; Extract the pipeline connection relationships of water affairs objects, and identify the object pairs directly connected by pipelines through the pipeline connection relationships; The flow direction among the first water level object sets is determined based on the network topology between object pairs. The first water level object set is divided by the flow direction to obtain the second water affairs object set.

3. The water data governance method according to claim 2, characterized in that, Based on the network topology between object pairs, the flow direction among the first water level object sets is determined to include: Confirm the pipeline topology based on the pipeline connection relationships; Based on the object pair, obtain the corresponding pipeline node identifier and adjacent pipeline node information, and confirm the node connection relationship based on the pipeline node identifier and adjacent pipeline node information. The direct flow relationship between the first water level object set was confirmed by the pipeline network topology and node connection relationship. The direction of flow between objects at the first water level is determined by the direct flow relationship.

4. The water data governance method according to claim 3, characterized in that, Determining the flow direction among the first water level objects using direct flow relationships includes: The flow direction range of each first water level object set is identified by using direct flow relationships, including unidirectional flow, bidirectional flow, or undetermined flow direction; The instantaneous flow rate between the first water level object set is extracted based on the flow direction range to calculate the flow rate difference; The flow difference is compared with a preset flow threshold. When the flow difference is greater than or equal to the flow threshold, the first flow direction is obtained; when the flow difference is less than the flow threshold, the second flow direction is obtained. The flow direction between the first water level object set is identified by the first flow direction and the second flow direction.

5. The water data governance method according to claim 1, characterized in that, Step S32 also includes: Using the water affairs object corresponding to the object governance baseline as the reference object, extract its attribute information for object governance to form an object governance baseline vector; For water objects that are not subject to the governance baseline, extract the attribute information corresponding to the object governance baseline vector to form a water object vector with a unified representation dimension. Using the object governance baseline vector as the directional reference for similarity calculation, the directional alignment process is performed on the vectors of each water affairs object to obtain the aligned water affairs object vectors. Calculate the cosine similarity between each water affairs object vector and the object governance baseline vector; Based on cosine similarity, the degree of similarity between each water resource object and the object governance baseline is confirmed.

6. A water resources data governance system, characterized in that, For performing the water data governance method as described in claim 1, the water data governance system includes: The objectification module is used to acquire multi-source water data from the business system and perform objectification processing on the multi-source water data to construct water objects corresponding to actual water entities. The benchmark module is used to identify benchmark water objects from water objects and to use benchmark water objects as the basis for object governance. The similarity comparison module is used to vectorize the attribute information of each water object and determine the similarity of the definition of each water object relative to the object governance baseline. The supplementary module is used to perform attribute fusion and supplementation based on the object governance baseline for water objects that are similar to the object governance baseline, according to preset business rules, to form a standard water object; The visualization module is used to write back standard water affairs objects to the water affairs data service platform to obtain a unified view of water affairs data.

Images