A complex sewer network operation and maintenance work intelligent task decomposition and resource configuration method

Abstract

This application discloses an intelligent task decomposition and resource allocation method for complex drainage pipeline network operation and maintenance. The method may include: constructing a standardized spatial database for infrastructure, managing data attributes and the responsibility area layers of each work team; configuring multiple construction methods, corresponding work subjects, and unit-time work capacity values ​​for different work subjects in a PostgreSQL database; retrieving unassigned tasks for a target time period from the database and determining the corresponding construction methods and work subjects, and filtering the tasks to be assigned to the corresponding work teams based on the responsibility area layers of each work team; dividing the tasks to be assigned into multiple daily task packages through reverse topology based on the construction methods, work subjects, and corresponding unit-time work capacity values; and dynamically allocating resources for the daily task packages using a knowledge graph. This invention ensures the spatial continuity and workload balance of task packages, significantly improving the efficiency and scientific nature of operation and maintenance management.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance management technology for smart city infrastructure, and more specifically, to a method for intelligent task decomposition and resource allocation for the operation and maintenance of complex drainage pipe networks. Background Technology

[0002] With the continuous advancement of urban infrastructure construction, underground drainage networks, as a crucial component of urban operations, are receiving increasing attention for their daily maintenance and management. While some cities have introduced information platforms to assist in developing maintenance plans, significant shortcomings remain in practical application: (1) Current maintenance tasks rely heavily on manual experience to formulate plans. Usually, management personnel randomly select pipe sections and manually allocate materials, equipment and workers. (2) Different maintenance plans are isolated and independent, and the hydraulic connectivity of the pipeline network is not considered. This can easily lead to repeated work, waste of resources, and even affect the overall drainage efficiency. In addition, the efficiency of planning is low. (3) Different types of pipes (such as rainwater pipes and sewage pipes) and different types of defects often require different maintenance methods and work items. The work capacity (i.e. "efficiency", usually measured by the length of pipe that can be maintained per day) of various work items varies significantly, making it difficult to assess and allocate the workload in a balanced manner. Existing methods have failed to effectively consider this characteristic. (4) When facing complex and large-scale pipeline systems, existing methods often take too long to formulate plans due to the lack of efficient algorithm support and automated decomposition mechanism.

[0003] Therefore, it is necessary to develop an intelligent task decomposition and resource allocation method for the operation and maintenance of complex drainage pipe networks.

[0004] The information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] This invention proposes an intelligent task decomposition and resource allocation method for the operation and maintenance of complex drainage pipe networks, which ensures the spatial continuity of task packages and the balance of workload, and significantly improves the efficiency and scientific nature of operation and maintenance management.

[0006] This disclosure provides an intelligent task decomposition and resource allocation method for the operation and maintenance of complex drainage pipe networks, including: Construct a standardized spatial database for infrastructure and manage data attributes and the responsible area layers for each work team; Configure multiple construction methods, corresponding work subjects for each construction method, and unit time work capacity values ​​for different work subjects in the PostgreSQL database; Retrieve unassigned tasks for the target time period from the database and determine the corresponding construction methods and work subjects. Filter the tasks to be assigned to the corresponding work group based on the area layer of each work group's responsibility. Based on the work method, work subject, and the corresponding unit time work capacity value of the work subject, the tasks to be assigned are divided into multiple daily task packages through reverse topology. For daily task packages, dynamic resource allocation is achieved through knowledge graphs.

[0007] Preferably, the spatial database stores the geometric and attribute data of various infrastructures such as inspection wells and pipelines.

[0008] Preferably, the data attributes include municipal-rainwater, municipal-sewage, residential-rainwater, and residential-sewage.

[0009] Preferably, the construction methods include water trucks, vacuum trucks, manual labor, machinery, and repair, with each method corresponding to multiple work items.

[0010] Preferably, the task to be assigned is a pipeline to be maintained.

[0011] Preferably, based on the work method, work subject, and the corresponding unit-time work capacity value of the work subject, the tasks to be assigned are divided into multiple daily task packages through reverse topology, including: The pipeline network is abstracted as a directed topology graph, with manholes as nodes, and tasks are decomposed for each type of data attribute. Find all pipelines without downstream nodes and trace upstream. During the traversal, calculate the cumulative workload of the current task package in real time.

[0012] Among them, L i k is the actual length of the i-th pipe; i The construction method type corresponding to the i-th pipeline; This refers to the hourly operating capacity of this construction method. The termination result is determined by the following formula:

[0013] Among them, L i+1 k is the length of the next pipe to be added to the task package. i+1 The construction method type corresponding to the pipeline to be added; Terminate indicates the termination result. If the termination result is 1, then terminate the current traversal path, stop adding the current pipeline to the current task package, and output the current task package as a daily task package. If the termination result is 0, continue adding pipelines. Repeated upstream tracing yields multiple daily task packages; Perform the above steps independently for municipal rainwater, municipal sewage, residential rainwater, and residential sewage to obtain the corresponding daily task packages.

[0014] Preferably, the reverse topology traversal adopts a constrained depth-first search strategy, wherein the constraints include capacity constraints, classification constraints, and work efficiency adaptation constraints corresponding to the work subjects.

[0015] Preferably, during the reverse topology traversal, when encountering a pipeline branch, a selection strategy based on heuristic evaluation of time deviation and spatial distance is used to determine the traversal priority:

[0016] in, t The weight of the duration deviation score, d The weights for spatial distance scores; P i S represents the traversal priority of the i-th subpath; the larger the value, the higher the priority. t,i The duration matching score for the i-th sub-path is... W i S represents the estimated job duration for the i-th sub-path; d,i The space compactness score for the i-th sub-path. D i D represents the average distance from the geometric center of the j-th pipe in the i-th sub-path to the geometric centers of all pipes that have been traversed within that sub-path, i.e., the spatial dispersion. min D represents the minimum spatial discreteness of all current branch sub-paths. max This represents the maximum spatial dispersion of all current branch sub-paths.

[0017] Preferably, dynamic resource allocation for daily task packages using knowledge graphs includes: For the work methods corresponding to the daily task packages, the optimal resource combination scheme is dynamically generated based on the pre-built knowledge graph, and the equipment and materials that are repeated or shared in multiple work methods are automatically and intelligently integrated.

[0018] Preferably, the knowledge graph takes maintenance methods as the core node and explicitly constructs the dependencies between the methods and equipment, materials, and vehicles through directed edges. The dependencies include: necessary equipment types, consumable material lists, vehicle specifications and ownership, resource quantity requirements, and configuration logic rules.

[0019] The method of the present invention has other features and advantages that will be apparent from or will be set forth in detail in the accompanying drawings and following detailed description, which together serve to explain the particular principles of the invention. Attached Figure Description

[0020] The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of exemplary embodiments of the invention in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same parts.

[0021] Figure 1 A flowchart illustrating the steps of the intelligent task decomposition and resource allocation method for complex drainage network operation and maintenance according to the present invention is shown.

[0022] Figure 2 A flowchart illustrating the steps of a method for intelligent task decomposition and resource allocation in the operation and maintenance of complex drainage pipe networks according to an embodiment of the present invention is shown.

[0023] Figure 3 A schematic diagram of a knowledge graph relating “work method-operation subject-efficiency-resources” according to an embodiment of the present invention is shown. Detailed Implementation

[0024] Preferred embodiments of the invention will now be described in more detail. While preferred embodiments of the invention are described below, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0025] To facilitate understanding of the solutions and effects of the embodiments of the present invention, a specific application example is given below. Those skilled in the art should understand that this example is merely for the purpose of understanding the present invention, and any specific details therein are not intended to limit the present invention in any way.

[0026] Example 1

[0027] Figure 1 A flowchart illustrating the steps of the intelligent task decomposition and resource allocation method for complex drainage network operation and maintenance according to the present invention is shown.

[0028] like Figure 1 As shown, the intelligent task decomposition and resource allocation method for the operation and maintenance of this complex drainage pipe network includes: Step 101: Construct a standardized spatial database for infrastructure and manage data attributes and the responsible area layers for each work team; Step 102: Configure multiple construction methods, corresponding work subjects for each construction method, and unit time work capacity values ​​for different work subjects in the PostgreSQL database; Step 103: Retrieve unassigned tasks for the target time period from the database and determine the corresponding work methods and tasks. Filter the tasks to be assigned for each work group based on the area layer of each work group's responsibility. Step 104: Based on the work method, work subject, and the unit time work capacity value corresponding to the work subject, divide the tasks to be assigned into multiple daily task packages through reverse topology. Step 105: Dynamic resource allocation is achieved for daily task packages using a knowledge graph.

[0029] In one example, the spatial database stores geometric and attribute data for various infrastructure types, such as inspection wells and pipelines.

[0030] In one example, the data attributes include municipal-rainwater, municipal-sewage, community-rainwater, and community-sewage.

[0031] In one example, the construction methods include water trucks, vacuum trucks, manual labor, machinery, and repairs, with each method corresponding to multiple work items.

[0032] In one example, the task to be assigned is a pipeline that needs maintenance.

[0033] In one example, based on the work method, work category, and the corresponding unit-time work capacity value of the work category, the tasks to be assigned are divided into multiple daily task packages using reverse topology, including: The pipeline network is abstracted as a directed topology graph, with manholes as nodes, and tasks are decomposed for each type of data attribute. Find all pipelines without downstream nodes and trace upstream. During the traversal, calculate the cumulative workload of the current task package in real time.

[0034] Among them, L i k is the actual length of the i-th pipe; i The construction method type corresponding to the i-th pipeline; This refers to the hourly operating capacity of this construction method. The termination result is determined by the following formula:

[0035] Among them, L i+1 k is the length of the next pipe to be added to the task package. i+1 The construction method type corresponding to the pipeline to be added; Terminate indicates the termination result. If the termination result is 1, then terminate the current traversal path, stop adding the current pipeline to the current task package, and output the current task package as a daily task package. If the termination result is 0, continue adding pipelines. Repeated upstream tracing yields multiple daily task packages; Perform the above steps independently for municipal rainwater, municipal sewage, residential rainwater, and residential sewage to obtain the corresponding daily task packages.

[0036] In one example, the reverse topology traversal adopts a constrained depth-first search strategy, where the constraints include capacity constraints, classification constraints, and work efficiency adaptation constraints corresponding to the task subjects.

[0037] In one example, during reverse topology traversal, when encountering a network branch, a selection strategy based on heuristic evaluation of time deviation and spatial distance is used to determine the traversal priority:

[0038] in, t The weight of the duration deviation score, d The weights for spatial distance scores; P i S represents the traversal priority of the i-th subpath; the larger the value, the higher the priority. t,i The duration matching score for the i-th sub-path is... W i S represents the estimated job duration for the i-th sub-path; d,i The space compactness score for the i-th sub-path. D i D represents the average distance from the geometric center of the j-th pipe in the i-th sub-path to the geometric centers of all pipes that have been traversed within that sub-path, i.e., the spatial dispersion. min D represents the minimum spatial discreteness of all current branch sub-paths. max This represents the maximum spatial dispersion of all current branch sub-paths.

[0039] In one example, dynamic resource allocation for daily task packages using a knowledge graph includes: For the work methods corresponding to the daily task packages, the optimal resource combination scheme is dynamically generated based on the pre-built knowledge graph, and the equipment and materials that are repeated or shared in multiple work methods are automatically and intelligently integrated.

[0040] In one example, the knowledge graph uses maintenance methods as the core node and explicitly constructs the dependencies between the methods and equipment, materials, and vehicles through directed edges. These dependencies include: required equipment types, a list of consumable materials, vehicle specifications and ownership, resource quantity requirements, and configuration logic rules.

[0041] Figure 2 A flowchart illustrating the steps of a method for intelligent task decomposition and resource allocation in the operation and maintenance of complex drainage pipe networks according to an embodiment of the present invention is shown.

[0042] Specifically, such as Figure 2 As shown, a standardized spatial database for infrastructure is constructed to store geometric and attribute data of various infrastructure types, including manholes and pipe networks, according to unified data specifications. Pipelines and manholes are tagged with attributes according to two dimensions: municipal and residential, and rainwater and sewage. Simultaneously, area layers representing the responsibility of each work team are added to a custom layer. Based on the different operational requirements of pipe network sections, various construction methods and corresponding unit-time operational capacity values ​​are configured in the PostgreSQL database. These include at least: water flushing, manual excavation, manhole cleaning, winch dredging, and pipe suction, each with a different daily operational capacity threshold. The unit-time operational capacity of each work item is converted to...

[0043] E k =L k,daily / 8

[0044] Among them, E k L represents the hourly operating capacity of the k-th construction method (unit: meters / hour); k,daily 8 represents the daily operating capacity of the k-th construction method (unit: meters / day); 8 represents the standard daily working hours (unit: hours).

[0045] The system receives the unique identifier of the monthly maintenance plan and the identifier of the target maintenance team. It retrieves the pipeline facility IDs for all unassigned daily plans under the monthly plan from the task-pipeline association table. Based on the geographic scope of the team management, it uses spatial intersection analysis to filter out the set of pipelines to be maintained within the team's responsibility area and loads the relevant pipeline attributes (facility ID, start and end nodes, geometry, length, node type, ownership, and category) into the temporary work area. Pipelines are processed separately according to four categories: (municipal-stormwater, municipal-sewage, residential-stormwater, and residential-sewage) to ensure that similar pipe sections are processed in the same task decomposition process, avoiding cross-interference.

[0046] Based on four categories, a reverse topology traversal is used to decompose the pipeline network task into categories. First, a directed topology graph G(V,E) of the pipeline network is constructed, where manholes are nodes and pipe segments are directed edges. A left outer join is used to determine if there is a downstream pipe segment originating from the current pipe segment's endpoint. If not, this pipe segment is identified as the topology endpoint and used as the starting point for reverse tracing. First, all pipelines without downstream nodes are found for upstream tracing. During the traversal, the cumulative workload of the current task package is calculated in real time.

[0047] Among them, L i k is the actual length of the i-th pipe; i The construction method type corresponding to the i-th pipeline; The hourly operating capacity of this construction method (unit: meters / hour); the termination result is determined by the following formula:

[0048] Among them, L i+1 k is the length of the next pipe to be added to the task package. i+1 The method type corresponding to the pipeline to be added is defined by 'Terminate'. If the termination result is 1, the current traversal path is terminated, adding the current pipeline to the current task package is stopped, and the current task package is output as a daily task package. If the termination result is 0, pipeline addition continues. The above decomposition process is performed on vertices of different categories according to a preset classification strategy. The current group construction is complete. Pipelines not added will be retained in the processing pool and may be processed as new endpoints in subsequent iterations. The reverse topology traversal adopts a constrained depth-first search (DFS) strategy, with constraints including capacity constraints, classification constraints, and efficiency adaptation constraints corresponding to the task subject.

[0049] During the reverse topology traversal, when encountering network branches, a selection strategy based on heuristic evaluation of time deviation and spatial distance is used to determine the traversal priority:

[0050] in, t The weight of the duration deviation score, d The weights for spatial distance scores, t + d =1, t =0.4, d =0.6; P i S represents the traversal priority of the i-th subpath; the larger the value, the higher the priority. t,i The duration matching score for the i-th sub-path is... W i S represents the estimated job duration for the i-th sub-path; d,i The space compactness score for the i-th sub-path. D i D represents the average distance (in meters) from the geometric center of the j-th pipe in the i-th sub-path to the geometric centers of all pipes that have been traversed within that sub-path, i.e., the spatial dispersion.min D represents the minimum spatial discreteness of all current branch sub-paths. max S represents the maximum spatial dispersion of all current branch sub-paths. d,i The score range is 0~1, when D i =D min At that time, S d,i =1, the space is most compact.

[0051] Finally, the output includes a result set containing facility number, task package number, geometric information, and attribute fields, which serves as the output of the daily task package generation module for subsequent resource configuration.

[0052] This method fully leverages the connectivity of the drainage network topology, combined with daily working time threshold constraints and classification isolation strategies, to effectively achieve a balanced distribution of daily workload while ensuring the continuity of task space.

[0053] Figure 3 A schematic diagram of a knowledge graph relating “work method-operation subject-efficiency-resources” according to an embodiment of the present invention is shown.

[0054] Using maintenance methods as the core node, a multi-dimensional operation and maintenance knowledge graph is constructed, encompassing resource entities such as equipment, materials, and vehicles. Figure 3 As shown, the dependencies between construction methods and their required resources are explicitly modeled using directed edges, including: necessary equipment types, consumable material lists, vehicle specifications, resource quantity requirements, and configuration logic rules, forming a structured system. After the daily task package is generated, intelligent retrieval and matching are performed based on this knowledge graph to dynamically generate the optimal resource combination scheme, automatically integrating duplicate or shareable equipment, vehicles, and materials from multiple construction methods. The system supports visual display of the facility and resource configuration results for daily task packages; clicking on any daily task package clearly presents the facilities, all matching equipment, vehicles, and material details corresponding to that day's plan, and provides flexible manual adjustment capabilities.

[0055] Those skilled in the art should understand that the above description of the embodiments of the present invention is only intended to illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any of the examples given.

[0056] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for intelligent task decomposition and resource allocation in the operation and maintenance of complex drainage pipe networks, characterized in that, include: Construct a standardized spatial database for infrastructure and manage data attributes and the responsible area layers for each work team; Configure multiple construction methods, corresponding work subjects for each construction method, and unit time work capacity values ​​for different work subjects in the PostgreSQL database; Retrieve unassigned tasks for the target time period from the database and determine the corresponding construction methods and work subjects. Filter the tasks to be assigned to the corresponding work group based on the area layer of each work group's responsibility. Based on the work method, work subject, and the corresponding unit time work capacity value of the work subject, the tasks to be assigned are divided into multiple daily task packages through reverse topology. For daily task packages, dynamic resource allocation is achieved through knowledge graphs.

2. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 1, wherein, Spatial databases store geometric and attribute data for various infrastructures such as inspection wells and pipelines.

3. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 1, wherein, Data attributes include municipal-rainwater, municipal-sewage, residential-rainwater, and residential-sewage.

4. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 1, wherein, The construction methods include water trucks, vacuum trucks, manual labor, machinery, and repair, with each method corresponding to multiple work items.

5. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 1, wherein, The task to be assigned is the pipeline that needs maintenance.

6. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance work according to claim 3, wherein, Based on the work method, work category, and corresponding unit-time work capacity value, the tasks to be assigned are divided into multiple daily task packages using reverse topology, including: The pipeline network is abstracted as a directed topology graph, with manholes as nodes, and tasks are decomposed for each type of data attribute. Find all pipelines without downstream nodes and trace upstream. During the traversal, calculate the cumulative workload of the current task package in real time. Among them, L i k is the actual length of the i-th pipe; i The construction method type corresponding to the i-th pipeline; This refers to the hourly operating capacity of this construction method. The termination result is determined by the following formula: Among them, L i+1 k is the length of the next pipe to be added to the task package. i+1 The construction method type corresponding to the pipeline to be added; Terminate indicates the termination result. If the termination result is 1, then terminate the current traversal path, stop adding the current pipeline to the current task package, and output the current task package as a daily task package. If the termination result is 0, continue adding pipelines. Repeated upstream tracing yields multiple daily task packages; Perform the above steps independently for municipal rainwater, municipal sewage, residential rainwater, and residential sewage to obtain the corresponding daily task packages.

7. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 6, wherein, The reverse topology traversal adopts a constrained depth-first search strategy, where the constraints include capacity constraints, classification constraints, and efficiency adaptation constraints corresponding to the task subjects.

8. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance work according to claim 6, wherein, During the reverse topology traversal, when encountering network branches, a selection strategy based on heuristic evaluation of time deviation and spatial distance is used to determine the traversal priority: in, t The weight of the duration deviation score, d The weights for spatial distance scores; P i S represents the traversal priority of the i-th subpath; the larger the value, the higher the priority. t,i The duration matching score for the i-th sub-path is... W i S represents the estimated job duration for the i-th sub-path; d,i The space compactness score for the i-th sub-path. D i D represents the average distance from the geometric center of the j-th pipe in the i-th sub-path to the geometric centers of all pipes that have been traversed within that sub-path, i.e., the spatial dispersion. min D represents the minimum spatial discreteness of all current branch sub-paths. max This represents the maximum spatial dispersion of all current branch sub-paths.

9. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 1, wherein, Dynamic resource allocation for daily task packages using knowledge graphs includes: For the work methods corresponding to the daily task packages, the optimal resource combination scheme is dynamically generated based on the pre-built knowledge graph, and the equipment and materials that are repeated or shared in multiple work methods are automatically and intelligently integrated.

10. The intelligent task decomposition and resource allocation method for complex drainage pipe network operation and maintenance as described in claim 9, wherein, The knowledge graph uses maintenance methods as the core node and explicitly constructs the dependencies between the methods and equipment, materials, and vehicles through directed edges. These dependencies include: required equipment types, consumable material lists, vehicle specifications and ownership, resource quantity requirements, and configuration logic rules.

Images