Dedicated line access path planning method and device, equipment, medium and program product

Abstract

The application provides a private line access path planning method, device, equipment, medium and program product. The method comprises the following steps: acquiring transmission external line resource data and user construction point; constructing a transmission resource network topology graph based on the transmission external line resource data; determining a target regional network topology graph of the user construction point based on the transmission resource network topology graph; and planning a private line access path based on the target regional network topology graph to obtain an optimal private line access path of the user construction point. The private line access path planning method provided by the application can acquire existing transmission external line resource data, construct a transmission resource network topology graph, and demarcate a target regional network topology graph according to a required user construction point. The method comprehensively considers the connected and non-connected conditions, plans a comprehensive path according to different conditions, and reuses existing resources for pipeline layout. The method can more accurately and at a lower cost realize the planning path of the private line service end to end, thereby improving the efficiency of private line access path planning.

Description

Technical Field

[0001] This invention relates to the field of communication transmission technology, and in particular to a leased line access path planning method, apparatus, equipment, medium, and program product. Background Technology

[0002] In recent years, with the rapid development of enterprise digital transformation and cloud computing, enterprises have been increasingly demanding high-performance and high-security network connections. Leased line services have become an important solution to support critical business applications, protect sensitive data, and meet compliance requirements. Operator leased line services have shown a significant growth trend globally.

[0003] Preliminary site survey of leased line access routes is a crucial step in the pre-sales process for leased lines. After a leased line order is placed with the local city, frontline network installation and maintenance personnel will visit the customer's location and several surrounding available access points to assess the availability of resources. Based on their professional experience, they will plan the leased line installation route from the customer's installation site to the optimal network access point and roughly estimate the fiber optic cable length.

[0004] Therefore, the current dedicated line access path planning method relies on manual processing, resulting in long path planning cycles and low efficiency. Summary of the Invention

[0005] This invention provides a leased line access path planning method, apparatus, equipment, medium, and program product to solve the problem of low efficiency in existing leased line access path planning methods.

[0006] In a first aspect, the present invention provides a leased line access path planning method, comprising:

[0007] Acquire external transmission resource data and user construction site locations;

[0008] Based on the aforementioned external transmission resource data, a transmission resource network topology diagram is constructed;

[0009] Based on the transmission resource network topology map, the target area network topology map of the user construction site is determined;

[0010] Based on the target area network topology map, a dedicated line access path is planned to obtain the optimal dedicated line access path for the user's construction site. The optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map.

[0011] In one embodiment, the transmission external resource data includes various types of pipeline segment resources and pipeline point resources; the step of constructing a transmission resource network topology map based on the transmission external resource data includes:

[0012] Pipeline segment resources of the same type are associated and matched according to the resource identifiers at the AZ end to construct the first pipeline topology map corresponding to each type of pipeline segment resource;

[0013] By graph association between the pipeline topology map corresponding to each type of pipeline segment resource and the latitude and longitude of the pipeline point resource of the same type, a second pipeline topology map corresponding to each type of pipeline segment resource is constructed.

[0014] Based on the latitude and longitude of each type of pipeline point resource, the second pipeline topology maps corresponding to different types of pipeline segment resources are graph-associated to construct a transmission resource network topology map.

[0015] In one embodiment, the transmission of external line resource data further includes multiple dedicated line access points; determining the target area network topology map of the user construction site based on the transmission resource network topology map includes:

[0016] Perform a resource quality assessment on each leased access point to obtain the remaining available resources for each leased access point;

[0017] Based on the remaining available resources of each leased access point, multiple available access points that meet the current resource requirements are selected from the multiple leased access points.

[0018] Calculate the first straight-line distance between each available access point and the user's construction point;

[0019] The available access points corresponding to the first n minimum first straight-line distances are determined as the nearest access points to the user's construction site;

[0020] The area radius is determined by a preset multiple of the first straight-line distance corresponding to the farthest neighboring access point.

[0021] Using the user construction site as the center, an initial regional network topology map of the user construction site is constructed based on the region radius;

[0022] Based on the initial regional network topology map, the target regional network topology map of the user's construction site is determined.

[0023] In one embodiment, determining the target area network topology map of the user's construction site based on the initial area network topology map includes:

[0024] Calculate the second straight-line distance of each pipeline point resource within the initial regional network topology;

[0025] The pipeline point resources corresponding to the first m minimum second straight-line distances are determined as the adjacent pipeline point resources of the user's construction site;

[0026] Based on the road network planning capabilities of the geographic information system, the path from the user's construction site to each adjacent pipeline resource point is planned;

[0027] Each path is connected to the initial area network topology as a virtual pipeline;

[0028] In the initial area network topology map after splicing, each adjacent pipeline point resource is connected to the target virtual access point in a virtual connection manner to obtain the target area network topology map of the user construction point.

[0029] In one embodiment, the step of planning the dedicated line access path based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site includes:

[0030] If there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined.

[0031] The sub-network topology map where the user's construction point is located is determined as the sub-topology to be searched, and the user's construction point is determined as the path starting point of the sub-topology to be searched;

[0032] Determine whether the target virtual access point is contained in the sub-topology to be searched;

[0033] If the target virtual access point is not included in the sub-topology to be searched, then calculate the third straight-line distance between each pipeline point resource in the sub-topology to be searched and the user construction point, and the fourth straight-line distance between each pipeline point resource in the sub-topology to be searched and the target virtual access point.

[0034] The distance cost of each pipeline point resource is obtained by weighted summing of the third and fourth straight-line distances corresponding to each pipeline point resource.

[0035] The pipeline point resource corresponding to the minimum distance cost is determined as the path termination point of the sub-topology to be searched;

[0036] The remaining subnetwork topology graph that is closest to the path termination point is searched using the shortest distance method; the remaining subnetwork topology graph is the subnetwork topology graph of the plurality of subnetwork topology graphs excluding those that are divided into subnetworks to be searched.

[0037] In the nearest remaining subnetwork topology graph, search for the pipeline point resource closest to the path termination point using the shortest distance;

[0038] Update the nearest remaining sub-network topology to the sub-topology to be searched, and update the nearest pipeline point resource to the path start point of the sub-topology to be searched;

[0039] The process iteratively executes the step of determining whether the target virtual access point is contained in the sub-topology to be searched until the target virtual access point is contained in the sub-topology to be searched. The target virtual access point is determined as the path termination point of the current sub-topology to be searched. The optimal path between the path start point and the path termination point in each sub-network topology is calculated, and the new pipeline path between each optimal path is calculated. The optimal paths and the new pipeline paths are spliced ​​together to obtain the first optimal dedicated line access path between the user construction point and the target virtual access point.

[0040] In one embodiment, the step of planning the leased line access path based on the target area network topology map to obtain the optimal leased line access path for the user's construction site further includes:

[0041] If there is a connected pipeline path in the target area network topology map, then the user construction point, the target area network topology map and the target virtual access point are input into the optimal path planning model to obtain the second optimal dedicated line access path between the user construction point and the target virtual access point output by the optimal path planning model;

[0042] The optimal path planning model is built using a deep learning network architecture that combines the Deep Deterministic Policy Gradient (DDPG) algorithm with a message-passing neural network.

[0043] In one embodiment, after planning the leased line access path based on the target area network topology map to obtain the optimal leased line access path for the user's construction site, the method further includes:

[0044] Determine the overall pipeline laying cost of the optimal dedicated line access path, the equipment cost required for the dedicated line access service, and the construction cost required for the dedicated line access service;

[0045] The total pipeline laying cost, the equipment cost, and the construction cost are summed to obtain the cost quotation for the dedicated line access service.

[0046] Secondly, the present invention also provides a leased line access path planning device, comprising:

[0047] The acquisition module is used to acquire data on external transmission resources and user construction locations;

[0048] The topology construction module is used to construct a transmission resource network topology map based on the transmission external resource data.

[0049] The determination module is used to determine the target area network topology map of the user's construction site based on the transmission resource network topology map;

[0050] The dedicated line access path planning module is used to plan dedicated line access paths based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site; the optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map.

[0051] Thirdly, the present invention provides an apparatus comprising an electronic device, the electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the above-described leased line access path planning methods.

[0052] Fourthly, the present invention also provides a medium comprising a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the leased line access path planning methods described above.

[0053] Fifthly, the present invention also provides a product comprising a computer program product, the computer program product comprising a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, and the computer program, when executed by the processor, implementing the steps of any of the leased line access path planning methods described above.

[0054] The leased line access path planning method, apparatus, equipment, medium, and program products provided by this invention acquire existing external transmission line resource data, construct a transmission resource network topology map, and delineate the target area network topology map according to the required user construction points. It comprehensively considers the possibility of connectivity and disconnection in the path search area of ​​the target area network topology map, and performs comprehensive planning of leased line access paths according to different situations, improving the accuracy of path planning. Furthermore, it reuses existing resources for pipeline deployment, and the selected resources are more in line with the needs of leased line services, enabling more accurate and cost-effective end-to-end planning of leased line services, thereby improving the overall efficiency of leased line access path planning. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1This is a flowchart illustrating the dedicated line access path planning method provided by the present invention.

[0057] Figure 2 This is a system functional framework diagram of the dedicated line access path planning device provided by the present invention.

[0058] Figure 3 This is a schematic diagram of the pipeline resource association method provided by the present invention.

[0059] Figure 4 This is a visual schematic diagram of a portion of the transmission resource network topology provided by the present invention.

[0060] Figure 5 This is a schematic diagram of the process for planning dedicated line access paths based on regional search provided by the present invention.

[0061] Figure 6 This is a flowchart illustrating the multi-subgraph path planning provided by the present invention.

[0062] Figure 7 This is a schematic diagram of the framework for dedicated line access path planning based on reinforcement learning provided by the present invention.

[0063] Figure 8 This is a schematic diagram of the message passing network provided by the present invention.

[0064] Figure 9 This is a schematic diagram of the cost quotation template provided by the present invention.

[0065] Figure 10 This is a schematic diagram of the dedicated line access path planning device provided by the present invention.

[0066] Figure 11 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0068] The terms "first," "second," etc., used in this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein.

[0069] The following is combined Figures 1-11This invention describes the leased line access path planning method, apparatus, equipment, medium, and program products provided by the present invention.

[0070] It should be noted that the leased line access path planning method provided in this embodiment of the invention is implemented based on a leased line access path planning device. This embodiment of the invention uses the leased line access path planning device as the execution subject to describe the leased line access path planning method.

[0071] Figure 1 This is a flowchart illustrating the leased line access path planning method provided by the present invention. Figure 2 This is a system functional framework diagram of the dedicated line access path planning device provided by the present invention.

[0072] like Figure 1 As shown, the method includes the following:

[0073] Step 101: Obtain external transmission resource data and user construction locations;

[0074] Step 102: Based on the aforementioned external transmission resource data, construct a transmission resource network topology diagram;

[0075] Step 103: Based on the transmission resource network topology map, determine the target area network topology map of the user construction site;

[0076] Step 104: Based on the target area network topology map, perform dedicated line access path planning to obtain the optimal dedicated line access path for the user's construction site.

[0077] In response to the increasingly expanding leased line business, particularly the pre-sales survey stage, and addressing the issues of long cycles, low efficiency, and poor accuracy in traditional leased line access path planning, this paper designs an intelligent leased line access path planning algorithm by integrating existing asset management platform resource data to automatically generate leased line access path plans and quotations.

[0078] like Figure 2 As shown, the leased line access path planning device can be divided into three parts according to system functions: transmission resource topology construction to provide data support, leased line access path planning to provide capability support, and service capability construction to enable external capability opening. Through these three functions, existing resources can be reused and leased line access path planning algorithms can be used to automatically generate leased line access path plans and quotations.

[0079] First, steps 101 and 102 enable the construction of transmission resource topology. This part is based on the existing network resources of the resource management system, and selects the transmission external line resource data necessary for the leased line access design. Prioritizing the reuse of existing transmission external line resource data can reduce construction costs. Furthermore, the latest transmission external line resource data in the resource management system is periodically obtained through data subscription, and multi-type pipeline topologies are constructed in combination with resource link relationships.

[0080] Specifically, external transmission resource data can be obtained from the resource management system. The specific content of the obtained external transmission resource data can be found in Table 1, which is the core resource data table for preliminary exploration.

[0081] Table 1 Core Resource Data Table for Preliminary Exploration

[0082]

[0083] Table 1 shows that the existing external transmission resources in the current network include at least pipeline segment resources such as pipe sections, pole sections, wall-mounted sections, and direct-buried sections; pipeline point resources such as manholes, pipes, and wall-mounted points; and dedicated line access points such as optical distribution boxes, optical fiber distribution boxes, base stations, and site equipment rooms.

[0084] The acquired transmission line resource data includes performance data items. The performance data items for pipeline segment resources include at least the resource name, resource identifier (Identity Document, ID), starting resource ID, ending resource ID, starting latitude and longitude, ending latitude and longitude, calculated length, pipeline capacity, and used capacity. The performance data items for pipeline point resources include at least the resource name, resource ID, resource latitude and longitude, and the pipeline segment to which it belongs. The performance data items for dedicated line access points include at least the resource name, resource ID, resource latitude and longitude, design capacity, and used capacity.

[0085] All of these external transmission resource data can be obtained through subscription on the resource management system platform, with an acquisition period of 1 day.

[0086] Simultaneously, based on the needs of the dedicated line service project, the system will confirm the user-specified construction sites, allowing users to select suitable sites according to their needs and preferences.

[0087] Furthermore, analysis of existing resource data in the resource management system reveals inconsistencies in data types and values ​​among different data entries due to the long construction period of transmission pipelines and inconsistent acquisition equipment. Data preprocessing is necessary for subsequent data mining and analysis.

[0088] Data preprocessing mainly includes:

[0089] (1) Data cleaning: Remove noisy and irrelevant data from the data by filling in missing values, smoothing noisy data, identifying and deleting outliers, and handle missing data and clean data, taking into account time order and data changes;

[0090] (2) Data integration: When the data to be analyzed and mined comes from multiple data sources, it is necessary to integrate multiple databases, data cubes or files.

[0091] After completing data preprocessing, integrating the scattered external resource data from various domains and constructing a connected resource network topology is the foundation and key to achieving subsequent rapid path planning.

[0092] Therefore, constructing a transmission resource network topology based on external transmission resource data can be understood as constructing a transmission resource network topology based on the relationships between pipeline segment resources of the same type, the relationships between pipeline point resources and pipeline segment resources of the same type as the pipeline segment resources, and the relationships between pipeline segment resources of different types.

[0093] Secondly, steps 103 and 104 enable dedicated line access path planning. This part achieves optimal access path planning from the user's construction site to the available uplink access point while reusing as many existing transmission lines as possible.

[0094] Specifically, due to the dense pipeline area, using a full-area path search would result in a significant waste of computation. Therefore, considering the characteristics of the preliminary survey task, based on the transmission resource network topology map, the target area network topology map near the user's construction site is first determined. Then, only the optimal dedicated line access path between the user's construction site and the final dedicated line access point needs to be selected from the target area network topology map, reducing a large amount of computation. Furthermore, the selected resources are more in line with the needs of dedicated line services, enabling more accurate and cost-effective end-to-end planning of dedicated line services.

[0095] Furthermore, based on the network topology map of the target area, dedicated line access path planning is performed to obtain the optimal dedicated line access path for the user's construction site.

[0096] While existing pipeline coverage can ensure a usable connecting pipeline path can be found in most scenarios to plan pipelines / fibers to dedicated access points, it is inevitable that due to incomplete construction or inadequate asset management of existing pipeline resources, there will be local sub-graphs that are not connected to other pipelines. Therefore, it is necessary to comprehensively consider both the existence of non-connected pipeline paths and the existence of connected pipeline paths in the target area network topology graph.

[0097] Therefore, it can be understood that if there are non-connected pipeline paths in the target area network topology map, then the best path is planned according to the local subgraphs based on the target area network topology map, and then the best paths are spliced ​​together to obtain the first optimal dedicated line access path for the user's construction point; if there are connected pipeline paths in the target area network topology map, then the second optimal dedicated line access path for the user's construction point is output through the reinforcement learning model based on the target area network topology map.

[0098] Furthermore, by planning the dedicated line access path, the optimal dedicated line access point recommendation can be achieved, and the end-to-end dedicated line access path can be automatically generated. The generated optimal dedicated line access path can provide a strong reference for the preliminary survey and construction route. At the same time, the cost quotation of dedicated line access services can be automatically calculated according to the overall cost template, effectively solving the pain points of first-line dedicated line preliminary survey site inspection, lack of pipeline maps, and inefficient planning.

[0099] The leased line access path planning method provided by this invention acquires existing external transmission resource data, constructs a transmission resource network topology map, and delineates the target area network topology map according to the required user construction points. It comprehensively considers the possibility of connectivity and disconnection in the path search area of ​​the target area network topology map, and performs comprehensive planning of leased line access paths according to different situations, thereby improving the accuracy of path planning. Furthermore, it reuses existing resources for pipeline deployment, and the selected resources are more in line with the needs of leased line services, enabling more accurate and cost-effective end-to-end planning of leased line services, thus improving the overall efficiency of leased line access path planning.

[0100] In some embodiments, based on step 102, constructing a transmission resource network topology map based on the transmission outside resource data includes:

[0101] Pipeline segment resources of the same type are associated and matched according to the resource identifiers at the AZ end to construct the first pipeline topology map corresponding to each type of pipeline segment resource;

[0102] By graph association between the pipeline topology map corresponding to each type of pipeline segment resource and the latitude and longitude of the pipeline point resource of the same type, a second pipeline topology map corresponding to each type of pipeline segment resource is constructed.

[0103] Based on the latitude and longitude of each type of pipeline point resource, the second pipeline topology maps corresponding to different types of pipeline segment resources are graph-associated to construct a transmission resource network topology map.

[0104] Combination Figure 3 , Figure 3This is a schematic diagram of the pipeline resource association method provided by the present invention. In the original data of the resource management system, pipeline segment resources can be associated by matching the first and last IDs of the resource IDs at the AZ end. That is, the connection relationship of pipeline segments can realize the construction of the complete pipeline segment topology by matching the starting resource ID and the ending resource ID. Similarly, the topology within a single domain of pole segment, wall-mounted segment, and direct-buried segment can also be obtained by matching the first and last IDs to construct the complete pole segment and wall-mounted segment topology.

[0105] Based on the correlation analysis, pipeline point resources such as manholes, utility poles, and wall mounting points are all AZ endpoints of pipeline segments / pole segments / wall mounting segments. Therefore, latitude and longitude information is used to perform graph association with the pipeline topology. At the same time, different types of pipeline topologies (referring to pipelines, wall mountings, pole lines, direct burial, etc.) can also be graph-associated through pipeline point resources, ultimately obtaining a transmission external topology map that includes complete pipelines, wall mountings, and pole lines.

[0106] Specifically, pipeline segment resources of the same type are associated and matched according to the resource ID at the AZ end to construct the first pipeline topology map corresponding to each type of pipeline segment resource. For example Figure 3 In the example, pipe segment 1 and pipe segment 2 are connected. Therefore, the topology between pipe segment 1 and pipe segment 2 can be constructed by matching the ending resource ID of pipe segment 1 with the starting resource ID of pipe segment 2. Through this association matching method, a complete pipeline topology map can be constructed, which is the first pipeline topology map corresponding to the pipe segment. Similarly, the complete topology map of wall-mounted and pole-mounted lines can be obtained.

[0107] Furthermore, a graph association is established between the pipeline topology map corresponding to each type of pipeline segment resource and the latitude and longitude of pipeline point resources of the same type, thus constructing a second fiber optic topology map corresponding to each type of pipeline segment resource. For example... Figure 3 In this context, manholes and pipeline segments both belong to the pipeline system category. Manholes serve as the A or Z end between pipeline segments. Therefore, manholes and pipeline segments can be associated through latitude and longitude information. By associating manholes in the topology between pipeline segment 1 and pipeline segment 2, a complete pipeline topology map with point resources can be constructed, which is the second pipeline topology map corresponding to the pipeline segment.

[0108] Furthermore, based on the latitude and longitude of each type of pipeline point resource, the second pipeline topology maps corresponding to different types of pipeline segment resources are linked together to construct a transmission resource network topology map. For example... Figure 3 In this process, the latitude and longitude of manholes / electric poles / wall-mounted points are associated with the latitude and longitude of the AZ ends of different types of pipeline segment resources. This allows the second pipeline topology maps corresponding to different types of pipeline segment resources to be linked together, thus constructing a cross-category transmission resource network topology map.

[0109] In one embodiment, combined with Figure 4 , Figure 4 This is a visual schematic diagram of a partial transmission resource network topology provided by the present invention. Taking a pilot area as an example, after necessary data cleaning, the partial transmission resource network topology diagram constructed through topology association is visualized as follows. Figure 4 As shown, Figure 4 In the diagram, blue lines represent pipe sections, purple lines represent pole sections, green lines represent wall-mounted sections, blue bubbles represent optical distribution boxes, pink circles represent optical fiber distribution boxes, and red bubbles represent user installation points.

[0110] This embodiment introduces the basic capabilities of Geographic Information System (GIS) mapping, integrating cloud GIS map basic data retrieval, resource presentation, layer control, and other visualization capabilities (including road network and basic map information presentation). It visualizes the collected external transmission resource data and generated route planning schemes, supporting clicking on resource icons such as pipelines and optical distribution boxes on the map. Information card pop-ups display the resource name of the selected resource, the services already carried, and the remaining resource status. The visualization result of the pipeline is... Figure 4 Displayed on the map.

[0111] This invention, through accessing external transmission resource data from an existing resource management system, constructs a cross-category transmission resource network topology map. This map enables end-to-end planning of dedicated line services, ensuring that the selected resources better meet the needs of dedicated line services and improving the rationality and accuracy of dedicated line access path planning.

[0112] In some embodiments, based on step 103, determining the target area network topology map of the user construction site based on the transmission resource network topology map includes:

[0113] Perform a resource quality assessment on each leased access point to obtain the remaining available resources for each leased access point;

[0114] Based on the remaining available resources of each leased access point, multiple available access points that meet the current resource requirements are selected from the multiple leased access points.

[0115] Calculate the first straight-line distance between each available access point and the user's construction point;

[0116] The available access points corresponding to the first n minimum first straight-line distances are determined as the nearest access points to the user's construction site;

[0117] The area radius is determined by a preset multiple of the first straight-line distance corresponding to the farthest neighboring access point.

[0118] Using the user construction site as the center, an initial regional network topology map of the user construction site is constructed based on the region radius;

[0119] Based on the initial regional network topology map, the target regional network topology map of the user's construction site is determined.

[0120] It should be noted that, to achieve more precise resource selection, in addition to considering the distance between the external transmission line resource data and the user's construction site, a quantitative assessment of resource quality should also be conducted to achieve more reasonable path planning. In leased line access services, the external transmission line resource data involved mainly concerns the utilization rate of the leased line access point. Therefore, resource utilization rate is used as an indicator for resource quality assessment. Among planned routes with similar paths, pipelines with lower resource utilization rates and access optical / optical splitting equipment are selected to reduce the likelihood of insufficient available resources to support the current service.

[0121] Furthermore, since this type of data is a "dumb resource," relying on manual on-site collection, it cannot be updated in real time. Therefore, historical operational data is used to estimate the current resource utilization, and optimal access roadbed planning is performed based on the predicted resource status to improve planning accuracy.

[0122] For real-time estimation of resource utilization, a method based on Extreme Gradient Boosting Regression Trees (XGBoost) is employed to estimate the real-time resource status. XGBoost is a machine learning algorithm based on Gradient Boosted Decision Trees (GBDT), which improves the model's predictions by iteratively adding new decision trees. In each iteration, XGBoost calculates the residuals of the current model and then constructs a new decision tree to fit these residuals, thereby gradually reducing prediction errors. To improve the model's generalization ability, XGBoost incorporates a regularization term into the loss function to control model complexity and prevent overfitting. In the actual training process, resource utilization is normalized, resource changes are used as labels, and the time span of resource changes is used as input. XGBoost is used to train a model that compares the time span with resource changes, fitting the correlation between the two to obtain F(t).

[0123] Specifically, the time of acquiring external resource data is obtained, and the current time is also obtained. The difference between the current time and the time of data acquisition is calculated to obtain the time span. This time span is then input into the already trained XGBoost model to obtain the resource changes at the current time, i.e., F(t). now -t0), where t nowLet t0 represent the current time, and t0 represent the time when data was collected. Further, the resource utilization of each dedicated line access point at time t0 is summed with the currently identified resource changes to obtain the resource utilization of each dedicated line access point at the current time, i.e., R. now =F(t now -t0)+R0, where R now Indicates t now The resource utilization status at time t0 is represented by R0, which improves the accuracy of obtaining resource status.

[0124] Furthermore, based on the resource utilization of each leased line access point, the remaining available resources of each leased line access point are determined. Based on the remaining available resources of each leased line access point, multiple available access points that meet the current resource requirements are selected from among the multiple leased line access points.

[0125] After selecting available access points with resources exceeding the project's requirements based on remaining resource results, intelligent leased line access path planning will be performed through regional search, which can be combined with... Figure 5 , Figure 5 This is a schematic diagram of the process for planning dedicated line access paths based on regional search provided by the present invention.

[0126] Based on the principle of prioritizing straight-line distance, the first straight-line distance between each available access point and the user's construction point is calculated. It should be noted that the distance calculation is performed by straight-line calculation using the latitude and longitude coordinates of both.

[0127] Furthermore, multiple first straight-line distances are compared numerically, and the top n smallest first straight-line distances are selected based on the comparison results. n is set according to the actual situation, and the available access points corresponding to the top n smallest first straight-line distances are determined as the nearest access points to the user's construction site. This method is to avoid the nearest available access point not being the optimal one on the pipeline map. Multiple available access points are selected as nearest access points to reduce such situations.

[0128] Furthermore, the area radius is determined by a preset multiple of the first straight-line distance corresponding to the farthest neighboring access point. The preset multiple is set according to the actual situation, and 1.5 times the farthest first straight-line distance can be selected as the area radius of the selected area.

[0129] Furthermore, an initial regional network topology map of the user's construction site is constructed based on the regional radius, with the user's construction site as the center.

[0130] Furthermore, based on the initial regional network topology map, the target regional network topology map for the user's construction site is determined.

[0131] This invention first assesses the resource quality of leased line access points. Based on the remaining available resources of the leased line access points, it filters out multiple available access points that meet the current resource requirements. Then, it filters out neighboring access points with the shortest distance as the objective. Centered on the user's construction site, it selects an initial regional network topology map that includes at least all neighboring access points. This map represents a portion of the topology in the transmission resource network topology map. Path planning is then performed based on this portion of the topology, greatly reducing the amount of computation. Furthermore, the resources within the selected area better meet the needs of leased line services, improving the efficiency of leased line access path planning while ensuring accuracy.

[0132] Based on the above steps, determining the target area network topology map of the user's construction site based on the initial area network topology map includes:

[0133] Calculate the second straight-line distance of each pipeline point resource within the initial regional network topology;

[0134] The pipeline point resources corresponding to the first m minimum second straight-line distances are determined as the adjacent pipeline point resources of the user's construction site;

[0135] Based on the road network planning capabilities of the geographic information system, the path from the user's construction site to each adjacent pipeline resource point is planned;

[0136] Each path is connected to the initial area network topology as a virtual pipeline;

[0137] In the initial area network topology map after splicing, each adjacent pipeline point resource is connected to the target virtual access point in a virtual connection manner to obtain the target area network topology map of the user construction point.

[0138] Specifically, calculate the second straight-line distance of each pipeline point resource within the initial regional network topology graph.

[0139] Furthermore, the numerical values ​​of the second straight-line distances will be compared, and the top m smallest second straight-line distances will be selected based on the comparison results. The pipeline point resources corresponding to the top m smallest second straight-line distances will be determined as the adjacent pipeline point resources of the user's construction point.

[0140] Furthermore, based on GIS road network planning capabilities, the path from the user's construction point to each adjacent pipeline resource is planned, and each path is spliced ​​into the initial regional network topology map in the form of virtual pipelines, thereby constructing a pipeline topology from the user's construction point (one) to m adjacent pipeline resources (many).

[0141] Furthermore, in order to simplify the one-to-many path planning problem to a one-to-one problem, in the spliced ​​initial regional network topology map, each adjacent pipeline point resource is connected to the target virtual access point in a virtual connection manner to obtain the target regional network topology map of the user's construction point.

[0142] After selecting the target area network topology map from the user's construction site, the intelligent leased line access path planning algorithm can be used to output the end-to-end leased line access path. Then, based on the cost template, the cost quotation of the end-to-end leased line access path can be intelligently calculated.

[0143] This invention selects nearby pipeline resources based on the shortest distance as the objective. Combining the existing GIS road network planning capabilities, it plans the path between the user's construction site and nearby pipeline resources. This path is then stitched into the initial regional network topology map as a virtual pipeline. Furthermore, to simplify the one-to-many path planning problem to a one-to-one problem, virtual connections are used to connect all nearby pipeline resources to the target virtual access point. Finally, the target regional network topology map is constructed, enabling intelligent end-to-end path planning from the user's construction site to the target virtual access point. This significantly reduces the computational load, and the resources within the selected area better meet the needs of dedicated line services. This improves the efficiency of dedicated line access path planning while ensuring accuracy.

[0144] In some embodiments, based on step 104, the step of planning the dedicated line access path based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site includes:

[0145] If there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined.

[0146] The sub-network topology map where the user's construction point is located is determined as the sub-topology to be searched, and the user's construction point is determined as the path starting point of the sub-topology to be searched;

[0147] Determine whether the target virtual access point is contained in the sub-topology to be searched;

[0148] If the target virtual access point is not included in the sub-topology to be searched, then calculate the third straight-line distance between each pipeline point resource in the sub-topology to be searched and the user construction point, and the fourth straight-line distance between each pipeline point resource in the sub-topology to be searched and the target virtual access point.

[0149] The distance cost of each pipeline point resource is obtained by weighted summing of the third and fourth straight-line distances corresponding to each pipeline point resource.

[0150] The pipeline point resource corresponding to the minimum distance cost is determined as the path termination point of the sub-topology to be searched;

[0151] The remaining subnetwork topology graph that is closest to the path termination point is searched using the shortest distance method; the remaining subnetwork topology graph is the subnetwork topology graph of the plurality of subnetwork topology graphs excluding those that are divided into subnetworks to be searched.

[0152] In the nearest remaining subnetwork topology graph, search for the pipeline point resource closest to the path termination point using the shortest distance;

[0153] Update the nearest remaining sub-network topology to the sub-topology to be searched, and update the nearest pipeline point resource to the path start point of the sub-topology to be searched;

[0154] The process iteratively executes the step of determining whether the target virtual access point is contained in the sub-topology to be searched until the target virtual access point is contained in the sub-topology to be searched. The target virtual access point is determined as the path termination point of the current sub-topology to be searched. The optimal path between the path start point and the path termination point in each sub-network topology is calculated, and the new pipeline path between each optimal path is calculated. The optimal paths and the new pipeline paths are spliced ​​together to obtain the first optimal dedicated line access path between the user construction point and the target virtual access point.

[0155] It should be noted that due to incomplete construction or inadequate asset management of existing pipeline resources, there may be local subgraphs that are not connected to other pipelines. To address the path planning problem when there are no connected pipelines and to recommend new pipeline paths for areas currently without pipeline connections, a multi-subgraph path planning algorithm based on segmented heuristic intelligent path planning is proposed, referencing the Astar heuristic algorithm. This algorithm can be combined with... Figure 6 , Figure 6 This is a flowchart illustrating the multi-subgraph path planning provided by the present invention.

[0156] Based on the experience of construction teams and the analysis of past project plans, fiber optic cable laying for missing pipeline sections typically involves wall mounting along roads or direct burial, connecting to the nearest pipeline resource point. Therefore, the system utilizes GIS path navigation capabilities and plans the laying route for missing pipeline sections according to the actual road network, which is more in line with actual construction methods. Compared to traditional design scenarios that use straight-line distances or Manhattan distance estimations from construction points to resource points, this approach provides a more accurate estimate of the fiber optic cable laying length.

[0157] Specifically, if there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined.

[0158] Furthermore, the sub-network topology where the user's construction point is located is determined as the sub-topology to be searched, and the user's construction point is determined as the starting point of the path in the sub-topology to be searched.

[0159] Further, determine whether the target virtual access point is contained in the sub-topology to be searched.

[0160] If the sub-topology to be searched contains the target virtual access point, the Dijkstra algorithm is used to calculate the optimal path between the user's construction point and the target virtual access point, and this path is determined as the first optimal leased line access path between the user's construction point and the target virtual access point.

[0161] If the sub-topology to be searched contains the target virtual access point, then calculate the third straight-line distance between each pipeline point resource in the sub-topology to be searched and the user construction point, and the fourth straight-line distance between each pipeline point resource in the sub-topology to be searched and the target virtual access point.

[0162] Furthermore, the third and fourth straight-line distances corresponding to each pipeline point resource are weighted and summed to obtain the distance cost of each pipeline point resource.

[0163] In one embodiment, the formula for calculating the distance cost of a pipeline point resource is as follows:

[0164]

[0165] in, The third straight-line distance between the pipeline point resource and the user's construction point; The fourth straight-line distance represents the distance between the pipeline point resource and the target virtual access point; a and b are preset weight values ​​that can be set according to the actual situation.

[0166] Furthermore, the pipeline point resource corresponding to the minimum distance cost is determined as the path termination point of the sub-topology to be searched. After the path termination point of the sub-topology to be searched is selected, the current sub-topology to be searched is marked as "searched" to prevent the generation of loop paths.

[0167] Furthermore, the remaining subnetwork topology graph closest to the path termination point is searched using the shortest distance method. Here, the remaining subnetwork topology graph refers to the subnetwork topology graph among multiple subnetwork topology graphs, excluding those that are divided into subnetwork topologies to be searched.

[0168] Furthermore, in the most recent remaining subnetwork topology graph, search for the pipeline point resource closest to the path termination point using the shortest distance.

[0169] Furthermore, the most recent remaining sub-network topology is updated to the sub-topology to be searched, and the most recent pipeline point resource is updated to the path start point of the sub-topology to be searched.

[0170] Further, the step of determining whether the target virtual access point is contained in the sub-topology to be searched is iteratively executed until the target virtual access point is contained in the sub-topology to be searched. The target virtual access point is determined as the path termination point of the current sub-topology to be searched. The Dijkstra algorithm is used to calculate the optimal path between the path start point and the path termination point in each sub-network topology graph. Since there are pipeline paths that cannot be connected between the optimal paths, the operation of adding pipeline paths is involved. Therefore, the GIS map navigation capability is used to generate the corresponding paths along the road network to obtain the new pipeline paths between each optimal path. Finally, the optimal paths and the new pipeline paths between each optimal path are spliced ​​together to obtain the first optimal dedicated line access path between the user's construction point and the target virtual access point.

[0171] The end-to-end leased line access path scheme generated based on the multi-subgraph path planning algorithm includes information on the reused transmission pipelines and resource points, and can also play a positive auxiliary reference role in the subsequent leased line construction drawing and on-site construction.

[0172] This invention addresses non-connected pipeline areas by using the shortest straight-line distance as a heuristic value to search for the optimal path termination point within a subgraph and the path start point of the next subgraph. This generates the shortest pipeline path from the path start point to the path termination point in each subgraph. Furthermore, for non-connected paths, the invention utilizes GIS map navigation capabilities to generate corresponding new pipeline paths along the road network. The shortest pipeline paths in each subgraph are then combined with the new pipeline paths between subgraphs, enabling dedicated line access path planning and new pipeline recommendation in non-connected areas. This enhances the flexibility and adaptability of dedicated line access path planning.

[0173] In some embodiments, based on step 104, the step of planning the dedicated line access path based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site further includes:

[0174] If there is a connected pipeline path in the target area network topology map, then the user construction point, the target area network topology map and the target virtual access point are input into the optimal path planning model to obtain the second optimal dedicated line access path between the user construction point and the target virtual access point output by the optimal path planning model;

[0175] The optimal path planning model is built using a deep learning network architecture that combines the Deep Deterministic Policy Gradient (DDPG) algorithm with a message-passing neural network.

[0176] It should be noted that the main goal of leased line access path planning is to find the shortest path to reduce the cost of fiber optic cable laying. Therefore, the goal of this path optimization problem is to minimize the path distance, and the available resources of the pipeline and the leased line access point are greater than the project requirements.

[0177] For intelligent path planning in a target area network topology where there are connected pipeline paths, a path planning method based on message passing network is adopted to plan the pipeline paths in the connected area.

[0178] The transmission resource network topology is a standard graph topology structure. Nodes represent pipeline resources such as manholes, utility poles, and wall mounts, while edges represent pipeline segments such as pipe sections, pole sections, and wall mounts. However, due to the complexity of the pipeline resources involved, even with timely region filtering, hundreds of nodes still exist within the selected area. Traditional optimal path search methods, such as Dijkstra's algorithm, have a time cost of [insert time cost here]. As the number of nodes increases, search efficiency decreases significantly.

[0179] To improve the efficiency of path search and comprehensively consider pipeline quality and distance to achieve more reasonable and reliable path planning, conventional reinforcement learning methods can only consider the distance between nodes in the pipeline, failing to fully utilize network topology features. Graph convolutional networks are typically used to handle graph topologies, but they rely on a large amount of historical path planning data, resulting in high training costs. Therefore, this study combines a message-passing network based on graph neural networks with deep reinforcement learning to analyze the optimal path planning scheme from a full graph perspective.

[0180] Specifically, if there are connected pipeline paths in the target area network topology map, the user construction point (as the starting point of the path), the target area network topology map, and the target virtual access point (as the ending point of the path) are input into the optimal path planning model to obtain the second optimal dedicated line access path between the user construction point and the target virtual access point output by the optimal path planning model.

[0181] The optimal path planning model is built using a deep learning network architecture that combines the Deep Deterministic Policy Gradient (DDPG) algorithm with a message-passing neural network.

[0182] In the model built using a deep learning network architecture combining the DDPG algorithm and a message-passing neural network, the state space, action space, and reward function in the overall reinforcement learning are first defined.

[0183] State space: The state of the topology is defined based on the pipeline characteristics in the target area network topology diagram. The state space corresponds to the input layer data of the neural network, including the initial pipeline characteristics of the input network topology, user construction points, dedicated line access points and the required number of optical fibers, {src, dst, bw}.

[0184] Action Space: Actions are defined as calculating the weighted shortest path for pipeline laying based on the weight of each edge in the target region network topology graph output by the neural network output layer.

[0185] Reward Function: Since the goal is to find the shortest path, the reward function is set to the shortest path cost. If a constraint is violated during action execution, the environment will feed back a large negative value as a penalty to the DRL Agent; if all constraints are satisfied, the penalty is 0.

[0186] DDPG was chosen as the reinforcement learning model here, based on [reference]. Figure 7 , Figure 7 This is a schematic diagram of the framework for leased line access path planning based on reinforcement learning provided by this invention. To accelerate model training, DDPG essentially borrows from the Deep Q-Network (DQN) algorithm, which uses an experience buffer and two sets of neural networks with identical structures but different update frequencies. The experience replay buffer stores sample data during training; by periodically incorporating this historical sample data into the learning process, better learning results can be achieved. Based on this, DDPG is based on the Actor-Critic framework: the Actor network interacts with the environment, generating deterministic policies based on the input state, while the Critic network's policies are evaluated and scored to guide the Actor network's optimization and updates. Simultaneously, to aggregate information from all topologies within the region to make optimal decisions, the Actor network utilizes a message-passing neural network to extract pipeline topology information.

[0187] Message Passing Neural Network (MPNN) is a variant of Graph Neural Network that uses an iterative message passing algorithm to pass information between graph nodes as a basic Graph Neural Network (GNN) structure. The message passing process is repeated t times. Each node v receives its hidden state after t message exchanges from its neighboring nodes i (i∈N(v)), and processes it using a message function M combined with the node's hidden state h. Then, these hidden states are concatenated using an aggregation function. Next, an update function u is used to compute a new hidden state f for each node based on the previous hidden state and the aggregated messages. Finally, after multiple iterations of message passing steps, a readout function R can predict the features of the entire graph or the attributes of individual nodes. Figure 8 As shown, Figure 8 This is a schematic diagram of the message passing network provided by the present invention.

[0188] Nodes exchange information represented as vectors during message passing, then encode this information as hidden states. After multiple iterations, each node gains information about the entire network. The neural network learns more about the network state through message passing. In the Actor network, the features of each edge in the input topology are used, and after iterative message passing, the final model outputs the optimal edge weights that fit the pipeline topology and state.

[0189] Finally, based on the selected start and end nodes, and using the weights of each edge in the topology output by the Actor network, the edge with the larger weight is selected at each pipeline node as the pipeline to be constructed in the next step, thus completing the construction of the leased line access path.

[0190] This invention proposes a pipeline topology path planning method based on reinforcement learning and message passing networks for connected pipeline areas. It does not rely on historical pipeline planning paths, but searches for the optimal planning path, which significantly reduces time complexity and improves the flexibility and accuracy of dedicated line access path planning.

[0191] In some embodiments, after planning the leased line access path based on the target area network topology map to obtain the optimal leased line access path for the user's construction site, the method further includes:

[0192] Determine the overall pipeline laying cost of the optimal dedicated line access path, the equipment cost required for the dedicated line access service, and the construction cost required for the dedicated line access service;

[0193] The total pipeline laying cost, the equipment cost, and the construction cost are summed to obtain the cost quotation for the dedicated line access service.

[0194] It should be noted that after completing the intelligent leased line access path planning by reusing existing network resources, at the business capability layer, by opening up interfaces for optimal access point recommendation and intelligent path planning, multiple available resource points and multiple feasible paths are recommended (in addition to the optimal leased line access path planned above, multiple suboptimal leased line access paths can also be calculated), providing on-site construction personnel with reference for actual construction. Furthermore, the numerical leased line access path cost quotation is a key application for empowering frontline personnel and reducing the pre-sales survey cycle.

[0195] Considering the differences in fiber optic cable materials, construction costs, and equipment installation and commissioning costs across different cities and projects, a universal cost quotation template has been designed to create a widely applicable tool for quickly estimating the cost of leased line access paths. This template combines past project quotation lists and EMO order fields, and includes three parts: pipeline / fiber optic costs, equipment costs, and construction costs. This template can be used as a reference. Figure 9 , Figure 9 This is a schematic diagram of the cost quotation template provided by the present invention.

[0196] Specifically, this involves determining the overall cost of laying pipelines / fiber optic cables for the optimal leased line access path, the equipment costs required for the leased line access service, and the construction costs required for the leased line access service.

[0197] The cost of laying pipelines / fiber optic cables is divided into two parts depending on whether new pipelines are needed: For areas requiring new pipelines, the required type of access pipeline is manually determined, and the special construction cost for the access terminal is calculated based on the laying length and construction specifications; for areas with existing pipelines, the laying cost is calculated based on the pipeline length and different pipeline types. Therefore, when new pipelines are needed, the total cost of laying pipelines / fiber optic cables is the sum of the special construction cost for the new pipelines and the laying cost for areas with existing pipelines; when no new pipelines are needed, the total cost of laying pipelines / fiber optic cables is only the laying cost for areas with existing pipelines.

[0198] Equipment cost refers to the additional optical network terminals, terminals, etc. required for leased line access services. First, the tool pre-sets some commonly used equipment models and costs for front-line personnel to make standardized selections. In addition, it also provides custom parameters, which front-line personnel can flexibly configure as new equipment according to their needs and determine their respective cost items.

[0199] The calculation of construction cost refers to the labor cost required to complete the dedicated line access service. To simplify the algorithm process, by analyzing past construction cases, the construction cost item is estimated on average based on the construction length and normalized to "construction price / meter". Therefore, the construction cost can be estimated based only on the construction length of the current period.

[0200] Furthermore, by summing up the overall pipeline laying cost, equipment cost, and construction cost, a cost quote for the dedicated line access service can be obtained.

[0201] This invention provides a pre-survey cost quotation template, which incorporates past dedicated line pre-survey quotation methods and combines planned routes to achieve automatic cost calculation for some costs, significantly reducing the pre-sales quotation cycle for dedicated lines and improving work efficiency. In addition, by using external transmission resource data to construct multi-category transmission resource network topology maps, it is possible to accurately calculate the length of optical fiber required to lay from the actual pipeline, thereby making cost estimation more accurate.

[0202] The leased line access path planning device provided by the present invention is described below. The leased line access path planning device described below and the leased line access path planning method described above can be referred to in correspondence.

[0203] Reference Figure 10 , Figure 10 This is a schematic diagram of the dedicated line access path planning device provided by the present invention.

[0204] The dedicated line access path planning device includes:

[0205] The acquisition module 1010 is used to acquire external transmission resource data and user construction points.

[0206] The topology construction module 1020 is used to construct a transmission resource network topology map based on the transmission external resource data.

[0207] The determination module 1030 is used to determine the target area network topology map of the user construction site based on the transmission resource network topology map.

[0208] The dedicated line access path planning module 1040 is used to plan dedicated line access paths based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site; the optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map.

[0209] The leased line access path planning device provided by this invention acquires existing external transmission resource data, constructs a transmission resource network topology map, and delineates the target area network topology map according to the required user construction points. It comprehensively considers the possibility of connectivity and disconnection in the path search area of ​​the target area network topology map, and performs comprehensive planning of leased line access paths according to different situations, thereby improving the accuracy of path planning. Furthermore, it reuses existing resources for pipeline deployment, and the selected resources are more in line with the needs of leased line services, enabling more accurate and cost-effective end-to-end planning of leased line services, thus improving the overall efficiency of leased line access path planning.

[0210] Furthermore, the topology building module 1020 is also used for:

[0211] Pipeline segment resources of the same type are associated and matched according to the resource identifiers at the AZ end to construct the first pipeline topology map corresponding to each type of pipeline segment resource;

[0212] By graph association between the pipeline topology map corresponding to each type of pipeline segment resource and the latitude and longitude of the pipeline point resource of the same type, a second pipeline topology map corresponding to each type of pipeline segment resource is constructed.

[0213] Based on the latitude and longitude of each type of pipeline point resource, the second pipeline topology maps corresponding to different types of pipeline segment resources are graph-associated to construct a transmission resource network topology map.

[0214] Furthermore, the determining module 1030 is also used for:

[0215] Perform a resource quality assessment on each leased access point to obtain the remaining available resources for each leased access point;

[0216] Based on the remaining available resources of each leased access point, multiple available access points that meet the current resource requirements are selected from the multiple leased access points.

[0217] Calculate the first straight-line distance between each available access point and the user's construction point;

[0218] The available access points corresponding to the first n minimum first straight-line distances are determined as the nearest access points to the user's construction site;

[0219] The area radius is determined by a preset multiple of the first straight-line distance corresponding to the farthest neighboring access point.

[0220] Using the user construction site as the center, an initial regional network topology map of the user construction site is constructed based on the region radius;

[0221] Based on the initial regional network topology map, the target regional network topology map of the user's construction site is determined.

[0222] Furthermore, the determining module 1030 is also used for:

[0223] Calculate the second straight-line distance of each pipeline point resource within the initial regional network topology;

[0224] The pipeline point resources corresponding to the first m minimum second straight-line distances are determined as the adjacent pipeline point resources of the user's construction site;

[0225] Based on the road network planning capabilities of the geographic information system, the path from the user's construction site to each adjacent pipeline resource point is planned;

[0226] Each path is connected to the initial area network topology as a virtual pipeline;

[0227] In the initial area network topology map after splicing, each adjacent pipeline point resource is connected to the target virtual access point in a virtual connection manner to obtain the target area network topology map of the user construction point.

[0228] Furthermore, the dedicated line access path planning module 1040 is also used for:

[0229] If there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined.

[0230] The sub-network topology map where the user's construction point is located is determined as the sub-topology to be searched, and the user's construction point is determined as the path starting point of the sub-topology to be searched;

[0231] Determine whether the target virtual access point is contained in the sub-topology to be searched;

[0232] If the target virtual access point is not included in the sub-topology to be searched, then calculate the third straight-line distance between each pipeline point resource in the sub-topology to be searched and the user construction point, and the fourth straight-line distance between each pipeline point resource in the sub-topology to be searched and the target virtual access point.

[0233] The distance cost of each pipeline point resource is obtained by weighted summing of the third and fourth straight-line distances corresponding to each pipeline point resource.

[0234] The pipeline point resource corresponding to the minimum distance cost is determined as the path termination point of the sub-topology to be searched;

[0235] The remaining subnetwork topology graph that is closest to the path termination point is searched using the shortest distance method; the remaining subnetwork topology graph is the subnetwork topology graph of the plurality of subnetwork topology graphs excluding those that are divided into subnetworks to be searched.

[0236] In the nearest remaining subnetwork topology graph, search for the pipeline point resource closest to the path termination point using the shortest distance;

[0237] Update the nearest remaining sub-network topology to the sub-topology to be searched, and update the nearest pipeline point resource to the path start point of the sub-topology to be searched;

[0238] The process iteratively executes the step of determining whether the target virtual access point is contained in the sub-topology to be searched until the target virtual access point is contained in the sub-topology to be searched. The target virtual access point is determined as the path termination point of the current sub-topology to be searched. The optimal path between the path start point and the path termination point in each sub-network topology is calculated, and the new pipeline path between each optimal path is calculated. The optimal paths and the new pipeline paths are spliced ​​together to obtain the first optimal dedicated line access path between the user construction point and the target virtual access point.

[0239] Furthermore, the dedicated line access path planning module 1040 is also used for:

[0240] If there is a connected pipeline path in the target area network topology map, then the user construction point, the target area network topology map and the target virtual access point are input into the optimal path planning model to obtain the second optimal dedicated line access path between the user construction point and the target virtual access point output by the optimal path planning model;

[0241] The optimal path planning model is built using a deep learning network architecture that combines the Deep Deterministic Policy Gradient (DDPG) algorithm with a message-passing neural network.

[0242] Furthermore, the dedicated line access path planning device is also used for:

[0243] Determine the overall pipeline laying cost of the optimal dedicated line access path, the equipment cost required for the dedicated line access service, and the construction cost required for the dedicated line access service;

[0244] The total pipeline laying cost, the equipment cost, and the construction cost are summed to obtain the cost quotation for the dedicated line access service.

[0245] It should be noted that the leased line access path planning device provided by the present invention can execute the leased line access path planning method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0246] Figure 11 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 11As shown, the electronic device may include: a processor 1110, a communications interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communications interface 1120, and the memory 1130 communicate with each other through the communication bus 1140. The processor 1110 can call logical instructions in the memory 1130 to execute a dedicated line access path planning method, which includes: acquiring transmission external line resource data and user construction points; constructing a transmission resource network topology map based on the transmission external line resource data; determining a target area network topology map for the user construction points based on the transmission resource network topology map; and performing dedicated line access path planning based on the target area network topology map to obtain the optimal dedicated line access path for the user construction points. The optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map.

[0247] Furthermore, the logical instructions in the aforementioned memory 1130 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0248] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the leased line access path planning method provided in the above embodiments, the method comprising: acquiring transmission external line resource data and user construction site locations; constructing a transmission resource network topology map based on the transmission external line resource data; determining a target area network topology map of the user construction site based on the transmission resource network topology map; performing leased line access path planning based on the target area network topology map to obtain an optimal leased line access path for the user construction site; the optimal leased line access path includes a first optimal leased line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal leased line access path obtained when there are connected pipeline paths in the target area network topology map.

[0249] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the leased line access path planning method provided in the above embodiments. The method includes: acquiring external transmission resource data and user construction sites; constructing a transmission resource network topology map based on the external transmission resource data; determining a target area network topology map for the user construction sites based on the transmission resource network topology map; and performing leased line access path planning based on the target area network topology map to obtain an optimal leased line access path for the user construction sites. The optimal leased line access path includes a first optimal leased line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal leased line access path obtained when there are connected pipeline paths in the target area network topology map.

[0250] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0251] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0252] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A leased line access path planning method, characterized in that, include: Acquire external transmission resource data and user construction site locations; Based on the aforementioned external transmission resource data, a transmission resource network topology diagram is constructed; Based on the transmission resource network topology map, the target area network topology map of the user construction site is determined; Based on the target area network topology map, the dedicated line access path is automatically planned to obtain the optimal dedicated line access path for the user's construction site; the optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map. The first optimal leased line access path is obtained in the following way: If there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined. Using the shortest straight-line distance as a heuristic, the optimal path termination point within the sub-network topology and the path start point of the next sub-network topology are searched to generate the optimal path from the path start point to the path termination point in each sub-network topology. Calculate the new pipeline path between each optimal path, and then splice the optimal paths and the new pipeline path to obtain the first optimal dedicated line access path between the user construction point and the target virtual access point.

2. The leased line access path planning method according to claim 1, characterized in that, The transmitted external line resource data includes various types of pipeline segment resources and pipeline point resources; The step of constructing a transmission resource network topology map based on the transmission external line resource data includes: Pipeline segment resources of the same type are associated and matched according to the resource identifiers at the AZ end to construct the first pipeline topology map corresponding to each type of pipeline segment resource; By graph association between the pipeline topology map corresponding to each type of pipeline segment resource and the latitude and longitude of the pipeline point resource of the same type, a second pipeline topology map corresponding to each type of pipeline segment resource is constructed. Based on the latitude and longitude of each type of pipeline point resource, the second pipeline topology maps corresponding to different types of pipeline segment resources are graph-associated to construct a transmission resource network topology map.

3. The leased line access path planning method according to claim 2, characterized in that, The transmitted external line resource data also includes multiple dedicated line access points; the determination of the target area network topology map of the user construction site based on the transmitted resource network topology map includes: Perform a resource quality assessment on each leased access point to obtain the remaining available resources for each leased access point; Based on the remaining available resources of each leased access point, multiple available access points that meet the current resource requirements are selected from the multiple leased access points. Calculate the first straight-line distance between each available access point and the user's construction point; The available access points corresponding to the first n minimum first straight-line distances are determined as the nearest access points to the user's construction site; The area radius is determined by a preset multiple of the first straight-line distance corresponding to the farthest neighboring access point. Using the user construction site as the center, an initial regional network topology map of the user construction site is constructed based on the region radius; Based on the initial regional network topology map, the target regional network topology map of the user's construction site is determined.

4. The leased line access path planning method according to claim 3, characterized in that, The step of determining the target area network topology map for the user's construction site based on the initial area network topology map includes: Calculate the second straight-line distance of each pipeline point resource within the initial regional network topology; The pipeline point resources corresponding to the first m minimum second straight-line distances are determined as the adjacent pipeline point resources of the user's construction site; Based on the road network planning capabilities of the geographic information system, the path from the user's construction site to each adjacent pipeline resource point is planned; Each path is connected to the initial area network topology as a virtual pipeline; In the initial area network topology map after splicing, each adjacent pipeline point resource is connected to the target virtual access point in a virtual connection manner to obtain the target area network topology map of the user construction point.

5. The leased line access path planning method according to claim 4, characterized in that, The automatic dedicated line access path planning based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site includes: The sub-network topology map where the user's construction point is located is determined as the sub-topology to be searched, and the user's construction point is determined as the path starting point of the sub-topology to be searched; Determine whether the target virtual access point is contained in the sub-topology to be searched; If the target virtual access point is not included in the sub-topology to be searched, then calculate the third straight-line distance between each pipeline point resource in the sub-topology to be searched and the user construction point, and the fourth straight-line distance between each pipeline point resource in the sub-topology to be searched and the target virtual access point. The distance cost of each pipeline point resource is obtained by weighted summing of the third and fourth straight-line distances corresponding to each pipeline point resource. The pipeline point resource corresponding to the minimum distance cost is determined as the path termination point of the sub-topology to be searched; The remaining subnetwork topology graph that is closest to the path termination point is searched using the shortest distance method; the remaining subnetwork topology graph is the subnetwork topology graph of the plurality of subnetwork topology graphs excluding those that are divided into subnetworks to be searched. In the nearest remaining subnetwork topology graph, search for the pipeline point resource closest to the path termination point using the shortest distance; Update the nearest remaining sub-network topology to the sub-topology to be searched, and update the nearest pipeline point resource to the path start point of the sub-topology to be searched; The process iteratively executes the step of determining whether the target virtual access point is contained in the sub-topology to be searched until the target virtual access point is contained in the sub-topology to be searched. The target virtual access point is then determined as the path termination point of the current sub-topology to be searched. The optimal path between the path start point and the path termination point in each sub-network topology graph is calculated.

6. The leased line access path planning method according to claim 4, characterized in that, The step of automatically planning dedicated line access paths based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site also includes: If there is a connected pipeline path in the target area network topology map, then the user construction point, the target area network topology map and the target virtual access point are input into the optimal path planning model to obtain the second optimal dedicated line access path between the user construction point and the target virtual access point output by the optimal path planning model; The optimal path planning model is built using a deep learning network architecture that combines the Deep Deterministic Policy Gradient (DDPG) algorithm with a message-passing neural network.

7. The leased line access path planning method according to any one of claims 1-6, characterized in that, After planning the dedicated line access path based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site, the process further includes: Determine the overall pipeline laying cost of the optimal dedicated line access path, the equipment cost required for the dedicated line access service, and the construction cost required for the dedicated line access service; The total pipeline laying cost, the equipment cost, and the construction cost are summed to obtain the cost quotation for the dedicated line access service.

8. A dedicated line access path planning device, characterized in that, include: The acquisition module is used to acquire external transmission resource data and user construction site locations; The topology construction module is used to construct a transmission resource network topology map based on the transmission external resource data. The determination module is used to determine the target area network topology map of the user's construction site based on the transmission resource network topology map. The dedicated line access path planning module is used to automatically plan dedicated line access paths based on the target area network topology map to obtain the optimal dedicated line access path for the user's construction site; the optimal dedicated line access path includes a first optimal dedicated line access path obtained when there are non-connected pipeline paths in the target area network topology map, and a second optimal dedicated line access path obtained when there are connected pipeline paths in the target area network topology map. The first optimal leased line access path is obtained in the following way: If there are disconnected pipeline paths in the target area network topology graph, then multiple disconnected sub-network topologies in the target area network topology graph are determined. Using the shortest straight-line distance as a heuristic, the optimal path termination point within the sub-network topology and the path start point of the next sub-network topology are searched to generate the optimal path from the path start point to the path termination point in each sub-network topology. Calculate the new pipeline path between each optimal path, and then splice the optimal paths and the new pipeline path to obtain the first optimal dedicated line access path between the user construction point and the target virtual access point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the leased line access path planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, comprising a non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the leased line access path planning method as described in any one of claims 1 to 7.

11. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the leased line access path planning method as described in any one of claims 1 to 7.

Images