Optical cable laying plan generation method, device, equipment and storage medium

Abstract

The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating an optical cable laying plan. The method comprises: processing engineering information to extract road section information; converting the road section information into a feature vector and inputting the feature vector into a laying method decision model to determine the laying method; determining whether to correct the laying method based on feature labels included in the road section information, and obtaining a cost correction coefficient if no correction is required; constructing an objective function and constraint conditions; solving the objective function using a hybrid genetic algorithm to obtain optical fiber information; integrating road section information, laying methods and optical fiber information to generate an optical cable laying plan; the method disclosed in the present application can automatically process engineering information to quickly obtain road section information, significantly shorten the design cycle to several days, reduce manual intervention, and improve planning efficiency; in addition, by constructing feature vectors and decision models, personalized optimization of road section laying is achieved to ensure accurate adaptation of the plan.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating an optical cable laying plan. Background Art

[0002] As a key component of communications network infrastructure, optical cable design must comprehensively consider three core objectives: transmission performance, cost-effectiveness, and environmental adaptability. However, traditional optical cable design methods rely primarily on engineers' experience, typically using unified standards combined with on-site adjustments. This approach has several fundamental problems:

[0003] First, engineers need to conduct field surveys and manually divide road sections during the design process. Due to the lack of quantitative analysis of geographical features such as slope and water distribution, the design cycle often takes weeks or even months, seriously affecting the efficiency and response speed of the project.

[0004] Secondly, traditional methods often use similar design solutions for different road sections, which makes it impossible to achieve personalized optimization for each section; in addition, the process of manually calculating costs and verifying parameters is prone to introduce errors, which can easily lead to multiple rework and adjustments, thereby increasing the complexity and cost of the design.

[0005] Finally, the formulation of routing plans often relies on the personal habits of designers and lacks a data-driven decision-making model. For example, in complex terrains such as mountains, designers may mistakenly choose direct burial, which will make the optical cable vulnerable to geological disasters, thereby increasing maintenance costs and potential network interruption risks.

[0006] It can be seen that the existing technology still needs to be improved and enhanced. Summary of the Invention

[0007] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide a method for generating an optical cable laying plan, which can significantly shorten the design cycle, reduce manual intervention, and improve planning efficiency; and can realize personalized optimization of road section laying to ensure precise adaptation of the laying plan.

[0008] The first aspect of the present invention provides a method for generating an optical cable laying plan, comprising: obtaining engineering information and performing preprocessing to obtain section information, wherein the section information includes multiple independent sections and feature labels corresponding to the independent sections; converting the section information into an input feature vector, and inputting the input feature vector into a pre-built laying method decision model to obtain a laying method output by the laying method decision model; confirming whether the laying method needs to be corrected based on the feature label, and if not, obtaining a cost correction coefficient corresponding to the laying method; constructing an objective function based on the section information, the laying method and the cost correction coefficient, and confirming constraints based on the engineering information, the section information and the laying method; based on the constraints, using a hybrid genetic algorithm to solve the objective function to obtain optical fiber information; integrating the section information, the laying method and the optical fiber information to obtain an optical cable laying plan.

[0009] Optionally, in a first implementation method of the first aspect of the present invention, the engineering information is obtained and preprocessed to obtain section information, and the section information includes multiple independent sections and feature tags corresponding to the independent sections, including: obtaining engineering information, the engineering information includes a starting point, an end point and a planned path connecting the starting point and the end point; calling a map API to obtain the geographical features and population density features of the planned path, the geographical features include slope and water area; segmenting the planned path based on the geographical features to obtain multiple independent sections, and configuring a geographical feature tag for each independent section; configuring an environmental feature tag for each independent section based on the population density feature, and configuring a cost feature tag for each independent section based on the population density feature and the geographical features corresponding to the independent section; the environmental feature tags include urban tags, suburban tags and rural tags, and the cost feature tags include low-budget tags, medium-budget tags and high-budget tags.

[0010] Optionally, in a second implementation method of the first aspect of the present invention, the planned path is segmented based on geographical features to obtain multiple independent sections, and a geographical feature label is configured for each independent section, including: extracting water intervals in the planned path based on geographical features, and calculating the length of each extracted water interval; segmenting the planned path once based on the calculation results to obtain one or more independent water sections and non-water planned paths, and configuring a cross-water label for each independent water section; obtaining a preset window length, and segmenting the non-water planned path twice based on the preset window length and slope to obtain multiple independent non-water sections, and configuring a slope label for each independent non-water section.

[0011] Optionally, in a third implementation method of the first aspect of the present invention, the road section information is converted into an input feature vector, and the input feature vector is input into a pre-built laying mode decision model to obtain the laying mode output by the laying mode decision model, including: numerically encoding the road section information to obtain the input feature vector; pre-building a model based on the XGBoost algorithm and training it to obtain a laying mode decision model; inputting the input feature vector into the laying mode decision model to obtain the laying mode.

[0012] Optionally, in a fourth implementation method of the first aspect of the present invention, the feature tag-based confirmation of whether the laying method needs to be corrected, if not, obtaining a cost correction coefficient corresponding to the laying method, including: judging whether the laying method of the independent road section with the water area label is overhead laying, and judging whether the laying method of the independent road section with the city label is pipeline laying; if the laying methods of the independent road sections with the water area label are all overhead laying and the laying methods of the independent road sections with the city label are all pipeline laying, then it is not necessary to obtain the laying method, and obtain the cost correction coefficient corresponding to the laying method; if there is any independent road section with a water area label whose laying method is not overhead laying, or there is any independent road section with a city label whose laying method is not pipeline laying, then the laying method is corrected, and the cost correction coefficient corresponding to the corrected laying method is obtained.

[0013] Optionally, in a fifth implementation of the first aspect of the present invention, the objective function is constructed based on the section information, the laying method and the cost correction coefficient, and the constraint conditions are confirmed based on the engineering information, the section information and the laying method, including: obtaining the time factor and the cost information corresponding to the laying method, the cost information including the standard production cost per unit length of optical fiber, the basic maintenance cost per unit length of optical fiber and the maintenance cost growth rate; constructing the objective function based on the section information, the cost correction coefficient, the time factor and the cost information corresponding to the laying method; confirming the PMD constraint conditions and the cutoff wavelength constraint conditions based on the engineering information, confirming the attenuation constraint conditions of each independent section based on the section information, and confirming the optical fiber type constraint conditions of each independent section based on the laying method.

[0014] Optionally, in a sixth implementation manner of the first aspect of the present invention, the objective function is solved based on the constraint conditions using a hybrid genetic algorithm to obtain optical fiber information, including: randomly generating a group of feasible solutions as the initial population, each feasible solution corresponding to a group of optical fiber parameter configurations, and the optical fiber parameter configurations including optical fiber type, core diameter and cladding parameters; according to the objective function value, selecting parent individuals from the initial population using a roulette wheel selection method, and performing a crossover operation on the parent individuals to obtain new offspring individuals; performing a mutation operation on the new offspring individuals using a random mutation method, and optimizing the new offspring individuals after the mutation operation using a gradient descent method; performing constraint processing on the optimized new offspring individuals using a penalty function method, and selecting a new parent individual from the new offspring individuals after the constraint processing using a roulette wheel selection method; replacing the parent individual with the new parent individual, returning to perform a crossover operation on the parent individual to obtain a new offspring individual; when the preset maximum number of iterations is reached, outputting the optimal individual as the optical fiber information.

[0015] The second aspect of the present invention provides a device for generating an optical cable laying plan, including: a processing module for acquiring engineering information and performing preprocessing to obtain road section information, wherein the road section information includes multiple independent road sections and feature labels corresponding to the independent road sections; an input module for converting the road section information into an input feature vector, and inputting the input feature vector into a pre-built laying method decision model to obtain the laying method output by the laying method decision model; a correction module for confirming whether the laying method needs to be corrected based on the feature label, and if not, obtaining the cost correction coefficient corresponding to the laying method; a construction module for constructing an objective function based on the road section information, the laying method and the cost correction coefficient, and confirming the constraint conditions based on the engineering information, the road section information and the laying method; a solution module for solving the objective function based on the constraint conditions using a hybrid genetic algorithm to obtain optical fiber information; an integration module for integrating the road section information, the laying method and the optical fiber information to obtain an optical cable laying plan.

[0016] The third aspect of the present invention provides an optical cable laying plan generating device, which includes: a memory and at least one processor, wherein the memory stores instructions; at least one processor calls the instructions in the memory to enable the optical cable laying plan generating device to perform each step of the optical cable laying plan generating method described in any one of the above items.

[0017] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the various steps of any of the above-mentioned methods for generating an optical cable laying plan.

[0018] In the technical solution of the present invention, by automatically processing engineering information to obtain road section information, the design cycle of road section division is significantly shortened, reducing it from several weeks or even months to the automated processing level, greatly reducing manual intervention, and thus improving the efficiency of road section planning; in addition, by constructing an input feature vector and a laying method decision model, the limitation of the traditional method of using similar design schemes for different road sections is overcome, and personalized optimization of each independent road section is achieved, ensuring the accuracy and adaptability of the laying scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A logic flow chart of a method for generating an optical cable laying plan provided in an embodiment of the present invention;

[0020] Figure 2 A schematic structural diagram of a device for generating an optical cable laying plan according to an embodiment of the present invention;

[0021] Figure 3 A schematic structural diagram of an optical cable laying plan generating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention provides a method, apparatus, device, and storage medium for generating an optical cable laying plan. In the present invention, the terms "first," "second," "third," "fourth," and the like (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this way are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or are inherent to these processes, methods, products, or devices.

[0023] This application discloses a method for generating an optical cable laying plan. For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of a method for generating an optical cable laying plan in an embodiment of the present invention includes:

[0024] 101. Acquire and preprocess project information to obtain road section information, where the road section information includes multiple independent road sections and feature labels corresponding to the independent road sections.

[0025] In this embodiment, by automatically acquiring project information and calling the map API to perform geographic feature analysis, intelligent segmentation processing and feature labeling of the planned path are achieved. Compared with traditional manual surveys and manual segmentation methods, this solution shortens the design cycle from weeks or even months to an automated processing level, significantly reducing human intervention.

[0026] 102. Convert the road section information into an input feature vector, and input the input feature vector into a pre-built laying mode decision model to obtain a laying mode output by the laying mode decision model;

[0027] 103. Determine whether the laying method needs to be modified based on the feature tag. If not, obtain a cost modification coefficient corresponding to the laying method.

[0028] In this embodiment, by constructing an input feature vector and a laying method decision model and coordinating it with a rule engine, differentiated decisions are made for the geographical feature labels (such as cross-water labels, slope labels) and environmental feature labels (urban / suburban / rural) of each independent road section, and fundamentally avoiding the traditional design risk of incorrectly choosing a direct burial method in mountainous terrain, which leads to a surge in maintenance costs.

[0029] 104. Construct an objective function based on the road section information, laying method and cost correction coefficient, and confirm the constraint conditions based on the project information, road section information and laying method;

[0030] 105. Based on the constraints, a hybrid genetic algorithm is used to solve the objective function and obtain the fiber information;

[0031] In this embodiment, by using a hybrid genetic algorithm to execute the multi-parameter optimization solution process, the rework problem caused by manual calculation errors is effectively avoided, thereby improving the overall work efficiency and the accuracy of the results.

[0032] 106. Integrate road section information, laying method and optical fiber information to obtain the optical cable laying plan;

[0033] In this embodiment, the developed optical cable laying plan includes a section list, an optical fiber parameter table, and a three-dimensional route map; the contents of the section list include the identification, length, characteristic label, and laying method of the section; the optical fiber parameter table lists in detail the model, attenuation coefficient, and polarization mode dispersion (PMD) value corresponding to the section ID; the three-dimensional route map is intuitively displayed by importing the planned path CAD drawing and marking key construction points.

[0034] The present application discloses a method for generating an optical cable laying plan. By automatically processing engineering information to obtain road section information, the design cycle of road section division is significantly shortened, reducing it from several weeks or even months to an automated processing level, greatly reducing manual intervention, and thus improving the efficiency of road section planning. In addition, by constructing an input feature vector and a laying method decision model, the limitation of using similar design plans for different road sections in traditional methods is overcome, and personalized optimization of each independent road section is achieved, ensuring the accuracy and adaptability of the laying plan.

[0035] Furthermore, in an embodiment of the present invention, the engineering information is obtained and preprocessed to obtain road section information, which includes multiple independent road sections and feature labels corresponding to the independent road sections, including:

[0036] 201. Acquire project information, where the project information includes a starting point, an end point, and a planned path connecting the starting point and the end point;

[0037] In this embodiment, a RESTful API interface is used to connect with the enterprise project management system to automatically capture the project's starting point longitude and latitude, end point coordinates, and CAD planning path files, and the conversion of vector data to geographic information system layers is achieved through the GDAL library.

[0038] 202. Calling a map API to obtain geographical features and population density features of the planned route, wherein the geographical features include slope and water areas;

[0039] In this embodiment, the Google Maps API is called to obtain altitude data, the slope and aspect are calculated using ArcGIS Pro, and the global water dataset is used to identify the range of water bodies such as rivers and lakes to obtain geographic features. Furthermore, the WorldPop population distribution data is accessed, the population count is extracted according to a 1km×1km grid, and the population agglomeration areas are divided in combination with the administrative boundary data to obtain population density characteristics.

[0040] 203. Segment the planned route based on geographic features to obtain multiple independent road segments, and configure a geographic feature label for each independent road segment;

[0041] 204. Configuring an environmental feature label for each independent road segment based on the population density feature, and configuring a cost feature label for each independent road segment based on the population density feature and geographical feature corresponding to the independent road segment; the environmental feature labels include an urban label, a suburban label, and a rural label, and the cost feature labels include a low-budget label, a medium-budget label, and a high-budget label;

[0042] In this embodiment, corresponding environmental feature labels are assigned to each independent road section based on the population density characteristics. Specifically, when the population density exceeds 5,000 people per square kilometer, an urban label is assigned; when the population density is between 1,000 and 5,000 people per square kilometer, a suburban label is assigned; and when the population density is less than 1,000 people per square kilometer, a rural label is assigned. By configuring environmental feature labels, a basis is provided for subsequent cost evaluation.

[0043] In this embodiment, a cost influencing factor matrix is ​​pre-constructed, such as setting the cost coefficient of the water section to 1.8, the cost coefficient of the hilly section to 1.5, and the cost coefficient of the urban section to 1.3; the hierarchical analysis method is used to calculate the comprehensive cost label, and the budget level is output accordingly, which is divided into three levels: low budget (less than 1.2), medium budget (1.2 to 1.5) and high budget (greater than 1.5).

[0044] Furthermore, in an embodiment of the present invention, segmenting the planned route based on geographic features to obtain multiple independent road segments, and configuring a geographic feature label for each independent road segment, includes:

[0045] 301. Extracting water areas in the planned route based on geographical features, and calculating the length of each extracted water area;

[0046] In this embodiment, the spatial intersection of the planned path and the water polygon is detected based on OpenCV image recognition technology, and the Douglas-Peucker algorithm is used to simplify the water boundary coordinates to obtain multiple independent water sections, and each independent water section is assigned an ID. By forcibly dividing the water sections, special designs such as overhead laying are ensured to be handled independently to avoid confusion with land sections.

[0047] 302. Segment the planned path based on the calculation results to obtain one or more independent water sections and a non-water planned path, and configure a cross-water label for each independent water section;

[0048] In this embodiment, different configuration strategies are adopted for different water widths. Specifically, if the water width is ≤50 meters and the conditions for erecting poles are met on both sides, the overhead installation adaptation tag is directly configured; if the water width is greater than 50 meters, a high-strength pole tower requirement tag is added in combination with the navigation level to ensure the structural feasibility of overhead installation; through differentiated tag configuration, it is helpful to customize the characteristics of different road sections, thereby ensuring the stability and safety of the entire planned path, and further improving the reliability and scientific nature of project implementation.

[0049] 303. Obtain a preset window length, perform secondary segmentation processing on the non-water area planned path based on the preset window length and slope, obtain multiple non-water area independent road sections, and configure a slope label for each non-water area independent road section;

[0050] In this embodiment, when planning a non-water path, a sliding window method is used in combination with cluster analysis technology to achieve automatic segmentation and identification of the path; the specific operations are as follows: first, with the starting point of the path as the benchmark, the initial window length is set to 5 kilometers; then, the coefficient of variation of the geographical features in the window is calculated, such as the standard deviation of the slope. When the calculated standard deviation exceeds a preset threshold (for example, the standard deviation is greater than 5 degrees), the path will be segmented at the variation point; with the segmentation point as the new starting point, the above steps are repeated until the entire non-water path is completely covered, and multiple independent non-water sections are obtained; the slope label includes three categories: flat, hilly and mountainous. Specifically, a slope of less than or equal to 10 degrees is defined as flat, a slope between 10 and 30 degrees is defined as hilly, and a slope greater than 30 degrees is defined as mountainous.

[0051] Furthermore, in an embodiment of the present invention, converting the road section information into an input feature vector, and inputting the input feature vector into a pre-built laying mode decision model to obtain a laying mode output by the laying mode decision model includes:

[0052] 401. Numerically encode the road section information to obtain an input feature vector;

[0053] In this embodiment, the road section information is numerically encoded by combining the one-hot encoding and Z-score normalization method to obtain an input feature vector, where the input feature vector input vector = [terrain code, environment code, cost threshold normalization value, distance normalization value]. By converting unstructured labels into feature vectors that can be recognized by the model and standardizing continuous variables, the model input compatibility can be improved.

[0054] 402. Pre-build a model based on the XGBoost algorithm and perform training to obtain a laying mode decision model;

[0055] In this embodiment, a dataset is constructed based on historical data of more than 5,000 engineering cases. The dataset contains 30 input feature dimensions, including derivative variables generated during the preprocessing process, and three different laying method labels, namely pipeline laying, direct burial laying, and overhead laying. Based on the dataset, the 5-fold cross-validation method and the EarlyStopping mechanism training model are combined to obtain a laying method decision model. The laying method decision model can output the probability distribution of each laying method (for example, the probability of overhead laying is 0.72, and the probability of pipeline laying is 0.25), and select the category with the highest probability as the final decision result.

[0056] 403. Input the input feature vector into the laying mode decision model to obtain the laying mode.

[0057] Furthermore, in an embodiment of the present invention, determining whether the laying method needs to be corrected based on the feature tag, and if not, obtaining a cost correction coefficient corresponding to the laying method, includes:

[0058] 501. Determine whether the laying method of the independent road section with the water area label is overhead laying, and determine whether the laying method of the independent road section with the city label is pipeline laying;

[0059] 502. If the laying method of all independent road sections with the water area tag is overhead laying and the laying method of all independent road sections with the city tag is pipeline laying, it is not necessary to obtain the laying method, and obtain the cost correction coefficient corresponding to the laying method;

[0060] 503. If the laying method of any independent road section with a water area tag is not overhead laying, or if the laying method of any independent road section with a city tag is not pipeline laying, then the laying method is corrected, and a cost correction coefficient corresponding to the corrected laying method is obtained;

[0061] In this embodiment, constraints are enforced through the rule engine, such as "water area → overhead laying", to ensure that the plan complies with the design specifications and avoid a surge in subsequent maintenance costs due to environmental adaptation errors; further, by limiting the laying method of water sections to overhead laying, the high difficulty of underwater construction and the risk of subsequent maintenance can be avoided, the construction period of water sections can be shortened, and the maintenance cost of water sections can be reduced; at the same time, overhead laying has a higher degree of standardization and is more compatible with the laying method of land sections, which improves the unity and feasibility of the overall plan.

[0062] In this embodiment, the cost correction coefficient can be obtained through a pre-constructed cost matrix, such as the cost correction coefficient of direct burial laying is 1.0, the cost correction coefficient of pipeline laying is 1.5, and the cost correction coefficient of overhead laying is 0.6.

[0063] Furthermore, in an embodiment of the present invention, constructing an objective function based on the road section information, the laying method, and the cost correction coefficient, and confirming the constraint conditions based on the project information, the road section information, and the laying method, includes:

[0064] 601. Obtain a time factor and cost information corresponding to the laying method, wherein the cost information includes a standard production cost per unit length of optical fiber, a basic maintenance cost per unit length of optical fiber, and a maintenance cost growth rate;

[0065] In this embodiment, the time factor includes the estimated service life and the inflation rate. The estimated service life is 15 years, and the inflation rate can be 3%. The cost information can be obtained through a pre-constructed cost matrix, such as the maintenance cost growth rate of direct burial laying is 3%, the maintenance cost growth rate of pipeline laying is 1%, and the maintenance cost growth rate of overhead laying is 5%. By introducing the time factor and the maintenance cost growth rate, the defect of the traditional solution that only focuses on the construction period cost is avoided.

[0066] 602. Constructing an objective function based on the road section information, the cost correction coefficient, the time factor, and the cost information corresponding to the laying method;

[0067] In this embodiment, the objective function constructed is:

[0068]

[0069] in, is the standard production cost per unit length of optical fiber, is the basic maintenance cost per unit length of optical fiber, K is the cost correction coefficient, L is the length of the section, which comes from the length data in the section information, and T is the estimated service life. is the maintenance cost growth rate, is the inflation rate.

[0070] 603. Confirm the PMD constraint and cutoff wavelength constraint based on the project information, confirm the attenuation constraint of each independent road section based on the road section information, and confirm the fiber type constraint of each independent road section based on the laying method;

[0071] In this embodiment, the PMD constraint condition sets an upper limit value according to the project transmission performance requirements, for example, PMD≤0.5ps / √km, the cut-off wavelength constraint condition is set according to the optical fiber multiplexing technology solution, for example, the cut-off wavelength≤1260nm, and the attenuation constraint condition is attenuation≤section index, which is set differently according to the section length and laying environment, for example, the attenuation of urban direct buried sections is ≤0.3dB / km, and the attenuation of mountain overhead sections is ≤0.25dB / km; the optical fiber type constraint condition includes: ADSS, OPPC or OPGW optical cable must be used for overhead laying; by setting the constraint conditions, the signal transmission quality and construction feasibility of the final generated optical cable laying plan are ensured, that is, the problem of single indicator meeting the standard but global infeasibility is avoided through the integration of multidisciplinary specifications.

[0072] Furthermore, in an embodiment of the present invention, the hybrid genetic algorithm is used to solve the objective function based on the constraint conditions to obtain the optical fiber information, including:

[0073] 701. Randomly generate a set of feasible solutions as an initial population, where each feasible solution corresponds to a set of fiber parameter configurations, where the fiber parameter configurations include fiber type, core diameter, and cladding parameters;

[0074] 702. Based on the objective function value, a roulette wheel selection method is used to select parent individuals from the initial population, and a crossover operation is performed on the parent individuals to obtain new offspring individuals;

[0075] In this embodiment, the global search capability of the genetic algorithm is used, such as using ADSS, OPPC or OPGW optical cables for overhead sections in water areas, to retain high-quality parameter combinations and improve the probability of the optimal solution.

[0076] 703. Using random mutation method to perform mutation operation on new offspring individuals, and using gradient descent method to optimize the new offspring individuals after mutation operation;

[0077] In this embodiment, new parameter combinations are introduced through random mutation, such as fine-tuning of the mode field diameter, and continuous variables such as the attenuation coefficient are optimized by gradient descent. This balances global exploration and local refinement, and the solution efficiency is improved by 40% compared with the pure genetic algorithm.

[0078] 704. Using a penalty function method to constrain the optimized new offspring individuals, and using a roulette wheel selection method to select new parent individuals from the constrained new offspring individuals;

[0079] In this embodiment, a penalty function method is used to filter infeasible solutions in real time. For example, for solutions that do not meet the fiber type constraint, the constraint violation rate is reduced from 28% to 3% during the iteration process, ensuring the feasibility of the output solution.

[0080] 705. Replace the parent individual with the new parent individual, return and perform a crossover operation on the parent individual to obtain a new child individual;

[0081] 706. When the preset maximum number of iterations is reached, the optimal individual is output as the optical fiber information;

[0082] In this embodiment, the maximum number of iterations is 1000 generations; the output fiber information is a combination of fiber parameters, such as G.652D fiber, core diameter 8.3μm, cladding diameter 125μm, tensile strength ≥1000MPa, suitable for urban direct buried road sections; the objective function is solved by a hybrid genetic algorithm so that the output fiber information can simultaneously meet performance and cost targets.

[0083] The above describes the method for generating an optical cable laying scheme according to an embodiment of the present invention. The following describes the device for generating an optical cable laying scheme according to an embodiment of the present invention. Figure 2 In one embodiment of the present invention, an optical cable laying plan generating device includes:

[0084] Processing module 801 is used to obtain and pre-process project information to obtain road section information, wherein the road section information includes multiple independent road sections and feature labels corresponding to the independent road sections;

[0085] Input module 802, used to convert road section information into input feature vectors, and input the input feature vectors into a pre-built laying mode decision model to obtain a laying mode output by the laying mode decision model;

[0086] The correction module 803 is used to determine whether the laying method needs to be corrected based on the feature tag, and if not, obtain a cost correction coefficient corresponding to the laying method;

[0087] A construction module 804 is used to construct an objective function based on the road section information, the laying method and the cost correction coefficient, and to confirm the constraint conditions based on the project information, the road section information and the laying method;

[0088] A solution module 805 is used to solve the objective function based on the constraint conditions using a hybrid genetic algorithm to obtain optical fiber information;

[0089] The integration module 806 is used to integrate the road section information, laying method and optical fiber information to obtain the optical cable laying plan.

[0090] Based on the same idea as the method in the above embodiment, the device provided in this application can implement the method in the above embodiment.

[0091] above Figure 2 The optical cable laying plan generating device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The optical cable laying plan generating device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0092] Figure 3FIG2 is a schematic diagram of the structure of an optical cable plan generation device provided in an embodiment of the present invention. The optical cable plan generation device 900 may vary significantly depending on configuration or performance. The device may include one or more processors (central processing units, CPUs) 910, a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage medium 930 may be either transient or persistent storage. The program stored in the storage medium 930 may include one or more modules (not shown), each of which may include a series of instructions for operating on the optical cable plan generation device 900. Furthermore, the processor 910 may be configured to communicate with the storage medium 930, allowing the device 900 to execute the series of instructions stored in the storage medium 930 to implement the steps of the optical cable plan generation method provided in the aforementioned method embodiments.

[0093] The optical cable laying plan generating device 900 may further include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be understood by those skilled in the art that Figure 3 The structure of the optical cable laying plan generating device shown does not constitute a limitation to the optical cable laying plan generating device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0094] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the optical cable laying plan generating method.

[0095] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0096] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or 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 for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0097] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for generating an optical cable laying plan, characterized in that: include: Acquire and preprocess the engineering information to obtain road section information, wherein the road section information includes a plurality of independent road sections and feature labels corresponding to the independent road sections; Specifically, obtaining project information, the project information including a starting point, an end point, and a planned path connecting the starting point and the end point; Calling the map API to obtain the geographical features and population density features of the planned route, wherein the geographical features include slope and water areas; segmenting the planned route based on the geographical features to obtain multiple independent road segments, and configuring a geographical feature label for each independent road segment; An environmental feature label is configured for each independent road segment based on the population density feature, and a cost feature label is configured for each independent road segment based on the population density feature and geographical feature corresponding to the independent road segment; the environmental feature label includes an urban label, a suburban label, and a rural label, and the cost feature label includes a low-budget label, a medium-budget label, and a high-budget label; The road section information is converted into an input feature vector, and the input feature vector is input into a pre-built laying mode decision model to obtain a laying mode output by the laying mode decision model. Specifically, the road section information is numerically encoded to obtain an input feature vector; a model is pre-built and trained based on the XGBoost algorithm to obtain a laying mode decision model; the input feature vector is input into the laying mode decision model to obtain a laying mode; Determine whether the laying method needs to be modified based on the feature tag, and if not, obtain the cost correction coefficient corresponding to the laying method; Construct an objective function based on road section information, laying method and cost correction coefficient, and confirm the constraints based on project information, road section information and laying method; Based on the constraints, a hybrid genetic algorithm is used to solve the objective function and obtain the fiber information. Integrate road section information, laying method and optical fiber information to obtain the optical cable laying plan.

2. The method for generating an optical cable laying plan according to claim 1, wherein: The planned route is segmented based on geographic features to obtain multiple independent road segments, and a geographic feature label is configured for each independent road segment, including: Extracting water areas in the planned route based on geographical features and calculating the length of each extracted water area; Based on the calculation results, the planned path is segmented to obtain one or more independent water sections and non-water planned paths, and a cross-water label is configured for each independent water section; Obtain a preset window length, perform secondary segmentation on the non-water planned path based on the preset window length and slope, obtain multiple non-water independent road sections, and configure a slope label for each non-water independent road section.

3. The method for generating an optical cable laying plan according to claim 2, wherein: The determining whether the laying mode needs to be modified based on the feature tag, and if not, obtaining a cost modification coefficient corresponding to the laying mode, includes: Determine whether the laying method of the independent road section with the water area label is overhead laying, and determine whether the laying method of the independent road section with the city label is pipeline laying; If the laying method of the independent road sections with the water area label is all overhead laying and the laying method of the independent road sections with the city label is all pipeline laying, it is not necessary to obtain the laying method, and obtain the cost correction coefficient corresponding to the laying method; If the laying method of any independent road section with a water area label is not overhead laying, or if the laying method of any independent road section with a city label is not pipeline laying, the laying method is corrected and the cost correction coefficient corresponding to the corrected laying method is obtained.

4. The method for generating an optical cable laying plan according to claim 1, wherein: The objective function is constructed based on the road section information, the laying method and the cost correction coefficient, and the constraint conditions are confirmed based on the project information, the road section information and the laying method, including: Obtaining a time factor and cost information corresponding to the laying method, wherein the cost information includes a standard production cost per unit length of optical fiber, a basic maintenance cost per unit length of optical fiber, and a maintenance cost growth rate; Constructing an objective function based on the road section information, cost correction coefficient, time factor and cost information corresponding to the laying method; Confirm the PMD constraints and cutoff wavelength constraints based on the project information, confirm the attenuation constraints of each independent section based on the section information, and confirm the fiber type constraints of each independent section based on the laying method.

5. The method for generating an optical cable laying plan according to claim 1, wherein: The objective function is solved by using a hybrid genetic algorithm based on the constraint conditions to obtain optical fiber information, including: Randomly generating a set of feasible solutions as an initial population, each feasible solution corresponding to a set of fiber parameter configurations, wherein the fiber parameter configurations include fiber type, core diameter, and cladding parameters; According to the objective function value, the roulette wheel selection method is used to select the parent individuals from the initial population, and the parent individuals are crossovered to obtain new offspring individuals; The random mutation method is used to perform mutation operation on the new offspring individuals, and the gradient descent method is used to optimize the new offspring individuals after the mutation operation; The penalty function method is used to constrain the optimized new offspring individuals, and the roulette wheel selection method is used to select new parent individuals from the constrained new offspring individuals. Replace the parent individual with the new parent individual, return and perform the crossover operation on the parent individual to obtain the new child individual; When the preset maximum number of iterations is reached, the optimal individual is output as the fiber information.

6. A device for generating an optical cable laying plan, characterized in that: include: a processing module, configured to obtain and pre-process engineering information to obtain road section information, wherein the road section information includes a plurality of independent road sections and feature labels corresponding to the independent road sections; Specifically, obtaining project information, the project information including a starting point, an end point, and a planned path connecting the starting point and the end point; Calling the map API to obtain the geographical features and population density features of the planned route, wherein the geographical features include slope and water areas; segmenting the planned route based on the geographical features to obtain multiple independent road segments, and configuring a geographical feature label for each independent road segment; An environmental feature label is configured for each independent road segment based on the population density feature, and a cost feature label is configured for each independent road segment based on the population density feature and geographical feature corresponding to the independent road segment; the environmental feature label includes an urban label, a suburban label, and a rural label, and the cost feature label includes a low-budget label, a medium-budget label, and a high-budget label; The input module is used to convert the road section information into an input feature vector, and input the input feature vector into a pre-built laying mode decision model to obtain the laying mode output by the laying mode decision model. Specifically, the road section information is numerically encoded to obtain the input feature vector; a model is pre-built and trained based on the XGBoost algorithm to obtain the laying mode decision model; the input feature vector is input into the laying mode decision model to obtain the laying mode; A correction module is used to determine whether the laying method needs to be corrected based on the feature tag, and if not, obtain a cost correction coefficient corresponding to the laying method; A construction module is used to construct an objective function based on road section information, laying method and cost correction coefficient, and to confirm constraint conditions based on project information, road section information and laying method; A solution module is used to solve the objective function based on the constraint conditions and obtain the optical fiber information by using a hybrid genetic algorithm; The integration module is used to integrate road section information, laying method and optical fiber information to obtain the optical cable laying plan.

7. An optical cable laying plan generating device, characterized in that: The optical cable laying plan generating device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors calls the instructions in the memory to enable the optical cable laying plan generating device to execute each step of the optical cable laying plan generating method according to any one of claims 1 to 5.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of the method for generating an optical cable laying plan according to any one of claims 1 to 5 are implemented.

Images