Method, device, electronic device, storage medium and computer program product for tourist highway classification

Abstract

The present application discloses a method, device, electronic device, storage medium and computer program product for grading tourist roads, the method comprising: obtaining a road network data set; determining the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and a pre-trained classification model; inputting the weight coefficient level of each traffic node, the weight coefficient level of each tourist attraction and the road network data set into a preset path search algorithm for processing to generate a global path data set; generating a multi-level road network based on each of the shortest paths in the global path data set. The method of the present application can improve the accuracy of tourist road identification.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a method, device, electronic equipment, storage medium and computer program product for grading tourist roads. Background Art

[0002] In recent years, the rapid development of global tourism has aroused widespread social attention to the planning of tourism highway networks. At present, there are still some problems in the development of global tourism in our province. Through refined transportation network analysis and the construction of a multi-level tourism highway network, the construction needs of tourism highways can be clarified and the tourism transportation service capacity can be further improved. In order to identify the global tourism transportation network, this paper adopts A The Search Algorithm performs the shortest path analysis and combines GIS (Geographic Information System) spatial technology and line density analysis methods to identify the main tourist channels with high correlation. Through the identification and construction of a multi-level "fast-in slow-out" tourist highway network, the present invention provides accurate decision-making support for planning and management departments, effectively improving the scientificity and practicality of tourist highway network planning.

[0003] The traditional method of identifying a tourist highway network takes the scenic area as the center, connects nearby towns, transportation hubs, and highway interchanges, etc., to find the tourist highways from the traffic source nodes to the scenic area, or connects the main scenic spots to find interconnected tourist highways. On this basis, through field surveys of tourist traffic volume, the strength of its tourism function is judged, and finally the provincial tourist highway network is identified. However, due to the excessive number of tourist resource points and traffic source nodes in the province, the traditional method of identifying tourist highways is a huge workload and prone to errors. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method, device, electronic device, storage medium and computer program product for grading tourist roads, aiming to improve the accuracy of tourist road identification.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] In the first aspect, the present application proposes a method for grading tourist roads, the method comprising:

[0007] Acquire a road network data set, wherein the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area;

[0008] Determine the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and the pre-trained classification model;

[0009] The weight coefficient level of each of the traffic nodes, the weight coefficient level of each of the tourist attractions and the road network data set are input into a preset path search algorithm for processing to generate a global path data set, wherein the global path data set includes the shortest path between any two tourist attractions in the target area, and the shortest path is a tourist path with the lowest comprehensive cost;

[0010] A multi-level highway network is generated based on the shortest paths in the global path data set.

[0011] In a second aspect, an embodiment of the present application provides a grading device for tourist roads, the device comprising:

[0012] A data acquisition module, used to acquire a road network data set, wherein the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area;

[0013] A weight level determination module, used to determine the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and the pre-trained classification model;

[0014] A data set generation module, used for inputting the weight coefficient level of each of the traffic nodes, the weight coefficient level of each of the tourist attractions and the road network data set into a preset path search algorithm for processing, and generating a global path data set, wherein the global path data set includes the shortest path between any two tourist attractions in the target area, and the shortest path is a tourist path with the lowest comprehensive cost;

[0015] The road network generation module is used to generate a multi-level road network based on each of the shortest paths in the global path data set.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor, when running the computer program, executes the steps of the method described in the first aspect of the embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect of the embodiment of the present application are implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect of the present application.

[0019] The technical solution provided by the embodiment of the present application determines the weight coefficient level of each traffic node and each tourist attraction, and combines the road network data set to input into the preset path search algorithm for processing, so as to obtain all the shortest paths in the target area, and the shortest path refers to the tourist path with the minimum comprehensive cost. Finally, each shortest path is hierarchical to obtain a multi-level highway network. In this way, the tourist path with the minimum comprehensive cost is determined between any two tourist attractions in the target area, which can optimize the user's travel route. And, after obtaining the shortest path based on this, each shortest path is hierarchical, which can improve the recognition accuracy of tourist roads. In addition, since the weight coefficient level of the traffic node is determined based on the average daily passenger flow of the corresponding traffic node, wherein the average daily passenger flow represents the size of the traffic node's daily passenger flow, it can reflect the degree to which the traffic node is required by users. The weight coefficient level of the tourist attraction is determined based on the annual number of tourists of the corresponding tourist attraction, wherein the annual number of tourists represents the number of tourists visiting the tourist attraction each year, which can reflect the degree to which the tourist attraction is loved by users. Determining the weight coefficient of a traffic node based on the average daily passenger flow of the traffic node can adjust the weight coefficient of the traffic node according to the degree to which the traffic node is required by users. Determining the weight coefficient of a tourist attraction based on the annual number of tourists at the tourist attraction can adjust the weight coefficient of the tourist attraction according to the degree to which the tourist attraction is liked by users. In this way, the highway network obtained can fully consider the degree of user demand for traffic nodes and the degree of user preference for tourist attractions, thereby improving the rationality and accuracy of highway network classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a method for grading tourist roads according to an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a flow chart of a method for grading tourist roads according to another embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of a grading device for a tourist highway according to an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0026] The embodiment of the present application provides a method for grading tourist roads. The SoC system runs in an electronic device, that is, the execution subject is an electronic device, and the electronic device can be any device that can execute the method for grading tourist roads, for example, it can be a terminal device or a server, etc., and the present application does not make specific restrictions on this. Figure 1 As shown, the method includes:

[0027] Step 101, obtaining a road network data set, where the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area.

[0028] The target area may be obtained by dividing the area according to the administrative domain. For example, a provincial area may be used as the target area. The target area may also be a set area as the target area. For example, a provincial area and a part of another provincial area may be used as the target area. This application does not limit this.

[0029] The target area may include multiple tourist attractions and multiple transportation nodes related to the tourist attractions. Transportation nodes refer to the stations corresponding to the transportation methods leading to the tourist attractions. Transportation nodes include but are not limited to airports, high-speed rail stations, conventional rail stations, highways, and bus stations (level 2 or above).

[0030] Step 102, based on the road network data set and the pre-trained classification model, determine the weight coefficient level of each traffic node and each tourist attraction.

[0031] The pre-trained classification model may be a Boosting algorithm or other algorithms that can be used for classification.

[0032] Based on the road network data set and the pre-trained classification model, the weight coefficient level of each traffic node in the road network data set and the weight coefficient level of each tourist attraction can be determined.

[0033] Here, the weight coefficient level can be understood as setting a corresponding level for the weight coefficient, which can facilitate the pre-trained classification model to better classify data.

[0034] Step 103, the weight coefficient level of each traffic node, the weight coefficient level of each tourist attraction and the road network data set are input into a preset path search algorithm for processing to generate a global path data set.

[0035] The global path data set includes the shortest path between any two tourist attractions in the target area. The shortest path between two tourist attractions can be a path with the lowest comprehensive cost, and the comprehensive cost includes distance cost and time cost.

[0036] Step 104: Generate a multi-level highway network based on the shortest paths in the global path data set.

[0037] Here, the road network includes the shortest paths in the target area. Multi-level means that the shortest paths in the road network have multiple levels. For example, tourist roads are divided into tourist trunk roads that have the function of "fast forward" and tourist distribution roads and tourist scenic roads that have the function of "slow travel". Among them, tourist trunk roads are expressways, tourist distribution roads are ordinary national and provincial roads, and tourist scenic roads are rural roads.

[0038] The technical solution provided by the embodiment of the present application determines the weight coefficient level of each traffic node and each tourist attraction by obtaining a road network data set, based on the road network data set and a pre-trained classification model. The weight coefficient level of each traffic node, the weight coefficient level of each tourist attraction and the road network data set are input into a preset path search algorithm for processing to generate a global path data set. Based on each shortest path in the global path data set, a multi-level highway network is generated. By determining the weight coefficient level of each traffic node and each tourist attraction, combined with the road network data set, they are input into a preset path search algorithm for processing, so as to obtain all the shortest paths in the target area, and the shortest path refers to the tourist path with the minimum comprehensive cost. Finally, each shortest path is hierarchical to obtain a multi-level highway network. In this way, the tourist path with the minimum comprehensive cost is determined between any two tourist attractions in the target area, so that the user's travel route can be optimized. Moreover, after the shortest path is obtained based on this, each shortest path is hierarchical to improve the recognition accuracy of the tourist highway.

[0039] In one embodiment, Figure 2 As shown, obtain the road network data set, including:

[0040] Step 201, obtaining target road network data and target tourism resource data.

[0041] The target road network data refers to the target data of the road network in the target area. The target tourism resource data refers to the target data of the tourist attractions in the target area.

[0042] Step 202: input the target road network data and the target tourism resource data into a preset geographic information system (GIS) model.

[0043] Step 203, geometric analysis and topology construction are performed on the target road network data through a preset GIS model to generate a topological structure of the road network.

[0044] Step 204, calculating and analyzing the topological structure of the road network and the target tourism resource data through a preset GIS model to obtain a road network data set.

[0045] Here, the target tourism resource data is calculated and analyzed based on the topological structure of the road network through the preset GIS model, and a road network data set can be obtained. The road network data set also includes the target tourism path from each tourist attraction to other tourist attractions except the tourist attraction itself in the target area. The target tourism path is the tourism path with the minimum time cost.

[0046] In one embodiment, the preset GIS model includes a target impedance function, which uses path length and travel time as main variables to calculate the minimum path cost from node i to node j. The expression of the target impedance function is as follows:

[0047] ;

[0048] in, represents the distance from node i to node j, represents the estimated time from node i to node j, and is the weight coefficient. Node i can be a tourist attraction and a transportation node, and node j can also be a tourist attraction and a transportation node.

[0049] The road network data set includes the travel paths between each tourist attraction and other tourist attractions in the target area. Exemplarily, there may be multiple travel paths between tourist attraction A (starting point node) and tourist attraction B (destination node). Taking one of the tourist paths as an example, the distance between tourist attraction A and the next path node (S1) is calculated along the forward direction. When the S1 node is a traffic node, the type and road section of the S1 node are determined based on the target road network data, and the road section has a corresponding driving speed limit. According to the type and road section of the S1 node and the distance between the S1 node and the A tourist attraction, the travel time from the A tourist attraction to the S1 node is determined. After that, the distance between the S1 node and the A tourist attraction and the travel time from the A tourist attraction to the S1 node are input into the target impedance function, and the time cost of the path segment between the A tourist attraction and the S1 node can be determined. For other nodes between the S1 node and the B tourist attraction, the corresponding travel time is calculated between each node, or between the node and the B tourist attraction. In this way, the total time cost of the path of the tourist path can be obtained. The calculation of the total time cost of other tourist routes between tourist attraction A and tourist attraction B is similar.

[0050] After determining the total time costs of multiple tourist paths between tourist attraction A and tourist attraction B, the total time costs of the paths of the various tourist paths are compared, and the tourist path with the smallest total time cost is determined as the target tourist path between tourist attraction A and tourist attraction B. Here, the tourist path with the smallest total time cost is the aforementioned tourist path with the smallest time cost.

[0051] Based on the same method as described above, after analyzing at least one tourist path between each tourist attraction and other tourist attractions in the target area, a target tourist path between each tourist attraction and other tourist attractions can be obtained.

[0052] In one embodiment, obtaining target road network data and target tourism resource data includes: obtaining first road network data and first tourism resource data; converting the first road network data and the first tourism resource data according to a preset format to obtain second road network data and second tourism resource data; converting the second road network data and the second tourism resource data into GIS data to obtain the target road network data and the target tourism resource data.

[0053] Among them, the first road network data is the initial road network data. The first tourism resource data is the initial tourism resource data. The first road network data and the first tourism resource data may usually come from different data sources, and thus the data formats are varied. In order to unify the data formats, the first road network data and the second road network data may be converted to obtain the second road network data and the second tourism resource data. It is understandable that the format of the second road network data and the second tourism resource data is a standardized and unified format, which can ensure the consistency and compatibility of the data, thereby facilitating the subsequent input into the preset GIS model for analysis and modeling.

[0054] Afterwards, the second road network data and the second tourism resource data are converted into data in GIS format to obtain the target road network data and the target tourism resource data. Converting the second road network data and the second tourism resource data into GIS data can be understood as converting the geographic coordinate system of the second road network data and the second tourism resource data into a unified coordinate system.

[0055] In one embodiment, after obtaining the first road network data and the first tourism resource data, the first road network data and the first tourism resource data are further cleaned. The data cleaning includes format and coordinate conversion, topology processing, and attribute improvement.

[0056] In one embodiment, after converting the second road network data and the second tourism resource data into GIS data, the second road network data and the second tourism resource data are topologically processed to repair possible topological errors, such as broken lines, intersection errors, discontinuous sections, etc. In addition, the attribute data is checked and improved, and the missing attribute information is filled to ensure that the attribute data of each road section and node is complete and accurately reflects the actual situation.

[0057] In one embodiment, the first road network data and the first tourism resource data are converted according to a preset format to obtain second road network data and second tourism resource data.

[0058] Here, the first road network data includes data of all traffic nodes related to tourist attractions in the target area. The first road network data may include identification information, category information, location data and section data of airports, high-speed rail stations, ordinary rail stations, highways and bus stations. The category information may be used to indicate the type of traffic node, for example, the type is to distinguish airports, high-speed rail stations, ordinary rail stations, highways or bus stations. The location data in the first road network data may include longitude, latitude and altitude. The section data includes the length of the section, the road grade and the speed limit. The speed limit is the maximum operating speed of the vehicle corresponding to the various traffic roads designed in advance. The first tourism resource data includes identification information, location data and grade information of all tourist attractions in the target area. The grade information may be used to indicate the grade of tourist attractions. The grade of tourist attractions may include provincial A-level scenic spots, national red tourism classic scenic spots, national and provincial characteristic towns, national rural tourism key villages, national historical and cultural towns, famous villages, etc.

[0059] In one embodiment, based on the road network data set and a pre-trained classification model, the weight coefficient level of each transportation node and each tourist attraction is determined, including: obtaining a first weight coefficient of each tourist attraction and a second weight coefficient of each transportation node; inputting the road network data set, each first weight coefficient and each second weight coefficient into the pre-trained classification model to obtain the weight coefficient level of each tourist attraction and the weight coefficient level of each transportation node.

[0060] Specifically, after obtaining the first weight coefficient of each tourist attraction and the second weight coefficient of each transportation node, they can be input into the Boosting algorithm to obtain the weight coefficient level of each tourist attraction and the weight coefficient level of each transportation node.

[0061] Exemplarily, the road network data set, the first weight coefficient of each tourist attraction, and the second weight coefficient of each traffic node can be divided into a training set and a validation set, with the ratio set to 80:20.

[0062] The output of the integrated model in the Boosting algorithm is:

[0063] ;

[0064] in, is the predicted value of the mth iteration, is the predicted value of the previous iteration, is the mth base learner, is the corresponding learning rate.

[0065] Using the constructed training set, train the Boosting model. In each iteration, the model optimizes the weights by minimizing the loss function. Minimize the loss function for:

[0066] ;

[0067] Among them, N is the number of training samples.

[0068] The model is updated through negative gradients, and the update formula is:

[0069] ;

[0070] in, is the pseudo residual of the mth iteration.

[0071] Model performance evaluation, using mean square error to evaluate the performance of the model. as follows:

[0072] ;

[0073] in, is the true value, is the model prediction value. The pre-trained Boosting model can be used to calculate the weight level of tourist attractions and transportation nodes in the province, so as to obtain the weight level of each tourist attraction and each transportation node. . This function represents Represents the node importance weight, and its value is When taking the maximum value, the corresponding The node importance weight is the weight coefficient indicating the importance of the node. Thus, it can be seen that the first weight coefficient is the weight coefficient indicating the importance of the tourist attraction, and the second weight coefficient is the weight coefficient indicating the importance of the transportation node.

[0074] In one embodiment, obtaining the first weight coefficient of each of the tourist attractions includes: obtaining the annual number of tourists at each of the tourist attractions; determining the first traffic connectivity of each of the tourist attractions based on the topological structure of the road network; inputting the annual number of tourists, grade and first traffic connectivity of each of the tourist attractions into a preset first weight algorithm for processing to obtain the first weight coefficient of each of the tourist attractions.

[0075] Here, the annual number of tourists can be the average annual number of tourists at the tourist attraction. The first traffic connectivity represents the degree of traffic convenience of the tourist attraction. For example, the richer the types of transportation around the tourist attraction and the larger the number of transportation vehicles, the higher the degree of traffic convenience of the tourist attraction. The level of the tourist attraction is the level of the scenic area of ​​the tourist attraction.

[0076] The preset first weight algorithm may be:

[0077] ;

[0078] in, represents the annual number of visitors to the tourist attraction, Indicates the scenic spot level of the tourist attraction. Indicates the transportation connectivity of the tourist attraction. represents the weight coefficient, Indicates the first weight coefficient of the tourist attraction.

[0079] Specifically, the annual number of tourists at each tourist attraction, the grade of the tourist attraction and the first traffic connectivity are input into a preset first weight algorithm for calculation and processing, so as to obtain the first weight coefficient of each tourist attraction.

[0080] In one embodiment, obtaining the second weight coefficient of each of the traffic nodes includes: obtaining the average daily passenger flow of each of the traffic nodes; determining the second traffic connectivity of each of the traffic nodes based on the topological structure of the road network; inputting the average daily passenger flow, type and second traffic connectivity of each of the traffic nodes into a preset second weight algorithm for processing to obtain the second weight coefficient of each of the traffic nodes.

[0081] Here, the average daily passenger flow refers to the average daily passenger flow of a transportation node, which can be calculated based on the total passenger flow in the past year or other preset time period. The second traffic connectivity characterizes the traffic convenience of a transportation node. For example, the richer the types of transportation around a transportation node and the larger the number, the higher the traffic convenience of the transportation node. Types of transportation nodes, such as airports, high-speed rail stations, ordinary rail stations, scenic spots, etc. Each type can be assigned a different weight value.

[0082] The preset second weighting algorithm may be:

[0083] ;

[0084] in, represents the average daily passenger flow of the traffic node, Indicates the type of traffic node. Indicates the traffic connectivity of the node. represents the weight coefficient, Indicates the second weight coefficient of the traffic node.

[0085] Specifically, the average daily passenger flow of each traffic node, the type of the traffic node and the second traffic connectivity are input into a preset second weight algorithm for processing to obtain a second weight coefficient of each traffic node.

[0086] In one embodiment, before obtaining the first weight coefficient of each of the tourist attractions and the second weight coefficient of each of the traffic nodes, the process further includes standardizing the data in the road network data set. The standardization calculation formula is as follows:

[0087] ;

[0088] in, is the original eigenvalue, is the mean of the feature, is the standard deviation of the feature.

[0089] In one embodiment, the target impedance function, the preset first weight algorithm and the preset second weight algorithm are combined to construct a comprehensive weight coefficient calculation function. The comprehensive weight coefficient calculation function can be used for edge weight calculation in path planning.

[0090] The comprehensive weight coefficient calculation function is:

[0091] ;

[0092] This formula means that when selecting a path, it is more inclined to pass through nodes with greater comprehensive weights.

[0093] The road network data set, the weight coefficient level of each traffic node and the weight coefficient level of each tourist attraction are input into the preset path search algorithm, and the algorithm processing process of determining the shortest path between any two tourist attractions is as follows:

[0094] Initialize A Algorithm, set the starting node S and the target node T, create an open set and a closed set. Initially, the open set contains the starting node S and adjacent nodes, and the closed set is empty. The cumulative cost of the starting node , set the heuristic function , used to estimate the minimum cost from node j to target node T, is the Euclidean distance from node j to the target node T.

[0095] Select the one with the minimum total valuation from the open set Expand node j, then remove node j from the open set and add it to the closed set. For each adjacent node k of node j, calculate the moving cost from j to k. If the adjacent node k is not in the open set, add it to the open set. If the adjacent node k is not in the closed set, or the path cost to reach k through node j is lower, update the cost of k and set the parent node of k to j. , repeat the above steps until the target node T is found or all open set nodes are calculated.

[0096] Alternatively, it can also be understood as obtaining the comprehensive weight coefficients of node i and each adjacent node j; obtaining the Euclidean distance between each adjacent node j and the destination node T; inputting each comprehensive weight coefficient and each Euclidean distance into the preset valuation algorithm for calculation to obtain the cost estimate of each adjacent node; expanding the adjacent node j with the smallest cost estimate until the destination node T is found or it is determined that all nodes in the open set have been calculated. The preset valuation algorithm is the aforementioned minimum total valuation function.

[0097] Finally, according to the calculated shortest path, the complete path is reconstructed and saved by tracing back from the target node T to the starting node S. The generated path includes the node order, total path length, travel time, and comprehensive weight value. The paths of different starting nodes and target nodes are calculated multiple times, and the shortest paths between all highly correlated tourist attractions are summarized to obtain a global path data set.

[0098] In one embodiment, the generation of a multi-level highway network based on each of the shortest paths in the global path data set includes: obtaining the path weight of each of the shortest paths in the global path data set; obtaining the unit weight density of the road segments of each of the shortest paths in the global path data set; mapping the weight density per unit length of each of the shortest paths to the topological structure of the road network to obtain the multi-level highway network.

[0099] Specifically, the path weight of each shortest path in the global path data set is calculated. The path weight refers to the total weight of the shortest path. The corresponding calculation formula for the path weight is:

[0100] ;

[0101] Where n is the number of nodes on the shortest path, represents the first weight coefficient or the second weight coefficient, Represents the path weight.

[0102] After that, the unit weight density of each shortest path segment is calculated. The calculation formula for the unit weight density of the corresponding segment is:

[0103] ;

[0104] in, is the total length of the shortest path, is the path weight, The unit weight density of the road segment. The shortest path includes at least one road segment. In the case of including multiple road segments, the unit weight density of the road segment of the shortest path refers to the average value of the weight density of multiple road segments of the shortest path.

[0105] In one embodiment, the line density analysis results can be spatially connected with the road network, and the calculated path line density results can be mapped to the actual road network segments, so that each road segment can inherit its corresponding path weight density, and the formula is used. The weight density of the path Assign values ​​to the corresponding sections of the highway network. If a section of highway overlaps with multiple paths, their weight densities are accumulated. Formula The details are as follows:

[0106] ;

[0107] in, is the final weight of the road segment, M is the number of paths that overlap with the road segment, is the total length of the highway segment, is the weight density of path k, is the overlapping length of path k and the road segment.

[0108] In one embodiment, according to the weights assigned to the road network, the classification standard of the multi-level tourist road network is determined, and the tourist roads are divided into tourist trunk roads with "fast-forward" functions and tourist distribution roads and tourist scenic roads with "slow travel" functions. The tourist trunk roads are expressways, the tourist distribution roads are ordinary national and provincial roads, and the tourist scenic roads are rural roads. The classification standard is applied to divide all road sections into different levels, forming a network of "fast-forward" trunk roads and "slow travel" branch roads.

[0109] This application obtains a data set of all tourist attractions and transportation nodes in the target area, constructs a comprehensive weight model including node importance weights and road network impedance function, and uses A The algorithm calculates the shortest path between tourist attractions. The generated tourist path set is spatially connected with the road network, and the line density of the road network is analyzed in combination with the path weight density, and the road network is divided into multiple levels of "fast-in slow-out" tourist road networks.

[0110] In order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a grading device for a tourist highway, which corresponds to the above-mentioned grading method for tourist highways, and each step in the embodiment of the above-mentioned grading method for tourist highways is also fully applicable to the embodiment of the grading device for tourist highways.

[0111] like Figure 3 As shown, the grading device 400 for the tourist highway includes:

[0112] The data acquisition module 401 is used to acquire a road network data set, wherein the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area;

[0113] A weight level determination module 402 is used to determine the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and the pre-trained classification model;

[0114] The data set generation module 403 is used to input the weight coefficient level of each of the traffic nodes, the weight coefficient level of each of the tourist attractions and the road network data set into a preset path search algorithm for processing, and generate a global path data set, wherein the global path data set includes the shortest path between any two tourist attractions in the target area, and the shortest path is a tourist path with the lowest comprehensive cost;

[0115] The road network generation module 404 is used to generate a multi-level road network based on the shortest paths in the global path data set.

[0116] It should be noted that: the grading device for tourist roads provided in the above embodiment only uses the division of the above program modules as an example when grading tourist roads. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the grading device for tourist roads provided in the above embodiment and the grading method embodiment for tourist roads belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0117] Based on the hardware implementation of the above program modules and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides an electronic device. Figure 4 Only an exemplary structure of the electronic device is shown, not all structures, and it can be implemented as needed. Figure 4Partial or complete structure shown.

[0118] like Figure 4 As shown, the electronic device 500 provided in the embodiment of the present application includes: at least one processor 501, a memory 502, a user interface 503 and at least one network interface 504. The various components in the electronic device 500 are coupled together through a bus system 505. It can be understood that the bus system 505 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 505 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, in Figure 4 In the figure, various buses are labeled as bus system 505. Among them, the user interface 503 may include a display, keyboard, mouse, trackball, click wheel, key, button, touch pad or touch screen. The memory 502 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of these data include: any computer program used to operate on the electronic device.

[0119] The tourist highway classification method disclosed in the embodiment of the present application can be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the tourist highway classification method can be completed by the hardware integrated logic circuit or software instructions in the processor 501. The above-mentioned processor 501 can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 501 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 502. The processor 501 reads the information in the memory 502 and completes the steps of the tourist highway classification method provided in the embodiment of the present application in combination with its hardware.

[0120] In an exemplary embodiment, the electronic device may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned method.

[0121] It can be understood that the memory 502 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0122] In an exemplary embodiment, the present application also provides a computer storage medium, which can be a computer-readable storage medium, for example, a memory 502 storing a computer program, and the computer program can be executed by a processor 501 of an electronic device to complete the steps described in the method of the present application embodiment. The computer-readable storage medium can be a memory such as a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disk, or a CD-ROM.

[0123] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0124] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0125] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0126] The above is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for grading tourist roads, characterized in that: The method comprises: Acquire a road network data set, wherein the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area; Based on the road network data set and the pre-trained classification model, the weight coefficient level of each traffic node and each tourist attraction is determined; the weight coefficient level of the traffic node is determined based on the daily average passenger flow of the corresponding traffic node, and the weight coefficient level of the tourist attraction is determined based on the annual number of tourists at the corresponding tourist attraction; the pre-trained classification model is a Boosting algorithm; The weight coefficient level of each of the traffic nodes, the weight coefficient level of each of the tourist attractions and the road network data set are input into a preset path search algorithm for processing to generate a global path data set, wherein the global path data set includes the shortest path between any two tourist attractions in the target area, and the shortest path is a tourist path with the lowest comprehensive cost; Generate a multi-level highway network based on each of the shortest paths in the global path data set; Determining the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and the pre-trained classification model includes: obtaining a first weight coefficient of each tourist attraction and a second weight coefficient of each traffic node; inputting the road network data set, each first weight coefficient and each second weight coefficient into the pre-trained classification model to obtain the weight coefficient level of each tourist attraction and the weight coefficient level of each traffic node; The obtaining of the first weight coefficient of each of the tourist attractions comprises: obtaining the annual number of tourists of each of the tourist attractions; determining the first traffic connectivity of each of the tourist attractions based on the topological structure of the road network; inputting the annual number of tourists, the grade and the first traffic connectivity of each of the tourist attractions into a preset first weight algorithm for processing, and obtaining the first weight coefficient of each of the tourist attractions; The obtaining of the second weight coefficient of each of the traffic nodes comprises: obtaining the average daily passenger flow of each of the traffic nodes; determining the second traffic connectivity of each of the traffic nodes based on the topological structure of the road network; inputting the average daily passenger flow, type and second traffic connectivity of each of the traffic nodes into a preset second weight algorithm for processing to obtain the second weight coefficient of each of the traffic nodes.

2. The method according to claim 1, characterized in that The step of obtaining a road network data set includes: Obtain target road network data and target tourism resource data; Inputting the target road network data and the target tourism resource data into a preset geographic information system (GIS) model; Performing geometric analysis and topological construction on the target road network data through the preset GIS model to generate a topological structure of the road network; The preset GIS model is used to calculate and analyze the topological structure of the road network and the target tourism resource data to obtain the road network data set.

3. The method according to claim 1, characterized in that: The generating a multi-level highway network based on each of the shortest paths in the global path data set includes: Obtaining the path weight of each shortest path in the global path data set; Obtaining the unit weight density of the segments of each shortest path in the global path data set; The weight density per unit length of each of the shortest paths is mapped to the topological structure of the road network to obtain the multi-level highway network.

4. A grading device for tourist roads, characterized in that: The device comprises: A data acquisition module, used to acquire a road network data set, wherein the road network data set includes a plurality of tourist attractions and a plurality of traffic nodes in a target area; A weight level determination module is used to determine the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and a pre-trained classification model; the weight coefficient level of the traffic node is determined based on the average daily passenger flow of the corresponding traffic node, and the weight coefficient level of the tourist attraction is determined based on the annual number of tourists at the corresponding tourist attraction; the pre-trained classification model is a Boosting algorithm; the weight coefficient level of each traffic node and each tourist attraction based on the road network data set and the pre-trained classification model is determined, including: obtaining a first weight coefficient of each tourist attraction and a second weight coefficient of each traffic node; inputting the road network data set, each of the first weight coefficients and each of the second weight coefficients into the pre-trained classification model to obtain the weight coefficient level of each tourist attraction. The weight coefficient level, and the weight coefficient level of each of the traffic nodes; the obtaining of the first weight coefficient of each of the tourist attractions, including: obtaining the annual number of tourists at each of the tourist attractions; determining the first traffic connectivity of each of the tourist attractions based on the topological structure of the road network; inputting the annual number of tourists, level and first traffic connectivity of each of the tourist attractions into a preset first weight algorithm for processing, to obtain the first weight coefficient of each of the tourist attractions; the obtaining of the second weight coefficient of each of the traffic nodes, including: obtaining the average daily passenger flow of each of the traffic nodes; determining the second traffic connectivity of each of the traffic nodes based on the topological structure of the road network; inputting the average daily passenger flow, type and second traffic connectivity of each of the traffic nodes into a preset second weight algorithm for processing, to obtain the second weight coefficient of each of the traffic nodes; A data set generation module, used for inputting the weight coefficient level of each of the traffic nodes, the weight coefficient level of each of the tourist attractions and the road network data set into a preset path search algorithm for processing, and generating a global path data set, wherein the global path data set includes the shortest path between any two tourist attractions in the target area, and the shortest path is a tourist path with the lowest comprehensive cost; The road network generation module is used to generate a multi-level road network based on each of the shortest paths in the global path data set.

5. An electronic device, characterized in that: The method comprises a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the method according to any one of claims 1 to 3 when running the computer program.

6. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images