Scenic area touring path planning method and system fused with real-time traffic

Abstract

The invention provides a scenic spot touring path planning method and system fused with real-time traffic, and relates to the technical field of touring path planning. The method comprises the following steps: collecting facility connection data of a target scenic area and historical touring record data of a plurality of users, extracting a touring movement track of each user from the historical touring record data, identifying a plurality of stay nodes included in each touring movement track, extracting a plurality of track fragments of each touring movement track, and storing the plurality of track fragments in the target scenic area; determining a plurality of candidate track structures according to the plurality of track segments, extracting a path signature of each candidate track structure, determining a candidate traffic structure of each candidate track structure, constructing a touring structure map of the target scenic area, and obtaining a touring structure map of the target scenic area after obtaining real-time position data and real-time traffic data of the target user. And performing real-time touring path planning on the target user based on the touring structure map, and generating a real-time touring planning strategy of the target user. According to the invention, personalized scenic spot touring path recommendation is provided for the user.

Description

Technical Field

[0001] This invention relates to the field of tour route planning technology, and in particular to a method and system for planning scenic tour routes that integrates real-time traffic. Background Technology

[0002] With the rapid development of the tourism industry, sightseeing has gradually become an important way for people to relax and enjoy themselves. When visiting scenic spots, tourists often face diverse needs. In addition to their interest in the attractions themselves, they also have higher expectations for the choice of tour routes, time efficiency, comfort, and personalization.

[0003] Some scenic area route planning techniques rely on traditional route calculation methods, typically based on the scenic area's road network structure, to calculate the shortest or optimal path from the starting point to the destination. These methods perform well in many scenarios. However, with the diversification of tourist needs, traditional route planning methods are gradually revealing their limitations. In tourist areas, the experience of some tourists depends not only on the choice of the shortest path but also on many other factors, such as personal preferences, the level of crowding at attractions, and time constraints. Furthermore, the real-time changes in tourist flow and traffic conditions within the scenic area mean that traditional static route planning cannot meet the flexible needs of tourists.

[0004] Therefore, how to provide tourists with more flexible and personalized route recommendations in a dynamic environment has become an important technical issue in improving the tourist experience. Summary of the Invention

[0005] To address the aforementioned technical issues, this invention proposes a method and system for planning scenic tour routes that integrates real-time traffic data. The aim is to provide tourists with flexible and personalized tour route recommendations, thereby enhancing their experience in scenic areas.

[0006] To achieve the above objectives, the first aspect of the present invention provides a method for planning scenic tour routes that integrates real-time traffic, comprising:

[0007] Collect facility connectivity data of the target scenic area and historical visit record data of multiple users. Based on the facility connectivity data, determine multiple facility units and path units of the target scenic area. Extract the visit movement trajectory of each user from the historical visit record data. The visit movement trajectory includes the user's location data at multiple sampling points.

[0008] Identify multiple stop nodes included in each tour movement trajectory, determine the affiliation structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the affiliation structure of the stop nodes.

[0009] Multiple candidate trajectory structures are determined based on multiple trajectory segments. The path signature of each candidate trajectory structure is extracted. The candidate passage structure of each candidate trajectory structure is determined based on the path signature and multiple tour movement trajectories.

[0010] A tour structure map of the target scenic area is constructed based on multiple facility units, path units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target users, real-time tour path planning is performed on the target users based on the tour structure map, and a real-time tour planning strategy for the target users is generated.

[0011] Preferably, each tour movement trajectory includes multiple stop nodes, and the attribution structure of each stop node is determined based on multiple facility units and path units. Based on the attribution structure of the stop nodes, multiple trajectory segments of each tour movement trajectory are extracted, including:

[0012] Each tour movement trajectory is processed by sliding window to determine the maximum movement distance within each window. Multiple stop windows are identified based on the maximum movement distance, and the stop node corresponding to the stop window is determined based on the position data of multiple sampling points in the stop window.

[0013] Based on the location areas corresponding to the facility units and path units, the structural unit to which each stop node belongs is determined, and the belonging structure of each stop node is obtained. Multiple sets of any two adjacent belonging structures in the tour movement trajectory are extracted to obtain multiple trajectory segments contained in the tour movement trajectory.

[0014] Preferably, extracting the path signature for each candidate trajectory structure includes:

[0015] Determine the starting structure and target structure of each trajectory segment, determine the multiple structural combinations contained in multiple trajectory segments, and obtain multiple candidate trajectory structures corresponding to multiple trajectory segments;

[0016] Multiple trajectory segments are grouped based on multiple candidate trajectory structures, a common sample set for each candidate trajectory structure is constructed, the structural unit to which each trajectory segment in the common sample set belongs at different sampling points is determined, and the trajectory vector of each trajectory segment is constructed.

[0017] Based on multiple trajectory vectors, a segment distance matrix is ​​constructed for the common sample set. Multiple tour modes in the common sample set are identified based on the segment distance matrix. Local tour paths for each tour mode are extracted. Based on the starting structure, target structure, and multiple local tour paths of the candidate trajectory structure, a path signature of the candidate trajectory structure is generated.

[0018] Preferably, the candidate passage structure for determining each candidate trajectory structure based on path signatures and multiple tour movement trajectories includes:

[0019] Perform popularity analysis on multiple local tour paths in each path signature, including counting the total number of segments contained in the tour mode to which each local tour path belongs, and calculating the popularity parameter of each local tour path based on the total number of segments contained in the tour mode.

[0020] Congestion sensitivity analysis is performed on each local tour path based on multiple tour movement trajectories. This includes calculating the trajectory structure window heat of candidate trajectory structures in multiple observation windows based on multiple tour movement trajectories, and calculating the local path heat of each local tour path in multiple observation windows. The trajectory structure window heat sequence of candidate trajectory structures with respect to multiple observation windows and the local path heat sequence of each local tour path with respect to multiple observation windows are constructed. Congestion sensitivity parameters of each local tour path are calculated based on the trajectory structure window heat sequence and the local path heat sequence.

[0021] Based on multiple popularity parameters and congestion sensitivity parameters, multiple candidate traffic structures are generated for each candidate trajectory structure. The candidate traffic structure includes one local tour path in the path signature of the candidate trajectory structure, as well as the popularity parameters and congestion sensitivity parameters corresponding to the local tour path.

[0022] Preferably, the real-time tour path planning for the target user based on the tour structure map, and the generation of the target user's real-time tour planning strategy, include:

[0023] The system acquires the target user's intended structural area and intended tour needs. Based on real-time location data and intended structural area, it determines the target trajectory structure that matches the target user from the tour structure map. Based on the intended tour needs and real-time traffic data, it determines the tour recommendation degree of multiple candidate passage structures in the target trajectory structure. Based on the tour recommendation degree, it determines the target user's target passage structure and generates a real-time tour planning strategy.

[0024] Preferably, the determination of the tour recommendation degree for multiple candidate passage structures in the target trajectory structure based on intended tour needs and real-time traffic data includes:

[0025] Based on the target users' intended travel needs, the popularity weight and congestion weight of the target users are determined. Based on the popularity weight and the popularity parameters of local travel routes, the popularity impact score of each local travel route is calculated. Based on real-time traffic data, the first congestion impact score of each local travel route is calculated and determined. The first congestion impact score is corrected by the congestion sensitivity parameter to generate the second congestion impact score. Based on the congestion weight, the popularity impact score and the second congestion impact score are integrated to obtain the travel recommendation degree of the candidate traffic structure.

[0026] A second aspect of this invention provides a scenic area tour route planning system integrating real-time traffic, used to implement the aforementioned scenic area tour route planning method integrating real-time traffic, comprising:

[0027] The tour data acquisition module is used to collect facility connectivity data of the target scenic area and historical tour record data of multiple users. Based on the facility connectivity data, it determines multiple facility units and path units of the target scenic area. It extracts the tour movement trajectory of each user from the historical tour record data. The tour movement trajectory includes the user's location data at multiple sampling points.

[0028] The trajectory segment extraction module is used to identify multiple stop nodes included in each tour movement trajectory, determine the belonging structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the belonging structure of the stop nodes.

[0029] The passage structure generation module is used to determine multiple candidate trajectory structures based on multiple trajectory segments, extract the path signature of each candidate trajectory structure, and determine the candidate passage structure of each candidate trajectory structure based on the path signature and multiple tour movement trajectories.

[0030] The tour route planning module is used to construct a tour structure map of the target scenic area based on multiple facility units, route units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target user, it performs real-time tour route planning for the target user based on the tour structure map and generates a real-time tour planning strategy for the target user.

[0031] The present invention has the following beneficial effects:

[0032] This invention analyzes the historical travel trajectories of multiple users to construct a travel structure map reflecting the dynamic traffic patterns of a scenic area. Based on the identification of dwelling nodes and the analysis of trajectory segments, candidate trajectory structures are extracted. The popularity and congestion sensitivity of local travel routes are quantified through path signatures. During the planning stage, the adaptation status of multiple travel routes to user preferences is analyzed by combining user intentions and real-time traffic data. This generates travel recommendations that take into account both personalized preferences and real-time traffic conditions, thereby improving the tourist experience in the scenic area. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating a scenic area tour route planning method that integrates real-time traffic, as provided in one embodiment of the present invention.

[0034] Figure 2 This is a schematic diagram of a scenic area tour route planning system that integrates real-time traffic, provided as one embodiment of the present invention. Detailed Implementation

[0035] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0036] Please see Figure 1 The first aspect of this invention provides a method for planning scenic area tour routes that integrates real-time traffic, the method comprising:

[0037] Step S1: Collect facility connectivity data of the target scenic area and historical visit record data of multiple users. Based on the facility connectivity data, determine multiple facility units and path units of the target scenic area, and extract the visit movement trajectory of each user from the historical visit record data.

[0038] Specifically, the data on the connectivity of facilities in the target scenic area and the historical visit records of multiple users are first collected as the data basis for route planning. The connectivity data can be derived from the construction and design data of the scenic area, and the historical visit record data is obtained by recording through the user's smart mobile device after authorization. This embodiment does not specifically limit these data.

[0039] Facility connectivity data includes the distribution of various facilities and paths within the scenic area, such as attractions, dining areas, rest areas, and restrooms, as well as the location information of connecting paths like trails, bridges, and roads. Based on this connectivity data, the overall layout of the target scenic area can be determined. Multiple facility units representing different attraction areas and functional zones, along with path units representing various connecting paths, collectively describe the internal road network structure of the scenic area. Historical visitor record data includes user movement information during their visit within the target scenic area, such as geolocation data corresponding to different timestamps. Through this historical visitor record data, each visitor's movement trajectory can be extracted, including the user's location data at different sampling points, to reconstruct the visitor's route and walking path.

[0040] Step S2: Identify the multiple stop nodes included in each tour movement trajectory, determine the affiliation structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the affiliation structure of the stop nodes.

[0041] Specifically, for different users' travel trajectories, multiple stopping points are identified within the trajectory. When a user stays at a certain location within the scenic area for a period of time, that location can be considered a stopping point. Combining the scenic area's structural layout and multiple stopping points, multiple trajectory segments are extracted from the travel trajectory, representing different movement processes of the user within the scenic area. Each trajectory segment can consist of the travel path of the tourist between two or more stopping points.

[0042] As an optional implementation process, the process of identifying dwell nodes and extracting trajectory segments includes:

[0043] For each tour movement trajectory, a sliding window process is applied to determine the maximum movement distance within each window. The window size can be set according to actual needs, and can be a certain duration or a fixed number of sampling points. For multiple sampling points within a sliding window, the distance between any two sampling points is calculated based on the position data of the sampling points, and the maximum distance is recorded as the maximum movement distance.

[0044] Multiple dwelling windows are identified based on the maximum movement distance, and the corresponding dwelling node is determined based on the location data of multiple sampling points within each dwelling window. In this process, if a user's activity range within a relatively small area within a certain time period, the user is considered to be in a dwelling state during that time. For example, in a window of duration T, if the user's maximum movement distance is less than a threshold R, the user is considered to have engaged in dwelling behavior within that window, and this window is recorded as a dwelling window. The duration and threshold can be reasonably set based on the scenic area's scenario and user needs; this embodiment does not impose specific limitations on them. After determining multiple dwelling windows, the corresponding dwelling node for each dwelling window is determined, for example, by taking the average of the corresponding positions of multiple sampling points.

[0045] After identifying multiple rest points along each visitor's movement path, the structural unit to which each rest point belongs is determined based on the location areas corresponding to facility units and path units, thus obtaining the structure to which each rest point belongs. Rest points may be located at an entrance / exit of a scenic spot, at the intersection of a main trail, or within various structures such as scenic spots and rest areas within the scenic area. Based on the specific areas covered by these structural units (facility units and path units) within the scenic area, it can be determined which specific structural unit each rest point belongs to. For example, one rest point might belong to one of the scenic area's entrances, while another might belong to a rest area, thus determining the structure to which each rest point belongs.

[0046] Based on this, for any given travel trajectory, multiple sets of any two adjacent attribution structures are extracted from the trajectory to form multiple trajectory segments. Each trajectory segment connects two different stop nodes, i.e., two adjacent stop nodes in the trajectory. The attribution structure of the stop nodes is used to help confirm the start and end positions of the trajectory segments.

[0047] Step S3: Determine multiple candidate trajectory structures based on multiple trajectory segments, extract the path signature of each candidate trajectory structure, and determine the candidate passage structure of each candidate trajectory structure based on the path signature and multiple tour movement trajectories.

[0048] Specifically, after extracting multiple trajectory segments, multiple candidate trajectory structures are constructed based on these segments. Feasible travel routes are then formed by merging these trajectory segments. Different candidate trajectory structures represent local dwelling areas frequently chosen by tourists within the scenic area; for example, after staying in one area, a user often chooses to stay in another. During the journey from one area to another, there are usually multiple travel routes to choose from. Further analysis of the travel trajectories of multiple users is conducted to construct path signatures describing each candidate trajectory structure, i.e., multiple routes that can be chosen during the journey from one area to another. By analyzing the actual choices of multiple users regarding these routes, representative candidate travel structures are extracted, representing common tourist travel routes between two areas.

[0049] As an optional implementation, extracting the path signature for each candidate trajectory structure includes:

[0050] For multiple candidate trajectory structures, the starting and target structures of each trajectory segment are first determined, i.e., the structures corresponding to the starting and ending stop nodes. For the extracted trajectory segments, the starting and target structures of some segments may belong to the same combination. Statistical analysis is performed on multiple trajectory segments to determine multiple structural combinations contained in the multiple trajectory segments, which serve as multiple candidate trajectory structures corresponding to the multiple trajectory segments. Each candidate trajectory structure represents a choice of tour stopping mode, such as stopping in one area and then stopping in another area. It is worth noting that, considering that some structural combinations only appear in the tour movement trajectories of a few individuals, those skilled in the art can conceive of removing structural combinations with low frequency of occurrence according to actual needs, in order to retain multiple representative candidate trajectory structures.

[0051] After identifying multiple candidate trajectory structures, multiple trajectory segments are grouped based on these structures to construct a common sample set for each candidate trajectory structure. For example, all trajectory segments from A to B are grouped together, and a corresponding common sample set is constructed. For multiple trajectory segments in the common sample set, the structural unit to which different sampling points belong can be determined, which is the same method used to determine the structure to which the stopping node belongs. Finally, the trajectory vector for each trajectory segment is constructed, including the starting structure and target structure of the trajectory segment, as well as the structural unit corresponding to each sampling point in the segment.

[0052] Based on multiple trajectory vectors, a segment distance matrix is ​​constructed for each travel sample set. This process considers that each trajectory vector shares only the start and end points, while the number of sampling points varies in dimensionality. In this case, the DTW (Dynamic Time Warping) distance between two trajectory vectors is calculated to construct a segment distance matrix for multiple trajectory segments. Each element in the matrix represents the similarity between two trajectory segments. Clustering algorithms such as K-means and hierarchical clustering are then used to cluster the multiple trajectory segments in the travel sample set. Finally, multiple tour patterns in the travel sample set are identified based on the segment distance matrix. Each tour pattern reflects the frequently chosen path by tourists when moving from one structural unit to another. Based on this, local tour paths for each tour pattern are extracted. Path signatures for candidate trajectory structures are generated based on the starting structure, target structure, and multiple local tour paths.

[0053] The extraction of local tour paths involves synchronizing the starting and target structures of the local tour path with those of the candidate trajectory structure. Using the starting structure of the candidate trajectory structure as a benchmark, the next structural unit adjacent to the starting structure in each trajectory segment of the common sample set is determined. The structural unit with the highest frequency among these units is selected as the next structural unit adjacent to the starting structure in the local tour path. This process is repeated using this structural unit as a benchmark. Simultaneously, using the target structure of the candidate trajectory structure as a benchmark, the previous structural unit adjacent to the starting structure in each trajectory segment of the common sample set is determined. The structural unit with the highest frequency among these units is selected as the previous structural unit adjacent to the target structure in the local tour path. This process is repeated until the structural units determined in both forward and reverse order are the same, thus generating the local tour path for the tour mode. It is worth noting that the overall paths of multiple trajectory segments within the same tour mode exhibit high similarity. Due to individual preferences, some individuals may have missing or added structural units compared to the local tour path. Selecting multiple frequently occurring structural units can effectively represent the common choices of most users in the tour mode.

[0054] As an optional implementation process, the candidate passage structure for each candidate trajectory structure is determined based on path signatures and multiple tour movement trajectories, including:

[0055] A popularity analysis is performed on multiple local tour paths within each path signature. This includes counting the total number of segments contained in the tour pattern to which each local tour path belongs. The number of trajectory segments contained in a tour pattern represents the number of times tourists have traversed that path in historical data. Combining the total number of segments contained in multiple tour patterns, the total number of segments contained in the tour pattern to which each local tour path belongs is normalized to obtain a popularity parameter for each local tour path. This parameter represents the popularity of different local tour paths within the candidate trajectory structure.

[0056] Congestion sensitivity analysis is performed on each local tour path based on multiple tour movement trajectories. This includes calculating the popularity of candidate trajectory structures within multiple observation windows based on multiple tour movement trajectories, and calculating the popularity of each local tour path within multiple observation windows. Specifically, based on the time information corresponding to the tour movement trajectories, multiple observation windows are determined based on a fixed duration, such as half an hour per window. Within each observation window, the total number of users in each local tour path, as well as the total number of users across multiple local tour paths, are counted to obtain the popularity of the candidate trajectory structure within the observation window and the popularity of the tour movement trajectory within the local path of the observation window.

[0057] Based on the heat dissipation of multiple trajectory structure windows, a heat dissipation sequence of the candidate trajectory structure with respect to multiple observation windows is constructed. Similarly, based on the heat dissipation of multiple local paths for each local tour path, a local path heat dissipation sequence of each local tour path with respect to multiple observation windows is constructed. Finally, correlation analysis is performed on the two heat dissipation sequences. Based on the trajectory structure window heat dissipation sequence and the local path heat dissipation sequence, a congestion sensitivity parameter for each local tour path is calculated. A higher congestion sensitivity parameter indicates a closer correlation between the path's congestion level and the total number of travelers, indicating a higher congestion sensitivity for the path.

[0058] Based on multiple popularity parameters and congestion sensitivity parameters, multiple candidate traffic structures are generated for each candidate trajectory structure. Each candidate traffic structure includes one local tour path in the path signature of the candidate trajectory structure, as well as the popularity parameters and congestion sensitivity parameters corresponding to the local tour path.

[0059] Step S4: Construct a tour structure map of the target scenic area based on multiple facility units, path units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target user, perform real-time tour path planning for the target user based on the tour structure map and generate a real-time tour planning strategy for the target user.

[0060] Specifically, after extracting multiple candidate access structures, a visitor structure map of the target scenic area is constructed using multiple facility units and path units as base nodes. Multiple access paths between any two base nodes are then determined based on the candidate access structures. This describes one or more selectable access relationships between any two stopping points within the scenic area.

[0061] Once the real-time location and traffic data of target tourists are obtained, real-time tour route planning can be performed based on the tour structure map. Combining the tourist's current location and desired next destination, and taking into account the user's actual needs regarding the scenic area's popularity and congestion levels, along with real-time traffic information, a suitable real-time tour planning strategy is generated. This provides personalized and dynamically adjustable tour routes for different tourists, responding dynamically to real-time changes within the scenic area and flexibly adjusting according to tourist preferences and real-time conditions, thus providing a better tour experience.

[0062] As an optional implementation process, real-time tour path planning for target users based on tour structure maps, and the generation of real-time tour planning strategies for target users, include:

[0063] The system acquires the target user's intended structural area and desired travel needs. Based on real-time location data and the intended structural area, it determines the target trajectory structure matching the target user from the travel structure map. The intended structural area specifically refers to the structural area the user wants to visit next, which could be a scenic spot or a nearby functional area. After determining the user's intended structural area, based on the structural units corresponding to that area and the structural units where the user's real-time location data is located, it determines the target trajectory structure corresponding to the current needs from the travel structure map. For multiple candidate passage structures included in the target trajectory structure, it further performs adaptation analysis by combining intended travel needs and real-time traffic data. Based on the intended travel needs and real-time traffic data, it determines the travel recommendation degree of multiple candidate passage structures in the target trajectory structure. Finally, based on the travel recommendation degree, it determines the target user's target passage structure and generates a real-time travel planning strategy.

[0064] Intended tour demand represents a user's acceptance of congestion and preference for certain routes during their tour. For calculating tour recommendation, the target user's popularity and congestion weights are first determined based on their intended tour demand. If a user prefers more popular routes, the route's popularity weight is higher; if a user is more concerned with avoiding densely populated areas, the popularity weight is lower, and vice versa. The quantification of popularity and congestion weights can be achieved by providing users with a manual selection method via smart mobile devices. Alternatively, those skilled in the art can use appropriate methods based on the specific application scenario to quantify the user's personalized needs.

[0065] After determining the popularity weight and congestion weight, the product of the popularity weight and the popularity parameters of the local tour route is calculated as the popularity impact score of the local tour route. A first congestion impact score is then calculated for each local tour route based on real-time traffic data. For the first congestion impact score, the total number of people in the user's current structural unit can be determined using real-time traffic data, and the corresponding first congestion impact score under the current passenger flow can be determined based on multiple pre-built bins. For example, using 5 people as a baseline, starting from 0, a passenger flow bin is created for every additional 5 people. A congestion value is assigned to each passenger flow bin; for example, within the range of 0 to 100, the congestion score of the passenger flow bin increases equally from 0.5 in ascending order. The scheme of determining the congestion score for different passenger flow ranges by dividing the congestion bins based on the total capacity of the structural unit is a well-known technique, and this embodiment does not specifically limit it. The above is merely an exemplary scheme for determining the first congestion impact score of a structural unit under a specific passenger flow based on real-time traffic data.

[0066] Based on this, a second congestion impact score is generated by modifying the first congestion impact score using a congestion sensitivity parameter. A larger congestion sensitivity parameter indicates a higher sensitivity of the corresponding local tour path to congestion. In this case, the more people in the user's current structural unit, the more likely the local tour path with a large congestion sensitivity parameter is to experience congestion during the user's subsequent tour. Finally, the tour recommendation degree of the candidate passage structure is obtained by integrating the popularity impact score and the second congestion impact score based on the congestion weight. The product of the congestion weight and the second congestion impact score can be calculated as the target congestion impact score, and the difference between the popularity impact score and the target congestion impact score can be calculated as the tour recommendation degree. In this case, the popularity impact score of the candidate passage structure indicates that the corresponding path better meets the user's popularity needs, while a smaller target congestion impact score indicates that the potential congestion state of the corresponding path better meets the user's congestion needs. Finally, the candidate passage structure with the highest tour recommendation degree can be used as the tour path for the target user to travel to the intended structural area. This method yields the target user's real-time tour planning strategy, comprehensively considering the user's intended needs and integrating real-time traffic data to ensure personalized tour paths are provided for different users.

[0067] Please see Figure 2 Based on the same inventive concept, a second aspect of the present invention also provides a scenic area tour route planning system that integrates real-time traffic, comprising:

[0068] The tour data acquisition module is used to collect facility connectivity data of the target scenic area and historical tour record data of multiple users. Based on the facility connectivity data, it determines multiple facility units and path units of the target scenic area. It extracts the tour movement trajectory of each user from the historical tour record data. The tour movement trajectory includes the user's location data at multiple sampling points.

[0069] The trajectory segment extraction module is used to identify multiple stop nodes included in each tour movement trajectory, determine the belonging structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the belonging structure of the stop nodes.

[0070] The passage structure generation module is used to determine multiple candidate trajectory structures based on multiple trajectory segments, extract the path signature of each candidate trajectory structure, and determine the candidate passage structure of each candidate trajectory structure based on the path signature and multiple tour movement trajectories.

[0071] The tour route planning module is used to construct a tour structure map of the target scenic area based on multiple facility units, route units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target user, it performs real-time tour route planning for the target user based on the tour structure map and generates a real-time tour planning strategy for the target user.

[0072] The above are merely specific embodiments of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art. Parts not described in detail in this specification are prior art known to those skilled in the art.

Claims

1. A method for planning scenic tour routes that integrates real-time traffic, characterized in that, include: Collect facility connectivity data of the target scenic area and historical visit record data of multiple users. Based on the facility connectivity data, determine multiple facility units and path units of the target scenic area. Extract the visit movement trajectory of each user from the historical visit record data. The visit movement trajectory includes the user's location data at multiple sampling points. Identify multiple stop nodes included in each tour movement trajectory, determine the affiliation structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the affiliation structure of the stop nodes. Multiple candidate trajectory structures are determined based on multiple trajectory segments. The path signature of each candidate trajectory structure is extracted. Based on the path signature and multiple tour movement trajectories, the candidate passage structure of each candidate trajectory structure is determined. A tour structure map of the target scenic area is constructed based on multiple facility units, path units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target users, real-time tour path planning is performed on the target users based on the tour structure map, and a real-time tour planning strategy for the target users is generated.

2. The scenic area tour route planning method integrating real-time traffic as described in claim 1, characterized in that, Identify multiple stop nodes within each tour movement trajectory, determine the affiliation structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments for each tour movement trajectory based on the affiliation structure of the stop nodes, including: Each tour movement trajectory is processed by sliding window to determine the maximum movement distance within each window. Multiple stop windows are identified based on the maximum movement distance, and the stop node corresponding to the stop window is determined based on the position data of multiple sampling points in the stop window. Based on the location areas corresponding to the facility units and path units, the structural unit to which each stop node belongs is determined, and the belonging structure of each stop node is obtained. Multiple sets of any two adjacent belonging structures in the tour movement trajectory are extracted to obtain multiple trajectory segments contained in the tour movement trajectory.

3. The scenic area tour route planning method integrating real-time traffic according to claim 2, characterized in that, Extracting the path signature for each candidate trajectory structure includes: Determine the starting structure and target structure of each trajectory segment, determine the multiple structural combinations contained in multiple trajectory segments, and obtain multiple candidate trajectory structures corresponding to multiple trajectory segments; Multiple trajectory segments are grouped based on multiple candidate trajectory structures, a common sample set for each candidate trajectory structure is constructed, the structural unit to which each trajectory segment in the common sample set belongs at different sampling points is determined, and the trajectory vector of each trajectory segment is constructed. Based on multiple trajectory vectors, a segment distance matrix is ​​constructed for the common sample set. Multiple tour modes in the common sample set are identified based on the segment distance matrix. Local tour paths for each tour mode are extracted. Based on the starting structure, target structure, and multiple local tour paths of the candidate trajectory structure, a path signature of the candidate trajectory structure is generated.

4. The scenic area tour route planning method integrating real-time traffic as described in claim 3, characterized in that, Based on path signatures and multiple visit movement trajectories, the candidate passage structures for each candidate trajectory structure are determined as follows: Perform popularity analysis on multiple local tour paths in each path signature, including counting the total number of segments contained in the tour mode to which each local tour path belongs, and calculating the popularity parameter of each local tour path based on the total number of segments contained in the tour mode. Congestion sensitivity analysis is performed on each local tour path based on multiple tour movement trajectories. This includes calculating the trajectory structure window heat of candidate trajectory structures in multiple observation windows based on multiple tour movement trajectories, and calculating the local path heat of each local tour path in multiple observation windows. The trajectory structure window heat sequence of candidate trajectory structures with respect to multiple observation windows and the local path heat sequence of each local tour path with respect to multiple observation windows are constructed. Congestion sensitivity parameters of each local tour path are calculated based on the trajectory structure window heat sequence and the local path heat sequence. Based on multiple popularity parameters and congestion sensitivity parameters, multiple candidate traffic structures are generated for each candidate trajectory structure. The candidate traffic structure includes one local tour path in the path signature of the candidate trajectory structure, as well as the popularity parameters and congestion sensitivity parameters corresponding to the local tour path.

5. The scenic area tour route planning method integrating real-time traffic according to claim 4, characterized in that, Based on the tour structure map, real-time tour path planning is performed for target users, generating real-time tour planning strategies for target users, including: The system acquires the target user's intended structural area and intended tour needs. Based on real-time location data and intended structural area, it determines the target trajectory structure that matches the target user from the tour structure map. Based on the intended tour needs and real-time traffic data, it determines the tour recommendation degree of multiple candidate passage structures in the target trajectory structure. Based on the tour recommendation degree, it determines the target user's target passage structure and generates a real-time tour planning strategy.

6. The scenic area tour route planning method integrating real-time traffic according to claim 5, characterized in that, Based on intended travel needs and real-time traffic data, the recommended travel profiles for multiple candidate traffic structures within the target trajectory structure are determined, including: Based on the target users' intended travel needs, the popularity weight and congestion weight of the target users are determined. Based on the popularity weight and the popularity parameters of local travel routes, the popularity impact score of each local travel route is calculated. Based on real-time traffic data, the first congestion impact score of each local travel route is calculated and determined. The first congestion impact score is corrected by the congestion sensitivity parameter to generate the second congestion impact score. Based on the congestion weight, the popularity impact score and the second congestion impact score are integrated to obtain the travel recommendation degree of the candidate traffic structure.

7. A scenic area tour route planning system integrating real-time traffic, characterized in that, The system is used to implement the scenic area tour route planning method integrating real-time traffic as described in any one of claims 1-6, including: The tour data acquisition module is used to collect facility connectivity data of the target scenic area and historical tour record data of multiple users. Based on the facility connectivity data, it determines multiple facility units and path units of the target scenic area. It extracts the tour movement trajectory of each user from the historical tour record data. The tour movement trajectory includes the user's location data at multiple sampling points. The trajectory segment extraction module is used to identify multiple stop nodes included in each tour movement trajectory, determine the belonging structure of each stop node based on multiple facility units and path units, and extract multiple trajectory segments of each tour movement trajectory based on the belonging structure of the stop nodes. The passage structure generation module is used to determine multiple candidate trajectory structures based on multiple trajectory segments, extract the path signature of each candidate trajectory structure, and determine the candidate passage structure of each candidate trajectory structure based on the path signature and multiple tour movement trajectories. The tour route planning module is used to construct a tour structure map of the target scenic area based on multiple facility units, route units, and candidate access structures. After obtaining the real-time location data and real-time traffic data of the target user, it performs real-time tour route planning for the target user based on the tour structure map and generates a real-time tour planning strategy for the target user.

Images