Visual analysis method and device for traffic simulation decision and medium

Abstract

The invention discloses a visual analysis method and device for traffic simulation decision and a medium, and the method comprises the steps: obtaining input data which comprises a road network with a static attribute and an OD pair set containing an OD travel related attribute; modeling the road network into a directed graph; oD travel is distributed to paths and roads in the road network, and the actual traffic volume and the actual driving time of each road are calculated based on a traffic distribution algorithm; and constructing and displaying a map view and a comparison view according to the directed graph and the actual traffic volume and the actual driving time of each road. According to the method, road traffic planning is carried out on the road network, a map view supporting an interactive road network editing function and a comparison view combining a historical tree and a matrix are realized, and a new mode is provided for displaying attribute comparison of multiple road network states; and deep analysis and decision-making processes in geographic backgrounds and attribute contexts are supported.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a visual analysis method, device and medium for traffic simulation decision-making. Background Art

[0002] The existing traffic planning system is the foundation of an efficient traffic system, and any improper planning may lead to huge economic losses. Currently, designing or optimizing a road network is an important task in traffic planning, where each vertex represents an intersection and each directed edge represents a road segment from one vertex to another. Each road segment has an attribute, called capacity, which determines the number of vehicles that can freely pass through the road segment. An ideal road network has the best traffic efficiency while meeting traffic demand.

[0003] Traffic planning experts usually use traffic simulation to propose and carefully evaluate each possible strategy (for example, increasing capacity by widening roads) instead of directly modifying traffic facilities in urban space. For example, experts first identify inefficient road sections based on traffic observation data (such as speed and flow), then increase their capacity by widening them, and finally evaluate whether the entire traffic system has become more efficient under simulation conditions.

[0004] Currently, a variety of transportation planning platforms have been developed to help experts design and optimize road networks. However, the interaction methods of these platforms still mainly rely on basic user interface components such as clicks and input boxes. Users cannot interact with and modify the road network intuitively and conveniently. In addition, the current road network design process is usually iterative and trial-and-error, and experts need to constantly modify the network structure that has been adjusted in previous steps. However, existing platforms cannot efficiently support iterative operations such as tracking, rolling back, and branching between various design steps. Ultimately, the iterative process will produce multiple road network states, but existing platforms cannot effectively compare these states, limiting the ability of experts to make informed decisions.

[0005] Although visual analytics techniques combine intuitive visualization and interaction to enhance the capabilities of expert users, no existing techniques focus on road traffic planning scenarios. Therefore, existing techniques cannot effectively address the interaction and comparison problems in transportation network design and optimization. Summary of the invention

[0006] In order to solve at least one of the technical problems existing in the prior art to a certain extent, the present invention aims to provide a visual analysis method, device and medium for traffic simulation decision making.

[0007] The first technical solution adopted by the present invention is:

[0008] A visual analysis method for traffic simulation decision-making includes the following steps:

[0009] Obtain input data, wherein the input data includes a road network with static attributes and an OD pair set including OD travel related attributes;

[0010] The road network is modeled as a directed graph G = (V, E), where V represents a road intersection and E represents a road or road section;

[0011] Assign OD trips to paths and roads in the road network, and calculate the actual traffic volume on each road based on the traffic assignment algorithm. and actual travel time

[0012] According to the directed graph, the actual traffic volume of each road and actual travel time Build and display map views and comparison views;

[0013] The map view is used to implement interactive road network editing functions, and the comparison view is used to compare iteratively generated multi-state road network attributes.

[0014] Furthermore, in a directed graph, each road has four static properties: the starting intersection, the ending intersection, and the road capacity f e (the maximum number of vehicles that can pass per unit time) and free flow travel time Each road also has two dynamic attributes: actual traffic volume and actual travel time

[0015] OD trip is the smallest unit in traffic assignment. An OD trip represents a trip of one person between OD pairs. The path p = {..., e, ...} consists of a set of ordered edges. Each ordered edge e describes how to move from the starting point of the OD pair to the end point. For O in the OD pair, there is a path set P o ={…,p i ,…}, the actual number of vehicles passing through path p is recorded as The actual travel time of the vehicle through the path is expressed as For D in the OD pair, it is obtained by calculating the sum of the actual travel time of each road in path p.

[0016] Furthermore, the traffic assignment algorithm works as follows:

[0017] Describing the actual driving time based on the BPR function The actual traffic volume The dependency relationship is as follows:

[0018]

[0019] Assuming that the driver is not always able to accurately know the actual travel time of each route, the Logit choice model is used to describe the probability of choosing a route. The formula is as follows:

[0020]

[0021] In the formula, Represents the path set P o A path in For path The actual driving time;

[0022] The parameter θ is used to measure the driver's sensitivity to travel time. The smaller the θ value, the less sensitive the driver is to travel time and the more random the route selection is. The larger the θ value, the more sensitive the driver is to travel time and the more the route selection tends to avoid congestion.

[0023] Further, the functions of the map view include road network visualization, and the road network visualization includes visualization of road network structure and visualization of road network attributes;

[0024] 1) Visualization of road network structure: A directed graph is used to represent the structure of the road network, where nodes represent intersections and links represent road segments. Nodes are accurately placed on the map based on their geographical locations, and links connect corresponding nodes. For roads with two-way traffic, links are displayed separately on the map according to local traffic rules.

[0025] 2) Visualization of road network attributes: Multiple visual codes are used to represent the attributes of each road. Traffic flow is represented by the size of nodes and the width of links. The larger the node or the wider the link, the greater the flow. Driving time is coded with gradient colors. The first preset color indicates a driving time close to the free flow time, and the second preset color indicates a driving time much greater than the free flow time. Users can hover to view specific road attributes, including traffic flow and actual driving time.

[0026] Further, the map view includes functions of travel demand visualization: after receiving trigger information of a user selecting a road, displaying OD travel demand passing through the road;

[0027] The map view also includes functions of interactively modifying the road network: receiving interactive information input by the user, and directly modifying and displaying the road network on the map to simulate different road traffic decision strategies.

[0028] Further, the comparison view includes a history tree and a road network status matrix;

[0029] The history tree is used to display each iterative step in the modification process and allow the user to roll back or create a new modification branch;

[0030] The road network state matrix is ​​used to arrange roads in different states in a comparative manner, supports detailed comparison of multiple edge or node attributes, and displays attribute changes of each road in different states, so as to achieve detailed comparison of multiple road network states.

[0031] Furthermore, the nodes and edges of the history tree are color-coded to show the performance of each road network after modification:

[0032] Calculate optimization indicators This metric represents the total travel time of all vehicles in the network;

[0033] In the history tree, the border color of each state node (s node) indicates the difference in optimization indicators between the state and the initial state; the node border of the initial state is the third preset color, and the border color of all modified states will change according to the optimization effect: the fourth preset color indicates an improvement in the optimization effect, and the fifth preset color indicates a decrease in the optimization effect. The depth of the color indicates the degree of change in the indicator.

[0034] Furthermore, each row of the road network state matrix represents a road, and each column represents a specific road network state, thereby allowing users to intuitively compare road performances under different states on the same interface;

[0035] Each matrix cell uses road primitives to encode four main attributes of the road: road capacity, actual traffic flow, free-flow travel time, and actual travel time.

[0036] The second technical solution adopted by the present invention is:

[0037] An electronic device comprises a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a visual analysis method for traffic simulation decision-making as described above.

[0038] The third technical solution adopted by the present invention is:

[0039] A computer-readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, wherein the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a visual analysis method for traffic simulation decision-making as described above.

[0040] The fourth technical solution adopted by the present invention is:

[0041] A computer program product or a computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above method.

[0042] The beneficial effects of the present invention are: the road traffic planning performed on the road network by the present invention realizes a map view supporting interactive road network editing functions and a comparison view combining a history tree and a matrix, providing a new way to display the attribute comparison of multiple road network states, and supporting in-depth analysis and decision-making processes in a geographical background and attribute context. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 is a schematic diagram of a map view and a comparison view in an embodiment of the present invention; wherein, Figure 1 A in the middle is the map view. Figure 1 B is a comparative view, and the reference numerals P1, P2, and P3 respectively represent three road construction operations performed in the implementation method;

[0045] Figure 2 is a travel demand visualization effect diagram of a map view in an embodiment of the present invention; wherein, Figure 2 A and B in the middle show the travel demand of two opposite roads respectively;

[0046] Figure 3 is a schematic diagram of an interactive design based on a map view in an embodiment of the present invention; wherein, Figure 3 Figure A in the middle is a schematic diagram of the interactive mode of expanding / narrowing roads. Figure 3 B is a schematic diagram of the interactive method of improving / limiting road conditions. Figure 3 Figure C in the middle is a schematic diagram of deleting the road interaction mode. Figure 3 D in the middle is a schematic diagram of the interaction mode of the newly built road;

[0047] Figure 4 is a schematic diagram of a road primitive in an embodiment of the present invention;

[0048] Figure 5 It is a flowchart of the steps of a visual analysis method for traffic simulation decision-making in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0050] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0051] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0052] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0053] Technical explanation:

[0054] (1) Traffic simulation is an effective means to evaluate new policies and countermeasures in the process of traffic planning. Traffic simulation models can be divided into three types according to the spatial scale: macro, meso and micro.

[0055] 1) Macro. Macro simulation models focus on traffic distribution within cities. They are used in urban planning and aim to analyze and replicate the macro characteristics of traffic flows. The core idea is to allocate or simulate vehicles traveling on each edge (i.e., road) given a road network and the traffic demand between each pair of traffic nodes.

[0056] 2) Mesoscopic. Mesoscopic simulation models shift the focus to vehicle groups. One of the classic models was proposed by Lighthill and Whitham, which treats traffic flow as a fluid and simulates vehicle behavior based on fluid dynamics description. This model has been widely adopted by many studies.

[0057] 3) Microscopic. Microscopic simulation takes a single vehicle as the main body. It mainly simulates the driving behavior and interaction relationship of each vehicle based on the following model or lane changing model.

[0058] Traffic simulation platforms are an important means for domain experts to use traffic simulation models and complete traffic planning tasks. Current traffic simulation platforms, such as TransCAD, EMME, and PTV-Visum, support macro-level traffic assignment and visualization of simulation results, but these platforms lack support for continuous iterative modification of road networks and comparison of multiple states, so there is still room for improvement in user interaction and visualization.

[0059] (2) Traffic visualization analysis combines traffic visualization, user interaction, and advanced urban computing models to serve traffic applications that require expert participation in decision-making, such as traffic congestion tracking, mobility analysis, route planning, traffic prediction, and location selection. Traffic visual analysis has many applications in decision-making. In AllAborad, an algorithm will expand / extend the existing road network based on OD (origin-destination) requirements, and then interactive visualization helps experts compare the new network with the original network, but mainly relies on numerical indicators. ShuttleVis helps experts compare multiple automatically generated bus routes based on multiple numerical indicators. In addition to supporting the comparison of candidate options, BNVA also enables experts to manually guide Monte Carlo tree search and expand bus routes. Existing visualization analysis has not focused on road traffic planning and is limited to route-based or line-based forms, which focus on selecting or organizing location sequences. However, road traffic planning requires road network-based interactions that contain traffic semantics, such as adding edges to simulate the construction of new roads. In addition, statistical summary comparison visualizations of each line are insufficient for road network comparison because they cannot support detailed inspection of edge attributes required for road traffic planning.

[0060] Traffic visualization aims to present traffic data intuitively for understanding and reasoning. Traffic data can be divided into non-spatial and spatial traffic data. 1) Non-spatial traffic data can be visualized in many forms, not just geographical maps. Take the public transportation system as an example: the number of passengers can be visualized as an OD matrix, schedule delays can be displayed through Marey diagrams, and efficiency can be analyzed through isochronous flow diagrams. 2) Spatial traffic data is usually presented through map-based visualizations to better understand the spatial context. Sun et al. allow temporal traffic data visualization to be embedded in road networks. Lee et al. overlay traffic information (e.g., speed) on road networks on maps like most navigation platforms, but fail to support comparison between multiple such networks. Nevertheless, considering existing geographical network visualizations, comparing multiple road networks at the attribute level remains unexplored. In this study, we follow the approach in most navigation platforms and overlay visualizations of traffic data (e.g., traffic speed and flow) on road networks based on road segments. Comparing the attributes of multiple road networks is a challenging problem.

[0061] (3) The interaction and comparison of road networks is one of the core tasks of iterative traffic planning.

[0062] First, in the scenario of the present invention, the interaction of the road network realizes the modification of the road network and obtains a modified road network state as an alternative design scheme. The existing platform needs to provide a basic user interface for road network modification, allowing users to interact through mouse interaction or through input commands. Previous studies have shown that the interaction method that is closely integrated with the user's intrinsic understanding or real-world semantics is more intuitive and convenient. However, existing network interaction methods mainly focus on adjusting or exploring network layouts rather than modifying a single network layout. The method of Eichner et al. allows the structure and properties of the network to be modified, and is the most relevant method to the present invention in this scenario. However, the method lacks an intuitive interaction method corresponding to the actual traffic improvement semantics, and fails to achieve a mapping between the semantics of real road network improvements and modified network interactions.

[0063] In the scenario of the present invention, different road network states obtained by multiple traffic simulation decisions are a prerequisite for making wise decisions. The first step is to visually monitor the progress of iterative planning. Many analysis tools achieve this goal through visualization means, most of which display the history of states through timelines or node connection diagrams. We borrow from these methods to clearly display the relationships between historical states. However, road networks containing geographical backgrounds, structural details, and related attributes cannot be simply abstracted into a single graph for effective understanding and comparison. To this end, for geographical networks, they can be drawn as mini maps or superimposed on the same map in an edge stacking manner for comparison. These visualization techniques mainly support structural comparison through network transformation and optimized layout. However, they have difficulties in revealing the differences in multiple related edge attributes (such as traffic flow) in multiple geographical networks, and visualization alignment with existing sources remains a challenge.

[0064] In the present invention, we focus on the macroscopic simulation of traffic, namely, the road traffic planning on the road network, and realize a map view supporting interactive road network editing function and a comparison view combining history tree and matrix, providing a new way to display the attribute comparison of multiple road network states, supporting in-depth analysis and decision-making process in geographical background and attribute context.

[0065] Specifically, existing traffic simulation decision-making technologies face the following two challenges: 1) Interactive road network editing capabilities. In the real world, measures such as road construction, widening, and closure correspond to modifications to the properties or structure of the abstract road network. However, existing road network interactive tools mainly focus on adjusting or exploring network layouts. In addition, intuitive interactive methods should be closely integrated with experts' semantic understanding of real-world road traffic planning, but this area has not been fully developed and requires close cooperation with domain experts. 2) Intuitive comparison of iteratively generated multi-state road network attributes. The road network modification process is usually iterative and multi-path branching, resulting in multiple road networks with different states. Experts must monitor the different states of these road networks and compare them with each other. However, it is challenging to compare the relevant information of each edge and each vertex in multiple geospatial networks. It is not sophisticated enough to simply sort these different states by extracting some quantitative indicators (such as the average speed of the entire road network), because improved road segments may mask the impact of those deteriorated road segments. Although some existing geographic network visualization methods can support the comparison of network structures, they cannot support detailed comparison of multiple edge or node attributes.

[0066] To address the above challenges, the present invention implements two visualization views: a map view and a comparison view.

[0067] The map view is used to present the traffic status of the road network and allows users to interactively modify the road network directly in the spatial context. In the map view, users can 1) analyze the current status of the road network and identify inefficient sections through visualization, 2) flexibly simulate different response measures on the map, such as expanding or closing roads, and immediately view the new traffic status after modifying the road network.

[0068] The comparison view is designed to help users compare road networks in different states generated by multiple iterative modifications. This view includes a history tree and a network state matrix. 1) The history tree displays each iterative step in the modification process and allows users to roll back or create new modification branches; 2) The network state matrix arranges roads in different states in a comparative manner, supports detailed comparison of multiple edge or node attributes, and displays the attribute changes of each road in different states, enabling detailed comparison of multiple network states.

[0069] Example 1

[0070] like Figure 5 As shown, this embodiment provides a visual analysis method for traffic simulation decision-making, comprising the following steps:

[0071] S1. Obtain input data, wherein the input data includes a road network with static attributes and an OD pair set including OD travel related attributes;

[0072] S2. Model the road network as a directed graph G = (V, E), where V represents a road intersection and E represents a road or road section;

[0073] S3: Assign OD trips to paths and roads in the road network and calculate the actual traffic volume on each road based on the traffic assignment algorithm. and actual travel time

[0074] S4. According to the directed graph, the actual traffic volume of each road and actual travel time Build and display map views and comparison views;

[0075] The map view is used to implement interactive road network editing functions, and the comparison view is used to compare iteratively generated multi-state road network attributes.

[0076] In this embodiment, the input data includes a road network with static attributes and a set of OD pairs related to OD trips. These OD trips are assigned to paths and roads in the road network, and the actual traffic volume of each road is calculated based on the traffic assignment algorithm. and actual travel time These data provide a basis for subsequent interactive traffic planning and multi-state road network comparison. This embodiment constructs a map view and a comparison view, and the intuitive map view realizes flexible modification of the road network and real-time status feedback, and realizes the close integration of the interaction mode of the abstract road network with the semantics of the actual road traffic planning. In addition, this embodiment implements a history tree that supports iterative road traffic planning process tracking and a road network state matrix that can quickly compare the simulation results of multiple road network states, effectively tracking and comparing multiple iterative states, combined with filtering and sorting functions, to help users quickly locate key roads, significantly improving the interactivity, operability, scientificity and efficiency of road traffic planning.

[0077] The above method is explained in detail below with reference to the accompanying drawings and specific implementation methods.

[0078] (1) Data input

[0079] In the embodiment of the present invention, the input data is a road network with static attributes and an OD pair set containing OD travel related attributes. The road network is modeled as a directed graph G = (V, E), where V is a vertex set (representing road intersections) and E is an edge set (representing roads or road sections). Each road e has four static attributes: the starting and ending intersections, the road capacity (the maximum number of vehicles that can pass per unit time), and f e and free flow travel time In addition, each road has two dynamic attributes: actual traffic volume and actual travel time These attributes together determine the current state of the road, and the state of all roads combined reflects the state of the entire road network.

[0080] OD trip is the smallest unit in traffic allocation. An OD trip represents a trip of one person between OD pairs. The travel demand of an OD pair corresponds to the number of OD trips between OD pairs. These demands are usually obtained through surveys or traffic measurement-based methods. Path p = {..., e, ...} consists of a set of ordered edges. Each ordered edge e describes how to move from the starting point of the OD pair to the end point. For an OD pair o, there can be multiple paths P o ={…,p i ,…}. The actual number of vehicles passing through path p is recorded as The actual travel time of the vehicle through the path is expressed as The latter is obtained by calculating the sum of the actual travel time for each road in path p.

[0081] (2) Traffic Assignment Algorithm

[0082] The traffic assignment process simulates the path selection behavior of drivers, obtains OD trips, assigns each OD trip to a path in the road network, and finally determines the state of the road. Usually, drivers will choose the path with the shortest estimated travel time, but as the number of vehicles increases, the actual travel time will exceed the free flow travel time. This invention is based on the BPR function

[39] Describe the actual travel time The actual traffic volume The dependency relationship is the following formula:

[0083]

[0084] This embodiment adopts the mature SUE (Stochastic User Equilibrium) model, assuming that the driver is not always able to accurately know the actual travel time of each route, and uses the Logit selection model to describe the probability of path selection. The formula is as follows:

[0085]

[0086] The model uses the parameter θ to represent the user's sensitivity to travel time. The smaller the θ value, the less sensitive the driver is to travel time and the more random the route selection is. The larger the θ value, the more sensitive the driver is to travel time and the more inclined the route selection is to avoid congestion. In this paper, we set θ to 0.3 based on classic research

[40] .

[0087] (3) Map view

[0088] See also Figure 1 A in the figure, the map view is used to implement interactive road network editing functions:

[0089] a) Road network visualization: Road network visualization can be divided into visualization of road network structure and visualization of road network attributes.

[0090] Visualization of road network structure: Embodiments of the present invention use a node-link graph to represent the structure of a road network, where nodes represent intersections and links represent road segments. Nodes are accurately placed on the map based on their geographic locations, and links connect corresponding nodes. For roads with two-way traffic, links are displayed on the map separately according to local traffic rules (e.g., driving on the left or driving on the right).

[0091] Visualization of road network attributes: The embodiments of the present invention use multiple visual codes to represent the attributes of each road. Traffic flow is represented by the size of the node and the width of the link. The larger the node or the wider the link, the greater the traffic flow. The driving time is coded in a green-red gradient color, with green indicating a driving time close to the free flow time and red indicating a driving time much greater than the free flow time. Users can view specific road attributes, including traffic flow and actual driving time, by hovering.

[0092] b) Travel demand visualization: Users can double-click a road to trigger the travel demand visualization mode, and the system will display the OD travel demand passing through the road, such as Figure 2 As shown. Each node uses a pie chart to show the number of OD trips that depart and arrive, where the pink part reflects the number of OD trips that arrive and the blue part reflects the number of OD trips that depart. The size of the pie chart represents the total number of OD trips at the node.

[0093] c) Interactive modification of road network: Users can interactively modify the road network directly on the map, such as expanding / narrowing roads, improving / restricting road conditions, closing roads or building new roads. Each modification is implemented through intuitive mouse operations. After the modification, the system will recalculate the road network status in real time and display the new results. The map view provides flexible interactive operations, allowing users to modify the road network directly on the map to simulate different road traffic decision strategies:

[0094] Widening / Narrowing of Roads: e.g. Figure 3 As shown in A, the user can click on a road, select the "Expand / Reduce" option, and increase or decrease the capacity of the road by dragging to adjust the width of the road or accurately entering the capacity value.

[0095] Improved / restricted road conditions: e.g. Figure 3 As shown in B, users can adjust the free flow time of the road by clicking the "Improve / Restrict" option. The operation is similar to adjusting the capacity. Users can change the speed of the road by dragging or entering a precise value.

[0096] Road closure: Figure 3 As shown in C, the user only needs to right-click on the road that needs to be closed, and the system will remove the road from the road network. The operation is simple and intuitive.

[0097] New roads: Figure 3 As shown in D, users can create a new road by clicking on two nodes. By default, a two-way road is added, but users can also choose to add a one-way road. The initial capacity and free flow travel time of the newly created road are based on the average value of existing roads, and users can adjust its properties by further modification.

[0098] These interactive methods closely match the actual operational needs of traffic planning, significantly improving the flexibility and intuitiveness of users when modifying road networks.

[0099] (4) Comparison View

[0100] See also Figure 1In B, the comparison view is used to compare the iteratively generated multi-state road network attributes. This embodiment displays the iterative modification process of the road network state in the form of a history tree:

[0101] a) State switching. Each node represents a state of the road network, and each edge represents a modification operation from the state of the parent node to the child node. Users can click back to any historical state and start a new modification from that state.

[0102] b) Color coding. The nodes and edges in the history tree are color-coded to show the changes in the road network optimization effect, so that users can intuitively judge the quality of each modification.

[0103] c) Optimization index. The nodes and edges of the history tree are color-coded to show how each road network modification leads to improvement or deterioration of network performance. First, the present invention calculates the optimization index This indicator represents the total travel time of all vehicles in the network. In the history tree, the border color of each state node (s node) indicates the difference in optimization indicators between the state and the initial state. The node border of the initial state is white, and the border color of all modified states will change according to the optimization effect: green indicates an improvement in optimization effect, red indicates a decrease in optimization effect, and the depth of the color indicates the degree of change in the indicator.

[0104] d) Economic cost indicator. The embodiment of the present invention displays a sequence of icons in the lower right corner of each node in the history tree to help users consider the economic cost of traffic planning. These icons represent the construction or expansion activities involved in each modification. Above the icons, the cumulative expenses are displayed, including the construction costs of ground roads and tunnels. Specifically, the cost of expanding and building new ground roads is calculated on a per kilometer basis. r The construction cost of the new tunnel is calculated based on the cost per kilometer. t Calculate. r and c t The default values ​​are 4 million and 14 million respectively, and users can adjust these values ​​according to their needs. In contrast, the costs of operations such as road narrowing, improvement, restriction and closure are negligible. It should be noted that since the actual cost will be affected by complex factors such as soil foundation and surrounding environment, these estimated values ​​of expenses are for reference only and are intended to assist the decision-making process.

[0105] Specifically, the present invention realizes the road-level parallel comparison of multiple road network states by introducing a road network state matrix. Each row of the matrix represents a road, and each column represents a specific road network state, thereby allowing users to intuitively compare road performance under different states on the same interface.

[0106] 1) Road primitives. Figure 4As shown in the figure, each matrix unit uses road primitives to encode four main attributes of the road: road capacity, actual traffic flow, free-flow travel time, and actual travel time. This primitive consists of two layers of rectangles. The width of the bottom gray rectangle represents the road capacity, and the width of the top semi-transparent purple rectangle represents the actual traffic flow. The height difference between the two rectangles represents the difference between the actual travel time and the free-flow travel time. Therefore, the higher the purple rectangle is, the closer the actual travel time is to the free-flow travel time, which means a faster actual travel speed. In addition, the background color of each matrix unit adopts a red-green gradient color. This color mapping reflects the difference in the actual travel time of the road network state corresponding to the matrix unit relative to the initial state. Red indicates that the road condition has deteriorated, while green indicates improvement. The depth of the color represents the magnitude of the change, which intuitively shows the difference in the road condition corresponding to the matrix unit relative to the initial road.

[0107] 2) Filtering and sorting. In order to handle large-scale road networks, the comparison view provides flexible filtering and sorting functions to help users focus on important roads. Users can select columns in the history tree according to the status of interest, and then filter and sort roads according to multiple indicators (such as traffic flow, road capacity, travel time, etc.). The system provides a histogram to display the distribution of each indicator, and users can filter roads by interactively adjusting the range on the histogram. The sorting function allows users to sort roads in descending or ascending order according to the selected indicator, so as to quickly identify roads with significant changes and simplify the process of comparative analysis.

[0108] (5) Advantages and beneficial effects

[0109] The method of the present invention effectively helps users design a better road network through two views: a map view and a comparison view, and satisfies the iterative road network design and road network comparison required by users to complete the task of traffic simulation decision-making.

[0110] In the map view, the combination of geographic spatial context and road network, and the design of a series of interactive means for traffic simulation decision-making, bring the advantages of intuitive, efficient and flexible road network modification and real-time status feedback. Specifically:

[0111] 1) The method of the present invention designs an intuitive road network interaction mode, including four core interaction modes: expanding / narrowing roads, improving / restricting roads, closing roads, and building new roads. At the same time, the interaction mode is closely integrated with the semantic understanding of real-world traffic planning by experts in traffic simulation decision-making, allowing users to modify the road network intuitively, efficiently and flexibly and obtain real-time feedback.

[0112] 2) The method of the present invention uses color gradient coding, node size and width coding to represent traffic road attributes, presenting the road network status in a concise manner, making it convenient for users to locate the road network area of ​​interest.

[0113] In the comparison view, the use of the history tree and the network status matrix brings the advantages of iterative network status tracking and parallel comparison of multiple network states. Specifically:

[0114] 1) This method displays the iterative modification process of the road network status in the form of a history tree. The tree structure intuitively presents the evolution of the road network status, allowing users to track the modification path and trace back to any historical state at any time.

[0115] 2) The history tree uses color coding to present the changes in optimization indicators and costs during the road network status modification process, helping users analyze the degree of optimization and cumulative costs brought about by each modification.

[0116] 3) This method presents the road-level differences between road networks in different states in parallel through the road network state matrix, allowing users to make detailed and efficient comparisons across multiple historical states.

[0117] 4) A road primitive is designed in the road network state matrix, which cleverly presents four road attributes in one primitive. This design retains as much road attribute information as possible in a compact matrix layout, making the visualization elements of the interface more intuitive and concise.

[0118] 5) The road network status matrix supports filtering and sorting functions, providing multiple indicators for users to filter and sort roads. This helps users find and focus on key roads, simplifying the analysis process.

[0119] Example 2

[0120] An embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the following Figure 5 A visual analysis method for traffic simulation decision making is shown.

[0121] It is understood that the memory may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory may be used to store instructions, programs, codes, code sets, or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data created according to the use of the server, etc.

[0122] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor can integrate one or a combination of a central processing unit (CPU) and a modem. Among them, the CPU mainly processes the operating system and application programs; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but implemented separately through a chip.

[0123] Since the electronic device is an electronic device corresponding to a visual analysis method for traffic simulation decision-making in an embodiment of the present invention, and the principle of solving the problem by the electronic device is similar to that of the method, the implementation of the electronic device can refer to the implementation process of the above-mentioned method embodiment, and the repeated parts will not be repeated.

[0124] Example 3

[0125] The embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by a processor to implement the following Figure 5 A visual analysis method for traffic simulation decision making is shown.

[0126] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0127] Since the storage medium is a storage medium corresponding to a visual analysis method for traffic simulation decision-making in an embodiment of the present invention, and the principle of solving the problem by the storage medium is similar to that of the method, the implementation of the storage medium can refer to the implementation process of the above-mentioned method embodiment, and the repeated parts will not be repeated.

[0128] Example 4

[0129] In some possible implementations, various aspects of the method of the embodiment of the present invention may also be implemented in the form of a program product, which includes a program code. When the program product is run on a computer device, the program code is used to enable the computer device to execute the steps of a visual analysis method for traffic simulation decision-making according to various exemplary embodiments of the present application described above in this specification. Among them, the executable computer program code or "code" for executing various embodiments may be written in a high-level programming language such as C, C++, C#, Smalltalk, Java, JavaScript, Visual Basic, structured query language (e.g., Transact-SQL), Perl, or in various other programming languages.

[0130] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0131] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0132] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable ordinary technicians in the field to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made based on the essence of the content of the present invention should be included in the protection scope of the present invention.

Claims

1. A visual analysis method for traffic simulation decision making, characterized in that: The following steps are involved: Obtain input data, wherein the input data includes a road network with static attributes and an OD pair set including OD travel related attributes; The road network is modeled as a directed graph G = (V, E), where V represents a road intersection and E represents a road or road section; Assign OD trips to paths and roads in the road network, and calculate the actual traffic volume on each road based on the traffic assignment algorithm. and actual travel time According to the directed graph, the actual traffic volume of each road and actual travel time Build and display map views and comparison views; The map view is used to implement interactive road network editing functions, and the comparison view is used to compare iteratively generated multi-state road network attributes.

2. A visual analysis method for traffic simulation decision-making according to claim 1, characterized in that: In a directed graph, each road has four static properties: the starting intersection, the ending intersection, and the road capacity f. e and free flow travel time Each road also has two dynamic attributes: actual traffic volume and actual travel time OD trip is the smallest unit in traffic assignment. An OD trip represents a trip of one person between OD pairs. The path p = {..., e, ...} consists of a set of ordered edges, each ordered edge e describes how to move from the starting point of the OD pair to the end point; for O in the OD pair, there is a path set P o ={…,p i ,…}, the actual number of vehicles passing through path p is recorded as The actual travel time of the vehicle through the path is expressed as For D in the OD pair, it is obtained by calculating the sum of the actual travel time of each road in path p.

3. A visual analysis method for traffic simulation decision-making according to claim 2, characterized in that: The traffic assignment algorithm works as follows: Describing the actual driving time based on the BPR function The actual traffic volume The dependency relationship is as follows: Assuming that the driver is not always able to accurately know the actual travel time of each route, the Logit choice model is used to describe the probability of choosing a route. The formula is as follows: In the formula, Represents the path set P o A path in For path The actual driving time; The parameter θ is used to measure the driver's sensitivity to travel time. The smaller the θ value, the less sensitive the driver is to travel time and the more random the route selection is. The larger the θ value, the more sensitive the driver is to travel time and the more the route selection tends to avoid congestion.

4. A visual analysis method for traffic simulation decision-making according to claim 1, characterized in that: The functions of the map view include road network visualization, and the road network visualization includes visualization of road network structure and visualization of road network attributes; 1) Visualization of road network structure: A directed graph is used to represent the structure of the road network, where nodes represent intersections and links represent road segments; Nodes are placed on the map precisely according to their geographical locations, and links connect the corresponding nodes; for roads with two-way traffic, links are displayed on the map separately according to local traffic rules; 2) Visualization of road network attributes: A variety of visual codes are used to represent the attributes of each road. Traffic flow is represented by the size of the node and the width of the link. The larger the node or the wider the link, the greater the traffic flow. Driving time is coded with gradient colors. The first preset color indicates a driving time close to the free flow time, and the second preset color indicates a driving time much greater than the free flow time.

5. The visual analysis method for traffic simulation decision-making according to claim 1, characterized in that: The functions of the map view include travel demand visualization: after receiving trigger information that a user selects a road, displaying the OD travel demand passing through the road; The map view also includes functions of interactively modifying the road network: receiving interactive information input by the user, and directly modifying and displaying the road network on the map to simulate different road traffic decision strategies.

6. A visual analysis method for traffic simulation decision-making according to claim 1, characterized in that: The comparison view includes a history tree and a road network status matrix; The history tree is used to display each iterative step in the modification process and allows the user to roll back or create a new modification branch; the road network status matrix is ​​used to arrange roads in different states in a comparative manner, supports detailed comparison of multiple edge or node attributes, and displays the attribute changes of each road in different states, so as to achieve detailed comparison of multiple road network states.

7. A visual analysis method for traffic simulation decision-making according to claim 6, characterized in that: The nodes and edges of the history tree are color-coded to show the performance of each road network modification: Calculate optimization indicators This metric represents the total travel time of all vehicles in the network; In the history tree, the border color of each state node indicates the difference in optimization indicators between the state and the initial state; the node border of the initial state is the third preset color, and the border color of all modified states will change according to the optimization effect: the fourth preset color indicates an improvement in the optimization effect, and the fifth preset color indicates a decrease in the optimization effect. The depth of the color indicates the degree of change in the indicator.

8. A visual analysis method for traffic simulation decision-making according to claim 6, characterized in that: Each row of the road network state matrix represents a road, and each column represents a specific road network state; Each matrix cell uses road primitives to encode four main attributes of the road: road capacity, actual traffic flow, free-flow travel time, and actual travel time.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method according to any one of claims 1 to 8.

Images