Multi-mode traffic management method and system based on positioning and service integration

Abstract

The invention discloses a multi-mode traffic management method and system based on positioning and service integration, and the method comprises the steps: obtaining the current position information of a user through a GPS or other position service providers, considering the current travel traffic mode of the user according to the obtained current position information of the user, defining the node features in a network diagram, and carrying out the positioning of the user. Constructing a dynamic traffic network diagram; creating a graph snapshot according to the dynamic traffic network graph, generating spatial features of nodes and time features of the nodes in the dynamic traffic network graph, and combining the spatial features of the nodes with the time features of the nodes to obtain node states; detecting the node state, updating the dynamic traffic network diagram according to the detection result, outputting the prediction result of the traffic flow, and guiding the user to select other travel traffic modes based on the prediction result of the traffic flow; convolution processing is performed on the dynamic traffic network diagram, user mode switching is responded in real time, the prediction result of the traffic flow is output, and the traffic management efficiency and the user travel experience are improved.

Description

Technical Field

[0001] The present invention relates to the field of traffic management and intelligent travel technology, and in particular to a multi-mode traffic management method and system based on positioning and service integration. Background Art

[0002] In the context of accelerating urbanization, multimodal traffic management has gradually become an important means to improve urban traffic efficiency. The core of multimodal traffic management is to integrate multiple modes of travel in the city (such as walking, public transportation, bicycle sharing, etc.) to provide users with the best travel plan. However, due to the complexity of traffic management systems and the unpredictability of urban population mobility, achieving accurate and real-time multimodal traffic management has always been a challenge.

[0003] At present, many research and technical solutions use positioning technology, sensor data, and machine learning to try to achieve travel route optimization and reasonable allocation of traffic resources. For example, by obtaining the user's real-time location through technologies such as GPS and Wi-Fi, combined with historical traffic flow data, users can be provided with route recommendations based on specific modes, and to some extent, traffic pressure in some areas has been alleviated. However, such solutions are usually relatively simple and cannot switch efficiently or dynamically between multiple modes, so they are limited when facing complex multi-modal traffic environments. First, most traffic management systems rely on static or semi-dynamic traffic network models and cannot respond to users' frequent mode switching needs in real time. For example, users may need to flexibly switch between walking, subways, and shared bicycles during their travels, but static or semi-dynamic network models cannot fully capture this dynamic behavior, resulting in delayed or inaccurate travel recommendations. Secondly, existing technologies are relatively weak in integrating and analyzing multi-source data. Many existing methods are limited to a single data source (such as historical traffic data or static location data), lacking dynamic analysis of real-time positioning information, speed, acceleration, and traffic mode preferences, which directly affects the system's accurate identification of user travel modes and the rationality of mode recommendations. In addition, existing methods do not fully integrate the characteristics of multi-modal traffic in traffic forecasting, resulting in low prediction accuracy of traffic bottlenecks and traffic distribution.

[0004] Therefore, there is an urgent need for a traffic management method that can respond dynamically in real time and has cross-modal guidance capabilities to more effectively manage traffic flow in multi-modal scenarios in cities. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a multi-mode traffic management method based on positioning and service integration to solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a multi-mode traffic management method based on positioning and service integration, comprising:

[0009] Obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define the node characteristics in the network diagram, and build a dynamic transportation network diagram;

[0010] Creating a graph snapshot according to the dynamic traffic network graph, generating spatial features of nodes and temporal features of nodes in the dynamic traffic network graph, combining the spatial features of the nodes with the temporal features of the nodes to obtain node states;

[0011] The node status is detected, a dynamic traffic network diagram is updated according to the detection result, a traffic flow prediction result is output, and based on the traffic flow prediction result, the user is guided to choose other travel modes to form a multi-mode traffic management method.

[0012] As a preferred solution of the multi-modal traffic management method based on positioning and service integration described in the present invention, wherein: considering the user's current travel mode according to the obtained user's current location information, including:

[0013] Perform data cleaning on the obtained user's current location information, remove the data point information with the largest error in the user's current location information, and obtain the movement trajectory of the user's current location;

[0014] By analyzing the distance and time interval of consecutive position points on the moving trajectory of the user's current position, the user's moving speed, acceleration curve and stop point are generated;

[0015] The user's current travel mode is obtained according to the moving speed, acceleration curve and stop point.

[0016] As a preferred solution of the multi-mode traffic management method based on positioning and service integration described in the present invention, wherein: defining node features in a network graph and constructing a dynamic traffic network graph includes:

[0017] Each piece of user location information obtained is used as a node in the network graph and node features are added;

[0018] The movement trajectory of the user's current location is defined as the directed edges between the nodes to form a traffic path;

[0019] By geographically clustering the user's stay points, high-frequency location area nodes are obtained, and the high-frequency location area nodes are used as traffic conversion points;

[0020] Connect the nodes in the network diagram with the traffic conversion points and traffic paths to form a dynamic traffic network diagram.

[0021] As a preferred solution of the multi-modal traffic management method based on positioning and service integration described in the present invention, wherein: creating a graph snapshot according to the dynamic traffic network graph, generating the spatial characteristics of the nodes and the time characteristics of the nodes in the dynamic traffic network graph, combining the spatial characteristics of the nodes with the time characteristics of the nodes to obtain the node status, including:

[0022] Create multiple dynamic graph snapshots in units of time windows. Each dynamic graph snapshot uses a one-dimensional convolutional layer to weight the features of the node and its neighboring nodes, calculate the traffic features of the node, generate the spatial features of the node in the dynamic traffic network graph, and time-series the traffic features of each node to generate the time features of the node in the dynamic traffic network graph.

[0023] The spatial features of the node and the temporal features of the node are concatenated and input into the fully connected layer to obtain the node state.

[0024] As a preferred solution of the multi-mode traffic management method based on positioning and service integration described in the present invention, wherein: detecting the node status, updating the dynamic traffic network diagram according to the detection result, and outputting the prediction result of the traffic flow, including:

[0025] Set a traffic flow threshold, calculate the traffic flow of the current node state, and if the traffic flow of the current node state exceeds the set traffic flow threshold or remains unchanged, trigger an abnormal reminder based on the user's current travel mode, mark the current node state as "abnormal", update the relevant information of the current node state to the dynamic traffic network diagram, and modify the weight value of the edge between the nodes related to the current node state;

[0026] Output the current traffic flow prediction results based on the updated dynamic traffic network diagram.

[0027] As a preferred solution of the multi-mode traffic management method based on positioning and service integration described in the present invention, it also includes:

[0028] Before updating, the number of edges between related nodes whose current node status is "abnormal" is counted and arranged in sequence. Each time the dynamic traffic network diagram is updated, the edges with the least number of statistics and the related nodes with the most number of statistics are removed.

[0029] As a preferred solution of the multi-modal traffic management method based on positioning and service integration described in the present invention, wherein: based on the predicted result of the traffic flow, guiding the user to choose other travel modes includes:

[0030] According to the output current traffic flow prediction results, observe the nodes where the traffic flow is higher than the average traffic flow, and connect these nodes to form a traffic hotspot path. If the current user's travel mode is on the traffic hotspot path, re-select other travel modes for the user.

[0031] In a second aspect, the present invention provides a multi-mode traffic management system based on positioning and service integration, which includes:

[0032] The dynamic traffic network diagram construction module is configured to obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define node features in the network diagram, and construct a dynamic traffic network diagram;

[0033] A graph snapshot generation and node feature extraction module is configured to create a graph snapshot according to the dynamic traffic network graph, generate spatial features of nodes and temporal features of nodes in the dynamic traffic network graph, and combine the spatial features of the nodes with the temporal features of the nodes to obtain the node status;

[0034] The traffic flow prediction and transportation mode recommendation module is configured to detect the node status, update the dynamic traffic network diagram according to the detection results, output the traffic flow prediction results, and guide the user to choose other travel modes based on the traffic flow prediction results, thereby forming a multi-mode traffic management method.

[0035] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: the processor implements any step of the above method when executing the computer program.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program implements any step of the above method when executed by a processor.

[0037] Compared with the prior art, the invention has the following beneficial effects:

[0038] 1. In view of the problem that the existing methods do not fully integrate multi-modal features in traffic prediction, resulting in low prediction accuracy, the solution of the present invention constructs a dynamic network that reflects multi-modal traffic characteristics through multiple time series snapshots. Especially in a multi-modal traffic environment, the system can timely identify high-traffic areas, traffic distribution trends and potential traffic bottlenecks, help users avoid congested areas, and improve the traffic scheduling efficiency of the traffic management system;

[0039] 2. By building a dynamic traffic network diagram, combined with the user's real-time location, traffic mode characteristics and network node status, the system can adjust the travel recommendation plan in real time when the user frequently switches travel modes (such as switching from walking to public transportation or shared bicycles). This is particularly suitable for coping with complex traffic needs in a multi-modal environment, effectively making up for the lag problem of the existing traffic management system;

[0040] 3. The present invention provides users with dynamic cross-modal traffic guidance by analyzing real-time traffic prediction results and user positioning data. When the congestion trend of the user's current travel mode is detected, the system can intelligently recommend other travel modes such as walking and shared bicycles based on the user's current location and surrounding mode selection, thereby optimizing the user's travel path and dispersing traffic flow. In contrast, traditional methods find it difficult to dynamically recommend cross-modal travel plans, and the present invention can better support users in freely switching between multiple modes in this regard, thereby improving travel efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0042] Figure 1 This is an overall flow chart of a multi-mode traffic management method based on positioning and service integration according to an embodiment of the present invention;

[0043] Figure 2 A flow trend comparison diagram of a multi-mode traffic management method based on positioning and service integration according to an embodiment of the present invention;

[0044] Figure 3 This is a comparison chart of average traffic flow changes in a multi-modal traffic management method based on positioning and service integration according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0049] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] Example 1

[0052] Reference Figure 1, which is the first embodiment of the present invention, and provides a multi-mode traffic management method based on positioning and service integration, including:

[0053] S1. Obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define the node characteristics in the network diagram, and construct a dynamic transportation network diagram;

[0054] Specifically, the user's current location information includes geographic coordinates (latitude and longitude) and a timestamp; wherein the timestamp records the specific time when the user is at the geographic coordinates (latitude and longitude), thereby forming the user's current location information in space and time;

[0055] It should be explained that since the user's current location information may be affected by signal obstruction or device accuracy, data points with large errors may appear, so the user's current location information needs to be cleaned;

[0056] Furthermore, the obtained user current location information is cleaned to remove the data point information with the largest error in the user current location information (coordinate mutation point or time stamp misalignment), and obtain the movement trajectory of the user's current location;

[0057] Furthermore, by analyzing the distance and time interval of consecutive position points on the moving trajectory of the user's current position, the user's moving speed, acceleration curve and stop points are generated;

[0058] Specifically, by calculating the distance and time difference between consecutive position points, the user's speed and acceleration can be obtained;

[0059] Specifically, when a user stays at a certain location for a long time (i.e., the time interval between the current location point and the next location point is long), it indicates that the location point where the user is currently located may be a "staying point"; wherein the stay point is represented as a destination (such as a restaurant, company, or parking lot, etc.);

[0060] It should be noted that the speed and acceleration indicators play an important role in the identification of travel modes, because different modes of transportation usually correspond to different speed and acceleration characteristics; for example, the average walking speed is usually low, generally between 3 and 6 kilometers per hour; because a person's walking speed is affected by the environment (such as road congestion) and personal status (such as walking speed), the walking speed usually fluctuates within a small range; it can be obtained that the acceleration of walking changes less and at a lower frequency; because the acceleration and deceleration of a person when walking are relatively slow, the acceleration curve will have slight speed fluctuations during walking, but no obvious oscillations will occur;

[0061] Furthermore, the user's current mode of transportation is obtained based on the moving speed, acceleration curve, and stop points;

[0062] It should be noted that the comprehensive consideration of movement rate, acceleration curve and stop point plays a key role in the accuracy of constructing the dynamic traffic network diagram;

[0063] Furthermore, each piece of user location information obtained is used as a node in the network graph and node features are added;

[0064] It should be explained that in graph theory, a node is an abstract representation of an entity or event; in the dynamic traffic network of the solution of the present invention, each piece of user location information is regarded as a node, that is, each node can be regarded as a tiny spatial unit in the traffic network;

[0065] Specifically, the node features added include the geographic location, timestamp, travel mode (such as walking, cycling, driving, etc.), and duration of stay mentioned above;

[0066] Furthermore, the movement trajectory of the user’s current location is defined as directed edges between nodes to form a traffic path;

[0067] It should be noted that by connecting the movement between nodes into directed edges, the actual travel path of the user can be generated, and the directed edge includes not only the actual path of the user, but also the direction in which the user is moving;

[0068] It should be explained that geographic clustering is a data analysis method that is mainly used to group or cluster data points in geographic space according to their spatial distribution characteristics. Through geographic clustering, it is possible to identify densely distributed point groups in a specific area.

[0069] Furthermore, by geographically clustering the user's stay points, high-frequency location area nodes are obtained, and the high-frequency location area nodes are used as traffic conversion points;

[0070] It should be noted that the stay point belongs to the low-frequency location area and there is no superposition of the locations of multiple users; while the transportation hub belongs to the high-frequency location area and often the locations of multiple users are superimposed;

[0071] Furthermore, the nodes in the network diagram are connected with traffic conversion points and traffic paths to form a dynamic traffic network diagram;

[0072] It should be noted that, according to the dynamic characteristics of the graph, the status of the nodes is updated over time, and the direction and path of the traffic flow will also change, which provides a basis for subsequent traffic flow prediction;

[0073] S2. Create a snapshot according to the dynamic traffic network graph, generate the spatial characteristics of nodes and the time characteristics of nodes in the dynamic traffic network graph, and combine the spatial characteristics of nodes with the time characteristics of nodes to obtain the node status;

[0074] It needs to be explained that in a traffic network graph, node flow is often affected by neighboring nodes. For example, the flow of a station will fluctuate due to changes in surrounding traffic conditions. The weighted convolution calculation of neighboring nodes can effectively reflect the spatial dependency between nodes.

[0075] Furthermore, multiple dynamic graph snapshots are created in units of time windows. Each dynamic graph snapshot uses a one-dimensional convolutional layer to perform feature weighting on the node and its neighboring nodes, calculate the traffic characteristics of the node, generate the spatial characteristics of the node in the dynamic traffic network graph, and time-series the traffic characteristics of each node to generate the time characteristics of the node in the dynamic traffic network graph;

[0076] Specifically, each time window represents a fixed time period. By “freezing” the state of the dynamic traffic network at different times, a series of snapshots are formed. These snapshots can be used to reflect the temporal trend of traffic flow.

[0077] Specifically, through the convolution operation, the traffic features of the neighboring nodes are combined with the features of the central node to generate the traffic features of the current node; in this way, the spatial features of the node not only consider its own state, but also include the traffic impact of its surrounding environment;

[0078] Furthermore, the spatial features of the node and the temporal features of the node are concatenated and input into the fully connected layer to obtain the node state;

[0079] Specifically, the node state refers to the current state information (congested state and unblocked state) of the node generated after the spatial and temporal features of the node are integrated. It is mainly used to detect the flow changes of the node in real time.

[0080] It should be noted that through the weighted operation of one-dimensional convolution, the influence weight of neighbor nodes on the target node can be dynamically adjusted, so that the model can adaptively aggregate the most representative neighbor features; compared with the traditional average pooling operation, it can better capture the correlation differences between nodes and reflect the subtle relationships in space;

[0081] S3, detect the node status, update the dynamic traffic network diagram according to the detection results, output the predicted results of traffic flow, and guide users to choose other travel modes based on the predicted results of traffic flow, so as to form a multi-mode traffic management method;

[0082] Furthermore, a traffic flow threshold is set, and the traffic flow of the current node state is calculated. If the traffic flow of the current node state exceeds the set traffic flow threshold or remains unchanged, an abnormal reminder is triggered according to the user's current travel mode, and the current node state is marked as "abnormal", and the relevant information of the current node state is updated to the dynamic traffic network diagram, and the weight value of the edge between the nodes related to the current node state is modified;

[0083] Specifically, the traffic flow threshold needs to be calculated based on the historical traffic data of the node in different time periods, and the average traffic value of the node during peak and off-peak periods;

[0084] Specifically, the traffic flow F of the current node state node The judgment of the traffic flow threshold T is as follows:

[0085] Smooth state: F node <T;

[0086] Congestion warning: T≤F node <1.2×T;

[0087] Congestion status: F node ≥1.2×T;

[0088] Furthermore, the traffic flow of the current node state is calculated by multiplying the weight of the neighbor node to the current node with the flow value of the neighbor node;

[0089] Specifically, the update process includes recalculating and assigning the node status and the weights of adjacent edges; if a node is marked as abnormal, the edge weights of the adjacent nodes need to be increased to reflect the congestion level of the path;

[0090] Furthermore, before updating, the number of edges between related nodes whose current node status is "abnormal" is counted and arranged in sequence. Each time the dynamic traffic network graph is updated, the edge with the least number of counts and the related node with the most number of counts are removed;

[0091] It should be noted that, on the one hand, by removing the edges with the least number, the load of the network graph can be reduced, focusing on the paths with larger traffic volume, which can ensure that the computational resources for traffic prediction are concentrated on the critical paths; on the other hand, removing these edges and their related nodes is to reduce the computational complexity of the network graph, ensuring that the network graph focuses on the main traffic flow areas and is not disturbed by low traffic areas;

[0092] Furthermore, the current traffic flow prediction result is outputted according to the updated dynamic traffic network diagram;

[0093] Furthermore, according to the output current traffic flow prediction result, the nodes with higher traffic flow than the average traffic flow are observed, and these nodes are connected to form a traffic hotspot path. If the current user's travel mode is on the traffic hotspot path, another travel mode is reselected for the user;

[0094] It should be explained that since the average traffic flow changes over time, the traffic hotspot nodes can dynamically reflect the current traffic conditions and are not easily disturbed by sudden high traffic, which improves the robustness of traffic identification;

[0095] Specifically, nodes with higher traffic flow than the average traffic flow are represented as traffic hotspot nodes, i.e., areas with significantly increased traffic flow in a specific time period;

[0096] It should be noted that by identifying the congestion of traffic hotspot paths and planning alternative options for users, it helps to disperse the actual traffic flow and alleviate the congestion pressure caused by traffic concentration.

[0097] Furthermore, this embodiment also provides a multi-mode traffic management system based on positioning and service integration, including:

[0098] The dynamic traffic network diagram construction module is configured to obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define node features in the network diagram, and construct a dynamic traffic network diagram;

[0099] A graph snapshot generation and node feature extraction module is configured to create a graph snapshot according to the dynamic traffic network graph, generate spatial features of nodes and temporal features of nodes in the dynamic traffic network graph, and combine the spatial features of the nodes with the temporal features of the nodes to obtain the node status;

[0100] The traffic flow prediction and transportation mode recommendation module is configured to detect the node status, update the dynamic traffic network diagram according to the detection results, output the traffic flow prediction results, and guide the user to choose other travel modes based on the traffic flow prediction results, thereby forming a multi-mode traffic management method.

[0101] This embodiment also provides a computer device, which is applicable to a multi-mode traffic management method based on positioning and service integration, and includes:

[0102] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the multi-modal traffic management method based on positioning and service integration as proposed in the above embodiment.

[0103] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0104] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the multi-modal traffic management method based on positioning and service integration as proposed in the above embodiment is implemented.

[0105] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0106] Example 2

[0107] Reference Figure 2 and Figure 3 , which is the second embodiment of the present invention, and this embodiment provides a multi-mode traffic management method based on positioning and service integration, including: In order to verify the effectiveness of the real-time traffic prediction and dynamic path recommendation functions, this experiment selected a large commercial area as the test area; the area has busy traffic, contains multiple key nodes (such as major street intersections, bus stops, etc.), and congestion often occurs during peak hours;

[0108] The experimental environment and configuration are as follows:

[0109] Test area: main roads in commercial areas, including 6 bus stops, 4 subway stations, 7 public parking lots, and 5 major intersections;

[0110] User travel mode: walking, cycling, public transportation;

[0111] Time window: refresh the network graph snapshot every 10 minutes to make real-time traffic prediction;

[0112] Test equipment: Smartphones and GPS devices were used to track the real-time location of 100 users who participated in the test, each of whom traveled in different modes;

[0113] Traffic prediction: A graph convolutional network (GCN) is used to perform real-time traffic prediction on the traffic network. By identifying nodes where traffic exceeds the threshold (traffic hotspot nodes), alternative routes are dynamically recommended for users on the path. The data in Table 1 are obtained.

[0114] Table 1

[0115]

[0116] It can be seen from Table 1 that after adopting the method of the present invention, the average actual travel time is shortened by 7 minutes, and the average number of route changes and the average speed are improved, which reflects the congestion avoidance ability and traffic efficiency of the method of the present invention, and can bring significant travel time and speed advantages to users;

[0117] Secondly, we test it by short time steps, referring to Figure 2 , the flow variance reflects the instability or volatility of the flow, while a lower variance indicates that the flow fluctuation in the system is smaller and the flow is more stable; Figure 2 It can be seen that the flow variance of the proposed method in the time step is relatively low, indicating that it performs better than the traditional method in terms of flow fluctuation control and stability; in addition, combined with Figure 3 , the average flow rate indicates the overall level of traffic in the system, and a higher average flow rate indicates a more efficient use of traffic flow; Figure 3 It can be seen that the method of the present invention maintains a relatively high average flow rate in the time step, indicating that the method of the present invention has greater advantages in traffic flow management and improving travel efficiency;

[0118] In summary, through experiments, it can be analyzed that the method of the present invention has greater advantages in the volatility and stability of traffic flow than the traditional method, which indirectly shows that while improving the travel efficiency of users, it also improves the flow scheduling efficiency of the traffic management system.

[0119] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A multi-modal traffic management method based on positioning and service integration, characterized in that: include: Obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define the node characteristics in the network diagram, and build a dynamic transportation network diagram; Creating a graph snapshot according to the dynamic traffic network graph, generating spatial features of nodes and temporal features of nodes in the dynamic traffic network graph, combining the spatial features of the nodes with the temporal features of the nodes to obtain node states; The node status is detected, a dynamic traffic network diagram is updated according to the detection result, a traffic flow prediction result is output, and based on the traffic flow prediction result, the user is guided to choose other travel modes to form a multi-mode traffic management method.

2. The multi-modal traffic management method based on positioning and service integration as claimed in claim 1, characterized in that: Consider the user's current mode of transportation based on the user's current location information, including: Perform data cleaning on the obtained user's current location information, remove the data point information with the largest error in the user's current location information, and obtain the movement trajectory of the user's current location; By analyzing the distance and time interval of consecutive position points on the moving trajectory of the user's current position, the user's moving speed, acceleration curve and stop point are generated; The user's current travel mode is obtained according to the moving speed, acceleration curve and stop point.

3. The multi-mode traffic management method based on positioning and service integration as claimed in claim 1, characterized in that: Define node features in the network graph and build a dynamic traffic network graph, including: Each piece of user location information obtained is used as a node in the network graph and node features are added; The movement trajectory of the user's current location is defined as the directed edges between the nodes to form a traffic path; By geographically clustering the user's stay points, high-frequency location area nodes are obtained, and the high-frequency location area nodes are used as traffic conversion points; Connect the nodes in the network diagram with the traffic conversion points and traffic paths to form a dynamic traffic network diagram.

4. The multi-mode traffic management method based on positioning and service integration as claimed in claim 3, characterized in that: Creating a graph snapshot according to the dynamic traffic network graph, generating spatial features of nodes and time features of nodes in the dynamic traffic network graph, combining the spatial features of the nodes with the time features of the nodes to obtain node states, including: Create multiple dynamic graph snapshots in units of time windows. Each dynamic graph snapshot uses a one-dimensional convolutional layer to weight the features of the node and its neighboring nodes, calculate the traffic features of the node, generate the spatial features of the node in the dynamic traffic network graph, and time-series the traffic features of each node to generate the time features of the node in the dynamic traffic network graph. The spatial features of the node and the temporal features of the node are concatenated and input into the fully connected layer to obtain the node state.

5. The multi-mode traffic management method based on positioning and service integration as claimed in claim 4, characterized in that: Detect the node status, update the dynamic traffic network diagram according to the detection result, and output the prediction result of traffic flow, including: Set a traffic flow threshold, calculate the traffic flow of the current node state, and if the traffic flow of the current node state exceeds the set traffic flow threshold or remains unchanged, trigger an abnormal reminder based on the user's current travel mode, mark the current node state as "abnormal", update the relevant information of the current node state to the dynamic traffic network diagram, and modify the weight value of the edge between the nodes related to the current node state; Output the current traffic flow prediction results based on the updated dynamic traffic network diagram.

6. The multi-mode traffic management method based on positioning and service integration as claimed in claim 5, characterized in that: Also includes: Before updating, the number of edges between related nodes whose current node status is "abnormal" is counted and arranged in sequence. Each time the dynamic traffic network diagram is updated, the edges with the least number of statistics and the related nodes with the most number of statistics are removed.

7. The multi-mode traffic management method based on positioning and service integration as claimed in claim 5, characterized in that: Based on the traffic flow prediction result, guide the user to choose other travel modes, including: According to the output current traffic flow prediction results, observe the nodes where the traffic flow is higher than the average traffic flow, and connect these nodes to form a traffic hotspot path. If the current user's travel mode is on the traffic hotspot path, re-select other travel modes for the user.

8. A multi-modal traffic management system based on positioning and service integration, based on the multi-modal traffic management method based on positioning and service integration according to any one of claims 1 to 7, characterized in that: include: The dynamic traffic network diagram construction module is configured to obtain the user's current location information through GPS or other location service providers, consider the user's current travel mode based on the obtained user's current location information, define node features in the network diagram, and construct a dynamic traffic network diagram; A graph snapshot generation and node feature extraction module is configured to create a graph snapshot according to the dynamic traffic network graph, generate spatial features of nodes and temporal features of nodes in the dynamic traffic network graph, and combine the spatial features of the nodes with the temporal features of the nodes to obtain the node status; The traffic flow prediction and transportation mode recommendation module is configured to detect the node status, update the dynamic traffic network diagram according to the detection results, output the traffic flow prediction results, and guide the user to choose other travel modes based on the traffic flow prediction results, thereby forming a multi-mode traffic management method.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images