Traffic network management method, device, equipment, medium and program product

Abstract

The invention provides a traffic network treatment method, device and equipment, a medium and a program product, and relates to the technical field of traffic. The method comprises the following steps: acquiring current traffic data of a target road network, wherein the target road network is a road network with a congestion condition; according to the current traffic data, the value of a road network toughness index of the target road network is calculated, and the road network toughness index is used for representing the toughness capability of the target road network under a preset condition; when the road network toughness index is higher than a preset threshold value, the congestion type of the target road network is recognized, congestion treatment is carried out on the target road network based on the congestion type and a pre-trained road network treatment model, the road network treatment model carries out iteration based on the road network toughness index predicted in real time, and the congestion type comprises a normal congestion point and a temporary congestion point. According to the invention, real-time monitoring, dynamic prediction and precise treatment of the traffic network are realized, the operation efficiency and toughness of an urban traffic system are effectively improved, and the problem of traffic congestion is solved.

Description

Background Art

[0002] Cities are important carriers of people's production and life. At the same time, they are shaped by the transportation system. In the current era of rapid urbanization around the world, more and more people are flocking to cities. The scale of cities continues to expand, the structure becomes more complex, and the status becomes increasingly important. In the urban model with a high urbanization rate and increasingly severe urban living environment, how can public health emergencies and urban planning avoid the occurrence of urban problems? The concept of "resilience" provides a new research direction and planning perspective to solve this problem.

[0003] Traditional traffic management methods can no longer meet the increasingly complex and dynamically changing traffic needs. Therefore, there is an urgent need for a method that can effectively manage traffic congestion.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a traffic network management method, device, equipment, medium and program product, which can overcome the problem of urban traffic congestion at least to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a traffic network management method is provided, comprising: obtaining current traffic data of a target road network, the target road network being a road network with congestion;

[0008] According to the current traffic data, the value of the road network resilience index of the target road network is calculated. The road network resilience index is used to characterize the resilience capacity of the target road network under preset conditions;

[0009] When the road network resilience index is higher than the preset threshold, the congestion category of the target road network is identified, and congestion management is performed on the target road network based on the congestion category and the pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion categories include normal congestion points and temporary congestion points.

[0010] In some embodiments, the above-mentioned road network resilience indicators include one or more of the following: redundancy, resistance, resilience and reliability;

[0011] Among them, redundancy represents the ability of the target road network to have multiple alternative paths;

[0012] Resistance represents the ability of the target road network to resist sudden accidents;

[0013] Resilience characterizes the ability of the target road network to recover from unexpected accidents;

[0014] Reliability characterizes the ability of the target road network to maintain traffic under unexpected circumstances.

[0015] In some embodiments, calculating the value of the road network resilience index of the target road network according to the current traffic data includes:

[0016] Calculate the redundancy value, resistance value, resilience value and reliability value respectively according to the current traffic data;

[0017] The comprehensive index value of road network resilience is determined based on the calculated redundancy value, resistance value, resilience value and reliability value. The comprehensive index value of road network resilience is the weighted average of the redundancy value, resistance value, resilience value and reliability value.

[0018] In some embodiments, when the congestion category of the target road network is a normal congestion point, the method further includes:

[0019] Obtain historical traffic network management data, which includes environmental condition data, traffic data and management plan data at different times;

[0020] Train the road network governance model based on historical governance plan data.

[0021] In some embodiments, the congestion category of the target road network is a temporary congestion point, and the method further includes:

[0022] Obtain surveillance video information of temporary traffic jams;

[0023] The type of disposal is determined based on the surveillance video information of temporary traffic jams, which include single-point real-time optimization, single-point time period plan, and manual locking of specified time length plan.

[0024] In some embodiments, the method further comprises:

[0025] When the road network resilience index is lower than a preset threshold, identify the congestion level of the target road network;

[0026] Determine the number of dredging personnel to be deployed based on the level of congestion.

[0027] According to another aspect of the present disclosure, there is also provided a traffic network management device, comprising: a traffic data acquisition module, used to acquire current traffic data of a target road network, the target road network being a road network with congestion;

[0028] A road network resilience index calculation module is used to calculate the value of the road network resilience index of the target road network based on the current traffic data. The road network resilience index is used to characterize the resilience capacity of the target road network under preset conditions;

[0029] The road network management module is used to identify the congestion category of the target road network when the road network resilience index is higher than the preset threshold, and to perform congestion management on the target road network based on the congestion category and a pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion categories include normal congestion points and temporary congestion points.

[0030] According to another aspect of the present disclosure, an electronic device is also provided, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned traffic network management methods by executing the executable instructions.

[0031] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the traffic network management method described in any one of the above is implemented.

[0032] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the computer program implements any one of the above-mentioned traffic network management methods.

[0033] The traffic network management method, device, equipment, medium and program product provided in the embodiments of the present disclosure collect the current traffic data of the target network in real time, analyze the collected current traffic data, and calculate the indicators reflecting the resilience of the road network under preset conditions, such as redundancy, resistance, resilience and reliability. When the road network resilience index is higher than the preset threshold, the congestion nature of the target network is identified so that the corresponding management plan can be automatically recommended or executed according to the congestion category and the pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index, continuously optimizes the management strategy, and improves the management effect. Through real-time data analysis and prediction, intelligent management of traffic congestion is realized, reducing the need for manual intervention. The management model based on the congestion category and the road network resilience index can quickly identify and take effective management measures, thereby improving the management efficiency. The road network management model can dynamically adjust the management strategy according to the real-time data to adapt to the changing traffic conditions. The embodiments of the present disclosure realize real-time monitoring, dynamic prediction and precise management of the traffic network, effectively improve the operating efficiency and resilience of the urban transportation system, and provide effective technical support for solving the traffic congestion problem.

[0034] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0036] Figure 1 A schematic diagram showing an exemplary application system architecture of an application traffic network management method according to an embodiment of the present disclosure;

[0037] Figure 2 A flow chart of a traffic network management method according to an embodiment of the present disclosure is shown;

[0038] Figure 3 A flow chart of another method for managing a traffic network in an embodiment of the present disclosure is shown;

[0039] Figure 4 A schematic diagram of a technical framework in an embodiment of the present disclosure is shown;

[0040] Figure 5 A schematic diagram of a normal blocking point operation management process in an embodiment of the present disclosure is shown;

[0041] Figure 6 A schematic diagram of a temporary blocking point processing flow in an embodiment of the present disclosure is shown;

[0042] Figure 7 A schematic diagram of a traffic network management device in an embodiment of the present disclosure is shown;

[0043] Figure 8 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0045] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0046] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0047] Figure 1 FIG. 1 is a schematic diagram showing an exemplary application system architecture to which the traffic network management method in the embodiment of the present disclosure can be applied. Figure 1 As shown, the system architecture may include a terminal device 101 , a network 102 and a server 103 .

[0048] The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103, and can be a wired network or a wireless network.

[0049] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is typically the Internet, but may also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPSec) and the like may be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies may also be used to replace or supplement the above-mentioned data communication technologies.

[0050] The terminal device 101 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, smart speakers, smart watches, wearable devices, augmented reality devices, virtual reality devices, etc.

[0051] Optionally, the client of the application installed in different terminal devices 101 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0052] The server 103 may be a server that provides various services, such as a background management server that provides support for the device operated by the user using the terminal device 101. The background management server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0053] Optionally, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0054] Those skilled in the art will know that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs, and the embodiments of the present disclosure do not limit this.

[0055] Under the above system architecture, a traffic network management method is provided in an embodiment of the present disclosure, and the method can be executed by any electronic device with computing and processing capabilities.

[0056] In some embodiments, the traffic network management method provided in the embodiments of the present disclosure can be executed by the terminal device of the above-mentioned system architecture; in other embodiments, the traffic network management method provided in the embodiments of the present disclosure can be executed by the server in the above-mentioned system architecture; in other embodiments, the traffic network management method provided in the embodiments of the present disclosure can be implemented by the terminal device and the server in the above-mentioned system architecture through interaction.

[0057] Figure 2 A flow chart of a traffic network management method in an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the traffic network management method provided in the embodiment of the present disclosure includes the following steps:

[0058] S202, obtaining current traffic data of a target road network, where the target road network is a road network with congestion.

[0059] It should be noted that the target road network can be any traffic road network to be traffic-managed and optimized, and can be a regional traffic road network in a city or a traffic road network in the entire city. In the disclosed embodiment, the target road network is a road network with congestion.

[0060] Current traffic data can be any real-time information that reflects the current traffic conditions of the target road network, which is crucial for traffic management. Current traffic data includes but is not limited to the following types:

[0061] Traffic flow: The number of vehicles passing through a certain section per unit time can reflect the road's capacity and congestion level.

[0062] Vehicle speed: The average speed of vehicles, which can reflect the smoothness of the road and traffic efficiency.

[0063] Delay time: The difference between the actual time and the ideal time of vehicle travel, which can reflect the impact of traffic congestion on vehicle travel.

[0064] Queue length: The length of the queue of vehicles waiting to pass through the intersection can reflect the degree of congestion at the intersection.

[0065] Traffic incidents: including traffic accidents, road construction, bad weather, etc., which can reflect emergencies that affect traffic operations.

[0066] Traffic signal control data: including signal light timing plan, phase difference, green-to-signal ratio, etc., which can reflect the regulatory effect of traffic signals on traffic flow.

[0067] The current traffic data can grasp the traffic operation status in real time and promptly discover problems such as traffic congestion and traffic accidents. In addition, understanding the traffic congestion situation based on the current traffic data is crucial to formulating targeted governance plans to alleviate traffic congestion and improve traffic efficiency.

[0068] S204, calculating the value of the road network resilience index of the target road network based on the current traffic data, where the road network resilience index is used to characterize the resilience capability of the target road network under preset conditions.

[0069] It should be noted that the road network resilience index is a set of data indicators used to measure the resilience of the traffic road network under preset conditions. The preset conditions refer to the adverse conditions that the road network may face, such as different weather conditions, road construction conditions, types of traffic accidents, etc. The road network resilience index characterizes the resilience of the target road network under preset conditions, that is, the ability of the target road network to maintain normal operation and return to normal state when facing adverse conditions.

[0070] Specifically, road network resilience indicators can include the following:

[0071] Redundancy: refers to whether there are multiple alternative paths or excess capacity in the road network. It is used to measure whether traffic can be bypassed or diverted through other paths when some sections of the road network are congested or interrupted.

[0072] Resistance: refers to the ability of a road network to resist adverse conditions, used to measure whether the road network can maintain normal operation when adverse conditions occur.

[0073] Resilience: refers to the ability of a road network to quickly return to normal after being damaged by emergencies such as natural disasters or traffic accidents.

[0074] Reliability: refers to the ability of a road network to maintain traffic under normal and adverse conditions, and is used to measure the stability and reliability of road network operation.

[0075] By calculating the value of the road network resilience index, the risk level of the target road network when facing adverse conditions can be evaluated, and a basis can be provided for formulating corresponding traffic management plans.

[0076] S206, when the road network resilience index is higher than a preset threshold, identify the congestion category of the target road network, and perform congestion management on the target road network based on the congestion category and a pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion categories include normal congestion points and temporary congestion points.

[0077] It should be noted that when the road network resilience index is higher than the preset threshold, it means that the target road network has strong resilience and can withstand the impact of adverse conditions to a certain extent and maintain normal operation. Specifically, this means that the road network has good redundancy: there are multiple alternative paths or surplus capacity in the road network, which can bypass or divert traffic through other paths when some sections are congested or interrupted to avoid traffic paralysis. The road network has strong resistance: the road network has a strong ability to resist adverse conditions, such as the road structure strength and drainage system can withstand the impact of natural disasters such as earthquakes, floods, and mudslides. The road network has strong resilience: the road network can quickly return to normal after being damaged by natural disasters or emergencies such as traffic accidents, such as a sound emergency rescue mechanism and an effective traffic diversion plan. The road network has high reliability: the road network can maintain a high capacity under normal and adverse conditions, such as traffic signal control and traffic information release can effectively regulate traffic flow and avoid congestion.

[0078] The road network resilience index is higher than the preset threshold or it can be the comprehensive value of the above indicators, indicating that the target road network has strong risk resistance and recovery capabilities.

[0079] In this case, it is necessary to further identify the congestion categories of the target road network, including normal congestion points and temporary congestion points.

[0080] Among them, regular congestion points: congestion occurs regularly and is linked to adjacent intersections to form a congestion combination.

[0081] Temporary congestion point: The congestion warning intersection of Internet access generally does not affect the adjacent intersections.

[0082] According to the identified congestion category, the target road network is congested based on the pre-trained road network management model. Specifically, based on different congestion categories, the corresponding road network management model can be different management strategies. Among them, the management of regular congestion points can use deep learning models to recommend management solutions, including signal control solution adjustments, manual operation solutions, etc.

[0083] Temporary traffic jams can be managed by making targeted adjustments to signal control plans based on the cause, intersection type, control rules, etc., and taking into account coordinated adjustments with surrounding intersections.

[0084] It should also be noted that the road network governance model is iterated based on the real-time predicted road network resilience index to continuously improve the accuracy and adaptability of the model. The road network governance model disclosed herein inputs the current traffic data and the identified congestion category of the target network, outputs governance plans and strategies suitable for the current road conditions of the target network, and re-predicts the traffic status and calculates the resilience index based on the governance effect, determines the road network recovery capacity, continuously adjusts the governance plan, optimizes the governance strategy, and improves the governance effect.

[0085] By comprehensively using road network resilience indicators, road network governance models and real-time traffic data, automatic early warning, classified governance and prediction of traffic congestion under adverse conditions are achieved. By calculating road network resilience indicators, the recovery and resistance of the target road network under adverse conditions can be evaluated, and a basis for formulating corresponding governance plans can be provided. By implementing the governance plan, the road network resilience can be improved so that it can better resist the impact of adverse conditions and maintain normal operation. Based on the congestion category and the pre-trained road network governance model, targeted governance plans can be formulated, including signal control plan adjustment, manual operation plan, etc., to optimize traffic organization and improve road network traffic efficiency. Through the real-time predicted road network resilience indicators, the governance effect can be evaluated, and the governance plan can be adjusted according to the evaluation results to improve traffic governance efficiency. Through effective governance measures, traffic congestion can be alleviated, traffic delays can be reduced, traffic efficiency can be improved, and the traffic travel environment can be improved. By using technologies such as big data and artificial intelligence, real-time monitoring, early warning and governance of traffic congestion can be achieved, and the intelligent level of traffic management can be improved. By improving road network resilience and optimizing traffic organization, the risk resistance of the transportation system under adverse conditions can be enhanced, and the safe, efficient and sustainable operation of the urban transportation system can be guaranteed.

[0086] The disclosed embodiments can effectively solve the problem of traffic congestion under adverse conditions, enhance urban traffic resilience, improve the traffic travel environment, improve traffic management efficiency, and enhance the risk resistance of the traffic system, and have important practical significance and application value.

[0087] In some embodiments of the present disclosure, calculating the value of the road network resilience index of the target road network according to the current traffic data further includes the following steps:

[0088] 1. Calculate the redundancy value, resistance value, resilience value and reliability value respectively according to the current traffic data;

[0089] 2. Determine the comprehensive index value of road network resilience based on the calculated redundancy value, resistance value, resilience value and reliability value. The comprehensive index value of road network resilience is the weighted average of the redundancy value, resistance value, resilience value and reliability value.

[0090] Calculate the values ​​of individual indicators, including the redundancy value. Specifically analyze the historical traffic volume and average speed data of the region, fit the relationship, calculate the theoretical traffic volume of the current road network, compare the actual traffic volume with the theoretical traffic volume, calculate the difference, and obtain the redundancy value. For the resistance value, set the speed change threshold according to different levels of road sections, different weather types and abnormal events, compare the real-time road section speed with the normal situation, judge the road section resistance level, calculate the regional resistance level, and obtain the resistance value. For the resilience value, specifically analyze the time change of the historical delay of the region, fit the curve, give the floating coefficient, record the recovery time after the delay reaches a worse level, calculate the average recovery time, and obtain the resilience value. For the reliability value, specifically calculate the travel time reliability and delay reliability, and comprehensively calculate the reserved time per kilometer of the road network to obtain the reliability value.

[0091] The redundancy value, resistance value, resilience value and reliability value are weighted averaged according to certain weights to obtain the comprehensive index value of road network resilience. The weight setting can be adjusted according to the actual situation. For example, the weight can be set according to the importance of different indicators or the degree of impact on traffic operation. The preset threshold of the comprehensive index value of road network resilience needs to be determined according to the specific situation of the road network. By calculating the comprehensive index value of road network resilience, the resilience capacity of the target road network under preset conditions can be evaluated to comprehensively judge whether the congested road network can be restored.

[0092] In some embodiments of the present disclosure, when the congestion category of the target road network is a normal congestion point, the method further includes the following steps:

[0093] 1. Obtain historical traffic network management data, which includes environmental condition data, traffic data and management plan data at different times;

[0094] 2. Train the road network management model based on historical traffic network management data.

[0095] The historical governance plan data includes various operational governance plans for normal traffic jams in different time periods, such as adjustment of signal control plans, reorganization of traffic flow, release of traffic information, etc. The historical governance plan data can be obtained from the archives of the traffic management department, or through historical traffic surveys and simulation experiments.

[0096] The road network management model is trained using the acquired historical traffic network management data. The model training process usually involves machine learning techniques, such as deep learning and regression analysis, so that the model can learn effective strategies for managing congestion from historical data. The trained model can recommend or automatically execute corresponding management plans based on current traffic conditions and environmental conditions to reduce or eliminate traffic congestion. The trained model can adjust the management plan in real time based on traffic data to improve traffic flow and the overall efficiency of the road network. Through continuous learning and adjustment of the model, the management plan can be continuously optimized to adapt to changing traffic needs and environmental conditions.

[0097] The disclosed embodiment can improve the intelligence level of traffic management by training the road network management model with historical traffic network management data, and realize the effective management and control of normal traffic jams. This method helps to improve the efficiency and effectiveness of traffic management, reduce traffic congestion, and improve the traffic capacity and resilience of the road network.

[0098] In some embodiments of the present disclosure, when the congestion category of the target road network is a temporary congestion point, the method further includes the following steps:

[0099] 1. Obtain surveillance video information of temporary congestion points;

[0100] 2. Determine the type of disposal based on the surveillance video information of temporary traffic jams, which include single-point real-time optimization, single-point time period plan, and manual locking of specified time length plan.

[0101] Obtain surveillance video information of temporary congestion points. The surveillance video information can come from high-definition cameras installed at intersections or road sections. These cameras can capture traffic flow in real time. Surveillance video information includes vehicle volume, vehicle speed, lane usage, traffic light status, etc. This information is crucial for understanding the cause of congestion and formulating governance strategies. Based on the surveillance video information, the type of disposal can be determined, including single-point real-time optimization, single-point time period solution, and manual lock-in for a specified time.

[0102] Among them, single-point real-time optimization: for current temporary congestion points, adjust the signal light timing or other traffic control measures in real time to immediately alleviate congestion. Single-point time plan: formulate a time-based signal control plan for changes in traffic flow within a specific time period to prevent future congestion. Manual lock-specified time plan: when necessary, traffic management personnel manually control the traffic lights and lock specific signal timing plans until the congestion is alleviated. Once the type of disposal is determined, the corresponding governance plan needs to be implemented, which may involve adjustments to the traffic signal control system, redirection of traffic flow, or other traffic management measures. After the implementation of the plan, it is necessary to evaluate its effect on alleviating traffic congestion and adjust it according to actual conditions.

[0103] By analyzing the surveillance video information of temporary traffic jams, the appropriate type of treatment can be quickly and accurately determined, thereby achieving timely response and effective management of traffic congestion. The disclosed embodiments can improve the flexibility and adaptability of traffic management, reduce the impact of traffic congestion on the road network, and improve the overall efficiency and resilience of the transportation system.

[0104] In some embodiments of the present disclosure, the following steps are also included:

[0105] 1. When the road network resilience index is lower than the preset threshold, identify the congestion level of the target road network;

[0106] 2. Determine the number of personnel to be deployed based on the level of congestion.

[0107] The value of the road network resilience index is calculated based on the current traffic data and compared with the preset threshold. If the road network resilience index is lower than the preset threshold, it means that the road network may face a higher risk under the preset conditions, the road network resilience is relatively low, and the congestion situation is not easy to alleviate. The road network governance model may not achieve good results, and it is necessary to further identify the congestion level and implement the solution of dispatching manpower to deal with it.

[0108] Determine the number of traffic dredging personnel to be deployed according to the identified congestion level. Deploy traffic dredging personnel to key sections or intersections to deal with possible traffic congestion or emergencies and ensure traffic order and safety. Evaluate the effect of traffic dredging personnel deployment on relieving traffic congestion and make adjustments based on actual conditions.

[0109] The specific congestion level and the amount of manpower deployed will depend on a number of factors, including but not limited to the following:

[0110] Congestion levels are usually classified according to the severity and scope of congestion, for example:

[0111] Minor congestion: Traffic volume is slightly higher than normal, but vehicles can still move smoothly.

[0112] Moderate congestion: Traffic flow increases significantly, and some sections of the road experience slow traffic or short-term congestion.

[0113] Severe congestion: The traffic volume is extremely large, most sections of the road are congested, and the vehicle speed drops significantly.

[0114] Extreme congestion: The traffic volume is extremely large, almost all road sections are congested, and vehicles can hardly move.

[0115] The number of dredging personnel deployed depends on factors such as the congestion level, congestion duration, impact area, weather conditions, road conditions, etc. Generally, the number of dredging personnel deployed will increase as the congestion level increases. For example:

[0116] Minor congestion: Additional congestion personnel may not be required, but traffic management personnel are required to monitor and provide guidance.

[0117] Moderate congestion: Additional manpower may be needed to direct traffic flow and avoid accidents.

[0118] Severe congestion: A large number of manpower, including traffic diversion personnel and traffic management staff, are required to conduct traffic diversion, accident handling and traffic flow control.

[0119] Extreme congestion: Emergency response may be required, including traffic control personnel, ambulances, fire trucks, etc., to handle the emergency and restore traffic order.

[0120] The disclosed embodiments can effectively deal with possible traffic congestion risks, ensure traffic order and safety, improve the response capabilities of traffic management, reduce the impact of traffic congestion on the road network, and enhance the overall efficiency and resilience of the transportation system by identifying the congestion level of the target road network and determining the number of personnel to be deployed according to the level.

[0121] In some embodiments of the present disclosure, Figure 3-Figure 6 Taking the road network management method disclosed in the present invention as an example, the road network management method disclosed in the present invention is described in detail.

[0122] like Figure 3 As shown, taking severe weather conditions as an example, the road network management methods include:

[0123] S302, taking into account the adverse weather factors and integrating the Internet warning intersection data, to provide reminders of the congestion spread at signalized intersections across the entire road network, and to design road network resilience indicators to evaluate road network resilience;

[0124] S304, determining whether the road network resilience is recoverable;

[0125] S306, when the road network resilience can be restored, judging the nature of the intersection according to the congestion characteristics of the intersection prompted in real time;

[0126] S308, automatically and adaptively discover the normal blocking points (i.e. normal key positions) and temporary blocking points (i.e. real-time key positions) of the road network by judging whether the congestion is spreading, traffic status data and manual experience data. The sign of whether the congestion is spreading is that the road sections and intersections associated with it have caused congestion in the connected sections. For the normal blocking points and temporary blocking points found, the resilience index of the blocking points is comprehensively analyzed, the response ability of the blocking points to the resilience index is judged, and the regional blocking points under the resilience conditions are screened. The highest strategy is to restore the resilience of the road network. For the normal blocking points and temporary blocking points, the operation mode and optimization mode are designed for comprehensive management. The operation mode is the method of normal congestion management, and the optimization mode is the single-point real-time management method; in view of the management characteristics of normal and temporary congestion points, the management goal is designed to optimize normal congestion to release, and optimize temporary congestion to smooth traffic; the comprehensive management strategy is designed for normal congestion points, shortening the congestion time on the basis of long-term recovery resilience, and preventing the congestion from spreading; for temporary congestion points, reduce delays and eliminate prompts on the basis of rapid recovery resilience; for the comprehensive management strategy of normal congestion points and the goals of the comprehensive management strategy, design a comprehensive management model based on deep learning neural network training. In view of the comprehensive management strategy of temporary congestion points and the goals of the comprehensive management strategy, design a single intersection timing optimization model.

[0127] S310, based on the governance strategy or single-point optimization plan and actual current traffic data (traffic status data and adverse condition data), predict the resilience of the road network under comprehensive governance, and provide feedback and iteration on the comprehensive governance model.

[0128] S312, under the condition that the road network resilience cannot be restored, the design of the dredging personnel deployment process requires human intervention on site.

[0129] Figure 4 A schematic diagram of a technical framework of an embodiment of the present disclosure is shown.

[0130] The road network resilience index defined in the embodiment of the present disclosure is specifically explained as follows:

[0131] Redundancy (red_index) refers to having multiple alternative paths or excess capacity. The design idea comes from combining the relationship between traffic volume and speed under different weather conditions in history, analyzing the minimum speed under different weather conditions, and then deriving the corresponding fuse traffic volume. When the traffic volume reaches or approaches this value, an early warning is generated; based on the current speed, it is determined whether there is redundancy in the traffic volume, thereby guiding traffic restrictions or diversion.

[0132] Calculation method:

[0133] (1) Analyze the historical data of regional traffic volume and average speed, and fit the relationship between the two (historical dynamic calculation);

[0134] (2) Using the fitting relationship, calculate the theoretical on-the-way quantity q′ of the current road network. During the calculation process, take the maximum value of the historical on-the-way quantity corresponding to the current average speed;

[0135] (3) Compare the actual in-transit quantity with the theoretical in-transit quantity and calculate the difference between the two;

[0136] (4) Calculate the current redundancy of the road network:

[0137]

[0138] If q>q′, it means the redundancy of the road network is 0.

[0139] Resistance (rl_index) is defined as the ability to resist natural disasters such as earthquakes, mudslides, and floods. The design idea comes from the resistance level of the road section based on whether the speed change in bad weather exceeds a given threshold. The threshold of each road section needs to be manually given in advance based on factors such as different weather and specific conditions of the road section. The key traffic status data indicator for calculating resistance is the road section level speed data.

[0140] Calculation method:

[0141] (1) Set corresponding speed change thresholds for different levels of road sections, different weather types (light, medium or heavy rain) and abnormal events (whether there is an accident or not). The thresholds are divided into two levels: Δt1 and Δt2;

[0142] (2) Compare the real-time road speed (10-minute level) with the speed value on the same working day / non-working day, at the same time, in normal weather, and without abnormal events, and take the difference Δt=t′-t;

[0143] (3) Compare the difference with the speed change threshold corresponding to the weather type in the current area and whether there are any abnormal events on the road section. If Δt<Δt1, the current resistance of the road section is Class A; if Δt1<Δt<Δt2, the current resistance of the road section is Class B. If Δt>Δt2, the current resistance of the road section is Class C.

[0144] (4) Determine the regional resistance level (rl_level):

[0145] When the proportion of A-level sections in the regional road network is greater than 50%, the regional resistance level is A-level;

[0146] When the proportion of C_rate in the regional road network is greater than 50%, the regional resistance level is C;

[0147] Except for the above two cases, the regional resistance level is B.

[0148] (5) Calculate the regional resistance (rl_index) level:

[0149]

[0150] Resilience (rf_index) refers to the ability to quickly recover from natural disasters and other emergencies. The design idea comes from analyzing the time required to recover to a non-congested level after the delay level reaches a worse level under bad weather based on historical delay data. The delay value corresponding to the "non-congested" level can be manually specified in advance. The key traffic status data indicator for calculating resilience is the regional level delay data.

[0151] Calculation method:

[0152] (1) Analyze the time variation of regional historical delays and fit the curve, denoted by t j The corresponding delay of the time fitting curve is d′ j ;

[0153] (2) Given a floating coefficient k;

[0154] (3) Record daily t j The actual delay is d j , when d j >d′ j *k, record the current time t j1 , and track to d j >d′ j *k (compared with the delay at the time of deterioration), record the current time t j2 , then the current recovery time rf_time=t j2 -t j1 ;

[0155] (4) All recovery times are averaged, and the result is the regional recovery time.

[0156] (5) Calculation of regional recovery capacity:

[0157]

[0158] Reliability (rel_index) refers to the ability to maintain traffic in daily and emergency situations. The design ideas come from two parts: one is (1 / congestion speed-1 / normal speed), where the speed unit is km / min; the other is (congestion delay index-normal delay index) / normal delay index. The calculation results can be divided into levels.

[0159] The key traffic status data indicators for calculating reliability are the segment-level speed and delay index data.

[0160] Reliability includes travel time reliability and delay reliability. Reliability can be expressed as the reserved time per kilometer of the road network. Calculation method of travel time reliability (differentiating between weather conditions):

[0161] (1) Obtain the historical road speed (converted to km / min);

[0162] (2) For each road segment l i , take the average speed at night (22:00-6:00 the next day) as the free flow speed v′ i ;

[0163] (3) For each road segment l i , record each time (t j , polymerization to 10min) speed v ij ;

[0164] (4) Calculate the reserved time per kilometer of the road network:

[0165]

[0166] Delay reliability calculation method (differentiating weather conditions):

[0167] (1) Obtain the historical regional delay index;

[0168] (2) Calculate the average historical delay index d′ of the region;

[0169] (3) At each time t in the region j The delay index is aggregated to 10 minutes and is recorded as d j ;

[0170] (4) Calculate regional delay reliability:

[0171]

[0172] Comprehensive resilience index: whether the resilience can be restored refers to whether the comprehensive value of each index is within a certain range.

[0173] The weighted average method is used to calculate the comprehensive resilience index t_index. The weight data of the index corresponds to [0.3, 0.3, 0.2, 0.2] according to the index level redundancy, resistance, resilience, and reliability:

[0174] t_index=0.3*red_index+0.3*rl_index+0.2*rf_index+0.2*rel_index

[0175] If t_index>0.65, it is judged that the regional road network resilience can be restored.

[0176] In some embodiments of the present disclosure, the congestion nature of the target road network is identified mainly by identifying normal key positions to confirm normal congestion points and real-time key positions to confirm temporary congestion points.

[0177] Normal congestion points refer to the congestion points that are regularly associated with adjacent intersections to form a combination of congested intersections. Specifically, first confirm the normal key positions, which refer to the points or intersections where regular congestion occurs. Regularity means that the congestion points have their own regularity, such as intersections with large traffic volume during commuting, tunnel elevated entrance roads, etc., and are associated with adjacent intersections as a congestion combination, which means that the congestion at the congestion point spreads to adjacent intersections, causing irreversible congestion at adjacent intersections. That is, congestion points with regular congestion and congestion spread are called normal congestion. When regular gambling points have real-time prompts, it is necessary to initiate a comprehensive governance strategy.

[0178] Temporary traffic jams are usually congestion warning intersections for Internet access, and their impact is generally not extended to adjacent intersections.

[0179] Among them, normal congestion warning:

[0180] First, based on expert experience, determine the existing difficult-to-manage congestion points in the road network and analyze the congestion patterns of normal congestion points. (Congestion patterns mainly refer to the regular characteristics of the occurrence, development and change of traffic congestion phenomena at specific times, places and conditions.) Expert experience determines normal congestion points; determines whether the predicted congestion points meet the conditions: regular congestion and whether it spreads to adjacent intersections;

[0181] Comprehensively analyze the historical data of road intersections at the congestion point location: traffic status indicators (flow patterns, congestion index patterns, speed patterns), intersection physical indicators (number of road sections, number of lanes, number of variable lanes, number of phases, whether there are tidal lanes, etc.), weather conditions and geographic location data (enumerated as 1. High-flow intersections; 2. Intersections connected to ramps; 3. Intersections in and out of the city (must pass); 4. Two-network construction points; 5. Intersections near business districts, hospitals, government units, schools, railway stations, etc.; 6. Intersections where main roads intersect with main roads, etc. 7-Ordinary ground intersections).

[0182] Select a suitable deep neural network model and predict key points of normal congestion based on historical data.

[0183] Deep neural networks, including but not limited to CNN, LSTM, RNN, BiLSTM, CNN-LSTM, CNN-BiGRU, Att-RNN, DA-RNN, etc.

[0184] Construct input data, the data content is shown in Table 1 below. Obtain historical data of at least 3 months, and construct an array of input data every 15 data cycles. Use 80% of the input data as a training set and the other 20% as a test set. After training the training set with different algorithms, generate different algorithm models and save them. Then put the test set data into the model to generate the predicted normal key points, compare the predicted normal key points with the actual normal key points, calculate the prediction accuracy, calculate the loss function, and finally compare the accuracy and loss function of each algorithm horizontally, select the algorithm with the highest accuracy corresponding to the intersection, and input the data obtained by the interface into the algorithm model.

[0185] Table 1

[0186]

[0187] After the model training is completed, the model is saved and then deployed in an online environment to iteratively train the model.

[0188] In some embodiments of the present disclosure, operation modes and optimization modes are designed for comprehensive management of normal and temporary congestion points, including a method in which the operation mode is normal congestion management and an optimization mode is a single-point real-time management method.

[0189] For regular congestion points, operation design and regular congestion point management target design are carried out according to their congestion characteristics, time characteristics and spatial characteristics.

[0190] Figure 5 A schematic diagram of a normal congestion point operation management process in an embodiment of the present disclosure is shown, and operation design considering the congestion problem of key congestion points is helpful to solve or alleviate the congestion points in a targeted manner. This includes the operation classification settings for date type, time period type, and weather type.

[0191] Dates are mainly classified according to the traffic status (such as flow) of N weeks. Currently, the date classification includes working days, non-working days, holidays and make-up days. Working days are divided into Monday, mid-week and Friday.

[0192] The time period classification includes classification according to fixed time periods and classification according to dynamic traffic status trends. Fixed time periods include morning peak, morning flat peak, noon flat peak, evening peak, evening flat peak and night flat peak. Dynamic time periods are reasonably divided mainly based on the trends and thresholds obtained from the historical statistics of traffic jams.

[0193] Weather type classification, according to static nature, includes all possible weather types. According to dynamic nature, the period is 3 months before the current date, and the weather types that have appeared in this period are selected.

[0194] In some embodiments of the present disclosure, the traffic network management model training process is as follows:

[0195] Select a suitable deep neural network model based on the current traffic status of normal traffic jams, including flow, delay and average speed data. Normal traffic jams include signal control scheme data at intersections, including any combination of cycle, green-to-signal ratio, phase difference, open or closed phase, etc. Historical manual operation schemes include setting manual schemes (cycle, green-to-signal ratio, phase difference) or locking the current scheme and the locking duration. Loop the operation data to train the traffic management model.

[0196] Deep neural networks, including but not limited to CNN, LSTM, RNN, BiLSTM, CNN-LSTM, CNN-BiGRU, Att-RNN, DA-RNN, etc.

[0197] Construct input data, including environmental condition data, traffic data and governance plan data at different times. The data content is shown in Table 2. Obtain historical data of traffic jams for at least 3 months, and construct an array of input data in a cycle of every 30 data cycles. Use 80% of the input data as a training set and the other 20% as a test set. After training the training set with different algorithms, generate different algorithm models and save them. Then put the test set data into the traffic governance model to generate a governance plan and the lock duration of the governance plan. The content of the governance plan is: modify the cycle or modify the green letter ratio or modify the phase difference or lock the plan and the lock duration of the plan or any combination of governance plans. Compare the recommendation with the actual results, calculate the loss function, and when the loss function converges, determine the readiness of the model, and then determine the accuracy of the various parameters of the algorithm training process. Finally, compare the accuracy of each algorithm model with the loss function horizontally, select the algorithm with the highest accuracy corresponding to the prompt situation, and determine the deployment of the algorithm.

[0198] Table 2

[0199]

[0200] Due to the application nature of the governance plan, the recommended governance plan involved in this patent will be implemented and applied after expert evaluation, and the expert evaluation results will also be used as necessary input data for model iteration.

[0201] After the model training is completed, the model is saved and then deployed in an online environment to iteratively train the model.

[0202] In some embodiments of the present disclosure, the calculation of the resilience index can be performed in real time through current traffic data, or can be predicted through a prediction model. The prediction model training process is as follows:

[0203] Select a suitable deep neural network model, obtain the recommended governance case and current traffic status data according to the actual scenario, predict the future short-term traffic status, and calculate the resilience index, that is, the predicted resilience index. According to the resilience index, the recovery capacity under the condition of road network congestion warning, that is, the comprehensive resilience index r_index should be greater than 0.65 to confirm whether to dispatch manpower.

[0204] Construct input data, including environmental condition data, traffic data and governance plan data at different times. The data content is shown in Table 3. Obtain historical data of traffic jams for at least 6 months, and construct an array of input data in a cycle of every 15 data cycles. Use 80% of the input data as a training set and the other 20% as a test set. After training the training set with different algorithms, generate different algorithm models and save them. Then put the test set data into the traffic prediction model to generate prediction data, including flow, delay and average speed. Calculate the road network resilience based on the prediction results. Compare the prediction results with the actual results, calculate the loss function, and determine the readiness of the model when the loss function converges and the loss function result is less than 0.2%, and then determine the accuracy of the parameters of the algorithm training process. Finally, compare the accuracy of each algorithm model with the loss function horizontally, select the algorithm with the highest accuracy corresponding to the prompt situation, and determine to deploy the algorithm.

[0205] Table 3

[0206]

[0207] Deploy and run the model based on offline training. Use real-time data to iterate the model during operation and optimize the model online.

[0208] When the model is running online, the scheduling model will predict the key points of congestion spread, output treatment plans for normal congestion points, predict the treatment effect of the treatment plan, that is, the results after treatment, observe the treatment effect, and quickly respond to whether manpower dispatch is needed.

[0209] In some embodiments of the present disclosure, temporary congestion points can be rectified according to the traffic management method of the present disclosure, or single-point congestion management can be directly implemented. The single-point congestion management process is as follows:

[0210] The goal of the prompt intersection treatment is to reduce delays and eliminate prompts. Prompt intersection treatment features:

[0211] (1) The reasons for the intersection warnings are delays and imbalances;

[0212] (2) Control rules: The control scheme control attention can be grouped into the following groups according to time and attention:

[0213] Time grouping: morning peak, off-peak, evening peak, night, weekdays, weekends, holidays Attention grouping: general intersections, key intersections.

[0214] Generally, the problem can be solved by pointing to the current intersection or the upstream and downstream intersections.

[0215] Key intersections include: 1. intersections with high traffic volume; 2. intersections connected to ramps; 3. intersections entering and exiting the city (must-pass); 4. intersections where main roads intersect with main roads, etc.

[0216] (3) The specific disposal contents are as shown in Table 4:

[0217] Table 4

[0218]

[0219] In some embodiments of the present disclosure, Figure 6 The figure shows a schematic diagram of the temporary blocking point processing process. Figure 6 As shown, check the monitoring, determine the traffic problem at this intersection based on the warning type and the status of surrounding intersections, check and adjust the intersection plan for this intersection and the surrounding intersections, and continue to observe the results to confirm whether the plan is reasonable until the peak ends.

[0220] In some embodiments of the present disclosure, the premise for deploying dredging personnel is that the resilience of the road network cannot be restored. The principle of deploying the number of manpower C can be calculated based on the normal blocking point level (I, II, III), the normal key point N1, the number of intersections N2 included in the blocking point, and the number of road sections M associated with the intersection.

[0221] The principles for evaluating the level of normal congestion points in the disclosed embodiment are: (1) whether the normal congestion point is associated with other normal key points; (2) the number of intersections included in the congestion point; and (3) the duration of the congestion.

[0222] Level I congestion: The congestion point is associated with at least one other normal key point, the number of intersections included in the congestion point is greater than or equal to 6, and the congestion duration is greater than 15 minutes; when the congestion level is I, the manpower quantity C1 is calculated as: each section of each normal key point requires one person.

[0223] Level II congestion: The congestion point is not associated with other normal key points, the number of intersections included in the congestion point is greater than or equal to 6, and the congestion duration is greater than 15 minutes; the manpower quantity C1 is calculated as: one person is required for each normal key point and the associated intersections.

[0224] Level III congestion: The congestion point is not associated with other normal key points, the number of intersections included in the congestion point is less than 6, and the congestion duration is less than 15 minutes; the manpower quantity C1 is calculated as: only one person is deployed at the normal key point.

[0225] The manpower quantity C is calculated as:

[0226]

[0227] Based on the same inventive concept, the present disclosure also provides a traffic network management device in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0228] Figure 7 A schematic diagram of a traffic network management device in an embodiment of the present disclosure is shown. Figure 7 As shown, the device comprises:

[0229] Traffic data acquisition module 1001, used to acquire current traffic data of a target road network, where the target road network is a road network with congestion;

[0230] A road network resilience index calculation module 1002 is used to calculate the value of the road network resilience index of the target road network according to the current traffic data. The road network resilience index is used to characterize the resilience capability of the target road network under preset conditions;

[0231] The road network management module 1003 is used to identify the congestion category of the target road network when the road network resilience index is higher than a preset threshold, and to perform congestion management on the target road network based on the congestion category and a pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion categories include normal congestion points and temporary congestion points.

[0232] In some embodiments of the present disclosure, the road network resilience index calculation module 1002 is also used to calculate the redundancy value, resistance value, resilience value and reliability value respectively according to the current traffic data; determine the comprehensive road network resilience index value according to the calculated redundancy value, resistance value, resilience value and reliability value, and the comprehensive road network resilience index value is the weighted average of the redundancy value, resistance value, resilience value and reliability value.

[0233] In some embodiments of the present disclosure, the traffic network management device is also used to obtain historical management solution data, which includes operation management solutions at different times; and train the road network management model based on the historical management solution data.

[0234] In some embodiments of the present disclosure, the traffic network management device is also used to obtain surveillance video information of temporary traffic jams; based on the surveillance video information of temporary traffic jams, the disposal type is determined, and the disposal types include single-point real-time optimization, single-point time period plan, and manual locking of specified time length plan.

[0235] In some embodiments of the present disclosure, the traffic network management device is also used to identify the congestion level of the target network when the network resilience index is lower than a preset threshold; and determine the number of dredging personnel to be deployed according to the congestion level.

[0236] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above method embodiments. It should be noted that the above modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0237] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0238] Refer to the following Figure 8 1100 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 1100 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0239] like Figure 8 As shown, the electronic device 1100 is in the form of a general computing device. The components of the electronic device 1100 may include but are not limited to: at least one processing unit 1110, at least one storage unit 1120, and a bus 1130 connecting different system components (including the storage unit 1120 and the processing unit 1110).

[0240] Among them, the storage unit stores a program code, and the program code can be executed by the processing unit 1110, so that the processing unit 1110 executes the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 1110 can execute the following steps of the above method embodiment: obtaining the current traffic data of the target road network, the target road network is a road network with congestion; according to the current traffic data, calculating the value of the road network resilience index of the target road network, the road network resilience index is used to characterize the resilience of the target road network under preset conditions; when the road network resilience index is higher than the preset threshold, identifying the congestion category of the target road network, and based on the congestion category and the pre-trained road network governance model, the target road network is congested. Governance, the road network governance model is iterated based on the real-time predicted road network resilience index, and the congestion category includes normal congestion points and temporary congestion points.

[0241] The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 11201 and / or a cache storage unit 11202 , and may further include a read-only storage unit (ROM) 11203 .

[0242] The storage unit 1120 may also include a program / utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0243] Bus 1130 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0244] The electronic device 1100 may also communicate with one or more external devices 1140 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1100, and / or communicate with any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1150. Furthermore, the electronic device 1100 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1160. As shown, the network adapter 1160 communicates with other modules of the electronic device 1100 via a bus 1130. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0245] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0246] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer program product, which includes: a computer program, which implements the method in the above embodiment when executed by a processor.

[0247] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0248] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0249] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0250] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0251] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0252] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0253] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0254] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0255] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for managing a traffic network, characterized in that: include: Acquire current traffic data of a target road network, wherein the target road network is a road network with congestion; Calculate the value of the road network resilience index of the target road network according to the current traffic data, where the road network resilience index is used to characterize the resilience capability of the target road network under preset conditions; When the road network resilience index is higher than a preset threshold, the congestion category of the target road network is identified, and congestion management is performed on the target road network based on the congestion category and a pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion category includes normal congestion points and temporary congestion points.

2. The traffic network management method according to claim 1, characterized in that: The road network resilience indicators include one or more of the following: redundancy, resistance, resilience and reliability; The redundancy represents the ability of the target road network to have multiple alternative paths; The resistance represents the ability of the target road network to resist unexpected accidents; The resilience represents the ability of the target road network to recover from an unexpected accident; The reliability represents the ability of the target road network to maintain traffic under unexpected circumstances.

3. The traffic network management method according to claim 2, characterized in that: Calculating a value of a road network resilience index of the target road network according to the current traffic data includes: Calculate the redundancy value, resistance value, resilience value and reliability value respectively according to the current traffic data; The comprehensive index value of road network resilience is determined based on the calculated redundancy value, resistance value, resilience value and reliability value. The comprehensive index value of road network resilience is the weighted average of the redundancy value, resistance value, resilience value and reliability value.

4. The method for managing a traffic network according to claim 1, characterized in that: When the congestion category of the target road network is a normal congestion point, the method further includes: Acquire historical traffic network management data, wherein the historical traffic network management data includes environmental condition data, traffic data and management plan data at different times; The road network management model is trained based on the historical management solution data.

5. The traffic network management method according to claim 1, characterized in that: When the congestion category of the target road network is a temporary congestion point, the method further includes: Obtaining surveillance video information of the temporary congestion point; According to the monitoring video information of the temporary traffic jam, the disposal type is determined, and the disposal type includes single-point real-time optimization, single-point time period plan and manual locking of a specified time length plan.

6. The method for managing a traffic network according to claim 1, characterized in that: The method further comprises: When the road network resilience index is lower than a preset threshold, identifying the congestion level of the target road network; The number of personnel to be deployed for clearing the congestion is determined based on the congestion level.

7. A traffic network management device, characterized in that: include: A traffic data acquisition module is used to acquire current traffic data of a target road network, wherein the target road network is a road network with congestion; A road network resilience index calculation module, used to calculate the value of the road network resilience index of the target road network according to the current traffic data, wherein the road network resilience index is used to characterize the resilience capacity of the target road network under preset conditions; The road network management module is used to identify the congestion category of the target road network when the road network resilience index is higher than a preset threshold, and perform congestion management on the target road network based on the congestion category and a pre-trained road network management model. The road network management model is iterated based on the real-time predicted road network resilience index. The congestion category includes normal congestion points and temporary congestion points.

8. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the traffic network management method described in any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the traffic network management method described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising: A computer program or instruction, characterized in that when the computer program or instruction is executed by a processor, it implements the traffic network management method described in any one of claims 1 to 6.

Images