Traffic guidance control method, system and device for road construction area

Abstract

The application discloses a traffic diversion control method, system and equipment for a road construction area, relates to the field of traffic control, and comprises the following steps: collecting traffic data of a target area, and establishing traffic characteristics of the target area; acquiring construction data of a construction area, fitting construction influence, and establishing a three-level interference path space structure; configuring a target traffic state, collecting data of a navigation account subject after the navigation reaches the construction area; predicting navigation diversion by using a behavior prediction model; acquiring a real-time traffic state of the target area, establishing a reach time node according to a navigation reach result, fitting and updating a traffic time sequence based on reach data flow, a prediction result and the real-time traffic state; and establishing a deviation identification result according to the target traffic state and the traffic time sequence fitting result, and generating a feedback incentive correction navigation diversion. The application solves the technical problem that the existing traffic diversion control has poor diversion effect, and achieves the technical effect of improving traffic diversion efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of traffic control, in particular to a traffic diversion control method, system and device for a road construction area. BACKGROUND

[0002] Traffic diversion control for a road construction area is crucial for ensuring smooth urban traffic and reducing the impact of construction on public travel. Currently, the main method to solve this problem is to plan traffic diversion based on fixed information or simple traffic flow statistics for the construction area. However, the current method fails to fully consider the dynamic changes of actual traffic flow, the complexity and diversity of construction impact, and the differences in individual travel behavior, resulting in poor diversion effect and difficulty in effectively responding to sudden conditions in the construction area traffic.

[0003] In the related art, traffic diversion control for a road construction area has the technical problem of poor diversion effect. SUMMARY

[0004] The present application provides a traffic diversion control method, system and device for a road construction area. By collecting traffic data for the target area, analyzing and constructing traffic characteristics for the target area, obtaining road construction data, combining the traffic characteristics for the target area, performing construction impact fitting analysis, establishing a three-level interference path spatial structure model, configuring the target traffic state based on the three-level interference path spatial structure model, collecting navigation account subject data when the navigation reaches the road construction area, constructing an account data set, using a behavior prediction model, combining the account data set and the construction data, performing navigation diversion prediction, generating a prediction result, obtaining the target area traffic state in real time, generating a reach time node based on the navigation reach result, forming a reach data stream, fitting and updating the traffic time sequence based on the reach data stream, the prediction result and the real-time traffic state, comparing the target traffic state with the traffic time sequence fitting result, identifying deviations and generating feedback incentives, correcting the navigation diversion strategy based on the feedback incentives, and implementing traffic diversion management, the present application solves the technical problem of poor diversion effect in the existing traffic diversion control for a road construction area, and achieves the technical effect of improving traffic diversion efficiency and accuracy.

[0005] The application provides a traffic diversion control method for a road construction area, comprising: collecting traffic data of a target area to establish traffic characteristics of the target area based on the collected traffic data; obtaining construction data of the road construction area, fitting construction influence based on the construction data and the traffic characteristics of the target area, and establishing a three-level interference path space structure; configuring a target traffic state based on the three-level interference path space structure, collecting data of a navigation account subject after any navigation reaches the road construction area, and establishing an account data set; predicting navigation diversion based on the account data set and the construction data by using a behavior prediction model, establishing a prediction result; obtaining a real-time traffic state of the target area, establishing a reach time node based on a navigation reach result, forming a reach data stream, fitting and updating a traffic time sequence based on the reach data stream, the prediction result, and the real-time traffic state; establishing a deviation identification result based on the target traffic state and the traffic time sequence fitting result, generating a feedback incentive, correcting navigation diversion based on the feedback incentive, and performing traffic diversion management.

[0006] In possible implementation manners, the deviation identification result is used to create a target correction task, the target correction task being a guide correction task for an abnormally predicted behavior user in the prediction result; the target correction task is used as a target to perform feedback incentive optimization under an incentive cost balance constraint, the feedback incentive including navigation integral incentive, carbon footprint incentive, route priority incentive, visual social exposure incentive, and group incentive; and the feedback incentive optimization result is used to generate the feedback incentive.

[0007] In possible implementation manners, the traffic diversion management is performed based on the feedback incentive, and the following processing is performed: after any navigation vehicle enters the road construction area, a real-time congestion state of the road construction area is identified to generate a congestion penalty coefficient; an additional path cost calculation of the navigation vehicle under the corrected navigation diversion is performed to generate a cost compensation coefficient; and green travel credit penalty management of the navigation vehicle is performed based on the congestion penalty coefficient and the cost compensation coefficient.

[0008] In a possible implementation manner, the target traffic flow state is configured by using the three-level interference path space structure, and the following processing is performed: a first-level interference path region, a second-level interference path region, and a third-level interference path region are located according to the three-level interference path space structure, the first-level interference path region is a direct construction influence region, the second-level interference path region is a nearby diversion region with an association degree satisfying an association threshold, and the third-level interference path region is a remote diversion region with an association degree not satisfying the association threshold; a path topology structure is established based on the first-level interference path region, the second-level interference path region, and the third-level interference path region; and traffic balance optimization of the three-level interference path is performed based on the path topology structure and the target region traffic feature as fitting data, to establish the target traffic flow state.

[0009] In a possible implementation manner, the target region traffic feature is established by using the traffic data collection result, and the following processing is performed: a first backtracking time window and a second backtracking time window are created by taking a current time node as a time zero point, the first backtracking time window is a week backtracking window, and the second backtracking time window is a month backtracking window; after trust factors of the first backtracking time window and the second backtracking time window are allocated, traffic feature verification and identification of the traffic data collection result are performed by using the first backtracking time window and the second backtracking time window, to establish the target region traffic feature.

[0010] In a possible implementation manner, the navigation diversion prediction based on the account data set and the construction data is performed by using the behavior prediction model, and a prediction result is established, and the following processing is performed: data features of the account data set are extracted by using an extraction layer of the behavior prediction model, the data features include a historical compliance rate, a response time delay, a path use preference, and an integral use history; after the construction data is extracted as construction features, a time sequence prediction layer is activated to perform navigation diversion compliance prediction based on the construction features and the data features, to establish the prediction result.

[0011] In a possible implementation manner, the traffic time sequence fitting is updated based on the touch data flow, the prediction result, and the real-time traffic flow state, and the following processing is performed: a traffic proportion prediction of a non-navigation vehicle is performed, a first time sequence fitting compensation is established by using a traffic proportion prediction result; influence analysis of non-vehicle traffic is performed according to the construction data, an influence prediction of non-vehicle traffic on a vehicle traffic road is generated based on an influence analysis result, and a second time sequence fitting compensation is established; and the traffic time sequence fitting result is compensated and managed according to the first time sequence fitting compensation and the second time sequence fitting compensation.

[0012] In a possible implementation manner, after the traffic diversion management is performed, the following processing is performed: traffic monitoring is performed on a road construction region; when a traffic monitoring result satisfies an abnormal threshold, a temporary closure instruction is triggered; and the road construction region is changed to a temporary closure state according to the temporary closure instruction.

[0013] The present application also provides a traffic diversion control system for road construction areas, including: a target area traffic feature establishment module, which is used to execute traffic data collection of the target area and establish the target area traffic features based on the traffic data collection results; a construction impact fitting module, which is used to obtain construction data of the road construction area, perform construction impact fitting based on the construction data and the target area traffic features, and establish a three-level interference path space structure; an account data set establishment module, which is used to configure the target traffic flow state with the three-level interference path space structure, and execute data collection of the navigation account subject after any navigation reaches the road construction area, and establish an account Data set; navigation diversion prediction module, used to use the behavior prediction model to perform navigation diversion prediction based on the account data set and construction data, and establish the prediction result; the traffic flow timing fitting update module, used to obtain the real-time traffic flow status of the target area, establish the touch time node according to the navigation touch result, form the touch data stream, and perform traffic flow timing fitting update based on the touch data stream, the prediction result, and the real-time traffic flow status; the navigation diversion correction module, used to establish the deviation recognition result and generate feedback incentive according to the target traffic flow status and the traffic flow timing fitting result, correct the navigation diversion according to the feedback incentive, and perform traffic diversion management.

[0014] The present application also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing a traffic diversion control method in a road construction area when executing the executable instructions stored in the memory.

[0015] The traffic diversion control method, system, and device for road construction areas proposed in this application first collect traffic data for the target area, establish traffic characteristics for the target area based on the traffic data collection results, then obtain construction data for the road construction area, perform construction impact fitting based on the construction data and the traffic characteristics of the target area, establish a three-level interference path spatial structure, and then configure the target traffic flow state based on the three-level interference path spatial structure. After any navigation reaches the road construction area, perform data collection on the navigation account subject to establish an account data set. Then, use the behavior prediction model to perform navigation diversion prediction based on the account data set and construction data, establish a prediction result, and then obtain the real-time traffic flow state of the target area. According to the navigation contact result, a contact time node is established to form a contact data stream. Based on the contact data stream, the prediction result, and the real-time traffic flow state, a traffic flow time series fitting and update is performed. Finally, according to the target traffic flow state and the traffic flow time series fitting result, a deviation recognition result is established and a feedback incentive is generated. According to the feedback incentive, navigation diversion is corrected and traffic diversion management is performed. The technical effect of improving traffic diversion efficiency and accuracy is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below, and the flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application in the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously according to needs. Meanwhile, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0017] Figure 1 The flowchart of the traffic diversion control method of the road construction area provided by the embodiments of the present application.

[0018] Figure 2 The structural schematic diagram of the traffic diversion control system of the road construction area provided by the embodiments of the present application.

[0019] Figure 3 The structural schematic diagram of the electronic device provided by the embodiments of the present application.

[0020] Label explanation: target area passing feature establishment module 10, construction influence fitting module 20, account data set establishment module 30, navigation diversion prediction module 40, vehicle flow time sequence fitting update module 50, navigation diversion correction module 60, input device 301, processor 302, memory 303, output device 304. DETAILED DESCRIPTION

[0021] The foregoing description is only a summary of the technical solutions of the present application, in order to more clearly understand the technical means of the present application, the embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0022] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings, and the described embodiments should not be regarded as limiting the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict, and the term "first\second" referred to only distinguishes similar objects, and does not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0024] The embodiments of the present application provide a traffic diversion control method for a road construction area, as shown in the following table: Figure 1 The method comprises the following steps:

[0025] In step S100, traffic data of a target area is collected, and traffic characteristics of the target area are established based on the collected traffic data.

[0026] Specifically, a plurality of sensors are installed in the target area (the range is greater than the road construction area), including but not limited to: traffic flow sensors, cameras, GPS data collectors, weather sensors, etc. Among them, the traffic flow sensor (such as a loop coil detector, a microwave radar detector) is used to detect the number and speed of vehicles passing through. The camera is used for license plate recognition and vehicle trajectory tracking. The GPS data collector (vehicle built-in GPS or mobile phone navigation application) is used to collect vehicle position and speed data. The weather sensor is used to monitor weather conditions, which will affect traffic flow.

[0027] Preliminary data processing and compression are performed at the sensor end using edge computing devices (such as small servers). The data is transmitted to the cloud or local data center for storage and further analysis. The traffic data is processed and analyzed in two time windows, short time window and long time window, to extract traffic characteristics such as average vehicle speed, vehicle flow, congestion index, etc.

[0028] For example, on a main road in a city, a microwave radar detector is installed every 50 meters, and a high-definition camera is installed every 100 meters. These devices collect vehicle speed and license plate information in real time and transmit data to a local server through a wireless network.

[0029] In a possible implementation, the step S100 of establishing the traffic feature of the target area based on the traffic data collection result further includes a step S110 of creating a first backtracking time window and a second backtracking time window, with a current time node as a time zero point. Specifically, the current time node (for example, the time when the system starts or the data collection begins) is taken as the time zero point to create the time window. The first backtracking time window (the weekly backtracking window) is a time range of 7 days (one week) backtracking from the current time node. The second backtracking time window (the monthly backtracking window) is a time range of 30 days (one month) backtracking from the current time node. In the data collection system, the specific start and end times of the two time windows are calculated according to the current time stamp.

[0030] For example, assuming that the current time node is May 19, 2025, 12:00, then: the start and end times of the first backtracking time window (the weekly backtracking window) are May 12, 2025, 12:00 to May 19, 2025, 12:00. The start and end times of the second backtracking time window (the monthly backtracking window) are April 19, 2025, 12:00 to May 19, 2025, 12:00.

[0031] The step S120 is to perform traffic feature verification and identification of the traffic data collection result in the first backtracking time window and the second backtracking time window after the trust factors of the first backtracking time window and the second backtracking time window are allocated, so as to establish the traffic feature of the target area. Specifically, the trust factor is a weight value for measuring the importance of data in different time windows. For example, a higher trust factor (such as 0.7) can be allocated to the first backtracking time window (the weekly backtracking window), because the data in the last week can better reflect the current traffic condition; a lower trust factor (such as 0.3) can be allocated to the second backtracking time window (the monthly backtracking window), because the data in a month can provide a longer-term trend, but the timeliness is weaker. The traffic data in the two time windows are respectively subjected to feature extraction, such as calculation of average speed, traffic volume, congestion index, etc. Statistical analysis or machine learning method is used to verify and identify the traffic features of the two time windows, such as through clustering analysis or anomaly detection algorithm, to judge whether the data conforms to the expected traffic mode. The traffic features of the two time windows are weighted and averaged according to the trust factors to obtain the comprehensive traffic feature. For example, if the average speed of the first backtracking time window is 40 km / h and the average speed of the second backtracking time window is 35 km / h, then the comprehensive average speed is: 0.7 x 40 + 0.3 x 35 = 38.5 km / h. This implementation can more accurately establish the traffic feature of the target area by introducing the two backtracking time windows and the trust factor, combining short-term and long-term data.

[0032] Step S200 , obtaining construction data of a road construction area, performing construction impact fitting based on the construction data and traffic characteristics of the target area, and establishing a three-level interference path spatial structure.

[0033] Specifically, the construction plan, including construction time, construction scope, number of occupied lanes, etc., is obtained through construction management software or manual input. Traffic simulation software (such as VISSIM or Synchro) is used to combine the traffic characteristics of the target area and construction data to simulate the impact of construction on traffic flow. Based on the fitting results of the construction impact, a three-level interference path spatial structure is established. The three-level interference path spatial structure is a traffic diversion area divided according to the impact of construction. Among them, the first-level induction area is the area closest to the road construction area, and vehicles need to directly detour or slow down. The second-level buffer area is an area slightly farther away from the road construction area, and vehicles may need to adjust their driving speed or lane. The third-level monitoring area is an area farther away from the road construction area, mainly used to monitor traffic flow changes and provide early warnings. These areas are dynamic and will be adjusted according to real-time traffic flow and construction progress.

[0034] For example, a road section is undergoing road repairs, with the construction area occupying one lane. The construction data includes the construction period from 9:00 AM to 5:00 PM, and the occupied lane number is Lane 2. The transportation department uses VISSIM software, combined with previously established target area traffic characteristics (such as average speed and volume), to simulate the impact of the construction on traffic flow. Based on the simulation results, the area 200 meters ahead of the road construction area is designated as a Level 1 guidance zone, 500 meters ahead as a Level 2 buffer zone, and 1000 meters ahead as a Level 3 monitoring zone. These zones are dynamically adjusted based on real-time traffic flow conditions.

[0035] In step S300 , the target traffic flow state is configured using the three-level interference path spatial structure, and after any navigation reaches a road construction area, data collection of the navigation account subject is performed to establish an account data set.

[0036] Specifically, the target traffic state refers to the distribution, speed, flow, and other indicators of traffic that are expected to be achieved in the road construction area and its surroundings. These indicators are set according to the construction impact and traffic relief goals. For example, the target traffic state can include: vehicle speed (vehicle speed before the road construction area should be maintained at 30 km / h or above), vehicle flow (vehicle flow through the road construction area per hour should be controlled within 1000 vehicles), congestion probability (congestion probability of the road construction area should be less than 30%). According to the three-level interference path spatial structure (first-level induction zone, second-level buffer zone, third-level monitoring zone), the traffic state is dynamically adjusted and optimized to achieve the goal of traffic relief. For example, in the first-level induction zone, traffic signal length can be adjusted, temporary traffic signs or variable message boards can be set up to guide vehicles to detour or slow down, and intelligent transportation system (ITS) platform can be used to send induction information to the navigation system of vehicles, prompting users to detour or slow down in advance; in the second-level buffer zone, traffic signal length can be adjusted to optimize traffic distribution and reduce vehicle flow entering the first-level induction zone, and variable message boards or broadcasts can be used to remind drivers of the upcoming construction and suggest adjusting the route in advance; in the third-level monitoring zone, sensor networks can be used to monitor traffic state in real time, early warning of possible congestion, and dynamic adjustment of traffic relief strategies such as adjusting signal length or issuing new navigation suggestions based on real-time monitoring data.

[0037] When any vehicle uses a navigation system (such as a car navigation system, a mobile phone navigation system) to approach the road construction area, the user's driving data is collected by the navigation software with the user's permission or authorization, including: historical navigation behavior (whether the user often chooses the route recommended by the navigation software, whether the user will choose to detour to avoid congestion), real-time navigation behavior (the actual driving route and speed of the user when approaching the road construction area), user feedback (whether the user manually adjusts the navigation route, whether the user provides feedback on the navigation suggestions, such as "not following the recommended route"). Among them, encryption technology is used to protect user data privacy. The collected navigation data is stored in the data center to form an account data set.

[0038] In one possible implementation, the step S300 of configuring the target traffic flow state according to the three-level interference path spatial structure further includes a step S310 of positioning a first-level interference path region, a second-level interference path region, and a third-level interference path region according to the three-level interference path spatial structure, the first-level interference path region being a direct construction impact region, the second-level interference path region being a nearby diversion region with a correlation degree satisfying a correlation threshold, and the third-level interference path region being a remote diversion region with a correlation degree not satisfying the correlation threshold. Specifically, the first-level interference path region is a region directly affected by construction, which is the road construction region itself and the lanes or road segments adjacent thereto. The second-level interference path region is a region with a relatively high correlation degree (for example, vehicles can be guided to these regions to detour) with the first-level interference path region but not directly affected by construction. The correlation degree can be calculated by factors such as traffic flow and distance, and when the correlation degree exceeds a certain threshold, the second-level interference path region is divided. The third-level interference path region is a region with a certain distance from the road construction region, a relatively low correlation degree (not reaching the threshold of the second-level interference path region), but still needing remote diversion. The three regions are accurately divided by using geographic information system (GIS) technology in combination with construction data and traffic flow data. The influence of construction on traffic flow is simulated by using traffic simulation software (such as VISSIM) to determine the boundaries of each region.

[0039] The step S320 of establishing a path topology based on the first-level interference path region, the second-level interference path region, and the third-level interference path region. Specifically, using the graph theory method, each interference path region is regarded as a node in the graph, and the road connection is regarded as an edge. The connection relationship between nodes is established to represent the possible paths of vehicles from one region to another region. According to the traffic flow and the road network, the weights (for example, distance, travel time, congestion probability) between nodes are determined. The complete path topology is constructed by using GIS data and traffic simulation results.

[0040] For example, it is assumed that the first-level interference path region is node A, the second-level interference path region is node B and C, and the third-level interference path region is node D and E. The connection relationship between nodes is as follows: A is connected with B and C (indicating that vehicles can directly detour from the construction region to the adjacent region). B is connected with D, and C is connected with E (indicating that vehicles can continue to detour from the adjacent region to the remote region). The weight of each connection edge is calculated according to the road length and the expected travel time.

[0041] Step S330, using the target area traffic characteristics as fitting data, based on the path topology, the traffic balance optimization of three-level interference paths is carried out to establish the target traffic state. Specifically, using optimization algorithm (such as genetic algorithm, simulated annealing algorithm) combined with the traffic characteristics (such as speed, traffic flow) of the target area, the optimal traffic distribution scheme is found on the path topology. The optimization goal is to maximize the traffic efficiency of the whole region, while trying to reduce congestion. According to the optimization result, the traffic state of each region (such as traffic flow, speed, congestion probability) is determined. These states are used as the basis for traffic guidance.

[0042] For example, assuming that the traffic characteristics of the target area show that the current average speed is 30 kilometers per hour and the traffic flow is 800 vehicles per hour. Through the optimization algorithm, the optimal traffic distribution scheme is found on the path topology: in the first-level interference path region, the vehicle is suggested to slow down to 20 kilometers per hour, and the traffic flow is controlled to 500 vehicles per hour. In the second-level interference path region, the vehicle is guided to detour, and the traffic flow is distributed to 200 vehicles per hour. In the third-level interference path region, the prompt of early deceleration or route adjustment is issued, and the traffic flow is distributed to 100 vehicles per hour. This implementation can more accurately identify the construction influence range and dynamically optimize the traffic distribution through the division of three-level interference path regions, the establishment of path topology and traffic balance optimization.

[0043] Step S400, using the behavior prediction model to predict the navigation guidance based on the account data set and the construction data, and establishing the prediction result.

[0044] Specifically, based on the user's historical navigation behavior and construction data, a behavior prediction model is constructed. The goal of this model is to predict the user's navigation choices when facing road construction areas (for example, whether to obey navigation suggestions, whether to choose detour, etc.). Machine learning algorithms (such as logistic regression, decision tree or deep learning models) are used to train the behavior prediction model. The input features include: user's historical navigation behavior (whether to choose recommended route frequently), detailed information of road construction area (such as construction time, number of occupied lanes, expected congestion degree). The output is the user's compliance probability to navigation suggestions (for example, the probability of user choosing detour is 80%). According to the user's compliance probability to navigation suggestions, the navigation guidance prediction result is generated. The prediction result can include: the route the user may choose, the time the user arrives at the construction area, whether the user may choose detour, etc. The prediction result is stored in the data center for subsequent traffic guidance management.

[0045] In a possible implementation, the step S400 of performing the navigation guidance prediction based on the account dataset and the construction data by using the behavior prediction model further includes a step S410 of extracting data features of the account dataset by using an extraction layer of the behavior prediction model, the data features including a historical compliance rate, a response time delay, a path use preference, and an integral use history. Specifically, the historical compliance rate refers to a proportion of compliance of a user to a navigation suggestion in a past navigation process. For example, if the user selects a route recommended by the navigation in 8 of the past 10 times of navigation, the historical compliance rate is 80%. The response time delay refers to a response time of the user to the navigation suggestion. For example, a time interval from a time when the navigation software pushes the suggestion to a time when the user actually starts to perform (such as changing the route). The path use preference refers to a preference of the user to different types of paths, for example, whether the user is inclined to select an expressway or to avoid a congested road segment. The integral use history refers to whether the user has used an integral system (such as exchanging a discount, obtaining a priority recommendation, and the like) of the navigation software. The extraction layer in the behavior prediction model is responsible for extracting the above features from the account dataset, and taking the features as input data for subsequent prediction. The extraction layer can be implemented by using a machine learning algorithm (such as a feature selection algorithm) or a convolution layer / full connection layer in deep learning.

[0046] For example, it is assumed that the account dataset of the user includes the following information: the historical compliance rate is 80%; the response time delay is 30 seconds on average; the path use preference is inclined to select an expressway and avoid a congested road segment; and the integral use history is that the priority recommendation service is used by using the integral exchange in the past one month. The extraction layer of the behavior prediction model extracts the information as features for subsequent prediction.

[0047] Step S420, after extracting the construction data into construction features, activate the time series prediction layer to perform navigation guidance compliance prediction based on construction features and data features, and establish prediction results. Specifically, the extraction layer of the behavior prediction model extracts key features from the construction data, such as construction time (specific time period of construction), number of occupied lanes (number of lanes occupied by construction), and predicted congestion level (congestion probability predicted according to construction range and historical data). The time series prediction layer is responsible for combining construction features and user behavior features (data features) to predict user compliance behavior to navigation guidance suggestions. The time series prediction layer uses time series analysis methods (such as LSTM, GRU) or deep learning models (such as Transformer) to process time series data. The prediction results include whether the user will choose to detour, the time to respond to navigation suggestions, etc. This implementation extracts user behavior features and construction features, and the behavior prediction model can more accurately predict user compliance behavior to navigation suggestions. This accurate prediction can reduce congestion caused by users not following navigation suggestions. According to the prediction results, the navigation system can dynamically adjust the navigation suggestions, such as pushing detour routes in advance, reminding users multiple times, etc., thereby improving the effect of navigation guidance.

[0048] Step S500, obtain the real-time traffic state of the target area, establish the touch time node according to the navigation touch result, form the touch data stream, and perform traffic time series fitting update based on the touch data stream, the prediction result, and the real-time traffic state.

[0049] Specifically, the traffic state of the target area is monitored in real time by a sensor network (such as traffic flow sensors, cameras, GPS data, etc.), including vehicle speed, traffic flow, congestion level, etc. For example, in the road construction area and its surroundings, high-definition cameras and microwave radar detectors are used to obtain real-time traffic speed and traffic flow data. When vehicles use navigation systems to reach road construction areas, the time points of vehicle arrival are recorded. These time nodes are part of the touch data stream. For example, the navigation system records that user X arrived at the road construction area at 9:05 am and user Y arrived at the road construction area at 9:10 am. All vehicle touch time nodes are aggregated to form a time series data stream. These data streams are used to analyze the frequency and time distribution of vehicles arriving at road construction areas. For example, the touch data stream shows that during 9:00-9:30 am, an average of 5 vehicles arrive at the construction area per minute. Combining the touch data stream, the prediction result (navigation guidance compliance prediction), and the real-time traffic state, use time series analysis methods (such as ARIMA model, LSTM, etc.) to fit and update the traffic state. Through fitting and updating, dynamically adjust the traffic guidance strategy to ensure that the guidance measures can adapt to real-time traffic conditions.

[0050] In one possible implementation, the traffic flow timing fitting update based on the traffic data stream, the prediction result, and the real-time traffic flow state, step S500 further includes a step S510 of predicting the passing proportion of non-navigation vehicles to establish a first timing fitting compensation with the passing proportion prediction result. Specifically, passing data of vehicles is collected through a sensor network (such as a traffic flow sensor or a camera). A machine learning algorithm (such as clustering analysis) is used to distinguish navigation vehicles and non-navigation vehicles. For example, the driving path of a navigation vehicle is generally consistent with navigation suggestions, while the driving path of a non-navigation vehicle is more random. Using historical data and real-time data, the passing proportion of non-navigation vehicles in the target area is predicted. For example, by analyzing the proportion of non-navigation vehicles to navigation vehicles in the past week, combined with the current traffic conditions, the proportion of non-navigation vehicles in the current period is predicted. According to the passing proportion prediction result, the traffic flow timing fitting result is compensated. If the proportion of non-navigation vehicles is high, it will have an additional impact on traffic flow, which needs to be considered in the fitting model.

[0051] Step S520, according to the construction data, the influence of non-vehicle passing is analyzed, and the influence prediction of non-vehicle passing on vehicle passing road is generated according to the influence analysis result to establish a second timing fitting compensation. Specifically, the construction data is analyzed to identify the influence of construction on non-vehicle passing (such as pedestrians, bicycles, construction vehicles, etc.). For example, construction may cause the sidewalk to narrow, and pedestrians and bicycles may need to occupy part of the lane. The influence of non-vehicle passing on vehicle passing road is simulated using traffic simulation software (such as VISSIM). According to the construction data and the simulation result, the influence degree of non-vehicle passing on vehicle passing road is predicted. For example, the probability and time of pedestrians and bicycles occupying the lane are predicted. According to the influence prediction result of non-vehicle passing, the traffic flow timing fitting result is compensated. If the influence of non-vehicle passing on vehicle passing road is large, it needs to be adjusted in the fitting model.

[0052] Step S530, according to the first timing fitting compensation, the second timing fitting compensation, the traffic flow timing fitting result is compensated and managed. Specifically, the first timing fitting compensation (the influence of non-navigation vehicles) and the second timing fitting compensation (the influence of non-vehicle passing) are combined to comprehensively compensate the traffic flow timing fitting result. Using weighted average or other statistical methods, the two compensation factors are integrated into the traffic flow timing fitting model. According to the compensated traffic flow timing fitting result, the traffic relief strategy is dynamically adjusted. For example, if the influence of non-navigation vehicles and non-vehicle passing is large, new navigation suggestions may need to be issued. This implementation can more comprehensively reflect the actual traffic conditions by introducing the influence analysis of non-navigation vehicles and non-vehicle passing and compensating the traffic flow timing fitting result, and dynamically adjusting the traffic relief strategy.

[0053] Step S600, according to the target traffic flow state and traffic flow time series fitting result to establish deviation identification result and generate feedback incentive, according to the feedback incentive to correct navigation guidance, execute traffic guidance management.

[0054] Specifically, by using machine learning or statistical analysis method (such as anomaly detection algorithm), compare the target traffic flow state and traffic flow time series fitting result, identify whether the actual state of traffic flow deviates from the expectation. If there is a significant difference between the traffic flow time series fitting result and the target traffic flow state, it is considered that deviation occurs. For example, the target traffic flow state result shows that the speed of the road construction area should be 30 kilometers per hour during 9:00 to 9:30 in the morning, but the speed in the traffic flow time series fitting result is only 25 kilometers per hour, which means that the traffic flow state deviates from the expectation. According to the deviation identification result, generate feedback incentive signal for adjusting navigation guidance strategy. Feedback incentive can include adjusting navigation suggestion, issuing new traffic guidance information, etc. For example, due to the deviation of traffic flow state from the expectation, the system generates feedback incentive signal to suggest that the navigation system pushes the user to a more optimal detour route. According to the feedback incentive signal, dynamically adjust the navigation guidance strategy, including updating the navigation path, issuing new traffic guidance information, etc. Through the intelligent transportation system platform, real-time monitoring of traffic flow state, and dynamic adjustment of guidance strategy according to feedback incentive signal. If necessary, traffic management personnel can manually intervene to optimize the guidance scheme.

[0055] In one possible implementation, the step S600 of establishing deviation identification result and generating feedback incentive according to the target traffic flow state and traffic flow time series fitting result further includes step S610 of creating target correction task using the deviation identification result, the target correction task being a guiding correction task for the user with abnormal prediction behavior in the prediction result. Specifically, through traffic flow time series fitting update, identify the deviation between actual traffic flow state and prediction result, determine which user's navigation behavior deviates from the prediction result, for example, the user does not detour according to the navigation suggestion, or the response time is too long. According to the deviation identification result, create target correction task to guide the navigation behavior of these users to return to the expected guidance strategy. Determine the number of users that need to be corrected and the specific correction target, for example, assume that through deviation identification, it is found that 20% of the users do not detour according to the navigation suggestion, causing the road construction area to be congested. Create target correction task, the target is to guide 10% of these deviated users to choose the recommended detour route to alleviate congestion.

[0056] Step S620, in order to achieve the target correction task, feedback incentive optimization under the constraint of incentive cost balance is performed, the feedback incentive including navigation integral incentive, carbon footprint incentive, route priority incentive, visual social exposure incentive, group incentive. Specifically, the cost budget of the incentive measures is determined, for example, the cost of navigation integral incentive, the reward amount of carbon footprint incentive, etc. The cost-benefit of different incentive measures is evaluated to ensure that the incentive measures achieve the target correction task under the condition of controllable cost. An optimization algorithm (such as linear programming, genetic algorithm) is used to find the optimal incentive combination under the constraint of incentive cost balance. Available incentive measures include: navigation integral incentive, carbon footprint incentive, route priority incentive, visual social exposure incentive, group incentive. Among them, the navigation integral incentive refers to that if the user selects the recommended route, points can be obtained, and the points can be used to exchange preferential treatment or services. The carbon footprint incentive refers to that if the user selects an environmentally friendly route (such as detouring to avoid congestion), a carbon footprint reward can be obtained, which can be used for environmental protection activities or exchanged for rewards. The route priority incentive refers to that if the user selects the recommended route, the user can obtain priority access, for example, access to a fast lane. The visual social exposure incentive refers to that if the user selects the recommended route, the user can obtain exposure on a social platform, thereby improving the user's social recognition. The group incentive refers to encouraging the user group to select the recommended route through a group reward mechanism, for example, a certain percentage of users in the group who select the recommended route can obtain additional rewards. The optimization goal is to maximize the achievement rate of the target correction task while minimizing the incentive cost.

[0057] For example, assuming that the target correction task is to guide 10% of the deviated users to select the recommended detour route. The incentive cost budget is 1000 points (assuming that points are virtual currency of navigation software). Through the optimization algorithm, the system decides to use the following incentive combination: navigation integral incentive: reward 50 points to the user who selects the recommended route; carbon footprint incentive: reward 30 points to the user who selects the environmentally friendly route; visual social exposure incentive: display the environmentally friendly behavior of the user who selects the recommended route on the social platform. This incentive combination is expected to guide 10% of the deviated users to select the recommended route while the incentive cost is controlled within the budget.

[0058] At step S630, the feedback incentive is generated based on the feedback incentive optimization result. Specifically, the specific incentive measures are generated according to the feedback incentive optimization result. The incentive measures are pushed to the user through the navigation software, for example, the information of the integral reward, the environmental protection reward, and the like is displayed on the navigation interface. The user selects the recommended route according to the incentive measures during the navigation process. The system monitors the navigation behavior of the user in real time, and confirms whether the user responds to the incentive measures. The effect of the incentive measures is evaluated, for example, how many users actually select the recommended route. According to the evaluation result, the incentive measures are dynamically adjusted to improve the incentive effect. For example, if it is found that the incentive effect is poor, the system can dynamically adjust the incentive measures, for example, increase the integral reward or introduce new incentive mechanisms. This implementation manner can effectively guide the user to select the recommended route and improve the response rate of the user to the navigation suggestion by creating a target correction task, performing feedback incentive optimization under the constraint of incentive cost balance, and generating specific feedback incentive measures.

[0059] In a possible implementation manner, the feedback incentive is used to correct the navigation guidance, and traffic guidance management is performed, and step S600 further includes step S640. When any navigation vehicle enters the road construction area, real-time congestion state identification of the road construction area is performed, and a congestion penalty coefficient is generated. Specifically, the traffic state of the road construction area is monitored in real time by using a sensor network (such as a traffic flow sensor, a camera, GPS data, and the like), including the vehicle speed, the traffic flow, the congestion degree, and the like. The real-time data is analyzed by using a machine learning algorithm (such as clustering analysis, anomaly detection) or a traffic simulation software (such as VISSIM) to identify the current congestion state. According to the severity of the congestion state, the congestion penalty coefficient is generated. For example, the higher the congestion degree, the larger the penalty coefficient. The penalty coefficient can be a numerical value, which is used to quantify the influence of the current congestion on the vehicle passing.

[0060] For example, it is assumed that the real-time monitoring data of the construction area shows that the current vehicle speed is 15 kilometers per hour, the traffic flow is 1200 vehicles per hour, and the congestion degree is high. Through the congestion state identification algorithm, the congestion penalty coefficient is generated as 1.5 (indicating that the current congestion degree is high, and the influence on the passing is large).

[0061] At step S650, the additional path cost calculation of the navigation vehicle under the corrected navigation guidance is performed, and a cost compensation coefficient is generated. Specifically, the additional path cost is calculated according to the actual driving path of the navigation vehicle and the corrected navigation guidance suggestion. For example, if the vehicle selects a detour route, the additional time and distance of the detour route compared with the original route are calculated. According to the additional path cost, the cost compensation coefficient is generated. For example, if the additional path cost is high, the compensation coefficient is also high, which is used to encourage the user to select the recommended route.

[0062] For example, assume that the navigation vehicle chooses a detour route, which increases the travel time by 10 minutes and the distance by 5 kilometers compared with the original route. Through the additional path cost calculation, a cost compensation coefficient of 1.2 is generated (indicating that the additional cost of the detour route is high and needs to be compensated to a certain extent).

[0063] In step S660, the green travel credit penalty management of the navigation vehicle is performed according to the congestion penalty coefficient and the cost compensation coefficient. Specifically, the green travel credit of the navigation vehicle is managed according to the congestion penalty coefficient and the cost compensation coefficient. If the vehicle chooses a detour route in a congestion situation, a certain credit reward is given; if the vehicle does not detour as recommended by the navigation, the corresponding credit score is deducted. The credit management measures can include: if the user chooses the recommended route, green points can be obtained, which can be used to exchange environmental rewards or preferential treatment. If the user's credit score is too low, the user may not be able to see the navigation recommendations for some congestion sections in the future, or the display is in an impassable state. According to the credit score of the user, the city pass recommendation label is given, such as "green travel user". Users with high credit scores can enjoy higher parking coupon acquisition probabilities and the like.

[0064] For example, assume that the navigation vehicle chooses a detour route in a congestion situation, and the congestion penalty coefficient is 1.5 and the cost compensation coefficient is 1.2. According to the two coefficients, the system gives the user a certain green point reward (for example, 50 points). If the user's credit score is high, the system will give the user a "green travel user" label and increase the probability of obtaining a parking coupon. This implementation mode can effectively encourage users to choose recommended routes and reduce congestion in construction areas through real-time congestion state identification, additional path cost calculation, and green travel credit management.

[0065] In a possible implementation mode, after the traffic diversion management is performed, the method further includes: monitoring the pass of the road construction area; when the pass monitoring result meets an abnormal threshold, triggering a temporary closure instruction; and changing the road construction area to a temporary closure state according to the temporary closure instruction.

[0066] Specifically, the traffic state of the road construction area is continuously monitored using sensor networks (such as traffic flow sensors, cameras, GPS data, etc.), including vehicle speed, traffic volume, congestion level, etc. The monitoring data is analyzed in real time by an intelligent transportation system (ITS) platform to identify whether there is an abnormal situation. For example, the intelligent transportation system platform analyzes the monitoring data once a minute to determine whether the traffic state is normal. An abnormal threshold is set, for example, the vehicle speed is lower than 10 kilometers / hour and the duration is more than 10 minutes, or the traffic volume exceeds a certain upper limit. When the monitoring data reaches or exceeds the abnormal threshold, the system automatically triggers a temporary closure instruction. According to the temporary closure instruction, temporary closure information is published through variable message boards, navigation software, broadcasts, etc. to remind drivers that the construction area is closed and suggests detouring. By allowing vehicles in the road construction area to exit but prohibiting external vehicles from entering, the smoothness is quickly restored. This implementation mode can quickly identify and alleviate the congestion situation in the road construction area through real-time traffic monitoring, abnormal threshold triggering mechanism and temporary closure measures.

[0067] The embodiment of the present application collects traffic data of the target area, analyzes and constructs traffic characteristics of the target area, obtains road construction data, combines the traffic characteristics of the target area, performs construction influence fitting analysis, establishes a three-level interference path space structure model, configures a target traffic state based on the three-level interference path space structure model, collects navigation account subject data when the navigation reaches the road construction area, constructs an account data set, uses a behavior prediction model, combines the account data set and the construction data, performs navigation guidance prediction, generates a prediction result, obtains a target area traffic state in real time, generates a reach time node combined with the navigation reach result, forms a reach data flow, performs fitting update of traffic timing based on the reach data flow, the prediction result and the real-time traffic state, compares the target traffic state with the fitting result of the traffic timing, identifies the deviation and generates a feedback incentive, corrects the navigation guidance strategy according to the feedback incentive, and implements traffic guidance management technical means, solves the technical problem that the traffic guidance control of the existing road construction area has poor guidance effect, and achieves the technical effect of improving the traffic guidance efficiency and accuracy.

[0068] In the foregoing, reference is made to Figure 1 The traffic guidance control method for the road construction area according to the embodiment of the present application is described in detail. Next, the traffic guidance control system for the road construction area according to the embodiment of the present application will be described with reference to Figure 2 The traffic guidance control system for the road construction area according to the embodiment of the present application is described in detail. Next, the traffic guidance control system for the road construction area according to the embodiment of the present application will be described with reference to

[0069] The road construction area traffic diversion control system according to the embodiment of the present application is used to solve the technical problem of poor traffic diversion effect of the existing road construction area traffic diversion control, and achieve the technical effect of improving the traffic diversion efficiency and accuracy. The road construction area traffic diversion control system comprises: a target area traffic feature establishing module 10, a construction influence fitting module 20, an account data set establishing module 30, a navigation diversion prediction module 40, a vehicle flow time sequence fitting updating module 50, and a navigation diversion correction module 60.

[0070] The target area traffic feature establishing module 10 is used to perform traffic data collection of a target area, and establish target area traffic features based on the traffic data collection results. The construction influence fitting module 20 is used to obtain construction data of a road construction area, and perform construction influence fitting based on the construction data and the target area traffic features, and establish a three-level interference path space structure. The account data set establishing module 30 is used to configure target vehicle flow states based on the three-level interference path space structure, and perform data collection of navigation account subjects after any navigation reaches the road construction area, and establish account data sets. The navigation diversion prediction module 40 is used to perform navigation diversion prediction based on the account data sets and the construction data by using a behavior prediction model, and establish prediction results. The vehicle flow time sequence fitting updating module 50 is used to obtain real-time vehicle flow states of the target area, establish reach time nodes based on navigation reach results, form reach data streams, and perform vehicle flow time sequence fitting updating based on the reach data streams, the prediction results, and the real-time vehicle flow states. The navigation diversion correction module 60 is used to establish deviation identification results based on the target vehicle flow states and the vehicle flow time sequence fitting results, and generate feedback incentives, correct the navigation diversion based on the feedback incentives, and perform traffic diversion management.

[0071] In the following, the specific configuration of the navigation diversion correction module 60 will be described in detail. As described above, the navigation diversion correction module 60 can further comprise: a target correction task creating unit for creating target correction tasks by using the deviation identification results, the target correction tasks being guidance correction tasks for users with abnormal prediction behaviors in the prediction results; a feedback incentive optimization unit for performing feedback incentive optimization under the constraint of incentive cost balance to achieve the target correction tasks, the feedback incentives including navigation integral incentives, carbon footprint incentives, route priority incentives, visual social exposure incentives, and group incentives; and a feedback incentive generating unit for generating feedback incentives by using the feedback incentive optimization results.

[0072] The navigation guidance modification module 60 can further include a real-time congestion state identification unit for identifying a real-time congestion state of the road construction area when any navigation vehicle enters the road construction area, and generating a congestion penalty coefficient; a cost calculation unit for calculating an additional path cost of the navigation vehicle under the modified navigation guidance, and generating a cost compensation coefficient; and a green travel credit penalty management unit for managing a green travel credit penalty of the navigation vehicle according to the congestion penalty coefficient and the cost compensation coefficient.

[0073] The account data set establishment module 30 can further include a disturbance path area positioning unit for positioning a first disturbance path area, a second disturbance path area, and a third disturbance path area according to the three-level disturbance path space structure, the first disturbance path area being a direct construction influence area, the second disturbance path area being a nearby guidance area with an association degree satisfying an association threshold, and the third disturbance path area being a remote guidance area with an association degree not satisfying the association threshold; a path topology structure establishment unit for establishing a path topology structure based on the first disturbance path area, the second disturbance path area, and the third disturbance path area; and a traffic balance optimization unit for taking the target area traffic characteristics as fitting data, and performing traffic balance optimization of the three-level disturbance path based on the path topology structure to establish the target traffic state.

[0074] The target area traffic characteristics establishment module 10 can further include a backtracking time window creation unit for taking a current time node as a time zero point, and creating a first backtracking time window and a second backtracking time window, the first backtracking time window being a weekly backtracking window, and the second backtracking time window being a monthly backtracking window; and a traffic characteristics verification and identification unit for assigning trust factors to the first backtracking time window and the second backtracking time window, and performing traffic characteristics verification and identification of the traffic data collection result in the first backtracking time window and the second backtracking time window to establish the target area traffic characteristics.

[0075] Below, the specific configuration of the navigation guidance prediction module 40 will be described in detail. As described above, the navigation guidance prediction based on the account data set and the construction data is performed by using the behavior prediction model to establish the prediction result, and the navigation guidance prediction module 40 can further include: a data feature extraction unit configured to extract data features of the account data set by using an extraction layer of the behavior prediction model, the data features including historical compliance rate, response time delay, path use preference, and integral use history; and a navigation guidance compliance prediction unit configured to, after extracting the construction data as construction features, activate a time sequence prediction layer to perform navigation guidance compliance prediction based on the construction features and the data features, and establish a prediction result.

[0076] Below, the specific configuration of the traffic flow time sequence fitting update module 50 will be described in detail. As described above, the traffic flow time sequence fitting update is performed based on the touch data flow, the prediction result, and the real-time traffic flow state, and the traffic flow time sequence fitting update module 50 can further include: a first time sequence fitting compensation establishment unit configured to predict the passing proportion of non-navigation vehicles to establish a first time sequence fitting compensation with the passing proportion prediction result; a second time sequence fitting compensation establishment unit configured to analyze the influence of non-vehicle passing according to the construction data to generate an influence prediction of non-vehicles on vehicle passing roads with the influence analysis result, and establish a second time sequence fitting compensation; and a compensation management unit configured to compensate and manage the traffic flow time sequence fitting result according to the first time sequence fitting compensation and the second time sequence fitting compensation.

[0077] After the traffic guidance management is performed, the system can further include: a passing monitoring module configured to monitor the passing of the road construction area; a temporary closure instruction triggering module configured to trigger a temporary closure instruction when the passing monitoring result meets an abnormal threshold; and a state changing module configured to change the road construction area to a temporary closure state according to the temporary closure instruction.

[0078] The traffic guidance control system for the road construction area provided in the embodiments of the present application can perform the traffic guidance control method for the road construction area provided in any of the embodiments of the present application, and has the function modules and beneficial effects corresponding to the execution method.

[0079] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and the various units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0080] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device. Figure 3is a structural schematic diagram of an electronic device provided by an embodiment of the present application, and shows a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present application. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the function and use range of the embodiment of the present application. The electronic device is in the form of a general computing device, and its components can include but are not limited to an input device 301, a processor 302, a memory 303 and an output device 304. The processor 302 can be one or more; the memory 303 can include a computer readable medium and at least one program product, which has a set of (at least one) program modules configured to perform the functions of the embodiments of the present application.

[0081] The memory 303 shown in the embodiment of the present application can adopt any combination of one or more computer readable media; the computer readable storage medium can be but is not limited to an infrared ray, a semiconductor system, a device or a component, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the traffic diversion control method for road construction area in the embodiment of the present application. The processor 302 performs various function applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 303, that is, implements the above-mentioned traffic diversion control method for road construction area.

[0082] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application. In some cases, the actions or steps described in the present application can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A traffic guidance control method for a road construction area, characterized by, The method comprises: Performing access data collection of the target area to establish access characteristics of the target area based on the access data collection results; Obtaining construction data of the road construction area, fitting construction influence based on the construction data and the access characteristics of the target area, and establishing a three-level interference path space structure; Configuring a target traffic flow state based on the three-level interference path space structure, and performing data collection of a navigation account subject after any navigation reaches the road construction area, establishing an account data set, the account data set including user historical navigation behavior, real-time navigation behavior, and user feedback; Using a behavior prediction model to predict navigation diversion compliance probability based on the account data set and the construction data, and establishing a navigation diversion prediction result based on the compliance probability; Obtaining a real-time traffic flow state of the target area, establishing a reach time node based on a navigation reach result, forming a reach data stream, and fitting and updating a traffic flow time sequence based on the reach data stream, the prediction result, and the real-time traffic flow state; Establishing a deviation identification result based on the target traffic flow state and the traffic flow time sequence fitting result, generating a feedback incentive, correcting the navigation diversion based on the feedback incentive, and performing traffic diversion management.

2. The traffic diversion control method for a road work zone according to Claim 1, characterized by, The method comprises: Creating a target correction task based on the deviation identification result, the target correction task being a guide correction task for an abnormally predicted behavior user in the prediction result; Performing feedback incentive optimization under the constraint of incentive cost balance to achieve the target correction task, the feedback incentive including navigation integral incentive, carbon footprint incentive, route priority incentive, visual social exposure incentive, and group incentive; Generating the feedback incentive based on the feedback incentive optimization result.

3. The traffic guidance control method for a road work zone according to Claim 1, wherein, The method comprises: When any navigation vehicle enters the road construction area, performing real-time congestion state identification of the road construction area to generate a congestion penalty coefficient; Performing additional path cost calculation of the navigation vehicle under the corrected navigation diversion to generate a cost compensation coefficient; Performing green travel credit penalty management of the navigation vehicle based on the congestion penalty coefficient and the cost compensation coefficient.

4. The traffic guidance control method for a road work zone according to Claim 1, characterized by, The method comprises: Positioning a first-level interference path area, a second-level interference path area, and a third-level interference path area based on the three-level interference path space structure, the first-level interference path area being a direct construction influence area, the second-level interference path area being a nearby diversion area with an association degree satisfying an association threshold, and the third-level interference path area being a remote diversion area with an association degree not satisfying the association threshold; Establishing a path topology structure based on the first-level interference path area, the second-level interference path area, and the third-level interference path area; Using the access characteristics of the target area as fitting data, performing three-level interference path access balance optimization based on the path topology structure to establish the target traffic flow state.

5. The traffic guidance control method for a road work zone according to Claim 1, wherein, The method comprises: Taking the current time node as a time zero point, a first backtracking time window and a second backtracking time window are created, the first backtracking time window being a week backtracking window and the second backtracking time window being a month backtracking window; After assigning trust factors to the first backtracking time window and the second backtracking time window, a traffic feature verification and identification of a traffic data collection result is performed in the first backtracking time window and the second backtracking time window to establish a target area traffic feature.

6. The traffic guidance control method for a road work zone according to Claim 1, wherein, The navigation guidance compliance probability prediction based on the account data set and the construction data by using the behavior prediction model, and the navigation guidance prediction result based on the compliance probability, include: The data features of the account data set are extracted by using the extraction layer of the behavior prediction model, and the data features include historical compliance rate, response time delay, path use preference, and integral use history; After the construction data is extracted as construction features, a time sequence prediction layer is activated to perform navigation guidance compliance prediction based on the construction features and the data features, and a prediction result is established.

7. The traffic guidance control method for a road work zone according to Claim 1, wherein, The vehicle flow time sequence fitting update based on the touch data flow, the prediction result, and the real-time vehicle flow state, includes: A non-navigation vehicle traffic proportion prediction is performed, and a first time sequence fitting compensation is established based on a traffic proportion prediction result; An influence analysis of non-vehicle traffic is performed according to the construction data, and an influence prediction of non-vehicle on vehicle traffic roads is generated based on an influence analysis result, and a second time sequence fitting compensation is established; The vehicle flow time sequence fitting result is compensated and managed according to the first time sequence fitting compensation and the second time sequence fitting compensation.

8. The traffic guidance control method for a road work zone according to Claim 1, wherein, After the traffic guidance management is performed, it includes: Traffic monitoring is performed on the road construction area; When the traffic monitoring result meets the abnormal threshold, a temporary closure instruction is triggered; According to the temporary closure instruction, the road construction area is changed to a temporary closed state.

9. A traffic management control system for a road works area characterised in that, The system is used to implement the traffic guidance control method of the road construction area according to any one of claims 1-8, and the system includes: A target area traffic feature establishment module is configured to perform traffic data collection of a target area, and establish a target area traffic feature based on a traffic data collection result; A construction influence fitting module is configured to obtain construction data of a road construction area, and perform construction influence fitting based on the construction data and the target area traffic feature, and establish a three-level interference path space structure; An account data set establishment module is configured to configure a target vehicle flow state based on the three-level interference path space structure, and perform data collection of a navigation account subject after any navigation touch reaches the road construction area, and establish an account data set, which includes user historical navigation behavior, real-time navigation behavior, and user feedback; A navigation guidance prediction module is configured to perform navigation guidance compliance probability prediction based on the account data set and the construction data by using a behavior prediction model, and establish a navigation guidance prediction result based on the compliance probability; A vehicle flow time sequence fitting update module is configured to obtain a real-time vehicle flow state of a target area, establish a touch time node based on a navigation touch result, form a touch data flow, and perform vehicle flow time sequence fitting update based on the touch data flow, the prediction result, and the real-time vehicle flow state. The navigation guidance correction module is configured to establish a deviation identification result and generate a feedback incentive according to the target traffic flow state and the traffic flow time sequence fitting result, correct the navigation guidance according to the feedback incentive, and perform traffic guidance management.

10. An electronic device, comprising: The electronic device comprises: a memory configured to store executable instructions; a processor configured to execute the executable instructions stored in the memory to implement the traffic guidance control method for the road construction area according to any one of claims 1 to 8.

Images