Highway vehicle speed control method and system based on control unit

Abstract

The invention provides a highway vehicle speed management and control method and system based on a management and control unit, and the method comprises the steps: obtaining a to-be-managed and controlled task of a target management and control unit of a target highway section, and aiming at a to-be-managed and controlled vehicle speed knowledge point of a to-be-managed and controlled vehicle, carrying out the management and control of the to-be-managed and controlled task under the condition that a current tracking node has vehicle speed data; and in combination with the current tracking node, the termination node of the first tracking time period and the tracking time period duration parameter, determining a vehicle speed distribution characteristic parameter of the to-be-controlled vehicle speed knowledge point of the to-be-controlled vehicle in the second tracking time period. And further, a target vehicle speed prediction scheme is determined based on the vehicle speed distribution characteristic parameters, and vehicle speed characteristic information of to-be-controlled vehicle speed knowledge points in the second tracking time period of the to-be-controlled vehicle is determined according to the target vehicle speed prediction scheme. The method can effectively predict and control the speed of the vehicle on the expressway, improves the accuracy and real-time performance of vehicle speed management, facilitates the optimization of the traffic flow of the expressway, and improves the traffic efficiency and safety of the road.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and more specifically, to a method and system for controlling the speed of highway vehicles based on a control unit. Background Art

[0002] With the rapid development of highways and the continuous increase in the number of vehicles, highway traffic management is facing increasing challenges. Among them, the control of vehicle speed is an important link in highway traffic management and is of great significance for ensuring road traffic efficiency and reducing traffic accidents.

[0003] Traditional methods for controlling the speed of highway vehicles often rely on manual monitoring and fixed speed limit measures, and these methods have many deficiencies. On the one hand, manual monitoring requires a large amount of human and material resources, and the monitoring range is limited, making it difficult to achieve comprehensive and real-time speed control. On the other hand, fixed speed limit measures lack flexibility and pertinence and cannot be adjusted in a timely manner according to the actual road conditions and vehicle driving conditions. Summary of the Invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present invention, embodiments of the present invention provide a method for controlling the speed of highway vehicles based on a control unit, the method comprising:

[0005] Obtaining a to-be-controlled task of a target control unit for a target highway section, the to-be-controlled task including a to-be-controlled vehicle and a to-be-controlled vehicle speed knowledge point;

[0006] If vehicle speed data of the to-be-controlled vehicle speed knowledge point exists at a current tracking node, then based on the current tracking node, an end node of a first tracking period, and a tracking period duration parameter, determining a vehicle speed distribution characteristic parameter of the to-be-controlled vehicle speed knowledge point within a second tracking period corresponding to the current tracking node, the first tracking period being a previous tracking period of the second tracking period;

[0007] Determining a target vehicle speed prediction scheme based on the vehicle speed distribution characteristic parameter of the to-be-controlled vehicle speed knowledge point within the second tracking period;

[0008] Determining vehicle speed characteristic information of the to-be-controlled vehicle speed knowledge point within the second tracking period based on the target vehicle speed prediction scheme.

[0009] In another aspect, an embodiment of the present invention further provides a highway vehicle speed control system based on a control unit, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor. The machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0010] Based on the above aspects, the embodiment of the present application obtains the to-be-controlled tasks of the target control unit of the target highway section, and for the to-be-controlled vehicle speed knowledge points of the to-be-controlled vehicle, when there is vehicle speed data at the current tracking node, combines the current tracking node, the termination node of the first tracking period, and the tracking period duration parameter to determine the vehicle speed distribution characteristic parameters of the to-be-controlled vehicle speed knowledge points within the second tracking period. Further, based on the vehicle speed distribution characteristic parameters, a target vehicle speed prediction scheme is determined, and according to the target vehicle speed prediction scheme, the vehicle speed characteristic information of the to-be-controlled vehicle speed knowledge points within the second tracking period is determined. This method can effectively predict and control the speed of highway vehicles, improve the accuracy and real-time performance of vehicle speed management, contribute to optimizing the traffic flow of highways, and enhancing road traffic efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic flowchart of the execution process of the highway vehicle speed control method based on the control unit provided by the embodiment of the present invention.

[0012] Figure 2 is a schematic diagram of the hardware architecture of the highway vehicle speed control system based on the control unit provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] The present invention will be specifically described below in conjunction with the accompanying drawings of the specification. Figure 1 is a schematic flowchart of the highway vehicle speed control method based on the control unit provided by an embodiment of the present invention. The highway vehicle speed control method based on the control unit will be introduced in detail below.

[0014] Step S110: Obtain the to-be-controlled tasks of the target control unit of the target highway section, where the to-be-controlled tasks include to-be-controlled vehicles and to-be-controlled vehicle speed knowledge points.

[0015] In this embodiment, consider such a scenario. On a busy highway section, it is divided into multiple control units for convenient traffic management. The target control unit is a specific control unit among them, for example, the section between a certain mileage marker K1 and K2 on the highway. The traffic management department has formulated a series of control tasks to ensure the traffic safety and efficient passage of this section.

[0016] Suppose there is a large transport truck identified as a vehicle to be controlled. Due to factors such as its large body and heavy load, controlling the vehicle speed is crucial. The knowledge points of the vehicle speed to be controlled may involve multiple aspects, such as the safe speed range under different road conditions, the speed requirements for specific road sections (such as curves, uphill sections, etc.), and the speed matching when maintaining a safe distance from the vehicle in front and behind. For example, within the target control unit, there is a continuous curve. According to the road design and traffic flow analysis, the knowledge point of the safe vehicle speed at the curve stipulates that the vehicle speed should not exceed 80 kilometers per hour. This vehicle speed requirement is part of the knowledge points of the vehicle speed to be controlled. After the management system identifies that this truck enters the target control unit through the monitoring device, it obtains a control task to be executed that includes this truck and the above-mentioned vehicle speed knowledge points.

[0017] For another example, in this target control unit, there are also some special construction areas. According to the construction safety regulations, within a certain range close to the construction area, the vehicle speed needs to be reduced to below 60 kilometers per hour. When it is detected that a vehicle is approaching the construction area, this knowledge of the vehicle speed limit in the construction area becomes a knowledge point of the vehicle speed to be controlled. At the same time, the vehicle approaching the construction area is identified as a vehicle to be controlled, and thus a control task to be executed that includes the vehicle and the vehicle speed knowledge point is obtained.

[0018] Step S120, if there is vehicle speed data of the knowledge points of the vehicle speed to be controlled for the vehicle to be controlled at the current tracking node, then based on the current tracking node, the termination node of the first tracking period, and the tracking period duration parameter, determine the vehicle speed distribution characteristic parameter of the knowledge points of the vehicle speed to be controlled for the vehicle to be controlled within the second tracking period corresponding to the current tracking node. The first tracking period is the previous tracking period of the second tracking period.

[0019] Suppose in the monitoring system of a target highway section, a tracking node is set at regular intervals of distance or time. Taking the large transport truck mentioned above as an example, at the current tracking node (assumed to be node N), the vehicle speed data of the truck regarding a certain knowledge point of the vehicle speed to be controlled (such as the vehicle speed limit at the curve) is obtained through a speed measurement device, and the vehicle speed is 75 kilometers per hour.

[0020] First, determine the termination node of the first tracking period. Suppose the first tracking period starts from a previous point in time or distance point and ends at node M. The tracking period duration parameter is set to one tracking period every 10 minutes.

[0021] Based on the current tracking node N and the termination node M of the first tracking period, determine the interval of nodes without vehicle speed data. Suppose there are 3 nodes between node M and node N where the vehicle speed data of the truck regarding this vehicle speed knowledge point has not been obtained. These 3 nodes form the interval of nodes without vehicle speed data.

[0022] Determine the speed distribution characteristic limit value based on the tracking period duration parameter (10 minutes) and a predefined determination strategy. For example, the predefined determination strategy is set according to historical data and traffic engineering theory. When the tracking period is 10 minutes, the threshold for the number of nodes in the speed distribution characteristic limit value is 5, the uniformity standard is that the interval between adjacent nodes without speed data does not exceed 2 nodes, and the ratio threshold is that the proportion of the interval of nodes without speed data in the entire second tracking period does not exceed 30%.

[0023] Determine the number of nodes in the interval of nodes without speed data, the uniformity characteristic of the node distribution, and the proportion range of the interval of nodes without speed data in the entire second tracking period, and generate the first analysis result. In this example, the number of nodes is 3, the node distribution is relatively uniform (the interval between adjacent nodes without speed data is 1 node each). Assuming that the second tracking period contains a total of 10 nodes from node M to node N, then the proportion of the interval of nodes without speed data is 30%.

[0024] Preliminarily classify the first analysis result according to the speed distribution characteristic limit value. Since the number of nodes without speed data, which is 3, is less than the node number threshold of 5, the preliminary classification result is marked as the first category; the node distribution uniformity meets the uniformity standard and is marked as the second category; the proportion of the interval of nodes without speed data, which is 30%, is equal to the ratio threshold of 30%, and it does not meet the conditions of the third category for the time being.

[0025] Conduct an integrated judgment on the preliminary classification result. Since the preliminary classification result includes the first category and the second category, perform the second integrated judgment logic. Assume that according to the specific characteristic combination of the first category and the second category results, the fourth integrated judgment result is output and marked as category D.

[0026] Construct a speed distribution characteristic parameter framework based on the integrated judgment result of category D, which covers the estimated factor of speed data change corresponding to the characteristic combination related to the first category and the second category, and the estimated factor of the interaction between the nodes without speed data and the nodes with speed data under this characteristic combination. For example, the estimated factor of speed data change may be set according to historical data and vehicle dynamics models. For each missing node of speed data, the subsequent speed data may have a fluctuation range of 5 km / h; the estimated factor of the interaction between the nodes without speed data and the nodes with speed data under this characteristic combination is set such that the speed data after the node without speed data will approach the speed value of the adjacent node with speed data with a certain probability (such as 30%).

[0027] Perform further refinement operations on this preliminary framework. For the specific calculation logic of the vehicle speed data change prediction factor, it may be set to perform weighted calculation based on factors such as the distance between nodes, vehicle type, and road slope; the quantization model of the interaction between no vehicle speed data and vehicle speed data under this feature combination can be constructed based on probability statistics and the principle of vehicle driving inertia. For example, by analyzing the subsequent vehicle speed change data of a large number of similar vehicles in a situation without vehicle speed data, a mathematical model is established to quantify this interaction.

[0028] Determine the final vehicle speed distribution characteristic parameters based on the refined vehicle speed distribution characteristic parameter framework. For example, it is determined that the comprehensive change rate characteristic parameter of vehicle speed data under the combined feature is that for each missing node vehicle speed data, the comprehensive change rate of vehicle speed is 0.1 (indicating that the vehicle speed may have a 10% change rate), and the correction coefficient characteristic parameter of vehicle speed data under the combined feature is 0.8 (indicating that the subsequent vehicle speed data needs to be multiplied by 0.8 to correct the impact caused by no vehicle speed data).

[0029] Step S130, determine the target vehicle speed prediction scheme based on the vehicle speed distribution characteristic parameters of the vehicle speed knowledge points to be controlled during the second tracking period.

[0030] Still taking a large transport truck as an example, according to the vehicle speed distribution characteristic parameters of the vehicle speed knowledge points to be controlled (curve speed limit) during the second tracking period determined in the previous steps. Assume that the vehicle speed distribution characteristic parameters are concentrated, which means that the vehicle speed data is relatively concentrated as a whole and there is no obvious discrete situation.

[0031] There are two main schemes among the previously defined multiple target vehicle speed prediction schemes. The first target vehicle speed prediction scheme is: ignore the node intervals without vehicle speed data and summarize and calculate the vehicle speed data of the vehicle speed knowledge points to be controlled during the current tracking period; the second target vehicle speed prediction scheme is: comprehensively calculate the vehicle speed data of the vehicle speed knowledge points to be controlled during the previous tracking period, the vehicle speed data of the vehicle speed knowledge points corresponding to the current tracking node, and the vehicle speed data of the vehicle speed knowledge points corresponding to the candidate tracking period. The candidate tracking period is the tracking period formed by the tracking trigger node of the previous tracking period to the tracking trigger node of the current tracking period.

[0032] Since the vehicle speed distribution characteristic parameters are concentrated, the second target vehicle speed prediction scheme is output as the target vehicle speed prediction scheme according to the rules. This is because in the case of concentrated vehicle speed data, calculating by comprehensively considering the vehicle speed data of multiple periods can more accurately predict the vehicle speed. Considering the driving coherence of the vehicle in different periods and the comprehensive influence of various factors that may be affected, this comprehensive calculation method can better reflect the actual driving state of the vehicle and the future vehicle speed trend.

[0033] Step S140: Determine the vehicle speed characteristic information of the speed knowledge point of the vehicle to be controlled during the second tracking period based on the target vehicle speed prediction scheme.

[0034] Since the target vehicle speed prediction scheme is the second target vehicle speed prediction scheme, the vehicle speed characteristic information of the speed knowledge point to be controlled (curve speed limit) of the vehicle to be controlled (large transport truck) during the second tracking period is determined according to the corresponding rules.

[0035] First, obtain the first vehicle speed data of the speed knowledge point to be controlled during the first tracking period from the cloud storage system. Assume that during the first tracking period, through the speed measurement devices of previous nodes, the average vehicle speed of this vehicle at the curve is 70 km / h, which is the first vehicle speed data. Then obtain the second vehicle speed data of the speed knowledge point to be controlled at the current tracking node. It was previously mentioned that the vehicle speed of this vehicle at the current tracking node N is 75 km / h, which is the second vehicle speed data.

[0036] Determine the candidate tracking period based on the tracking trigger node of the first tracking period and the tracking trigger node of the second tracking period. Assume that the first tracking period starts from time point T1 and ends at T2, and the second tracking period starts from T2 and ends at T3. Then the candidate tracking period is from T1 to T3. Determine the third vehicle speed data of the speed knowledge point to be controlled during the candidate tracking period. For example, by performing weighted averaging (based on factors such as node distance and time weight) on the vehicle speed data of each node during this time period, the third vehicle speed data is obtained as 72 km / h.

[0037] Perform comprehensive calculation on the first vehicle speed data, the second vehicle speed data, and the third vehicle speed data to generate the vehicle speed characteristic information of the speed knowledge point to be controlled of the vehicle to be controlled during the second tracking period. For example, according to the pre-set calculation method (such as the weighted average method, with the weight of the first vehicle speed data being 0.3, the weight of the second vehicle speed data being 0.4, and the weight of the third vehicle speed data being 0.3), the calculated vehicle speed characteristic information is (70×0.3 + 75×0.4 + 72×0.3) = 72.6 km / h. This vehicle speed characteristic information can accurately reflect the vehicle speed characteristics of this vehicle regarding the curve speed limit knowledge point during the second tracking period, providing an important basis for subsequent traffic control decisions. For example, it can be used to determine whether the vehicle complies with the curve speed limit regulations, whether it is necessary to remind the driver or take other control measures, etc.

[0038] Based on the above steps, in the embodiment of the present application, by obtaining the to-be-controlled tasks of the target control unit of the target highway section, and for the to-be-controlled vehicle speed knowledge points of the to-be-controlled vehicles, in the case where vehicle speed data exists at the current tracking node, combining the current tracking node, the termination node of the first tracking period, and the tracking period duration parameter, the vehicle speed distribution characteristic parameters of the to-be-controlled vehicle speed knowledge points within the second tracking period are determined. Further, based on the vehicle speed distribution characteristic parameters, a target vehicle speed prediction scheme is determined, and according to the target vehicle speed prediction scheme, the vehicle speed characteristic information of the to-be-controlled vehicle speed knowledge points within the second tracking period is determined. This method can effectively predict and control the speed of highway vehicles, improve the accuracy and real-time performance of vehicle speed management, contribute to optimizing the traffic flow of highways, and enhance road traffic efficiency and safety.

[0039] In a possible implementation manner, step S120 includes:

[0040] Step S121, based on the current tracking node and the termination node of the first tracking period, determine the node interval without vehicle speed data.

[0041] Step S122, based on the tracking period duration parameter and a predefined determination strategy, determine the vehicle speed distribution characteristic limit value.

[0042] Step S123, based on the node interval without vehicle speed data and the vehicle speed distribution characteristic limit value, determine the vehicle speed distribution characteristic parameters of the to-be-controlled vehicle speed knowledge points within the second tracking period corresponding to the current tracking node.

[0043] In a possible implementation manner, step S123 includes:

[0044] Step S1231, determine the number of nodes in the node interval without vehicle speed data, the uniformity characteristic of the node distribution, and the proportion range of the node interval without vehicle speed data in the entire second tracking period, and generate a first analysis result.

[0045] Step S1232, perform a preliminary classification on the first analysis result according to the vehicle speed distribution characteristic limit value. Among them, if the number of nodes in the node interval without vehicle speed data is less than the node number threshold set by the vehicle speed distribution characteristic limit value, mark the preliminary classification result as the first category. If the uniformity characteristic of the node distribution in the node interval without vehicle speed data meets the uniformity standard set by the vehicle speed distribution characteristic limit value, mark the preliminary classification result as the second category. If the proportion range of the node interval without vehicle speed data in the entire second tracking period is less than the proportion threshold set by the vehicle speed distribution characteristic limit value, mark the preliminary classification result as the third category, and thus output the preliminary classification result.

[0046] Step S1233, perform an integrated judgment on the preliminary classification result. If the preliminary classification result contains the first category, the second category, and the third category at the same time, perform the first integrated judgment logic. Under the first integrated judgment logic, further analyze the relative position of the no-vehicle-speed data node interval within the entire second tracking period. If the no-vehicle-speed data node interval is located at the starting part of the second tracking period, output an integrated judgment result, marked as category A. If the no-vehicle-speed data node interval is located in the middle part of the second tracking period, output another integrated judgment result, marked as category B. If the no-vehicle-speed data node interval is located at the ending part of the second tracking period, output a third integrated judgment result, marked as category C. And, if the preliminary classification result only contains the first category and the second category, perform the second integrated judgment logic, and output a fourth integrated judgment result, marked as category D or category E, according to the specific feature combination of the first category and the second category results. And, if the preliminary classification result only contains the second category and the third category, perform the third integrated judgment logic, and output the corresponding integrated judgment result, marked as category F or category G, and output a fifth integrated judgment result.

[0047] Step S1234, determine the preliminary framework of the vehicle speed distribution characteristic parameters based on various integrated judgment results. Among them, if the integrated judgment result is of type A, construct a vehicle speed distribution characteristic parameter framework with the lack of vehicle speed data at the starting part as the influencing factor. The specific framework content includes the prediction factor for the influence of the lack of vehicle speed data at the starting part on the subsequent vehicle speed data trend, and the prediction factor for the fluctuation range of the subsequent vehicle speed data under the influence of the lack of vehicle speed data at the starting part. Also, if the integrated judgment result is of type B, construct a vehicle speed distribution characteristic parameter framework with the lack of vehicle speed data in the middle part as the concerned consideration factor. The specific framework content includes the prediction factor for the segmentation influence of the lack of vehicle speed data in the middle part on the front and rear vehicle speed data, and the prediction factor for the correlation degree of the front and rear vehicle speed data segmented by the lack of vehicle speed data in the middle. Also, if the integrated judgment result is of type C, construct a vehicle speed distribution characteristic parameter framework with the lack of vehicle speed data at the ending part as the concerned consideration factor. The specific framework content includes the prediction factor for the influence of the lack of vehicle speed data at the ending part on the integrity of the overall vehicle speed data, and the prediction factor for the proportion of valid data in the overall vehicle speed data in the presence of the lack of vehicle speed data at the ending. Also, if the integrated judgment result is of type D, construct a vehicle speed distribution characteristic parameter framework based on the combined characteristics of the first type and the second type. The specific framework content covers the prediction factor for the change of vehicle speed data corresponding to the combined characteristics related to the first type and the second type, and the prediction factor for the interaction between the lack of vehicle speed data and the vehicle speed data under this combined characteristic. Also, if the integrated judgment result is of type E, construct another vehicle speed distribution characteristic parameter framework based on the combined characteristics of the first type and the second type. The specific framework content includes the prediction factor for the fluctuation correlation of vehicle speed data corresponding to other combined characteristics of the first type and the second type, and the prediction factor for the influence of the lack of vehicle speed data on the continuity of vehicle speed data under a specific combination. Also, if the integrated judgment result is of type F, construct a vehicle speed distribution characteristic parameter framework based on the combined characteristics of the second type and the third type. The specific framework content includes the prediction factor for the stability of vehicle speed data corresponding to the combined characteristics related to the second type and the third type, and the prediction factor for the influence of the lack of vehicle speed data on the overall vehicle speed data trend under this combined characteristic. Also, if the integrated judgment result is of type G, construct another vehicle speed distribution characteristic parameter framework based on the combined characteristics of the second type and the third type. The specific framework content covers the prediction factor for the dynamic change of vehicle speed data corresponding to other combined characteristics of the second type and the third type, and the prediction factor for the influence of the lack of vehicle speed data on the extreme value of vehicle speed data under a specific combination.

[0048] Step S1235: For each preliminary framework, perform further refinement operations to generate a refined vehicle speed distribution characteristic parameter framework. Among them, if the framework focuses on the starting part without vehicle speed data, the refinement operations include determining the specific influence degree of the time length of the starting part without vehicle speed data on the estimation factor, and the specific functional relationship between the starting part without vehicle speed data and the subsequent vehicle speed data. Also, if the framework focuses on the middle part without vehicle speed data, the refinement operations include determining the specific quantitative index of the influence of the middle part without vehicle speed data on the segmentation of the front and rear vehicle speed data, and the specific correlation function of the front and rear vehicle speed data under the segmentation of the middle part without vehicle speed data. Also, if the framework focuses on the ending part without vehicle speed data, the refinement operations include determining the quantitative evaluation method of the influence of the ending part without vehicle speed data on the integrity of the overall vehicle speed data, and the specific calculation method of the proportion of valid data of the overall vehicle speed data in the presence of the ending part without vehicle speed data. Also, if the framework is based on the combined characteristics of the first type and the second type, the refinement operations include determining the specific calculation logic of the vehicle speed data change estimation factor under the combined characteristics of the first type and the second type, and the quantitative model of the interaction between the vehicle speed data without vehicle speed data and the vehicle speed data with vehicle speed data under this combined characteristic. Also, if the framework is based on the combined characteristics of the second type and the third type, the refinement operations include determining the specific numerical range of the vehicle speed data stability estimation factor under the combined characteristics of the second type and the third type, and the quantitative relationship of the influence of the vehicle speed data without vehicle speed data on the overall vehicle speed data trend under this combined characteristic.

[0049] Step S1236: Determine the final vehicle speed distribution characteristic parameters based on the refined vehicle speed distribution characteristic parameter framework. Among them, for each refined vehicle speed distribution characteristic parameter framework, if it is a framework related to the starting part without vehicle speed data, determine the average vehicle speed characteristic parameter under the influence of the starting part without vehicle speed data and the vehicle speed fluctuation range characteristic parameter under the influence of the starting part without vehicle speed data according to the refined content. Also, if it is a framework related to the middle part without vehicle speed data, determine the front and rear vehicle speed difference characteristic parameter under the segmentation of the middle part without vehicle speed data and the vehicle speed dispersion characteristic parameter under the segmentation of the middle part without vehicle speed data. Also, if it is a framework related to the ending part without vehicle speed data, determine the overall vehicle speed deviation characteristic parameter under the ending part without vehicle speed data and the vehicle speed extreme value characteristic parameter under the ending part without vehicle speed data. Also, if it is a framework based on the combined characteristics of the first type and the second type, determine the comprehensive change rate characteristic parameter of the vehicle speed data under the combined characteristic and the vehicle speed data correction coefficient characteristic parameter under the combined characteristic. Also, if it is a framework based on the combined characteristics of the second type and the third type, determine the vehicle speed data stability adjustment parameter under the combined characteristic and the vehicle speed data trend correction characteristic parameter under the combined characteristic.

[0050] In this embodiment, taking a certain highway as an example, a dense monitoring system is set up on this highway for traffic control. Assume that the target vehicle to be controlled is a long-distance bus, which is driving on a specific highway section. The traffic control unit of this section is responsible for controlling its vehicle speed, and the vehicle speed knowledge point to be controlled is the safe vehicle speed range during normal driving (for example, 60 - 100 kilometers per hour).

[0051] In the monitoring system of the highway, tracking nodes are set at fixed distances or time intervals. For example, a node is set every 1 kilometer, and each node has a vehicle speed measurement function. The first tracking period is set to the first 10 minutes after the bus enters the specific section, and its termination node is the tracking node corresponding to the 10 - minute moment. The current tracking node is a certain node after the end of the first tracking period.

[0052] Based on the current tracking node and the termination node of the first tracking period, determine the interval of nodes without vehicle speed data. During the driving of the bus, due to possible failures or interferences of the speed measurement devices of some nodes, vehicle speed data of the bus regarding the vehicle speed knowledge point is not obtained at some nodes. For example, between the termination node of the first tracking period and the current tracking node, there are 5 nodes that do not obtain vehicle speed data, and these 5 nodes constitute the interval of nodes without vehicle speed data.

[0053] Based on the tracking period duration parameter (10 minutes) and a predefined determination strategy, determine the boundary value of the vehicle speed distribution characteristics. The predefined determination strategy is formulated according to a large amount of historical traffic data and the design and operation characteristics of the highway. For a 10 - minute tracking period, the set node quantity threshold is 8, the uniformity standard is that the adjacent interval of nodes without vehicle speed data does not exceed 3 nodes, and the proportion threshold is that the proportion of the interval of nodes without vehicle speed data in the entire second tracking period does not exceed 40%.

[0054] Determine the number of nodes (5) in the interval of nodes without vehicle speed data, the uniformity characteristics of the node distribution (assuming that the adjacent intervals of nodes without vehicle speed data are 1, 2, 1, 1 nodes respectively, which basically meets the uniformity standard), and the proportion range of the interval of nodes without vehicle speed data in the entire second tracking period. Assume that the second tracking period from the termination node of the first tracking period to the current tracking node contains a total of 15 nodes, then the proportion of the interval of nodes without vehicle speed data is 5 / 15≈33.3%, and generate the first analysis result.

[0055] The first analysis result is preliminarily classified according to the boundary values of the vehicle speed distribution characteristics. Since the number of nodes in the interval without vehicle speed data is 5, which is less than the node number threshold of 8, the preliminary classification result is marked as the first category; the uniformity characteristic of the node distribution basically meets the uniformity standard, and the preliminary classification result is marked as the second category; the proportion of the interval without vehicle speed data is 33.3%, which is less than the proportion threshold of 40%, and the preliminary classification result is marked as the third category. Thus, the output preliminary classification result includes the first category, the second category, and the third category.

[0056] An integrated judgment is made on the preliminary classification result. Since the preliminary classification result includes the first category, the second category, and the third category at the same time, the first integrated judgment logic is carried out. Further analyze the relative position of the interval without vehicle speed data in the entire second tracking period. Assuming that the interval without vehicle speed data is located in the middle part of the second tracking period, the integrated judgment result is output and marked as category B.

[0057] Based on the integrated judgment result of category B, a vehicle speed distribution characteristic parameter framework is constructed with the focus on the vehicle speed data without speed in the middle part as a consideration factor. The specific framework content includes the estimated factor of the segmentation effect of the vehicle speed data without speed in the middle part on the front and rear vehicle speed data, and the estimated factor of the correlation degree of the front and rear vehicle speed data under the segmentation of the vehicle speed data without speed in the middle. The setting of the estimated factor of the segmentation effect of the vehicle speed data without speed in the middle part on the front and rear vehicle speed data is based on the principle of vehicle driving continuity. For example, according to historical data and vehicle dynamics models, the occurrence of vehicle speed data without speed may cause a certain degree of disconnection between the front and rear vehicle speed data, and the estimated factor is set to 0.3, indicating that there may be a 30% disconnection effect; the estimated factor of the correlation degree of the front and rear vehicle speed data under the segmentation of the vehicle speed data without speed in the middle is set to 0.6, indicating that there is still a 60% correlation between the front and rear vehicle speed data under the segmentation of the vehicle speed data without speed in the middle.

[0058] Further refinement operations are carried out for this preliminary framework. For the specific quantitative index of the segmentation effect of the vehicle speed data without speed in the middle part on the front and rear vehicle speed data, it can be determined according to factors such as the distance between nodes, the acceleration characteristics of the vehicle, and the road slope. For example, the greater the distance between nodes, the smaller the vehicle acceleration, and the flatter the road slope, the smaller the segmentation effect. The specific correlation function can be constructed based on probability theory and time series analysis, considering factors such as the time sequence and speed change trend of the front and rear vehicle speed data. Assuming that the constructed correlation function is a multiple linear regression function, the coefficients of the function are obtained by fitting through historical data.

[0059] Determine the final vehicle speed distribution characteristic parameters based on the refined vehicle speed distribution characteristic parameter framework. For the framework without vehicle speed data in the middle part, determine the characteristic parameters of the vehicle speed difference before and after the segmentation without vehicle speed data in the middle part. For example, by analyzing the distribution of the vehicle speed data before and after and the influence of the lack of vehicle speed data in the middle, it is determined that the vehicle speed difference in this case may be between 10 - 15 km / h; the characteristic parameter of the vehicle speed dispersion under the segmentation without vehicle speed data in the middle part can be obtained by calculating the standard deviation of the vehicle speed data before and after, which is assumed to be 8 km / h, indicating the degree of dispersion of the vehicle speed in the front and back parts.

[0060] Taking another case as an example, assume that the target control vehicle is a freight truck, and the vehicle speed knowledge point to be controlled is the safe vehicle speed on a specific slope section (assumed to be 40 - 60 km / h). The tracking period is set to 15 minutes per period. There are 3 nodes without vehicle speed data between the termination node of the first tracking period and the current tracking node, forming an interval of nodes without vehicle speed data. The entire second tracking period from the termination node of the first tracking period to the current tracking node contains a total of 12 nodes.

[0061] Determine the vehicle speed distribution characteristic boundary values based on the same determination strategy. For a 15 - minute tracking period, the node number threshold is 6, the uniformity standard is that the adjacent interval of nodes without vehicle speed data does not exceed 2 nodes, and the proportion threshold is that the proportion of the interval of nodes without vehicle speed data in the entire second tracking period does not exceed 25%. The number of nodes in the interval of nodes without vehicle speed data, which is 3, is less than the node number threshold of 6, and it is marked as the first category; the adjacent intervals of nodes without vehicle speed data are 1, 1, and 1 node respectively, meeting the uniformity standard, and it is marked as the second category; the proportion of the interval of nodes without vehicle speed data is 3 / 12 = 25%, exactly equal to the proportion threshold, and it does not meet the third category for the time being. The preliminary classification result includes the first category and the second category.

[0062] Conduct the second integrated judgment logic. According to the specific characteristic combination of the results of the first category and the second category, assume that the fourth integrated judgment result is output and marked as category D. Construct a vehicle speed distribution characteristic parameter framework based on the combined characteristics of the first category and the second category, covering the vehicle speed data change prediction factor corresponding to the characteristic combination related to the first category and the second category, and the interaction prediction factor between the vehicle speed data without and with vehicle speed data under this characteristic combination. The vehicle speed data change prediction factor is set according to the vehicle type, road conditions, and historical data. For each missing node of vehicle speed data, the subsequent vehicle speed data may have a fluctuation range of 3 km / h; the interaction prediction factor between the vehicle speed data without and with vehicle speed data under this characteristic combination is set such that the vehicle speed data after the node without vehicle speed data will approach the vehicle speed value of the adjacent node with vehicle speed data with a certain probability (such as 20%).

[0063] Refine this framework. For the specific calculation logic of the vehicle speed data change prediction factor, weighted calculation is performed based on factors such as the vehicle's load, tire wear degree, and road friction coefficient. The quantization model of the interaction between no vehicle speed data and vehicle speed data under this feature combination is constructed based on probability statistics and the physical principles of vehicle driving. By analyzing the subsequent vehicle speed change data of a large number of freight trucks in a situation similar to no vehicle speed data, a mathematical model is established to quantify this interaction.

[0064] Determine the final vehicle speed distribution characteristic parameters based on the refined framework. For the frameworks based on the first and second types of combined features, the characteristic parameter of the comprehensive change rate of vehicle speed data under the combined features is determined as follows: for each missing node of vehicle speed data, the comprehensive change rate of vehicle speed is 0.08 (indicating that the vehicle speed may have a change rate of 8%), and the characteristic parameter of the correction coefficient of vehicle speed data under the combined features is 0.9 (indicating that the subsequent vehicle speed data needs to be multiplied by 0.9 to correct the impact caused by no vehicle speed data).

[0065] Assume again that the target control vehicle is a small car, and the vehicle speed knowledge point to be controlled is the safe vehicle speed in the tunnel (assumed to be 80 - 100 km / h). The tracking period is set to 20 minutes per period. There are 4 nodes for which vehicle speed data has not been obtained between the end node of the first tracking period and the current tracking node. The entire second tracking period from the end node of the first tracking period to the current tracking node contains a total of 18 nodes.

[0066] Determine the vehicle speed distribution characteristic boundary values according to the determination strategy. For a 20 - minute tracking period, the node number threshold is 7, the uniformity standard is that the interval between adjacent nodes without vehicle speed data does not exceed 3 nodes, and the ratio threshold is that the proportion of the interval of nodes without vehicle speed data in the entire second tracking period does not exceed 30%. The number of nodes in the interval of nodes without vehicle speed data, which is 4, is less than the node number threshold of 7, and it is marked as the first type; the intervals between adjacent nodes without vehicle speed data are 1, 2, and 1 node respectively, which meet the uniformity standard, and it is marked as the second type; the proportion of the interval of nodes without vehicle speed data is 4 / 18 ≈ 22.2%, which is less than the ratio threshold, and it is marked as the third type. The preliminary classification result includes the second type and the third type.

[0067] Perform the third integrated judgment logic. According to the specific feature combination of the second category and the third category, assume that the fifth integrated judgment result is output and marked as category F. Construct a vehicle speed distribution characteristic parameter framework based on the combined features of the second category and the third category, including the vehicle speed data stability prediction factor corresponding to the feature combination related to the second category and the third category, and the influence prediction factor of the absence of vehicle speed data on the overall vehicle speed data trend under this feature combination. The vehicle speed data stability prediction factor is set to 0.8 according to the vehicle's handling performance, ventilation conditions, and lighting conditions in the tunnel, indicating that the vehicle speed data is relatively stable; the influence prediction factor of the absence of vehicle speed data on the overall vehicle speed data trend under this feature combination is set to the fact that the absence of vehicle speed data may cause a 10% fluctuation in the overall vehicle speed data trend.

[0068] Refine this framework. For the specific numerical range of the vehicle speed data stability prediction factor, consider factors such as the vehicle's engine performance and brake system status for adjustment, and determine that it is between 0.7 and 0.9. Establish a quantitative model for the quantitative relationship between the influence of the absence of vehicle speed data on the overall vehicle speed data trend under this feature combination according to factors such as the traffic flow in the tunnel and the following distance of the vehicle.

[0069] Determine the final vehicle speed distribution characteristic parameters based on the refined framework. For the framework based on the combined features of the second category and the third category, determine that the vehicle speed data stability adjustment parameter under the combined features is 0.05 (indicating a 5% adjustment to the vehicle speed data stability), and the vehicle speed data trend correction characteristic parameter under the combined features is 0.95 (indicating a 0.95 correction to the overall vehicle speed data trend). Through such a series of steps, the vehicle speed distribution characteristic parameters of the vehicle speed knowledge points to be controlled for the vehicle to be controlled in the corresponding tracking period under different conditions can be accurately determined, providing an important basis for subsequent vehicle speed prediction and control.

[0070] In a possible implementation manner, step S130 includes:

[0071] Step S131, if the vehicle speed distribution characteristic parameters of the vehicle speed knowledge point to be controlled in the second tracking period are discrete, then output the first target vehicle speed prediction scheme among the previously defined multiple target vehicle speed prediction schemes as the target vehicle speed prediction scheme. The first target vehicle speed prediction scheme includes: ignoring the node intervals of the absence of vehicle speed data and summarizing and calculating the vehicle speed data of the vehicle speed knowledge point to be controlled in the current tracking period.

[0072] In step S132, if the vehicle speed distribution characteristic parameter of the vehicle speed knowledge point to be controlled during the second tracking period is concentrated, the second target vehicle speed prediction scheme among a plurality of predefined target vehicle speed prediction schemes is output as the target vehicle speed prediction scheme. The second target vehicle speed prediction scheme includes: comprehensively calculating the vehicle speed data of the vehicle speed knowledge point to be controlled during the previous tracking period, the vehicle speed data of the vehicle speed knowledge point corresponding to the current tracking node, and the vehicle speed data of the vehicle speed knowledge point corresponding to the candidate tracking period. The candidate tracking period is the tracking period formed by the tracking trigger node of the previous tracking period to the tracking trigger node of the current tracking period.

[0073] In this embodiment, taking the highway traffic control scenario mentioned above as an example, for the control of long-distance buses. Suppose a long-distance bus is traveling on a specific highway section, and the vehicle speed knowledge point to be controlled is the safe vehicle speed range (60 - 100 km / h) during normal driving. After a series of analyses of the interval of nodes without vehicle speed data and the boundary values of vehicle speed distribution characteristics, the vehicle speed distribution characteristic parameter of the vehicle speed knowledge point to be controlled during the second tracking period is determined.

[0074] If the vehicle speed distribution characteristic parameter is discrete, it means that during the second tracking period, the vehicle speed data of the long-distance bus shows a relatively dispersed state at each node. For example, the vehicle speed at some nodes is close to the lower limit of the safe vehicle speed range, 60 km / h, while the vehicle speed at other nodes is close to the upper limit, 100 km / h, and there is no obvious concentrated trend in the middle. This discrete situation may be caused by complex changes in road conditions (such as large differences in slopes of different road sections, changes in road surface friction coefficients, etc.) or unstable driving states of the bus itself (such as frequent acceleration and deceleration).

[0075] At this time, according to the pre-defined rules, the first target vehicle speed prediction scheme among the previously defined multiple target vehicle speed prediction schemes is output as the target target vehicle speed prediction scheme. The first target vehicle speed prediction scheme is to ignore the interval of nodes without vehicle speed data and summarize and calculate the vehicle speed data of the vehicle speed knowledge points to be controlled during the current tracking period. This is because in the case of discrete vehicle speed data, the influence of the interval of nodes without vehicle speed data on the overall vehicle speed data is relatively small, and more attention is paid to the overall situation of the vehicle speed data actually obtained during the current tracking period. Specifically, by summarizing the vehicle speed data obtained at each node during the current tracking period, for example, the method of calculating the average value can be used to obtain a value representing the vehicle speed of the passenger car during the current tracking period. Suppose there are 10 nodes that have obtained vehicle speed data during the current tracking period, which are 62, 65, 95, 90, 68, 92, 63, 98, 66, and 93 km / h respectively. After adding these vehicle speed data and dividing by 10, the average value is 79.2 km / h. This average value can be used as an important vehicle speed characteristic index under the target target vehicle speed prediction scheme for subsequent vehicle speed control decision-making and other operations.

[0076] Next, look at the situation of a cargo truck driving on a specific slope section. The vehicle speed knowledge point to be controlled is the safe vehicle speed (40 - 60 km / h) on this slope section. When determining the vehicle speed distribution characteristic parameters of the vehicle speed knowledge point to be controlled during the second tracking period, if it is found that the vehicle speed distribution characteristic parameters are concentrated. This means that the vehicle speed data of the cargo truck during this second tracking period is relatively concentrated around a certain range or a certain value. For example, the vehicle speed data obtained by most nodes are between 45 - 50 km / h. This may be because when the cargo truck is driving on the slope section, it is affected by factors such as the vehicle load, the limitation of the slope on the vehicle driving, and the driver maintaining a relatively fixed vehicle speed to ensure safe and stable driving.

[0077] According to the rules, at this time, the second target vehicle speed prediction scheme among the previously defined multiple target vehicle speed prediction schemes is output as the target target vehicle speed prediction scheme. The second target vehicle speed prediction scheme comprehensively calculates the vehicle speed data of the vehicle speed knowledge points to be controlled in a previous tracking period, the vehicle speed data of the vehicle speed knowledge points to be controlled corresponding to the current tracking node, and the vehicle speed data of the vehicle speed knowledge points to be controlled corresponding to the candidate tracking period. Suppose that in a previous tracking period, the average value of the vehicle speed data obtained through each node is 48 km / h (obtained by summing up the vehicle speed data of all nodes in this period and dividing by the number of nodes). At the current tracking node, the vehicle speed of the freight truck is measured to be 47 km / h. For the candidate tracking period, that is, the tracking period formed by the tracking trigger node of the previous tracking period to the tracking trigger node of the current tracking period, after calculation, the average value of the vehicle speed data in this period is 46 km / h (also obtained by summing up the vehicle speed data of all nodes in this period and dividing by the number of nodes). According to the pre-set weighted calculation method (for example, the weight of the previous tracking period is 0.3, the weight of the current tracking node is 0.4, and the weight of the candidate tracking period is 0.3), the comprehensively calculated vehicle speed is (48×0.3 + 47×0.4 + 46×0.3) = 47 km / h. This calculated vehicle speed value is the vehicle speed characteristic index of the freight truck regarding the vehicle speed knowledge points to be controlled in the second tracking period based on the second target vehicle speed prediction scheme. It comprehensively considers the vehicle speed data of different periods and can more accurately reflect the actual vehicle speed situation of the freight truck in this period, thereby providing a basis for further vehicle speed control measures (such as determining whether it is speeding, whether the vehicle speed needs to be adjusted, etc.).

[0078] For the situation of a small car driving in a tunnel, the vehicle speed knowledge points to be controlled are the safe vehicle speeds in the tunnel (80 - 100 km / h). When the vehicle speed distribution characteristic parameter of the vehicle speed knowledge points to be controlled in the second tracking period is determined to be discrete, similar to the situation of a long-distance bus, the vehicle speed data is scattered at each node in the tunnel. This may be caused by factors such as changes in vehicle density in the tunnel and different reactions of drivers to the tunnel environment (for example, some drivers will suddenly decelerate when entering the tunnel, while some drivers maintain a higher vehicle speed). According to the regulations, the first target vehicle speed prediction scheme is adopted, ignoring the node intervals without vehicle speed data, and summarizing the vehicle speed data in the current tracking period. Suppose the vehicle speed data obtained in the current tracking period are 82, 95, 85, 98, and 88 km / h respectively, and the calculated average value is (82 + 95 + 85 + 98 + 88) ÷ 5 = 89.6 km / h. This average value is used as the vehicle speed characteristic index under the target target vehicle speed prediction scheme, which can be used to evaluate the vehicle speed situation of the small car in the tunnel to determine whether it meets the requirements of the safe vehicle speed in the tunnel and other control operations.

[0079] If a compact car is driving in a tunnel, the speed distribution characteristic parameter of the speed points to be controlled during the second tracking period is concentrated. For example, most of the speed data is concentrated between 85 and 90 kilometers per hour. This may be due to the relatively stable environment in the tunnel (such as stable lighting, ventilation, etc.) and the general perception of the safe speed in the tunnel by drivers. According to the rules, the second target speed prediction scheme is adopted. Assuming that the average speed data in the previous tracking period is 88 kilometers per hour, the current tracking node speed is 86 kilometers per hour, and the average speed data of the candidate tracking period is 87 kilometers per hour, and comprehensive calculation is carried out according to the set weights (such as 0.3, 0.4, 0.3), and (88×0.3 + 86×0.4 + 87×0.3) = 87.1 kilometers per hour is obtained. This calculation result is used as the speed characteristic index determined based on the second target speed prediction scheme, which helps to accurately grasp the speed condition of the compact car in the tunnel and provide an accurate basis for traffic control. For example, it can be used to judge whether it is necessary to adjust the speed to ensure traffic safety and efficient passage in the tunnel and other operations.

[0080] In a possible implementation manner, the target speed prediction scheme is the first target speed prediction scheme, and the step S140 may include:

[0081] Obtain the first period duration parameter corresponding to the speed data node interval without speed for the speed points to be controlled during the second tracking period from the cloud storage system.

[0082] Obtain the speed data of the speed points to be controlled with the second period duration parameter from the cloud storage system, where the second period duration parameter is each period duration parameter other than the first period duration parameter during the second tracking period.

[0083] Summarize and calculate the speed data of the speed points to be controlled with the second period duration parameter to generate the speed characteristic information of the vehicle to be controlled for the speed points to be controlled during the second tracking period.

[0084] In a possible implementation manner, the target speed prediction scheme is the second target speed prediction scheme, and the step S140 may include:

[0085] Obtain the first speed data of the speed points to be controlled during the first tracking period from the cloud storage system, and obtain the second speed data of the speed points to be controlled at the current tracking node.

[0086] Determine a candidate tracking period based on the tracking trigger node of the first tracking period and the tracking trigger node of the second tracking period, and determine the third speed data of the speed points to be controlled during the candidate tracking period.

[0087] Perform comprehensive calculations on the first vehicle speed data, the second vehicle speed data, and the third vehicle speed data to generate the vehicle speed characteristic information of the vehicle speed knowledge points to be controlled for the vehicle to be controlled during the second tracking period.

[0088] In this embodiment, taking a long-distance bus driving on a specific section of a highway as an example, the control unit of this section controls the vehicle speed knowledge points to be controlled (the normal driving safe speed range is 60-100 km / h). When the target vehicle speed prediction scheme is the first target vehicle speed prediction scheme, that is, ignoring the interval of nodes without vehicle speed data, the vehicle speed data of the vehicle speed knowledge points to be controlled during the current tracking period is summarized and calculated.

[0089] First, obtain the first period duration parameter corresponding to the interval of nodes without vehicle speed data of the vehicle speed knowledge points to be controlled during the second tracking period from the cloud storage system. The cloud storage system records the detailed information of each node on the highway, including the period information of each node. For the long-distance bus, during the second tracking period, assume that the first period duration parameter corresponding to the interval of nodes without vehicle speed data is the time period from node 10 to node 15, with a duration of 5 minutes. This information is accurately obtained from the cloud storage system, which represents the period situation of the nodes without vehicle speed data.

[0090] Next, obtain the vehicle speed data of the vehicle speed knowledge points to be controlled with the second period duration parameter, where the second period duration parameter is the period duration parameters of each period during the second tracking period except for the first period duration parameter. For example, during the second tracking period in the time period from node 5 to node 20, except for the nodes from node 10 to node 15 without vehicle speed data, the vehicle speed data of other nodes needs to be obtained. Assume that the vehicle speed data from node 5 to node 9 are 70, 72, 75, 73, and 71 km / h respectively, and the vehicle speed data from node 16 to node 20 are 78, 80, 82, 85, and 83 km / h respectively.

[0091] Then, summarize and calculate the vehicle speed data of the vehicle speed knowledge points of the second time period's continuous parameter to generate the vehicle speed characteristic information of the vehicle speed knowledge points of the vehicle to be controlled during the second tracking period. In this example, summarize and calculate the obtained vehicle speed data (70, 72, 75, 73, 71, 78, 80, 82, 85, 83), such as calculating the average value. First, add these vehicle speed data: 70 + 72 + 75 + 73 + 71 + 78 + 80 + 82 + 85 + 83 = 769 km / h, and then divide by the number of data, which is 10, to obtain an average value of 76.9 km / h. This 76.9 km / h is the vehicle speed characteristic information of the long-distance bus regarding the vehicle speed knowledge points during the second tracking period. This information can reflect the vehicle speed characteristics of the long-distance bus during this period and provide a basis for subsequent control operations such as determining whether the bus is within the safe vehicle speed range.

[0092] Taking a cargo truck driving on a specific slope section as an example, the vehicle speed knowledge point to be controlled is the safe vehicle speed (40 - 60 km / h) of this slope section. When the target vehicle speed prediction scheme is the second target vehicle speed prediction scheme, relevant data needs to be obtained from the cloud storage system for comprehensive calculation to determine the vehicle speed characteristic information.

[0093] Obtain the first vehicle speed data of the vehicle speed knowledge point to be controlled during the first tracking period from the cloud storage system, and obtain the second vehicle speed data of the vehicle speed knowledge point to be controlled at the current tracking node. Assume that during the first tracking period, after statistical calculation of the vehicle speed data of each node of the cargo truck on this slope section, the first vehicle speed data (average value) is 48 km / h. This data is accurately obtained from the cloud storage system and reflects the vehicle speed situation of the cargo truck regarding the vehicle speed knowledge point during the first tracking period. At the current tracking node, the measured vehicle speed of the cargo truck is 47 km / h, which is the second vehicle speed data, and relevant records are also obtained from the cloud storage system.

[0094] Determine the candidate tracking period based on the tracking trigger node of the first tracking period and the tracking trigger node of the second tracking period, and determine the third vehicle speed data of the vehicle speed knowledge point to be controlled during the candidate tracking period. Assume that the first tracking period starts from time point T1 and ends at T2, and the second tracking period starts from T2 and ends at T3. Then the candidate tracking period is from T1 to T3. During this candidate tracking period, after statistical analysis of the vehicle speed data of each node, assume that the third vehicle speed data (average value) is 46 km / h. This data is accurately obtained from the cloud storage system according to the records of relevant nodes.

[0095] Finally, the first vehicle speed data, the second vehicle speed data, and the third vehicle speed data are comprehensively calculated to generate the vehicle speed characteristic information of the vehicle to be controlled for the vehicle speed knowledge points during the second tracking period. According to the pre-set calculation method, for example, the weighted average method is used. Assume that the weight of the first vehicle speed data is 0.3, the weight of the second vehicle speed data is 0.4, and the weight of the third vehicle speed data is 0.3. The calculation process is: (48×0.3 + 47×0.4 + 46×0.3) = 47 km / h. This 47 km / h is the vehicle speed characteristic information of the freight truck for the vehicle speed knowledge points during the second tracking period. Through such a calculation method, the vehicle speed data of different periods is comprehensively considered, which can more accurately reflect the vehicle speed condition of the freight truck during the second tracking period on this slope section, help to judge whether the freight truck complies with the safe vehicle speed regulations, and provide an accurate basis for traffic control.

[0096] For the case of a small car driving in a tunnel, the vehicle speed knowledge point to be controlled is the safe vehicle speed in the tunnel (80 - 100 km / h).

[0097] When the target vehicle speed prediction scheme is the first target vehicle speed prediction scheme, information is obtained from the cloud storage system. Assume that during the second tracking period, the duration parameter of the first period corresponding to the vehicle speed data node interval is the time period from node 8 to node 12, with a duration of 4 minutes. Then, the vehicle speed data of the vehicle speed knowledge points of the second period duration parameter is obtained. Among nodes 3 to 20 during the second tracking period, except for the vehicle speed data missing from node 8 to node 12, the vehicle speed data of other nodes is as follows: The vehicle speed data from node 3 to node 7 are 82, 85, 88, 90, 92 km / h respectively, and the vehicle speed data from node 13 to node 20 are 95, 93, 90, 88, 86, 85, 83, 82 km / h respectively. These vehicle speed data are aggregated and the average value is calculated. First, sum them up: 82 + 85 + 88 + 90 + 92 + 95 + 93 + 90 + 88 + 86 + 85 + 83 + 82 = 1139 km / h, and then divide by the number of data 13, to get an average value of approximately 87.62 km / h. This 87.62 km / h is the vehicle speed characteristic information of the small car for the vehicle speed knowledge points during the second tracking period, which can be used to evaluate whether the vehicle speed of the small car in the tunnel meets the safety requirements.

[0098] When the target vehicle speed prediction scheme is the second target vehicle speed prediction scheme, obtain the first vehicle speed data of the compact car in the first tracking period from the cloud storage system. Suppose the average value calculated through statistics is 88 kilometers per hour; the second vehicle speed data at the current tracking node is 86 kilometers per hour. Determine the candidate tracking period based on the tracking trigger node. Suppose the average value of the third vehicle speed data within the candidate tracking period is 87 kilometers per hour. Perform comprehensive calculation according to the set weighted average method (suppose the weights are 0.3, 0.4, and 0.3 respectively): (88×0.3 + 86×0.4 + 87×0.3) = 87.1 kilometers per hour. This 87.1 kilometers per hour is the vehicle speed characteristic information of the compact car regarding the vehicle speed knowledge point to be controlled within the second tracking period, providing an accurate basis for vehicle speed conditions for traffic control.

[0099] In a possible implementation manner, the method further includes:

[0100] Step A110, determine the vehicle speed characteristic information of the vehicle speed knowledge point to be controlled for each node period of the vehicle to be controlled within the second tracking period.

[0101] Step A120, obtain the period duration parameters of each node period within the second tracking period, where the period duration parameters include the initial node and the termination node.

[0102] Step A130, store the period duration parameters of each node period and the vehicle speed characteristic information of the vehicle speed knowledge point to be controlled for the vehicle to be controlled within each node period into the cloud storage system.

[0103] In a possible implementation manner, the method further includes:

[0104] Step B110, obtain the period characteristic parameters of the second tracking period, where the period characteristic parameters include the initial node and the termination node.

[0105] Step B120, store the period characteristic parameters of the second tracking period and the vehicle speed characteristic information of the vehicle speed knowledge point to be controlled for the vehicle to be controlled within the second tracking period into the cloud storage system.

[0106] In this embodiment, taking a long-distance bus driving on a specific section of the highway as an example, the control unit of this section controls the vehicle speed knowledge point to be controlled (the normal driving safety speed range is 60 - 100 kilometers per hour).

[0107] First, determine the speed characteristic information of the speed knowledge points of the vehicle to be controlled (long-distance bus) for each node period within the second tracking period. Within the second tracking period, assuming this period ranges from node 1 to node 20, for each node period, it is necessary to analyze its speed characteristic information. For example, for the node period from node 1 to node 3, the speed data obtained through the speed measurement device are 70, 72, and 73 km / h respectively. Calculate its average value as (70 + 72 + 73) ÷ 3 = 71.67 km / h, which is the speed characteristic information of this node period. For the node period from node 4 to node 6, the speed data are 75, 78, and 80 km / h, and the average value is (75 + 78 + 80) ÷ 3 = 77.67 km / h, which is also the speed characteristic information of this node period. In this way, determine the speed characteristic information of each node period in turn.

[0108] Next, obtain the period duration parameters of each node period within the second tracking period. The period duration parameters include the initial node and the termination node. For the node period from node 1 to node 3, the initial node is 1 and the termination node is 3. This information defines the scope of this node period. For the node period from node 4 to node 6, the initial node is 4 and the termination node is 6. Obtain the period duration parameters of each node period in this way.

[0109] Then, store the period duration parameters of each node period and the speed characteristic information of the speed knowledge points of the vehicle to be controlled within each node period into the cloud storage system. For the node period from node 1 to node 3, store the initial node 1, the termination node 3, and the speed characteristic information of 71.67 km / h into the cloud storage system. The cloud storage system will store data according to a certain data structure for subsequent query and analysis. For the node period from node 4 to node 6, store the initial node 4, the termination node 6, and the speed characteristic information of 77.67 km / h into the cloud storage system. According to this process, store the relevant information of all node periods into the cloud storage system to provide a detailed data basis for subsequent traffic control analysis.

[0110] Next, look at the situation of obtaining the period characteristic parameters of the second tracking period and storing the relevant information into the cloud storage system. Obtain the period characteristic parameters of the second tracking period. Assuming the second tracking period starts from node 1 corresponding to time point T1 and ends at node 20 corresponding to time point T2, then the initial node is 1 and the termination node is 20. This is the period characteristic parameter of the second tracking period.

[0111] Then, store the period feature parameters of the second tracking period and the vehicle speed feature information of the vehicle to be controlled regarding the vehicle speed knowledge points during the second tracking period in the cloud storage system. Assume that the previously calculated vehicle speed feature information of the long-distance bus during the second tracking period is 78 km / h (obtained by aggregating and calculating the vehicle speed data of all nodes during the entire second tracking period). Store the initial node 1, the terminal node 20, and the vehicle speed feature information 78 km / h in the cloud storage system. In this way, the cloud storage system stores both the detailed information of each node period and the summary information of the entire second tracking period, and this information is very important for the traffic control department to analyze the vehicle speed of the long-distance bus on this section of the road. For example, based on this information, it can be determined whether the vehicle speed of the long-distance bus meets the safety regulations at different times and whether there are abnormal vehicle speed fluctuations, etc., so as to take corresponding control measures.

[0112] Taking a cargo truck driving on a specific slope section as an example, the vehicle speed knowledge point to be controlled is the safe vehicle speed (40 - 60 km / h) of this slope section.

[0113] Regarding determining the vehicle speed feature information of the vehicle speed knowledge points to be controlled for each node period of the cargo truck during the second tracking period, assume that the second tracking period is from node 5 to node 15. For the node period from node 5 to node 7, the vehicle speed data obtained by the speed measurement device is 45, 46, 48 km / h, and its average value (45 + 46 + 48) ÷ 3 = 46.33 km / h is the vehicle speed feature information of this node period. For the node period from node 8 to node 10, the vehicle speed data is 49, 50, 52 km / h, and the average value is (49 + 50 + 52) ÷ 3 = 50.33 km / h, which is the vehicle speed feature information of this node period. Determine the vehicle speed feature information of each node period in this way.

[0114] Obtain the period duration parameters of each node period during the second tracking period. For the node period from node 5 to node 7, the initial node is 5 and the terminal node is 7. For the node period from node 8 to node 10, the initial node is 8 and the terminal node is 10.

[0115] Store the period duration parameters of each node period and the vehicle speed feature information of the vehicle speed knowledge points to be controlled for the cargo truck in each node period in the cloud storage system. For the node period from node 5 to node 7, store the initial node 5, the terminal node 7, and the vehicle speed feature information 46.33 km / h in the cloud storage system. For the node period from node 8 to node 10, store the initial node 8, the terminal node 10, and the vehicle speed feature information 50.33 km / h in the cloud storage system.

[0116] Regarding obtaining the time period characteristic parameters of the second tracking period and storing relevant information, assume that the second tracking period starts from node 5 corresponding to time point T3 and ends at node 15 corresponding to time point T4. The initial node is 5 and the termination node is 15. These are the time period characteristic parameters of the second tracking period. Assume that the vehicle speed characteristic information of the freight truck throughout the second tracking period is 48 km / h (obtained by summarizing and calculating the vehicle speed data of all nodes during the entire second tracking period), and store the initial node 5, the termination node 15, and the vehicle speed characteristic information of 48 km / h into the cloud storage system. This information helps the traffic control department analyze the vehicle speed of the freight truck on this slope section, such as determining whether the freight truck is driving within the safe vehicle speed range, whether there is overspeeding or unstable vehicle speed, so as to take control measures in a timely manner.

[0117] Taking a small car driving in a tunnel as an example, the knowledge point of the vehicle speed to be controlled is the safe vehicle speed in the tunnel (80 - 100 km / h).

[0118] When determining the vehicle speed characteristic information of the knowledge point of the vehicle speed to be controlled for each node time period of the small car during the second tracking period, assume that the second tracking period is from node 3 to node 12. For the node time period from node 3 to node 5, the obtained vehicle speed data are 82, 85, and 83 km / h, and its average value (82 + 85 + 83) ÷ 3 = 83.33 km / h is the vehicle speed characteristic information of this node time period. For the node time period from node 6 to node 8, the vehicle speed data are 88, 90, and 92 km / h, and the average value is (88 + 90 + 92) ÷ 3 = 90 km / h, which is the vehicle speed characteristic information of this node time period.

[0119] Obtain the time period duration parameters for each node time period during the second tracking period. For the node time period from node 3 to node 5, the initial node is 3 and the termination node is 5. For the node time period from node 6 to node 8, the initial node is 6 and the termination node is 8.

[0120] Store the time period duration parameters of each node time period and the vehicle speed characteristic information of the knowledge point of the vehicle speed to be controlled for the small car in each node time period into the cloud storage system. For the node time period from node 3 to node 5, store the initial node 3, the termination node 5, and the vehicle speed characteristic information of 83.33 km / h into the cloud storage system. For the node time period from node 6 to node 8, store the initial node 6, the termination node 8, and the vehicle speed characteristic information of 90 km / h into the cloud storage system.

[0121] For obtaining the time period characteristic parameters of the second tracking period and storing relevant information, assume that the second tracking period starts from node 3 corresponding to time point T5 and ends at node 12 corresponding to time point T6. The initial node is 3 and the termination node is 12. These are the time period characteristic parameters of the second tracking period. Assume that the vehicle speed characteristic information of the compact car during the entire second tracking period is 86 km / h (obtained by aggregating and calculating the vehicle speed data of all nodes during the entire second tracking period), and store the initial node 3, the termination node 12, and the vehicle speed characteristic information of 86 km / h in the cloud storage system. The information stored in the cloud storage system can provide the traffic control department with a comprehensive understanding of the vehicle speed of the compact car in the tunnel, so as to make vehicle speed control decisions, such as determining whether the compact car is driving at a safe speed in the tunnel and whether a vehicle speed adjustment prompt needs to be issued, etc.

[0122] In a possible implementation manner, after step S140, the method further includes:

[0123] Step S150, generating a speed control plan for the vehicle to be controlled based on the vehicle speed characteristic information of the vehicle to be controlled at the knowledge point of the vehicle speed to be controlled during the second tracking period.

[0124] In this embodiment, taking a long-distance bus driving on a specific section of the highway as an example, the control unit of this section controls the knowledge point of the vehicle speed to be controlled (the normal driving safe speed range is 60 - 100 km / h).

[0125] After determining the vehicle speed characteristic information of the long-distance bus at the knowledge point of the vehicle speed to be controlled during the second tracking period based on the target vehicle speed prediction plan, for example, the vehicle speed characteristic information is 75 km / h. Generate a speed control plan for the vehicle to be controlled (long-distance bus) based on this vehicle speed characteristic information.

[0126] If the vehicle speed characteristic information indicates that the speed of the long-distance bus, which is 75 km / h, is within the safe speed range (60 - 100 km / h) but close to the lower limit of 60 km / h, considering the overall traffic flow and efficiency of the highway, the speed control plan may include the following. Since the relatively low speed of the long-distance bus may have a certain impact on the normal driving of the following vehicles, the traffic control system can send a prompt message to the long-distance bus through the traffic control system, advising it to appropriately increase the speed on the premise of ensuring safety. The prompt message can be sent to the long-distance bus driver through the roadside electronic display or in-vehicle terminal device. At the same time, the control system will continuously monitor the speed change of the vehicle. If the speed does not increase to a reasonable range (such as 65 - 70 km / h) within a certain period of time (for example, 5 minutes), the traffic conditions around the bus will be further analyzed. If it is found that there is an obvious congestion accumulation of the vehicles behind the bus, in order to avoid the expansion of traffic jams, the control system can adjust the speed limit signs or traffic lights (if any) on the nearby sections to guide the following vehicles for reasonable diversion, such as guiding some vehicles to switch to other lanes or enter the nearby service area to wait.

[0127] If the vehicle speed characteristic information shows that the speed of the long-distance bus, which is 75 km / h, is close to the upper limit of 100 km / h of the safe speed range, the speed control plan will be different. Due to the certain safety risks associated with the relatively high speed, especially for a large vehicle like a long-distance bus, the control system will send a warning message to the bus, asking the driver to check the speed and ensure driving within the safe range. The warning message can also be sent through the roadside electronic display or in-vehicle terminal device. At the same time, the control system will increase the monitoring frequency of the vehicle, changing from obtaining the vehicle speed data every 10 minutes originally to every 5 minutes, so as to promptly detect abnormal changes in the vehicle speed. If the vehicle speed of the bus continues to remain at a level close to the upper limit or continues to increase, the control system will contact the bus operating company, asking the company to remind and educate the driver about safe driving, and if necessary, set up a temporary speed limit sign in front of the bus or guide the vehicle to enter the slow lane to ensure traffic safety on the highway.

[0128] Next, look at the situation of a freight truck driving on a specific slope section. The speed to be controlled is the safe speed (40 - 60 km / h) of this slope section. Suppose the vehicle speed characteristic information of the speed point to be controlled of the freight truck in the second tracking period determined based on the target vehicle speed prediction plan is 55 km / h.

[0129] Since the vehicle speed of 55 km / h is within the safe speed range, but considering the particularity of the slope section and the load situation of the freight truck, the speed control plan needs to be considered from multiple aspects. On the one hand, the control system will evaluate the speed stability of the freight truck. If it is found that although the vehicle speed is within the safe range, but the fluctuation is large (for example, it fluctuates frequently between 50 - 60 km / h), a prompt message will be sent to the truck driver to inform him / her to pay attention to the speed stability and avoid sudden acceleration or sudden braking to prevent dangerous situations such as the vehicle getting out of control on the slope section. The prompt message can be sent through the on-vehicle terminal device. On the other hand, the control system will formulate a control plan in combination with the traffic flow situation of the slope section. If it is found that there are many vehicles behind the lane where the freight truck is located, in order to avoid rear-end collisions, the control system can adjust the lane speed limit signs on the slope section to reduce the maximum speed limit of the vehicles behind, thereby increasing the safety distance between vehicles. At the same time, the control system will continuously monitor the status of the braking system of the freight truck (obtaining data by connecting with on-vehicle sensors). If it is found that there are abnormalities in the braking system (such as too high braking temperature or unstable braking pressure, etc.), even if the vehicle speed is within the safe range, an emergency warning message will be immediately sent to the truck driver, asking him / her to stop and check as soon as possible, and guiding the vehicle into the emergency stop lane if necessary.

[0130] If the vehicle speed characteristic information of the freight truck shows that the vehicle speed is 62 km / h, exceeding the upper limit of the safe speed range of 60 km / h. The speed control plan will first send a serious warning message to the truck driver, informing him / her that he / she has exceeded the speed limit and asking him / her to immediately reduce the vehicle speed. While the warning message is sent through the on-vehicle terminal device, the electronic display screen by the roadside will also display the speeding information of this vehicle to remind other vehicles to pay attention. The control system will immediately increase the monitoring frequency of this vehicle, changing from obtaining vehicle speed data every 15 minutes to obtaining it every 3 minutes to closely monitor the decrease in vehicle speed. If the truck driver does not respond to the warning message in time and the vehicle speed does not drop to the safe range within the specified time (for example, 2 minutes), the control system will contact the law enforcement department. Law enforcement officers can punish the truck through law enforcement equipment (such as speed cameras, etc.) set on the highway. At the same time, the control system will guide the surrounding vehicles to avoid, for example, by adjusting the traffic lights or electronic guiding signs in the nearby lanes to guide the surrounding vehicles to other safe lanes to avoid the speeding freight truck causing danger to other vehicles.

[0131] Taking a small car driving in a tunnel as an example, the speed to be controlled is the safe speed in the tunnel (80 - 100 km / h). Suppose the vehicle speed characteristic information of the small car to be controlled at the speed knowledge point in the second tracking period is 90 km / h.

[0132] Since the vehicle speed of 90 km / h is within the safe speed range, the speed control scheme mainly focuses on maintaining the safe driving of the vehicle in the tunnel. The control system will analyze the speed change trend of the compact car. If it is found that the vehicle speed has a gradually increasing trend, although it has not exceeded the safety limit yet, in order to avoid the risk of speeding in the tunnel, the control system will send a reminder message to the car driver, advising him / her to maintain a stable vehicle speed. The reminder message is sent through the in-vehicle terminal device. At the same time, the control system will adjust the control strategy in combination with environmental factors such as lighting and ventilation in the tunnel. If the ventilation in the tunnel is poor, which may affect the driver's vision and driving state, the control system will reduce the maximum speed limit in the tunnel (for example, from 100 km / h to 95 km / h) and send a notice to all vehicles in the tunnel, requiring the vehicles to drive according to the new speed limit. For the compact car, the control system will continuously monitor the distance between it and the vehicle in front. If it is found that the distance is too close (less than the safety distance standard), a warning message will be sent to the car driver, asking him / her to maintain a safe distance.

[0133] If the speed characteristic information of the compact car shows that the vehicle speed is 105 km / h, which exceeds the safe speed range. The speed control scheme will first send an emergency warning message to the car driver, asking him / her to decelerate immediately. While the warning message is sent through the in-vehicle terminal device, the electronic display screen in the tunnel will also display the speeding information of this vehicle to warn other vehicles. The control system will quickly increase the monitoring frequency of this vehicle, changing from obtaining the vehicle speed data every 8 minutes to obtaining it every 1 minute, and closely monitor the decrease in the vehicle speed. If the car driver does not decelerate in time and the vehicle speed is still higher than the safe range within the specified time (for example, 1 minute), the control system will take further measures. It will contact the tunnel management department to set up a speed bump or a temporary speed limit sign in the tunnel to force the car to decelerate. At the same time, the control system will guide other vehicles in the tunnel to avoid, for example, by adjusting the lane signal lights to guide other vehicles to the safe lane to prevent the speeding car from causing a collision risk to other vehicles.

[0134] Through the above process of generating a speed control scheme based on the speed characteristic information for different vehicle types in their respective driving scenarios, it can be seen that this control scheme based on the speed characteristic information can effectively ensure the driving safety of vehicles on the highway and improve the efficiency and accuracy of traffic management.

[0135] Figure 2 The hardware structure diagram of the highway vehicle speed control system 100 based on the control unit for implementing the above highway vehicle speed control method based on the control unit provided by the embodiment of the present invention is shown, as Figure 2As shown, the highway vehicle speed control system 100 based on a control unit may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

[0136] The machine-readable storage medium 120 may store data and / or instructions. In some embodiments, the machine-readable storage medium 120 may store data obtained from an external terminal. In some embodiments, the machine-readable storage medium 120 may store the data and / or instructions used by the highway vehicle speed control system 100 based on a control unit to execute or use to complete the exemplary methods described in the present invention.

[0137] In a specific implementation process, one or more processors 110 execute the computer-executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the highway vehicle speed control method based on a control unit as described in the above method embodiments. The processor 110, the machine-readable storage medium 120, and the communication unit 140 are connected through the bus 130, and the processor 110 may be used to control the transceiver actions of the communication unit 140.

[0138] For the specific implementation process of the processor 110, reference may be made to the various method embodiments executed by the highway vehicle speed control system 100 based on a control unit described above. Their implementation principles and technical effects are similar, and will not be elaborated here in this embodiment.

[0139] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When a processor executes the computer-executable instructions, the above highway vehicle speed control method based on a control unit is implemented.

[0140] It should be noted that, in order to simplify the description of the present invention disclosure and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, sometimes multiple features are merged into one embodiment, drawing, or description thereof.

Claims

1. A method for controlling the speed of vehicles on a highway based on a control unit, characterized in that: The method comprises: Acquire the tasks to be controlled of the target control unit of the target expressway section, wherein the tasks to be controlled include the vehicles to be controlled and the vehicle speed knowledge points to be controlled; If the speed knowledge point to be controlled of the vehicle to be controlled has speed data at the current tracking node, then based on the current tracking node, the end node of the first tracking period and the tracking period duration parameter, determine the speed distribution characteristic parameter of the speed knowledge point to be controlled of the vehicle to be controlled in the second tracking period corresponding to the current tracking node, the first tracking period being a previous tracking period of the second tracking period; Determining a target vehicle speed prediction scheme based on the vehicle speed distribution characteristic parameters of the vehicle speed knowledge point to be controlled during the second tracking period; The vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled within the second tracking period is determined based on the target vehicle speed prediction scheme.

2. The highway vehicle speed control method based on the control unit according to claim 1 is characterized in that: The determining, based on the current tracking node, the termination node of the first tracking period, and the tracking period duration parameter, of the vehicle speed distribution characteristic parameter of the vehicle speed knowledge point to be controlled within the second tracking period corresponding to the current tracking node includes: Determine a node interval without vehicle speed data based on the current tracking node and the end node of the first tracking period; Determining a vehicle speed distribution characteristic limit value based on the tracking period duration parameter and a predefined determination strategy; The speed distribution characteristic parameters of the to-be-controlled vehicle speed knowledge point within the second tracking period corresponding to the current tracking node are determined based on the node interval without vehicle speed data and the speed distribution characteristic limit value.

3. The highway vehicle speed control method based on the control unit according to claim 2 is characterized in that: The step of determining the vehicle speed distribution characteristic parameter of the vehicle speed knowledge point to be controlled within the second tracking period corresponding to the current tracking node based on the node interval without vehicle speed data and the vehicle speed distribution characteristic limit value comprises: Determine the number of nodes in the node interval without vehicle speed data, the uniformity characteristics of node distribution, and the proportion range of the node interval without vehicle speed data in the entire second tracking period, and generate a first analysis result; The first analysis result is preliminarily classified according to the vehicle speed distribution characteristic limit value, wherein if the number of nodes in the node interval without vehicle speed data is less than the node number threshold value set by the vehicle speed distribution characteristic limit value, the preliminary classification result is marked as the first category; if the uniformity characteristic of the node distribution in the node interval without vehicle speed data meets the uniformity standard set by the vehicle speed distribution characteristic limit value, the preliminary classification result is marked as the second category; if the proportion range of the node interval without vehicle speed data in the entire second tracking period is less than the proportion threshold value set by the vehicle speed distribution characteristic limit value, the preliminary classification result is marked as the third category, thereby outputting the preliminary classification result; Performing an integrated judgment on the preliminary classification results, if the preliminary classification results include the first category, the second category and the third category at the same time, performing a first integrated judgment logic, under which the relative position of the node interval without vehicle speed data in the entire second tracking period is further analyzed, if the node interval without vehicle speed data is located at the beginning of the second tracking period, outputting an integrated judgment result, marked as category A; if the node interval without vehicle speed data is located in the middle of the second tracking period, outputting another integrated judgment result, marked as category B; if the node interval without vehicle speed data is located at the end of the second tracking period, outputting a third integrated judgment result, marked as category C; and, if the preliminary classification results only include the first category and the second category, performing a second integrated judgment logic, and outputting a fourth integrated judgment result, marked as category D or category E according to the specific feature combination of the first category and the second category results; and, if the preliminary classification results only include the second category and the third category, performing a third integrated judgment logic, and outputting a corresponding integrated judgment result, marked as category F or category G according to the specific feature combination of the second category and the third category, and outputting a fifth integrated judgment result; A preliminary framework of vehicle speed distribution characteristic parameters is determined based on various integrated judgment results. If the integrated judgment result is Class A, a vehicle speed distribution characteristic parameter framework is constructed with the initial part without vehicle speed data as the influencing factor. The specific framework content includes the estimated factors of the influence of the initial part without vehicle speed data on the trend of subsequent vehicle speed data, and the estimated factors of the fluctuation range of subsequent vehicle speed data under the influence of the initial part without vehicle speed data; and if the integrated judgment result is Class B, a vehicle speed distribution characteristic parameter framework is constructed with the middle part without vehicle speed data as the focus factor. The specific framework content includes the middle part without vehicle speed data. The estimated factors of the impact of the speed data on the segmentation of the front and rear speed data, and the estimated factors of the correlation of the front and rear speed data when there is no speed data in the middle; and, if the integrated judgment result is Class C, a speed distribution characteristic parameter framework is constructed with the lack of speed data at the end as the focus of consideration. The specific framework content includes the estimated factors of the impact of the lack of speed data at the end on the integrity of the overall speed data, and the estimated factors of the proportion of valid data of the overall speed data when there is no speed data at the end; and, if the integrated judgment result is Class D, a speed distribution characteristic parameter based on the combined features of the first and second categories is constructed. The specific content of the framework includes the speed data change prediction factors corresponding to the feature combinations related to the first and second categories, and the interaction prediction factors between the speed data without and with the speed data under the feature combination; and, if the integrated judgment result is E, then another speed distribution feature parameter framework based on the first and second category combined features is constructed, and the specific content of the framework includes the speed data fluctuation correlation prediction factors corresponding to other combined features of the first and second categories, and the influence prediction factors of the speed data continuity without speed data under a specific combination; and, if the integrated judgment result is F, then a basic A vehicle speed distribution characteristic parameter framework based on the second and third category combined features, the specific framework content includes the vehicle speed data stability prediction factor corresponding to the feature combination related to the second and third categories, and the prediction factor of the influence of no vehicle speed data on the overall vehicle speed data trend under the feature combination; and, if the integrated judgment result is Class G, another vehicle speed distribution characteristic parameter framework based on the second and third category combined features is constructed, the specific framework content covers the vehicle speed data dynamic change prediction factor corresponding to other combination features of the second and third categories, and the prediction factor of the influence of no vehicle speed data on the extreme value of vehicle speed data under a specific combination; A further refinement operation is performed on each preliminary framework to generate a refined vehicle speed distribution characteristic parameter framework; wherein, if it is a framework with no vehicle speed data in the initial part as the focus, the refinement operation includes determining the specific degree of influence of the length of time without vehicle speed data in the initial part on the estimation factor, and the specific functional relationship between the no vehicle speed data in the initial part and the subsequent vehicle speed data; and, if it is a framework with no vehicle speed data in the middle part as the focus, the refinement operation includes determining the specific quantitative index of the influence of the no vehicle speed data in the middle part on the segmentation of the front and rear vehicle speed data, and the specific correlation function of the front and rear vehicle speed data under the segmentation without vehicle speed data in the middle; and, if it is a framework with no vehicle speed data in the ending part as the focus, the refinement operation includes determining the ending part A quantitative evaluation method for the impact of no speed data on the integrity of the overall speed data, and a specific calculation method for the proportion of valid data in the overall speed data when no speed data exists at the end; and, if it is a framework based on the first and second types of combined features, the refinement operation includes determining the specific calculation logic of the speed data change prediction factor under the first and second types of related feature combinations, and a quantitative model for the interaction between the speed data without speed data and the speed data with the feature combination; and, if it is a framework based on the second and third types of combined features, the refinement operation includes determining the specific numerical range of the speed data stability prediction factor under the second and third types of related feature combinations, and the quantitative relationship of the impact of no speed data on the overall speed data trend under the feature combination; The final vehicle speed distribution characteristic parameters are determined based on the refined vehicle speed distribution characteristic parameter framework, wherein, for each refined vehicle speed distribution characteristic parameter framework, if it is a framework with no vehicle speed data related to the initial part, the average vehicle speed characteristic parameters under the influence of no vehicle speed data in the initial part and the vehicle speed fluctuation range characteristic parameters under the influence of no vehicle speed data in the initial part are determined according to the refined content; and if it is a framework with no vehicle speed data related to the middle part, the front and rear vehicle speed difference characteristic parameters under the segmentation of no vehicle speed data in the middle part and the vehicle speed dispersion characteristic parameters under the segmentation of no vehicle speed data in the middle part are determined. ; and, if it is a framework related to the end part without vehicle speed data, determine the overall vehicle speed deviation characteristic parameters when there is no vehicle speed data at the end part, and the vehicle speed extreme value characteristic parameters when there is no vehicle speed data at the end part; and, if it is a framework based on the first and second types of combined features, determine the comprehensive change rate characteristic parameters of the speed data under the combined features, and the speed data correction coefficient characteristic parameters under the combined features; and, if it is a framework based on the second and third types of combined features, determine the speed data stability adjustment parameters under the combined features, and the speed data trend correction characteristic parameters under the combined features.

4. The highway vehicle speed control method based on the control unit according to any one of claims 1 to 3, characterized in that: The method of determining a target vehicle speed prediction scheme based on the vehicle speed distribution characteristic parameters of the vehicle speed knowledge point to be controlled within the second tracking period includes: If the speed distribution characteristic parameter of the to-be-controlled speed knowledge point in the second tracking period is discrete, outputting the first target speed prediction scheme among the plurality of target speed prediction schemes defined previously as the target speed prediction scheme, the first target speed prediction scheme comprising: ignoring the node interval without speed data, and summarizing and calculating the speed data of the to-be-controlled speed knowledge point in the current tracking period; If the vehicle speed distribution characteristic parameters of the vehicle speed knowledge point to be controlled in the second tracking period are concentrated, the second target vehicle speed prediction scheme among the multiple target vehicle speed prediction schemes previously defined will be output as the target vehicle speed prediction scheme, and the second target vehicle speed prediction scheme includes: comprehensively calculating the vehicle speed data of the vehicle speed knowledge point to be controlled in the previous tracking period, the vehicle speed data of the vehicle speed knowledge point to be controlled corresponding to the current tracking node, and the vehicle speed data of the vehicle speed knowledge point to be controlled corresponding to the candidate tracking period; the candidate tracking period is a tracking period composed of the tracking trigger node of the previous tracking period to the tracking trigger node of the current tracking period.

5. The highway vehicle speed control method based on the control unit according to claim 4 is characterized in that: The target vehicle speed prediction scheme is the first target vehicle speed prediction scheme, and determining the vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled within the second tracking period based on the target vehicle speed prediction scheme includes: Acquire, from the cloud storage system, a first time period duration parameter corresponding to the interval of the node without vehicle speed data of the vehicle speed knowledge point to be controlled within the second tracking time period; Acquire the vehicle speed data of the to-be-controlled vehicle speed knowledge point of the second time period continuous parameter from the cloud storage system, where the second time period continuous parameter is each time period continuous parameter in the second tracking time period except the first time period continuous parameter; The vehicle speed data of the to-be-controlled vehicle speed knowledge point of the second time period duration parameter are summarized and calculated to generate vehicle speed characteristic information of the to-be-controlled vehicle speed knowledge point during the second tracking period.

6. The highway vehicle speed control method based on the control unit according to claim 4 is characterized in that: The target vehicle speed prediction scheme is the second target vehicle speed prediction scheme, and determining the vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled within the second tracking period based on the target vehicle speed prediction scheme includes: Acquire the first vehicle speed data of the vehicle speed knowledge point to be controlled in the first tracking period from the cloud storage system, and acquire the second vehicle speed data of the vehicle speed knowledge point to be controlled at the current tracking node; Determine a candidate tracking period based on the tracking trigger node of the first tracking period and the tracking trigger node of the second tracking period, and determine the third vehicle speed data of the to-be-controlled vehicle speed knowledge point in the candidate tracking period; The first vehicle speed data, the second vehicle speed data and the third vehicle speed data are comprehensively calculated to generate vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled during the second tracking period.

7. The highway vehicle speed control method based on the control unit according to claim 5 or 6, characterized in that: The method further comprises: Determining vehicle speed characteristic information of the vehicle to be controlled at each node time period of the vehicle speed knowledge point to be controlled within the second tracking time period; Acquire a period duration parameter of each node period in the second tracking period, wherein the period duration parameter includes an initial node and an end node; The time period duration parameter of each node time period and the vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled within each node time period are stored in the cloud storage system.

8. The highway vehicle speed control method based on the control unit according to claim 5 or 6, characterized in that: The method further comprises: Acquire a period characteristic parameter of the second tracking period, wherein the period characteristic parameter includes an initial node and an end node; The time period characteristic parameters of the second tracking time period and the vehicle speed characteristic information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled during the second tracking time period are stored in the cloud storage system.

9. The highway vehicle speed control method based on the control unit according to claim 1, characterized in that: After the step of determining the vehicle speed characteristic information of the vehicle speed knowledge point to be controlled within the second tracking period based on the target vehicle speed prediction scheme, the method further includes: A speed control plan for the vehicle to be controlled is generated based on the vehicle speed feature information of the vehicle to be controlled at the vehicle speed knowledge point to be controlled during the second tracking period.

10. A highway vehicle speed control system based on a control unit, characterized in that: The highway vehicle speed control system based on the control unit includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the highway vehicle speed control method based on the control unit as described in any one of claims 1 to 9 above.

Images