Remote operation and maintenance management platform for safe driving of intelligent motorcade

Abstract

The invention relates to the technical field of motorcade driving management, in particular to a remote operation and maintenance management platform for safe driving of an intelligent motorcade. The platform comprises a broken line graph construction unit used for collecting driving data and GPS data of each vehicle and obtaining a driving broken line graph and a GPS broken line graph respectively; the target vehicle acquisition unit is used for respectively acquiring a first characteristic value sequence and a second characteristic value sequence according to the driving broken line graph and the GPS broken line graph of one vehicle, obtaining a difference characteristic value sequence and further judging whether the vehicle is a target vehicle or not; the target moment determining unit is used for acquiring a to-be-corrected moment of the target vehicle and then judging whether the to-be-corrected moment is a target moment or not; and the correction unit is used for classifying the target moments according to the distribution characteristics of the target moments of one vehicle, and correcting the GPS data of the target moments according to the classified result. According to the invention, the GPS data in the driving process of the motorcade vehicles can be corrected.

Description

Technical Field

[0001] The present invention relates to the technical field of fleet driving management, and in particular to a remote operation and maintenance management platform for the safe driving of intelligent fleets. Background Art

[0002] With the development of intelligent transportation and connected vehicle technologies, fleet management is accelerating its upgrade towards intelligent and remote management. Building an intelligent fleet safe driving remote operation and maintenance management platform that integrates positioning monitoring, driving behavior analysis, fault warning, and task scheduling has become a key means of improving operational efficiency and ensuring driving safety. Within this platform, GPS positioning data, as core fundamental information, is widely used for functions such as trajectory playback, boundary crossing alarms, and route optimization. Its accuracy is directly related to the stability of system operations and the effectiveness of decision-making. However, due to factors such as signal obstruction and multipath interference, GPS drift often occurs while vehicles are moving or stationary, leading to positioning jumps, trajectory anomalies, and other issues. This can lead to safety and management errors such as misjudged stops and false boundary crossings. Therefore, improving the accuracy of positioning information is crucial for ensuring safe driving and remote operation and maintenance of fleets.

[0003] While existing filtering methods can correct for GPS data drift, most still have limitations in practical applications. Some rely solely on fixed distance thresholds or simple filtering algorithms, making them difficult to adapt to real-world driving environments and prone to misjudgment or correction failure. For example, traditional models like the Kalman filter rely heavily on fixed parameters when filtering GPS data, lacking the ability to dynamically respond to and incorporate vehicle conditions. This results in unstable corrections in complex scenarios and makes it difficult to guarantee accuracy after correction. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a remote operation and maintenance management platform for the safe driving of intelligent fleets. The technical solutions adopted are as follows: One embodiment of the present invention provides a remote operation and maintenance management platform for safe driving of an intelligent fleet, the platform comprising: A line graph construction unit is used to collect driving data and GPS data of each vehicle; and obtain a driving line graph and a GPS line graph based on the driving data and GPS data of a vehicle respectively; A target vehicle acquisition unit is configured to respectively acquire a first eigenvalue sequence and a second eigenvalue sequence based on a vehicle's travel line graph and GPS line graph; the absolute values ​​of the differences between the elements at corresponding moments in the first and second eigenvalue sequences form a difference eigenvalue sequence; and the difference eigenvalue sequence of a vehicle is used to determine whether the vehicle is a target vehicle. A target time determination unit is configured to obtain a time to be corrected of a target vehicle based on a sequence of difference characteristic values ​​of the target vehicle; and to determine whether the time to be corrected is a target time based on two adjacent times to the time to be corrected; The correction unit is used to classify the target time according to the distribution characteristics of the target time of a vehicle, and correct the GPS data of the target time according to the classification result.

[0005] Preferably, the driving data includes the vehicle's speed, acceleration and driving direction.

[0006] Preferably, obtaining a driving line graph and a GPS line graph based on driving data and GPS data of a vehicle respectively includes: The vehicle's driving direction at the previous moment is used as the reference direction at that moment. The displacement between the two moments is obtained based on the vehicle speed at that moment and the acceleration at the next moment. The deflection angle of the vehicle's driving direction at that moment relative to its reference direction is also obtained. Similarly, the displacement between each two moments and the deflection angle of the vehicle's driving direction at each moment relative to its reference direction are obtained. A driving line graph is then obtained with each moment as a node. The length of the line between two moments in the driving line graph represents the displacement distance between the two moments. The longitude and latitude coordinates of a vehicle at each moment are obtained based on the GPS data of the vehicle at each moment during its travel, and two adjacent longitude and latitude coordinates are connected by a line segment to obtain a GPS line graph of the vehicle.

[0007] Preferably, obtaining the first eigenvalue sequence and the second eigenvalue sequence respectively according to a driving line graph and a GPS line graph of a vehicle includes: The nodes other than the first and last nodes in the driving line graph are taken as the vertices of the angles; the lines between a vertex and the two adjacent nodes are obtained, with the line on the right as the starting edge and the line on the left as the ending edge, and the angle from the starting edge to the ending edge is calculated in a counterclockwise direction and recorded as the angle value of the vertex at the corresponding time; the angle values ​​of each vertex at the corresponding time in the driving line graph constitute the first eigenvalue sequence; similarly, the second eigenvalue sequence is obtained based on the GPS line graph.

[0008] Preferably, determining whether a vehicle is a target vehicle by using a difference feature value sequence of the vehicle includes: The average value of the elements in the difference characteristic value sequence of a vehicle is calculated and multiplied by the maximum value in the sequence to obtain the multiplication result. The multiplication result is normalized to obtain the necessity of vehicle correction; if the necessity of vehicle correction of the vehicle is greater than the judgment threshold, the vehicle is considered a target vehicle.

[0009] Preferably, obtaining the time to be corrected of the target vehicle according to the difference characteristic value sequence of the target vehicle includes: If the normalized value of the square of the difference characteristic value corresponding to a moment in the difference characteristic value sequence of the target vehicle is greater than the judgment threshold, then the moment is the moment to be corrected.

[0010] Preferably, determining whether a time to be corrected is a target time based on two adjacent times to a time to be corrected includes: If there is at least one non-to-be-corrected time between the two adjacent times to be corrected, then the to-be-corrected time is not the target time. Otherwise, the to-be-corrected time is the target time, and all times except the target time are normal times.

[0011] Preferably, the target time is classified according to the distribution characteristics of the target time of a vehicle, including: The target moments where both adjacent moments are normal moments are recorded as the first category; the target moments where the continuous distribution is continuous and both ends of the target moments are normal moments are recorded as the second category; the target moments where the continuous distribution is continuous and only one end of the two ends of the target moments is a normal moment are recorded as the third category.

[0012] Preferably, the GPS data at the target time is corrected according to the classification result, including: If the target moment is the first category, a two-dimensional coordinate system is established with the vehicle driving direction at the previous adjacent moment as the horizontal axis, the latitude and longitude of the vehicle at the previous adjacent moment as the origin, and the vertical axis perpendicular to the horizontal axis. In the two-dimensional coordinate system, the displacement between the previous adjacent moment and the target moment is decomposed to obtain two component displacements, and the two component displacements are converted into longitude and latitude, which are recorded as the reference longitude and reference latitude corresponding to the previous adjacent moment. Similarly, the reference longitude and reference latitude corresponding to the next adjacent moment are obtained; an exponential function with a natural constant as the base is used to decompose the displacement between the previous adjacent moment and the target moment. The normalized value of the square of the difference eigenvalue of the moment is negatively correlated to obtain the mapping value corresponding to the previous adjacent moment, and similarly obtain the mapping value corresponding to the next adjacent moment; the mapping value corresponding to the previous adjacent moment divided by the sum of the mapping values ​​corresponding to the previous adjacent moment and the next adjacent moment is the weight corresponding to the previous adjacent moment, and similarly obtain the weight corresponding to the next adjacent moment; the weights corresponding to the previous adjacent moment and the next adjacent moment are used to perform weighted summation on the reference longitudes corresponding to the previous adjacent moment and the next adjacent moment to obtain the corrected longitude corresponding to the target moment, and similarly obtain the corrected latitude corresponding to the target moment; For the third type of target moment, the normal moment at one end of the third type of target moment is used as the reference moment; the third type of target moment is marked as the first target moment, the second target moment, the third target moment in order from the reference moment to the target moment, until the last target moment is marked as the end target moment; the reference longitude and reference latitude corresponding to the reference moment are obtained according to the longitude and latitude of the vehicle at the reference moment and the displacement between the first target moment and the reference moment, as the corrected longitude and corrected latitude of the first target moment; the reference longitude and reference latitude corresponding to the first target moment are obtained according to the corrected longitude and corrected latitude of the first target moment and the displacement between the first target moment and the second target moment, as the corrected longitude and corrected latitude of the second target moment, and so on, to obtain the corrected longitude and corrected latitude of each target moment in the third type of target moment; For the second type of target moment, the normal moments at both ends of the second type of target moment are recorded as the first reference moment and the second reference moment respectively; the order from the first reference moment to the target moment is recorded as the forward order, and the order from the second reference moment to the target moment is recorded as the reverse order; the method of obtaining the corrected longitude and corrected latitude of the target moment by using the third type of target moment is to obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in the forward order starting from the first reference moment, and similarly, obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in the reverse order starting from the second reference moment. The reverse corrected longitude and reverse corrected latitude of the moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment of a target moment in the second type of target moment are obtained according to the weight method corresponding to the previous adjacent moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment are used to weightedly sum the forward corrected longitude and the reverse corrected longitude of a target moment to obtain the corrected longitude of the target moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment are used to weightedly sum the forward corrected dimension and the reverse corrected dimension of a target moment to obtain the corrected dimension of the target moment.

[0013] The embodiments of the present invention have at least the following beneficial effects: the present application collects the driving data and GPS data of each vehicle, obtains the corresponding driving line graph and GPS line graph respectively, and then obtains the difference characteristic value sequence of the vehicle based on the comparative analysis of the driving line graph and the GPS line graph of a vehicle, judges whether the GPS data of the vehicle needs to be corrected, and then obtains the vehicle that needs to be corrected, that is, the target vehicle, to reduce the subsequent calculation amount; further, the time to be corrected of the target vehicle is obtained through the difference characteristic value sequence of the target vehicle, and judges whether the time to be corrected is the target time based on the adjacent times before and after the target vehicle, and further locks the time when the GPS data needs to be corrected to achieve the effect of accurate correction; finally, a target vehicle of a vehicle is classified according to its distribution characteristics, and then the GPS data of the target time is corrected according to the classification results, thereby improving the accuracy of the vehicle GPS data, etc., so as to facilitate the subsequent remote management of the vehicle data, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A schematic diagram of the architecture of a remote operation and maintenance management platform for safe driving of an intelligent fleet provided by an embodiment of the present invention; Figure 2 A schematic line chart of a remote operation and maintenance management platform for safe driving of an intelligent fleet provided by an embodiment of the present invention; Figure 3 A schematic diagram of a line chart angle of a remote operation and maintenance management platform for safe driving of an intelligent fleet provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of a remote operation and maintenance management platform for safe driving of intelligent fleets proposed in accordance with the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The following describes in detail a specific solution of a remote operation and maintenance management platform for safe driving of an intelligent vehicle fleet provided by the present invention with reference to the accompanying drawings.

[0019] Embodiment: The main application scenario of the present invention is to build an adaptive and robust GPS drift correction system to improve the accuracy of positioning data and provide solid data support for fleet safety driving and remote operation and maintenance management.

[0020] See also Figure 1 , which shows a schematic diagram of the architecture of a remote operation and maintenance management platform for safe driving of an intelligent fleet provided by an embodiment of the present invention. The platform includes the following units: The line graph construction unit is used to collect the driving data and GPS data of each vehicle; and obtain a driving line graph and a GPS line graph based on the driving data and GPS data of a vehicle.

[0021] In the remote operation and maintenance management platform for safe driving of smart fleets, the platform comprehensively perceives the vehicle's operating status through on-board terminals and multiple types of sensor equipment, and uploads data to the cloud or dispatch center in real time through the 4G / 5G communication network to facilitate subsequent operation and maintenance management of the vehicle.

[0022] Furthermore, it is necessary to collect vehicle driving data, which includes vehicle speed, acceleration, and direction. This allows the speed, acceleration, and direction (i.e., the vehicle's orientation) to be determined at each moment. Since the time between moments is relatively short, the acceleration at one moment is the average acceleration between the previous moment and the vehicle's on-board device (OBD) interface or inertial measurement unit (IMU), while the vehicle's direction is provided by a gyroscope or electronic compass. Furthermore, GPS data must be collected at each moment, using a high-precision satellite positioning module. It is important to note that driving data and GPS data are collected at the same frequency. The platform analyzes and processes this collected data to improve vehicle positioning accuracy, facilitating subsequent remote vehicle operation and maintenance management.

[0023] In the remote operation and maintenance management platform for safe driving in intelligent fleets, GPS positioning data is the foundation for key functions such as vehicle trajectory monitoring, driving behavior analysis, and operational scheduling. However, during actual driving, GPS data collected by vehicles can drift due to various factors, such as obstruction by tall buildings, electromagnetic interference, signal reflections under tunnels or overpasses, and weak or insufficient satellite signals. These interferences can cause instantaneous positioning point offsets, jumps, or trajectory discontinuities, affecting the platform's accurate assessment of the vehicle's actual position and operating status. This can lead to problems such as false boundary violations, abnormal alarms, and trajectory deviation analysis errors, reducing the platform's operational reliability and scheduling accuracy.

[0024] Therefore, in the remote operation and maintenance management of fleets, improving the accuracy and stability of GPS data is of great significance to ensuring driving safety and efficient operation and maintenance.

[0025] In order to verify and correct the accuracy of the vehicle's GPS data, the data collected by any vehicle is analyzed as an example.

[0026] Furthermore, a corresponding driving line graph is obtained based on the driving data of a vehicle to represent its driving trajectory. Specifically, the driving direction of a vehicle at a moment before a moment is taken as the reference direction of the moment, and then the displacement between the two moments is obtained based on the vehicle speed at the moment and the acceleration at the next moment, and the deflection angle of the vehicle driving direction at the moment relative to its reference direction is obtained. Similarly, the displacement between each two moments and the deflection angle of the vehicle driving direction at each moment relative to its reference direction are obtained, and then a driving line graph is obtained with each moment as a node. The length of the line between the two moments in the driving line graph represents the displacement distance between the two moments. The driving line graph is as follows: Figure 2 shown.

[0027] In the figure, tn represents the nth moment, that is, the n+1th moment. For example, t0, t1, t2 and t3 represent the initial moment, the first moment, the second moment and the third moment in the vehicle collection data, that is, the first moment, the second moment, the third moment and the fourth moment.

[0028] atn represents the deflection angle of the vehicle's direction at time tn relative to the reference direction, using the vehicle's direction at the moment before time n as the reference direction. at1 represents the deflection angle of the vehicle's direction at time 1 relative to the reference direction (i.e., the vehicle's direction at the initial moment). X_tn represents the vehicle's displacement during the period between time n and the moment before it, while X_t1 represents the vehicle's displacement during the period between time 1 and the moment before it (i.e., the initial moment). at2 represents the deflection angle of the vehicle's direction at time 2 relative to the reference direction, using the vehicle's direction at time 1 as the reference direction. at3 represents the deflection angle of the vehicle's direction at time 3 relative to the reference direction, using the vehicle's direction at time 2 as the reference direction. This creates a line graph of the vehicle's movement.

[0029] Similarly, based on the GPS data of a vehicle at each sampling moment during its driving process, the corresponding longitude and latitude coordinates can be obtained. Adjacent longitude and latitude coordinates are connected by line segments to form a line graph, which is recorded as a GPS line graph. Each node in the two line graphs corresponds to each moment.

[0030] The target vehicle acquisition unit is used to respectively obtain a first eigenvalue sequence and a second eigenvalue sequence based on a vehicle's driving line graph and GPS line graph; the absolute values ​​of the differences between the elements at corresponding moments in the first and second eigenvalue sequences constitute a difference eigenvalue sequence; and the difference eigenvalue sequence of a vehicle is used to determine whether the vehicle is a target vehicle.

[0031] Based on the driving data and GPS data of each vehicle during its driving process, the driving line graph and GPS line graph corresponding to each vehicle are obtained respectively. If the GPS data collected during the driving process of a vehicle is relatively accurate, then the GPS line graph obtained through the GPS data and the driving line graph obtained during the vehicle's driving process will theoretically have a high degree of similarity and consistency. This is because when the actual driving position of the vehicle shifts, the corresponding collected GPS data should also shift. If the actual driving position of the vehicle shifts and the shift reflected by the collected GPS data is inconsistent, then it may indicate that the GPS data has drifted or other inaccuracies. At this time, it may be necessary to correct the GPS data of the vehicle.

[0032] Because not every vehicle's GPS data will drift during driving, unnecessary corrections to GPS data that has no deviation or has deviations within a controllable range may increase the system's computational load and time. Therefore, corrections only need to be made to GPS data that may have drifted.

[0033] Take a vehicle's driving line graph and GPS line graph as an example. Each node in the driving line graph is the vertex of an angle (excluding the nodes corresponding to the initial moment and the nodes corresponding to the last moment). Get the line between a vertex and the two adjacent nodes in front and behind. Take the line on the right as the starting edge and the line on the left as the ending edge. Calculate the angle from the starting edge to the ending edge in a counterclockwise direction and record it as the angle value of the vertex at the corresponding moment. The angle value of each vertex in the driving line graph at the corresponding moment constitutes the first eigenvalue sequence. Figure 3 As shown in the figure, T_2 represents the angle value of the vertex corresponding to time t2 in the driving line graph, which is used as the feature value of the vertex corresponding to the time. Similarly, the second feature value sequence is obtained based on the GPS line graph.

[0034] Then, the elements in the first eigenvalue sequence and the second eigenvalue sequence corresponding to a vehicle are aligned according to the sampling timestamp, and then the absolute value of the difference between the elements at the corresponding moments in the first and second eigenvalue sequences is obtained, that is, the absolute value of the difference between the two eigenvalues ​​at the same sampling moment, and then the absolute value of the difference between the elements at the corresponding moments in the first and second eigenvalue sequences are combined into a difference eigenvalue sequence, and each element in the sequence is a difference eigenvalue.

[0035] Then, the GPS data of a vehicle is analyzed based on the difference characteristic value sequence corresponding to the vehicle to determine whether correction is necessary.

[0036] Specifically, the average value of the elements in the difference eigenvalue sequence is obtained, and multiplied by the maximum value in the sequence to obtain a multiplication result, and the multiplication result is normalized to obtain the necessity of vehicle correction.

[0037] The specific calculation model for the necessity of vehicle correction is: ,

[0038] Among them, N is the vehicle correction necessity of a vehicle, which is used to indicate whether the GPS data collected by the vehicle needs to be corrected. The larger the value, the greater the necessity of correction. norm represents the linear normalization function used for normalization, m represents the number of sampling moments of the vehicle, and m-2 represents the number of elements in the difference eigenvalue sequence. represents the i-th difference characteristic value in the difference characteristic value sequence corresponding to the vehicle, Represents the difference characteristic value sequence corresponding to the vehicle, and max() represents the maximum function. It represents the mean of all difference eigenvalues ​​in the difference eigenvalue sequence corresponding to the vehicle. The larger the value, the greater the deviation between the vehicle's GPS data and its actual running trajectory. The greater the possibility of GPS data drift, the greater the necessity of correcting the vehicle's GPS data. It represents the maximum value in the difference feature value sequence. The larger the value, the higher the possibility that the vehicle's GPS data may contain abnormal GPS data such as drift, and the higher the necessity of correction.

[0039] Furthermore, a judgment threshold G is set, and its value is set to 0.2 (an empirical value, which is determined according to the GPS usage requirements collected during vehicle operation and maintenance management under actual circumstances. If the vehicle positioning accuracy requirement is higher, the threshold is set to a smaller value. Otherwise, it can be increased, that is, the positioning accuracy is allowed to be within an acceptable range).

[0040] Finally, if N>G, that is, the necessity of vehicle correction is greater than the judgment threshold, it means that the GPS data of the vehicle may be biased and needs to be corrected. Otherwise, the correction operation for subsequent analysis will not be performed, and the vehicle whose necessity of vehicle correction is greater than the judgment threshold will be recorded as the target vehicle.

[0041] The target time determination unit is used to obtain the time to be corrected of the target vehicle according to the difference characteristic value sequence of the target vehicle; and judge whether the time to be corrected is the target time based on two adjacent times of the time to be corrected.

[0042] Because the GPS data in the target vehicle may have some deviations, while some data may be normal, that is, data within the allowable deviation range, therefore, only the GPS data that may be outside the allowable deviation range needs to be corrected.

[0043] In order to obtain GPS data of target vehicles that may be out of the deviation range for correction, and to obtain normal GPS data as a reference for GPS data that needs correction, it is necessary to sequentially traverse the difference feature value sequence corresponding to each target vehicle to obtain the sampling time that needs correction.

[0044] Specifically, a ternary expression is constructed based on each difference feature value in the difference feature sequence, specifically: , in, It is the judgment result of the i-th moment in the difference feature sequence, indicating whether the GPS data at the i-th moment needs to be corrected. If correction is required, the result is Ttue (true), and if not, the result is False (false). represents the square of the difference characteristic value corresponding to the i-th moment in the difference characteristic sequence, and G represents the judgment threshold. Based on the above, the GPS data corresponding to the sampling time marked as Ttue is used as the data moment that may require correction for the current target vehicle, i.e., the pending correction time. In other words, if the normalized square of the difference characteristic value corresponding to a moment in the difference characteristic value sequence of the target vehicle is greater than the judgment threshold, that moment is considered the pending correction time.

[0045] Because a positioning deviation at one of the moments to be corrected may cause the calculation of the angle characteristic values ​​of the moments before and after it, resulting in the false appearance of positioning deviation. Therefore, the time points corresponding to the moment to be corrected generally appear at least two times consecutively.

[0046] Whether a time to be corrected is a target time is determined based on two adjacent times. If one or more of the two adjacent times is not a target time, the time to be corrected is not a target time. Otherwise, the time to be corrected is a target time. If the time to be corrected is not a target time, the GPS data corresponding to the time to be corrected is considered normal GPS data and does not require correction.

[0047] The to-be-corrected moments that are not target moments are filtered out, and the remaining to-be-corrected moments are target moments. For sampling moments, all moments except the target moments are recorded as normal moments.

[0048] The correction unit is used to classify the target time according to the distribution characteristics of the target time of a vehicle, and correct the GPS data of the target time according to the classification result.

[0049] The target times vary in their distribution characteristics across the entire time series, requiring different correction methods. Therefore, target times must be classified based on their distribution characteristics. Specifically, target times with two adjacent moments being normal are classified as the first category; target times with continuously distributed moments and both ends being normal are classified as the second category; and target times with continuously distributed moments and only one end being normal is classified as the third category. Continuous distribution refers to a continuous distribution over the time series.

[0050] Furthermore, the GPS data corresponding to the three types of target moments are corrected respectively. Specifically, if the target moment is the first type, a two-dimensional coordinate system is established with the vehicle driving direction at the previous adjacent moment before the target moment as the horizontal axis, the latitude and longitude of the vehicle at the previous adjacent moment before the target moment as the origin, and the vertical axis perpendicular to the horizontal axis. In the two-dimensional coordinate system, the displacement between the previous adjacent moment and the target moment is decomposed to obtain two component displacements, and the two component displacements are converted into longitude and latitude, which are recorded as the reference longitude and reference latitude corresponding to the previous adjacent moment. Similarly, the reference longitude and reference latitude corresponding to the next adjacent moment are obtained; an exponential function with a natural constant as the base is used to decompose the displacement between the previous adjacent moment and the target moment. The normalized value of the square of the difference eigenvalue of the adjacent moments is negatively correlated to obtain the mapping value corresponding to the previous adjacent moment, and similarly, the mapping value corresponding to the next adjacent moment is obtained; the mapping value corresponding to the previous adjacent moment divided by the sum of the mapping values ​​corresponding to the previous adjacent moment and the next adjacent moment is the weight corresponding to the previous adjacent moment, and similarly, the weight corresponding to the next adjacent moment is obtained; the weights corresponding to the previous adjacent moment and the next adjacent moment are used to perform weighted summation on the reference longitudes corresponding to the previous adjacent moment and the next adjacent moment to obtain the corrected longitude corresponding to the target moment, and similarly, the corrected dimension corresponding to the target moment is obtained.

[0051] The calculation model of the weight corresponding to the next adjacent moment is specifically as follows: , in, is the weight corresponding to the sth moment in the adjacent moments before and after the target moment t belonging to the first category, indicating the reliability of the latitude and longitude information of the sth moment for predicting the target moment; e represents a natural constant, The square of the difference characteristic value corresponding to the sth moment between the adjacent moments. The smaller the value, the higher the accuracy of the GPS data at that moment. This may also indirectly reflect that the accuracy of the GPS data at the normal moment adjacent to the target moment is higher. Therefore, the smaller the value, the higher the accuracy of the GPS data at the normal moment adjacent to the target moment. This means that the GPS data corresponding to the reference time (the adjacent time before and after) selected at the target time is more reliable when used as a reference. The difference eigenvalue is obtained from the corresponding difference eigenvalue sequence. norm represents the normalization function. Indicates the number of adjacent moments, which is 2; It means that the reliability of the predicted longitude and latitude information at the sth moment in the previous or next adjacent moment corresponding to the target moment t in the current analysis vehicle is normalized to obtain its weight.

[0052] For the third type of target time, only one of the two ends of the continuously distributed target time has a normal time, that is, only the GPS data at the normal time at one end does not need to be corrected and is accurate. Therefore, the GPS data of this type of target time can only be corrected using the GPS data at the normal time at one end. The third type of target time can only be continuously distributed at the beginning or end of the time series. For example, if the starting time is the target time, and four consecutive times from the starting time are target times, and the fifth is a normal time, then the first target time to the fifth time are the third type of target time.

[0053] Specifically, the normal moment at one end of the third type of target moment is used as the reference moment; the third type of target moment is marked as the first target moment, the second target moment, the third target moment in order from the reference moment to the target moment, until the last target moment is marked as the end target moment; the reference longitude and reference latitude corresponding to the reference moment are obtained according to the longitude and latitude of the vehicle at the reference moment and the displacement between the first target moment and the reference moment, as the corrected longitude and corrected latitude of the first target moment; the reference longitude and reference latitude corresponding to the first target moment are obtained according to the corrected longitude and corrected latitude of the first target moment and the displacement between the first target moment and the second target moment, as the corrected longitude and corrected latitude of the second target moment, and so on, to obtain the corrected longitude and corrected latitude of each target moment in the third type of target moment.

[0054] For example, the distribution arrangement of the third type of target moments is normal moment, target moment 1, target moment 2, target moment 3, and target moment 4. Then the normal moment is the reference moment, target moment 1, target moment 2, target moment 3, and target moment 4 are the first target moment, the second target moment, the third target moment, and the fourth target moment. According to the longitude and latitude of the vehicle at the reference moment and the displacement between the first target moment and the reference moment, the reference longitude and reference latitude corresponding to the reference moment are obtained as the corrected longitude and corrected latitude of the first target moment. Similarly, the corrected longitude and corrected latitude of the first target moment, the second target moment, the third target moment, and the fourth target moment can be obtained.

[0055] For the second type of target time, since there are normal times at both ends of the continuously distributed target time, it is necessary to use these two normal times to correct the GPS data of the target time in the middle from both ends, and then combine the correction results at both ends to obtain the final prediction result.

[0056] Specifically, the normal moments at both ends of the second type of target moment are recorded as the first reference moment and the second reference moment respectively; the order from the first reference moment toward the target moment is recorded as the forward order, and the order from the second reference moment toward the target moment is recorded as the reverse order; the method of obtaining the corrected longitude and corrected latitude of the target moment by using the third type of target moment is to obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in forward order starting from the first reference moment, and similarly, obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in reverse order starting from the second reference moment. Reversely corrected longitude and reversely corrected latitude; according to the method for obtaining the weight corresponding to the previous adjacent moment, respectively obtain the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment of a target moment in the second type of target moment; use the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment to weightedly sum the forward corrected longitude and the reverse corrected longitude of a target moment to obtain the corrected longitude of the target moment; use the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment to weightedly sum the forward corrected dimension and the reverse corrected dimension of a target moment to obtain the corrected dimension of the target moment.

[0057] In essence, the correction method for GPS data of the second type of target moment is a combination of the correction methods of the first type of target moment and the second type of target moment, because there is a normal time GPS data at each end of a continuously distributed target moment that can be used as a reference for correction. For example, the distribution of the third type of target moment is arranged as normal time 1, target time 1, target time 2, target time 3, and normal time 2. Normal time 1 and normal time 2 are the first reference time and the second reference time respectively. The order of the first reference time, target time 1, target time 2, and target time 3 is in forward order, and the order of normal time 2, target time 3, target time 2, and target time 1 is in reverse order. At this time, the method for obtaining the corrected longitude and corrected latitude of the target moment in the third type of target moment can be used. Starting from the first reference time, in forward order, the forward corrected longitude and forward corrected latitude of target time 1, target time 2, and target time 3 can be obtained respectively. In reverse order, the target time can be obtained respectively. The reverse corrected longitude and reverse corrected latitude of target moment 1, target moment 2, and target moment 3. For target moment 1, the forward adjacent moment is the first reference moment, and the reverse adjacent moment is target moment 2. According to the method of obtaining the weights of adjacent moments in the first type of target moment, the weights corresponding to the two forward and reverse adjacent moments are obtained, and then the forward corrected longitude and reverse corrected longitude of target moment 1 are weighted and summed, and the forward corrected latitude and reverse corrected latitude of target moment 1 are weighted and summed, and the corrected longitude and corrected latitude of target moment 1 are weighted and summed, and the corrected longitude and corrected latitude of target moment 1 are weighted and summed.

[0058] In this way, the original longitude and latitude information (GPS data) at all target moments are replaced with the corrected longitude and latitude, completing the correction of the GPS data at the moment that needs to be corrected during the driving process of the vehicle that needs to be corrected.

[0059] After correcting the vehicle's GPS data, the platform can accurately monitor the fleet's operating status, identify abnormal behaviors, trace driving routes, and optimize scheduling based on high-precision trajectories, thereby improving the safety and intelligence of remote operation and maintenance management, and achieving effective management of key links such as vehicle positioning, operating efficiency, driving behavior, and risk warning.

[0060] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0061] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A remote operation and maintenance management platform for safe driving of intelligent fleets, characterized by: The platform includes: A line graph construction unit is used to collect driving data and GPS data of each vehicle; and obtain a driving line graph and a GPS line graph based on the driving data and GPS data of a vehicle respectively; A target vehicle acquisition unit is configured to respectively acquire a first eigenvalue sequence and a second eigenvalue sequence based on a vehicle's travel line graph and GPS line graph; the absolute values ​​of the differences between the elements at corresponding moments in the first and second eigenvalue sequences form a difference eigenvalue sequence; and the difference eigenvalue sequence of a vehicle is used to determine whether the vehicle is a target vehicle. A target time determination unit is configured to obtain a time to be corrected of a target vehicle based on a sequence of difference characteristic values ​​of the target vehicle; and to determine whether the time to be corrected is a target time based on two adjacent times to the time to be corrected; The correction unit is used to classify the target time according to the distribution characteristics of the target time of a vehicle, and correct the GPS data of the target time according to the classification result.

2. The remote operation and maintenance management platform for safe driving of intelligent fleets according to claim 1 is characterized in that: The driving data includes the vehicle's speed, acceleration, and driving direction.

3. The remote operation and maintenance management platform for safe driving of intelligent fleet according to claim 1 is characterized in that: The method of obtaining a driving line graph and a GPS line graph based on driving data and GPS data of a vehicle respectively includes: The vehicle's driving direction at the previous moment is used as the reference direction at that moment. The displacement between the two moments is obtained based on the vehicle speed at that moment and the acceleration at the next moment. The deflection angle of the vehicle's driving direction at that moment relative to its reference direction is also obtained. Similarly, the displacement between each two moments and the deflection angle of the vehicle's driving direction at each moment relative to its reference direction are obtained. A driving line graph is then obtained with each moment as a node. The length of the line between two moments in the driving line graph represents the displacement distance between the two moments. The longitude and latitude coordinates of a vehicle at each moment are obtained based on the GPS data of the vehicle at each moment during its travel, and two adjacent longitude and latitude coordinates are connected by a line segment to obtain a GPS line graph of the vehicle.

4. The remote operation and maintenance management platform for safe driving of intelligent fleets according to claim 1 is characterized in that: The method of obtaining a first eigenvalue sequence and a second eigenvalue sequence respectively according to a driving line graph and a GPS line graph of a vehicle includes: The nodes other than the first and last nodes in the driving line graph are taken as the vertices of the angles; the lines between a vertex and the two adjacent nodes are obtained, with the line on the right as the starting edge and the line on the left as the ending edge, and the angle from the starting edge to the ending edge is calculated in a counterclockwise direction and recorded as the angle value of the vertex at the corresponding time; the angle values ​​of each vertex at the corresponding time in the driving line graph constitute the first eigenvalue sequence; similarly, the second eigenvalue sequence is obtained based on the GPS line graph.

5. The remote operation and maintenance management platform for safe driving of intelligent fleet according to claim 1 is characterized in that: The method of using a vehicle's difference feature value sequence to determine whether the vehicle is a target vehicle includes: The average value of the elements in the difference characteristic value sequence of a vehicle is calculated and multiplied by the maximum value in the sequence to obtain the multiplication result. The multiplication result is normalized to obtain the necessity of vehicle correction; if the necessity of vehicle correction of the vehicle is greater than the judgment threshold, the vehicle is considered a target vehicle.

6. The remote operation and maintenance management platform for safe driving of intelligent fleets according to claim 1 is characterized in that: The step of obtaining the time to be corrected of the target vehicle according to the difference characteristic value sequence of the target vehicle includes: If the normalized value of the square of the difference characteristic value corresponding to a moment in the difference characteristic value sequence of the target vehicle is greater than the judgment threshold, then the moment is the moment to be corrected.

7. The remote operation and maintenance management platform for safe driving of intelligent fleet according to claim 1 is characterized in that: The determining whether the time to be corrected is the target time based on two adjacent time points of the time to be corrected includes: If there is at least one non-to-be-corrected time between the two adjacent times to be corrected, then the to-be-corrected time is not the target time. Otherwise, the to-be-corrected time is the target time, and all times except the target time are normal times.

8. The remote operation and maintenance management platform for safe driving of intelligent fleets according to claim 1 is characterized in that: The classifying the target time according to the distribution characteristics of the target time of a vehicle includes: The target moments where both adjacent moments are normal moments are recorded as the first category; the target moments where the continuous distribution is continuous and both ends of the target moments are normal moments are recorded as the second category; the target moments where the continuous distribution is continuous and only one end of the two ends of the target moments is a normal moment are recorded as the third category.

9. The remote operation and maintenance management platform for safe driving of intelligent fleet according to claim 1 is characterized in that: The method of correcting the GPS data at the target time according to the classification result includes: If the target moment is the first category, a two-dimensional coordinate system is established with the vehicle driving direction at the previous adjacent moment as the horizontal axis, the latitude and longitude of the vehicle at the previous adjacent moment as the origin, and the vertical axis perpendicular to the horizontal axis. In the two-dimensional coordinate system, the displacement between the previous adjacent moment and the target moment is decomposed to obtain two component displacements, and the two component displacements are converted into longitude and latitude, which are recorded as the reference longitude and reference latitude corresponding to the previous adjacent moment. Similarly, the reference longitude and reference latitude corresponding to the next adjacent moment are obtained; an exponential function with a natural constant as the base is used to decompose the displacement between the previous adjacent moment and the target moment. The normalized value of the square of the difference eigenvalue of the moment is negatively correlated to obtain the mapping value corresponding to the previous adjacent moment, and similarly obtain the mapping value corresponding to the next adjacent moment; the mapping value corresponding to the previous adjacent moment divided by the sum of the mapping values ​​corresponding to the previous adjacent moment and the next adjacent moment is the weight corresponding to the previous adjacent moment, and similarly obtain the weight corresponding to the next adjacent moment; the weights corresponding to the previous adjacent moment and the next adjacent moment are used to perform weighted summation on the reference longitudes corresponding to the previous adjacent moment and the next adjacent moment to obtain the corrected longitude corresponding to the target moment, and similarly obtain the corrected latitude corresponding to the target moment; For the third type of target moment, the normal moment at one end of the third type of target moment is used as the reference moment; the third type of target moment is marked as the first target moment, the second target moment, the third target moment in order from the reference moment to the target moment, until the last target moment is marked as the end target moment; the reference longitude and reference latitude corresponding to the reference moment are obtained according to the longitude and latitude of the vehicle at the reference moment and the displacement between the first target moment and the reference moment, as the corrected longitude and corrected latitude of the first target moment; the reference longitude and reference latitude corresponding to the first target moment are obtained according to the corrected longitude and corrected latitude of the first target moment and the displacement between the first target moment and the second target moment, as the corrected longitude and corrected latitude of the second target moment, and so on, to obtain the corrected longitude and corrected latitude of each target moment in the third type of target moment; For the second type of target moment, the normal moments at both ends of the second type of target moment are recorded as the first reference moment and the second reference moment respectively; the order from the first reference moment to the target moment is recorded as the forward order, and the order from the second reference moment to the target moment is recorded as the reverse order; the method of obtaining the corrected longitude and corrected latitude of the target moment by using the third type of target moment is to obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in the forward order starting from the first reference moment, and similarly, obtain the forward corrected longitude and forward corrected latitude of each target moment in the second type of target moment in the reverse order starting from the second reference moment. The reverse corrected longitude and reverse corrected latitude of the moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment of a target moment in the second type of target moment are obtained according to the weight method corresponding to the previous adjacent moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment are used to weightedly sum the forward corrected longitude and the reverse corrected longitude of a target moment to obtain the corrected longitude of the target moment; the weights corresponding to the forward adjacent target moment and the reverse adjacent target moment are used to weightedly sum the forward corrected dimension and the reverse corrected dimension of a target moment to obtain the corrected dimension of the target moment.

Images