Online car-hailing charging method based on adaptive extended Kalman filtering and related equipment

Abstract

The invention relates to the technical field of data processing, in particular to an online car-hailing charging method and related equipment based on adaptive extended Kalman filtering, and the method comprises the steps: collecting the GPS data of an online car-hailing in real time, and determining the basic data of the position, time and speed; establishing a system model comprising a state equation and an observation equation based on an adaptive extended Kalman filtering algorithm; wherein the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input comprises the vehicle acceleration; through the system model, the vehicle speed at the next moment is predicted according to the basic data at the previous moment; when the error between the predicted vehicle speed and the actual vehicle speed at the same moment is larger than a preset threshold value, noise parameters in the system model are adjusted based on the measurement residual error; and performing charging based on the predicted vehicle speed, and performing charging compensation when an error exceeds a target range. Therefore, the charging precision of the online car-hailing can be greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for charging online car-hailing based on adaptive extended Kalman filtering and related devices. Background Art

[0002] Currently, the charging for online car-hailing is generally carried out through GPS data. However, in environments with weak GPS signals such as urban canyons or tunnels, there are the following disadvantages in directly charging according to GPS data:

[0003] The navigation drift point problem caused by unstable GPS signals: Due to the occlusion and interference of GPS signals in environments such as urban canyons or tunnels, the GPS positioning is inaccurate, resulting in the phenomenon of navigation drift points, that is, the positioning points move frequently and irregularly on the map; The accuracy problem of time-period-based charging in the charging template: Since the vehicle speed measurement is inaccurate due to weak GPS signals, when calculating the cost across time periods, the driving mileage and time of each time period cannot be accurately calculated, affecting the accuracy of charging.

[0004] In addition, the current abnormal judgment of the speed of online car-hailing mainly relies on empirical values and cannot accurately identify and handle speed abnormal situations. Therefore, there is an urgent need for a method to improve the charging accuracy of online car-hailing. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method for charging online car-hailing based on adaptive extended Kalman filtering and related devices to overcome the problem of poor charging accuracy of current online car-hailing.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present application provides a method for charging online car-hailing based on adaptive extended Kalman filtering, including:

[0008] Real-time collect the GPS data of the online car-hailing, and determine the basic data based on the GPS data, where the basic data includes position, time, and vehicle speed;

[0009] Establish a system model of the vehicle based on the adaptive extended Kalman filtering algorithm, where the system model includes a state equation and an observation equation. The state equation is used to describe the change of the vehicle's position and speed over time, and the observation equation is used to describe the relationship between the vehicle's observation data and the vehicle state; among them, the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration;

[0010] Through the system model, predict the vehicle speed at the next moment according to the basic data at the previous moment;

[0011] When the error between the predicted vehicle speed and the actual vehicle speed at the same moment is greater than a preset threshold, adjust the noise parameters in the system model based on the measurement residuals;

[0012] Perform billing based on the predicted vehicle speed, and perform billing compensation when the error exceeds the target range.

[0013] Further, in some embodiments of the present application, the state equation is:

[0014] X k =A k-1 X k-1 +B k-1 μ k-1 +W k-1

[0015] The observation equation is:

[0016] Z k =H k X k +V k

[0017] Where k is the time mark; X represents the state vector; A represents the state transition matrix; B represents the control input matrix; u represents the control input; W represents the process noise; Z represents the observation vector; H represents the observation matrix, and V represents the observation noise.

[0018] Further, in some embodiments of the present application, the predicting the vehicle speed at the next moment according to the basic data at the previous moment through the system model includes:

[0019] Initialize the state vector, covariance matrix, process noise covariance matrix, and observation noise covariance matrix;

[0020] Based on the initialization result, predict the state vector through the state prediction formula and predict the covariance matrix through the covariance prediction formula;

[0021] Where the state prediction formula is:

[0022]

[0023] The covariance prediction formula is:

[0024]

[0025] Where Q represents the process noise covariance matrix and T represents the transpose operation.

[0026] Further, in some embodiments of the present application, it further includes: updating the prediction result based on the previous moment according to the basic data obtained at the subsequent moment to obtain an updated prediction result.

[0027] Further, in some embodiments of the present application, the update includes: updating the state vector through a state update formula and updating the covariance matrix through a covariance update formula;

[0028] Among them, the state update formula is:

[0029]

[0030] The covariance update formula is:

[0031] P k|k =(I-K k H k )P k|k-1

[0032] Among them, K represents the Kalman gain; I represents the identity matrix.

[0033] Further, in some embodiments of the present application, the formula for adjusting the noise parameter in the system model based on the measurement residual is:

[0034] Q x =K k ·Error x ·K′ k

[0035] Among them, Qx represents the updated process noise covariance matrix; Error x represents the measurement residual.

[0036] In a second aspect, the present application provides a taxi charging device based on adaptive extended Kalman filtering, including:

[0037] An acquisition module, configured to collect GPS data of a taxi in real time and determine basic data based on the GPS data, where the basic data includes location, time, and vehicle speed;

[0038] A modeling module, configured to establish a system model of the vehicle based on the adaptive extended Kalman filtering algorithm, where the system model includes a state equation and an observation equation. The state equation is used to describe the change of the vehicle's position and speed over time, and the observation equation is used to describe the relationship between the vehicle's observation data and the vehicle state; among them, the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration;

[0039] A prediction module, configured to predict the vehicle speed at the next moment according to the basic data at the previous moment through the system model;

[0040] An error detection module, configured to adjust the noise parameter in the system model based on the measurement residual when the error between the predicted vehicle speed and the actual vehicle speed at the same moment is greater than a preset threshold;

[0041] A billing detection module, configured to perform billing based on the predicted vehicle speed and perform billing compensation when the error exceeds the target range.

[0042] In a third aspect, the present application provides a car-hailing billing device based on an adaptive extended Kalman filter, including a processor and a memory, where the processor is connected to the memory:

[0043] Wherein, the processor is configured to call and execute the program stored in the memory;

[0044] The memory is configured to store the program, and the program is at least used to execute the above-mentioned car-hailing billing method based on an adaptive extended Kalman filter

[0045] The present invention relates to the technical field of data processing, and specifically relates to a car-hailing billing method and related devices based on an adaptive extended Kalman filter. The method includes: collecting GPS data of a car-hailing vehicle in real time to determine basic data including position, time, and vehicle speed; establishing a system model of the vehicle based on the adaptive extended Kalman filter algorithm, where the system model includes a state equation and an observation equation, the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration; predicting the vehicle speed at the next moment according to the basic data at the previous moment through the system model; and when the error between the predicted vehicle speed and the actual vehicle speed at the same moment is greater than a preset threshold, adjusting the noise parameter in the system model based on the measurement residual; and performing billing based on the predicted vehicle speed and performing billing compensation when the error exceeds the target range. In this way, the billing accuracy of car-hailing can be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0047] Figure 1 It is a schematic flowchart of the car-hailing billing method based on an adaptive extended Kalman filter provided by an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of the principle of the online car-hailing charging method based on adaptive extended Kalman filtering provided by an embodiment of the present invention.

[0049] Figure 3 It is a schematic structural diagram of the online car-hailing charging device based on adaptive extended Kalman filtering provided by an embodiment of the present invention.

[0050] Figure 4 It is a schematic structural diagram of the online car-hailing charging device based on adaptive extended Kalman filtering provided by an embodiment of the present invention. Detailed implementation manners

[0051] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other implementation manners obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope protected by the present invention.

[0052] Figure 1 It is a schematic flowchart of the online car-hailing charging method based on adaptive extended Kalman filtering provided by an embodiment of the present invention. Figure 2 It is a schematic diagram of the principle of the online car-hailing charging method based on adaptive extended Kalman filtering provided by an embodiment of the present invention. Please refer to Figure 1 and Figure 2 , this embodiment may include the following steps:

[0053] S101. Real-time collect the GPS data of the online car-hailing, and determine the basic data based on the GPS data.

[0054] Specifically, the GPS data of the vehicle can be collected through a preset app, and then the position, speed and timestamp of the vehicle can be obtained based on the GPS data.

[0055] S102. Establish a system model of the vehicle based on the adaptive extended Kalman filtering algorithm.

[0056] Specifically, in this application, the system model includes a state equation and an observation equation. The state equation is used to describe the change of the position and speed of the vehicle over time, and the observation equation is used to describe the relationship between the observed data of the vehicle and the vehicle state. Among them, the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration.

[0057] S103. Through the system model, predict the vehicle speed at the next moment according to the basic data at the previous moment.

[0058] S104. When the error between the predicted vehicle speed and the actual vehicle speed at the same time is greater than a preset threshold, adjust the noise parameters in the system model based on the measurement residual.

[0059] S105. Charge based on the predicted vehicle speed, and when the error exceeds the target range, perform a charge compensation.

[0060] Specifically, first, based on the set error threshold and a reasonable target range, perform error detection and evaluation. When the error exceeds the error threshold, adaptively adjust the noise parameters in the system model based on the measurement residual, and when the error exceeds the target range, trigger a pre-set compensation mechanism to perform a charge compensation when charging based on the predicted vehicle speed.

[0061] The online car-hailing charging method based on adaptive extended Kalman filtering provided by this application determines the basic data including position, time, and vehicle speed by collecting the GPS data of the online car-hailing in real time; establishes a system model including a state equation and an observation equation based on the adaptive extended Kalman filtering algorithm; where the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration; predicts the vehicle speed at the next moment through the system model according to the basic data at the previous moment; and when the error between the predicted vehicle speed and the actual vehicle speed at the same time is greater than a preset threshold, adjust the noise parameters in the system model based on the measurement residual; and charge based on the predicted vehicle speed, and when the error exceeds the target range, perform a charge compensation, which can greatly improve the charging accuracy of the online car-hailing.

[0062] Further, in the implementation of this application, the above-mentioned state equation is specifically:

[0063] X k =A k-1 X k-1 +B k-1 μ k-1 +W k-1

[0064] The observation equation is:

[0065] Z k =H k X k +V k

[0066] Wherein, k is a time marker; X represents a state vector; A represents a state transition matrix; B represents a control input matrix; u represents a control input; W represents a process noise; Z represents an observation vector; H represents an observation matrix, and V represents an observation noise. It can be understood that for the above symbols, those with a subscript of k represent the corresponding parameters at the k-th moment (which is the next moment compared to the (k - 1)-th moment), and those with a subscript of k - 1 represent the corresponding parameters at the (k - 1)-th moment (which is the previous moment compared to the k-th moment).

[0067] On this basis, when the present application is actually applied, data initialization is required, including initializing the state vector, covariance matrix, process noise covariance matrix, and observation noise covariance matrix. It includes performing an initial state estimation based on the GPS data at the initial moment, that is, initializing the state vector. And initializing the covariance matrix P representing the uncertainty of the initial state estimation. And initializing the process noise covariance matrix Q and the observation noise covariance matrix R, so as to perform subsequent prediction and update steps.

[0068] In the present application, the prediction step specifically includes predicting the state, that is, predicting the state vector, and predicting the covariance matrix. Among them, the state prediction formula is:

[0069]

[0070] The covariance prediction formula is:

[0071]

[0072] Wherein, Q represents the process noise covariance matrix, and T represents the transpose operation.

[0073] And in the update step, based on the basic data obtained at the later moment, the result predicted based on the previous moment is updated to obtain the updated prediction result, which specifically includes updating the state vector through the state update formula, and updating the covariance matrix through the covariance update formula. Among them, the state update formula is:

[0074]

[0075] The covariance update formula is:

[0076] P k|k =(I - K k H k )P k|k-1

[0077] Wherein, K represents the Kalman gain; I represents the identity matrix, and the calculation formula of the Kalman gain is specifically:

[0078]

[0079] And the formula for adjusting the noise parameters in the system model based on the measurement residuals is as follows:

[0080] Qx ＝ K k ·Error x ·K′ k

[0081] Where Qx represents the updated process noise covariance matrix; Error x represents the measurement residual; K′ k is the transpose of the Kalman gain. It can be understood that in this application, the adaptive extended Kalman filtering algorithm is a recursive process that repeats the prediction and update steps (i.e., makes predictions based on the above prediction formula and updates based on the above update formula) at each time step to achieve real-time tracking and prediction of the vehicle speed.

[0082] It should be noted that in addition to the individual subscripts k and k - 1 for the parameters in the above formula, there are also combinations of the two, namely k|k - 1, k|k, and k - 1|k - 1, which represent the sources of the corresponding parameters. For example, the parameter with the subscript k|k - 1 is the parameter at time k directly predicted and estimated based on the data at time k - 1, while k|k represents the result after updating the parameter at time k predicted previously based on the data obtained at time k (the same applies to k - 1|k - 1). This part can be understood based on the relevant content of the Kalman filtering algorithm in the prior art and will not be elaborated here one by one.

[0083] In practical applications, after determining the above state equation for describing the changes in the position and speed of the vehicle over time, and the observation equation that relates the observed position obtained from GPS observation data to the vehicle state, an initialization stage is carried out, that is, the initial state estimate is set according to the initial position and speed of the vehicle, namely the estimated predicted state vector and covariance matrix, as well as the other initialized parameters mentioned above. Then, at each time step, the above prediction formula is used to predict the next state of the vehicle, and the update formula is used to update the state estimate based on the position, time, and speed information obtained from the newly acquired GPS data.

[0084] For example, given the position and speed of the vehicle at time k - 1, then through the above prediction formula, the position and speed of the vehicle at the next time step k are predicted. When a new position Z k arrives based on the new GPS data, the Kalman gain is calculated and the state update information is calculated using the update formula, and then an update is performed to obtain a more accurate speed estimate. In this way, the speed of the vehicle can be tracked and predicted in real time, and high accuracy can be maintained even when the GPS signal is unstable or noisy.

[0085] On this basis, error detection and evaluation are carried out, including first monitoring in real time the error between the speed finally predicted through the above steps (specifically, the updated result) and the real speed (which can be based on vehicle GPS data or determined in cooperation with the observation formula). The size of the error is evaluated by calculating the difference between the two, and it is determined whether it exceeds the preset threshold and whether it is within a reasonable target range.

[0086] When the error exceeds the preset threshold, an error handling mechanism is triggered. At this time, the above-mentioned adaptive adjustment based on the measurement residual formula can be used to correct the error, so as to dynamically adjust the noise parameters according to the observation residual and system performance, thereby improving the accuracy and robustness of state estimation.

[0087] And when the error exceeds the target range, when charging based on the predicted vehicle speed, a compensation mechanism is triggered to adjust the fee. If the error does not exceed the target range, normal charging is performed based on the predicted vehicle speed.

[0088] In practical applications, in the online car-hailing charging method based on adaptive extended Kalman filtering provided in this application, GPS data can be collected at the APP side, calculations based on the adaptive extended Kalman filtering algorithm can be performed at the charging system side, and parameters such as the above-mentioned preset threshold and target range can be set through an operation configuration platform connected to the charging system.

[0089] The online car-hailing charging method based on adaptive extended Kalman filtering provided in this application uses the relevant principles of Kalman filters to reduce noise and errors based on the collected GPS data. In urban canyons or tunnel environments with weak GPS signals, it can significantly improve the positioning accuracy, thereby reducing the navigation drift phenomenon and improving the navigation accuracy; at the same time, by predicting the vehicle speed of the online car-hailing, it can calculate the driving mileage and time of each period more accurately, improve the accuracy of time-based charging, and ensure the fairness of charging; and through refined speed prediction and anomaly judgment, it can more accurately identify speed anomaly situations, provide a reliable basis for whether charging triggers compensation, thereby enhancing the reliability of the online car-hailing charging system; and based on the adaptive adjustment mechanism, it can dynamically adjust the system noise parameters to adapt to changes in system noise and provide more accurate and stable state estimation. Thus, the problem of inaccurate online car-hailing charging at present is solved, user complaints are reduced, and user satisfaction with online car-hailing services is improved.

[0090] Based on the same inventive concept, this application also provides an online car-hailing charging device based on adaptive extended Kalman filtering for implementing the above method embodiments. Figure 3 It is a schematic structural diagram of the online car-hailing charging device based on adaptive extended Kalman filtering provided by the embodiment of the present invention, asFigure 3 As shown in the figure, the online car-hailing charging device based on adaptive extended Kalman filtering provided by the present application includes:

[0091] An acquisition module 11, configured to collect GPS data of the online car-hailing in real time, and determine basic data based on the GPS data, where the basic data includes location, time, and vehicle speed;

[0092] A modeling module 12, configured to establish a system model of the vehicle based on the adaptive extended Kalman filtering algorithm. The system model includes a state equation and an observation equation. The state equation is used to describe the change of the vehicle's position and speed over time, and the observation equation is used to describe the relationship between the vehicle's observed data and the vehicle state. Among them, the state vector is the vehicle position and the vehicle speed, the observation vector is the vehicle position, and the control input includes the vehicle acceleration;

[0093] A prediction module 13, configured to predict the vehicle speed at the next moment through the system model according to the basic data at the previous moment;

[0094] An error detection module 14, configured to adjust the noise parameters in the system model based on the measurement residual when the error between the predicted vehicle speed and the actual vehicle speed at the same moment is greater than a preset threshold;

[0095] A charging detection module 15, configured to perform charging based on the predicted vehicle speed, and perform charging compensation when the error exceeds the target range.

[0096] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0097] The present invention also provides an online car-hailing charging device based on adaptive extended Kalman filtering, which is used to implement the above method embodiments. Figure 4 is a schematic structural diagram of the online car-hailing charging device based on adaptive extended Kalman filtering provided by the embodiments of the present invention. As Figure 4 shown, the online car-hailing charging device based on adaptive extended Kalman filtering in this embodiment includes a processor 21 and a memory 22, and the processor 21 is connected to the memory 22. Among them, the processor 21 is used to call and execute the program stored in the memory 22; the memory 22 is used to store the program, and the program is at least used to execute the online car-hailing charging method based on adaptive extended Kalman filtering in the above embodiments.

[0098] The specific implementation of the online car-hailing charging device based on adaptive extended Kalman filtering provided by the embodiments of the present application can refer to the implementation manners of the online car-hailing charging method based on adaptive extended Kalman filtering in any of the above embodiments, and will not be elaborated here.

[0099] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not described in detail in some embodiments can be seen in the same or similar content of other embodiments.

[0100] It should be noted that in the description of the present invention, terms such as "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a plurality of" refers to at least two.

[0101] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the technical field of the embodiments of the present invention.

[0102] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following well-known technologies in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0103] Those of ordinary skill in the technical field of the present invention can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0104] In addition, each functional unit in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into a module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0105] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disk, etc.

[0106] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0107] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A billing method for online car-hailing based on adaptive extended Kalman filter, characterized in that, Including: Real-time collect the GPS data of the online car-hailing vehicle, and determine the basic data based on the GPS data, where the basic data includes location, time, and vehicle speed; Establish a system model of the vehicle based on the adaptive extended Kalman filter algorithm, where the system model includes a state equation and an observation equation. The state equation is used to describe the changes in the position and speed of the vehicle over time, and the observation equation is used to describe the relationship between the observed data of the vehicle and the vehicle state. Among them, the state vector is the vehicle position and vehicle speed, the observation vector is the vehicle position, and the control input includes vehicle acceleration; Through the system model, predict the vehicle speed at the next moment according to the basic data at the previous moment; When the error between the predicted vehicle speed and the actual vehicle speed at the same moment is greater than the preset threshold, adjust the noise parameters in the system model based on the measurement residual; Billing is based on the predicted vehicle speed, and when the error exceeds the target range, billing compensation is performed.

2. The online car-hailing charging method based on adaptive extended Kalman filtering according to claim 1, wherein The state equation is: X k = A k-1 X k-1 + B k-1 μ k-1 + W k-1 The observation equation is: Z k = H k X k + V k Among them, k is the time mark; X represents the state vector; A represents the state transition matrix; B represents the control input matrix; u represents the control input; W represents the process noise; Z represents the observation vector; H represents the observation matrix, and V represents the observation noise.

3. The online car-hailing charging method based on adaptive extended Kalman filtering according to claim 2, wherein, The predicting the vehicle speed at the next moment according to the basic data at the previous moment through the system model includes: Initialize the state vector, covariance matrix, process noise covariance matrix, and observation noise covariance matrix; Based on the initialization result, predict the state vector through the state prediction formula and predict the covariance matrix through the covariance prediction formula; Among them, the state prediction formula is: The covariance prediction formula is: Among them, Q represents the process noise covariance matrix, and T represents the transpose operation.

4. The online car-hailing billing method based on adaptive extended Kalman filtering according to claim 3, wherein, Also including: Based on the basic data obtained at the later moment, update the prediction result based on the prediction at the previous moment to obtain the updated prediction result.

5. The online car-hailing charging method based on adaptive extended Kalman filtering according to claim 4, wherein, The update includes: updating the state vector through the state update formula and updating the covariance matrix through the covariance update formula; Among them, the state update formula is: The covariance update formula is: P k|k = (I - K k H k )P k|k-1 Among them, K represents the Kalman gain; I represents the identity matrix.

6. The online car-hailing charging method based on adaptive extended Kalman filtering according to claim 5, wherein The formula for adjusting the noise parameters in the system model based on the measurement residual is: Q x = K k · Error x · K' k Among them, Qx represents the updated process noise covariance matrix; Error x represents the measurement residual.

7. A car-hailing charging device based on adaptive extended Kalman filter, characterized in that, Including: A collection module, which is used to collect the GPS data of the online car-hailing vehicle in real time and determine the basic data based on the GPS data. The basic data includes location, time, and vehicle speed; A modeling module, which is used to establish a system model of the vehicle based on the adaptive extended Kalman filter algorithm. The system model includes a state equation and an observation equation. The state equation is used to describe the changes in the position and speed of the vehicle over time, and the observation equation is used to describe the relationship between the observed data of the vehicle and the vehicle state. Among them, the state vector is the vehicle position and vehicle speed, the observation vector is the vehicle position, and the control input includes vehicle acceleration; A prediction module, which is used to predict the vehicle speed at the next moment through the system model according to the basic data at the previous moment; An error detection module, configured to adjust the noise parameters in the system model based on measurement residuals when the error between the predicted vehicle speed and the actual vehicle speed at the same time is greater than a preset threshold; A billing detection module, configured to perform billing based on the predicted vehicle speed and perform billing compensation when the error exceeds a target range.

8. A car-hailing charging device based on adaptive extended Kalman filtering, characterized in that, It includes a processor and a memory, and the processor is connected to the memory: Wherein, the processor is configured to call and execute the program stored in the memory; The memory is configured to store the program, and the program is at least used to execute the online car-hailing billing method based on adaptive extended Kalman filtering according to any one of claims 1-6.

Images