Vehicle speed prediction method and device, vehicle and storage medium

Abstract

The invention provides a vehicle speed prediction method and device, a vehicle and a storage medium, and belongs to the technical field of vehicle speed prediction.The method comprises the steps that a first vehicle speed signal in the previous time period and a second vehicle speed signal in the current time period are obtained; inputting the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; determining at least two weight distribution schemes of the at least two vehicle speed prediction signals based on the at least two deviation algorithms, and determining at least two weighted prediction signals in one-to-one correspondence with the at least two deviation algorithms based on the at least two weight distribution schemes; and determining a secondary weight distribution scheme of the at least two weighted prediction signals, and determining a comprehensive vehicle speed prediction signal based on the secondary weight distribution scheme and the at least two weighted prediction signals. According to the invention, through multi-dimensional weighting, the vehicle speed prediction precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle speed prediction, and in particular to a vehicle speed prediction method, device, vehicle and storage medium. Background Art

[0002] In order to make the vehicle more intelligent, it is necessary to predict the possible operating conditions of the vehicle in the short term in the future. Based on the prediction results, the ECU can open and close related functions in advance, so that the vehicle can give feedback on possible changes in the future in advance, thereby achieving smooth control and more efficient and energy-saving operation. Among all the operating parameters of the vehicle, vehicle speed is an important prediction parameter.

[0003] The existing method of predicting vehicle speed is to predict the vehicle speed through a single vehicle speed prediction method, and directly use the predicted vehicle speed as the input of the ECU. The problem with this method is that the accuracy and reliability of the single vehicle speed prediction method are not high, resulting in inaccurate vehicle speed prediction.

[0004] Therefore, there is an urgent need to provide a vehicle speed prediction method, device, vehicle and storage medium for realizing multi-dimensional vehicle speed prediction to improve the accuracy of the predicted vehicle speed. Summary of the invention

[0005] In view of this, it is necessary to provide a vehicle speed prediction method, device, vehicle and storage medium to solve the technical problem in the prior art that the vehicle speed is predicted by a single prediction method, resulting in low accuracy of the predicted vehicle speed.

[0006] On the one hand, in order to solve the above technical problems, the present invention provides a vehicle speed prediction method, comprising: Acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; Inputting the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; Determining at least two weight allocation schemes for the at least two vehicle speed prediction signals based on at least two deviation algorithms, and determining at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; A secondary weight distribution scheme of the at least two weighted prediction signals is determined, and a comprehensive vehicle speed prediction signal is determined based on the secondary weight distribution scheme and the at least two weighted prediction signals.

[0007] In a possible implementation, the at least two vehicle speed prediction models include a first vehicle speed prediction model and a second vehicle speed prediction model having different model structures; the at least two vehicle speed prediction signals include a first vehicle speed prediction signal corresponding to the first vehicle speed prediction model and a second vehicle speed prediction signal corresponding to the second vehicle speed prediction model; the at least two deviation algorithms include a first deviation algorithm and a second deviation algorithm; Then the step of determining at least two weight allocation schemes of the at least two vehicle speed prediction signals based on the at least two deviation algorithms, and determining at least two weighted prediction signals corresponding to the at least two deviation algorithms based on the at least two weight allocation schemes, includes: determining a first difference between the first vehicle speed prediction signal and the second vehicle speed signal and a second difference between the second vehicle speed prediction signal and the second vehicle speed signal based on the first deviation algorithm; determining a first weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the first difference and the second difference; determining a third difference between the first vehicle speed prediction signal and the second vehicle speed signal and a fourth difference between the second vehicle speed prediction signal and the second vehicle speed signal based on the second deviation algorithm; determining a second weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the third difference and the fourth difference; The first vehicle speed prediction signal and the second vehicle speed prediction signal are weighted based on the first weight allocation scheme to obtain a first weighted prediction signal, and the first vehicle speed prediction signal and the second vehicle speed prediction signal are weighted based on the second weight allocation scheme to obtain a second weighted prediction signal.

[0008] In a possible implementation, the weights in the weight distribution scheme are:

[0009] In the formula, is the weight of the i-th vehicle speed prediction model; is the difference between the vehicle speed prediction signal predicted by the i-th vehicle speed prediction model and the second vehicle speed signal; is the variable coefficient; is a constant; n is the total number of vehicle speed prediction models.

[0010] In a possible implementation, the deviation algorithm is a least squares method, an absolute deviation normalization accumulation method, or a window moving average deviation normalization method.

[0011] In a possible implementation, the at least two weighted prediction signals include a first weighted prediction signal corresponding to the least squares method, a second weighted prediction signal corresponding to the absolute deviation normalization accumulation method, and a third weighted prediction signal corresponding to the window moving average deviation normalization method; Then the determining of the secondary weight allocation scheme of the at least two weighted prediction signals includes: Determining a first prediction difference between the first weighted prediction signal and the second vehicle speed signal, a second prediction difference between the second weighted prediction signal and the second vehicle speed signal, and a third prediction difference between the third weighted prediction signal and the second vehicle speed signal; The secondary weight allocation scheme is determined based on the first prediction difference value, the second prediction difference value, and the third prediction difference value.

[0012] In a possible implementation, the vehicle speed prediction model is a least squares curve fitting algorithm, a moving average window algorithm, a long short-term memory network model, or a gated recurrent unit network model.

[0013] In a possible implementation manner, before determining the secondary weight allocation scheme of the at least two weighted prediction signals, the method further includes: Kalman filtering is performed on each of the weighted prediction signals.

[0014] On the other hand, the present invention also provides a vehicle speed prediction device, comprising: A vehicle speed signal acquisition unit, used to acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; a vehicle speed prediction unit, configured to input the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; a first weight allocation unit, configured to determine at least two weight allocation schemes of the at least two vehicle speed prediction signals based on at least two deviation algorithms, and to determine at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; The second weight allocation unit is used to determine a secondary weight allocation scheme for the at least two weighted prediction signals, and determine a comprehensive vehicle speed prediction signal based on the secondary weight allocation scheme and the at least two weighted prediction signals.

[0015] In another aspect, the present invention further provides a vehicle, comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the vehicle speed prediction method described in any one of the possible implementations above.

[0016] On the other hand, the present invention also provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the vehicle speed prediction method described in any possible implementation method mentioned above are implemented.

[0017] The beneficial effects of the present invention are as follows: the vehicle speed prediction method provided by the present invention first inputs the first vehicle speed signal into at least two vehicle speed prediction models, predicts the vehicle speed in the current time period through at least two vehicle speed prediction models, obtains at least two vehicle speed prediction signals, and then determines the deviation between the vehicle speed prediction signal and the actual second vehicle speed signal by different deviation algorithms, and weights the vehicle speed prediction signals predicted by at least two vehicle speed prediction models based on the deviation to obtain a weighted prediction signal corresponding to the deviation algorithm one by one, and reduces the error generated by predicting the vehicle speed by a single method to a certain extent through weighted processing, thereby improving the accuracy of the determined predicted vehicle speed. Furthermore, in order to avoid problems such as deviation caused by a single deviation algorithm, after determining at least two weighted prediction signals, the present invention determines a secondary weight distribution scheme for at least two weighted prediction signals, performs a second weighted processing on at least two weighted prediction signals, and finally obtains a comprehensive vehicle speed prediction signal, thereby further improving the accuracy of the determined comprehensive vehicle speed prediction signal. That is, the present invention distributes weights from two dimensions, namely, the prediction model and the deviation algorithm, thereby eliminating the limitations or inaccuracies caused by a single prediction algorithm and a single deviation evaluation method, and ensuring the accuracy of the obtained comprehensive vehicle speed prediction signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic flow chart of an embodiment of a vehicle speed prediction method provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of step S102; Figure 3 This is a flow chart of an embodiment of determining a secondary weight allocation scheme in step S103 of the present invention; Figure 4 A schematic diagram of the structure of an embodiment of a vehicle speed prediction device provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of a vehicle provided by the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] It should be understood that the schematic drawings are not drawn to scale. The flowchart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present invention, can add one or more other operations to the flowchart, and can also remove one or more operations from the flowchart. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0022] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a vehicle speed prediction method, device, vehicle and storage medium, which are respectively described below.

[0024] The embodiment of the present invention provides a vehicle speed prediction method, such as Figure 1 As shown, the vehicle speed prediction method includes: S101, obtaining a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; S102, inputting the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; S103, determining at least two weight allocation schemes for at least two vehicle speed prediction signals based on at least two deviation algorithms, and determining at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; S104: Determine a secondary weight distribution scheme for at least two weighted prediction signals, and determine a comprehensive vehicle speed prediction signal based on the secondary weight distribution scheme and the at least two weighted prediction signals.

[0025] The previous time period and the current time period in step S101 are continuous time periods. For example, after the vehicle starts running, the first vehicle speed signal of 45 seconds is obtained to predict the vehicle speed prediction signal within the next 30 seconds to achieve rolling prediction.

[0026] It should be noted that the vehicle speed prediction model in step S102 can be a traditional vehicle speed prediction model that predicts vehicle speed through curve fitting and moving window, or it can be a relatively novel neural network prediction model.

[0027] Specifically, the traditional vehicle speed prediction model includes but is not limited to: a least square method (Least Square Method) curve fitting algorithm and a weighted moving average (Weighted Moving Average, WMA) algorithm.

[0028] The specific prediction process is: fitting and weighted moving processing are performed on the first vehicle speed signal in the first time period to obtain a vehicle speed trend curve, and the vehicle speed in the second time period is predicted based on the vehicle speed trend curve.

[0029] Neural network prediction models include but are not limited to: Long Short Term Memory (LSTM) model and Gated Recurrent Unit (GRU) model.

[0030] The specific prediction process is as follows: train, verify and test the initial neural network model based on the sample set to obtain a fully trained neural network prediction model, input the first vehicle speed signal in the first time period into the neural network prediction model, and obtain the vehicle speed prediction signal in the second time period.

[0031] It should also be noted that the deviation algorithm is the least square method, the absolute deviation normalization accumulation method or the window moving average deviation normalization method.

[0032] It should be understood that the number of vehicle speed prediction models and the number of deviation algorithms can be set or adjusted according to the actual application scenario. For example, the higher the vehicle speed prediction accuracy, the greater the number of the two. The higher the efficiency requirement for vehicle speed prediction, the more the number of the two should be appropriately reduced.

[0033] Compared with the prior art, the vehicle speed prediction method provided by the embodiment of the present invention first inputs the first vehicle speed signal into at least two vehicle speed prediction models, predicts the vehicle speed in the current time period through at least two vehicle speed prediction models, obtains at least two vehicle speed prediction signals, and then determines the deviation between the vehicle speed prediction signal and the actual second vehicle speed signal by different deviation algorithms, and weights the vehicle speed prediction signals predicted by at least two vehicle speed prediction models based on the deviation to obtain a weighted prediction signal corresponding to the deviation algorithm one by one, and reduces the error generated by predicting the vehicle speed by a single method to a certain extent through weighted processing, thereby improving the accuracy of the determined predicted vehicle speed. Furthermore, in order to avoid the problem of deviation caused by a single deviation algorithm, the embodiment of the present invention determines a secondary weight distribution scheme for at least two weighted prediction signals after determining at least two weighted prediction signals, performs a second weighted processing on at least two weighted prediction signals, and finally obtains a comprehensive vehicle speed prediction signal, thereby further improving the accuracy of the determined comprehensive vehicle speed prediction signal. That is, the embodiment of the present invention performs weight allocation from two dimensions, namely, the prediction model and the deviation algorithm, thereby eliminating the limitations or inaccuracies caused by a single prediction algorithm and a single deviation evaluation method, and ensuring the accuracy of the obtained comprehensive vehicle speed prediction signal.

[0034] For ease of explanation, the embodiment of the present invention is described by taking an example in which a vehicle speed prediction model includes a first vehicle speed prediction model and a second vehicle speed prediction model with different model structures, and at least two deviation algorithms include a first deviation algorithm and a second deviation algorithm.

[0035] Correspondingly, the at least two vehicle speed prediction signals include a first vehicle speed prediction signal corresponding to the first vehicle speed prediction model and a second vehicle speed prediction signal corresponding to the second vehicle speed prediction model; then Figure 2 As shown, step S102 includes: S201, determining a first difference between a first vehicle speed prediction signal and a second vehicle speed signal and a second difference between a second vehicle speed prediction signal and a second vehicle speed signal based on a first deviation algorithm; S202, determining a first weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the first difference and the second difference; S203, determining a third difference between the first vehicle speed prediction signal and the second vehicle speed signal and a fourth difference between the second vehicle speed prediction signal and the second vehicle speed signal based on a second deviation algorithm; S204, determining a second weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the third difference and the fourth difference; S205. Perform weighted processing on the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the first weight allocation scheme to obtain a first weighted prediction signal, and perform weighted processing on the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the second weight allocation scheme to obtain a second weighted prediction signal.

[0036] It should be understood that the allocation principle of the first weight allocation scheme and the second weight allocation scheme is: the larger the deviation, the smaller the weight, so as to ensure that the vehicle speed prediction model with smaller deviation has a larger weight, thereby ensuring the accuracy and precision of the final vehicle speed prediction signal.

[0037] In a specific embodiment of the present invention, the weights in the weight distribution scheme are:

[0038] In the formula, is the weight of the i-th vehicle speed prediction model; is the difference between the vehicle speed prediction signal predicted by the i-th vehicle speed prediction model and the second vehicle speed signal; is the variable coefficient; is a constant; n is the total number of vehicle speed prediction models.

[0039] It should be noted that: when the deviation algorithm is the absolute deviation normalization accumulation method, the difference between the vehicle speed prediction signal predicted by each vehicle speed prediction model and the second vehicle speed signal is the normalized absolute deviation.

[0040] Specifically, the upper speed limit is determined according to the vehicle model, the absolute deviation between the predicted speed signal and the second speed signal is determined, and the ratio of the absolute deviation to the upper speed limit is used as the difference in the above weight calculation formula.

[0041] It should also be noted that: when the deviation algorithm is the window moving average deviation normalization method, the average value within the preset time length is first determined, and the initial difference between the vehicle speed prediction signal and the average value is determined, and the ratio of the initial difference to the vehicle speed upper limit is used as the difference in the weight calculation formula.

[0042] In some embodiments of the present invention, the number of deviation algorithms is 3, and the at least two weighted prediction signals in step S103 include a first weighted prediction signal corresponding to the least squares method, a second weighted prediction signal corresponding to the absolute deviation normalization accumulation method, and a third weighted prediction signal corresponding to the window moving average deviation normalization method; If Figure 3 As shown, the secondary weight allocation scheme for determining at least two weighted prediction signals in step S103 includes: S301, determining a first prediction difference between the first weighted prediction signal and the second vehicle speed signal, a second prediction difference between the second weighted prediction signal and the second vehicle speed signal, and a third prediction difference between the third weighted prediction signal and the second vehicle speed signal; S302: Determine a secondary weight allocation scheme based on the first prediction difference, the second prediction difference, and the third prediction difference.

[0043] The principle of the secondary weight allocation scheme in step S302 is: the larger the prediction difference is, the smaller its weight is.

[0044] It should be noted that the weight calculation formula in the quadratic weight allocation scheme is the same as the weight calculation formula in the aforementioned weight allocation scheme, with the inverse square root of the predicted difference as the weight numerator and the denominator being the inverse square root sum of multiple predicted differences.

[0045] The secondary weight distribution scheme includes weights corresponding to each deviation algorithm. Then, the comprehensive vehicle speed prediction signal is determined based on the secondary weight distribution scheme and at least two weighted prediction signals in step S104 as follows: the weights of each weighted prediction signal in the secondary weight distribution scheme are first multiplied by the weighted prediction signal, and then added to obtain a comprehensive vehicle speed prediction signal.

[0046] Since signal distortion may occur in the deviation processing and weighting process of the vehicle speed prediction signal, which may lead to noise pollution, in order to avoid this technical problem, in some embodiments of the present invention, before step S104, the following steps are further included: Kalman filtering is performed on each weighted prediction signal.

[0047] The embodiment of the present invention can eliminate noise pollution in the deviation processing process by performing Kalman filtering on each weighted prediction signal, improve the accuracy of the weighted prediction signal, and further improve the accuracy and precision of the final determined comprehensive vehicle speed prediction signal.

[0048] In a specific embodiment of the present invention, the number of vehicle speed prediction models is 5, and the number of deviation calculation methods is 3, namely, the least square method, the absolute deviation normalization accumulation method, and the window moving average deviation normalization method. Then the implementation process of the vehicle speed prediction method proposed in the embodiment of the present invention is specifically as follows: First, the five speed prediction models all use the data of segment A to predict the speed of segment B, and five predicted speeds will be obtained, which are respectively denoted as B Speed1 , B Speed2 , B Speed3 , B Speed4 , B Speed5 , the original speed of section B is recorded as B Speed .

[0049] Secondly, by the least squares method, evaluate B Speed1 , B Speed2 , B Speed3 , B Speed4 , B Speed5 With B Speed The deviation is obtained, and the deviation ranking is made according to the deviation size. For different ranking methods, different weights are given according to the deviation size, that is, B Weight1 , B Weight2 , BWeight3 , B Weight4 , B Weight5 After that, each vehicle speed prediction value is multiplied by the corresponding weight value, and the output model value is subjected to Kalman filtering to obtain the first weighted prediction signal Moedel1.

[0050] Then, the second weighted prediction signal Model2 is obtained by the absolute deviation normalization accumulation method, and the third weighted prediction signal Model3 is obtained by the window moving average deviation normalization method.

[0051] Finally, after secondary weight distribution for the three weighted prediction signals, the final three model values ​​are obtained, and the final comprehensive vehicle speed prediction signal is obtained through weight distribution.

[0052] This multi-dimensional vehicle speed prediction method can minimize the error caused by a single method prediction, and significantly improve the accuracy of the prediction. According to actual data verification, the average prediction deviation of the vehicle speed prediction method proposed in the embodiment of the present invention is less than 1%, which verifies its effectiveness.

[0053] In order to better implement the vehicle speed prediction method in the embodiment of the present invention, based on the vehicle speed prediction method, the embodiment of the present invention also provides a vehicle speed prediction device, such as Figure 4 As shown, the vehicle speed prediction device 400 includes: The vehicle speed signal acquisition unit 401 is used to acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; A vehicle speed prediction unit 402, configured to input the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; A first weight allocation unit 403 is used to determine at least two weight allocation schemes of at least two vehicle speed prediction signals based on at least two deviation algorithms, and determine at least two weighted prediction signals corresponding to the at least two deviation algorithms based on the at least two weight allocation schemes; The second weight allocation unit 404 is used to determine a secondary weight allocation scheme for at least two weighted prediction signals, and determine a comprehensive vehicle speed prediction signal based on the secondary weight allocation scheme and the at least two weighted prediction signals.

[0054] It should be noted that the vehicle speed prediction device 400 provided in the above embodiment can implement the technical solution described in the above vehicle speed prediction method embodiment. The specific implementation principles or specific implementation details of the above modules or units can refer to the corresponding contents in the above vehicle speed prediction method embodiment, which will not be described one by one here.

[0055] like Figure 5 As shown, the present invention also provides a vehicle 500. The vehicle 500 includes a processor 501, a memory 502 and a display 503. Figure 5 Only some of the components of vehicle 500 are shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0056] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 502, such as the vehicle speed prediction method of the present invention.

[0057] In some embodiments of the present invention, processor 501 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 501 may be local or remote. In some embodiments, processor 501 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0058] In some embodiments, the memory 502 may be an internal storage unit of the vehicle 500 , such as a hard disk or a memory of the vehicle 500 .

[0059] Furthermore, the memory 502 may include both an internal storage unit of the vehicle 500 and an external storage device. The memory 502 is used to store application software installed in the vehicle 500 and various data.

[0060] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display information of the vehicle 500 and to display a visual user interface. The components 501-503 of the vehicle 500 communicate with each other via a system bus.

[0061] In some embodiments of the present invention, when the processor 501 executes the vehicle speed prediction program in the memory 502, the following steps may be implemented: Acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; Inputting the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; Determine at least two weight allocation schemes for at least two vehicle speed prediction signals based on at least two deviation algorithms, and determine at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; A secondary weight distribution scheme of at least two weighted prediction signals is determined, and a comprehensive vehicle speed prediction signal is determined based on the secondary weight distribution scheme and the at least two weighted prediction signals.

[0062] It should be understood that: when the processor 501 executes the vehicle speed prediction program in the memory 502, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0063] Furthermore, the embodiment of the present invention does not specifically limit the type of vehicle 500 mentioned, and vehicle 500 may be a pure electric vehicle, a fuel vehicle, or a hybrid vehicle.

[0064] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the vehicle speed prediction method provided in the above-mentioned method embodiments can be implemented.

[0065] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0066] The above is a detailed introduction to a vehicle speed prediction method, device, vehicle and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A vehicle speed prediction method, characterized in that: include: Acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; Inputting the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; Determining at least two weight allocation schemes for the at least two vehicle speed prediction signals based on at least two deviation algorithms, and determining at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; A secondary weight distribution scheme of the at least two weighted prediction signals is determined, and a comprehensive vehicle speed prediction signal is determined based on the secondary weight distribution scheme and the at least two weighted prediction signals.

2. The vehicle speed prediction method according to claim 1, characterized in that: The at least two vehicle speed prediction models include a first vehicle speed prediction model and a second vehicle speed prediction model with different model structures; the at least two vehicle speed prediction signals include a first vehicle speed prediction signal corresponding to the first vehicle speed prediction model and a second vehicle speed prediction signal corresponding to the second vehicle speed prediction model; the at least two deviation algorithms include a first deviation algorithm and a second deviation algorithm; Then the step of determining at least two weight allocation schemes of the at least two vehicle speed prediction signals based on the at least two deviation algorithms, and determining at least two weighted prediction signals corresponding to the at least two deviation algorithms based on the at least two weight allocation schemes, includes: determining a first difference between the first vehicle speed prediction signal and the second vehicle speed signal and a second difference between the second vehicle speed prediction signal and the second vehicle speed signal based on the first deviation algorithm; determining a first weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the first difference and the second difference; determining a third difference between the first vehicle speed prediction signal and the second vehicle speed signal and a fourth difference between the second vehicle speed prediction signal and the second vehicle speed signal based on the second deviation algorithm; determining a second weight allocation scheme for the first vehicle speed prediction signal and the second vehicle speed prediction signal based on the third difference and the fourth difference; The first vehicle speed prediction signal and the second vehicle speed prediction signal are weighted based on the first weight allocation scheme to obtain a first weighted prediction signal, and the first vehicle speed prediction signal and the second vehicle speed prediction signal are weighted based on the second weight allocation scheme to obtain a second weighted prediction signal.

3. The vehicle speed prediction method according to claim 1, characterized in that: The weights in the weight distribution scheme are: In the formula, is the weight of the i-th vehicle speed prediction model; is the difference between the vehicle speed prediction signal predicted by the i-th vehicle speed prediction model and the second vehicle speed signal; is the variable coefficient; is a constant; n is the total number of vehicle speed prediction models.

4. The vehicle speed prediction method according to claim 1, characterized in that: The deviation algorithm is the least square method, the absolute deviation normalization accumulation method or the window moving average deviation normalization method.

5. The vehicle speed prediction method according to claim 4, characterized in that: The at least two weighted prediction signals include a first weighted prediction signal corresponding to the least square method, a second weighted prediction signal corresponding to the absolute deviation normalization accumulation method, and a third weighted prediction signal corresponding to the window moving average deviation normalization method; Then the determining of the secondary weight allocation scheme of the at least two weighted prediction signals includes: Determining a first prediction difference between the first weighted prediction signal and the second vehicle speed signal, a second prediction difference between the second weighted prediction signal and the second vehicle speed signal, and a third prediction difference between the third weighted prediction signal and the second vehicle speed signal; The secondary weight allocation scheme is determined based on the first prediction difference value, the second prediction difference value, and the third prediction difference value.

6. The vehicle speed prediction method according to claim 1, characterized in that: The vehicle speed prediction model is a least squares curve fitting algorithm, a moving average window algorithm, a long short-term memory network model or a gated recurrent unit network model.

7. The vehicle speed prediction method according to claim 1, characterized in that: Before determining the secondary weight allocation scheme of the at least two weighted prediction signals, the method further includes: Kalman filtering is performed on each of the weighted prediction signals.

8. A vehicle speed prediction device, characterized in that: include: A vehicle speed signal acquisition unit, used to acquire a first vehicle speed signal in a previous time period and a second vehicle speed signal in a current time period; a vehicle speed prediction unit, configured to input the first vehicle speed signal into at least two vehicle speed prediction models to obtain at least two vehicle speed prediction signals; a first weight allocation unit, configured to determine at least two weight allocation schemes of the at least two vehicle speed prediction signals based on at least two deviation algorithms, and to determine at least two weighted prediction signals corresponding one-to-one to the at least two deviation algorithms based on the at least two weight allocation schemes; The second weight allocation unit is used to determine a secondary weight allocation scheme for the at least two weighted prediction signals, and determine a comprehensive vehicle speed prediction signal based on the secondary weight allocation scheme and the at least two weighted prediction signals.

9. A vehicle, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the vehicle speed prediction method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps in the vehicle speed prediction method described in any one of claims 1 to 7 are implemented.

Images