Vehicle road condition prediction methods and vehicles

Abstract

This application provides a method and vehicle for predicting road conditions for a vehicle. The method includes: acquiring driving information of a target vehicle ahead; outputting road condition information of the target vehicle based on the driving information and a target road condition prediction model; fusing the road condition information of multiple target vehicles to obtain fused information; and determining the road conditions of the road where the target vehicle is located based on the fused information. This method uses the driving information of the target vehicle ahead, inputs it into a target road condition prediction model to output multiple road condition information of the target vehicle, and then fuses these multiple road condition information to determine the road conditions of the road where the target vehicle is located. This improves the anti-interference ability and accuracy of vehicle road condition prediction, thereby solving the problem of insufficient accuracy in predicting future road conditions using information from the target vehicle in existing technologies.

Description

Technical Field

[0001] This application relates to vehicles, and more specifically, to a method for predicting road conditions for a vehicle, a computer-readable storage medium, a processor, and a vehicle. Background Technology

[0002] The efficient use of vehicle energy is a problem that requires continuous optimization. If the future driving conditions of a vehicle can be accurately predicted, it will play a key role in the intelligent energy management of the whole vehicle. In the current technology, due to the complexity of the actual traffic environment and other factors, the identification information of the vehicle in front of the target vehicle is relatively simple. The use of information is not comprehensive or accurate, and it does not take into account the interference of special situations, so it cannot guarantee the accuracy of the prediction results. Moreover, there is usually only one target vehicle in front used to predict driving conditions. In terms of the way of obtaining operating condition information, there are problems such as the single factor consideration and insufficient effectiveness of the acquisition method, which leads to low accuracy of the acquired data information and weak reference for future driving conditions.

[0003] There is currently no effective solution to the aforementioned problems in the relevant technologies.

[0004] The information disclosed above in the background section is only intended to enhance the understanding of the background art of the art described herein. Therefore, the background art may contain certain information that does not constitute prior art known to those skilled in the art in this country. Summary of the Invention

[0005] The main objective of this application is to provide a method for predicting road conditions for a vehicle, a computer-readable storage medium, a processor, and a vehicle, in order to solve the problem that the prediction of future road conditions for a vehicle based on information from a preceding vehicle is not accurate enough in the prior art.

[0006] To achieve the above objectives, according to one aspect of this application, a method for predicting road conditions for a vehicle is provided, comprising: acquiring driving information of a target vehicle ahead, wherein the driving information includes driving environment information and driving parameters, and the target vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel; based on the driving information, outputting road condition information of the target vehicle ahead through a target road condition prediction model, wherein the road condition information represents the road condition where the target vehicle is located, and the target road condition prediction model is trained using multiple sets of historical data, each set of historical data including: historical driving information of the target vehicle ahead and historical road condition information of the target vehicle ahead; fusing the road condition information of multiple target vehicles ahead to obtain fused information; and determining the road condition of the road where the target vehicle is located based on the fused information.

[0007] Furthermore, the method includes: when the distance between the vehicle in front and the target vehicle is within a preset distance range, the vehicle in front has an onboard sensor, the vehicle in front and the target vehicle are traveling in the same direction, and the lane where the vehicle in front is located is the same as the lane where the target vehicle is located, acquiring the time corresponding to the overlapping trajectory of the target vehicle's driving trajectory and the historical driving trajectory of the vehicle in front, wherein the vehicle in front is a vehicle located on one side of the target vehicle's direction of travel; and when the time corresponding to the overlapping trajectory is greater than a preset time, identifying the vehicle in front as the target vehicle in front.

[0008] Furthermore, the method also includes: constructing an initial traffic condition prediction model, wherein the initial traffic condition prediction model includes an input layer, a hidden layer, and an output layer; acquiring multiple historical driving information and multiple historical traffic condition information; training the initial traffic condition prediction model based on the multiple historical driving information and multiple historical traffic condition information, wherein the input layer receives multiple sets of historical data and sends the multiple sets of historical data to the hidden layer, the hidden layer controls multiple weights corresponding to multiple historical driving information to form a recognition pattern bias, and sends the multiple sets of historical data and multiple weights to the output layer, the output layer adjusts multiple weights according to the historical traffic condition information to obtain the target traffic condition prediction model, wherein the recognition pattern bias represents the operation corresponding to the processing of multiple sets of historical data, and the operation includes any one of the following: classification processing operation, regression analysis operation.

[0009] Furthermore, based on the driving information, the target road condition prediction model outputs the road condition information of the vehicle ahead, including: obtaining the recognition mode bias corresponding to the hidden layer of the target road condition prediction model; and controlling the target road condition prediction model to output the road condition information based on the recognition mode bias.

[0010] Furthermore, based on the identification pattern bias, the target traffic condition prediction model is controlled to output traffic condition information, including: when the identification pattern bias is a classification processing operation, the target traffic condition prediction model is controlled to output first traffic condition information, wherein the first traffic condition information represents the road condition category, and the road condition category includes at least: urban condition, rural condition, and highway condition; when the identification pattern bias is a regression analysis operation, the target traffic condition prediction model is controlled to output second traffic condition information, wherein the second traffic condition information represents the degree of road congestion.

[0011] Furthermore, the road condition information of multiple vehicles ahead of the target is fused to obtain target fusion information, including: obtaining the number of vehicles surrounding the vehicle ahead of the target, wherein the surrounding vehicles are vehicles whose distance from the vehicle ahead of the target is within a preset range; obtaining the road condition distance, wherein the road condition distance is the distance from the starting point of the preset distance range to the current position of the vehicle ahead of the target; determining the prediction score of multiple road condition information according to the formula g=a×l+(1-a)×n, wherein g is the prediction score, a is the weight of the road condition distance, l is the road condition distance, and n is the number of surrounding vehicles; comparing the size of multiple prediction scores to obtain the maximum prediction score; and determining the road condition information of the vehicle ahead of the target corresponding to the maximum prediction score as the target fusion information.

[0012] Furthermore, the method also includes: deleting outlier traffic information from multiple traffic information sets, wherein outlier traffic information is traffic information whose proportion is less than a preset proportion among the multiple traffic information sets.

[0013] To achieve the above objectives, according to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes any of the above-described methods for predicting road conditions for a vehicle.

[0014] To achieve the above objectives, according to another aspect of this application, a processor is provided, which runs a program that executes any of the above-described methods for predicting road conditions for vehicles.

[0015] To achieve the above objectives, according to another aspect of this application, a vehicle is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for performing a road condition prediction method for any of the above-described vehicles.

[0016] By applying the technical solution of this application, the driving information of the target vehicle ahead is obtained, including driving environment information and driving parameters. The target vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel. Based on the driving information, a target road condition prediction model is used to output the road condition information of the target vehicle ahead. The road condition information represents the driving road condition of the target vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data, each set of historical data including the historical driving information and historical road condition information of the target vehicle ahead. The road condition information of multiple target vehicles ahead is fused to obtain fused information. Based on the fused information, the driving road condition of the road where the target vehicle is located is determined. This solves the problem of insufficient accuracy in predicting the future driving road condition of a vehicle using information from the target vehicle ahead in the prior art, thereby improving the anti-interference and accuracy of the vehicle's driving road condition prediction. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 The flowchart of a vehicle road condition prediction method according to an embodiment of this application is shown. Figure 1 ;

[0019] Figure 2 A schematic diagram of a target road condition prediction model according to an embodiment of this application is shown;

[0020] Figure 3 A schematic diagram of a vehicle road condition prediction device according to an embodiment of this application is shown;

[0021] Figure 4 The flowchart of a vehicle road condition prediction method according to an embodiment of this application is shown. Figure 2 ;

[0022] Figure 5 A schematic diagram of a target vehicle road condition identification method according to an embodiment of this application is shown. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element may be directly on the other element, or there may be an intermediate element present. Furthermore, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element, or "connected" to the other element via a third element.

[0027] As mentioned in the background section, the prior art lacks the ability to accurately predict future road conditions of a vehicle based on information from preceding vehicles. To address this issue, in a typical embodiment of this application, a method for predicting road conditions of a vehicle, a computer-readable storage medium, a processor, and a vehicle are provided.

[0028] According to an embodiment of this application, a method for predicting road conditions for vehicles is provided.

[0029] Figure 1 This is a flowchart of a vehicle road condition prediction method according to an embodiment of this application. Figure 1 .like Figure 1 As shown, the method includes the following steps:

[0030] Step S101: Obtain the driving information of the vehicle ahead of the target. The driving information includes driving environment information and driving parameters. The vehicle ahead of the target is the vehicle located on the side of the target vehicle's direction of travel.

[0031] Step S102: Based on the driving information, the road condition information of the vehicle ahead is output through the target road condition prediction model. The road condition information represents the driving road condition of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. Each set of historical data includes: the historical driving information of the vehicle ahead and the historical road condition information of the vehicle ahead.

[0032] Step S103: The road condition information of multiple vehicles ahead is fused to obtain fused information;

[0033] Step S104: Based on the fused information, determine the road conditions of the road where the target vehicle is located.

[0034] The above-mentioned process first involves acquiring the driving information of the vehicle ahead, including driving environment information and driving parameters. The vehicle ahead is the vehicle located on the side of the target vehicle's direction of travel. Then, based on the driving information, a target road condition prediction model is used to output the road condition information of the vehicle ahead. The road condition information represents the road conditions where the vehicle ahead is traveling. The target road condition prediction model is trained using multiple sets of historical data, each set of historical data including the historical driving information and historical road condition information of the vehicle ahead. Next, the road condition information of multiple vehicles ahead is fused to obtain fused information. Finally, based on the fused information, the road conditions of the road where the target vehicle is located are determined. In this method, driving information is acquired and input into a target road condition prediction model. The target road condition prediction model outputs road condition information of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. By acquiring and training multiple sets of historical data, the target road condition prediction model has higher accuracy. The road condition information is related to the operation of the target road condition prediction model in processing multiple sets of historical data. It can provide effective road condition information as energy management decision for the target vehicle, solving the problem that the prediction of the future driving road condition of the vehicle based on the information of the vehicle ahead is not accurate enough in the existing technology, thereby improving the anti-interference and accuracy of the vehicle's driving road condition prediction.

[0035] In this application, the driving information of the vehicle ahead includes, but is not limited to, the average speed, average acceleration, slope information, lane information, number of surrounding vehicles, average speed, and average acceleration of surrounding vehicles. Faced with complex traffic conditions, this application collects driving information more comprehensively, resulting in higher accuracy in traffic condition prediction. The traffic condition information is related to the operations performed by the target traffic condition prediction model on multiple sets of historical data. For example, when the operation is a classification process, the traffic condition information includes urban, rural, and highway conditions; when it is a regression analysis process, the traffic condition information is the congestion coefficient. This traffic condition information is used as the basis for the target vehicle's energy management decisions.

[0036] In this application, the road condition information of the vehicle ahead output by the target road condition prediction model may still contain errors. It is necessary to fuse multiple road condition information to eliminate errors and obtain more accurate road condition information, i.e. fused information. With more accurate road condition information, the driving conditions of the road where the target vehicle is located can be determined, so that the vehicle energy utilization rate is higher and it is more economical and environmentally friendly.

[0037] In an optional embodiment, the method includes: when the distance between the vehicle ahead and the target vehicle is within a preset distance range, the vehicle ahead has an onboard sensor, the vehicle ahead and the target vehicle are traveling in the same direction, and the lane where the vehicle ahead is located is the same as the lane where the target vehicle is located, acquiring the time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle ahead, wherein the vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel; and when the time corresponding to the overlap is greater than a preset time, identifying the vehicle ahead as the target vehicle ahead. In this method, a vehicle ahead that meets multiple conditions is identified as the target vehicle ahead. These conditions include: the distance between the vehicle ahead and the target vehicle is within a preset distance range, the vehicle ahead has an onboard sensor, the vehicle ahead and the target vehicle are traveling in the same direction, the lane where the vehicle ahead is located is the same as the lane where the target vehicle is located, and the time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle ahead is greater than a preset time. This makes it meaningful to predict the target vehicle's driving conditions using the road condition information of the vehicle ahead, ensuring that the target vehicle will eventually travel to the road condition where the vehicle ahead is located, thus improving the accuracy of predicting the target vehicle's driving conditions using the road condition information of the vehicle ahead.

[0038] Specifically, the V2V (vehicle-to-vehicle) communication system and GPS positioning system are used to identify the distance to the vehicle ahead, its orientation, and sensor type. The V2I (vehicle-to-infrastructure) interconnection system is used to identify the current lane type of the vehicle ahead, the target vehicle's lane type, and historical road segments. The determination of the target vehicle ahead requires the following conditions to be met: 1) The distance between the vehicle ahead and the target vehicle is within a preset distance range. Predicting road conditions too close is meaningless, and predicting road conditions too far away will result in significant errors. Therefore, the distance between the target vehicle ahead and the target vehicle must be within a preset distance range, which can be set according to actual needs; 2) The vehicle ahead has onboard sensors. Complete onboard sensors ensure that all necessary information can be collected, resulting in more comprehensive driving information and more accurate road condition information output by the target road condition prediction model; 3) The vehicle ahead and the target vehicle are traveling in the same direction and in the same lane. This indicates that the driving direction or future driving route is consistent with the target vehicle within a preset distance range, making it more meaningful to predict the driving conditions of the target vehicle based on the vehicle in front; 4) The time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle in front is greater than the preset time.

[0039] It should be noted that all vehicles ahead that meet the above conditions are target vehicles ahead in this application. The target vehicles ahead in this application are not unique. The purpose is to minimize the error caused by a single target vehicle ahead and avoid the problem of decreased prediction accuracy due to inaccurate information of individual vehicles. This improves the stability of the prediction of the target vehicle's driving conditions.

[0040] In an optional embodiment, the method further includes: constructing an initial traffic condition prediction model, wherein the initial traffic condition prediction model includes an input layer, a hidden layer, and an output layer; acquiring multiple historical driving information and multiple historical traffic condition information; training the initial traffic condition prediction model based on the multiple historical driving information and multiple historical traffic condition information, wherein the input layer receives multiple sets of historical data and sends the multiple sets of historical data to the hidden layer, the hidden layer controls multiple weights corresponding to multiple historical driving information to form a recognition pattern bias, and sends the multiple sets of historical data and multiple weights to the output layer, the output layer adjusts the multiple weights according to the historical traffic condition information to obtain a target traffic condition prediction model, wherein the recognition pattern bias represents the operation corresponding to processing multiple sets of historical data, and the operation includes any one of the following: classification processing operation, regression analysis operation. In this method, road condition information is output by modeling historical driving and road condition information acquired by vehicles. The driving information collected by vehicles ahead is used to predict road conditions. The initial road condition prediction model is built and calculated offline based on big data. Deep modeling is performed between historical driving and road condition information to acquire prior knowledge and obtain an accurate target road condition prediction model. The road condition prediction model trained based on historical driving and road condition information has a more realistic effect on actual road conditions, making the output results of the road condition prediction model more accurate. The target road condition prediction model makes the road condition prediction more resistant to interference.

[0041] Specifically, such as Figure 2 As shown, Figure 2 A schematic diagram of a target road condition prediction model according to an embodiment of this application is shown. The road condition prediction model can be a neural network model. The future road condition prediction of the target vehicle is not only based on historical driving information and historical road condition information over a period of time, but also on big data to model the road condition prediction model. The historical driving information and historical road condition information acquired by the vehicle are modeled and output as road condition information. Thus, the driving information collected by the vehicle ahead is used to predict the road condition, and the data is transmitted to the target vehicle through a V2V vehicle-to-vehicle communication system to predict the future driving road conditions.

[0042] In one optional embodiment, based on driving information, a target road condition prediction model outputs road condition information of the vehicle ahead, including: obtaining the recognition pattern bias corresponding to the hidden layer of the target road condition prediction model; and controlling the target road condition prediction model to output road condition information based on the recognition pattern bias. In this method, the road condition information output by the target road condition prediction model based on the recognition pattern bias allows different road condition information to provide different effective information for the vehicle's energy management decisions, resulting in higher energy utilization, greater economy and environmental friendliness, and maximizing the vehicle's driving range.

[0043] Specifically, the identification pattern bias is the operation corresponding to multiple sets of historical data that is characterized by the identification pattern bias. The operation includes any of the following: classification processing operation, regression analysis operation. Depending on the operation, the output road condition information will also be different for the driving information input into the target road condition prediction model.

[0044] In one optional embodiment, the target traffic condition prediction model is controlled to output traffic condition information based on the identification pattern bias. This includes: when the identification pattern bias is a classification processing operation, the target traffic condition prediction model is controlled to output first traffic condition information, wherein the first traffic condition information represents the road condition category, which includes at least: urban conditions, rural conditions, and highway conditions; when the identification pattern bias is a regression analysis operation, the target traffic condition prediction model is controlled to output second traffic condition information, wherein the second traffic condition information represents the degree of road congestion. In this method, different identification pattern biases result in different output traffic condition information, and different traffic condition information can provide vehicles with effective information for energy management decisions, thereby improving vehicle energy utilization.

[0045] Specifically, when the recognition mode is biased towards classification processing, the road condition information includes at least urban conditions, rural conditions, and highway conditions. When the recognition mode is biased towards regression analysis, the road condition information is the congestion coefficient. Inputting driving information, the output road condition information is either the road condition classification result or the congestion coefficient. For example, when the recognition mode is biased towards classification processing, the output road condition information is urban conditions, and the vehicle makes energy management decisions based on urban road conditions. When the recognition mode is biased towards regression analysis, and the road condition information has a congestion coefficient of five (note: in this embodiment, the congestion coefficient ranges from one to ten), the vehicle makes energy management decisions based on a congestion coefficient of five.

[0046] In one optional embodiment, road condition information of multiple vehicles ahead of a target is fused to obtain target fused information, including: obtaining the number of vehicles surrounding the vehicle ahead of the target, wherein the surrounding vehicles are vehicles whose distance from the vehicle ahead of the target is within a preset range; obtaining the road condition distance, wherein the road condition distance is the distance from the starting point of the preset distance range to the current position of the vehicle ahead of the target; determining the prediction score of multiple road condition information according to the formula g=a×l+(1-a)×n, wherein g is the prediction score, a is the weight of the road condition distance, l is the road condition distance, and n is the number of surrounding vehicles; comparing the size of the multiple prediction scores to obtain the maximum prediction score; and determining the road condition information of the vehicle ahead of the target corresponding to the maximum prediction score as the target fused information. In this method, there may still be significant discrepancies in road condition information within a preset distance range. Therefore, the road condition distance and the number of surrounding vehicles need to be weighted to further eliminate errors. A prediction score is calculated using a formula, and the road condition information with the higher score is used as the final judgment of the vehicle's driving road condition. The starting position of the road condition is stored and updated in real time to ensure that it is always within the preset distance range. By fusing road condition information, the interference of adverse factors is further eliminated, the anti-interference ability is improved, and the prediction of the future driving road condition of the target vehicle is more accurate.

[0047] Specifically, the road condition distance is the distance from the starting point of a preset distance range to the current position of the vehicle ahead of the target. Vehicles within the preset distance range are considered as surrounding vehicles. The preset range is set according to requirements. Considering road condition information that may differ significantly within the preset distance range, the effective factors are weighted to calculate a road condition prediction score, and the highest score is used as the final predicted road condition.

[0048] In an optional embodiment, the method further includes: deleting outlier road condition information from multiple road condition information sets, wherein outlier road condition information is defined as road condition information whose proportion among the multiple road condition information sets is less than a preset proportion. In this method, the multiple road condition information sets output by the target road condition prediction model may contain road condition information that differs from other road condition information sets, and the proportion of road condition information differing from other road condition information sets is less than a preset proportion, which can be set according to actual needs. Road condition information differing from other road condition information sets is identified as outlier road condition information, and deleting outlier road condition information eliminates errors caused by the road condition information.

[0049] Specifically, when the recognition mode is biased towards classification processing, with a preset proportion of 20%, nine out of the ten output traffic condition information are urban traffic conditions, one is a rural traffic condition, and the rural traffic condition accounts for 10% of the ten traffic condition information, which is less than the preset proportion. Therefore, the rural traffic condition is considered an outlier traffic condition. When the recognition mode is biased towards regression analysis, with a preset proportion of 20%, nine out of the ten output traffic condition information have a congestion coefficient of five, one has a congestion coefficient of nine, and the one with a congestion coefficient of nine accounts for 10% of the ten traffic condition information, which is less than the preset proportion. Therefore, the traffic condition with a congestion coefficient of nine is considered an outlier traffic condition.

[0050] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0051] This invention provides a computer-readable storage medium storing a program that, when executed by a processor, implements the aforementioned method for predicting road conditions for a vehicle.

[0052] This invention provides a processor for running a program, wherein the program executes the aforementioned method for predicting road conditions for a vehicle.

[0053] This invention provides a vehicle, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing road condition prediction for any of the aforementioned vehicles.

[0054] This application also provides a vehicle traffic condition prediction device. It should be noted that the vehicle traffic condition prediction device of this application can be used to execute the vehicle traffic condition prediction method provided in this application. The following describes the vehicle traffic condition prediction device provided in this application.

[0055] Figure 3 This is a schematic diagram of a vehicle road condition prediction device according to an embodiment of this application. Figure 3As shown, the device includes: a first acquisition unit 301, used to acquire driving information of a target vehicle ahead, wherein the driving information includes driving environment information and driving parameters, and the target vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel; an output unit 302, used to output road condition information of the target vehicle ahead based on the driving information and through a target road condition prediction model, wherein the road condition information represents the driving road condition of the target vehicle ahead, and the target road condition prediction model is trained using multiple sets of historical data, each set of historical data including: historical driving information of the target vehicle ahead and historical road condition information of the target vehicle ahead; a fusion unit 303, used to fuse the road condition information of multiple target vehicles ahead and obtain fused information; and a first determination unit 304, used to determine the driving road condition of the road where the target vehicle is located based on the fused information.

[0056] The above-mentioned process first involves acquiring the driving information of the vehicle ahead, including driving environment information and driving parameters. The vehicle ahead is the vehicle located on the side of the target vehicle's direction of travel. Then, based on the driving information, a target road condition prediction model is used to output the road condition information of the vehicle ahead. The road condition information represents the road conditions where the vehicle ahead is traveling. The target road condition prediction model is trained using multiple sets of historical data, each set of historical data including the historical driving information and historical road condition information of the vehicle ahead. Next, the road condition information of multiple vehicles ahead is fused to obtain fused information. Finally, based on the fused information, the road conditions of the road where the target vehicle is located are determined. In this device, driving information is acquired and input into a target road condition prediction model. The target road condition prediction model outputs road condition information of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. By acquiring and training multiple sets of historical data, the target road condition prediction model has higher accuracy. The road condition information is related to the operation of the target road condition prediction model in processing multiple sets of historical data. It can provide effective road condition information as energy management decision-making for the target vehicle, solving the problem that the prediction of future driving road conditions of a vehicle based on the information of the vehicle ahead is not accurate enough in the existing technology. This improves the anti-interference and accuracy of the vehicle's driving road condition prediction.

[0057] In this application, the driving information of the vehicle ahead includes, but is not limited to, the average speed, average acceleration, slope information, lane information, number of surrounding vehicles, average speed, and average acceleration of surrounding vehicles. Faced with complex traffic conditions, this application collects driving information more comprehensively, resulting in higher accuracy in traffic condition prediction. The traffic condition information is related to the operations performed by the target traffic condition prediction model on multiple sets of historical data. For example, when the operation is a classification process, the traffic condition information includes urban, rural, and highway conditions; when it is a regression analysis process, the traffic condition information is the congestion coefficient. This traffic condition information is used as the basis for the target vehicle's energy management decisions.

[0058] In this application, the road condition information of the vehicle ahead output by the target road condition prediction model may still contain errors. It is necessary to fuse multiple road condition information to eliminate errors and obtain more accurate road condition information, i.e. fused information. With more accurate road condition information, the driving conditions of the road where the target vehicle is located can be determined, so that the vehicle energy utilization rate is higher and it is more economical and environmentally friendly.

[0059] In one optional embodiment, the device includes: a second acquisition unit, configured to acquire the time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle in front, wherein the vehicle in front is located on one side of the target vehicle's direction of travel, provided that the distance between the vehicle in front and the target vehicle is within a preset distance range, the vehicle in front has an onboard sensor, the vehicle in front and the target vehicle are traveling in the same direction, and the lane in front is in the same lane as the target vehicle; and a second determination unit, configured to determine the vehicle in front as the target vehicle in front if the time corresponding to the overlap trajectory is greater than a preset time. In this device, a vehicle in front that meets multiple conditions is determined as the target vehicle in front. These conditions include: the distance between the vehicle in front and the target vehicle is within a preset distance range, the vehicle in front has an onboard sensor, the vehicle in front and the target vehicle are traveling in the same direction, the lane in front is in the same lane as the target vehicle, and the time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle in front is greater than a preset time. This makes it meaningful to predict the target vehicle's driving conditions using the road condition information of the vehicle in front, ensuring that the target vehicle will eventually travel to the road condition where the vehicle in front is located, and improving the accuracy of predicting the target vehicle's driving conditions using the road condition information of the vehicle in front.

[0060] Specifically, the V2V (vehicle-to-vehicle) communication system and GPS positioning system are used to identify the distance to the vehicle ahead, its orientation, and sensor type. The V2I (vehicle-to-infrastructure) interconnection system is used to identify the current lane type of the vehicle ahead, the target vehicle's lane type, and historical road segments. The determination of the target vehicle ahead requires the following conditions to be met: 1) The distance between the vehicle ahead and the target vehicle is within a preset distance range. Predicting road conditions too close is meaningless, and predicting road conditions too far away will result in significant errors. Therefore, the distance between the target vehicle ahead and the target vehicle must be within a preset distance range, which can be set according to actual needs; 2) The vehicle ahead has onboard sensors. Complete onboard sensors ensure that all necessary information can be collected, resulting in more comprehensive driving information and more accurate road condition information output by the target road condition prediction model; 3) The vehicle ahead and the target vehicle are traveling in the same direction and in the same lane. This indicates that the driving direction or future driving route is consistent with the target vehicle within a preset distance range, making it more meaningful to predict the driving conditions of the target vehicle based on the vehicle in front; 4) The time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle in front is greater than the preset time.

[0061] It should be noted that all vehicles ahead that meet the above conditions are target vehicles ahead in this application. The target vehicles ahead in this application are not unique. The purpose is to minimize the error caused by a single target vehicle ahead and avoid the problem of decreased prediction accuracy due to inaccurate information of individual vehicles. This improves the stability of the prediction of the target vehicle's driving conditions.

[0062] In an optional embodiment, the device further includes: a construction unit for constructing an initial traffic condition prediction model, wherein the initial traffic condition prediction model includes an input layer, a hidden layer, and an output layer; a third acquisition unit for acquiring multiple historical driving information and multiple historical traffic condition information; and a training unit for training the initial traffic condition prediction model based on the multiple historical driving information and multiple historical traffic condition information, wherein the input layer receives multiple sets of historical data and sends the multiple sets of historical data to the hidden layer, the hidden layer controls multiple weights corresponding to the multiple historical driving information to form a recognition pattern bias, and sends the multiple sets of historical data and multiple weights to the output layer, the output layer adjusts the multiple weights according to the historical traffic condition information to obtain a target traffic condition prediction model, wherein the recognition pattern bias represents the operation corresponding to processing the multiple sets of historical data, and the operation includes any one of the following: classification processing operation and regression analysis operation. In this device, road condition information is output by modeling historical driving and road condition information acquired by vehicles. The driving information collected by vehicles ahead is used to predict road conditions. The initial road condition prediction model is built and calculated offline based on big data. Deep modeling is performed between historical driving and road condition information to acquire prior knowledge and obtain an accurate target road condition prediction model. The road condition prediction model trained based on historical driving and road condition information has a more realistic effect on actual road conditions, making the output results of the road condition prediction model more accurate. The target road condition prediction model makes the road condition prediction more resistant to interference.

[0063] Specifically, such as Figure 2 As shown, Figure 2 A schematic diagram of a target road condition prediction model according to an embodiment of this application is shown. The road condition prediction model can be a neural network model. The future road condition prediction of the target vehicle is not only based on historical driving information and historical road condition information over a period of time, but also on big data to model the road condition prediction model. The historical driving information and historical road condition information acquired by the vehicle are modeled and output as road condition information. Thus, the driving information collected by the vehicle ahead is used to predict the road condition, and the data is transmitted to the target vehicle through a V2V vehicle-to-vehicle communication system to predict the future driving road conditions.

[0064] In one optional embodiment, the output unit 302 includes: a first acquisition subunit, configured to acquire the recognition pattern bias corresponding to the hidden layer of the target road condition prediction model; and a control subunit, configured to control the target road condition prediction model to output road condition information based on the recognition pattern bias. In this device, road condition information is output through the target road condition prediction model based on the recognition pattern bias. Different road condition information can provide different effective information for the vehicle's energy management decisions, resulting in higher energy utilization, greater economy and environmental friendliness, and maximizing the vehicle's driving range.

[0065] Specifically, the identification pattern bias is the operation corresponding to multiple sets of historical data that is characterized by the identification pattern bias. The operation includes any of the following: classification processing operation, regression analysis operation. Depending on the operation, the output road condition information will also be different for the driving information input into the target road condition prediction model.

[0066] In one optional embodiment, the control subunit includes: a first control module, configured to control the target road condition prediction model to output first road condition information when the identification mode bias is classification processing, wherein the first road condition information represents road condition categories, and the road condition categories include at least: urban conditions, rural conditions, and highway conditions; and a second control module, configured to control the target road condition prediction model to output second road condition information when the identification mode bias is regression analysis, wherein the second road condition information represents the degree of road congestion. In this device, different identification mode biases result in different output road condition information, and different road condition information can provide vehicles with effective information for energy management decisions, thereby improving vehicle energy utilization.

[0067] Specifically, when the recognition mode is biased towards classification processing, the road condition information includes at least urban conditions, rural conditions, and highway conditions. When the recognition mode is biased towards regression analysis, the road condition information is the congestion coefficient. Inputting driving information, the output road condition information is either the road condition classification result or the congestion coefficient. For example, when the recognition mode is biased towards classification processing, the output road condition information is urban conditions, and the vehicle makes energy management decisions based on urban road conditions. When the recognition mode is biased towards regression analysis, and the road condition information has a congestion coefficient of five (note: in this embodiment, the congestion coefficient ranges from one to ten), the vehicle makes energy management decisions based on a congestion coefficient of five.

[0068] In an optional embodiment, the fusion unit 303 includes: a second acquisition subunit, configured to acquire the number of vehicles surrounding the target vehicle, wherein the surrounding vehicles are vehicles whose distance from the target vehicle is within a preset range; a third acquisition subunit, configured to acquire road condition distance, wherein the road condition distance is the distance from the starting point of the preset distance range to the current position of the target vehicle; a first determination subunit, configured to determine the prediction scores of multiple road condition information according to the formula g=a×l+(1-a)×n, wherein g is the prediction score, a is the weight of the road condition distance, l is the road condition distance, and n is the number of surrounding vehicles; a comparison subunit, configured to compare the size of the multiple prediction scores to obtain the maximum prediction score; and a second determination subunit, configured to determine the road condition information of the target vehicle corresponding to the maximum prediction score as the target fusion information. In this device, there may still be significant discrepancies in road condition information within a preset distance range. The road condition distance needs to be weighted by the number of surrounding vehicles to further eliminate errors. A prediction score is calculated using a formula, and the road condition information with the higher score is used as the final judgment of the vehicle's driving road condition. The starting position of the road condition is stored and updated in real time to ensure that it is always within the preset distance range. By fusing road condition information, interference from adverse factors is further eliminated, the anti-interference ability is improved, and the prediction of the future driving road condition of the target vehicle is more accurate.

[0069] Specifically, the road condition distance is the distance from the starting point of a preset distance range to the current position of the vehicle ahead of the target. Vehicles within the preset distance range are considered as surrounding vehicles. The preset range is set according to requirements. Considering road condition information that may differ significantly within the preset distance range, the effective factors are weighted to calculate a road condition prediction score, and the highest score is used as the final predicted road condition.

[0070] In an optional embodiment, the device further includes a deletion unit for deleting outlier road condition information from multiple road condition information sets. The outlier road condition information is defined as road condition information whose proportion among the multiple road condition information sets is less than a preset proportion. In this device, the multiple road condition information sets output by the target road condition prediction model may contain road condition information that differs from other road condition information sets. The number of road condition information sets that differ from other road condition information sets is less than a preset proportion in the total number of road condition information sets. The preset proportion can be set according to actual needs. Road condition information sets that differ from other road condition information sets are identified as outlier road condition information, and these outlier road condition information sets are deleted to eliminate errors caused by the road condition information.

[0071] Specifically, when the recognition mode is biased towards classification processing, with a preset proportion of 20%, nine out of the ten output traffic condition information are urban traffic conditions, one is a rural traffic condition, and the rural traffic condition accounts for 10% of the ten traffic condition information, which is less than the preset proportion. Therefore, the rural traffic condition is considered an outlier traffic condition. When the recognition mode is biased towards regression analysis, with a preset proportion of 20%, nine out of the ten output traffic condition information have a congestion coefficient of five, one has a congestion coefficient of nine, and the one with a congestion coefficient of nine accounts for 10% of the ten traffic condition information, which is less than the preset proportion. Therefore, the traffic condition with a congestion coefficient of nine is considered an outlier traffic condition.

[0072] To enable those skilled in the art to more clearly understand the technical solution of this application, the following description will be provided in conjunction with specific embodiments:

[0073] Example

[0074] In one embodiment provided in this application, such as Figure 4 As shown, Figure 4 The flowchart of a vehicle road condition prediction method according to an embodiment of this application is shown. Figure 2 By filtering target vehicles ahead through V2V vehicle-to-vehicle communication systems and V2I vehicle infrastructure interconnection systems, and acquiring the driving information of target vehicles ahead, a target road condition prediction model is obtained by modeling historical driving information and historical road condition information acquired through V2V vehicle-to-vehicle communication systems and V2I vehicle infrastructure interconnection systems. The target road condition prediction model is then used to calculate the road condition information of target vehicles ahead, and multiple road condition information is fused. The fused information is used to predict the future driving road conditions of target vehicles, thereby improving the stability of the target vehicle's driving road condition prediction.

[0075] Specifically, V2V (Vehicle-to-Vehicle) communication systems connect vehicles into a network, enabling real-time information transmission between them. V2I (Vehicle-to-Infrastructure) systems allow vehicles to communicate with infrastructure, ensuring more comprehensive access to information that other vehicles cannot obtain through sensors. Vehicle information can also be uploaded to big data terminals. Through these systems, comprehensive information on the vehicle's own status, the status of target vehicles, and traffic conditions is acquired. Based on this information, vehicles can identify road conditions, congestion, and road type.

[0076] In another embodiment provided in this application, such as Figure 5 As shown, Figure 5 This diagram illustrates a target vehicle road condition recognition method according to an embodiment of this application. When the future road condition prediction function of a new energy vehicle is activated, the vehicle can automatically identify the road conditions within a certain distance in the future. Figure 5Within the S1-S2 range, it provides sufficient road condition information, especially for the intelligent energy management system of hybrid vehicles, to assist in energy management strategies, thereby making the vehicle's energy utilization rate higher, more economical and environmentally friendly, and maximizing the driving range.

[0077] The aforementioned vehicle road condition prediction device includes a processor and a memory. The aforementioned first acquisition unit 301 and others are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0078] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem of insufficient accuracy in predicting future road conditions based on information from preceding vehicles in existing technologies.

[0079] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0080] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the aforementioned method for predicting vehicle driving conditions.

[0081] This invention provides a processor for running a program, wherein the program executes the aforementioned method for predicting road conditions for a vehicle.

[0082] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0083] Step S101: Obtain the driving information of the vehicle ahead of the target. The driving information includes driving environment information and driving parameters. The vehicle ahead of the target is the vehicle located on the side of the target vehicle's direction of travel.

[0084] Step S102: Based on the driving information, the road condition information of the vehicle ahead is output through the target road condition prediction model. The road condition information represents the driving road condition of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. Each set of historical data includes: the historical driving information of the vehicle ahead and the historical road condition information of the vehicle ahead.

[0085] Step S103: The road condition information of multiple vehicles ahead is fused to obtain fused information;

[0086] Step S104: Based on the fused information, determine the road conditions of the road where the target vehicle is located.

[0087] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0088] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0089] Step S101: Obtain the driving information of the vehicle ahead of the target. The driving information includes driving environment information and driving parameters. The vehicle ahead of the target is the vehicle located on the side of the target vehicle's direction of travel.

[0090] Step S102: Based on the driving information, the road condition information of the vehicle ahead is output through the target road condition prediction model. The road condition information represents the driving road condition of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. Each set of historical data includes: the historical driving information of the vehicle ahead and the historical road condition information of the vehicle ahead.

[0091] Step S103: The road condition information of multiple vehicles ahead is fused to obtain fused information;

[0092] Step S104: Based on the fused information, determine the road conditions of the road where the target vehicle is located.

[0093] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0095] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0096] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0097] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0098] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0099] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0100] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0101] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0102] 1) In the vehicle driving condition prediction method of this application, the method obtains the driving information of the target vehicle ahead, which includes driving environment information and driving parameters. The target vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel. Based on the driving information, a target road condition prediction model outputs the road condition information of the vehicle ahead. The road condition information represents the driving condition of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. Each set of historical data includes the historical driving information and historical road condition information of the vehicle ahead. The road condition information of multiple vehicles ahead is fused to obtain fused information. Based on the fused information, the driving condition of the road where the target vehicle is located is determined. This method uses the driving information of the target vehicle ahead, inputs it into the target road condition prediction model to output multiple road condition information of the vehicle ahead, and fuses these multiple road condition information to determine the driving condition of the road where the target vehicle is located. This solves the problem of insufficient accuracy in predicting the future driving condition of a vehicle using information from the vehicle ahead in the prior art, thereby improving the anti-interference and accuracy of vehicle driving condition prediction.

[0103] 2) In the vehicle driving condition prediction device of this application, a first acquisition unit is used to acquire the driving information of the target vehicle ahead, wherein the driving information includes driving environment information and driving parameters, and the target vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel; an output unit is used to output the road condition information of the target vehicle ahead based on the driving information and through a target road condition prediction model, wherein the road condition information represents the driving road condition of the target vehicle ahead, and the target road condition prediction model is trained using multiple sets of historical data, each set of historical data including: the historical driving information of the target vehicle ahead and the historical road condition information of the target vehicle ahead; a fusion unit is used to fuse the road condition information of multiple target vehicles ahead and obtain fused information; a first determination unit is used to determine the driving road condition of the road where the target vehicle is located based on the fused information. This device uses the driving information of the target vehicle ahead, inputs it into the target road condition prediction model to output the road condition information of multiple target vehicles ahead, and fuses the multiple road condition information to determine the driving road condition of the road where the target vehicle is located, thus solving the problem that the prediction of the future driving road condition of a vehicle based on the information of the target vehicle ahead is not accurate enough in the prior art, thereby improving the anti-interference and accuracy of vehicle driving road condition prediction.

[0104] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting road conditions for vehicles, characterized in that, include: Acquire driving information of a vehicle ahead of a target, wherein the driving information includes driving environment information and driving parameters, the vehicle ahead of the target is a vehicle located on one side of the direction of travel of the target vehicle, the driving parameters include at least the average speed and average acceleration of the vehicle ahead of the target, and the driving environment information includes at least the slope information, lane information, number of vehicles around the vehicle ahead of the target, average speed and average acceleration of the surrounding vehicles. Based on the driving information, the road condition information of the vehicle ahead is output through the target road condition prediction model. The road condition information represents the driving road condition of the vehicle ahead. The target road condition prediction model is trained using multiple sets of historical data. Each set of historical data includes: the historical driving information of the vehicle ahead and the historical road condition information of the vehicle ahead. The road condition information of multiple vehicles ahead is fused to obtain fused information; Based on the fused information, the road conditions of the road where the target vehicle is located are determined; When the distance between the vehicle ahead and the target vehicle is within a preset distance range, the vehicle ahead has onboard sensors, the vehicle ahead and the target vehicle are traveling in the same direction, and the vehicle ahead is in the same lane as the target vehicle, the time corresponding to the overlap between the target vehicle's driving trajectory and the historical driving trajectory of the vehicle ahead is obtained, where the vehicle ahead is a vehicle located on one side of the target vehicle's direction of travel; if the time corresponding to the overlap trajectory is greater than a preset time, the vehicle ahead is identified as the target vehicle ahead. The road condition information of multiple vehicles ahead of the target is fused to obtain target fusion information, including: obtaining the number of vehicles surrounding the vehicle ahead of the target, wherein the surrounding vehicles are vehicles whose distance from the vehicle ahead of the target is within a preset range; obtaining the road condition distance, wherein the road condition distance is the distance from the start of the preset distance range to the current position of the vehicle ahead of the target; and according to the formula... Determine prediction scores for multiple road condition information items, wherein, The predicted score, The weights of the road condition distances are... The distance to the road conditions is described. The number of surrounding vehicles is given; the magnitudes of multiple prediction scores are compared to obtain the maximum prediction score; the road condition information of the target vehicle corresponding to the maximum prediction score is determined as the target fusion information.

2. The method according to claim 1, characterized in that, The method further includes: Construct an initial traffic condition prediction model, wherein the initial traffic condition prediction model includes an input layer, a hidden layer, and an output layer; Acquire multiple sets of historical driving information and multiple sets of historical road condition information; Based on multiple sets of historical driving information and multiple sets of historical road condition information, an initial road condition prediction model is trained. The input layer receives multiple sets of historical data and sends them to the hidden layer. The hidden layer controls multiple weights corresponding to the multiple sets of historical driving information to form a recognition pattern bias. The input layer then sends the multiple sets of historical data and the multiple weights to the output layer. The output layer adjusts the multiple weights according to the historical road condition information to obtain the target road condition prediction model. The recognition pattern bias represents the operation corresponding to the processing of the multiple sets of historical data, and the operation includes any one of the following: classification processing operation and regression analysis operation.

3. The method according to claim 2, characterized in that, Based on the driving information, the road condition information of the vehicle ahead is output through the target road condition prediction model, including: Obtain the recognition pattern bias corresponding to the hidden layer of the target road condition prediction model; Based on the identified pattern bias, the target road condition prediction model is controlled to output the road condition information.

4. The method according to claim 3, characterized in that, Based on the identified pattern bias, the target road condition prediction model is controlled to output the road condition information, including: When the identification mode is biased towards the classification processing operation, the target road condition prediction model is controlled to output first road condition information, wherein the first road condition information represents the road condition category, and the road condition category includes at least: urban conditions, rural conditions, and highway conditions. When the identification mode is biased towards the regression analysis operation, the target traffic prediction model is controlled to output second traffic information, wherein the second traffic information represents the degree of road congestion.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Delete outlier traffic information from multiple traffic information sources, wherein the outlier traffic information is traffic information whose proportion is less than a preset proportion among the multiple traffic information sources.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the vehicle road condition prediction method according to any one of claims 1 to 5.

7. A processor, characterized in that, The processor is used to run a program, wherein the program executes the vehicle driving road condition prediction method according to any one of claims 1 to 5 when it runs.

8. A vehicle, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing a driving road condition prediction method for a vehicle according to any one of claims 1 to 5.

Images