Driver behavior prediction method and device, equipment, storage medium and product

Abstract

The invention discloses a driver behavior prediction method and device, equipment, a storage medium and a product, and relates to the technical field of Internet of Vehicles, and the driver behavior prediction method comprises the steps: obtaining vehicle state data and road state data; dividing a vehicle speed feature tag for the current vehicle based on the vehicle state data; dividing environment feature tags for the current road based on the road state data; and inputting a data set formed by combining the vehicle speed feature tag and the environment feature tag into a pre-training decision tree model for prediction to obtain a driver behavior. The driver behavior is predicted by combining the vehicle state data and the road state data, so that the driving safety and comfort are improved, flexible adjustment can be performed according to the actual road working condition, and the application range of the method is widened.

Description

Technical Field

[0001] The present application relates to the field of vehicle networking technology, and in particular to driver behavior prediction methods, devices, equipment, storage media and products. Background Art

[0002] With the development of Internet of Vehicles technology, cars have become an intelligent mobile platform, and driver behavior has a vital impact on traffic safety. Therefore, accurate prediction of driver behavior can help vehicle systems make intelligent decisions based on real-time conditions and improve traffic safety.

[0003] In existing solutions, the prediction of driver behavior mainly relies on sensor data inside the vehicle. This approach often fails to fully reflect the complexity and variability of the road environment, resulting in limited prediction accuracy. Summary of the invention

[0004] The main purpose of this application is to provide a driver behavior prediction method, device, equipment, storage medium and product, aiming to solve the technical problem of low prediction accuracy of existing driver behavior prediction solutions.

[0005] To achieve the above objectives, the present application proposes a driver behavior prediction method, which includes:

[0006] Obtain vehicle status data and road status data;

[0007] Based on the vehicle status data, a speed characteristic label is assigned to the current vehicle;

[0008] Based on the road state data, an environmental feature label is assigned to the current road;

[0009] The data set composed of the vehicle speed feature label and the environment feature label is input into the pre-trained decision tree model for prediction to obtain the driver behavior.

[0010] In one embodiment, the step of assigning a speed feature label to the current vehicle based on the vehicle status data includes:

[0011] Performing data cleaning and data standardization on the vehicle status data to obtain standardized vehicle status data;

[0012] Determining the vehicle speed information of the current vehicle based on the standardized vehicle status data;

[0013] Determine the vehicle speed state interval of the current vehicle according to the vehicle speed information;

[0014] A vehicle speed feature label is assigned to the current vehicle based on the vehicle speed state interval.

[0015] In one embodiment, the step of dividing the environmental feature labels for the current road based on the road state data includes:

[0016] Performing data cleaning and data standardization on the road state data to obtain standardized road state data;

[0017] Road type information, road location information, road congestion status information and vehicle distance information determined based on the standardized road status data;

[0018] Environmental feature labels of different dimensions of the current road are determined based on the road type information, the road position information, the road congestion status information and the vehicle distance information.

[0019] In one embodiment, before the step of acquiring vehicle status data and road status data, the method further includes:

[0020] Acquire vehicle state training data and road state training data;

[0021] Determine a training vehicle speed feature label and a training environment feature label based on the vehicle training data and the road state training data;

[0022] Constructing a training feature set based on the training vehicle speed feature label and the training environment feature label;

[0023] Determining split evaluation parameters of the training data set;

[0024] The features in the training data set are node-split according to the split evaluation parameters until a model training condition is met to obtain a pre-trained decision tree model.

[0025] In one embodiment, after the step of performing node splitting on the features in the training data set according to the split evaluation parameter until the model training condition is met to obtain the pre-trained decision tree model, the step further includes:

[0026] Get the test feature set;

[0027] The pre-trained decision tree model is evaluated based on the test feature set.

[0028] In one embodiment, the training feature set includes a training feature set and a training feature sample; the step of determining the split evaluation parameter of the training data set includes:

[0029] A first data set entropy based on the training feature set and a second data set entropy of the training feature set under the training feature sample condition;

[0030] A split evaluation parameter of the training feature sample in the training data set is determined according to the entropy of the first data set and the entropy of the second data set.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a driver behavior prediction device, the driver behavior prediction device comprising:

[0032] A data acquisition module, used to acquire vehicle status data and road status data;

[0033] A label determination module, used for assigning a vehicle speed characteristic label to the current vehicle based on the vehicle status data;

[0034] The label determination module is further used to divide the environmental feature label for the current road based on the road state data;

[0035] The behavior prediction module is used to input the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a driver behavior prediction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the driver behavior prediction method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the driver behavior prediction method described above are implemented.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the driver behavior prediction method described above are implemented.

[0039] One or more technical solutions proposed in this application have at least the following technical effects:

[0040] The present application obtains vehicle status data and road status data; divides the vehicle speed feature label for the current vehicle based on the vehicle status data; divides the environment feature label for the current road based on the road status data; and inputs the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior. Since the driver behavior is predicted by combining the vehicle status data and the road status data, the driving safety and comfort are improved, and the method can be flexibly adjusted according to the actual road conditions, thereby increasing the scope of application of the method. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A flowchart of the first embodiment of the driver behavior prediction method of the present application is provided;

[0044] Figure 2 A flowchart diagram of the second embodiment of the driver behavior prediction method of the present application is provided;

[0045] Figure 3 A flowchart of the third embodiment of the driver behavior prediction method of the present application is provided;

[0046] Figure 4 This is a schematic diagram of the module structure of the driver behavior prediction device according to an embodiment of the present application;

[0047] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the driver behavior prediction method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solutions of the embodiments of the present application are: obtaining vehicle status data and road status data; dividing the vehicle speed feature label for the current vehicle based on the vehicle status data; dividing the environment feature label for the current road based on the road status data; inputting the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior.

[0052] At present, the prediction of driver behavior in the existing technology mainly relies on the internal sensor data of the vehicle, but the comprehensive consideration of the road environment is less. In order to make up for the shortcomings of the existing technology, this application proposes a driver behavior prediction method that comprehensively considers the vehicle state and the road environment to improve driving safety and comfort.

[0053] Specifically, this application aims to provide a solution that can accurately predict driver behavior based on the road environment and real-time vehicle status. The solution collects vehicle sensor data and road environment data, and uses machine learning algorithms to predict driver behavior, thereby providing an important reference for safe vehicle driving.

[0054] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a vehicle terminal, a server, etc., or an electronic device, a virtual device, etc. that can realize the above functions. The following takes the driver behavior prediction device (hereinafter referred to as the prediction device) as an example to illustrate this embodiment and the following embodiments.

[0055] Based on this, the embodiment of the present application provides a driver behavior prediction method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the driver behavior prediction method of the present application.

[0056] In this embodiment, the driver behavior prediction method includes steps S10 to S40:

[0057] Step S10, acquiring vehicle status data and road status data;

[0058] It should be noted that the vehicle status data and road status data can be collected through the vehicle's internal sensors and external environment perception devices. Among them, the vehicle status data is a kind of data that can be used to evaluate or characterize the vehicle's driving status, and specifically may include data such as vehicle speed, accelerator pedal opening, vehicle acceleration, brake pedal opening, and wheel-side torque read by the vehicle's internal controller. Road status data is a kind of data that evaluates or characterizes the road congestion and road conditions, and specifically may include information such as road type, road location, road congestion obtained based on networked maps, and the distance to the vehicle in front read through vehicle radar data.

[0059] It is understandable that combining the vehicle status data collected by vehicle sensors and the road status data of the road environment can achieve the construction of a more comprehensive, accurate and reliable prediction model.

[0060] In a specific implementation, the prediction device can collect vehicle status data, road condition information, and driving status of surrounding vehicles through internal vehicle sensors and external environment perception devices.

[0061] Step S20, assigning a vehicle speed characteristic label to the current vehicle based on the vehicle state data;

[0062] Step S30, dividing the environmental feature label for the current road based on the road state data;

[0063] It should be noted that based on the vehicle status data, the speed information of the current vehicle can be determined, and the speed feature label of the current vehicle can be divided according to the speed information. Specifically, the step of dividing the speed feature label of the current vehicle based on the vehicle status data includes:

[0064] Performing data cleaning and data standardization on the vehicle status data to obtain standardized vehicle status data;

[0065] Determining the vehicle speed information of the current vehicle based on the standardized vehicle status data;

[0066] Determine the vehicle speed state interval of the current vehicle according to the vehicle speed information;

[0067] A vehicle speed feature label is assigned to the current vehicle based on the vehicle speed state interval.

[0068] It is understandable that in order to improve the accuracy of prediction, the collected vehicle status data and road status data can be preprocessed before label division. Specifically, the preprocessing process can include data cleaning, data table correction, and feature extraction. By preprocessing the collected data, it is easier to train and predict the model.

[0069] It should be understood that by performing data cleaning on the vehicle status data / road status data, inconsistencies and outlier processing can be identified and corrected (or deleted). By performing data cleaning on the vehicle status data, missing values, incorrect data types, duplicate data, abnormal values, and data that do not conform to business logic can be deleted and corrected, thereby ensuring the accuracy, completeness, consistency and reliability of the collected vehicle status data / road status data, thereby improving the accuracy of subsequent model construction and prediction.

[0070] It can be understood that data standardization is to scale the data so that it falls into a specific interval, such as the 0-1 interval. Data standardization can eliminate the dimensional influence between different features, so that the influence of each feature on the target variable can be uniformly compared, thereby improving the accuracy of the model and the speed of model convergence.

[0071] It should be noted that based on the standardized vehicle state data obtained after data cleaning and data standardization, the speed information of the current vehicle can be determined. Based on the speed information, the speed state interval of the current vehicle can be determined.

[0072] It should be explained that the vehicle speed state range can be a preset range. In one implementation of the embodiment of the present application, when the vehicle speed is between 0 and 20 km / h, it can be determined that the current vehicle is in a creeping driving state range; when the vehicle speed is between 20 and 50 km / h, it can be determined that the current vehicle is in a low-speed driving state range; when the vehicle speed is between 50 and 80 km / h, it can be determined that the current vehicle is in a medium-speed driving state range; when the vehicle speed is above 80 km / h, it can be determined that the current vehicle is in a high-speed driving state range.

[0073] Correspondingly, different speed status intervals may correspond to different speed marks. Therefore, when determining the speed status interval of the current vehicle, a speed feature label may be further determined for the current vehicle. In one implementation of the embodiment of the present application, for the state interval of creeping driving, the corresponding speed feature label may be 0; for the state interval of low-speed driving, the corresponding speed feature label may be 1; for the state interval of medium-speed driving, the corresponding speed feature label may be 2; for the state interval of high-speed driving, the corresponding speed feature label may be 3.

[0074] Similarly, the step of dividing the environmental feature labels for the current road based on the road state data includes:

[0075] Performing data cleaning and data standardization on the road state data to obtain standardized road state data;

[0076] Road type information, road location information, road congestion status information and vehicle distance information determined based on the standardized road status data;

[0077] Environmental feature labels of different dimensions of the current road are determined based on the road type information, the road position information, the road congestion status information and the vehicle distance information.

[0078] It should be noted that the road type information of the current road may include abnormal roads and normal roads. The road type label corresponding to the abnormal road may be 0, and the road type label corresponding to the normal road may be 1. The road position of the current road may include urban roads, suburban roads and expressways. The road position label corresponding to the urban road may be 0, the road position label corresponding to the suburban road may be 1, and the road position label corresponding to the expressway may be 2.

[0079] It should be explained that the road congestion status information of the current road may include unobstructed roads, congested roads and severely congested roads. Among them, the road congestion status label corresponding to the unobstructed road may be 0, the road congestion status label corresponding to the congested road may be 1, and the road congestion status label corresponding to the severely congested road may be 2.

[0080] It should be noted that the vehicle distance information type corresponding to the vehicle distance information of the current vehicle on the current road may include closely following the vehicle and normal driving. Among them, for the closely following vehicle type (such as the distance between the current vehicle and the vehicle in front is less than 2m), the corresponding vehicle distance label may be 0; for the normal driving type (such as the distance between the current vehicle and the vehicle in front is greater than or equal to 2m), the corresponding vehicle distance label may be 1.

[0081] It can be understood that the environmental feature labels of different dimensions of the above-mentioned current road may include road type labels, road position labels, road congestion status labels, and vehicle distance labels, etc., which can be specifically selected according to the actual application situation, and the embodiments of the present application are not limited to this.

[0082] The embodiment of the present application obtains vehicle status data and road status data; divides the vehicle speed feature label for the current vehicle based on the vehicle status data; divides the environment feature label for the current road based on the road status data; and inputs the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior. Since the driver behavior is predicted by combining the vehicle status data and the road status data, the driving safety and comfort are improved, and the method can be flexibly adjusted according to the actual road conditions, thereby increasing the scope of application of the method.

[0083] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , before the step of acquiring vehicle status data and road status data, it also includes:

[0084] Step S100, obtaining vehicle state training data and road state training data;

[0085] Step S200, determining a training vehicle speed feature label and a training environment feature label based on the vehicle training data and the road state training data;

[0086] It should be noted that the vehicle training data and road condition training data in the present application may be obtained as described in the above-mentioned embodiment 1, or may be data generated based on simulation or other methods, and the embodiments of the present application are not limited to this.

[0087] Step S300, constructing a training feature set based on the training vehicle speed feature label and the training environment feature label;

[0088] It should be noted that, when the training vehicle speed label and the training environment feature label are obtained, a data set can be constructed based on the training vehicle speed feature label and the training environment feature label.

[0089] Specifically, the data set may include a feature set and a feature sample.

[0090] In one implementation of the embodiment of the present application, the training vehicle speed feature label and the training environment feature label can be combined into a data set, in which each row can represent a feature sample. The data set can be specifically shown in the following table:

[0091] Speed Road Type Road location Road congestion Distance between vehicles Tags(Behavior) 0 1 0 0 0 0 2 1 1 1 1 1 3 0 2 0 2 2 … … … … … …

[0092] It should be noted that after the data set is constructed, the data in the data set can be used to train the initial decision tree model. The decision tree model is a classification algorithm based on a tree structure, which can make decisions through conditional branches of features.

[0093] In one implementation of the embodiment of the present application, the detailed steps of the training process can be described as follows:

[0094] In order to evaluate the performance of the model, the obtained data set can be divided into a training data set and a test feature set. Generally speaking, 80% of the data in the data set can be divided into a training data set and 20% of the data can be divided into a test feature set. The specific division ratio can be selected according to the needs of the actual application. By dividing the data set, it can help verify the generalization ability of the model.

[0095] Specifically, for the training data set Xtrain and its corresponding training label set ytrain; the training data set Xtrain can be a matrix composed of feature data, including feature data such as vehicle speed, road type, road location, road congestion, and vehicle distance; the training label set ytrain is a label vector composed of labels (behaviors) corresponding to each training feature sample. Through the training data set Xtrain and the training label set ytrain, the training of the decision tree model can be realized. For the test feature set Xtest and its corresponding test label set ytest, the evaluation of the trained decision tree model can be realized.

[0096] It should be noted that during the model training process, the decision tree model can generate a tree structure based on different values ​​of the features for classification. The model training process may include the following steps:

[0097] Step S400, determining the split evaluation parameters of the training data set;

[0098] Step S500, performing node splitting on the features in the training data set according to the split evaluation parameters until a model training condition is met to obtain a pre-trained decision tree model.

[0099] It should be noted that, in the embodiment of the present application, information gain or Gini index can be used as an index (i.e., a splitting evaluation parameter) for evaluating the effect of feature splitting. Based on information gain or Gini index, the best splitting feature of the decision tree model can be selected.

[0100] Specifically, the calculation formula of information gain can be shown as follows:

[0101] IG(D,A)=H(D)-H(D|A);

[0102] Among them, H(D) is the entropy of the training data set D (that is, the first data set entropy), and H(D|A) is the data set entropy under the condition of feature sample A (that is, the second data set entropy).

[0103] Specifically, the training feature set includes a training feature set and a training feature sample; the step of determining the split evaluation parameter of the training data set includes:

[0104] A first data set entropy based on the training feature set and a second data set entropy of the training feature set under the training feature sample condition;

[0105] A split evaluation parameter of the training feature sample in the training data set is determined according to the entropy of the first data set and the entropy of the second data set.

[0106] In one implementation of the embodiment of the present application, the calculation formula of the Gini index can be as follows:

[0107]

[0108] Among them, p i is the proportion of (driver behavior) category i in the training dataset D, and C is the total number of categories.

[0109] It should be noted that the pre-trained decision tree model can be obtained by performing node splitting according to the selected feature samples and the corresponding split evaluation parameters until the model training conditions are met (such as reaching the maximum depth or the number of samples is less than a preset threshold, and the maximum depth or preset threshold can be selected according to actual needs).

[0110] In the embodiment of the present application, vehicle state training data and road state training data are obtained; based on the vehicle training data and road state training data, training vehicle speed feature labels and training environment feature labels are determined; based on the training vehicle speed feature labels and training environment feature labels, a training feature set is constructed; the split evaluation parameter of the training data set is determined; and the features in the training data set are node-split according to the split evaluation parameter until the model training conditions are met to obtain a pre-trained decision tree model. Since the decision tree model is pre-trained, the classification accuracy is improved by generating a tree structure according to different values ​​of the features.

[0111] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned first embodiment and / or the second embodiment can refer to the above introduction, and will not be repeated later. Figure 3 , after the step of performing node splitting on the features in the training data set according to the split evaluation parameter until the model training condition is met to obtain a pre-trained decision tree model, it also includes:

[0112] Step S600, obtaining a test feature set;

[0113] Step S700, evaluating the pre-trained decision tree model based on the test feature set.

[0114] It should be noted that in order to improve the accuracy of model classification, the model parameters of the pre-trained decision tree model can also be adjusted through methods such as differential verification to improve the performance of the model.

[0115] Furthermore, the pre-trained decision tree model can also be evaluated using the test feature set. In the embodiment of the present application, the main evaluation indicators may include accuracy, precision, recall, and F1 score.

[0116] Specifically, the accuracy can be calculated as follows:

[0117]

[0118] Among them, TP (True Positives) represents true positive examples, that is, the number of samples that are actually positive and predicted as positive by the model; TN (True Negatives) represents true negative examples, that is, the number of samples that are actually negative and predicted as negative by the model; FP (False Positives) represents false positive examples, that is, the number of samples that are actually negative but predicted as positive by the model, that is, false alarms; FN (False Negatives) represents false negative examples, that is, the number of samples that are actually positive but predicted as negative by the model, that is, missed alarms.

[0119] It should be noted that the calculation method of accuracy can be as follows:

[0120]

[0121] The recall rate can be calculated as follows:

[0122]

[0123] The calculation of F1 score can be as follows:

[0124]

[0125] In one implementation of the embodiment of the present application, the pre-trained decision tree model can be visualized. The visualization of the decision tree model helps to understand the decision-making process of the model. Through the tree diagram, the role and influence of each feature in the decision can be clearly seen.

[0126] It is understandable that when the pre-trained decision tree model is trained and evaluated, the model can be used to predict new driver behaviors. When using the model for prediction, a data set consisting of vehicle speed feature labels and environmental feature labels is input into the pre-trained decision tree model, and the pre-trained decision tree model can traverse the input features according to the tree structure and finally output the predicted behavior label.

[0127] It should be understood that the input data should be in the same format as the feature vector during training (that is, the same format as the training feature sample in the training data set Xtrain). When the feature vector is passed into the pre-trained decision tree model, the model will make a judgment based on the structure of the tree. Specifically, (1) starting from the root node, the corresponding child node can be selected according to the value of the feature; (2) the above process (1) is repeated until a leaf node is reached; (3) the value of the leaf node is the model's prediction result for the input feature.

[0128] The embodiment of the present application obtains a test feature set and evaluates the pre-trained decision tree model based on the test feature set, thereby improving the accuracy and precision of the model and ensuring the accuracy of the prediction.

[0129] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the driver behavior prediction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0130] This application also provides a driver behavior prediction device, please refer to Figure 4 , the driver behavior prediction device comprises:

[0131] A data acquisition module 10 is used to acquire vehicle status data and road status data;

[0132] A label determination module 20, configured to classify a vehicle speed characteristic label for the current vehicle based on the vehicle state data;

[0133] The label determination module 20 is further used to classify an environmental feature label for the current road based on the road state data;

[0134] The behavior prediction module 30 is used to input the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior.

[0135] The driver behavior prediction device provided by the present application adopts the driver behavior prediction method in the above embodiment, which can solve the technical problem of low prediction accuracy of the existing driver behavior prediction scheme. Compared with the prior art, the beneficial effects of the driver behavior prediction device provided by the present application are the same as the beneficial effects of the driver behavior prediction method provided by the above embodiment, and other technical features in the driver behavior prediction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0136] The present application provides a driver behavior prediction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the driver behavior prediction method in the above-mentioned embodiment one.

[0137] Reference below Figure 5 , which shows a schematic diagram of the structure of a driver behavior prediction device suitable for implementing an embodiment of the present application. The driver behavior prediction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The driver behavior prediction device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0138] like Figure 5As shown, the driver behavior prediction device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the driver behavior prediction device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the driver behavior prediction device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a driver behavior prediction device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0139] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0140] The driver behavior prediction device provided by the present application adopts the driver behavior prediction method in the above embodiment, which can solve the technical problem of low prediction accuracy of the existing driver behavior prediction scheme. Compared with the prior art, the beneficial effects of the driver behavior prediction device provided by the present application are the same as the beneficial effects of the driver behavior prediction method provided by the above embodiment, and the other technical features in the driver behavior prediction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0141] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0142] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0143] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the driver behavior prediction method in the above-mentioned embodiment.

[0144] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0145] The computer-readable storage medium may be included in the driver behavior prediction device; or may exist independently without being assembled into the driver behavior prediction device.

[0146] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the driver behavior prediction device, the driver behavior prediction device:

[0147] Obtain vehicle status data and road status data;

[0148] Based on the vehicle status data, a speed characteristic label is assigned to the current vehicle;

[0149] Based on the road state data, an environmental feature label is assigned to the current road;

[0150] The data set composed of the vehicle speed feature label and the environment feature label is input into the pre-trained decision tree model for prediction to obtain the driver behavior.

[0151] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0154] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned driver behavior prediction method, and can solve the technical problem of low prediction accuracy of existing driver behavior prediction schemes. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the driver behavior prediction method provided by the above-mentioned embodiment, and will not be repeated here.

[0155] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned driver behavior prediction method when executed by a processor.

[0156] The computer program product provided by the present application can solve the technical problem of low prediction accuracy of the existing driver behavior prediction scheme. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the driver behavior prediction method provided by the above embodiment, which will not be repeated here.

[0157] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A driver behavior prediction method, characterized in that: The method comprises: Obtain vehicle status data and road status data; Based on the vehicle status data, a speed characteristic label is assigned to the current vehicle; Based on the road state data, an environmental feature label is assigned to the current road; The data set composed of the vehicle speed feature label and the environment feature label is input into the pre-trained decision tree model for prediction to obtain the driver behavior.

2. The driver behavior prediction method according to claim 1, characterized in that: The step of assigning a vehicle speed characteristic label to the current vehicle based on the vehicle state data comprises: Performing data cleaning and data standardization on the vehicle status data to obtain standardized vehicle status data; Determining the vehicle speed information of the current vehicle based on the standardized vehicle status data; Determine the vehicle speed state interval of the current vehicle according to the vehicle speed information; A vehicle speed feature label is assigned to the current vehicle based on the vehicle speed state interval.

3. The driver behavior prediction method according to claim 1, characterized in that: The step of dividing the environmental feature labels for the current road based on the road state data comprises: Performing data cleaning and data standardization on the road state data to obtain standardized road state data; Road type information, road location information, road congestion status information and vehicle distance information determined based on the standardized road status data; Environmental feature labels of different dimensions of the current road are determined based on the road type information, the road position information, the road congestion status information and the vehicle distance information.

4. The driver behavior prediction method according to claim 1, characterized in that: Before the step of acquiring vehicle status data and road status data, the method further includes: Acquire vehicle state training data and road state training data; Determine a training vehicle speed feature label and a training environment feature label based on the vehicle training data and the road state training data; Constructing a training feature set based on the training vehicle speed feature label and the training environment feature label; Determining split evaluation parameters of the training data set; The features in the training data set are node-split according to the split evaluation parameters until a model training condition is met to obtain a pre-trained decision tree model.

5. The driver behavior prediction method according to claim 4, characterized in that: After the step of performing node splitting on the features in the training data set according to the split evaluation parameter until the model training condition is met to obtain the pre-trained decision tree model, the method further includes: Get the test feature set; The pre-trained decision tree model is evaluated based on the test feature set.

6. The driver behavior prediction method according to claim 4, characterized in that: The training feature set includes a training feature set and a training feature sample; The step of determining the split evaluation parameters of the training data set includes: A first data set entropy based on the training feature set and a second data set entropy of the training feature set under the training feature sample condition; A split evaluation parameter of the training feature sample in the training data set is determined according to the entropy of the first data set and the entropy of the second data set.

7. A driver behavior prediction device, characterized in that: The driver behavior prediction device comprises: A data acquisition module, used to acquire vehicle status data and road status data; A label determination module, used for assigning a vehicle speed characteristic label to the current vehicle based on the vehicle status data; The label determination module is further used to divide the environmental feature label for the current road based on the road state data; The behavior prediction module is used to input the data set composed of the vehicle speed feature label and the environment feature label into the pre-trained decision tree model for prediction to obtain the driver behavior.

8. A driver behavior prediction device, characterized in that: The device comprises: a memory, a processor, and a driver behavior prediction program stored in the memory and executable on the processor, wherein the driver behavior prediction program is configured to implement the steps of the driver behavior prediction method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a driver behavior prediction program, which, when executed by a processor, implements the steps of the driver behavior prediction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the driver behavior prediction method according to any one of claims 1 to 6 are implemented.

Images