Method, device, equipment and computer-readable storage medium for generating simulated traffic flow

Abstract

The embodiment of the present invention discloses a method, device, equipment and medium for generating simulated traffic flow. The method obtains actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes index data of at least two dimensions; performs index data cluster analysis on the actual driving behavior data to classify driving behaviors and obtain classification proportions; determines the index configuration parameters of the corresponding driving behaviors according to the actual driving behavior data of each type of driving behavior; establishes a traffic flow simulation model according to the classification and classification proportion of the driving behaviors, as well as the index configuration parameters of each type of driving behaviors; generates simulated traffic flow according to the traffic flow simulation model. The embodiment of the present invention has the technical effect of improving the accuracy of generating scenes in random simulated traffic flow.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of vehicle technology, and in particular to a method for generating simulated traffic flow. Background Art

[0002] After the development of the current vehicle's autonomous driving function is completed, it needs to undergo a large number of tests to meet the requirements of actual vehicle application. A single test scenario is difficult to meet the simulation needs of large-scale concurrent testing, so it is necessary to establish random traffic flows and construct simulation scenarios in the entire traffic flow network.

[0003] At present, the existing methods of generating random traffic flows usually involve automatically generating random traffic flows based on software, or setting driver model parameters based on empirical data. The simulated traffic flows generated in this way are distorted and cannot meet the driving habits of Chinese drivers, resulting in poor authenticity of the generated simulation scenes, which affects the results of the next simulation test. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and computer-readable storage medium for generating a simulated traffic flow, so as to achieve the authenticity and effectiveness of generating a simulated traffic flow.

[0005] In a first aspect, an embodiment of the present invention provides a method for generating a simulated traffic flow, comprising:

[0006] Acquire actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0007] Performing index data cluster analysis on the actual driving behavior data to classify the driving behaviors and obtain classification proportions;

[0008] Determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior;

[0009] A traffic flow simulation model is established according to the classification and classification proportion of the driving behaviors and the indicator configuration parameters of each type of driving behavior;

[0010] A simulated traffic flow is generated according to the traffic flow simulation model.

[0011] In a second aspect, an embodiment of the present invention further provides a device for generating a simulated traffic flow, comprising:

[0012] A behavior data acquisition module is used to acquire actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0013] A driving behavior analysis module, used to perform index data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio;

[0014] A configuration parameter determination module, used to determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior;

[0015] A simulation model building module, used to build a traffic flow simulation model according to the classification and classification proportion of the driving behavior, and the indicator configuration parameters of each type of driving behavior;

[0016] The traffic flow generation module is used to generate simulated traffic flow according to the traffic flow simulation model.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0018] one or more processors;

[0019] A memory for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for generating a simulated traffic flow as described in the first aspect.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for generating a simulated traffic flow as described in the first aspect.

[0022] The embodiment of the present invention obtains actual driving behavior data collected during the actual driving process of the driver, wherein the actual driving behavior data includes indicator data of at least two dimensions; performs indicator data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio; determines the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior; establishes a traffic flow simulation model according to the classification and classification ratio of the driving behavior, as well as the indicator configuration parameters of each type of driving behavior; generates a simulated traffic flow according to the traffic flow simulation model, thereby solving the technical problem that the existing random traffic flow automatic generation method has poor authenticity, and achieving the technical effect of providing strong data support for constructing a driver model in the simulated traffic flow, making the driver's driving behavior in the simulated traffic flow more in line with the habits of Chinese drivers, and improving the accuracy of the scene generated in the simulated traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of a method for generating a simulated traffic flow is provided for the first embodiment of the present invention;

[0024] Figure 2 A flowchart of a method for generating a simulated traffic flow is provided for the second embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a device for generating simulated traffic flow is provided for the third embodiment of the present invention;

[0026] Figure 4 It is a structural schematic diagram of an electronic device provided in accordance with a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a method for generating a simulated traffic flow provided in Embodiment 1 of the present invention. This embodiment can be applied to the case of building a simulated traffic flow for the testing requirements of an autonomous driving vehicle. The method can be executed by a device for generating a simulated traffic flow, which can be implemented in software and / or hardware. The device can be configured in an electronic device with data processing capabilities. The method specifically includes:

[0031] S110, acquiring actual driving behavior data collected during the actual driving process of the driver, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0032] Optionally, the locations of the actual driving process include: expressways, urban roads, rural roads and suburban roads, etc., and the modes of the actual driving process may include: going straight, reversing, turning and turning on the spot, etc.

[0033] The index data may include at least two of the following: vehicle speed, acceleration / deceleration, mileage, steering wheel angle, etc. The index data may be data that can reflect the actual driving behavior of the driver.

[0034] Specifically, the vehicle speed may include the average speed of the vehicle at fixed intervals, and the fixed intervals may be preset to 10 meters, 50 meters or 100 meters, etc. The acceleration and deceleration may be the rate of change generated each time a speed change is detected. The mileage may include the driving length or driving trajectory of a complete journey of the vehicle. A complete journey refers to the driving process of the same vehicle in which the driving speed is non-zero except at the beginning and the end.

[0035] Furthermore, the actual driving behavior data collected during the actual driving process of the driver is obtained, which also includes: acceleration gradient, deceleration gradient, steering wheel angle velocity, etc. calculated based on the index data.

[0036] Optionally, actual driving behavior data collected during the driver's actual driving process is obtained, including:

[0037] The actual driving behavior data collected by the driver during actual driving is obtained from the Internet of Vehicles data.

[0038] It can be obtained that the actual driving behavior data collected from the actual driving process of the driver can be obtained from the Internet of Vehicles data, which has the significant advantages of large data volume (information of sold vehicles can be collected) and multiple CAN signal acquisition channels. Internet of Vehicles data meets the data needs of big data analysis, and the conclusions obtained from this data analysis can represent the driving habits of Chinese drivers. In addition, the driving styles of drivers in different regions (differences between the north and the south, and between urban and rural areas) can be classified and analyzed based on the screening of GPS data, or the driving styles of drivers at different driving times (peak hours, holidays) can be classified based on the screening of time, so that a driver model can be constructed more accurately.

[0039] Among them, the Internet of Vehicles data includes: sensor signal data on mass-produced vehicles produced and sold by the OEM.

[0040] It should be noted that the Internet of Vehicles refers to the effective use of all vehicle dynamic information in the information network platform by the on-board equipment on the vehicle through wireless communication technology. The Internet of Vehicles architecture is mainly composed of three major hierarchical structures, which are the application layer, network layer and acquisition layer from high to low. The Internet of Vehicles data collected in the embodiment of the present invention mainly comes from the acquisition layer, which is completed by various on-board sensors, including real-time vehicle operating parameters, road environment parameters and prediction parameters, such as vehicle speed, direction, location, mileage, engine speed, vehicle temperature, etc. All collected data will be uploaded to the background server for unified processing and analysis to obtain the business data required by users, providing reliable data support for the Internet of Vehicles.

[0041] In the technical solution of this embodiment, optionally, after obtaining the actual driving behavior data collected by the driver during the actual driving process, at least one of the following operations is performed:

[0042] Supplementing the missing parts of the actual driving behavior data;

[0043] Deleting false positive data of the sensor signal data;

[0044] The actual driving behavior data is deduplicated.

[0045] Specifically, when detecting a driving process with obvious missing data, such as incomplete signal data types, or sensor false alarm data, such as data that obviously exceeds the normal threshold, the missing or false alarm data can be fitted according to the corresponding data within the threshold range of other vehicles, and the fitted data can be used to supplement, replace or delete the original missing or erroneous data.

[0046] Furthermore, when there is missing data or erroneous data, the original data is supplemented and replaced by fitting. If there is both missing data and erroneous data in the same driving process, the driving behavior data can be directly deleted.

[0047] S120, performing index data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain classification proportions;

[0048] It should be noted that the cluster analysis refers to the analysis process of grouping a collection of physical or abstract objects into multiple classes consisting of similar objects. The embodiment of the present invention performs index data cluster analysis on the actual driving behavior data to make the data display more intuitive and concise.

[0049] S130, determining an indicator configuration parameter of a corresponding driving behavior according to actual driving behavior data of each type of driving behavior;

[0050] It can be obtained that after clustering the actual driving behavior data, the classification proportion of each type of driving behavior indicator data can be obtained. The proportion of driver style in the random traffic flow is set according to the actual driver driving style proportion, and the driver model is set according to the driving parameters of different styles. The generated random vehicle driving behavior can be made more in line with the habits of Chinese drivers, improve the authenticity of the simulation scene, help improve the accuracy of the simulation test, and make the test results of the algorithm more convincing.

[0051] S140, establishing a traffic flow simulation model according to the classification and classification proportion of the driving behaviors, and the indicator configuration parameters of each type of driving behavior;

[0052] It can be seen that in the prior art, only the driver's driving state data is usually analyzed and modeled, and the generated simulation scene has poor authenticity. In the embodiment of the present invention, more parameters are used for driver behavior analysis, which not only considers the actual driving behavior data, but also includes the driver's driving style and the distribution state of driving parameters in different driving styles, so that the trained model has the advantages of high prediction accuracy and low cost.

[0053] Optionally, according to the classification and classification ratio of the driving behaviors, and the indicator configuration parameters of each type of driving behaviors, a traffic flow simulation model can be established through a deep learning model or a machine learning model. The driver model can be established through modeling software or simulation hardware.

[0054] S150: Generate a simulated traffic flow according to the traffic flow simulation model.

[0055] Specifically, the distribution of parameters in the model is also set according to the distribution states of driving parameters in different driving styles, and the model output is a simulated vehicle driving state.

[0056] It should be noted that the type of simulated traffic flow in the embodiment of the present invention is random traffic flow. Specifically, the random traffic flow is a probability model that assumes the driving state of each vehicle under the assumption that the vehicles traveling on the road are independent of each other and the vehicle distribution is random.

[0057] It can be seen that the random traffic flow used in the embodiment of the present invention can well meet the needs of large-scale concurrent simulation testing. Specifically, modeling the random traffic flow can improve the coverage of autonomous driving simulation test scenarios, improve the efficiency of simulation testing, make the driving behavior of drivers in the traffic flow more in line with the habits of Chinese drivers, and improve the accuracy of the generated scenarios in the random traffic flow.

[0058] The technical solution of this embodiment is to obtain actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions; perform indicator data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio; determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior; establish a traffic flow simulation model according to the classification and classification ratio of the driving behavior, as well as the indicator configuration parameters of each type of driving behavior; generate a simulated traffic flow according to the traffic flow simulation model, thereby solving the technical problem of poor authenticity of the existing random traffic flow automatic generation method, and achieving the technical effect of providing strong data support for constructing a driver model in the simulated traffic flow, making the driver's driving behavior in the simulated traffic flow more in line with the habits of Chinese drivers, and improving the accuracy of the scene generated in the simulated traffic flow.

[0059] Embodiment 2

[0060] Figure 2 This is a flow chart of a method provided in Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the above embodiments. “Performing index data cluster analysis on the actual driving behavior data to classify driving behavior and obtaining classification proportions” provides a specific implementation scheme and provides a process for determining the index configuration parameters of driving behavior. The method specifically includes the following steps:

[0061] S210, acquiring actual driving behavior data collected during the actual driving process of the driver, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0062] S220, normalizing the index data of each dimension of the actual driving behavior data, and performing multi-dimensional factor dimensionality reduction processing on the normalized result by using principal component analysis;

[0063] It should be noted that the normalization method is to convert the number into a decimal between (0, 1), which is mainly proposed for the convenience of data processing, and the data is mapped to the range of 0 to 1 for processing. The embodiment of the present invention converts various types of driving behavior index data into various types of dimensionless data between 0 and 1 through normalization, making subsequent data processing more convenient and faster.

[0064] Furthermore, principal component analysis is a statistical method. A group of variables that may be correlated is converted into a group of linearly uncorrelated variables through orthogonal transformation. The group of variables after conversion is called principal component. In the embodiment of the present invention, the multi-dimensional factor dimensionality reduction processing is performed on the index data after normalization of various types by principal component analysis, so as to obtain a group of new data that are unrelated to each other and have a substantial effect on the modeling results. The multi-dimensional factor dimensionality reduction processing is performed on the normalized results by principal component analysis, which reduces the amount of data and improves the analysis efficiency.

[0065] S230: Cluster the indicator data after the dimension reduction process to obtain the driving behavior classification results and classification proportions.

[0066] Optionally, the driving behavior classification results include: a mild driver, an aggressive driver and a general driver.

[0067] Specifically, the embodiment of the present invention obtains the classification proportions corresponding to the mild driver, the aggressive driver and the general driver respectively, and the traffic flow in the traffic flow simulation model is also distributed according to the classification proportions, and then the simulated vehicle driving state is generated in proportion.

[0068] S240, normalizing the index data of each dimension of each type of actual driving behavior data, and performing multi-dimensional factor dimensionality reduction processing on the normalized result using a principal component analysis method;

[0069] S250. For each type of indicator data after the dimensionality reduction process, extract statistical values ​​as indicator configuration parameters for this type of indicator data.

[0070] S260, establishing a traffic flow simulation model according to the classification and classification proportion of the driving behaviors, and the indicator configuration parameters of each type of driving behavior;

[0071] S270: Generate a simulated traffic flow according to the traffic flow simulation model.

[0072] Specifically, the embodiment of the present invention establishes a traffic flow simulation model based on the classification and classification ratio of the driving behavior, as well as the indicator configuration parameters of each type of driving behavior. It can be obtained that in the prior art, only the driver's driving state data is usually analyzed and modeled, and the generated simulation scene has poor authenticity. In the embodiment of the present invention, there are more parameters for analyzing the driver's behavior, which not only takes into account the actual driving behavior data, but also includes the driver's driving style and the distribution state of driving parameters in different driving styles, so that the trained model has the advantages of high prediction accuracy and low cost.

[0073] The technical solution of this embodiment normalizes the indicator data of each dimension of the actual driving behavior data, performs multidimensional factor dimensionality reduction processing on the normalized result using the principal component analysis method, and clusters the indicator data after dimensionality reduction processing to obtain the driving behavior classification result and classification proportion, thereby solving the technical problem of excessively high computing cost caused by excessive amount of selected data, achieving the technical effect of improving the computing efficiency of the model and the timeliness of modeling, reducing the impact of invalid and erroneous data on modeling, and improving the accuracy of modeling.

[0074] Embodiment 3

[0075] Figure 3 This is a schematic diagram of the structure of a simulated traffic flow generation device provided in the third embodiment of the present invention. The device can execute the simulated traffic flow generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. This embodiment can be applied to the environment of simulated road testing of real vehicles. The device includes: a behavior data acquisition module 301, a driving behavior analysis module 302, a configuration parameter determination module 303, a simulation model establishment module 304, and a traffic flow generation module 305.

[0076] The behavior data acquisition module 301 is used to acquire the actual driving behavior data collected by the driver during the actual driving process, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0077] The driving behavior analysis module 302 is used to perform index data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio;

[0078] The configuration parameter determination module 303 is used to determine the index configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior;

[0079] A simulation model building module 304 is used to build a traffic flow simulation model according to the classification and classification proportion of the driving behavior and the indicator configuration parameters of each type of driving behavior;

[0080] The traffic flow generation module 305 is used to generate simulated traffic flow according to the traffic flow simulation model.

[0081] Furthermore, the index data includes at least two of the following: vehicle speed, acceleration / deceleration, mileage and steering wheel angle.

[0082] Furthermore, the driving behavior analysis module 302 further includes:

[0083] An index data dimensionality reduction unit, used for normalizing the index data of each dimension of the actual driving behavior data, and performing multi-dimensional factor dimensionality reduction processing on the normalized result by using a principal component analysis method;

[0084] The index data clustering unit is used to cluster the index data after dimensionality reduction processing to obtain the driving behavior classification results and classification proportions.

[0085] Furthermore, the driving behavior classification results include: a mild driver, an aggressive driver and a general driver.

[0086] Furthermore, the configuration parameter determination module 303 further includes:

[0087] The indicator data of each dimension of each type of actual driving behavior data is normalized, and the normalized results are subjected to multi-dimensional factor dimensionality reduction processing using principal component analysis;

[0088] For each type of indicator data after dimensionality reduction processing, statistical values ​​are extracted as indicator configuration parameters for this type of indicator data.

[0089] Furthermore, the actual driving behavior data collected during the actual driving process of the driver is obtained, including:

[0090] Acquire actual driving behavior data collected during the driver's actual driving process from the Internet of Vehicles data;

[0091] Among them, the Internet of Vehicles data includes: sensor signal data on mass-produced vehicles produced and sold by the OEM.

[0092] Furthermore, the device further comprises:

[0093] A behavior data preprocessing module, used to supplement the missing parts of the actual driving behavior data;

[0094] Deleting false positive data of the sensor signal data;

[0095] The actual driving behavior data is deduplicated.

[0096] The technical solution of this embodiment is to obtain actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions; perform indicator data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio; determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior; establish a traffic flow simulation model according to the classification and classification ratio of the driving behavior, as well as the indicator configuration parameters of each type of driving behavior; generate a simulated traffic flow according to the traffic flow simulation model, thereby solving the technical problem of poor authenticity of the existing random traffic flow automatic generation method, and achieving the technical effect of providing strong data support for constructing a driver model in the simulated traffic flow, making the driver's driving behavior in the simulated traffic flow more in line with the habits of Chinese drivers, and improving the accuracy of the scene generated in the simulated traffic flow.

[0097] Embodiment 4

[0098] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram of a terminal 412 suitable for implementing embodiments of the present invention is shown. Figure 4 The terminal 412 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0099] like Figure 4 As shown, the terminal 412 is in the form of a general computing device and has the functions of saving pictures and translating by taking pictures, screenshots, etc. The components of the terminal 412 may include, but are not limited to: one or more processors 416, a storage device 428, and a bus 418 connecting different system components (including the storage device 428 and the processor 416).

[0100] Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0101] Terminal 412 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 412, including volatile and non-volatile media, removable and non-removable media.

[0102] Storage device 428 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 430 and / or cache memory 432. Terminal 412 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 434 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 418 via one or more data medium interfaces. The storage device 428 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0103] A program 440 having a set (at least one) of program modules 442 may be stored, for example, in a storage device 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 442 generally perform the functions and / or methods of the embodiments described herein.

[0104] The terminal 412 may also communicate with one or more external devices 414 (e.g., keyboards, pointing devices, cameras, displays 424, etc.), may communicate with one or more devices that enable a user to interact with the terminal 412, and / or may communicate with any device that enables the terminal 412 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 422. Furthermore, the terminal 412 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 420. As shown, the network adapter 420 communicates with other modules of the terminal 412 via a bus 418. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the terminal 412, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0105] The processor 416 executes various functional applications and data processing by running the programs stored in the storage device 428, such as implementing a method for generating a simulated traffic flow provided in the above embodiment of the present invention.

[0106] Embodiment 6

[0107] Embodiment 6 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a method for generating a simulated traffic flow when executed by a computer processor, the method comprising:

[0108] Acquire actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions;

[0109] Performing index data cluster analysis on the actual driving behavior data to classify the driving behaviors and obtain classification proportions;

[0110] Determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior;

[0111] According to the classification and classification proportion of the driving behaviors, and the indicator configuration parameters of each type of driving behavior, a traffic flow simulation model is used;

[0112] A simulated traffic flow is generated according to the traffic flow simulation model.

[0113] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided in an embodiment of the present invention are not limited to the method operations described above, and can also execute related operations in the method for generating simulated traffic flow provided in any embodiment of the present invention.

[0114] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0115] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0116] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for generating simulated traffic flow, characterized in that: include: Acquire actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions; Performing index data cluster analysis on the actual driving behavior data to classify the driving behaviors and obtain classification proportions; Determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior; A traffic flow simulation model is established according to the classification and classification proportion of the driving behaviors and the indicator configuration parameters of each type of driving behavior; generating a simulated traffic flow according to the traffic flow simulation model; Wherein, determining the index configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior includes: The indicator data of each dimension of each type of actual driving behavior data is normalized, and the normalized results are subjected to multi-dimensional factor dimensionality reduction processing using principal component analysis; For each type of indicator data after dimensionality reduction processing, statistical values ​​are extracted as indicator configuration parameters for this type of indicator data.

2. The method according to claim 1, characterized in that The index data includes at least two of the following: vehicle speed, acceleration / deceleration, mileage and steering wheel angle.

3. The method according to claim 1, characterized in that Performing index data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification proportions include: Normalizing the index data of each dimension of the actual driving behavior data, and performing multi-dimensional factor dimensionality reduction processing on the normalized results using principal component analysis; Cluster the indicator data after dimensionality reduction to obtain the driving behavior classification results and classification proportions.

4. The method according to claim 1, characterized in that: The driving behavior classification results include: a mild driver, an aggressive driver, and a general driver.

5. The method according to claim 1, characterized in that: Acquire the actual driving behavior data collected by the driver during the actual driving process, including: Acquire actual driving behavior data collected during the driver's actual driving process from the Internet of Vehicles data; Among them, the Internet of Vehicles data includes: sensor signal data on mass-produced vehicles produced and sold by the OEM.

6. The method according to claim 5, characterized in that After obtaining the actual driving behavior data collected by the driver during the actual driving process, the method further includes performing at least one of the following operations: Supplementing the missing parts of the actual driving behavior data; Deleting false positive data of the sensor signal data; The actual driving behavior data is deduplicated.

7. A device for generating simulated traffic flow, characterized in that: include: A behavior data acquisition module is used to acquire actual driving behavior data collected by the driver during actual driving, wherein the actual driving behavior data includes indicator data of at least two dimensions; A driving behavior analysis module, used to perform index data cluster analysis on the actual driving behavior data to classify the driving behavior and obtain the classification ratio; A configuration parameter determination module, used to determine the indicator configuration parameters of the corresponding driving behavior according to the actual driving behavior data of each type of driving behavior; A simulation model building module, used to build a traffic flow simulation model according to the classification and classification proportion of the driving behavior, and the indicator configuration parameters of each type of driving behavior; A traffic flow generation module, used to generate a simulated traffic flow according to the traffic flow simulation model; The configuration parameter determination module is further used to normalize the index data of each dimension of each type of actual driving behavior data, and perform multi-dimensional factor dimensionality reduction processing on the normalized result using the principal component analysis method; For each type of indicator data after dimensionality reduction processing, statistical values ​​are extracted as indicator configuration parameters for this type of indicator data.

8. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a method for generating a simulated traffic flow as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for generating a simulated traffic flow as described in any one of claims 1 to 6 is implemented.

Images