Apparatus for predicting traffic information and method thereof

Abstract

Disclosed are a device for predicting traffic information and a method thereof. The device for predicting traffic information includes a memory storing a traffic information prediction model; and a controller configured to calculate a congestion transition rate W of a target link based on a traffic volume and a vehicle density AB and input the congestion transition rate, a speed of the target link, a speed of a link in front of the target link, and a speed of a link behind the target link to the traffic information prediction model to estimate traffic information of the target link.

Description

[0001] Related applications

[0002] This application claims the benefit of Korean Patent Application No. 10-2021-0092504, filed with the Korean Intellectual Property Office on July 14, 2021, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to devices and methods for using models to predict traffic information, and more specifically, to devices and methods for predicting traffic information by utilizing a traffic information prediction model that incorporates machine learning based on congestion transfer rates. Background Technology

[0004] The traffic information currently provided corresponds to information predicted based on past speed patterns. In other words, the current traffic information (e.g., speed information) is derived using previous speed patterns under the assumption that similar speeds will occur at the same time of day.

[0005] When using traffic information from the same day and time period in the past, for example, using the speed on Monday, February 3, from 9:00 AM to 9:05 AM and the speed on Monday, February 10, from 9:00 AM to 9:05 AM to predict the speed on Monday, March 2, from 9:00 AM to 9:05 AM.

[0006] However, because anomalies that can occur at a given point in time (e.g., changes in weather or season) can vary in speed based on past patterns, and because traffic volume changes every moment, inappropriate data can be used for speed prediction. In other words, the assumption of maintaining similar speeds over the same time period is likely to increase the likelihood of errors in predicting traffic information.

[0007] Meanwhile, research is underway on whether changes in the form of detection vehicles (hereinafter referred to as "detectors") affect transportation for predicting traffic information. In this case, it is possible to predict congestion times macroscopically based on the timing of GPS events, but limitations exist in microscopic predictions (such as speed prediction for each time period on a link (the road to be predicted)) due to the limited number of detection samples.

[0008] Therefore, when using past-pattern speeds, it is necessary to use speeds similar to those during traffic conditions, rather than just speeds within the same time period. Meanwhile, density, corresponding to vehicle density, is considered the most objective and effective measure for determining traffic conditions in traffic engineering.

[0009] Research on density estimation can calculate the average number of vehicles on a limited road segment by taking images of that segment, and can also identify the number of all vehicles on a real road by taking images. However, it has limitations in terms of ensuring data availability when density data is always needed, for example, in traffic prediction.

[0010] The details described in the background section are included to enhance understanding of the background of this disclosure, and may include details that are not prior art well known to those skilled in the art. Summary of the Invention

[0011] The present invention provides an apparatus and method for predicting traffic information, the apparatus calculating the congestion transfer rate of a target road segment based on traffic volume information and density information; learning a traffic information prediction model using the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment; and predicting traffic information of the target road segment based on the traffic information prediction model to predict traffic information with high accuracy under traffic conditions different from the past.

[0012] The purpose of this disclosure is not limited to the foregoing objectives, and any other objectives and advantages not mentioned herein will be clearly understood from the following description and will become more apparent from the implementation of this disclosure. Furthermore, it will be readily apparent that the objectives and advantages of this disclosure can be achieved by the apparatus and / or methods and combinations thereof indicated in the claims.

[0013] According to one aspect of this disclosure, an apparatus for predicting traffic information may include: a memory storing a traffic information prediction model; and a controller calculating a congestion transfer rate W for a target road segment based on traffic volume and vehicle density. AB Furthermore, the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment are input into the traffic information prediction model to estimate the traffic information of the target road segment.

[0014] In embodiments of this disclosure, the controller may calculate the congestion transfer rate.

[0015] In embodiments of this disclosure, the memory may also store traffic volume estimation models.

[0016] In embodiments of this disclosure, the controller may estimate the traffic volume on a target road segment based on a traffic volume estimation model, corresponding to the number of detection vehicles passing through a specific point on the target road segment during a reference time period.

[0017] In embodiments of this disclosure, the controller can calculate vehicle density based on interval distance.

[0018] In embodiments of this disclosure, the controller can calculate the interval distance using the gap between the detection vehicle and the vehicle in front and the length of the vehicle in front.

[0019] In embodiments of this disclosure, the controller may calculate vehicle density based on the following Equation 4.

[0020] In embodiments of this disclosure, traffic information may include at least one of the average speed of the target road segment or the time taken to traverse the target road segment.

[0021] According to another aspect of this disclosure, a method for predicting traffic information may include: storing a traffic information prediction model in a memory; and calculating a congestion transfer rate W for a target road segment based on traffic volume and vehicle density using a controller. AB Furthermore, the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment are input into the traffic information prediction model through the controller to estimate the traffic information of the target road segment.

[0022] In embodiments of this disclosure, calculating the congestion transfer rate may include calculating the congestion transfer rate.

[0023] In embodiments of this disclosure, the method may further include storing a traffic volume estimation model in a memory.

[0024] In embodiments of this disclosure, the calculation of the congestion transfer rate may include: estimating the traffic volume on the target road segment based on a traffic volume estimation model, the traffic volume corresponding to the number of detection vehicles passing through a specific point on the target road segment during a reference time period.

[0025] In embodiments of this disclosure, the calculation of the congestion transfer rate may include: calculating the interval distance using the gap between the detection vehicle and the vehicle in front and the length of the vehicle in front, and calculating the vehicle density based on the interval distance.

[0026] In embodiments of this disclosure, calculating vehicle density may include calculating vehicle density.

[0027] In embodiments of this disclosure, the method may further include outputting traffic information via an output device. Attached Figure Description

[0028] The above and other objects, features, and advantages of this disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings:

[0029] Figure 1 This is a block diagram illustrating the configuration of a device for predicting traffic information according to an embodiment of the present disclosure;

[0030] Figure 2This is a diagram illustrating a traffic volume estimation model stored in a memory provided in a device for predicting traffic information, according to an embodiment of the present disclosure.

[0031] Figure 3 This is a diagram illustrating the process of calculating interval distances in a controller installed in a device for predicting traffic information according to an embodiment of the present disclosure;

[0032] Figure 4 This is a diagram illustrating the process of estimating density based on interval distance in a controller provided in a device for predicting traffic information according to an embodiment of the present disclosure;

[0033] Figure 5 This is a diagram illustrating the process of calculating the congestion transfer rate of a target road segment in a controller installed in a device for predicting traffic information according to an embodiment of the present disclosure.

[0034] Figure 6 This is a flowchart illustrating a method for predicting traffic information according to embodiments of the present disclosure; and

[0035] Figure 7 This is a block diagram illustrating a computing system for performing a method for predicting traffic information according to an embodiment of the present disclosure. Detailed Implementation

[0036] It is to be understood that the term “vehicle” or “of a vehicle” or other similar terms as used herein include motor vehicles, generally, for example, passenger cars, including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles, boats (including various vessels and ships), aircraft, etc., and includes hybrid vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other vehicles powered by alternative fuels (e.g., fuels obtained from resources other than petroleum). As mentioned herein, a hybrid vehicle is a vehicle having two or more power sources, such as a gasoline-powered and an electric vehicle.

[0037] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” as used herein are intended to also include the plural forms. It should also be understood that when the terms “comprises” and / or “comprising” are used in this specification, they specify the presence of the stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or combinations thereof. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items. Throughout the specification, unless explicitly stated otherwise, the word “comprise” and variations such as “comprises” or “comprising” will be understood to imply the inclusion of the stated elements, but do not exclude any other elements. Furthermore, the terms “unit,” “device,” “block,” and “module” described in the specification mean a unit for performing at least one function and operation, and can be implemented by hardware components or software components and combinations thereof.

[0038] Furthermore, the control logic of this disclosure may be embodied in a non-volatile computer-readable medium containing executable program instructions that can be executed by a processor, controller, etc. Examples of computer-readable media include, but are not limited to, ROM, RAM, optical disc (CD)-ROM, magnetic tape, floppy disk, flash drive, smart card, and optical data storage devices. The computer-readable medium may also be distributed across a network-coupled computer system, enabling it to be stored and executed in a distributed manner, for example, via a telematics server or a controller area network (CAN).

[0039] In the following, some embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Furthermore, when reference numerals are affixed to the constituent elements of each drawing, the same reference numerals will be used to indicate the same constituent element if it is shown in other drawings. In addition, detailed descriptions of well-known features or functions will be omitted in the description of embodiments of the present disclosure to avoid unnecessarily obscuring the spirit of the disclosure.

[0040] In describing components according to embodiments of this disclosure, terms such as first, second, "A", "B", (a), (b), etc., may be used. These terms are intended only to distinguish one component from another, and they do not limit the nature, order, or sequence of the constituent components. Furthermore, unless otherwise defined, all terms used herein (including technical or scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. Terms as defined in commonly used dictionaries should be interpreted as having a meaning equivalent to that in the context of the relevant field and should not be interpreted as having an ideal or overly formal meaning unless explicitly defined as having an ideal or overly formal meaning in this application.

[0041] Figure 1 This is a block diagram illustrating the configuration of a device for predicting traffic information according to an embodiment of the present disclosure.

[0042] like Figure 1 As shown, the device 100 for predicting traffic information according to an embodiment of the present disclosure may include a memory 10, a communication device 20, an output device 30, and a controller 40. In such a case, depending on how the device 100 for predicting traffic information according to an embodiment of the present disclosure is executed, the various components may be combined into one component, and some components may be omitted.

[0043] First, let's look at the corresponding components. The memory 10 can store various logics, algorithms, and programs required in the following processes: calculating the congestion transfer rate of the target road segment based on traffic volume and density information; learning a traffic information prediction model using the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment; and predicting traffic information of the target road segment based on the traffic information prediction model.

[0044] Additionally, memory 10 can also store a traffic volume estimation model used to estimate traffic volume on a target road segment based on the number of detection vehicles passing through specific points on the target road segment within a reference time period (e.g., 1 hour). An example of such a traffic volume estimation model is... Figure 2 As shown.

[0045] Figure 2 This is a diagram illustrating a traffic volume estimation model stored in a memory provided in a device for predicting traffic information, according to an embodiment of the present disclosure. The horizontal axis represents the number of detection vehicles, and the vertical axis represents traffic volume. For example, when the number of detection vehicles 200 passing through a specific point on a target road segment during a reference time (e.g., 1 hour) is q i At that time, the traffic volume on the target road segment can be Q. i .

[0046] It can be achieved by Figure 1 The traffic volume estimation model is generated by performing regression analysis on the number of detection vehicles 200 detected by the detection vehicle detector 300 and the number of ordinary vehicles (service subscription vehicles) designated as detection vehicles 200.

[0047] The memory 10 can store logic for calculating the interval distance based on the detection data received from the detection vehicle 200 and for calculating the vehicle density based on the interval distance.

[0048] Such a memory 10 may include at least one type of storage medium, such as flash memory, hard disk memory, micro memory, card memory (e.g., security digital (SD) card or extreme digital (XD) card), random access memory (RAM), static RAM (SRAM), read-only memory (ROM), programmable ROM (PROM), electrically erasable PROM (EEPROM), magnetic RAM (MRAM), magnetic disk and optical disk.

[0049] The communication device 20 may be a module providing a communication interface with a detection vehicle 200 traveling on the road and a detection vehicle detector 300 located at a specific point on the road. It can periodically receive detection data from both the detection vehicle 200 and the detection vehicle detector 300. In this case, the detection data received from the detection vehicle 200 via the communication device 20 may include identification information (ID), driving speed, location (e.g., Global Positioning System (GPS) location), the length of the vehicle ahead, the gap between the detection vehicle 200 and the vehicle ahead, or the gap between the detection vehicle 200 and the vehicle behind. The detection data received from the detection vehicle detector 300 via the communication device 20 may include identification information (ID), driving speed, the length of the vehicle ahead, the gap between the detection vehicle 200 and the vehicle ahead, or the gap between the detection vehicle 200 and the vehicle behind. This detection vehicle 200 may have a telematics terminal serving as a vehicle terminal. Furthermore, the detection vehicle 200 can obtain the gap between itself and the vehicle in front using a front sensor, the gap between itself and the vehicle behind using a rear sensor, and the length of the vehicle in front using a forward-facing camera. In this case, the detection vehicle 200 can distinguish the vehicle type (e.g., bus, van, SUV, truck, etc.) based on the rear or side shape of the vehicle in front, and can pre-store the length according to the vehicle type.

[0050] The communication device 20 may include at least one of a mobile communication module, a wireless internet module, and a short-range communication module for communicating with the detection vehicle 200 and the detection vehicle detector 300.

[0051] The mobile communication module can communicate with the detection vehicle 200 and the detection vehicle detector 300 through a mobile communication network established according to the mobile communication technical standards or communication schemes (e.g., Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA2000), Enhanced Voice Data Optimized or Enhanced Voice Data Only (EV-DO), Wideband CDMA (WCDMA), High-Speed ​​Downlink Packet Access (HSDPA), High-Speed ​​Uplink Packet Access (HSUPA), Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), etc.), fourth-generation (4G) mobile telecommunications, or fifth-generation (5G) mobile telecommunications.

[0052] The wireless internet module can be a module for wireless internet access, which can communicate with the detection vehicle 200 and the detection vehicle detector 300 through wireless LAN (WLAN), Wi-Fi, Wi-Fi Direct, Digital Living Network Alliance (DLNA), WiBro, Global Microwave Interconnection Access (WiMAX), High-Speed ​​Downlink Packet Access (HSDPA), High-Speed ​​Uplink Packet Access (HSUPA), Long Term Evolution (LTE), and Advanced Long Term Evolution (LTE-A).

[0053] The short-range communication module can use Bluetooth. TM It requires at least one of the following technologies to support short-range communication: Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC), and Wireless Universal Serial Bus (USB).

[0054] Figure 1 Output device 30 can provide users with... Figure 1 The controller 40 predicts traffic information for the target road segment. In this case, the traffic information may include the passing speed (average speed) of the target road segment, the minimum speed of the target road segment, the maximum speed of the target road segment, the time taken to pass through the target road segment, etc.

[0055] The controller 40 can perform overall control, enabling each component to perform its own function normally. Such a controller 40 can be implemented in hardware, in software, or a combination thereof. Preferably, the controller 40 can be implemented as, but is not limited to, a microprocessor.

[0056] Specifically, controller 40 can perform various controls in the following processes: calculating the congestion transfer rate of the target road segment based on traffic volume and density information; learning a traffic information prediction model using the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment; and predicting traffic information for the target road segment based on the traffic information prediction model. In this case, controller 40 can detect the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment based on detection data.

[0057] The controller 40 can estimate the traffic volume corresponding to the number of detection vehicles 200 passing through a specific point on the target road segment during a reference time (e.g., 1 hour) based on a traffic volume estimation model stored in the memory 10.

[0058] The controller 40 can estimate the density (e.g., vehicle density) of a target road segment based on detection data obtained from the detection vehicle 200 and the detection vehicle detector 300. In other words, the controller 40 can calculate the interval distance based on the detection data and can calculate the density based on the interval distance.

[0059] In the following text, reference will be made to Figure 3 and Figure 4 The process of estimating density in controller 40 is described in detail.

[0060] Figure 3 This is a diagram illustrating the process of calculating interval distances in a controller installed in a device for predicting traffic information according to an embodiment of the present disclosure. Figure 4 This is a diagram illustrating the process of estimating density based on interval distance in a controller installed in a device for predicting traffic information according to an embodiment of the present disclosure.

[0061] like Figure 3 As shown, Figure 1 The controller 40 can calculate the distance based on the gap between the detection vehicle 200 and the vehicle in front 400, and the length of the vehicle in front 400, received from the detection vehicle 200. In other words, the controller 40 can calculate the distance by adding the gap between the detection vehicle 200 and the vehicle in front 400 to the length of the vehicle in front 400. For example, when the gap between the detection vehicle 200 and the vehicle in front 400 is 60m, and the length of the vehicle in front 400 is 9m, the distance is 69m (=60m+9m).

[0062] Subsequently, the controller 40 can estimate the average interval distance of the population using N samples at multiple interval distances received from multiple detection vehicles 200. In this case, when the number of samples at interval distances is N, when the mean of the N samples at interval distances is E(x), and when the standard deviation of the N samples at interval distances is s, the average interval distance μ of the population can be expressed as the statistic T after distribution t. This statistic T can be expressed as Equation 1 below.

[0063] (Equation 1):

[0064]

[0065] In this paper, Equation 1 above can be expressed as follows: Figure 4 The illustration shown is in [the image]. Figure 4 In this case, when the degrees of freedom are N-1 and the limit at the 95% confidence level is α, T can be expressed as Equation 2 for α. The average interval distance μ of the population can then be expressed as Equation 3 with a range of a to b.

[0066] (Equation 2)

[0067] -α≤T≤α

[0068] (Equation 3)

[0069] a≤μ≤b

[0070] When the average interval distance μ of the group is obtained as in Equation 3 above, the controller 40 can obtain the density K of a specific road segment with a specific length, as in Equation 4 below.

[0071]

[0072] In this paper, L represents the length of a specific road segment, a represents the minimum average interval distance μ of the group, and b represents the maximum average interval distance μ of the group.

[0073] At the same time, such as Figure 5 As shown, controller 40 can calculate the congestion transfer rate of the target road segment based on traffic volume and density.

[0074] Figure 5 This is a diagram illustrating the process of calculating the congestion transfer rate of a target road segment in a controller installed in a device for predicting traffic information according to an embodiment of the present disclosure.

[0075] exist Figure 5 In the diagram, segment A represents the segment where congestion occurs, segment B represents the target segment, and segment C represents the segment following the target segment.

[0076] Figure 1The controller 40 can estimate the traffic volume (number of vehicles / h) corresponding to the number of detection vehicles 200 on road segment A, can estimate the traffic volume corresponding to the number of detection vehicles 200 on road segment B, and can detect the density of road segment A (number of vehicles / km) and the density of road segment B.

[0077] Subsequently, controller 40 can calculate the speed at which congestion shifts from segment A to segment B based on the following equation 5 (hereinafter referred to as the congestion shift rate of segment B).

[0078] (Equation 5)

[0079]

[0080] Here, q A q represents the traffic volume on road segment A. B k represents the traffic volume on road segment B. A k represents the density of road segment A. B This represents the density of road segment B. As an example, when q... A 800, q B For 1200, k A It is 50, and k B When the value is 30, the congestion transfer rate of road segment B becomes -20km / h.

[0081] Subsequently, the controller 40 can calculate the speed (average passing speed) of road segment A, the speed of road segment B, and the speed of road segment C based on the detected data.

[0082] Subsequently, controller 40 can estimate the traffic information of road segment B based on its machine learning-based traffic information prediction model, taking into account the congestion transfer rate of road segment B, the speed of road segment A, the speed of road segment B, and the speed of road segment C. In this case, the traffic information can be the traffic information of road segment B within a specific time period (e.g., 2 hours) starting from the current time point, which may include the average passing speed of road segment B or the time spent passing through road segment B.

[0083] Simultaneously, upon receiving the congestion transfer rate, speed, preceding speed, and following speed of the target road segment, the controller 40 can learn a traffic information prediction model to output predicted traffic information for the target road segment. Here, the controller 40 can implement the traffic information prediction model as a random forest. In this case, the objective function can be set to a random search using the root mean square error (RMSE) or parameter tuning, and the validation can be set to cross-validation (k: 10).

[0084] Figure 6 This is a flowchart illustrating a method for predicting traffic information according to an embodiment of the present disclosure.

[0085] First, in operation 601, Figure 1 The memory 10 can store traffic information prediction models.

[0086] In operation 602, Figure 1 The controller 40 can calculate the congestion transfer rate of the target road segment based on traffic volume and vehicle density.

[0087] In operation 603, controller 40 can input congestion transfer rate, speed of target segment, speed of segment before target segment, and speed of segment after target segment into traffic information prediction model to estimate traffic information of target segment.

[0088] Figure 7 This is a block diagram illustrating a computing system for performing a method for predicting traffic information according to an embodiment of the present disclosure.

[0089] Reference Figure 7 The method for predicting traffic information according to embodiments of this disclosure can be implemented by a computing system. The computing system 1000 may include at least a processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage device 1600, and a network interface 1700 connected to each other via a system bus 1200.

[0090] Processor 1100 may be a central processing unit (CPU) or semiconductor device that processes instructions stored in memory 1300 and / or storage 1600. Memory 1300 and storage 1600 may include various types of volatile or non-volatile storage media. For example, memory 1300 may include ROM (Read-Only Memory) 1310 and RAM (Random Access Memory) 1320.

[0091] Therefore, the operation of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware or by software modules or combinations thereof executed by processor 1100. The software modules may reside on storage media such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disks, SSDs (solid-state drives), removable disks, and CD-ROMs (i.e., memory 1300 and / or storage 1600). Exemplary storage media may be coupled to processor 1100. Processor 1100 may read information from and write information to the storage media. Alternatively, the storage media may be integrated with processor 1100. The processor and storage media may reside in an application-specific integrated circuit (ASIC). The ASIC may be located within the user terminal. In another case, the processor and storage media may be located as separate components in the user terminal.

[0092] The apparatus and method for predicting traffic information according to embodiments of the present disclosure can be provided to calculate the congestion transfer rate of a target road segment based on traffic volume information and density information, learn a traffic information prediction model using the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment, and predict the traffic information of the target road segment based on the traffic information prediction model, thereby predicting traffic information with high accuracy in traffic conditions different from the past.

[0093] While this disclosure has been described above with reference to exemplary embodiments and accompanying drawings, it is not limited thereto. Various modifications and alterations may be made by those skilled in the art to which this disclosure pertains without departing from the spirit and scope of this disclosure as claimed in the appended claims.

[0094] Therefore, exemplary embodiments of this disclosure are provided to illustrate the spirit and scope of this disclosure, but are not intended to limit them, such that the spirit and scope of this disclosure are not limited by the embodiments. The scope of this disclosure should be interpreted based on the appended claims, and all technical concepts within the scope of the claims should be included within the scope of this disclosure.

Claims

1. A device for predicting traffic information, the device comprising: The memory stores traffic information prediction models; as well as The controller is configured to calculate the congestion transfer rate W of the target road segment based on traffic volume and vehicle density. AB Furthermore, the congestion transfer rate, the speed of the target road segment, the speed of the road segment preceding the target road segment, and the speed of the road segment following the target road segment are input into the traffic information prediction model to estimate the traffic information of the target road segment. The memory also stores a traffic volume estimation model, and the controller is further configured to estimate the traffic volume of the target road segment based on the traffic volume estimation model, wherein the traffic volume estimation model is generated by performing regression analysis on the number of detection vehicles detected by the detection vehicle detector and the number of ordinary vehicles designated as detection vehicles.

2. The device according to claim 1, wherein, The controller calculates the congestion transfer rate W based on the following equation: AB : Where, q A q represents the traffic volume of the road segment following the target road segment. B k represents the traffic volume on the target road segment. A k represents the density of road segments following the target road segment. B This indicates the density of the target road segment.

3. The device according to claim 1, wherein, The traffic volume on the target road segment corresponds to the number of detection vehicles that passed through a specific point on the target road segment during the reference time period.

4. The device according to claim 1, wherein, The controller calculates the vehicle density based on the interval distance.

5. The device according to claim 4, wherein, The controller uses the gap between the detection vehicle and the vehicle in front, as well as the length of the vehicle in front, to calculate the interval distance.

6. The device according to claim 4, wherein, The controller calculates the vehicle density based on the following equation: Where L represents the length of the target road segment, Let represent the minimum value of the average interval distance μ of the population, and b represent the maximum value of the average interval distance μ of the population.

7. The device according to claim 1, wherein, The traffic information includes at least one of the average speed of the target road segment and the time taken to travel through the target road segment.

8. The device according to claim 1, further comprising: The output device is configured to output the traffic information.

9. A method for predicting traffic information, the method comprising: Traffic information prediction models are stored in memory; The controller calculates the congestion transfer rate W of the target road segment based on traffic volume and vehicle density. AB ; The controller inputs the congestion transfer rate, the speed of the target road segment, the speed of the road segments preceding the target road segment, and the speed of the road segments following the target road segment into the traffic information prediction model to estimate the traffic information of the target road segment. The traffic volume estimation model is stored in the memory, and The traffic volume of the target road segment is estimated based on the traffic volume estimation model, wherein the traffic volume estimation model is generated by performing regression analysis on the number of detection vehicles detected by the detection vehicle detector and the number of ordinary vehicles designated as detection vehicles.

10. The method according to claim 9, wherein, Calculating the congestion transfer rate includes: The congestion transfer rate W is calculated based on the following equation. AB : Where, q A q represents the traffic volume of the road segment following the target road segment. B k represents the traffic volume on the target road segment. A k represents the density of road segments following the target road segment. B This indicates the density of the target road segment.

11. The method according to claim 9, wherein, The traffic volume on the target road segment corresponds to the number of detection vehicles that pass through a specific point on the target road segment within a reference time period.

12. The method according to claim 9, wherein, Calculating the congestion transfer rate includes: The distance is calculated using the gap between the detection vehicle and the vehicle in front, and the length of the vehicle in front; and The vehicle density is calculated based on the interval distance.

13. The method according to claim 12, wherein, Calculating the vehicle density includes: The vehicle density is calculated based on the following equation: Where L represents the length of the target road segment, Let represent the minimum value of the average interval distance μ of the population, and b represent the maximum value of the average interval distance μ of the population.

14. The method according to claim 9, wherein, The traffic information includes at least one of the average speed of the target road segment and the time taken to travel through the target road segment.

15. The method of claim 9, further comprising: The traffic information is output through the output device.

Images