Apparatus and method for predicting traffic speed

Abstract

The invention relates to an apparatus and a method for predicting traffic speed. In a traffic speed prediction apparatus and method, the traffic speed prediction apparatus includes a processor configured to estimate a path navigation demand based on current path navigation data for each road segment, predicting a future traffic speed by using the path navigation demand and past speed data of each road section starting from the current time point; the memory is configured to store algorithms and data driven by the processor.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present application claims priority to Korean Patent Application No. 10-2023-0161402 filed on Nov. 20, 2013, the entire contents of which application is incorporated herein for all purposes by this reference. Technical Field

[0003] The present invention relates to a traffic speed prediction device and method, and more particularly, to a technology for predicting future traffic speed data by considering path navigation requirements. Background Art

[0004] In metropolitan areas where traffic congestion generates huge social and economic costs, the construction and expansion of road infrastructure is constrained by budget constraints and land availability. Therefore, various traffic information is provided instead of expanding road infrastructure.

[0005] Traditionally, only past speed data is used to predict future traffic speed data. Therefore, for routes that are longer than a certain period of time (long-distance routes), it may be difficult to find the causality of traffic volume causing traffic speed, and trends can only be predicted based on the assumption that past speed data is repeated. Therefore, with the current time point as the benchmark, causality is insufficient and there is no choice but to rely on the correlation with past speed data.

[0006] Furthermore, conventionally, the total number of probe vehicles passing through traffic collection points is calculated for each time interval. In this case, the probe vehicles may need to pass through all traffic collection points, so there is a delay in collecting real-time traffic volume, making it difficult to use data in a prediction model to predict congestion in advance.

[0007] The information included in this Background of the Invention section is only intended to enhance understanding of the overall background of the invention and should not be taken as an acknowledgment or any form of suggestion that this information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0008] Various aspects of the present invention are directed to providing a traffic speed prediction apparatus and method configured to improve the accuracy of future traffic prediction by estimating the expected travel demand of each road segment in advance and applying it to future traffic prediction.

[0009] Furthermore, exemplary embodiments of the present invention attempt to provide a traffic speed prediction apparatus and method configured to, when a user requests route navigation by inputting a destination, determine how many vehicles will arrive at each road segment using the number of route navigation requests and predict the traffic volume of the corresponding road by estimating the demand for the corresponding road.

[0010] Furthermore, exemplary embodiments of the present invention attempt to provide a traffic speed prediction apparatus and method configured to predict the traffic speed of each road section, rather than predicting the traffic speed based on a single road section, thereby accurately predicting traffic congestion.

[0011] The technical objectives of the present invention are not limited to the above objectives, and those skilled in the art can clearly understand other technical objectives not mentioned through the description of the claims.

[0012] An exemplary embodiment of the present invention provides a traffic speed prediction device, which includes a processor and a memory, wherein the processor is configured to estimate a route navigation demand based on current route navigation data of each road segment, and to predict future traffic speeds using the route navigation demand and past speed data of each road segment starting from a current time point; and the memory is configured to store algorithms and data driven by the processor.

[0013] In an exemplary embodiment of the present invention, the processor may be configured to generate a route navigation requirement table based on 3D data, wherein the 3D data includes road segments, a route navigation request time point for each road segment, and an arrival time point for each road segment.

[0014] In an exemplary embodiment of the present invention, the processor can be configured to generate a route navigation demand table based on the road segments, the route navigation request time points of each road segment, and the arrival time points of each road segment, wherein the route navigation demand table includes the number of vehicles scheduled to arrive at each arrival time point of each road segment.

[0015] In an exemplary embodiment of the present invention, the processor can be configured to: select a segment using linked segments of a road; divide 24 hours into a predetermined first time unit and assign an index to each path navigation request time point of each segment; divide 24 hours into a predetermined second time unit and assign an index to each arrival time point of each segment; generate a path navigation demand table by mapping the index of each path navigation request time point of each segment with the number of vehicles scheduled to arrive for each index of each arrival time point of each segment.

[0016] In an exemplary embodiment of the present invention, the processor may be configured to determine that the future traffic speed will decrease as the number of vehicles scheduled to arrive at each arrival time point of each road segment increases.

[0017] In an exemplary embodiment of the present invention, the processor may be configured to estimate the demand of each road segment according to the number of vehicles scheduled to arrive at each arrival time point of each road segment, and estimate the future traffic speed according to the demand.

[0018] In an exemplary embodiment of the present invention, the processor may be configured to estimate the traffic speed of each road segment according to the number of route guidance at each route guidance request time point of each road segment.

[0019] In an exemplary embodiment of the present invention, the processor may be configured to predict future traffic speed by further reflecting auxiliary data including at least one of weather, day of the week, time of day, season information, or a combination thereof.

[0020] In an exemplary embodiment of the present invention, the processor may include an attention model, an embedding layer, and a prediction model, taking past speed data and path navigation data as inputs of the attention model; the embedding layer is used to embed auxiliary data; and the prediction model is used to predict future traffic speeds using the outputs of the attention model and the embedding layer.

[0021] In an exemplary embodiment of the present invention, the processor can be configured to: select at least one road section for data collection; determine whether past speed data, path navigation data and auxiliary data have been collected normally from the exploration vehicle in at least one selected road section; and reselect another road section in response to a situation where any one of the past speed data, path navigation data and auxiliary data has not been collected normally.

[0022] In an exemplary embodiment of the present invention, the processor may be configured to configure the route guidance requirement table based on the route guidance data in response to a situation in which past speed data, route guidance data, and auxiliary data are normally collected.

[0023] In an exemplary embodiment of the present invention, a communication device operably connected to the processor may be further included, the communication device being configured to collect past speed data and path navigation data from the investigation vehicle.

[0024] An exemplary embodiment of the present invention provides a traffic speed prediction method, the method comprising: collecting, by a processor, past speed data and path navigation data from a detection vehicle starting from a current time point for each road segment; estimating, by a processor, path navigation demand based on the path navigation data at the current time point for each road segment; and predicting, by a processor, future traffic speed using the path navigation demand and the past speed data of each road segment starting from the current time point.

[0025] In an exemplary embodiment of the present invention, prediction of future traffic speed may include: generating, by a processor, a path navigation requirement table based on 3D data, wherein the 3D data includes road segments, path navigation request time points for each road segment, and arrival time points for each road segment.

[0026] In an exemplary embodiment of the present invention, the prediction of future traffic speed may include: generating a route navigation demand table based on road segments, route navigation request time points for each road segment and arrival time points for each road segment through a processor, wherein the route navigation demand table includes the number of vehicles scheduled to arrive at each arrival time point for each road segment.

[0027] In an exemplary embodiment of the present invention, the generation of a path navigation demand table may include: by a processor, selecting a segment by utilizing linked segments of a road; by a processor, dividing 24 hours by a predetermined first time unit, and assigning an index to each path navigation request time point of each segment; by a processor, dividing 24 hours by a predetermined second time unit, and assigning an index to each arrival time point of each segment; by a processor, mapping the index of each path navigation request time point of each segment with the number of vehicles planned to arrive at each index of each arrival time point of each segment.

[0028] In an exemplary embodiment of the present invention, the prediction of the future traffic speed may include: determining, by a processor, that the future traffic speed will decrease as the number of vehicles scheduled to arrive at each arrival time point of each road segment increases.

[0029] In an exemplary embodiment of the present invention, the prediction of future traffic speed may include: by a processor, estimating the demand of each road segment according to the number of vehicles scheduled to arrive at each arrival time point of each road segment, and estimating the future traffic speed according to the demand.

[0030] In an exemplary embodiment of the present invention, the prediction of future traffic speed may include: predicting the future traffic speed by further reflecting auxiliary data by a processor, wherein the auxiliary data includes at least one of weather, day of the week, time of day, season information or a combination thereof.

[0031] In an exemplary embodiment of the present invention, prediction of future traffic speed may include: selecting, by a processor, at least one road segment for data collection; determining, by a processor, whether past speed data, path navigation data, and auxiliary data have been normally collected from a survey vehicle in at least one selected road segment; and reselecting, by a processor, another road segment in response to a situation in which any one of the past speed data, path navigation data, and auxiliary data has not been normally collected.

[0032] According to an exemplary embodiment of the present invention, the accuracy of future traffic prediction can be improved by estimating the expected travel demand of each road segment in advance and applying it to future traffic prediction.

[0033] Furthermore, in the case where a user requests route guidance by inputting a destination, the number of route guidance requests may be used to determine how many vehicles will arrive at each road segment, and the traffic volume on the corresponding road may be predicted by estimating the demand for the corresponding road.

[0034] Furthermore, rather than predicting traffic speed based on a single road segment, the traffic speed for each road segment can be predicted, thereby accurately predicting traffic congestion.

[0035] Furthermore, various effects that can be directly or indirectly determined by the present specification can be provided.

[0036] The methods and apparatus of the present invention have other features and advantages, which will be apparent from or are described in detail in the accompanying drawings and subsequent detailed descriptions incorporated herein, which together serve to explain the specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A block diagram showing an exemplary traffic speed prediction apparatus is shown.

[0038] Figure 2 The structure of an exemplary traffic speed prediction model is shown.

[0039] Figure 3 An example of a path navigation requirement table is shown.

[0040] Figure 4 A schematic diagram for describing an example of route navigation data is shown.

[0041] Figure 5 An example of predicting future traffic speed using past traffic speed is shown.

[0042] Figure 6 A two-dimensional graph is shown for describing an exemplary relationship between traffic speed, traffic volume, and traffic demand.

[0043] Figure 7 An example graph expressing the relationship between traffic speed, traffic volume, and traffic demand as a heat map is shown.

[0044] Fig. 8A , Figure 8B , Figure 8C and Fig.8D An example graph showing traffic speed according to route demand is shown respectively.

[0045] Fig. 9 A flow chart showing an exemplary traffic speed prediction method is shown.

[0046] Fig.10An exemplary computing system is shown.

[0047] It should be understood that the accompanying drawings are not necessarily drawn to scale, but rather present appropriately simplified depictions of various features illustrating the basic principles of the present invention. The specific design features of the present invention included herein, such as specific dimensions, directions, positions, shapes, positions, and shapes, will be determined in part by the specific target application and the environment of use.

[0048] In the drawings, like reference numbers refer to the same or equivalent parts of the present invention throughout the several figures of the drawing.

[0049] Description of reference numerals:

[0050] 100: Traffic speed prediction device

[0051] 110: Communication device

[0052] 120: Storage device

[0053] 130: Interface device

[0054] 140: Processor. DETAILED DESCRIPTION

[0055] The following will be referred to in detail various embodiments of the present invention, examples of which are shown in the accompanying drawings and described below. Although the present invention will be described in conjunction with exemplary embodiments of the present invention, it will be understood that this specification is not intended to limit the present invention to those exemplary embodiments of the present invention. On the other hand, the present invention is intended to cover not only the exemplary embodiments of the present invention, but also various alternatives, modifications, equivalents and other embodiments that may be included in the spirit and scope of the present invention defined by the appended claims.

[0056] Some exemplary embodiments of the present invention will be described in detail below with reference to the exemplary drawings. It should be noted that when adding reference numerals to the constituent elements of each drawing, even if the same constituent elements are represented on different drawings, the same constituent elements include the same reference numerals as much as possible. When describing the exemplary embodiments of the present invention, when it is determined that the detailed description of the known configuration or function related to the exemplary embodiments of the present invention may obscure the main points of the present invention, the detailed description thereof will be omitted.

[0057] When describing the constituent elements according to the exemplary embodiments of the present invention, terms such as first, second, A, B, (a) and (b) may be used. These terms are only used to distinguish constituent elements from other constituent elements, and the nature, order or sequence of the constituent elements are not limited by these terms. In addition, all terms (including technical scientific terms) used in this article have the same meaning as the meaning commonly understood by the technicians (those skilled in the art) in the technical field of the present invention to which the exemplary embodiments of the present invention belong, unless they have different definitions. The terms defined in the commonly used dictionaries should be interpreted as having the meanings that match the context of the relevant technology, and should not be interpreted as having idealized or overly formal meanings, unless they are clearly defined in this specification.

[0058] The following will refer to Figures 1 to 10 Various exemplary embodiments of the present invention are described in detail.

[0059] Figure 1 A block diagram showing an exemplary traffic speed prediction apparatus is shown.

[0060] The traffic speed prediction device 100 according to the exemplary embodiment of the present invention can be implemented in a server or center outside the vehicle. The traffic speed prediction device 100 can be configured to communicate with the vehicle to collect traffic data (speed data, etc.), path navigation data, auxiliary data, etc. from the vehicle, and provide the vehicle with a traffic speed prediction result. In this case, the auxiliary data may include weather, day of the week, time of day, seasonal information, etc., and the auxiliary data may be provided not only by the vehicle but also by an external server that provides information such as weather.

[0061] The traffic speed prediction device 100 may be configured to use past traffic speed data, route navigation data, and auxiliary data to predict future traffic speeds. In this case, the route navigation data may include the number of times a user inputs a destination and performs route navigation for each road segment. Accordingly, the traffic speed prediction device 100 may be configured to determine that the expected driving demand of the corresponding road segment is high in response to the situation that the number of times the route of each road segment has been navigated exceeds a predetermined number of times. In addition, the traffic speed prediction device 100 may be configured to predict that the traffic volume of the road segment with a high route navigation demand will increase. In this case, the road segment may include a link road segment, and in the case where the user inputs a destination to generate a path, the path can be generated by connecting a plurality of link road segments.

[0062] Reference Figure 1, the traffic speed prediction device 100 may include a communication device 110, a storage device 120, an interface device 130, and a processor 140. According to an exemplary embodiment of the present invention, the traffic speed prediction device 100 may be implemented as a single unit by coupling components to each other, and some components may be omitted.

[0063] The communication device 110 is a hardware device implemented using various electronic circuits to send and receive signals through wireless or wired connections. The communication device 110 can send and receive information with components within the traffic speed prediction device 100 based on network communication technology.

[0064] In addition, the communication device 110 can communicate with the exploration vehicle or the like through wireless Internet technology, mobile communication technology, or short-range communication technology.

[0065] In this article, wireless communication technology may include wireless local area network (WLAN), wireless broadband (WiBro), Wi-Fi, world interoperability for microwave access (WiMAX), etc. In addition, short-range communication technology may include Bluetooth, ZigBee, ultra-wideband (UWB), radio frequency identification (RFID), infrared data association (IrDA), etc.

[0066] The mobile communication technology may include a mobile communication network established according to a mobile communication technology standard or communication method (for example, Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA 2000), Enhanced Voice Data Optimization 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), Long Term Evolution-Advanced (LTE-A), fourth generation mobile communication (4G), fifth generation mobile communication (5G), etc.), and the communication device 110 may communicate with the exploration vehicle through the mobile communication network.

[0067] Wireless Internet technologies may include wireless local area network (WLAN), wireless fidelity (Wi-Fi), Wi-Fi direct, Digital Living Network Alliance (DLNA), wireless broadband (WiBro), world interoperability for microwave access (WiMAX), high-speed downlink packet access (HSDPA), high-speed uplink packet access (HSUPA), long-term evolution (LTE), long-term evolution-advanced (LTE-A), etc. For wireless Internet access, the communication device 110 may communicate with the exploration vehicle through a mobile communication network.

[0068] Short-range communication technologies may include using Bluetooth TM, radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, near field communication (NFC), wireless universal serial bus (USB) technology, or any combination thereof.

[0069] For example, the communication device 110 may receive traffic data (speed data), route navigation data, assistance data, etc. from the survey vehicle, and may provide the vehicle with predicted future traffic speeds.

[0070] The storage device 120 may store data and / or algorithms required for the processor 140 to run.

[0071] For example, the storage device 120 may store traffic data (speed data) received from the exploration vehicle, route navigation data, auxiliary data, etc. In addition, the storage device 120 may store information such as future traffic speed predicted by the processor 140 .

[0072] The storage device 120 may include at least one type of storage medium among the following types of memories: flash memory, hard disk, microcomputer, card (such as secure digital card (SD) or extreme digital card (XD)), random access memory (RAM), static RAM (SRAM), read-only memory (ROM), programmable ROM (PROM), electrically erasable PROM (EEPROM), magnetic storage medium (MRAM), magnetic disk and optical disk.

[0073] The interface device 130 may include an input device for receiving a control command from a user and an output device for outputting the operating state and operating results of the device 100. In this context, the input device may include a key button, and may include a mouse, a joystick, a shuttle knob, a stylus pen, etc. In addition, the input device may include a soft key implemented on a display.

[0074] The output device may include a display, and may also include a voice output device such as a speaker. In this case, in response to the case where a touch sensor formed of a touch film, a touch sheet, or a touch pad is provided on the display, the display may operate as a touch screen, and may be implemented in a form in which the input device and the output device are integrated. In an exemplary embodiment of the present invention, the output device may output predicted traffic speed information and traffic volume for each road section.

[0075] In this case, the display may include at least one of a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFTLCD), an organic light emitting diode display (OLED display), a flexible display, a field emission display (FED), and a 3D display.

[0076] The processor 140 may be electrically connected to the communication device 110 , the storage device 120 , the interface device 130 , etc., may electrically control each component, and may be a circuit that executes software commands, thereby performing various data processing and calculations described below.

[0077] The processor 140 may be configured to process signals transmitted between the various components of the traffic speed prediction device 100 and perform overall control so that each component can normally perform its function. The processor 140 may be implemented in the form of hardware, software, or a combination of hardware and software. For example, the processor 140 may be implemented in the form of a microprocessor, but the present invention is not limited thereto.

[0078] The processor 140 may be configured to estimate the route navigation demand based on the past speed data of each road segment from the current time and the route navigation data of the current time, thereby predicting the future traffic speed. In this case, the route navigation demand may be reflected as a route navigation demand table.

[0079] The processor 140 may be configured to generate a route navigation requirement table based on the 3D data, the 3D data including a plurality of road sections, a route navigation request time point for each road section, and an arrival time point for each road section. In addition, the processor 140 may be configured to generate a route navigation requirement table based on the road section, a route navigation request time point for each road section, and an arrival time point for each road section, the route navigation requirement table including the number of vehicles scheduled to arrive at each arrival time point for each road section.

[0080] The processor 140 may be configured to select a road segment using a link road segment of a road, divide 24 hours into a predetermined first time unit (e.g., 10 minutes) and assign an index to each route navigation request time point of each road segment, and divide 24 hours into a predetermined second time unit (e.g., 5 minutes) and assign an index to each arrival time point of each road segment. In addition, the processor 140 may be configured to generate a route navigation demand table by mapping the index of each route navigation request time point of each road segment with the number of vehicles scheduled to arrive for each index of each arrival time point of each road segment.

[0081] The processor 140 may be configured to determine that future traffic speed will decrease as the number of vehicles scheduled to arrive at each arrival time point for each road segment increases.

[0082] The processor 140 may be configured to estimate the demand for each road segment according to the number of vehicles scheduled to arrive at each arrival time point of each road segment, and estimate the future traffic speed according to the demand.

[0083] The processor 140 may be configured to estimate the traffic speed of each road segment according to the number of route guidance at each route guidance request time point of each road segment.

[0084] The processor 140 may be configured to predict future traffic speed by further reflecting auxiliary data including at least one of weather, day of the week, time of day, season information, or a combination thereof.

[0085] The processor 140 may include an attention model, an embedding layer, and a prediction model, with past speed data and path navigation data as inputs to the attention model; the embedding layer is used to embed auxiliary data; the prediction model is used to predict future traffic speeds using the outputs of the attention model and the embedding layer, which will be referred to later. Figure 2 Describe in detail.

[0086] The processor 140 may be configured to select at least one road section for data collection, determine whether past speed data, path navigation data, and auxiliary data are normally collected from the exploration vehicle in the at least one selected road section, and reselect another road section in response to the situation that any one of the past speed data, path navigation data, and auxiliary data is not normally collected. Thereafter, the processor 140 may be configured to collect data from other reselected road sections to predict future traffic speeds. At this time, if there is collected data, the processor 140 may be configured to determine that the data is normally collected; if there is no collected data, the processor 140 may be configured to determine that the data is not normally collected.

[0087] In response to the situation that the past speed data, route guidance data and auxiliary data are normally collected, the processor 140 can be configured to configure the route guidance requirement table based on the route guidance data. Figure 4 To describe the path navigation requirements table.

[0088] Figure 2 The structure of an exemplary traffic speed prediction model is shown.

[0089] Reference Figure 2 , the attention model 141 can utilize past traffic speed data and path navigation data as input of the attention model.

[0090] The current traffic conditions and route navigation demand data are respectively input as a sequence, a key, and a value of the attention model 141. The attention model 141, which explores factors attributable to future outputs, can be applied to easily identify causality with future traffic speed.

[0091] The attention model 141 is a model that enables a deep learning model to focus on the most important vectors in a vector sequence, which may use a typical attention model.

[0092] The embedding layer 142 may embed auxiliary data such as weather, day of the week, time of day, and season information, and the result thereof may be input to the prediction model 143 .

[0093] The prediction model (prediction mode) 143 may be configured to predict future traffic speed data using the embedded auxiliary data of the embedding layer 142 and the output value of the attention model 141 .

[0094] The prediction model 143 may reflect existing traffic data (which reflects current traffic conditions) and route navigation demand data that is planned to arrive at a later point in time.

[0095] Figure 3 shows an example of a path navigation requirement table, Figure 4 A schematic diagram for describing an example of route navigation data is shown.

[0096] Reference Figure 3 , the route navigation demand table may include a three-dimensional structure, in which the horizontal axis represents the arrival time point, the vertical axis represents the request time point, and the height axis represents the road section. For example, the route navigation demand table has three-dimensional data (N×E×R), and the variables are the road section N, the arrival time point E, and the request time point R.

[0097] The arrival time point refers to the time point at which the vehicle arrives at the road section. The arrival time point can be divided into the time from 00:00 to 24:00 at intervals of 5 minutes, and can be displayed as an index at every 5-minute interval. For example, in the case of 00:50 to 00:55, the index can be 10. For example, in response to the user inputting a destination to navigate the path, a path to the destination is generated by connecting multiple link sections from the user's current location to the destination. In this case, the link section is referred to as a road section, which refers to the time point at which the vehicle arrives at each road section. For example, in the case of reaching the destination from the current location through the first link, the second link, the third link, and the fourth link, the time point at which the vehicle arrives at the first link, the time point at which the vehicle arrives at the second link, the time point at which the vehicle arrives at the third link, and the time point at which the vehicle arrives at the fourth link are respectively referred to as the arrival time points of each road section. In this case, as the number of vehicles arriving at each road section increases, the possibility of congestion may increase.

[0098] The request time point may refer to the time point at which the route navigation is requested, and the time from 00:00 to 24:00 may be divided into 5-minute intervals, and may be displayed as an index for each minute interval. For example, in the case of 00:15 to 00:20, the index may be 3.

[0099] The road segment may refer to a link road segment that is the minimum basic distance unit for collecting the average speed.

[0100] Reference Figure 4 , showing the request time point, road segment (linked road segments) and arrival time point in two dimensions.

[0101] The request time point and the link road segments may be displayed on the vertical side, and the request time point may be represented by 5 samples with indexes 0, 1, 2, 3 and 4, and each request time point uses 6 link road segments as an example.

[0102] The horizontal side shows the arrival time points, indexed from 2 to 21.

[0103] For example, it can be seen that when the request time point (current time point) is index 3, the arrival time point is index 10, and the link segment is "2190708", 5 vehicles are scheduled to arrive.

[0104] Figure 5 An example of using past traffic speeds to predict future traffic speeds is shown.

[0105] Reference Figure 5 , one hour of speed data can be collected every five minutes in the past, and one hour of speed data can be predicted starting from the current time point in units of five minutes in the future.

[0106] However, in Figure 5 In the case where only past speed data is used to predict future speed as shown, the long-distance prediction accuracy may be low.

[0107] Figure 6 A two-dimensional graph is shown for describing an exemplary relationship between traffic speed, traffic volume and traffic demand, Figure 7 An example graph expressing the relationship between traffic speed, traffic volume, and traffic demand in the form of a heat map is shown.

[0108] Reference Figure 6 , based on the current time point, the speed data of the road section collected by past data, the traffic volume from the current time point to the arrival time point, and the traffic speed at the arrival time point can be used to predict the future traffic speed. Figure 6 In the above, we can know the relationship between traffic speed, traffic volume and traffic demand within a single road segment. Considering the connectivity between links, the predictability of demand can be enhanced by expanding the link that will reach the corresponding point after the current time point into multiple links. Figure 7 Shown in the form of a heat map Figure 6 Schematic diagram of a two-dimensional curve graph.

[0109] Fig. 8A , Figure 8B , Figure 8C and Fig.8D An example graph showing traffic speed according to route demand is shown respectively. Fig. 8A , Figure 8B , Figure 8C and Fig.8D The actual speed variation according to the path demand is shown.

[0110] Fig. 8A and Figure 8B An example diagram showing a case where path demand is low.

[0111] The traffic speed trend of 216 road segments is shown, and it shows a situation where there is almost no need for route guidance. In this case, there is almost no need for route guidance, and there are few road segments with low traffic speeds due to low traffic volume.

[0112] on the other hand, Figure 8C and Fig.8D An example of a situation where path demand is high is shown.

[0113] It can be seen that at points 12 and 14, where the demand for path navigation is high on the 216 road segments, the traffic volume increases and the traffic speed decreases, which leads to congestion at points 11 and 13.

[0114] Through this method, it can be seen that at the sections and time points where route navigation is increased than usual, the actual traffic volume increases, resulting in lower traffic speeds and congestion.

[0115] In the following, reference will be made to Fig. 9 A traffic speed prediction method according to an exemplary embodiment of the present invention is described. Fig. 9 A flow chart showing an exemplary traffic speed prediction method is shown.

[0116] In the following, it is assumed Figure 1 The traffic speed prediction device 100 is configured to perform Fig. 9 In addition, Fig. 9 In the description of , the operation described as being performed by the device can be understood as being controlled by the processor 140 of the traffic speed prediction device 100. In the following exemplary embodiments of the present invention, the operations of step S101 to step S109 can be performed in sequence, but they do not have to be performed in sequence. For example, the order of each operation can be changed, and at least two operations can be performed in parallel.

[0117] Reference Fig. 9 , the traffic speed prediction device 100 can be configured to select N target road segments (S101). In this case, the number N can be determined in advance by experimental values, for example, it can be 216 or 1000. In this case, the selected N road segments can be configured as a target road network considering connectivity.

[0118] The traffic speed prediction device 100 may be configured to determine whether traffic data, route navigation data, and auxiliary data are collected ( S102 , S103 , S104 ).

[0119] The traffic speed prediction device 100 may be configured to reselect another road segment in response to a situation where at least one of the traffic data, the route navigation data, or the auxiliary data is not collected ( S108 ).

[0120] The traffic speed prediction device 100 may be configured to configure a route guidance requirement table in response to a situation in which traffic data, route guidance data, and auxiliary data are all normally collected from the selected N road sections ( S105 ).

[0121] The traffic speed prediction device 100 may be configured to input past traffic speed data and route navigation data into the attention model, and input the auxiliary data and output data of the attention model into the prediction model ( S106 ).

[0122] The traffic speed prediction device 100 may be configured to determine future traffic speed data through a prediction model and provide the future traffic speed data to the vehicle (S107). Thereafter, the traffic speed prediction device 100 provides the predicted future traffic speed data to the vehicle.

[0123] Therefore, according to an exemplary embodiment of the present invention, the traffic condition at the time point of arrival at the future road section may be estimated by requesting route navigation and estimating the number of vehicles on each road section of the traveling vehicles.

[0124] That is, the existing prediction model based on the past speed data collected so far can improve the prediction accuracy of the traffic speed prediction model by solving the problem that it is difficult to reflect the current and future traffic conditions.

[0125] Furthermore, according to an exemplary embodiment of the present invention, in response to a situation where the estimated traffic demand on a specific road is too large compared to usual, the reliability of route navigation and user satisfaction may be improved by reducing the traffic speed to guide it to take a detour.

[0126] Furthermore, the congestion level of a point of interest (POI) in each time zone can be estimated by estimating the future demand for the links around the POI, and user satisfaction can be improved by making recommendations based on user preferences (e.g., users who want to avoid congestion).

[0127] Fig.10 An exemplary computing system is shown.

[0128] Reference Fig.10The computing system 1000 includes at least one 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 via a bus 1200 .

[0129] The processor 1100 may be a central processing unit (CPU) or a semiconductor device configured to process commands stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) 1310 and a random access memory (RAM) 1320.

[0130] Accordingly, the steps of the methods or algorithms described in conjunction with the exemplary embodiments included herein may be implemented directly by hardware, software modules, or a combination of both executed by the processor 1100. The software modules may reside in a storage medium (i.e., memory 1300 and / or storage device 1600), such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, and an optical disk.

[0131] An exemplary storage medium is coupled to the processor 1100, and the processor 1100 can read information from the storage medium and write information to the storage medium. Alternatively, the storage medium can be integrated with the processor 1100. The processor and the storage medium can reside in an application specific integrated circuit (ASIC). The ASIC can reside in a user terminal. Alternatively, the processor and the storage medium can reside in a user terminal as separate components.

[0132] The above description merely illustrates the technical concept of the present invention, and those skilled in the art to which the present invention belongs may make various modifications and changes without departing from the basic features of the present invention.

[0133] In various exemplary embodiments of the present invention, the above-described operations may be performed by a control device, and the control device may be configured by a plurality of control devices or an integrated single control device.

[0134] In various exemplary embodiments of the present invention, the memory and the processor may be provided as one chip, or provided as separate chips.

[0135] In various exemplary embodiments of the present invention, the scope of the present invention includes software or machine-executable commands (e.g., operating systems, applications, firmware, programs, etc.) for enabling operations of methods according to various embodiments to be performed on a device or computer, and non-transitory computer-readable media including such software or commands stored thereon and executable on a device or computer.

[0136] In various exemplary embodiments of the present invention, the control device may be implemented in the form of hardware or software, or may be implemented in the form of a combination of hardware and software.

[0137] Furthermore, terms such as “unit”, “module” and the like included in the specification refer to a unit for processing at least one function or operation, which can be implemented by hardware, software or a combination thereof.

[0138] In an exemplary embodiment of the present invention, a vehicle may be referred to as being based on a concept including various vehicles. In some cases, a vehicle may be interpreted as being based on a concept that includes not only various land vehicles traveling on roads, such as cars, motorcycles, trucks, and buses, but also various vehicles such as airplanes, drones, ships, and the like.

[0139] For convenience of explanation and precise definition of the appended claims, the terms "upper", "lower", "inner", "outer", "above", "below", "upward", "downward", "front", "rear", "back", "inside", "outside", "inward", "outward", "interior", "exterior", "inner", "exterior", "forward" and "rearward" are used to describe the features of the exemplary embodiments with reference to the positions of such features as shown in the accompanying drawings. It will be further understood that the term "connect" or its derivatives refer to both direct and indirect connections.

[0140] The term "and / or" may include a combination of multiple related listed items or any one of the multiple related listed items. For example, "A and / or B" includes all three cases, for example, "A", "B" and "A and B".

[0141] In an exemplary embodiment of the present invention, "at least one of A and B" may refer to "at least one of A or B" or "at least one of a combination of at least one of A and B". In addition, "one or more of A and B" may refer to "one or more of A or B" or "one or more of a combination of one or more of A and B".

[0142] In this specification, unless otherwise specified, an expression in a singular form also includes an expression in a plural form unless the context clearly indicates otherwise.

[0143] In the exemplary embodiments of the present invention, it should be understood that terms such as "include" or "have" are intended to indicate that the features, values, steps, operations, elements, parts or a combination thereof described in the specification are present, and do not exclude the possibility of adding or existing one or more other features, values, steps, operations, elements, parts or a combination thereof.

[0144] According to the exemplary embodiments of the present invention, components may be combined with each other to be implemented as one, or some components may be omitted.

[0145] Hereinafter, a case where multiple pieces of hardware are operably coupled may include a case where direct and / or indirect connections are established between the multiple pieces of hardware via wired and / or wireless means.

[0146] The foregoing descriptions of specific exemplary embodiments of the present invention are presented for the purpose of illustration and description. They are not intended to be exhaustive or to limit the present invention to the precise form disclosed, and it is apparent that many modifications and changes may be made in light of the above teachings. The exemplary embodiments are selected and described in order to explain the specific principles of the present invention and their practical application, so that other persons skilled in the art can make and use various exemplary embodiments of the present invention and various alternatives and modifications thereof. The scope of the present invention is intended to be limited by the appended claims and their equivalents.

Claims

1. A traffic speed prediction device, comprising: a processor configured to: estimate a routing requirement based on current routing data for each road segment, and predict future traffic speeds using the routing requirement and past speed data for each road segment starting from a current time point; and A memory configured to store algorithms and data driven by the processor.

2. The traffic speed prediction device according to claim 1, wherein: The processor is further configured to generate a path navigation requirement table based on three-dimensional data, wherein the three-dimensional data includes road sections, a path navigation request time point for each road section, and an arrival time point for each road section.

3. The traffic speed prediction device according to claim 1, wherein: The processor is further configured to generate a route navigation requirement table based on the road segments, the route navigation request time points of each road segment and the arrival time points of each road segment, wherein the route navigation requirement table includes the number of vehicles scheduled to arrive at each arrival time point of each road segment.

4. The traffic speed prediction device according to claim 3, wherein: The processor is further configured to: Selecting road segments using the road's link segments; Divide 24 hours into a predetermined first time unit and assign an index to each route navigation request time point of each road segment; Divide 24 hours into a predetermined second time unit and assign an index to each arrival time point of each road segment; The route navigation demand table is generated by mapping the index of each route navigation request time point of each road segment with the number of vehicles scheduled to arrive at each index of each arrival time point of each road segment.

5. The traffic speed prediction device according to claim 3, wherein: The processor is further configured to determine that the future traffic speed will decrease as the number of vehicles scheduled to arrive at each arrival time point of each road segment increases.

6. The traffic speed prediction device according to claim 3, wherein: The processor is further configured to estimate the demand of each road segment according to the number of vehicles scheduled to arrive at each arrival time point of each road segment, and estimate the future traffic speed according to the demand.

7. The traffic speed prediction device according to claim 1, wherein: The processor is further configured to estimate the traffic speed of each road section according to the number of route guidance at each route guidance request time point of each road section.

8. The traffic speed prediction device according to claim 1, wherein: The processor is further configured to predict future traffic speed by further reflecting auxiliary data including at least one of weather, day of the week, time of day, season information, or a combination thereof.

9. The traffic speed prediction device according to claim 8, wherein: The processor comprises: an attention model, wherein past speed data and path navigation data are used as inputs of the attention model; an embedding layer for embedding auxiliary data; and A prediction model that uses the output of the attention model and the embedding layer to predict future traffic speeds.

10. The traffic speed prediction device according to claim 8, wherein: The processor is further configured to: selecting at least one road segment for data collection; determining whether past speed data, route navigation data, and auxiliary data are normally collected from the exploration vehicle in at least one selected road segment; In response to a situation where any one of the past speed data, the route guidance data, and the auxiliary data is not normally collected, another road section is reselected.

11. The traffic speed prediction device according to claim 10, wherein: The processor is further configured to: In response to a situation in which past speed data, route guidance data, and auxiliary data are normally collected, a route guidance requirement table is configured based on the route guidance data.

12. The traffic speed prediction device according to claim 1, further comprising: A communication device is operably connected to the processor, the communication device being configured to collect past speed data and path navigation data from the probe vehicle.

13. A traffic speed prediction method, comprising: collecting, by a processor, past speed data and path navigation data from the exploration vehicle for each road segment starting from a current time point; estimating, by a processor, a route navigation demand based on the route navigation data at a current point in time for each road segment; Future traffic speeds are predicted by a processor using route navigation requirements and past speed data for each road segment from the current point in time.

14. The traffic speed prediction method according to claim 13, wherein: Predictions of future traffic speeds include: A path navigation requirement table is generated by a processor based on three-dimensional data, wherein the three-dimensional data includes road sections, a path navigation request time point of each road section, and an arrival time point of each road section.

15. The traffic speed prediction method according to claim 13, wherein: Predictions of future traffic speeds include: A route navigation requirement table is generated by a processor based on the road segments, the route navigation request time points of each road segment and the arrival time points of each road segment, wherein the route navigation requirement table includes the number of vehicles scheduled to arrive at each arrival time point of each road segment.

16. The traffic speed prediction method according to claim 15, wherein: The generation of the path navigation requirement table includes: Selecting, by a processor, a road segment using linked road segments of the road; By means of a processor, 24 hours are divided into predetermined first time units, and an index is assigned to each time point of the route navigation request for each road segment; By means of a processor, 24 hours are divided into predetermined second time units, and an index is assigned to each arrival time point of each road segment; The processor maps the index of each path navigation request time point of each road segment to the number of vehicles scheduled to arrive at each index of each arrival time point of each road segment.

17. The traffic speed prediction method according to claim 16, wherein: Predictions of future traffic speeds include: By the processor, as the number of vehicles scheduled to arrive at each arrival time point of each road segment increases, it is determined that the future traffic speed will decrease.

18. The traffic speed prediction method according to claim 16, wherein: Predictions of future traffic speeds include: The processor estimates the demand of each road segment according to the number of vehicles scheduled to arrive at each arrival time point of each road segment, and estimates the future traffic speed according to the demand.

19. The traffic speed prediction method according to claim 13, wherein: Predictions of future traffic speeds include: Future traffic speeds are predicted, by the processor, by further reflecting auxiliary data including at least one of weather, day of the week, time of day, seasonal information, or a combination thereof.

20. The traffic speed prediction method according to claim 13, wherein: Predictions of future traffic speeds include: selecting, by a processor, at least one road segment for data collection; determining, by a processor, whether past speed data, route navigation data, and auxiliary data are normally collected from a survey vehicle in at least one selected road segment; By the processor, in response to a situation where any one of the past speed data, the route guidance data, and the auxiliary data is not normally collected, another road section is reselected.

Images