Apparatus and method for estimating traffic volume based on demand of route search

Abstract

The invention relates to an apparatus and a method for estimating traffic volume based on requirements of route search. An apparatus for estimating traffic volume based on a demand of a route search includes a processor and a storage medium configured to record one or more programs configured to be executable by the processor. The processor is configured to collect a plurality of route search data, generate route search demand data based on the collected plurality of route search data, correct the route search demand data based on an overcrowded road exceeding a marginal traffic volume, and transmit the corrected route search demand data to the controller. And estimating an actual traffic volume for each road by applying the corrected route search demand data to the pre-trained learning model.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the priority of Korean Patent Application No. 10-2023-0153368 filed in the Korean Intellectual Property Office on November 8, 2023, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] The invention relates to a device and method for estimating traffic volume based on route search requirements. Background Art

[0004] Due to the rapid increase in vehicle penetration in society, the number of vehicles has increased exponentially. In contrast, the number of roads is far from this. Accordingly, since the traffic volume on the roads may increase, it is necessary to accurately estimate the traffic volume on the roads in order to calculate the estimated time of arrival (ETA).

[0005] To estimate the volume of traffic on a road, route search data retrieved from multiple vehicles (e.g., a road ID of a road and a predicted time to enter the road) may be utilized. However, the route search data may show an overestimated volume of traffic compared to the actual volume of traffic. For example, a road may have a marginal volume of traffic allowed (i.e., a maximum number of vehicles). When the collected route search data is utilized, the collected route search data may show that there are more vehicles traveling on a particular road than the marginal volume of traffic, resulting in an overestimation of the volume of traffic.

[0006] In other cases, the route search data may show an underestimated traffic volume compared to the actual traffic volume. For example, the traffic volume may be underestimated when the vehicle is traveling without a route search, when the vehicle traveling using a route search leaves a road included in the route, or when a new vehicle enters the road after the time point when the traffic volume is estimated.

[0007] Accordingly, when estimating traffic volume using route search data, it may be necessary to accurately estimate actual traffic volume by reflecting overestimation and underestimation. Summary of the invention

[0008] One aspect of the present invention provides an apparatus and method for estimating traffic volume based on route search requirements, which can accurately estimate the actual traffic volume of each road, thereby improving the reliability of route search and user satisfaction.

[0009] According to one aspect of the present invention, there is provided an apparatus for estimating traffic volume based on route search demand, the apparatus comprising a processor and a storage medium, the storage medium being configured to record one or more programs, the one or more programs being configured to be executable by the processor. The processor may be configured to: collect a plurality of route search data, generate route search demand data based on the collected plurality of route search data, correct the route search demand data based on overcrowded roads exceeding marginal traffic volume, and estimate the actual traffic volume of each road by applying the corrected route search demand data to a pre-trained learning model.

[0010] According to another aspect of the present invention, a method for estimating traffic volume based on route search demand is provided, the method comprising: collecting a plurality of route search data, generating route search demand data based on the collected plurality of route search data, correcting the route search demand data based on overcrowded roads exceeding marginal traffic volume, and estimating the actual traffic volume of each road by applying the corrected route search demand data to a pre-trained learning model.

[0011] According to another aspect of the present invention, there is provided a computer-readable storage medium storing a program for executing the method on a computer.

[0012] According to an exemplary embodiment of the present invention, the route search demand data can be corrected based on the marginal traffic volume, and then the corrected route search demand data can be applied to the pre-trained learning model to accurately estimate the actual traffic volume of each road. As a result, the quality of navigation instructions can be improved.

[0013] Specifically, when a specific road is expected to be congested due to increased traffic volume, such as during holidays, the estimated actual traffic volume can be used to guide a detour route for the specific congested road, thereby improving the reliability of route search and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other aspects, features and advantages of the present invention will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0015] Figure 1 is a schematic diagram showing a traffic volume estimation device based on route search requirements according to an exemplary embodiment of the present invention;

[0016] Figure 2A , Figure 2B and Figure 2C is a schematic diagram showing a relationship between a traffic volume estimated based on route search data and an actual traffic volume according to an exemplary embodiment of the present invention;

[0017] Figure 3 is a schematic diagram showing a connection relationship between roads according to a driving direction according to an exemplary embodiment of the present invention;

[0018] Figure 4A , Figure 4B , Figure 4C , Figure 4D , Figure 4E , Figure 4F and Figure 4G is an exemplary schematic diagram illustrating a calculation process of correcting route search demand data at a specific time point (t=0) according to an exemplary embodiment of the present invention;

[0019] Figure 5 is a schematic diagram illustrating a learning model according to an exemplary embodiment of the present invention;

[0020] Figure 6 is a flow chart showing a traffic volume estimation method based on route search requirements according to an exemplary embodiment of the present invention;

[0021] Figure 7 It specifically shows Figure 6 Flowchart of the steps.

[0022] Figure 8 is a block diagram showing a computing device that can fully or partially implement a traffic volume estimation device based on route search requirements according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0023] Hereinafter, specific exemplary embodiments of the present invention will be described with reference to the accompanying drawings. The following detailed description is provided to help fully understand the methods, devices and / or systems described in this specification. However, the detailed description is only for illustrative purposes, and the present invention is not limited thereto.

[0024] When describing the exemplary embodiments of the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the main idea of ​​the present invention, the detailed description thereof will be omitted. In addition, the terms to be described later are terms defined in view of the functions in the present invention, and can be changed according to the intention or habit of the user or operator. Therefore, the definition of these terms should be based on the content of the entire present specification. The terms used herein are only for the purpose of describing a specific exemplary embodiment and are not intended to limit the exemplary embodiment. As used herein, the singular forms "one", "one" and "said" are intended to also include plural forms, unless the context clearly indicates otherwise. As used herein, the term "and / or" includes any one and any combination of any two or more related enumerated items. It will also be understood that when the terms "including" and / or "including" are used in this specification, it is indicated that the features, values, steps, operations, elements, components or combinations thereof exist, but it is not excluded that one or more other features, values, steps, operations, elements, components and / or groups thereof exist or are added.

[0025] Figure 1 1 is a schematic diagram showing a traffic volume estimation device based on route search requirements according to an exemplary embodiment of the present invention. The traffic volume estimation device based on route search requirements 100 may include a data collection unit 110 , a control unit 120 , and a storage unit 130 .

[0026] The traffic volume estimation device 100 based on route search demand may include a processor (e.g., a computer, a microprocessor, a CPU, an ASIC, a logic circuit, etc.) and a memory, the memory storing software instructions, which, when executed by the processor, provide the functions of the control unit 120. Here, the processor and the memory may be implemented as separate semiconductor circuits. Alternatively, the processor and the memory may be implemented as a single integrated semiconductor circuit. The number of processors may be one or more.

[0027] First, the data collection unit 110 may collect a plurality of route search data (route search data 1 to route search data N). The collected plurality of route search data may be sent to the control unit 120. Here, each of the plurality of route search data may include: a road ID of each road included in the route searched by the vehicle and a predicted entry time of each road.

[0028] Subsequently, the control unit 120 may generate route search demand data based on the collected plurality of route search data, and may correct the route search demand data based on an overcrowded road exceeding a marginal traffic volume. Here, the route search demand data may represent the traffic volume of each road estimated based on a road ID and a predicted entry time, and the traffic volume may represent the number of vehicles. That is, the route search demand data may be estimated as the traffic volume on a road with a specific road ID at a predicted entry time. In addition, the marginal traffic volume may be represented as the maximum number of vehicles set for each road, and an overcrowded road may be a road on which the estimated traffic volume exceeds the marginal traffic volume.

[0029] In order to correct the route search demand data, the control unit 120 can disperse the excess demand traffic exceeding the marginal traffic volume to the upstream road connected to the overcrowded road for the overcrowded road. Here, the upstream road can be a road connected to the overcrowded road in the opposite direction of the driving direction.

[0030] Specifically, the control unit 120 can repeatedly calculate the process of dispersing excess demand traffic to upstream roads according to a preset percentage, and when the sum of the excess demand traffic of each road after the dispersion is less than or equal to a specific percentage of the sum of the marginal traffic of each road, the control unit 120 can end the process.

[0031] Figure 2A , Figure 2B and Figure 2C is a schematic diagram illustrating a relationship between a traffic volume estimated based on route search data and an actual traffic volume according to an exemplary embodiment of the present invention. Figure 2A The vehicle speed over time for each road ID is shown. Darker colors may represent slower vehicle speeds. Figure 2B The estimated traffic volume for each road ID over time is shown. Darker colors may represent larger estimated traffic volumes. Figure 2C A bottleneck phenomenon occurring on a second road entering the first road due to heavy traffic on the first road is shown.

[0032] That is to say, Figure 2A and Figure 2B As shown, it can be seen that as the traffic volume estimated based on the route search data increases, the vehicle speed decreases accordingly. As a result, it can be seen that the traffic volume estimated based on the route search data and the actual traffic volume show similar flow rates.

[0033] In addition, if Figure 2CAs shown, when the traffic volume on the first road 301 increases, the vehicle speed on the second road 302 may decrease after a certain period of time, thereby causing a bottleneck phenomenon. That is, in the case of roads with a specific connection relationship, when the traffic volume on one road 301 exceeds the marginal traffic volume, the traffic volume may be dispersed to another road 302 connected to the road 301 after a certain time point.

[0034] Accordingly, according to the present invention, the traffic volume of each road can be estimated based on the route search data. In the case of an overcrowded road (on which the estimated traffic volume exceeds the marginal traffic volume), the excess demand traffic volume can be dispersed to upstream roads to correct the route search demand data.

[0035] Hereinafter, an exemplary embodiment of correcting route search demand data based on a connection relationship between roads, route search demand data, and marginal traffic volume will be described.

[0036] first, Figure 3 2 is a schematic diagram showing a connection relationship between roads according to a driving direction according to an exemplary embodiment of the present invention. Both rows and columns may represent road IDs.

[0037] like Figure 3 As shown, it is assumed that the road includes Road 1 to Road 6 in the driving direction. Road 1 can be connected to Road 3 and Road 4, Road 2 can be connected to Road 3 and Road 4, Road 4 can be connected to Road 5, Road 6 can be connected to Road 5, and the connection relationship (A) between the roads can be represented by the following matrix. In the following matrix, rows and columns can represent road IDs. In addition, the term upstream or downstream is based on the driving direction. For example, Road 1 can be an upstream road of Road 3 and Road 4, and conversely, Road 3 and Road 4 can be downstream roads of Road 1.

[0038]

[0039] According to an exemplary embodiment of the present invention, the route search demand data and the marginal traffic volume may be represented by a matrix.

[0040] Specifically, the route search demand data D may be represented by the following matrix. The rows may represent road IDs, namely, roads 1 to 6, and the columns may represent a plurality of specific time points, namely, time point 1 to time point 6 with a predetermined time interval. That is, the route search demand data D may represent the traffic volume of each road estimated based on the road ID and the predicted entry time. For example, the traffic volume of road 1 at time point 1 may be 142, and the traffic volume of road 6 at time point 2 may be 199.

[0041]

[0042] In addition, the marginal traffic volume (F max ) can be represented by the following matrix. The rows can represent road IDs, i.e., road 1 to road 6. For example, the marginal traffic volume (F max ) can be 200, and the marginal traffic volume of road 4 can be 190.

[0043]

[0044] Table 1 below shows equations for correcting route search requirement data.

[0045] Table 1

[0046]

[0047] In Equation 1, D over,t It can be a matrix representing the excess demand traffic volume of each road at a specific time point t, D t can be a matrix representing the estimated traffic volume of each road at a specific time point t, and F max It can be a matrix representing the marginal traffic volume of each road.

[0048] In equation 2, D over Can be a matrix list D of all time points (0 to T) over,t .

[0049] In Equation 3, U over It can be D over The identity matrix of .

[0050] In Equation 4, P prop,t can be a matrix representing the dispersion percentage at a specific time point t, α can be the dispersion percentage (constant), U over,t can be the identity matrix representing the excess demand traffic volume of each road at a specific time point t, and diag() can be the matrix that converts U over,t A function that becomes a diagonal matrix, I may be a unit matrix, and A may be a matrix representing the connection relationship between roads according to the driving direction.

[0051] In equation 5, It can be a matrix that represents the dispersion of excess demand traffic volume for each road at a specific time point t.

[0052] In equation 6, Can be a matrix list of all time points

[0053] In Equation 7, R tcan be a matrix representing the excess demand traffic volume of each road at a specific time point t, and D t is the estimated traffic volume of each road at a specific time point t.

[0054] In Equation 8, R can be a matrix list R for all time points t .

[0055] In equation 9, It can be a matrix representing the excess demand of each road at a specific time point t after performing n times of dispersion.

[0056] In equation 10, It can be a matrix representing the excess demand traffic after performing n times of dispersion.

[0057] In Equation 11, D (n) can represent the route search demand data after performing n scatters, and It can represent the increase or decrease in traffic volume on each road at a specific time point t after performing n times of dispersion.

[0058] FIG. 4A to FIG. 4G is an exemplary diagram illustrating a calculation process for correcting route search demand data at a specific time point (t=0) according to an exemplary embodiment of the present invention.

[0059] In the following, in order to facilitate the understanding of the present invention, reference will be made to Figure 1 , Figure 3 , FIG. 4A to FIG. 4G , Table 1 and the above matrix (D, F max A) and B) describe the calculation process of correcting the route search demand data D at a specific time point (t=0) as an example. In Table 1, it can be assumed that α is 0.8.

[0060] First, if Figure 4A and Figure 4B (See Equation 1 and Equation 3 in Table 1) as shown in over,0 and U over,0 Here, as mentioned above, D over,0 can be a matrix representing the excess demand traffic volume of each road at a specific time point t = 0, and U over,0 It can be D over,0 Accordingly, it can be seen that at a specific time point t=0, the excess demand traffic volume on road 2 is 56, and the excess demand traffic volume on road 4 is 97.

[0061] Then, if Figure 4C and Figure 4D(See Equation 4 and Equation 5 in Table 1) as shown in prop,0 and As mentioned above, P prop,0 can be a matrix representing the percentage of dispersion at a specific time point t=0, and It can be a matrix that represents the dispersion of excess demand traffic volume for each road at a specific time point t=0.

[0062] Accordingly, after performing the scatter, Figure 4E As shown, it can be seen that the excess demand traffic volume (97) on Road 4 is reduced from 97 to 77.6 (=97*0.8), and a dispersion of 19.4 (=97*0.2) is performed on Road 1 and Road 2. In addition, it can be seen that the excess demand traffic volume (56) on Road 2 is reduced to 28.36.

[0063] Afterwards, if Figure 4F (See Equation 7 and Equation 9 in Table 1) as shown in FIG. 0 and Here, as mentioned above, R 0 can be a matrix representing the excess demand traffic for each road, and It can be a matrix representing the excess demand traffic volume of each road after a dispersion is performed.

[0064] Accordingly, after performing the dispersion, Road 1 may have an excess demand traffic volume of 38.6, Road 3 may have an excess demand traffic volume of 79, and Road 6 may have an excess demand traffic volume of 39.

[0065] Afterwards, if Figure 4G (See equation 10 in Table 1) as shown in here, The excess demand traffic volume at a specific time point t=0 after performing one dispersion may be represented. That is, Road 4 may have an excess demand traffic volume reduced to 77.6, and Road 1 may have an excess demand traffic volume reduced to 28.36.

[0066] In this case, the control unit 120 can obtain the sum of the excess demand traffic volumes of each road after the dispersion is performed (77.6+28.38=105.98), and can determine whether the obtained sum is less than or equal to a specific percentage (e.g., 10%) of the sum of the marginal traffic volumes of each road (200+300+250+230+190+240=1410), and when the obtained sum is less than or equal to the specific percentage (e.g., 10%) of the sum of the marginal traffic volumes of each road (200+300+250+230+190+240=1410), the control unit 120 can end the above process. However, when the obtained sum exceeds a specific percentage (e.g., 10%) of the sum of the marginal traffic volumes of each road (200+300+250+230+190+240=1410), the above process can be repeatedly performed.

[0067] Finally, according to Equation 11 in Table 1 (see Equation 11 in Table 1), the control unit 120 can obtain the corrected route search demand data D after performing one dispersion. (1) That is, the route search demand data D corrected after performing one dispersion can be obtained by increasing the traffic volume D. (1) , that is, when executing a dispersion, the initial route search demand data D (0) Increase or decrease

[0068] Thereafter, the control unit 120 may estimate the actual traffic volume of each road by applying the corrected route search demand data to the pre-trained learning model.

[0069] The above-mentioned learning model may include a generative adversarial network (GAN), which includes a generator and a discriminator.

[0070] Figure 5 is a schematic diagram illustrating a learning model according to an exemplary embodiment of the present invention.

[0071] like Figure 5 As shown, during training 510, the control unit 120 may train the discriminator 502 using the estimated traffic volume data F′ and the actual traffic volume data F. That is, the estimated traffic volume data F′ may also be trained to be false (0), while the actual traffic volume data F may be trained to be true (1). Thereafter, the generator 501 may be trained in a direction to deceive the trained discriminator 502. Here, the estimated traffic volume data F′ may be the route search demand data D′ obtained by the generator 501 based on the corrected route search demand data D′. (n)The number of vehicles on each road is generated, and the actual traffic volume data F may be the actual number of vehicles on each road.

[0072] Thereafter, during estimation 520, the generator 501 may receive the corrected route search demand data D (n) And generate actual traffic volume data F.

[0073] In the present invention, a generative adversarial network may be exemplified as a learning model, but it should be noted that the present invention is not limited thereto.

[0074] Finally, the storage unit 130 may store various programs and data to implement the functions performed by the above-mentioned control unit 120. In addition, the above-mentioned data may include route search data, route search demand data, marginal traffic volume, corrected route search demand data, and the like.

[0075] As described above, according to an exemplary embodiment of the present invention, the route search demand data can be corrected based on the marginal traffic volume, and then the corrected route search demand data can be applied to the pre-trained learning model to accurately estimate the actual traffic volume of each road. As a result, the quality of navigation instructions can be improved.

[0076] Specifically, when a specific road is expected to be congested due to increased traffic volume, such as during holidays, it can be used to guide a detour route for the specific congested road, thereby improving the reliability of route search and user satisfaction.

[0077] Figure 6 is a flowchart illustrating a traffic volume estimation method based on a route search requirement according to an exemplary embodiment of the present invention. Figure 7 It specifically shows Figure 6 Flow chart of step S630.

[0078] In the following, reference will be made to Figures 1 to 7 The traffic volume estimation method (S600) based on route search requirements according to an exemplary embodiment of the present invention is described in detail. However, in order to simplify the present invention, the following description will be omitted. Figures 1 to 5 Duplicate description.

[0079] refer to Figures 1 to 7 , the traffic volume estimation method (S600) based on the route search demand according to the exemplary embodiment of the present invention may start from the step (S610) of collecting a plurality of route search data (route search data 1 to route search data N). Here, as described above, each of the plurality of route search data may include: a road ID of each road included in the route searched by the vehicle and a predicted entry time of each road.

[0080] Subsequently, the traffic volume estimation device 100 may generate route search demand data based on the collected plurality of route search data (S620). As described above, the route search demand data may represent the traffic volume of each road estimated based on the road ID and the predicted entry time, and the traffic volume may be the number of vehicles.

[0081] Subsequently, the traffic volume estimation device 100 can correct the route search demand data based on the overcrowded roads exceeding the marginal traffic volume (S630). As described above, the above-mentioned marginal traffic volume can be represented by the maximum number of vehicles set for each road, and the overcrowded road can be a road where the estimated traffic volume exceeds the marginal traffic volume.

[0082] That is to say, Figure 7 As shown, the traffic volume estimation device 100 can disperse the excess demand traffic volume exceeding the marginal traffic volume to the upstream road connected to the overcrowded road (S701). Here, as described above, the upstream road can be a road connected to the overcrowded road in the opposite direction of the driving direction.

[0083] Thereafter, the traffic volume estimation device 100 may determine the excess demand traffic volume of the corresponding road. The sum of Is it less than or equal to the marginal traffic volume F of the corresponding road? max The sum of ∑F max As a result of the determination, when Less than or equal to ∑F max When a certain percentage (e.g., 10%) of the traffic volume estimation device 100 is reached, the traffic volume estimation device 100 may end the process. When the specific percentage is exceeded, steps S701 and S702 may be repeatedly performed.

[0084] Finally, the traffic volume estimation apparatus 100 may estimate the actual traffic volume of each road by applying the corrected route search demand data to the pre-trained learning model ( S640 ).

[0085] Specifically, as described above, the above-mentioned learning model may include a generative adversarial network (GAN), which includes a generator and a discriminator, and the discriminator may be trained using estimated traffic volume data and actual traffic volume data, and then the generator may be trained in the direction of deceiving the trained discriminator.

[0086] As described above, according to an exemplary embodiment of the present invention, the route search demand data can be corrected based on the marginal traffic volume, and then the corrected route search demand data can be applied to the pre-trained learning model to accurately estimate the actual traffic volume of each road. As a result, the quality of navigation instructions can be improved.

[0087] Specifically, when a specific road is expected to be congested due to increased traffic volume, such as during holidays, it can be used to guide a detour route for the specific congested road, thereby improving the reliability of route search and user satisfaction.

[0088] Figure 8 is a block diagram showing a computing device 800 that can fully or partially implement the traffic volume estimation device 100 based on route search requirements according to an exemplary embodiment of the present invention.

[0089] like Figure 8 As shown, computing device 800 may include at least one processor 801 , a computer-readable storage medium 802 , and a communication bus 803 .

[0090] The processor 801 may cause the computing device 800 to operate according to the exemplary embodiments described above. For example, the processor 801 may execute one or more programs stored in the computer-readable storage medium 802. The one or more programs may include one or more computer-executable instructions, and when the one or more computer-executable instructions are executed by the processor 801, the one or more computer-executable instructions may be configured to cause the computing device 800 to perform steps according to the exemplary embodiments.

[0091] The computer-readable storage medium 802 may be configured to store computer-executable instructions or program codes, program data, and / or other suitable forms of information. The program 802a stored in the computer-readable storage medium 802 may include a set of instructions that may be executed by the processor 801. In an exemplary embodiment, the computer-readable storage medium 802 may be a memory (volatile memory such as random access memory, non-volatile memory, or any suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, other types of storage media that may be accessed by the computing device 800 and capable of storing desired information, or any suitable combination thereof.

[0092] The communication bus 803 may interconnect various other components of the computing device 800 , including the processor 801 and the computer-readable storage medium 802 .

[0093] The computing device 800 may also include one or more input / output interfaces 805 and one or more network communication interfaces 806, the one or more input / output interfaces 805 providing an interface for one or more input / output devices 804. The input / output interface 805 and the network communication interface 806 may be connected to the communication bus 803. The network may be one of cellular networks, such as Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Time Division-CDMA (TD-CDMA), Universal Mobile Telecommunications System (UMTS) or Long-Term Evolution (LTE), or other cellular networks.

[0094] The input / output device 804 may be connected to other components of the computing device 800 through the input / output interface 805. Exemplary input / output devices 804 may include a pointing device (such as a mouse or a touchpad), a keyboard, a touch input device (such as a touchpad or a touch screen), a voice or sound input device, an input device such as various types of sensor devices and / or a photographic device, and / or an output device such as a display device, a printer, a speaker, and / or a network card. Exemplary input / output devices 804 may be included in the computing device 800 as a component included in the computing device 800, or may be connected to the computing device 800 as a device distinct from the computing device 800.

[0095] The exemplary embodiments of the present invention may include a program for executing the method described herein on a computer, and a computer-readable recording medium including the program. The computer-readable recording medium may include local data files, local data structures, etc., either individually or in combination with program instructions. The medium may be those specifically designed and constructed for the purpose of the exemplary embodiments, or may be a known type, and is available to the technician in the field of computer software. The example of a computer-readable medium includes magnetic media such as hard disks, floppy disks and tapes, optical media such as CD ROMs and DVDs, magneto-optical media such as optical disks, and hardware devices (such as read-only memory (ROM), random access memory (RAM), flash memory, etc.) that are specifically configured to store and execute program instructions. The example of a program may include machine code (such as code generated by a compiler) and higher-level code (which can be executed by a computer utilizing an interpreter).

[0096] While exemplary embodiments have been shown and described above, it will be apparent to those skilled in the art that modifications and variations may be made without departing from the scope of the invention as defined by the appended claims.

Claims

1. A device for estimating traffic volume based on route search requirements, the device comprising: processor; and a storage medium configured to record one or more programs, wherein the one or more programs are configured to be executable by the processor; Wherein, the processor is configured as follows: Collect multiple route search data; generating route search demand data based on the collected plurality of route search data; Correcting route search demand data based on overcrowded roads exceeding marginal traffic volumes; The actual traffic volumes of multiple roads are estimated by applying the corrected route search demand data to the pre-trained learning model.

2. The device for estimating traffic volume based on route search requirements according to claim 1, wherein: Each of the plurality of route search data includes: a road ID of each of a plurality of roads included in a route searched by the vehicle and a predicted entry time of each of the plurality of roads; The route search demand data includes a traffic volume of each of a plurality of roads estimated based on a road ID and a predicted entry time, the traffic volume indicating the number of vehicles; The marginal traffic volume is a maximum number of vehicles set for each of a plurality of roads.

3. The device for estimating traffic volume based on route search requirements according to claim 2, wherein: The processor is configured to disperse, for an overcongested road, excess demand traffic exceeding a marginal traffic volume to an upstream road connected to the overcongested road, the upstream road being a road connected to the overcongested road in a direction opposite to the driving direction.

4. The device for estimating traffic volume based on route search requirements according to claim 3, wherein: The processor is configured as follows: The process of repeatedly calculating the distribution of excess demand traffic to upstream roads according to a preset percentage; When the sum of the excess demand traffic volumes of the various roads after the dispersion is less than or equal to a specific percentage of the sum of the marginal traffic volumes of the various roads, the process of dispersing the excess demand traffic volume to the upstream roads is terminated.

5. The device for estimating traffic volume based on route search requirements according to claim 3, wherein: The route search demand data and marginal traffic volume are represented by a matrix.

6. The device for estimating traffic volume based on route search requirements according to claim 3, wherein: The processor is configured to perform scattering according to the following equation: in, is a matrix representing the dispersion of excess demand traffic volume on each road at a specific time point t, P prop,t is a matrix representing the percentage of dispersion at a specific time point t, and D over,t It is a matrix representing the excess demand traffic volume of each road at a specific time point t.

7. The device for estimating traffic volume based on route search requirements according to claim 6, wherein: P is obtained by the following equation prop,t : P prop,t =α*diag(U over,t )*I+(1-α)*A, Among them, α is a constant, U over,t is the identity matrix representing the excess traffic demand of each road at a specific time point t, and diag() is the matrix that converts U over,t A function that becomes a diagonal matrix, I is the identity matrix, and A is a matrix representing the connection relationship between roads according to the driving direction.

8. The device for estimating traffic volume based on route search requirements according to claim 6, wherein: The plurality of specific time points have a predetermined time interval.

9. The device for estimating traffic volume based on route search requirements according to claim 1, wherein: The learning model includes a generative adversarial network, which includes a generator and a discriminator.

10. The device for estimating traffic volume based on route search requirements according to claim 9, wherein: The processor is configured to train a discriminator using estimated traffic volume data and actual traffic volume data, and then train a generator in a direction to deceive the trained discriminator, wherein the estimated traffic volume data is generated by the generator based on the corrected route search demand data.

11. A method for estimating traffic volume based on route search requirements, the method comprising: collecting, by a processor, a plurality of route search data; generating route search demand data based on the collected plurality of route search data; Correcting route search demand data based on overcrowded roads exceeding marginal traffic volumes; The actual traffic volumes of multiple roads are estimated by applying the corrected route search demand data to the pre-trained learning model.

12. The method for estimating traffic volume based on route search requirements according to claim 11, wherein: Each of the plurality of route search data includes: a road ID of each of a plurality of roads included in a route searched by the vehicle and a predicted entry time of each of the plurality of roads; The route search demand data includes a traffic volume of each of a plurality of roads estimated based on a road ID and a predicted entry time, the traffic volume indicating the number of vehicles; The marginal traffic volume is a maximum number of vehicles set for each of a plurality of roads.

13. The method for estimating traffic volume based on route search demand according to claim 12, wherein: The correction includes: for the overcongested road, dispersing the excess demand traffic volume exceeding the marginal traffic volume to an upstream road connected to the overcongested road, wherein the upstream road is a road connected to the overcongested road in the opposite direction of the traveling direction.

14. The method for estimating traffic volume based on route search demand according to claim 13, wherein: The correction further includes: The process of repeatedly calculating the distribution of excess demand traffic to upstream roads according to a preset percentage; When the sum of the excess demand traffic volumes of the various roads after the dispersion is less than or equal to a specific percentage of the sum of the marginal traffic volumes of the various roads, the process of dispersing the excess demand traffic volume to the upstream roads is terminated.

15. The method for estimating traffic volume based on route search demand according to claim 13, wherein: The route search demand data and marginal traffic volume are represented by a matrix.

16. The method for estimating traffic volume based on route search demand according to claim 13, wherein: Scattering involves performing a scatter according to the following equation: in, is a matrix representing the dispersion of excess demand traffic at a specific time point t, P prop,t is a matrix representing the percentage of dispersion at a specific time point t, and D over,t is a matrix representing the excess demand traffic at a specific time point t.

17. The method for estimating traffic volume based on route search demand according to claim 16, wherein: P is obtained according to the following equation prop,t : P prop,t =α*diag(U iver,t )*I+(1-α)*A, Among them, α is a constant, U over,t is the identity matrix representing the excess demand traffic at a specific time point t, and diag() is the matrix that converts U over,t A function that becomes a diagonal matrix, I is the identity matrix, and A is a matrix representing the connection relationship between roads according to the driving direction.

18. The method for estimating traffic volume based on route search requirements according to claim 16, wherein: The plurality of specific time points have a predetermined time interval.

19. The method for estimating traffic volume based on route search demand according to claim 11, wherein: The learning model includes a generative adversarial network, which includes a generator and a discriminator.

20. The method for estimating traffic volume based on route search demand according to claim 19, further comprising: The discriminator is trained using estimated traffic volume data and actual traffic volume data, and then the generator is trained in a direction to deceive the trained discriminator, wherein the estimated traffic volume data is generated by the generator based on the corrected route search demand data.

Images