Information processing apparatus

Abstract

The purpose of the present disclosure is to predict congestion more accurately than in the prior art. The information processing device predicts traffic demands for a plurality of destinations, and predicts the number of vehicles each day for each departure point on the basis of past route information. Then, the information processing device determines the time at which a congestion occurs in the first section, on the basis of the number of vehicles that have been distinguished by time periods and that have passed through the first section, calculated on the basis of the route information, and estimates the travel time in the target section.

Description

Technical Field

[0001] This disclosure relates to an information processing apparatus for predicting congestion. Background Technology

[0002] There is a technique for predicting road congestion. Relatedly, for example, Patent Document 1 discloses a congestion prediction model creation apparatus that selects population data from a group that contributes relatively highly to congestion data at the predicted congestion location, and constructs a congestion prediction model based on the selected population data and the congestion data at the predicted congestion location through regression analysis.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2019-066930 Summary of the Invention

[0006] It is believed that with the development of machine learning, models for predicting congestion will evolve in the future. The purpose of this disclosure is to predict congestion with higher accuracy than ever before.

[0007] One aspect of this disclosure is an information processing apparatus comprising a control unit that performs the following actions: estimating a traffic flow rate, wherein the traffic flow rate is the number of vehicles passing through a first location per unit time; estimating traffic volume based on vehicle density, wherein the vehicle density is the density of vehicles within a first interval, which is a range from a specified location to the first location, the vehicle density being calculated based on travel information relating to the travel of multiple vehicles traveling within the first interval, and the traffic volume being the number of vehicles present in the first interval at a specified time point; and estimating the travel time of the first interval based on the traffic flow rate and the traffic volume, wherein the control unit further performs the following actions: for each of a plurality of destinations included in origin-end point (OD) information, estimating a first number of vehicles based on first information, wherein the OD information is past route information of multiple vehicles, and the first number of vehicles is a predicted number of vehicles traveling to that destination on a given day; and, based on the OD information, calculating a first ratio for each of the plurality of destinations, wherein the first ratio is the ratio of each origin to the first number of vehicles traveling to each destination. The method involves: multiplying the first number of vehicles calculated for each destination by the first ratio calculated for each departure point to calculate a second number of vehicles per OD pair, where the OD pair is a pair of departure and destination points, and the second number is the predicted number of vehicles arriving at the destination from the departure point on a given day; multiplying the second number of vehicles calculated for each OD pair by the ratio of vehicles passing through the first interval obtained based on the OD information to calculate a third number of vehicles per OD pair, where the third number is the predicted number of vehicles passing through the first interval; calculating a fourth number of vehicles per OD pair based on the third number of vehicles calculated for each OD pair and information related to the time period of passage through the first interval obtained based on the OD information, where the fourth number is the predicted number of vehicles passing through the first interval in a specific time period; determining a first moment based on the fourth number of vehicles calculated for each OD pair, where the first moment is the moment when the number of vehicles passing through the first interval exceeds a predetermined threshold; and using the time period including the first moment as the congestion occurrence time period, applying the traffic flow rate in the congestion flow to the first interval to estimate the travel time within the first interval.

[0008] In addition, as another option, a program for causing a computer to execute the information processing method executed by the aforementioned information processing apparatus, or a computer-readable storage medium that non-temporarily stores the program, can be provided.

[0009] Invention Effects

[0010] According to this disclosure, congestion can be predicted with higher accuracy than ever before. Attached Figure Description

[0011] Figure 1 This is a diagram showing an outline of the processes performed by the server device in the implementation method.

[0012] Figure 2 This diagram illustrates the constituent elements of the server device according to the embodiment.

[0013] Figure 3 This is a flowchart of the processes performed by the control unit of the server device in the embodiment.

[0014] Explanation of reference numerals in the attached figures

[0015] 100: Server device; 110: Control unit; 111: First prediction unit; 112: Second prediction unit; 113: Third prediction unit; 114: Fourth prediction unit; 115: Time determination unit; 116: Estimation unit; 120: Storage unit; 130: Communication unit. Detailed Implementation

[0016] (summary)

[0017] There is a technology for predicting road congestion.

[0018] For example, as existing technology, there are known information processing devices for predicting congestion. These devices acquire population data from the vicinity of the departure point and select population data that contributes relatively highly to the congestion data at the predicted congestion location. Then, the devices perform regression analysis based on the selected population data and the congestion data at the predicted congestion location, thereby constructing a congestion prediction model.

[0019] Thus, in the aforementioned prior art, a congestion prediction model is constructed based on population data around the departure point, thereby predicting congestion based on the population dynamics around the departure point. However, this method cannot accurately predict potential congestion if the population dynamics around the departure point do not change. Here, the situation where the population dynamics around the departure point do not change is considered as situations where vehicles depart from the residences of vehicle users, etc., where there is no prior population inflow to the departure point.

[0020] However, when users are traveling to their destination, the outbound journey usually starts from the user's residence, so accurate congestion prediction is also required in such cases.

[0021] Therefore, in order to accurately predict congestion for outbound journeys as well, it is preferable that the information processing device predicts congestion not based on population dynamics at the departure point, which does not contribute to the prediction of outbound congestion, but rather based, for example, on traffic demand at the vehicle's destination.

[0022] One information processing apparatus of this disclosure includes a control unit that performs the following operations: estimating a traffic flow rate, wherein the traffic flow rate is the number of vehicles passing through a first location per unit time; estimating traffic volume based on vehicle density, wherein the vehicle density is the density of vehicles in a first interval, which is an interval from a specified location to the first location, the vehicle density being calculated based on driving information as information related to the driving of multiple vehicles traveling in the first interval, and the traffic volume being the number of vehicles present in the first interval at a specified time point; and estimating the travel time of the first interval based on the traffic flow rate and the traffic volume, wherein the control unit further performs the following operations: for each of the multiple destinations included in the origin-destination (OD) information, predicting a first number of vehicles based on first information, wherein the OD information is past route information of multiple vehicles, and the first number of vehicles is the predicted number of vehicles traveling to that destination on the target date; and calculating a first ratio for each of the multiple destinations based on the OD information, wherein the first ratio is the ratio of each origin to the number of destinations. The ratio of the first number of vehicles; multiplying the first number of vehicles calculated for each destination by the first ratio calculated for each departure point to calculate a second number of vehicles per OD pair, wherein the OD pair is a pair of departure points and destinations, and the second number of vehicles is the predicted number of vehicles arriving at the destination from the departure point on a given day; multiplying the second number of vehicles calculated for each OD pair by the ratio of vehicles passing through the first interval obtained based on the OD information, thereby calculating a third number of vehicles per OD pair, wherein the third number of vehicles is the predicted number of vehicles passing through the first interval; calculating a fourth number of vehicles per OD pair based on the third number of vehicles calculated for each OD pair and information related to the time period of passage through the first interval obtained based on the OD information, wherein the fourth number of vehicles is the predicted number of vehicles passing through the first interval in a specific time period; determining a first moment based on the fourth number of vehicles calculated for each OD pair, wherein the first moment is the moment when the number of vehicles passing through the first interval exceeds a predetermined threshold; and using the time period including the first moment as the congestion occurrence time period, applying the traffic flow rate in the congestion flow to the first interval to estimate the travel time within the first interval.

[0023] The control unit estimates the traffic volume as the number of vehicles present in the first section based on the vehicle density of the first section, and estimates the travel time of the first section based on the traffic flow rate and the estimated traffic volume.

[0024] Traffic flow rate is the number of vehicles that can pass through a specific location per unit of time. Traffic flow rate may differ between normal and congested periods.

[0025] The first section is the section of the road from a designated location to a first location. Here, the first location refers to a location that may become a bottleneck for congestion. In other words, the first section is a section that is prone to frequent congestion due to traffic concentration. The information processing device of this disclosure estimates travel time based on the first section.

[0026] Vehicle density is the number of vehicles per unit distance.

[0027] Traffic volume is the number of vehicles present in the first interval. Traffic volume is calculated by multiplying the length of the first interval by the vehicle density.

[0028] Travel time is the time it takes to move from one place to another.

[0029] If the length and vehicle density of the first interval are known, the number of vehicles in the first interval, i.e., the traffic volume, can be estimated, and the travel time of the first interval can be estimated based on the estimated traffic volume and traffic flow rate.

[0030] Furthermore, if the future vehicle density within the first interval is known, future travel times can be estimated. For example, one can estimate the number of vehicles that will pass through the first interval in the future based on the past route information (OD information) of multiple vehicles, thereby estimating the future travel time within the first interval.

[0031] However, OD information is generated based on data sent from the probe vehicle, so the predicted number of all vehicles cannot be determined solely from OD information. Therefore, the control unit calculates the ratio of vehicles traveling to the multiple destinations included in the OD information that pass through the first interval, and multiplies this ratio by the predicted number of vehicles traveling to each destination on a given day, thereby estimating the number of vehicles passing through the first interval.

[0032] First, for each of the multiple destinations included in the OD information, the control unit calculates the predicted number of vehicles traveling to the destination on the target date based on the first information (the total number of vehicles traveling from all departure points to the target destination. The following is the first number).

[0033] The first piece of information is used to determine the number of vehicles at a specified destination. For example, the first piece of information might include information related to an event being held at the specified destination, calendar information, etc.

[0034] Next, the control unit calculates a first ratio, which is the ratio of the number of vehicles (first number) from each origin to each of the multiple destinations included in the OD information. The first ratio is calculated for each of the multiple destinations included in the OD information.

[0035] In addition, the control unit multiplies the first number by a first ratio calculated for each departure point to determine the predicted number of vehicles on the route connecting the departure and destination points for one day (the second number). The second number is calculated for each departure-destination pair (hereinafter referred to as the OD pair).

[0036] In addition, the control unit multiplies the second number calculated for each OD pair by the ratio of passing through the first interval obtained based on the OD information, thereby calculating the predicted number of units passing through the first interval (the third number) for each OD pair.

[0037] Furthermore, the control unit calculates the predicted number of units passing through the first interval in a specific time period, i.e., the fourth number, based on the third number calculated for each OD pair and the information related to the traversal time period of the first interval obtained from the OD information.

[0038] The OD information contains information related to the time period during which vehicles pass through the first interval. Using this information, the predicted number of vehicles passing through the first interval during a certain time period (the fourth vehicle count) can be calculated.

[0039] By summing the fourth number of stations calculated for multiple OD pairs, the total number of stations passing through the first interval can be estimated for each future time period.

[0040] In addition, the control unit calculates the first moment based on the fourth number calculated for each OD pair.

[0041] The first moment is when the total number of vehicles in the fourth segment within the first interval exceeds the threshold at which the flow of vehicles on the road transitions from free flow to congested flow. The total number of vehicles exceeding the threshold signifies congestion within the first segment. In other words, the first moment is the moment when congestion occurs within the first segment.

[0042] Since the first moment is when congestion occurs, the travel time of the first section changes from this moment onwards. Therefore, within the time period including this first moment, the control unit uses the traffic flow rate in the congested flow to calculate the travel time of the first section.

[0043] Thus, the information processing device of one scheme of this disclosure predicts the traffic demand at a destination and, based on past route information, infers the number of vehicles traveling to the destination from multiple origins. Then, based on the inferred number of vehicles, the information processing device infers the number of vehicles passing through a first interval existing between the origin and the destination, and determines the time when congestion occurs within that first interval. Based on this, during the period when congestion occurs, the information processing device applies the traffic flow rate in the congestion flow to estimate the travel time within the first interval, thereby estimating the travel time to the destination.

[0044] Based on this configuration, the information processing apparatus of this disclosure can predict congestion with higher accuracy than ever before.

[0045] Hereinafter, specific embodiments of the present disclosure will be described based on the accompanying drawings. Unless otherwise specified, the hardware configuration, module configuration, functional configuration, etc., described in each embodiment are not intended to limit the scope of the disclosed technology.

[0046] (Implementation Method)

[0047] [Summary of the processing performed by the server device]

[0048] Reference Figure 1 The outline of the processes performed by the server device in the implementation method will be described. Figure 1 This is a diagram illustrating the outline of the processing performed by the server device 100 in this embodiment. One aspect of the information processing apparatus disclosed herein is implemented as the server device 100. In this embodiment, the server device 100 predicts traffic demand at the destination of a vehicle and determines the timing of congestion within a specific area based on the predicted traffic demand.

[0049] First, the server device 100 predicts the number of vehicles that will pass through a specific interval ("first interval" in this disclosure) during a specific time period based on the past driving history of multiple vehicles.

[0050] First, the server device 100 predicts the number of vehicles heading to multiple destinations contained in the OD information based on the past route information of multiple vehicles, i.e., OD information.

[0051] At this time, the server device 100 predicts the traffic demand for each destination (i.e., how many vehicles will travel to the destination in a day) based on the activity information at multiple destinations contained in the OD information.

[0052] Next, the server device 100 calculates the number of vehicles departing from a certain origin and arriving at a certain destination for each origin-destination pair (OD pair) based on the OD information. Then, based on the route information contained in the OD information, it predicts the number of vehicles passing through a target interval within a specific time period. Here, the target interval is a defined interval of length, with the location serving as a bottleneck for congestion at the head of the queue.

[0053] Next, the server device 100 determines the time when congestion occurs based on the number of vehicles passing through the target section within a specific time period. The server device 100 determines the time when the flow of vehicles within the target section transforms into a congested flow.

[0054] Then, during the time period that includes the moment when congestion occurs within the object section, the server device 100 applies the traffic flow rate of the congestion flow to the object section to estimate the travel time required to travel within the object section.

[0055] Traffic flow rate is a value obtained by converting the traffic volume (number of vehicles that have passed) measured at a specified location into traffic volume per unit of time (typically one hour). For example, in places where congestion occurs due to bottlenecks, the traffic flow rate may sometimes be much lower than usual. Traffic flow rate can vary depending on the location of the bottleneck, the cause of the congestion, and other factors.

[0056] By applying the traffic flow rate in the congestion flow to the congestion-occurring section, the travel time within the target section when congestion occurs can be calculated.

[0057] As described above, server device 100 predicts traffic demand for each of multiple destinations and predicts the number of vehicles heading to each destination based on OD information for each origin. Then, server device 100 predicts the future number of vehicles passing through a target interval based on the number of vehicles calculated for each OD pair, and, based on determining the time when congestion occurs within that target interval, estimates the travel time within the time period including that time. Therefore, server device 100 can predict congestion with higher accuracy than before.

[0058] [Server Device Configuration]

[0059] Next, the hardware and software configuration of the server device 100 will be described. Figure 2 This diagram illustrates the constituent elements of the server device 100 according to the embodiment.

[0060] Server device 100 can be configured as a computer having a processor (CPU (Central Processing Unit), GPU (Graphics Processing Unit), etc.), main storage (RAM (Random Access Memory), ROM (Read Only Memory), etc.), and auxiliary storage (EPROM (Erasable Programmable Read Only Memory), hard disk drive, removable media, etc.). The auxiliary storage device stores the operating system (OS), various programs, various tables, etc. By executing the programs stored in the auxiliary storage device, various functions (software modules) that meet the specified purpose can be achieved, as described later. However, some or all of the functions can also be implemented as hardware modules using hardware circuits such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0061] The server device 100 is configured to include a control unit 110, a storage unit 120, and a communication unit 130.

[0062] The control unit 110 is a computing unit that executes prescribed programs to implement various functions of the server device 100. The control unit 110 can be implemented, for example, by a hardware processor such as a CPU. Furthermore, the control unit 110 may also be configured to include RAM, ROM (read-only memory), cache memory, etc.

[0063] In this embodiment, the control unit 110 of the server device 100 is configured to have six software modules: a first prediction unit 111, a second prediction unit 112, a third prediction unit 113, a fourth prediction unit 114, a timing determination unit 115, and an estimation unit 116. Each software module can be implemented by the control unit 110 (CPU) or the like executing a program stored in the storage unit 120. It should be noted that the information processing performed by the software modules has the same meaning as the information processing performed by the control unit 110 (CPU, etc.).

[0064] The first forecasting unit 111 estimates the number of vehicles traveling to the specified destination on a given day, i.e., the first number of vehicles, based on information about traffic demand for the target day, i.e., the first information, where the traffic demand is the number of vehicles that will be present at the specified destination.

[0065] The first prediction unit 111 estimates the first number of vehicles based on each of the multiple destinations contained in the past route information of multiple vehicles, i.e., the OD information.

[0066] The second prediction unit 112 calculates the ratio (hereinafter referred to as the first ratio) for each of the multiple destinations included in the OD information. Furthermore, the second prediction unit 112 multiplies the first number of vehicles calculated for each destination by the first ratio to calculate a second number of vehicles. The second number is the predicted number of vehicles arriving at the destination from a given origin in one day, calculated for each origin-destination pair (OD pair).

[0067] The third prediction unit 113 calculates the number of vehicles passing through the target area in a day by multiplying the second number calculated for each OD pair by the passing ratio obtained based on the OD information. This third number is calculated for each OD pair.

[0068] The fourth prediction unit 114 calculates the fourth number of vehicles passing through the target interval in a specific time period by multiplying the third number calculated for each OD pair by the time period ratio obtained from the OD information for each time period passing through the target interval. The fourth number is calculated for each OD pair and each time period.

[0069] The time determination unit 115 determines the first time based on the fourth number of vehicles calculated for each OD pair and each time period, wherein the first time is the time when the number of vehicles passing through the target section exceeds the threshold at which the flow of vehicles on the road within the target section changes from free flow to congested flow.

[0070] The estimation unit 116 uses the time period including the first moment as the time period of congestion occurrence, and applies the traffic flow rate in the congestion flow to the target interval to estimate the travel time of the route from the specified location to the specified destination via the first location.

[0071] The storage unit 120 is a unit for storing information and is composed of storage media such as RAM, disk, and flash memory. The storage unit 120 stores programs executed by the control unit 110 and data used by those programs. In this embodiment, the storage unit 120 stores the aforementioned OD information.

[0072] The communication unit 130 is a communication interface for connecting the server device 100 to an external network. The communication unit 130 is configured, for example, to communicate with external devices via cellular communication networks such as wireless LAN (Local Area Network), 3G (3rd Generation), 4G (4th Generation), or 5G (5th Generation).

[0073] It should be noted that, Figure 2 The configuration shown is an example; all or part of the functions illustrated can also be executed using specially designed circuitry. Furthermore, programs can be stored or executed using a combination of main and auxiliary storage devices, other than those shown in the diagram.

[0074] [Server device processing]

[0075] Next, the specific details of the processing performed by the server device 100 of one embodiment of this disclosure will be explained. Figure 3 This is a flowchart of the processes performed by the control unit 110 of the server device 100 in this embodiment. Figure 3 The following processing is explained: The server device 100 determines the time of congestion based on the traffic demand at the destination and estimates the travel time for the target area.

[0076] When server device 100 receives a request from a vehicle under its management, it begins step S10. Alternatively, server device 100 may also begin step S10 when a user in the vehicle receives some input via an in-vehicle terminal or the like. Alternatively, server device 100 may periodically begin the processing illustrated.

[0077] The processing steps S10 to S12 are performed for each of the multiple destinations contained in the OD information.

[0078] First, in step S10, the first prediction unit 111 estimates the number of vehicles traveling to the destination of the processing object on a given day, i.e., the first number, based on information used to predict traffic demand (first information). For example, the first prediction unit 111 may predict the number of vehicles traveling to the destination of the processing object based on information related to the scheduled activities at the destination of the processing object, calendar information, past performance values, etc.

[0079] In step S11, the second prediction unit 112 statistically analyzes the journeys to the destination of the processing object in the OD information for each departure point, and calculates the ratio of each departure point to all vehicles traveling to the destination of the processing object. In other words, the second prediction unit 112 calculates the ratio of vehicles traveling from a certain departure point to the destination of the processing object relative to all vehicles traveling from all departure points to the destination of the processing object, i.e., the first ratio.

[0080] In step S12, the second prediction unit 112 predicts the number of vehicles traveling to the destination of the processing object in one day based on the first ratio calculated for each departure point in step S11. Specifically, the second prediction unit 112 may multiply the first number of vehicles by the first ratio. Then, the first prediction unit 111 and the second prediction unit 112 repeatedly perform steps S10 to S12 for all destinations.

[0081] Next, in step S13, the third prediction unit 113 predicts the number of vehicles passing through the target interval in one day, i.e., the third number of vehicles. Specifically, the third prediction unit 113 multiplies the second number of vehicles calculated for each OD pair by the ratio of vehicles passing through the target interval (passage ratio) obtained based on the OD information, thereby calculating the predicted number of vehicles passing through the target interval for each OD pair, i.e., the third number of vehicles.

[0082] Next, in step S14, the fourth prediction unit 114 multiplies the third number calculated for each OD pair by the time period ratio relative to the ratio of all vehicles passing through the target interval in each of the multiple time periods to calculate the fourth number of vehicles passing through the target interval. By summing the fourth number calculated for each OD pair separately by time period, the fourth prediction unit 114 can calculate the number of vehicles passing through the target interval in a specific time period.

[0083] Next, in step S15, the time determination unit 115 determines the moment when the flow of vehicles in the target section changes from free flow to congested flow. Specifically, the time determination unit 115 determines the first moment when the fourth number of vehicles exceeds the threshold for the flow of vehicles in the target section to change from free flow to congested flow, based on the fourth number calculated for each OD pair and each time period.

[0084] Next, in step S16, within the congestion occurrence time period including the time determined in step S15, the estimation unit 116 estimates the travel time of the target section using the traffic flow rate in the congestion flow. The travel time within the target section is the time it takes for a vehicle to move from the beginning to the end of the target section. Specifically, the estimation unit 116 can set the travel time within the target section as the value obtained by dividing the traffic volume (fourth vehicle number) of each time period within the target section by the traffic flow rate (traffic flow rate in the congestion flow) within the target section.

[0085] It should be noted that the estimation unit 116 can also estimate the traffic flow rate within the congested object section based on the vehicle density within the congested object section and the speeds of multiple vehicles within the congested object section. The estimation unit 116 can calculate the vehicle density based on the average speed of multiple vehicles that have passed through the object section.

[0086] The formula Q = KV (1)

[0087] Q: Traffic flow rate (traffic volume), K: Vehicle density, V: Average speed.

[0088] Here, the average speed can also be expressed by the following formula (Underwood formula).

[0089] V = Vf·e －(K / Kc) Equation (2)

[0090] V: Average speed, Vf: Maximum speed, K: Vehicle density, Kc: Critical density.

[0091] According to formula (2), the value of vehicle density K can be obtained, and the traffic flow rate Q can be obtained according to formula (1).

[0092] As described above, the server device 100 in this embodiment predicts the number of vehicles traveling to the destination in a day based on the traffic demand at the vehicle's destination, and predicts the number of vehicles passing through the target interval during a specific time period based on OD information. Then, the server device 100 determines the time of congestion within the target interval, and during the congestion period, applies the traffic flow rate during congestion to estimate the travel time within the target interval. Therefore, the server device 100 can predict the time required to overcome congestion with higher accuracy than before.

[0093] It should be noted that in this embodiment, the target interval is fixed. However, if there are multiple intervals that are prone to congestion caused by traffic concentration, the above processing can also be performed on multiple intervals.

[0094] (Other variations)

[0095] The above-described embodiments are merely examples, and this disclosure can be implemented with appropriate modifications without departing from its spirit. For example, the processing and elements described in this disclosure can be freely combined and implemented as long as no technical contradictions arise.

[0096] This disclosure can also be implemented by supplying a computer program that implements the functions described in the above embodiments to a computer, which then reads and executes the program using one or more processors. Such a computer program can be provided to the computer either via a non-transitory computer-readable storage medium that can be connected to the computer's system bus or via a network. Non-transitory computer-readable storage media include, for example, any type of disk such as a hard disk (floppy disk, hard disk drive, etc.), an optical disk (CD-ROM, DVD, Blu-ray disc, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM (Electrically Erasable Programmable Read Only Memory), a magnetic card, flash memory, an optical card, or any type of medium suitable for storing electronic instructions.

Claims

1. An information processing apparatus comprising a control unit, the control unit performing the following operations: Estimated traffic flow rate, of which, The traffic flow rate is the number of vehicles that pass through the first location per unit of time. Traffic volume is estimated based on vehicle density, wherein the vehicle density is the density of vehicles within a first interval from a specified location to the first location, the vehicle density is calculated based on driving information relating to the movement of multiple vehicles traveling in the first interval, and the traffic volume is the number of vehicles present in the first interval at a specified time point; and The travel time for the first section is estimated based on the traffic flow rate and the traffic volume. The control unit also performs the following actions: For each of the multiple destinations contained in the origin-end point (OD) information, a first number of vehicles is estimated based on first information, wherein the OD information is the past route information of multiple vehicles, and the first number of vehicles is the predicted number of vehicles traveling to that destination on the target date. Based on the OD information, a first ratio is calculated for each of the plurality of destinations, wherein the first ratio is the ratio of each origin to the first number of vehicles heading to each destination. The first number of vehicles calculated for each destination is multiplied by the first ratio calculated for each departure point to calculate the second number of vehicles per OD pair, wherein the OD pair is a pair of departure points and destinations, and the second number of vehicles is the predicted number of vehicles arriving at the destination from the departure point in one day. The second number of units calculated for each OD pair is multiplied by the ratio of units passing through the first interval obtained based on the OD information, thereby calculating a third number of units for each OD pair, wherein the third number of units is the predicted number of units passing through the first interval. A fourth number of units is calculated for each OD pair based on the third number of units calculated for each OD pair and information related to the traversal time period of the first interval obtained from the OD information, wherein the fourth number of units is the predicted number of units traversing the first interval in a specific time period. The first moment is determined based on the fourth number of vehicles calculated for each OD pair, wherein the first moment is the moment when the number of vehicles passing through the first interval exceeds a predetermined threshold; and The congestion occurs within a time period that includes the first moment. The travel time within the first interval is estimated by applying the traffic flow rate in the congestion flow to the first interval.

Images