KR20240032811A - Server, method and computer program for generating traffic information - Google Patents

Abstract

The traffic information generation server that generates traffic information is based on a collection unit that collects wireless communication access data from a plurality of base stations located within a preset radius from the road, past wireless communication access data collected from a plurality of base stations, and road speed data. A model generator that generates a time-series deep learning-based traffic speed learning model, inputs the real-time connection volume to multiple base stations and the wireless communication influence on wireless communication at each base station into the traffic speed learning model to determine the real-time speed of the road. It may include a speed prediction unit that makes predictions and a traffic information generator that generates traffic information about the road based on the predicted real-time speed.

Description

Server, method and computer program for generating traffic information {SERVER, METHOD AND COMPUTER PROGRAM FOR GENERATING TRAFFIC INFORMATION}

The present invention relates to a server, method, and computer program for generating traffic information.

Recently, various traffic information provision services have been provided, and a representative traffic information provision service is provided through in-vehicle navigation.

Car navigation can receive the user's current location information through GPS and provide the user with a route to the destination, shortening the arrival time to the destination.

For traffic information services, it is very important to increase the level of prediction of future traffic information in order to provide more accurate information (congestion level, estimated time of arrival, etc.).

However, conventional traffic information provision services predict future traffic information by applying multidimensional time information such as speed, day of the week, date, and weather to past statistical data. In other words, the conventional traffic information provision service does not consider spatial information about traffic information on surrounding roads at all.

Accordingly, it is known that the accuracy of future traffic information in conventional traffic information provision services is only 87% on average.

Additionally, conventional traffic information provision services rely on past statistical data even for shaded roads where speeds are difficult to collect.

Korean Patent Publication No. 2009-0003431 (published on January 12, 2009)

The present invention is intended to solve the problems of the prior art described above, and predicts the real-time speed of the road using a traffic speed learning model generated based on past wireless communication access data and road speed data collected from a plurality of base stations. The purpose is to provide a traffic information generation server, method, and computer program.

Specifically, the aim is to provide a traffic information generation server, method, and computer program that predicts real-time speed of a road by inputting real-time wireless communication access data collected from a plurality of base stations into a traffic speed learning model. However, the technical challenges that this embodiment aims to achieve are not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, the traffic information generation server that generates traffic information according to the first aspect of the present invention includes a collection unit that collects wireless communication access data from a plurality of base stations located within a preset radius from the road. ; a model generator that generates a time-series deep learning-based traffic speed learning model based on past wireless communication connection data collected from the plurality of base stations and the road speed data; a speed prediction unit that predicts the real-time speed of the road by inputting the real-time connection volume to the plurality of base stations and the influence of wireless communication on wireless communication at each base station into the traffic speed learning model; and a traffic information generator that generates traffic information for the road based on the predicted real-time speed.

A method of generating traffic information in a traffic information generation server according to a second aspect of the present invention includes collecting wireless communication access data from a plurality of base stations located within a preset radius from a road; Generating a time series deep learning-based traffic speed learning model based on past wireless communication connection data collected from the plurality of base stations and the road speed data; predicting the real-time speed of the road by inputting real-time connection volume to the plurality of base stations and wireless communication influence on wireless communication at each base station into the traffic speed learning model; and generating traffic information for the road based on the predicted real-time speed.

In the computer program stored in a medium containing a sequence of instructions for generating traffic information according to the third aspect of the present invention, the computer program, when executed by a computing device, wirelessly transmits data from a plurality of base stations located within a preset radius from the road. Collect communication connection data, generate a time-series deep learning-based traffic speed learning model based on past wireless communication connection data collected from the plurality of base stations and the road speed data, and generate real-time connection volume to the plurality of base stations. and instructions for predicting the real-time speed of the road by inputting the influence of wireless communication on wireless communication at each base station into the traffic speed learning model and generating traffic information for the road based on the predicted real-time speed. Can contain sequences.

The above-described means for solving the problem are merely illustrative and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description of the invention.

According to one of the means for solving the problems of the present invention described above, the present invention determines the real-time speed of the road using a traffic speed learning model generated based on past wireless communication access data and road speed data collected from a plurality of base stations. A traffic information generation server, method, and computer program that predict can be provided.

Specifically, the present invention can provide a traffic information generation server, method, and computer program for predicting real-time speed of a road by inputting real-time wireless communication access data collected from a plurality of base stations into a traffic speed learning model.

Through this, the present invention can reduce the processing load of the system because it predicts road speed using wireless communication access data collected from a plurality of base stations.

In addition, the present invention predicts the real-time speed of the current road by inputting real-time wireless communication access data into a traffic speed learning model even on roads such as shaded areas where it is difficult to collect traffic data, thereby improving the prediction accuracy of the real-time speed for the road. It can be raised.

1 is a block diagram of a traffic information generation server according to an embodiment of the present invention.
2A to 2C are diagrams for explaining a method of collecting wireless communication access data according to an embodiment of the present invention.
Figure 3 is a diagram illustrating a method of predicting real-time speed of a road using a traffic speed learning model according to an embodiment of the present invention.
Figures 4a and 4b are diagrams for explaining a method of calculating a connection volume weight per base station according to an embodiment of the present invention.
Figure 5 is a flowchart showing a method for generating traffic information according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware.

In this specification, some of the operations or functions described as being performed by a terminal or device may instead be performed on a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed on a terminal or device connected to the server.

Hereinafter, specific details for implementing the present invention will be described with reference to the attached configuration diagram or processing flow diagram.

Figure 1 is a block diagram of a traffic information generation server 10 according to an embodiment of the present invention.

Referring to FIG. 1, the traffic information generation server 10 includes a collection unit 100, a filtering unit 110, a model creation unit 120, a speed prediction unit 130, a traffic information generation unit 140, and an emergency situation. It may include a prediction unit 150. Here, the filtering unit 110 may include a first filtering unit 112 and a second filtering unit 114. However, the traffic information generating server 10 shown in FIG. 1 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG. 1. Hereinafter, Figures 2A to 4B will be described along with Figure 1.

The collection unit 100 may collect wireless communication access data from a plurality of base stations located within a preset radius from the road. For example, referring to FIG. 2A, the collection unit 100 selects a base station located within a preset radius (e.g., 200 m) from an intersection where at least two roads meet as an effective base station, and wireless communication is performed from each selected effective base station. Access data can be collected.

At this time, the base station selected as an effective base station may be, for example, a base station whose antenna is directed toward the road and whose antenna is installed outside the base station.

For example, the collection unit 100 collects wireless communication access data from a plurality of base stations belonging to the first effective base station group selected for the first intersection, and belongs to the second effective base station group selected for the second intersection. Wireless communication connection data can be collected from multiple base stations.

For example, the collection unit 100 collects wireless communication access data from an effective base station located within a preset radius from a first road (e.g., West Coast Expressway) and an effective base station located within a preset radius from a second road (e.g., Yeongdong Expressway). can be collected. Here, the collected wireless communication connection data may include, for example, information about a plurality of user terminals that attempted wireless access to each effective base station and information about each effective base station (e.g., location information of the base station, etc.).

The collection unit 100 may distinguish between an upward direction and a downward direction of a road based on location information of a plurality of base stations and a distribution map of wireless communication connection volume for the plurality of base stations. By distinguishing the up and down line directions, the collection unit 100 can predict the real-time speed of each up and down line, as will be described later.

For example, referring to Figure 2b, the collection unit 100 determines the distribution of the connection volume of each base station using log data for the S1-AP protocol collected from a plurality of base stations located within a preset radius from the first road, and , Road directionality (upward direction and downward direction) for the first road can be given through the correlation between the location of each base station and the connection volume distribution.

Here, the S1-AP (S1-Application Protocol) protocol periodically applies even when a user's terminal subscribed to an LTE network/service is connected to the base station (e.g., using the Internet, using a phone, etc.) or is not connected (idle state). It is a protocol that provides a communication connection between a user terminal and a base station so that a communication connection with the base station can occur. Since log data for the S1-AP protocol is real-time data on user terminals periodically connected to the base station through the S1-AP protocol and is also standard protocol information for LTE communication, it is specially used for purposes such as monitoring communication quality. This is data that can be unconditionally collected by telecommunication companies without permission. Log data for the S1-AP protocol can be used to determine the connection volume and connection mobility of each base station per hour based on the connection time and location of the base station, so it is suitable for learning a traffic speed learning model. For example, among a plurality of base stations located within a preset radius from the first road, the connection volume of the base station 20 located at the first distance from Seoul is greater than the connection volume of the base station 22 located at a second distance from Seoul (further than the first distance). If the connection volume is high, the collection unit 100 determines that the vehicle flow on the downbound line 201 for the first road is in a congested state, and determines that the vehicle flow on the upbound line 203 for the first road is in a smooth state. You can.

The filtering unit 110 may extract wireless communication connection data generated within a vehicle located on the road from a plurality of collected wireless communication connection data. For example, the filtering unit 110 may extract wireless connection data generated from a terminal (eg, smart phone, smart watch, etc.) of a driver or passenger of a vehicle traveling on the road from among the collected wireless communication connection data.

For example, the first filtering unit 112 may exclude wireless communication connection data collected by the base station more than a preset number of times per day from the plurality of collected wireless communication connection data. For example, the first filtering unit 112 collects wireless communication connection data due to paging communication that occurs periodically during a preset time (e.g., 1:00 am to 6:00 am) by collecting a plurality of wireless communication access data. It can be excluded from the data. Here, paging communication refers to broadcast communication that periodically wakes up the terminal in order to determine the reception status of the terminal in an inactive state and the approximate location of the terminal. Since such wireless communication connection data resulting from paging communication is not wireless communication connection data generated within a vehicle on the road, it needs to be excluded from the plurality of collected wireless communication connection data in order to increase the accuracy of prediction of road speed.

In addition, the first filtering unit 112 further excludes wireless communication connection data of user terminals (terminals of residents or pedestrians) that have connected to one base station more than a preset number of times during a certain period of time from the collected plurality of wireless communication connection data. can do. Wireless communication access data accessed by the terminal of a pedestrian or resident who stays in the area near the road for a certain period of time (e.g., 1 day) (determined as wireless communication access data connected to one base station more than a preset number of times during a certain period of time) ) is unlikely to be wireless communication access data generated within a vehicle on the road, so the accuracy of prediction of road speed can be improved by excluding the wireless communication access data.

The second filtering unit 114 may exclude wireless communication connection data related to a preset service from a plurality of wireless communication connection data collected based on an index value for the service purpose of the communication protocol. Here, the preset service may be a service that imposes restrictions while driving (for example, a streaming video service, etc.).

Since these preset services are usually difficult to use in vehicles, they need to be excluded from the plurality of wireless communication access data collected to increase the accuracy of prediction of road speed. For example, the second filtering unit 114 selects a service that is restricted during operation among the index values (e.g., QCI value) for service use of the S1-AP protocol (e.g., QCI No. 3 of the S1-AP protocol in FIG. 2C). (24) and streaming video service of QCI No. 6 (26), etc.) may be excluded from the collected plurality of wireless communication connection data.

Referring to Figure 2c, the QCI (Quality of service Class Index) of the S1-AP protocol is an index value expressing priority as an integer to guarantee traffic quality according to the importance of the service.

The filtering unit 110 includes wireless communication access data collected by a base station more than a preset number of times per day and wireless communication access data related to preset services excluded from the plurality of collected wireless communication access data. can only be extracted.

Conventionally, the handover-type speed measurement method (searching for base stations that have been continuously handed over in units of numerous users, and checking the distance (or target road length) between discovered base stations and the difference in access time between two consecutive base stations in real time) However, these methods do not take into account errors due to data accessed from pedestrians and residents' terminals, and due to user-level handover analysis, There were problems such as system overload.

Accordingly, in the present invention, the processing load of the system can be reduced by predicting the road speed using wireless communication access data collected in real time at the base station level.

In addition, in predicting road speed, only the wireless communication connection data connected to the driver's or passenger's terminal is used, excluding the wireless communication connection data connected to the terminals of pedestrians and residents, so the prediction accuracy of road speed can be increased.

The model generator 120 may generate a traffic speed learning model based on past wireless communication access data and road speed data collected from a plurality of base stations. For example, the model generator 120 performs first traffic speed learning by pairing wireless communication connection data at time t-1, wireless communication connection data at time t-2, and road speed data at time t. By creating a model and pairing the wireless communication connection data at time t-2, the wireless communication connection data at time t-3, and the road speed data at time t-1, a second traffic speed learning model is generated. A time series-based traffic speed learning model can be created.

The model generator 120 may input past wireless communication access data collected from a plurality of base stations into a traffic speed learning model and learn the traffic speed learning model so that current road speed data is output.

For example, the model generator 120 inputs wireless communication connection data at time t-1 and wireless communication connection data at time t-2 into the first traffic speed learning model to obtain road speed data at time t. You can learn to output . In addition, the model generator 120 inputs the wireless communication connection data at time t-2 and the wireless communication connection data at time t-3 into the second traffic speed learning model to obtain road speed data at time t-1. You can learn to output .

The model generator 120 may classify the extracted wireless communication connection data into past wireless communication connection data by incoming and past wireless communication connection data by outgoing based on the index value for the connection type of the communication protocol. For example, the model generator 120 classifies the wireless communication connection data having an index value for the incoming connection type of the S1-AP protocol among the extracted wireless communication connection data as past wireless communication connection data due to incoming calls, and S1 -Wireless communication connection data with an index value for the originating connection type of the AP protocol can be classified as past wireless communication connection data by origination.

The model generator 120 may calculate the incoming connection amount based on classified past wireless communication connection data for incoming calls and calculate the outgoing connection amount based on past wireless communication connection data for outgoing calls.

The model generator 120 may generate a traffic speed learning model based on past incoming connection volume, past outgoing connection volume, and road speed data. Here, the traffic speed learning model may be, for example, a Long-Short Term Memory (LSTM) model, which is a time series deep learning learning model.

For example, the model generator 120 determines the first traffic speed based on the incoming and outgoing connection volume at time t-1, the incoming and outgoing connection volume at time t-2, and the road speed data at time t. A second traffic speed that creates and trains a learning model and pairs the incoming and outgoing connection volume at time t-2, the incoming and outgoing connection volume at time t-3, and the speed data of the road at time t-1. You can create and learn learning models.

The speed prediction unit 130 can predict the real-time speed of the road by inputting real-time wireless communication access data collected from a plurality of base stations into a traffic speed learning model. For example, referring to FIG. 3, the speed prediction unit 130 collects real-time wireless communication access data (real-time incoming connection volume and real-time outgoing connection volume) and date collected at time t from a plurality of base stations (first to third base stations). By inputting information (day and time information) into a time series-based traffic speed learning model, the up and down speeds of the road at time t can be predicted, respectively.

The speed prediction unit 130 may calculate the wireless communication influence on wireless communication at each base station based on the antenna angles of the plurality of base stations (base stations selected as effective base stations) or the external environment information of the area where the plurality of base stations are located. there is. Here, the wireless communication influence may be a concept corresponding to the wireless communication reach (strength of the wireless communication received signal). The speed prediction unit 130 can calculate the distance range from each base station to an area where the received signal strength indication (RSSI) is greater than the preset signal strength as the wireless communication influence of each base station. . Alternatively, the speed prediction unit 130 may calculate the distance range from each base station to an area corresponding to a point where it is difficult to distinguish the strength of the wireless communication reception signal of each base station as the wireless communication influence of each base station. For example, the larger the angle of the antenna facing the road, the higher the influence of wireless communication on the road and the wider the range of wireless communication. The smaller the angle of the antenna, the smaller the influence of wireless communication on the road. The reach of wireless communications becomes narrow. This influence on wireless communication may vary depending on the topography and weather where the base station is installed.

The speed prediction unit 130 inputs the real-time connection volume to a plurality of base stations and the influence of wireless communication on wireless communication at each base station into a traffic speed learning model to predict real-time speed information for each of the up and down directions of the road. You can.

The speed prediction unit 130 may calculate a connection volume weight for each base station based on the wireless communication influence per base station.

For example, referring to FIG. 4A, the speed prediction unit 130 predicts the influence of wireless communication at the first base station 401 and the second base station (401) according to the external environment (e.g., weather, terrain, etc.) on the target road. 403), the connection volume weight of each of the first base station 401 and the second base station 403 can be calculated based on the ratio between the wireless communication influences.

When the range of wireless communication influence on the wireless communication provided by the first base station 401 and the range of wireless communication influence on the wireless communication provided by the second base station 403 have a ratio of 1:3, The connection volume weight of the first base station 401 and the connection volume weight of the second base station 403 may also be calculated at a ratio of 1:3.

Referring to FIG. 4B, the speed prediction unit 130 determines the ratio between the wireless communication reception range according to the antenna angle of the first base station 401 and the wireless communication reception range according to the antenna angle of the second base station 403 toward the target road. Based on this, the connection volume weight of each of the first base station 401 and the second base station 403 can be calculated.

The speed prediction unit 130 inputs the real-time connection volume to a plurality of base stations, wireless communication influence per base station, and connection volume weight into a traffic speed learning model to predict real-time speed information for each of the up and down directions of the road.

Previously, models based on past speed statistics were mainly used, but these models had the problem of being difficult to use as is when the road environment changes and having low prediction accuracy.

Accordingly, the present invention uses a time series-based traffic speed learning model learned based on past wireless communication connection data (past incoming connection volume, past outgoing connection volume), so that it can be applied even when the road environment has changed, and it is difficult to collect traffic data. Even on roads such as local areas, real-time wireless communication access data is input into a traffic speed learning model to predict the real-time speed of the current road, thereby improving the prediction accuracy of real-time speed for that road.

In addition, in the case of the conventional handover method, there is a problem of speed measurement that may be biased toward some users (e.g., stopped drivers, outliers, etc.), but the present invention provides wireless communication access data (past incoming connection volume) in which handover does not occur. , past outgoing connection volume), this conventional problem can be solved by generating a generalized traffic speed learning model.

The traffic information generator 140 may generate traffic information about the road based on the predicted real-time speed on the road. For example, the traffic information generator 140 may generate traffic information that sets the road traffic status to smooth, normal, congested, etc. based on the predicted real-time speed. For example, the traffic information generator 140 may generate traffic information that displays a section with smooth traffic flow in green and a section with congested traffic flow in red among a plurality of sections of a road.

The unexpected situation prediction unit 150 may predict an unexpected situation on the road based on predicted real-time speed information on the road and pattern speed trend information on the road. For example, the emergency situation prediction unit 150 continues for a certain period of time in a state where the real-time speed information on the road predicted per minute is lower than the pattern speed trend (past pattern speed trend or predicted pattern speed trend) on the road. If so, it can be determined that an unexpected situation has occurred on the road.

The unexpected situation prediction unit 150 may determine that an unexpected situation has occurred on the road when the accumulated amount of real-time speed information predicted on the road exceeds a preset threshold speed value. For example, the road speed at minute t-2 is -5 km/h, the road speed at minute t-1 is -10 km/h, the road speed at minute t is -9 km/h, and the preset threshold Assuming that the speed value is 20km/h, the accumulated amount of real-time speed information (|-5km/h| + |-10km/h| + |-9km/h| = 25km/h) exceeds the preset threshold speed value. In this case, it can be determined that a bottleneck phenomenon has occurred on the road due to an accident on the road and traffic congestion has occurred.

The traffic information generator 140 may generate traffic information reflecting unexpected situation prediction information for a road where an unexpected situation occurs. For example, when an unexpected situation on a road (e.g., a traffic accident, etc.) is predicted, the traffic information generator 140 includes unexpected situation prediction information for the road and guidance information on a detour road with smooth traffic conditions. traffic information can be generated.

Conventionally, unexpected situations on the road were identified by relying on citizen reports and accident information received from police agencies due to unexpected situations occurring on the road, but the present invention provides predicted real-time speed information and pattern speed trend information on the road ( By determining unexpected situations on the road considering past pattern speed trends or predicted pattern speed trends, unexpected situations on the road can be detected accurately and quickly, and response measures can also be provided to drivers.

Meanwhile, those skilled in the art will know that the collection unit 100, the filtering unit 110, the first filtering unit 112, the second filtering unit 114, the model creation unit 120, the speed prediction unit 130, and the traffic information generation. It will be fully understood that the unit 140 and the emergency situation prediction unit 150 may be implemented separately, or one or more of them may be integrated and implemented.

Figure 5 is a flowchart showing a method for generating traffic information according to an embodiment of the present invention. The method of generating traffic information in the traffic information generating server 10 shown in FIG. 5 includes steps processed in time series by the embodiment shown in FIGS. 1 to 4. Therefore, even if the content is omitted below, it also applies to the method of generating traffic information in the traffic information generation server 10 according to the embodiment shown in FIGS. 1 to 4.

Referring to FIG. 5, in step S501, the traffic information generating server 10 may collect wireless communication access data from a plurality of base stations located within a preset radius from the road.

In step S503, the traffic information generation server 10 may generate a traffic speed learning model based on past wireless communication access data and road speed data collected from a plurality of base stations.

In step S505, the traffic information generation server 10 can predict the real-time speed of the road by inputting real-time wireless communication access data collected from a plurality of base stations into a traffic speed learning model.

In step S507, the traffic information generating server 10 may generate traffic information about the road based on the predicted real-time speed.

In the above description, steps S501 to S507 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Additionally, some steps may be omitted or the order between steps may be changed as needed.

The method of generating traffic information in the traffic information generation server 10 described with reference to FIGS. 1 to 5 may be in the form of a computer program stored on a medium executed by a computer or a recording medium containing instructions executable by a computer. It can be implemented. Additionally, the method of generating traffic information in the traffic information generating server 10 described with reference to FIGS. 1 to 5 may also be implemented in the form of a computer program stored in a medium executed by a computer.

Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

10: Traffic information generation server
100: Collection Department
110: filtering unit
112: first filtering unit
114: second filtering unit
120: Model creation unit
130: Speed prediction unit
140: Traffic information generation unit
150: Emergency situation prediction unit

Claims (17)

In the traffic information generation server that generates traffic information,
a collection unit that collects wireless communication access data from a plurality of base stations located within a preset radius from the road;
a model generator that generates a time-series deep learning-based traffic speed learning model based on past wireless communication connection data collected from the plurality of base stations and the road speed data;
a speed prediction unit that predicts the real-time speed of the road by inputting the real-time connection volume to the plurality of base stations and the influence of wireless communication on wireless communication at each base station into the traffic speed learning model; and
A traffic information generator that generates traffic information for the road based on the predicted real-time speed
A traffic information generation server containing a.
According to claim 1,
The collection department
A traffic information generation server that distinguishes the up and down directions of the road based on location information of the plurality of base stations and a distribution map of wireless communication connection volume for the plurality of base stations.
According to claim 2,
The speed prediction unit predicts real-time speed information for each of the up and down directions of the road.
According to claim 1,
The traffic information generation server wherein the wireless communication influence is calculated based on the antenna angle of each base station or external environment information of the area where each base station is located.
According to claim 1,
The wireless communication influence is a distance range to an area where the received signal strength indication (RSSI) of each base station corresponds to a preset signal strength or higher.
According to claim 1,
The traffic information generation server wherein the speed prediction unit calculates a connection volume weight for each base station based on the wireless communication influence.
According to claim 6,
The speed prediction unit further inputs the connection volume weight per base station to the traffic speed learning model to predict real-time speed information on the road.
According to claim 1,
Further comprising a filtering unit that extracts wireless communication connection data generated in a vehicle located on the road from the collected wireless communication connection data,
The filtering unit
A traffic information generating server comprising a first filtering unit that excludes wireless communication connection data resulting from paging communication that occurs periodically during a preset time from the wireless communication connection data.
According to claim 8,
The filtering unit
A traffic information generating server comprising a second filtering unit that excludes wireless communication connection data having an index value related to a service that is restricted during driving from the wireless communication connection data based on an index value for a service purpose of a communication protocol. .
In a method of generating traffic information in a traffic information generation server,
Collecting wireless communication access data from a plurality of base stations located within a preset radius from the road;
Generating a time series deep learning-based traffic speed learning model based on past wireless communication connection data collected from the plurality of base stations and the road speed data;
predicting the real-time speed of the road by inputting real-time connection volume to the plurality of base stations and wireless communication influence on wireless communication at each base station into the traffic speed learning model; and
Generating traffic information for the road based on the predicted real-time speed
A method of generating traffic information including.
According to claim 10,
The step of collecting the wireless communication connection data is,
A method for generating traffic information, comprising the step of distinguishing the up and down directions of the road based on location information of the plurality of base stations and a distribution map of wireless communication connection volume for the plurality of base stations.
According to claim 11,
The step of predicting the real-time speed of the road is,
A traffic information generating method comprising predicting real-time speed information for each of the up and down directions of the road.
According to claim 10,
The wireless communication influence is calculated based on the antenna angle of each base station or external environment information of the area where each base station is located.
According to claim 10,
The wireless communication influence is a distance range to an area where the received signal strength indication (RSSI) of each base station corresponds to a preset signal strength or higher.
According to claim 10,
The step of predicting the real-time speed of the road is,
A traffic information generation method comprising calculating a connection volume weight for each base station based on the wireless communication influence.
According to claim 15,
The step of predicting the real-time speed of the road is,
A method of generating traffic information, wherein real-time speed information on the road is predicted by further inputting the connection volume weight per base station into the traffic speed learning model.
A computer program stored on a medium containing a sequence of instructions for generating traffic information, comprising:
When the computer program is executed by a computing device,
Collects wireless communication access data from multiple base stations located within a preset radius from the road,
Generating a time-series deep learning-based traffic speed learning model based on past wireless communication access data collected from the plurality of base stations and the road speed data,
Predicting the real-time speed of the road by inputting the real-time connection volume to the plurality of base stations and the influence of wireless communication on wireless communication at each base station into the traffic speed learning model,
A computer program stored on a medium, comprising a sequence of instructions for generating traffic information for the roadway based on the predicted real-time speed.