KR101656145B1 - Method for providing path information - Google Patents

Abstract

The present invention relates to an information providing method capable of providing an optimal path to a destination in anticipation of congestion at a desired future time point by a user.
Receiving a user request for route guidance information at a specific future time point from a user terminal according to an embodiment of the present invention; Collecting image data for a specific region at predetermined time intervals; Calculating congestion prediction information at the specific future time point by considering the collected image data; And providing route guidance information at the specific future time point to the user terminal using the calculated congestion prediction information.

Description

METHOD FOR PROVIDING PATH INFORMATION "

The present invention relates to a route information providing method, and more particularly, to an information providing method capable of providing an optimal route to a destination in anticipation of congestion at a desired future time point by a user.

People who commute, go to and from work between about 10 million transit passengers a day in Seoul often say, 'How good it would be if I could find out from where I could go by bus and subway, or at least not too crowded. ?' think. In these troubles, the technology to calculate the congestion level in the vehicle emerges. Korean Patent Laid-Open No. 10-2009-0005597 as related literature.

Japanese Patent Laid-Open Publication No. 10-2009-0005597 discloses a technique of calculating the congestion degree in a vehicle by counting the number of times of detection of the payment means upon boarding a bus.

However, the aforementioned patents can not be applied to the subway. It is because the passengers who entered the same station do not know which way to get the train, when, and by whom. In addition, it is more difficult in a transfer station where you can change to another line. What really needs passengers using the subway is the congestion information for each train car. It is also information about the future ahead of departure time.

Therefore, it is necessary to study the future route guidance method which can be applied to the subway.

It is an object of the present invention to provide a route information providing method capable of collecting image data acquired through a video equipment installed in a specific area and calculating the congestion prediction information at a future time point using the collected image data to guide the optimal route .

According to an aspect of the present invention, there is provided a method for providing route guidance information to a user terminal, the method comprising: receiving a user request for route guidance information at a specific future time point from a user terminal; Collecting image data for a specific region at predetermined time intervals; Calculating congestion prediction information at the specific future time point by considering the collected image data; And providing route guidance information at the specific future time point to the user terminal using the calculated congestion prediction information.

The route information providing method according to an embodiment of the present invention provides a route through which a public transportation user can comfortably and safely arrive at a destination beyond a simple arrival scheduled service.

According to one embodiment of the present invention, it is possible to more efficiently operate public transportation by preventing safety accidents caused by crowded crowded customers, and to provide information useful for station and station construction, . ≪ / RTI >

In addition, according to an embodiment of the present invention, prediction information can be provided to a user by being applied to various fields including movement of objects such as department stores, parking lots, as well as public transportation.

1 is a view for explaining a route information providing service according to an embodiment of the present invention.
2 is a diagram for explaining congestion associated with an embodiment of the present invention.
3 is a block diagram of a route information providing system according to an embodiment of the present invention.
4 is a flowchart illustrating a path information providing method according to an embodiment of the present invention.
5 is a view for explaining a specxture of an image according to an embodiment of the present invention.
6 is a graph showing the values for the radius and angle for FIG.
7 is a diagram for explaining a technique used for calculating congestion among path information providing methods related to an embodiment of the present invention.
8 is a diagram for explaining the concept of the Adaboost algorithm related to an embodiment of the present invention.
9 is a graph illustrating a movement path of a specific user in the path information providing method according to an embodiment of the present invention.
10 shows a predicted congestion graph associated with an embodiment of the present invention.
11 is a graph of data used to calculate congestion prediction information in the path information providing method according to an embodiment of the present invention.

Hereinafter, a route information providing method and a route information providing system according to an embodiment of the present invention will be described with reference to the drawings.

As used herein, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. In this specification, the terms "comprising ", or" comprising "and the like should not be construed as necessarily including the various elements or steps described in the specification, Or may be further comprised of additional components or steps.

 1 is a view for explaining a route information providing service according to an embodiment of the present invention.

As shown in the figure, the passenger using the public transportation can go to the destination safely and comfortably using the route information providing service related to the embodiment of the present invention. The present invention provides a method of providing route information related to an embodiment of the present invention. The present invention further provides a method for providing a route information to a passenger You can provide information to get to your destination safely and comfortably. According to an embodiment of the present invention, in order to analyze the pattern of the residual seas as described above, it is necessary to first collect images and analyze the congestion from the collected images.

2 is a diagram for explaining congestion associated with an embodiment of the present invention.

As shown in the figure, the route information providing system according to an embodiment of the present invention utilizes a CCTV image installed in a public transportation (bus, subway) to analyze spatial density (i.e., congestion) The metadata about the space can be extracted.

Hereinafter, a method of providing route guidance information at a future point of view through congestion analysis and congestion analysis through a route information providing system will be described in detail.

3 is a block diagram of a route information providing system according to an embodiment of the present invention.

The path information providing system 100 includes a receiving unit 110, a collecting unit 120, a database 130, a prediction information calculating unit 140, a transmitting unit 150, and a control unit 160 .

The receiving unit 110 can receive various information, data, and the like. For example, the receiving unit 110 may receive a user request for route guidance information at a specific future time from a user terminal. The user terminal may include a mobile terminal. The mobile terminal may include a mobile phone, a smart phone, a notebook computer, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a navigation device, and a tablet PC.

The collection unit 120 may collect image data obtained by a video device (e.g., a CCTV installed in a public transportation). The video equipment can acquire video data of a specific area (for example, in public transport) at predetermined intervals. For example, the video equipment can acquire image data in public transit in real time.

The database 130 may store collected image data or specific location (e.g., by train car) and hourly congestion information (e.g., congestion value) calculated from the image data.

The prediction information calculation unit 140 may calculate the congestion prediction information at a specific future time point requested by the user in consideration of the collected image data and the request time point of the user. The congestion degree prediction information may be calculated using the collected congestion degree by collecting the congestion degree in a time-series manner. A concrete method of calculating the congestion degree prediction information will be described later.

The transmission unit 150 may provide optimal route guidance information (e.g., public transportation guide information) at a specific future time point desired by the user to the user terminal based on the calculated congestion prediction information.

The control unit 160 may control the receiving unit 110, the collecting unit 120, the database 130, the predictive information calculating unit 140, and the transmitting unit 150 as a whole.

4 is a flowchart illustrating a path information providing method according to an embodiment of the present invention.

The collection unit 130 may receive and collect the image data acquired by the imaging device at predetermined time intervals (e.g., real-time intervals) (S410). For example, the video device may be a CCTV installed in each cell of the subway.

The receiving unit 110 may receive a user request for route guidance information at a specific future time from the user terminal (S420). For example, the user may request the route information providing system 100 for an optimal subway route from the departure point A to the destination B at 10:00 tomorrow. The optimal route can be calculated in consideration of the time from the source to the destination and the congestion of the subway.

The predictive information calculation unit 140 analyzes the collected image data and accumulates the congestion data for the corresponding image in the database 130 (S430).

According to an embodiment of the present invention, the prediction information calculation unit 140 may calculate the frequency domain feature information in order to classify the congestion (e.g., passenger density) in the collected image data (e.g., Can be analyzed. The feature information analysis may be performed by analyzing the distribution of the spectral energy of Equation (1).

는 극좌표계에서의 원점으로부터의 각도 값이며 S(

)는 하기 수학식 2로부터 유도될 수 있다.In Equation (1), S is a spectral function

Is the angle value from the origin in the polar coordinate system and S (

) Can be derived from the following equation (2).

에 대한 함수로, r은 반지름,

는 각도 값으로 서로 독립적이다. 즉, 수학식 1은 극좌표계로 표현된 주파수 영역에서 반지름 r에 대한 marginal함수 값으로 각도에 대한 특성을 포함한다.In Equation (2), S is a value of r in the polar coordinate system

As a function of, r is the radius,

Are independent of each other as angle values. That is, Equation (1) includes a characteristic for an angle as a marginal function value with respect to a radius r in a frequency domain represented by a polar coordinate system.

The spectral function is a transformation method that utilizes characteristics that are easy to analyze in the frequency domain of an image when an image arrives.

는 특정 각도에서 함수값이 크게 나오는 특징을 보인다.In general,

Shows a characteristic in which a function value is greatly increased at a certain angle.

5 is a view for explaining a specxture of an image according to an embodiment of the present invention.

FIG. 5 is a diagram comparing the specxture of an image of a matchstick placed in an orderly manner and the image of a matchstick in a non-matchstick. Fig. 5 (a) shows an irregularly arranged matchstick, Fig. 5 (b) shows regularly arranged matchstick images, and Figs. 5 (c) and 5 (d) show images in respective frequency regions.

6 is a graph showing the values for the radius and angle for FIG.

The result of the row of FIG. 6 (a) is the result of the image of FIG. 5 (a) and the result of the row of FIG. 6 (b) is the result of the image of FIG. is. That is, as can be seen from FIG. 6, in the case of an image obtained by refining a matchstick, there is a characteristic having a peak value at a specific angle in the specxture for the angle. This feature allows extracting features in an image.

Depending on the density of the passengers, CCTV specxture can have some characteristics. With this feature, congestion can be quantified by classification according to density.

Adaboost is available as a technique for classifying the feature distribution calculated in Equation (1). The Adaboost algorithm classifies features by linear combination of weak classifiers that output a binary result as a feature classification method when a feature value arrives. Here, the term weak classifier refers to a classifier that distinguishes two spaces through a single line in a space where features exist.

7 is a diagram for explaining a technique used for calculating congestion among path information providing methods related to an embodiment of the present invention.

FIG. 7 shows a process in which a weak classifier is classified in a space where features are distributed. In the case of Fig. 7 (a), when one line is defined, the two spaces are divided and the characteristic is distinguished through one line again in Fig. 7 (b). As shown in FIG. 7 (c), finally differentiates the features through several weak classifiers. Multi-class Adaboost is a method to classify two or more features in the above space.

는 m번째 weak classifier의 가중치 값을 의미하며 k는 class의 색인 값을 나타낸다. 수학식 3은 multi-class Adaboost에 대한 수식을 나타내며 분류 과정은 도 8과 같이 나타낼 수 있다. In Equation (3), T denotes a weak classifier and M denotes a total number of weak classifiers.

Denotes the weight value of the mth weak classifier, and k denotes the index value of the class. Equation (3) represents an equation for multi-class Adaboost, and the classification process can be expressed as shown in FIG.

Multi-class Adaboost is an algorithm for quickly classifying multiple classes. It constructs a strong classifier through a combination of weak classifiers to perform classification of features accurately and quickly.

The concept of the Adaboost algorithm is that a weak classifier is a process that classifies a result roughly inaccurately and roughly, and then delicately distinguishes the features through a weakly connected classifier. In other words, it is possible to save time by categorizing roughly from the beginning, without performing many calculations at once to sort out the results, and to improve the accuracy through the cascade structure.

8 is a diagram for explaining the concept of the Adaboost algorithm related to an embodiment of the present invention.

In this embodiment, the flow of the Adaboost algorithm is made up of four strong classifiers, and very low, low, high and very high classes are classified according to the density distribution in a total of four classes.

Each strong classifier is composed of several weak classifiers in cascade form, as described above. That is, in Equation (3), k denotes a class value for four density distribution states. A congestion level can be assigned to each class to be used later for statistical estimation. The number of classes can be added according to circumstances. The more classes, the more granular the value of the congestion can be identified, but the processing speed can be slowed down and the accuracy of the classification can also be reduced.

The predictive information calculation unit 140 may calculate the congestion prediction information at a specific future point in consideration of the congestion degree data calculated through Equation (3) and the time point at which the user requests the route guidance information at step S440.

The congestion data may include not only congestion but also time and place data. The path information providing system 100 may analyze the accumulated congestion data to estimate a congestion degree at a desired place and a desired place. The congestion prediction information obtained by this method is the data for suggesting the route with the least congestion at the corresponding time from the start point to the destination point.

The information for determining the public transport route at the time of departure must necessarily be predictive data (or predictive information). The periodicity from the past can be analyzed to estimate the congestion at the future point. Assuming that things happening in the same situation will occur similarly in the future, the congestion data, including the time / location metadata, allows to estimate the congestion at the time / place to represent similar future situations. The data observed at regular intervals along with the passage of time is called time series data.

The prediction information calculation unit 140 may collect the congestion in the form of time series data and store the collected congestion in the database 130.

There will be certain patterns during weekdays where the cyclical use patterns of commuters and scholars, who are public transportation users, are expected, and the long-term periodicity of visitors who will meet the characteristics of each time point on weekends or holidays will appear. Techniques that can measure congestion at appropriate points in time can be essential data for predicting future congestion prediction information.

The prediction information calculating unit 140 can estimate the future congestion degree using the following equation (4).

The generalization of Equation (4) can be expressed as Equation (5) below.

Where a is a smoothing constant that determines the proportion of variables at each point in time. a has a value between 0 and 1. Also, X _t is the congestion actually calculated through the acquired image data at the time t, and S _t is the predicted future congestion at the future time t.

As can be seen from Equation (4), the predicted value S _t can be expressed as a function of all time series values before t. In addition, due to the smoothing constant a, the influence of the time series value far from the t point is less influenced, and the influence of the nearby time series value is greatly influenced, thereby reflecting the latest trend. In the embodiment of the present invention, the congestion degree of the future is predicted by considering the variability of the congestion degree in the subway using this method. The more a trend has less effect, the closer to zero.

9 is a graph illustrating a movement path of a specific user in the path information providing method according to an embodiment of the present invention. Fig. 9 is a graph showing a case where a person K goes from the departure place to the destination on the 24th.

The time of departure for person K is before 10:00, the time when train arrives at A station. Therefore, the required data is the predicted congestion of station A to E.

10 shows a predicted congestion graph associated with an embodiment of the present invention.

FIG. 10 is a graph that predicts the congestion at 10:00 on the 24th day A based on past data. The path information providing system 100 can know the tendency from the past time series data through Equation (5), and predict the congestion degree of the coming train with the tendency.

The transmission unit 150 may provide route guidance information at a specific future point determined using the predicted congestion prediction prediction information as shown in FIG. 10 to the user terminal (S450).

Next, the process of determining a recommendation route suggested to users by using the prediction data will be described.

Let's suppose that the trends of the collected data over the past hour are obtained and the expected congestion of each cell at A, B, and C stations is obtained as follows. Table 1 below shows the expected congestion at 10:00 A station, Table 2 is the expected congestion at 10:02 A station, and Table 3 is the expected congestion at 10:05 A station. The shaded cell in Tables 1 to 3 below means the closest cell to the transfer passage in the next station.

1 car 2 cars 3 cars 4 cars 5 cars 6 cars 7 cars 8 cars 50 55 58 63 62 60 59 56

1 car 2 cars 3 cars 4 cars 5 cars 6 cars 7 cars 8 cars 51 52 54 58 58 61 63 60

1 car 2 cars 3 cars 4 cars 5 cars 6 cars 7 cars 8 cars 48 52 54 56 58 62 64 62

If you have an empty seat and you have a comfortable car with a degree of congestion that you can go to, there is a good chance you will have to stand in all the squares of the tank, It can have a significant impact on discomfort. Therefore, not only the congestion of station A, which is the boarding point, but also the fluctuation of congestion in B, C, and D, which are going through in the moving process, can be taken into account, so that the recommended route can maximize the comfort of the upright passenger.

Based on the above expected data, the average and standard deviation of the congestion for each column of the train from station A to station D can be obtained as shown in Table 4.

1 Hokan 2 hokan 3 hokan 4 Hokan 5 Hokan 6 Hokan 7 Hokan 8 Hokan Average congestion 49.67 53 56 59 59.33 61 62 58.67 Weighted
Average congestion 59.6 63.6 67.2 70.8 71.2 73.2 74.4 70.4 Standard Deviation 1.52 1.73 2.3 3.6 2.31 One 2.65 3.06 Weighted
Standard Deviation 1.06 1.21 1.61 2.52 1.62 0.7 1.86 2.14

, 예상 혼잡도의 평균에 대한 표준편차를

라고 한다. 제일 쾌적한 칸을 안내하기 위해서는 단순히 C_n가 제일 작은 칸을 안내하면 안된다. A정거장에서 C_n가 최소여도 B, C를 거쳐 D정거장에 도착했을 때 C_n가 최소가 아닐 수 있기 때문이다.The average of the expected congestion levels obtained in Table 4 is C _n

, The standard deviation of the mean of the expected congestion

. In order to guide the most comfortable space, you should not simply guide the space where C _n is the smallest. When C _n arrive at the station D via the minimum even B, C from the A station it is because the C _n may not be a minimum.

를 이용하였다.C_n,

모두 수치가 적으면 적을수록 이상적이게 된다. Therefore, when passing through several stops, the passengers should take into account the variability of their spaces when guiding them. In the present embodiment, the indexes of the " congestion degree " as the train travels through the stations are indicated as A, B, and C stations

Were used. C _n ,

The smaller the number, the more ideal it becomes.

을 같은 비중으로 다루면 안된다.

은 C_n에 비해 2차적인 판단 기준이기 때문이다. 따라서 본 발명의 일실시예에 의한 경로 정보 제공 시스템(100)은

와 C_n의 비중을 다르게 두고 이 두 가지의 지표를 이용하여 승객들에게 가장 쾌적한 루트를 제공할 수 있다. 표 4에서의 Weighted 혼잡도 평균은 혼잡도의 평균에 1.2를 곱하고, Weighted 표준편차는 표준편차에 0.6을 곱한 값이다.However, as C _n,

Should not be treated as equal.

Is a secondary criterion compared to C _n . Therefore, the path information providing system 100 according to the embodiment of the present invention

And C _n are different from each other, it is possible to provide the most comfortable route to passengers by using these two indicators. The Weighted Congestion Average in Table 4 is the average of the Congestion Factor multiplied by 1.2, and the Weighted Standard Deviation is the standard deviation multiplied by 0.6.

와 C_n는 적으면 적을수록 좋다. 본 실시예에서는 이를 위해 Weighted된

와 C_n의 그래프에서 벡터 거리,

을 이용하였다.

의 값이 작을수록 해당

번째 칸의

와 C_n의 수치가 적은 것이기 때문이다.As described above,

And C _n are as small as possible. In this embodiment,

And C _n ,

Was used.

The smaller the value of

Column

And C _n are small.

의 값이 제일 적으므로,

과 C_n를 고려하였을 때 다른 칸에 비해 1번째 칸이 제일 유력하게 승객에게 안내가 될 것이다.11 is a graph of data used to calculate congestion prediction information in the path information providing method according to an embodiment of the present invention. 11,

Since the value of < RTI ID = 0.0 >

And C _n , the first column will be the most likely guide to passengers compared to the other one.

The route information providing system 100 may consider a box close to the transfer passage when finally providing the route to the passenger. This is because if you do not consider the transfer box, you can provide a route that you must walk too much. The gait speed can also be used as a factor with a certain weight in calculating the optimal route. It is possible to calculate the walking speed of the user by using the user's GPS data or the indirect data to provide a route for moving to a comfortable space, for example, 50 meters away from the transfer station.

The calculation method described below is a more simplified method of calculating the recommended path, and is a suitable method to be applied to the initial model. Weights are given to the use within the range of convenience of movement in the cell near the transfer passage, so that users can use a more comfortable space while minimizing the walking distance to move.

First, you can specify the allowable range for the transfer box. It can be designated as left and right + 2 columns based on the relevant transfer box. For convenience, this range is called range H. Table 5 shows an example in which the congestion degree is calculated by setting H (5th to 8th floors) based on the transfer station (No.7).

1 Hokan 2 hokan 3 hokan 4 Hokan 5 Hokan 6 Hokan 7 Hokan 8 Hokan Synthesis
Congestion 59.62 63.61 67.22 70.84 71.22 73.1 74.42 70.43

이제일 적어도, 범위

에서의 칸들 중에서 1호칸과

이 그리 차이가 나지 않는 칸이 있다면 오히려 범위

내의 객실을 안내해 주어야 승객들은 더 편히 목적지까지 갈 수 있게 된다. 따라서 "그리 크지 않은 차이"의 기준을 범위

내에서의

의 최대값과 최소값의 차이의 50%로 하였고, 이를 편의상, 혼잡 허용도(A)라고 호칭하기로 한다.1

Now at least, range

Among the cells in

If there is a space where this difference does not occur,

Passengers should be able to get to their destinations better. Therefore, the criteria of "not so great difference"

Within

(50%) of the difference between the maximum value and the minimum value of the congestion tolerance (A).

과 구간

내의

을 선택하는 부등식이다.Equation (6) is a formula for selecting a route guide in consideration of congestion tolerance,

And section

undergarment

Is an inequality to choose.

이

에

를 더한 값보다 작을 경우

와

의 혼잡도의 차이를

가 보상(compensate)해준다고 여기고, 승객에게는 구간

내의 객실로 안내를 할 수 있다. 반대로 경로 정보 제공 시스템(100)은

가

에

를 더한 값보다 클 경우 전체 칸에서 제일 적은

값을 가지는 칸을 안내해 준다. 비록 안내된 칸은 환승 객실과 다소 거리가 있지만, 그 거리를 쾌적함이 보상할 수 있다. 수학식 6을 K씨가 A역에서 D역까지 타고가는 지하철 객실 선택에 적용하면 수학식 7과 같이 나타낼 수 있다.Referring to Equation (6), the path information providing system 100

this

on

Is less than the sum of

Wow

The difference in congestion

The passenger is considered to compensate,

We can guide to guest room in. On the contrary, the path information providing system 100

end

on

Is greater than the sum of

Lead the space with the value. Although the guided spaces are somewhat distant from the transfer rooms, the comfort can compensate the distance. Equation (6) can be expressed as Equation (7) when K is applied to the selection of subway rooms that ride from A station to D station.

가

에

를 더한 값보다 크다. 이는 구간

안에 타서 환승 구간에 가까운 것 보다

이 제일 작은

, 즉 첫 번째 칸에 타서 D정거장까지 가는 것이 K씨에게 가장 쾌적하다 판단하는 근거가 된다. 이에 따라 경로 정보 제공 시스템(100)은 K씨에게 A정거장에서 D정거장까지 타는 열차의 객차를 안내해 줄 때에는 첫 번째 객실로 타라고 안내를 해주게 된다.As shown in Equation (7)

end

on

. This section

It is more convenient than getting near the transit section

This smallest

, That is, going to station D by getting in the first cell is the most comfortable basis for K. Accordingly, the route information providing system 100 instructs Mr. K to take the first cabin when he guides the carriage of the train from the A station to the D station.

In addition, the route information providing system 100 guides the user through the above-described algorithm to determine the number of the spaces to be taken when the train to the destination E station is changed after changing at the D station.

According to an embodiment of the present invention, an algorithm for suggesting a recommended path using predicted data may be various.

For example, as shown above, the transfer range H may be specified and a weight may be given to provide a closer space. In a more informed navigation, the gait speed may be calculated, And provide the congestion per cell, so that the user can make a choice. Specifically, an electric car "a" that can be caught by walking a little bit (8 km per hour) can ride with a congestion of 70, but can walk slowly and walk 50 m from the easy-to- You can sit in a congestion 30 seat and go to your destination 5 minutes late.

An embodiment of the present invention can provide a method of extracting congestion time series data of a public subway using an image analysis technique and establishing a basis for producing congestion public data and predicted data.

As described above, the route information providing method according to an embodiment of the present invention provides a route through which a public transportation user can comfortably and safely arrive at a destination beyond a simple arrival scheduled service.

According to one embodiment of the present invention, it is possible to more efficiently operate public transportation by preventing safety accidents caused by crowded crowded customers, and to provide information useful for station and station construction, . ≪ / RTI >

In addition, according to an embodiment of the present invention, prediction information can be provided to a user by being applied to various fields including movement of objects such as department stores, parking lots, as well as public transportation.

The path information providing method described above can be implemented in the form of a program command that can be executed through various computer means and recorded on a computer-readable recording medium. At this time, the computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. On the other hand, the program instructions recorded on the recording medium may be those specially designed and configured for the present invention or may be available to those skilled in the art of computer software.

The computer-readable recording medium includes a magnetic recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical medium such as a CD-ROM and a DVD, a magnetic disk such as a floppy disk, A magneto-optical media, and a hardware device specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

The recording medium may be a transmission medium such as a light or metal line, a wave guide, or the like including a carrier wave for transmitting a signal designating a program command, a data structure, and the like.

The program instructions also include machine language code, such as those generated by the compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

The above-described path information providing method and system are not limited to the configuration and method of the above-described embodiments, but the embodiments may be modified such that all or some of the embodiments are selectively And may be configured in combination.

100: Path information providing system
110:
120: collecting section
130: Database
140: prediction information calculating unit
150:
160:

Claims (5)

Receiving a user request for route guidance information at a specific future time from a user terminal;
Collecting image data for a specific region at predetermined time intervals;
Calculating congestion prediction information at a specific future time point using the collected image data and considering the user request reception time point;
And providing route guidance information at the specific future time point to the user terminal using the calculated congestion degree prediction information,
Wherein the congestion degree prediction information calculation step includes analyzing a frequency domain characteristic of the collected image data and the characteristic analysis of the frequency domain is performed using Equation 1 and Equation 2: Information delivery method.
[Equation 1]

&Quot; (2) "

(Where S is the spectral function < RTI ID = 0.0 >

Is the angle value from the origin in the polar coordinate system and S (

) Is derived from the following equation (2), and S in the equation (2) is derived from r in the polar coordinate system

As a function of, r is the radius,

Are independent of each other as angle values.) The method of claim 1, wherein the congestion degree prediction information calculation step
Collecting congestion in the form of time series data; And
And calculating congestion degree prediction information at the specific future time point using the collected congestion degree. 3. The method of claim 2, wherein the congestion degree prediction information calculation step
Further comprising the step of calculating the congestion degree prediction information at the specific future time point by assigning a larger weight to the congestion degree at the latest time point. 4. The method of claim 3, wherein the congestion prediction information comprises
And calculating the average value of the congestion degree and the standard deviation value in the specific area. 4. The method according to claim 3, wherein the route guidance information providing step
And providing the route guidance information at the specific future time point to the user terminal by further using the location of the transfer point.

Images