KR20100132762A - Path prediction apparatus and method - Google Patents

Abstract

PURPOSE: A path prediction apparatus and a method thereof are provided to predict the path of a mobile object by extracting the path prediction hit rate. CONSTITUTION: A situation information acquisition unit(110) acquires the current situation information about a mobile object. A current information generator(120) creates the current information including the moving path information of the mobile object and the current situation information. A search unit(140) extracts the previous information corresponding to the current situation information. Based on the extracted previous information and generated current information, a moving path prediction unit(150) predicts the moving path about the mobile object.

Description

PATH PREDICTION APPARATUS AND METHOD}

The disclosed technique relates to a path prediction apparatus and a path prediction method.

With the development of mobile devices such as mobile phones, smartphones and PDAs, mobile devices provide various services such as telephone, music or movie watching, internet, games and photography. In addition, by providing a GPS chip in the mobile device, the service to inform the location of the mobile device is also provided, combining the mobile device with LBS (Location Based Services) using GPS information, active research into technology to provide a variety of services It is becoming.

Among the embodiments, the path prediction apparatus may include a situation information obtaining unit obtaining current situation information on a moving object, a current information generating unit generating current information including the current situation information and current moving path information of the moving object; A retrieving unit for retrieving previous information, the previous information including previous situation information and previous moving path information of the moving object, and extracting previous information corresponding to the current situation information, and the extracted previous information and the generation Based on the current information, the moving path prediction unit for predicting the moving path for the moving object.

In embodiments, the method for predicting a route may include: acquiring current context information about a moving object, generating current information including the current context information and current movement path information of the moving object, previous information—the previous information Includes previous situation information and previous movement path information of the moving object to extract previous information corresponding to the current situation information, and based on the extracted previous information and the generated current information, Predicting a moving path for the moving object.

The description of the disclosed technique is merely an example for structural or functional explanation and the scope of the disclosed technology should not be construed as being limited by the embodiments described in the text. That is, the embodiments may be variously modified and may have various forms, and thus the scope of the disclosed technology should be understood to include equivalents capable of realizing the technical idea.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

When a component is referred to as being "connected" to another component, it should be understood that there may be other components in between, although it may be directly connected to the other component. On the other hand, when a component is said to be "directly connected" to another component, it should be understood that there is no other component in between. On the other hand, other expressions describing the relationship between the components, such as "between" and "immediately between" or "neighboring to" and "directly neighboring to", should be interpreted as well.

Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "include" or "have" refer to features, numbers, steps, operations, components, parts, or parts thereof described. It is to be understood that the combination is intended to be present, but not to exclude in advance the possibility of the presence or addition of one or more other features or numbers, steps, operations, components, parts or combinations thereof.

Each step may occur differently from the stated order unless the context clearly dictates the specific order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. Terms defined in commonly used dictionaries should be interpreted to be consistent with meaning in the context of the relevant art and can not be construed as having ideal or overly formal meaning unless expressly defined in the present application.

1 is a block diagram illustrating a configuration of a path prediction apparatus according to an embodiment of the disclosed technology.

Referring to FIG. 1, the path predicting apparatus 1000 may include the situation information obtaining unit 110, the current information generating unit 120, the storage unit 130, the searching unit 140, and the moving path predicting unit 150. Include.

The contextual information obtaining unit 110 obtains current contextual information about the moving object. Here, the moving object may be a user who owns the path prediction apparatus 1000. For example, the current situation information may include information on at least one mobile device around the moving object and information on a moving start time of the moving object.

The current information generation unit 120 generates current information including the current situation information acquired by the situation information acquisition unit 110 and current movement path information of the moving object. Here, the current movement path information means movement trajectory information according to the time of the moving object, and may include a combination of the position information of the moving object and the elapsed time from the moving start time of the moving object. Here, the location information of the moving object may be received via a GPS signal or a location tracking service using a base station. In addition, the elapsed time may be generated using a built-in timer or may be generated using time information received from a base station.

The storage unit 130 stores previous information including previous situation information and previous moving path information of the moving object. Here, the previous information may be information previously generated by the current information generator 120. For example, the previous situation information may include information about at least one mobile device around the moving object and information about a start time of the moving object.

The searcher 140 searches for previous information stored in the storage 130 and extracts previous information corresponding to the current situation information acquired by the situation information acquirer 110. For example, the searcher 140 may search for previous information and extract previous information including mobile device information corresponding to the information about the mobile device obtained by the situation information acquirer 110. .

The movement path predictor 150 predicts a movement path for the moving object based on the previous information extracted by the searcher 140 and the current information generated by the current information generator 120. For example, the movement path predictor 150 may determine the similarity between the current movement path information of the moving object and the previous movement path information according to the extracted previous information, and the start point of the movement of the moving object and the extracted previous information. Considering the similarity between the start points of movement, the previous information most similar to the current information can be determined. The movement path predictor 150 may predict the movement path information according to the most similar previous information as the movement path of the moving object.

FIG. 2 is a block diagram illustrating a configuration of the situation information obtaining unit of FIG. 1.

Referring to FIG. 2, the contextual information acquisition unit 110 includes a mobile device information acquisition unit 210 and a viewpoint information acquisition unit 220.

The mobile device information acquisition unit 210 obtains information on at least one mobile device around the moving object. For example, the mobile device information acquisition unit 210 may communicate with the mobile device through short range wireless communication such as Bluetooth, UWB, ZigBee, IrDA, and acquire identification information of the mobile device located in the vicinity. For example, the identification information of the mobile device may be a unique address BD_ADDR of the Bluetooth device when the mobile device includes the Bluetooth device.

The viewpoint information acquisition unit 220 acquires information on a movement start time point of the moving object. For example, the viewpoint information acquisition unit 220 may acquire information about a movement start time of the moving object by using a built-in clock or using time information received by the base station. Herein, the movement start time may be displayed as a time of 'hours and minutes'.

Equation 1 below is an equation for describing an example in which the current information generator of FIG. 1 generates current information.

Here, the information of the mobile device included in the current situation information is ID1, ID2, the moving start time of the moving object is start_time, and the combination of the position information of the moving object and the elapsed time from the moving start time of the moving object is (p0). , 0), (p1, t1)... (pn, tn).

According to Equation 1, the current information generating unit 120 has ID1 and ID2 located around the moving object, the moving object starts moving at the start_time time point, first starts moving at p0, and the moving object starts time. Generates current information that the point p1 has passed when t1 has elapsed and that it has passed the point pn when time tn has elapsed.

Equation 2 below is an equation for explaining an example in which the movement path predictor of FIG. 1 calculates a similarity between the current information and the extracted previous information.

Here, PathSim (p, q) is the similarity between the current information p and the previous information q, w is a weight having a value of 0 or more and 1 or less, and DTW (p, q) is the current information (p). The path similarity calculated by the dynamic time warping between the moving path of the moving path and the moving path of the previous information (q), and TimeSim is the starting point of the moving object and the previous information (q) according to the current information (p). Similarity between the starting points of movement of the moving object.

According to Equation 2, the movement path predicting unit 150 calculates a path similarity DTW according to a dynamic matching method for the movement path of the current information p and the movement path of the previous information q, and applies the current information to the current information. The timing similarity (TimeSim) between the movement start time and the movement start time according to the previous information is calculated. Calculate

3 is a block diagram illustrating a configuration of a moving path predictor of FIG. 1.

Referring to FIG. 3, the movement path predictor 150 includes a path similarity calculator 310, a timing similarity calculator 320, a similarity calculator 330, and a path predictor 340.

The path similarity calculator 310 calculates a path similarity that is a similarity between the current moving path information of the moving object included in the current situation information and the previous moving path information of the moving object included in the extracted previous information. Here, the path similarity may indicate how similar points are included between the current travel path and the previous travel path. For example, the path similarity calculator 310 may calculate path similarity using a dynamic time warping on the current moving path and the previous moving path.

The timing similarity 320 is a moving start time point (hereinafter referred to as a first time point) of the moving object included in the current situation information and a moving start time point (hereinafter referred to as a second time point) of the moving object included in the extracted previous information. Calculate the timing similarity, which is the similarity between. For example, the timing similarity 320 may make the inverse of the difference between the first time point and the second time point as the timing similarity.

The similarity calculator 330 calculates the similarity between the current information and the previous information by using the path similarity and the timing similarity. For example, the similarity calculator 330 may calculate the similarity by multiplying the path similarity and the timing similarity by a predetermined weight and adding the path similarity and the timing similarity in which the predetermined weight is reflected.

The path predicting unit 340 compares the similarity calculated by the similarity calculating unit 330, and predicts a path of the moving object by referring to previous information generating the largest similarity. For example, the path predictor 340 may predict the previous moving path of the previous information that generates the largest similarity as the path of the moving object that is currently moving.

4 is a flowchart illustrating a path prediction method according to an embodiment of the disclosed technology.

Referring to FIG. 4, in operation 410, the path prediction apparatus obtains current situation information about a moving object. For example, the moving object may be a user having a route prediction device. For example, the current situation information may include information on at least one mobile device around the moving object and information on a moving start time of the moving object.

In operation 420, the path prediction apparatus generates current information including current situation information and current moving path information of the moving object. Here, the current movement path information means movement trajectory information according to the time of the moving object, and may include a combination of the position information of the moving object and the elapsed time from the moving start time of the moving object. Here, the location information of the moving object may be received via a GPS signal or a location tracking service using a base station. In addition, the elapsed time may be generated using a built-in timer or may be generated using time information received from a base station. For example, the path prediction apparatus may generate current information as shown in Equation 1 below.

In operation 430, the route prediction apparatus searches for stored previous information and extracts previous information corresponding to the current situation information. For example, the route prediction apparatus may search for the previous information and extract the previous information including the mobile device information corresponding to the information about the mobile device included in the current situation information.

In operation 440, the path prediction apparatus calculates a similarity between the previous information and the current information with respect to all the extracted previous information. For example, the path predicting apparatus may include a similarity between the current moving path information of the moving object and the previous moving path information according to the extracted previous information, and the starting point of the moving object and the starting point of the moving object according to the extracted previous information. The similarity between the two may be calculated, and weighted values may be added to each similarity and then added to calculate the similarity between the extracted information and the current information. That is, the path prediction apparatus may calculate the similarity according to Equation 2.

In operation 450, the path predicting apparatus predicts a path of the moving object by referring to previous information that generates the largest similarity among the similarities calculated in operation 440. For example, the path prediction apparatus may predict the previous moving path of the previous information that generates the largest similarity as the path of the moving object that is currently moving.

The disclosed technique may have the following effects. It is to be understood, however, that the scope of the disclosed technology is not to be construed as limited thereby, as it is not meant to imply that a particular embodiment should include all of the following effects or only the following effects.

The apparatus for predicting a route according to an embodiment may improve the prediction speed by identifying a mobile device located near the moving object, extracting previous information having a high hit rate from the previous information, and predicting the path of the moving object.

The path prediction apparatus according to an embodiment may improve the accuracy of the path prediction by predicting the path of the moving object in consideration of not only the similarity of the moving path information, but also the similarity of the departure time of the moving object.

Although described above with reference to a preferred embodiment of the present invention, those skilled in the art will be variously modified and changed within the scope of the invention without departing from the spirit and scope of the invention described in the claims below I can understand that you can.

1 is a block diagram illustrating a configuration of a path prediction apparatus according to an embodiment of the disclosed technology.

FIG. 2 is a block diagram illustrating a configuration of the situation information obtaining unit of FIG. 1.

3 is a block diagram illustrating a configuration of a moving path predictor of FIG. 1.

4 is a flowchart illustrating a path prediction method according to an embodiment of the disclosed technology.

Claims (14)

A situation information obtaining unit obtaining current situation information on the moving object; A current information generator configured to generate current information including the current situation information and current movement path information of the moving object; A retrieval unit configured to retrieve previous information, the previous information including previous situation information and previous movement path information of the moving object, and extract previous information corresponding to the current situation information; And And a moving path estimator for predicting a moving path for the moving object based on the extracted previous information and the generated current information. The method of claim 1, wherein the moving object And a user possessing the path prediction device. The method of claim 1, wherein the current situation information is And information on at least one mobile device around the moving object and information on a start point of the movement of the moving object. The method of claim 3, wherein the search unit And searching for the previous information to extract previous information including information about a mobile device corresponding to at least one mobile device around the moving object. The method of claim 3, wherein the moving path predictor A path similarity calculator configured to calculate a path similarity which is a similarity between current moving path information of the moving object and previous moving path information of the moving object according to the extracted previous information; A timing similarity calculation unit configured to calculate a timing similarity which is a similarity between the movement start time of the moving object included in the current situation information and the movement start time of the moving object according to the extracted previous information; A similarity calculator which reflects a predetermined weight to the path similarity and the timing similarity, and adds the path similarity and the timing similarity reflecting the weight to calculate a similarity between the extracted previous information and the current information; And And a path predicting unit predicting previous moving path information based on the previous information having the greatest similarity as the moving path of the moving object. The method of claim 5, wherein the path similarity calculation unit And calculating the path similarity with respect to the current moving path of the moving object and the previous moving path of the moving object by using dynamic time warping. The method of claim 5, wherein the timing similarity calculation unit And the reciprocal of the difference between the start time of the movement of the moving object according to the current situation information and the start time of the movement of the moving object according to the extracted previous information as the timing similarity. Obtaining current situation information about the moving object; Generating current information including the current situation information and current moving path information of the moving object; Searching for previous information, the previous information including previous situation information and previous movement path information of the moving object, and extracting previous information corresponding to the current situation information; And Predicting a moving path for the moving object based on the extracted previous information and the generated current information. The method of claim 8, wherein the moving object Path prediction method characterized in that the user possessing the path prediction device. The method of claim 8, wherein the current situation information And information on at least one mobile device around the moving object and information on a start point of the movement of the moving object. The method of claim 10, wherein searching for the previous information and extracting previous information corresponding to the current situation information comprises: And searching for the previous information to extract previous information including information about a mobile device corresponding to at least one mobile device around the moving object. The method of claim 10, wherein estimating a moving path for the moving object based on the extracted previous information and the generated current information. Calculating a path similarity which is a similarity between current moving path information of the moving object and previous moving path information of the moving object according to the extracted previous information; Calculating a timing similarity which is a similarity between a moving start time of the moving object included in the current situation information and a moving start time of the moving object according to the extracted previous information; Calculating a similarity between the extracted previous information and the current information by reflecting a predetermined weight on the path similarity and the timing similarity, respectively, and adding the path similarity and the timing similarity to which the weight is reflected; And And predicting previous moving path information according to the previous information having the greatest similarity as the moving path of the moving object. 13. The method of claim 12, wherein calculating the path similarity And calculating the path similarity with respect to the current moving path of the moving object and the previous moving path of the moving object by using dynamic time warping. 13. The method of claim 12, wherein calculating the timing similarity And the reciprocal of the difference between the start time of the movement of the moving object according to the current situation information and the start time of the movement of the moving object according to the extracted previous information as the timing similarity.

Images