KR20160136906A - Moving pattern analysis system and method using point of interest - Google Patents

Abstract

The present invention relates to a moving pattern analysis system using a point of interest and a method for the same and, specifically, to a technique of analyzing a moving pattern of a user by using a beacon signal. To achieve the purpose of the present invention, according to an embodiment of the present invention, the moving pattern analysis system using the point of interest includes: a first analysis unit extracting a life pattern of the user based on position information of the user, which is collected in accordance with time; and a second analysis unit calculating point of interest (POI) based on the life pattern of the user, which is analyzed, and modeling a POI sequence based on the calculated POI. The moving pattern analysis system senses that a user breaks away from a route in which the user usually passes or senses wandering of the user, using the beacon signal. Especially, the moving pattern analysis system can grasp abnormality of the user using the beacon signal based on a usual moving pattern of the user.

Description

[0001] MOVING PATTERN ANALYSIS SYSTEM AND METHOD USING POINT OF INTEREST [0002]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system and method for analyzing a movement pattern using a point of interest, and more particularly, to a technique for analyzing a movement pattern of a user using a beacon signal.

The present invention is derived from the research conducted as part of the basic research projects of the future creation science department and the Korea Research Foundation [assignment number: 2013R1A1A2009556, title: Study on Healing Care Index Model and Healing Care System].

In recent years, beacons have been replaced by beacons in place of NFC (near field communication), which has attracted attention as a smartphone short range communication technology. Beacons use Bluetooth communication to transmit information, Communication technology.

Beacons can communicate with handsets (smart devices including smart phones) up to 50 m radius in the building, so instant guidance service or mobile coupon is provided when visitors enter a specific place or store where beacon is installed without having to tag the terminal And the use of a beacon terminal supporting low-power Bluetooth low energy (BLE) technology is advantageous in that the consumption of the smartphone battery is low. In addition, there is an error of several tens meters in the case of GPS, while a beacon can be precisely positioned up to about 5 cm. Thus, the introduction of beacon system is rapidly spreading around the world in recent years.

The beacon having these advantages not only provides a discount coupon for a user who enters the store as described above but also provides goods in a non-contact manner, provides various baseball use information to visitors who visited the baseball field, It is also used to provide services such as showing the boarding pass automatically when passengers approach the departure gate at the airport, and a number of patent applications related thereto have been made.

For example, Korean Patent Laid-Open Publication No. 2014-0097074 (published on August 31, 2014) provides a push message to a customer's smartphone when a customer passes through a restaurant, (Published on 2012.09.13.) Will automatically provide various benefits when a user visits a franchisee, and the benefits provided by such benefits Based automated order payment technology that allows users to order and pay for a menu directly from their smartphone.

In recent years, crimes such as kidnapping or molestation for children and women have been raised as social issues, and these crimes are mainly in the blind spot and late return, but there are many crimes in bright daylight. Therefore, each local government is trying to eliminate the blind spot by installing more CCTV, but CCTV installation is limited to protect the safety of children and women.

Accordingly, the caregivers of children and women are demanding more reliable and safer measures, and various proposals for relief home services have been made in response to these demands. However, it is difficult to precisely grasp the situation of the protected person because the conventional technologies related to the relieved home service provide the service using only the location information of the protected terminal. Especially, in case of a sudden crisis such as kidnapping, There is a drawback.

Accordingly, there is a demand for a technology capable of immediately grasping a crisis situation or an abnormal situation of a target to be protected such as a child and a woman.

Korean Laid-Open Patent Application No. 2014-0097074 (published on Aug. 20, 2014) Korea Open Patent No. 2012-0101244 (Publication date: 2012.09.13.)

The present invention relates to a moving pattern analysis system and method using point of interest, and more particularly, to a technique for analyzing a movement pattern of a user using a beacon signal.

The present invention aims at immediately grasping a crisis situation or an abnormal situation of a target to be protected such as a child and a woman.

It is an object of the present invention to detect whether a user is roaming or departing from an ordinary route by using a beacon signal.

An object of the present invention is to identify a user's abnormality by using a beacon signal based on a user's usual movement pattern.

The present invention models a movement pattern of a user using a means capable of measuring a position including a beacon (i.e., a location based service, a WiFi AP (access point), etc.) To be provided.

To achieve these and other advantages and in accordance with the purpose of the present invention, as embodied and broadly described herein, there is provided a system for analyzing movement patterns using points of interest, comprising a first analyzer for extracting a life pattern of a user based on position information of a user, And a second analyzer for calculating a point of interest (POI) based on the life pattern of the analyzed user and modeling the POI sequence based on the calculated point of interest.

At this time, the first analyzing unit divides the collected location information into predetermined reference unit areas, and determines the living area of the user in consideration of at least one of the time, frequency, weather, And the second analyzing unit can model the POI sequence by assigning a weight to the computed interest point in consideration of a time per unit time, and furthermore, the POI sequence can be modeled by time, Or the like.

In addition, the movement pattern analysis system using the point of interest according to an embodiment of the present invention may further include a determination unit for determining whether the user deviates the path based on the modeled POI sequence.

Here, the determination unit may compare the current location of the user based on the modeled POI sequence, determine that the user is roaming if the current location of the user is out of a predetermined error range, Compares the current location of the user based on the modeled POI sequence and determines at least one of a speed out of the path corresponding to the modeled POI sequence and a stay time at a position outside the predetermined error range for the path It is possible to determine whether the user is wandering.

Meanwhile, a method for analyzing a movement pattern using a point of interest according to an exemplary embodiment of the present invention includes extracting a life pattern of the user based on position information of a user collected over time, Calculating a point of interest (POI) with the calculated point of interest, and modeling the POI sequence based on the calculated point of interest.

In this case, the extracting step may include dividing the collected location information into predetermined reference unit areas, and considering at least one of the time, frequency, weather, and behavior of the user in each of the divided reference unit areas, And the modeling step may model the POI sequence by assigning a weight to the computed point of interest at a time that per unit time is taken into consideration, and further, the POI sequence may be modeled by time, Or the like.

In addition, the method for analyzing a moving pattern using a point of interest according to an embodiment of the present invention may further include determining whether the user leaves the path based on the modeled POI sequence.

Here, the determining may include comparing the current location of the user based on the modeled POI sequence, determining that the user is roaming if the current location of the user is outside a predetermined error range, Wherein the determining comprises comparing a current location of the user based on the modeled POI sequence, determining a rate of departure from a path corresponding to the modeled POI sequence, a staying time at a location outside a predetermined error range for the path, It is possible to determine whether the user is wandering by using at least one of them.

The present invention relates to a system and method for analyzing a movement pattern using a point of interest, and more particularly to a system and method for analyzing a movement pattern of a user using a beacon signal.

The present invention has an effect of promptly grasping a crisis situation or an abnormal situation of a target to be protected such as a child and a woman.

The present invention can detect whether a user is roaming or departing from a normal route by using a beacon signal. In particular, the beacon signal can be used to determine a user's abnormality based on a user's usual movement pattern.

The present invention extracts the life pattern of the user based on the location information of the user collected over time, calculates a point of interest (POI) based on the life pattern of the user, The POI sequence is modeled on the basis of the modeled POI sequence.

The present invention divides the collected location information of the user into predetermined reference unit areas and analyzes the living pattern by considering at least one of the time, frequency, weather, and behavior of the user in each of the divided reference unit areas Thereby, there is an effect that the movement pattern of the user can be analyzed.

The present invention has an effect of analyzing a movement pattern of a user by modeling a POI sequence by assigning a weight to a point of interest calculated in consideration of a time per unit time.

The present invention models a movement pattern of a user using a means capable of measuring a position including a beacon (i.e., a location based service, a WiFi AP (access point), etc.) Can be provided.

FIG. 1 is a diagram illustrating a schematic configuration of a movement pattern analysis system using points of interest according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a movement pattern analysis system using points of interest according to another embodiment of the present invention. Referring to FIG.
3 is a view illustrating an example of calculating a point of interest according to an embodiment of the present invention.
4 is a diagram illustrating a first process of modeling a POI sequence according to an embodiment of the present invention.
5 is a diagram illustrating a second process of modeling a POI sequence according to an embodiment of the present invention.
6 is a diagram illustrating a third process of modeling a POI sequence according to an embodiment of the present invention.
7 is a flowchart illustrating a fourth process of modeling a POI sequence according to an embodiment of the present invention.
8 is a flowchart illustrating a method of analyzing a movement pattern using a point of interest according to an embodiment of the present invention.
9 is a diagram schematically illustrating an example of providing a service that can be provided by using a movement pattern analysis system using a point of interest according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. In the following description of the embodiments of the present invention, specific values are only examples.

The present invention relates to a system and method for analyzing a movement pattern using a point of interest, and more particularly to a system and method for analyzing a user's life pattern using a beacon signal, , Point of Interest) to detect whether a user is wandering or departing from a route that the user normally travels.

FIG. 1 is a diagram illustrating a schematic configuration of a movement pattern analysis system using points of interest according to an embodiment of the present invention.

Referring to FIG. 1, a movement pattern analysis system 100 using a point of interest according to an embodiment of the present invention may include a processor 130, and the processor 130 may include a first analysis unit 110 and a second analysis unit 120. [ 2 analyzer 120. The analyzer 120 may be a microcomputer.

The first analysis unit 110 may extract the life pattern of the user based on the location information of the user collected over time.

In this case, the first analysis unit 110 may collect wearer's position information according to time using a wearable beacon. The wearable beacon refers to a beacon that can be worn on the body of a user. The wearable beacon includes a low power Bluetooth , Bluetooth Low Energy), and can be implemented as a band type, a nameplate type, an attachment type (such as a shoe or hair clip).

In this case, the wearable beacon may further include a three-axis acceleration sensor and a gyro sensor. The first analysis unit 110 may use the three-axis acceleration sensor, the gyro sensor, or the like provided in the wearable beacon, The life pattern can identify the behavior the user is currently doing (e.g., walking, running, standing, sitting, sitting in a vehicle, etc.).

In addition, the first analysis unit 110 may calculate not only the location information of the user (in particular, the location coordinate information) but also the weather, temperature, behavior, frequency, time of point Tp, (Ts), time during stay, and so on. The present invention may further comprise sensors (e.g., temperature sensors, humidity sensors, etc.) corresponding to each function in order to collect such information, in addition to the wearable beacon.

Meanwhile, FIG. 9 is a view schematically showing an example of providing a service that can be provided by using a movement pattern analysis system using a point of interest according to an embodiment of the present invention.

Referring to FIG. 9, for example, the movement pattern analyzing system 100 using an interest point according to an embodiment of the present invention may further include an information collecting unit (not shown) Various data related to the user can be acquired from the BLE (Bluetooth Low Energy) wearable beacon 900 and stored (S910).

At this time, the user-related data stored in the collecting unit includes not only information acquired from the wearable beacon 900 (for example, direction, angular velocity, battery remaining amount information of the wearable beacon, etc.) Information (i.e., information on the ambient temperature, humidity, CO ₂ , illuminance, and the like). Also, in order to obtain more precise user location information, a CCTV camera 902 capable of detecting a beacon signal or a beacon AP (Access Point) 903 supporting BLE may be used in the present invention. Information acquired from the camera 902 or the beacon AP 903 (i.e., image information, advertisement packet information received from a plurality of beacons, beacon AP ID information, major information, minor information, RSSI (Received Signal Strength Indication, etc.) can also be stored.

Then, the movement pattern analysis system 100 can extract the life pattern of the user based on the collected information as described above. Further, the user's movement path (POI sequence) can be calculated using the point of interest calculation method proposed in the present invention Can be modeled. A more detailed description thereof will be described later.

The system 100 of the present invention provides the analyzed information (in particular, the modeled POI sequence information and the determination result information of the departure or absence) to the user's parent terminal (smart phone, PC, etc.) together with the current real- (S920).

Accordingly, the guardian of the user can monitor the user's real-time position (at this time, not only the current position but also the past travel path can be monitored), the indoor environment information (temperature, humidity, CO2, Monitoring activity information of the user through the beacon position change amount and various sensor information in the beacon (that is, the information using the acceleration sensor, the gyro sensor, direction information, etc.) It is possible to receive a notification message of the occurrence of the situation, and it is possible to immediately recognize the emergency situation or the like. In particular, the guardian can recognize that an error has occurred to the user when the user to be at a specific position at a specific time is in another place. In this case, the protector may be a parent of the user, or a person who is set to contact first when a user is in an emergency situation, or if the user is a dementia patient, a bruising patient, etc., Lt; / RTI >

Although the BLE beacon is used as an example in the general description of the present invention including the above embodiments, the present invention is not limited thereto. The WiFi access point (AP) Technology or the like can be used to detect whether or not the user is leaving. Various modifications and variations may be made thereto by those skilled in the art to which the present invention pertains.

1, the first analyzer 110 divides the collected location information into predetermined reference unit areas, and stores at least one of the time, frequency, weather, and behavior of the user in each of the divided reference unit areas The living pattern can be analyzed in consideration of the above.

At this time, the first analysis unit 110 may divide the total travel route moved by the user based on the collected location information into the reference unit areas (for example, 20 m distance on the road on the map) Clustering the collected information (i.e., staying time, frequency, weather, behavior information, etc.) for each divided region can be performed.

Clustering refers to an analysis technique of grouping objects or objects into a plurality of clusters so that objects having similar characteristics are grouped together by similarity or distance. For example, the location information of the user collected by the first analysis unit 110 can be divided into 20 m distance units based on the road on the map, and the time, frequency, weather, And the like can be grouped together. In this case, dividing each region by 20 m is an example, but the present invention is not limited thereto, and it may be divided into other criteria such as 50 m and 100 m.

The second analyzing unit 120 calculates a point of interest (POI) based on the life pattern of the user analyzed by the first analyzing unit 110, and models the POI sequence based on the calculated point of interest do.

At this time, when calculating the point of interest, the second analysis unit 120 may use the clustered information based on the position information and the staying time information. The second analysis unit 120 may calculate the point of interest based on the information previously input from the user, or may calculate the point of interest (for example, time data collected at a period of time (hour, day, weekly, month, day, season, etc.). At this time, in the case of the former case (when the point of interest is calculated using the information previously inputted from the user), it means that the user sets the initial center of gravity point of the cluster in advance. In the latter case (when the point of interest is calculated using the data collected for a predetermined period of time), the second analysis unit 120 stores the information on the long staying time, the location information, and the frequency information in each divided area By assigning a weight based on the point of interest, the point of interest can be calculated.

In addition, the second analyzer 120 may observe the behavior of the user stochastically using a HMM (Hidden Markov Model), and may calculate a point of interest based on the behavior.

3 is a view illustrating an example of calculating a point of interest according to an embodiment of the present invention.

Referring to FIG. 3, the second analyzer 120 may calculate a point of interest by assigning weights to the divided regions using the time, location information, and frequency information. For example, let's say that a user goes to work on a day-to-day basis, leaves the house in the morning, crosses a crosswalk, crosses an overpass, arrives at the company, works at a company, and returns home after work.

At this time, the first analysis unit 110 can divide the path from the home before going home to the home returning home to a reference distance of 20 m, and it can be confirmed that the divided path is divided into six regions in total . At this time, more specifically, the area staying in the house before work, the area passing through the crosswalk, the area passing through the overpass is the third area, the area staying in the company is the fourth area, The area is the fifth area, and the area of the house which is returned home after work is the sixth area.

Next, in order to calculate the point of interest (POI), the second analyzing unit 120 may calculate the total stay time per unit time for each area of the divided path, thereby giving different weights to the respective areas . For example, the time remaining in the first area 301 is 4 hours, the time remaining in the second area 302 is 5 minutes, the time remaining in the third area 303 is 8 minutes, the time remaining in the fourth area 304 The time for staying in the fifth area 305 is 15 minutes, and the time for staying in the sixth area 306 is 5 hours, a high weight can be given to the area where the staying time is large. That is, the second analyzing unit 120 can calculate the area exceeding one hour (i.e., the first area, the fourth area, and the sixth area) as a very significant point of interest, and if the staying time exceeds 30 minutes The second region, the third region, and the fifth region) can be calculated as a normal point of interest.

In other words, the second analyzing unit 120 may assign different weights to the divided regions in consideration of the time spent per unit time, the frequency, and the like, That is, a very significant point of interest, a meaningful point of interest, or a point of common interest). The reference value of importance for the point of interest may be preset by the user or the order of importance of the point of interest may be automatically calculated by using an average of the calculated values. The above example is only one embodiment, but the present invention is not limited thereto, and various modifications are possible

The second analysis unit 120 may model the POI sequence based on the calculated point of interest. In this case, the POI sequence may be classified into a daily, weekly, and monthly month), and the like.

In addition, when the POI sequence model is modeled for each time period, the second analysis unit 120 classifies the clustered region and the POI (for example, the clustered region is yellow, Meaningful points of interest are shown in red). The second analyzing unit 120 analyzes the classified clustered region (i.e., the region clustered by the first analyzing unit 110) and the point of interest (i.e., the POI calculated by the second analyzing unit 1200) Can be modeled in a sequence format for each time zone to model the POI sequence (i. E., Path).

FIG. 2 is a schematic diagram of a movement pattern analysis system using points of interest according to another embodiment of the present invention. Referring to FIG.

Referring to FIG. 2, a movement pattern analysis system 200 using a point of interest according to another embodiment of the present invention may include a processor 240. The processor 240 may include a first analysis unit 210, 2 analysis unit 220 and a determination unit 230. [ The first analyzing unit 210 and the second analyzing unit 220 are the same as those of the first analyzing unit 110 and the second analyzing unit 120 shown in FIG. 1, do.

The determination unit 230 may determine whether the user is out of the route (or roaming) based on the POI sequence modeled by the second analysis unit 220. [

At this time, the determination unit 230 may compare the current position of the user based on the modeled POI sequence in real time, and may determine that the user wanders when the current position of the user is out of a predetermined error range.

In addition, the determination unit 230 compares the current position of the user in real time based on the modeled POI sequence, calculates a speed at which the path is out of the path corresponding to the modeled POI sequence, The user can determine whether the user is wandering by using at least one of the staying time at the location.

That is, when the user is out of the path corresponding to the modeled POI sequence, the determining unit 230 uses the information such as the staying time, the out-of-path distance, or the out-of-path information, It is possible to immediately recognize a crisis situation such as a kidnapping or an abnormal situation to a user (that is, a child, a woman or the like who needs protection).

Hereinafter, a process of modeling a POI sequence according to an embodiment of the present invention will be described with reference to FIGS. 4 through 7 based on the details described above. Prior to the explanation, the examples of Figs. 4 to 7 are for the case where the user is an elementary school student going home and school.

4 is a diagram illustrating a first process of modeling a POI sequence according to an embodiment of the present invention.

Referring to FIG. 4, a movement pattern analyzing system 100 using a point of interest according to an embodiment of the present invention analyzes various data during a user's going to and from school, that is, time Weather information, behavior information, and the like according to the wearable beacon worn by the user. At this time, the first analysis unit 110 may receive data for correcting errors, and may store the acquired information in a time order.

5 is a diagram illustrating a second process of modeling a POI sequence according to an embodiment of the present invention.

Referring to FIG. 5, the first analysis unit 110 divides a user's moving path into reference unit areas using the collected data. In this case, for example, the reference unit area may be divided into a distance of 20 m based on the road on the map, and the information such as time of stay, frequency, weather, and behavior may be clustered in each divided area. In FIG. 4 (b), it is understood that the division is divided into five regions as a result of dividing the distance between the home and the school by a reference distance of 20 m.

6 is a diagram illustrating a third process of modeling a POI sequence according to an embodiment of the present invention.

Referring to FIG. 6, the second analyzing unit 120 assigns weights to the respective divided regions using information on the accumulated time, location information, and frequency, among the collected user related information, Interest). Since the weighting is described in detail above, the following description is omitted. At this time, the point of interest may be calculated based on the information previously input from the user (that is, the user may set the home or school as a point of interest in advance), or may collect data collected during a certain period (weeks, month, etc.) And may be calculated by assigning weights based on the weights. In FIG. 4 (c), for example, it can be seen that the house and the school are very significant points of interest, and that the school is a meaningful point of interest, and the other areas are the basic clustered areas.

7 is a flowchart illustrating a fourth process of modeling a POI sequence according to an embodiment of the present invention.

Referring to FIG. 7, the second analyzer 120 may model the POI sequence based on the calculated point of interest. In this case, one example of FIG. 4 (d) is a model of the POI sequence by time zone, and houses, schools, and academies are modeled as points of interest and the other areas are modeled as basic clustered areas. That is, the second analysis unit 120 may model the behavior pattern of the user in time sequence based on the user's location information according to time during POI sequence modeling.

Then, the determination unit 230 may determine whether the user's path is deviated from the path using the modeled POI sequence. In particular, the determination unit 230 may determine whether the user's current location is based on the modeled POI sequence And when the user is out of the path corresponding to the modeled POI sequence, it is determined whether or not the path is departed by using the information such as the staying time outside the path, the distance outside the path, or the speed at which the user leaves the path .

8 is a flowchart illustrating a method of analyzing a movement pattern using a point of interest according to an embodiment of the present invention.

The operational flow diagram of the present invention will be briefly described based on the details described above.

Referring to FIG. 8, a method for analyzing a movement pattern using a point of interest according to an embodiment of the present invention is firstly performed by a first analysis unit 210 of a system 200, using a wearable beacon, The life pattern of the user is extracted based on the user's location information (in this case, the information using the acceleration sensor and the gyro sensor can also be obtained) (S810). At this time, information such as staying time, weather, behavior (walking, running, staying, etc.) can be taken into consideration when extracting the life pattern of the user.

Next, the second analyzing unit 220 of the system 200 calculates a point of interest (POI) by weighting the long stay time based on the life pattern of the analyzed user (S820). At this time, the second analyzing unit 220 may calculate the point of interest using information to be input from the user in advance, or may be calculated based on data collected for a predetermined period of time.

Next, the second analysis unit 220 of the system 200 may model the POI sequence by time, season, day of the week or the like based on the calculated point of interest (S830). At this time, in step S830, the POI sequence may be modeled by assigning weights considering the time and frequency information per unit time to the calculated point of interest.

Next, the determination unit 230 of the system 200 determines whether the user is out of route (or wandering) based on the modeled POI sequence (S840).

At this time, the determination unit 230 may compare the current position of the user based on the modeled POI sequence in real time, and may determine that the user wanders when the current position of the user is out of a predetermined error range, Also, it is possible to determine whether the user is wandering by using at least one of a speed out of the path corresponding to the modeled POI sequence and a staying time at a position outside the predetermined error range with respect to the path.

The method for analyzing the movement pattern using the point of interest according to an embodiment of the present invention may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a 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.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains.

Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

100, 200: Moving pattern analysis system using point of interest
110, 210: first analysis unit 120, 220: second analysis unit
230: determination unit 130, 240: processor

Claims (15)

A first analyzing unit for extracting the life pattern of the user based on the location information of the user collected according to time; And
A second analyzing unit for calculating a point of interest (POI) based on the analyzed user life pattern and modeling a POI sequence based on the calculated point of interest;
A moving pattern analyzing system using a point of interest. The method according to claim 1,
The first analyzer
Analyzing the life pattern by dividing the collected location information into predetermined reference unit areas and considering at least one of the time, frequency, weather, and behavior of the user in each of the divided reference unit areas
A moving pattern analysis system using points of interest. The method according to claim 1,
The second analyzing unit
Modeling the POI sequence by assigning a weight to the computed point of interest at a time that pertains to the time per unit time
A moving pattern analysis system using points of interest. The method according to claim 1,
The second analyzing unit
Modeling the POI sequence in one cycle of time, day of the week, and season
A moving pattern analysis system using points of interest. The method according to claim 1,
A determination unit for determining whether the user leaves the path based on the modeled POI sequence;
A moving pattern analyzing system using a point of interest, 6. The method of claim 5,
The determination unit
Comparing the current position of the user based on the modeled POI sequence and determining that the user wanders if the current position of the user is out of a predetermined error range
A moving pattern analysis system using points of interest. 6. The method of claim 5,
The determination unit
Comparing the current position of the user based on the modeled POI sequence and using at least one of a speed out of a path corresponding to the modeled POI sequence and a staying time at a position outside a predetermined error range for the path To determine whether or not the user is wandering
A moving pattern analysis system using points of interest. Extracting the life pattern of the user based on the location information of the user collected according to time;
Calculating a point of interest (POI) based on the analyzed life pattern of the user; And
Modeling the POI sequence based on the calculated point of interest;
The method comprising the steps of: 9. The method of claim 8,
The extracting step
Analyzing the life pattern by dividing the collected location information into predetermined reference unit areas and considering at least one of the time, frequency, weather, and behavior of the user in each of the divided reference unit areas
A method of analyzing a movement pattern using a point of interest. 9. The method of claim 8,
The modeling step
Modeling the POI sequence by assigning a weight to the computed point of interest at a time that pertains to the time per unit time
A method of analyzing a movement pattern using a point of interest. 9. The method of claim 8,
The modeling step
Modeling the POI sequence in one cycle of time, day of the week, and season
A method of analyzing a movement pattern using a point of interest. 9. The method of claim 8,
Determining whether the user leaves the path based on the modeled POI sequence;
The method comprising the steps of: 13. The method of claim 12,
The determining step
Comparing the current position of the user based on the modeled POI sequence and determining that the user wanders if the current position of the user is out of a predetermined error range
A method of analyzing a movement pattern using a point of interest. 13. The method of claim 12,
The determining step
Comparing the current position of the user based on the modeled POI sequence and using at least one of a speed out of a path corresponding to the modeled POI sequence and a staying time at a position outside a predetermined error range for the path To determine whether or not the user is wandering
A method of analyzing a movement pattern using a point of interest. A computer-readable recording medium having recorded thereon a program for executing the method according to any one of claims 8 to 14.

Images