KR101718146B1 - System and method for providing a user visits a place - Google Patents

Abstract

A method for providing a place for users to visit comprises: a step of receiving GPS trace information of a user; a step of distinguishing a section where the user moves below predetermined threshold speed from the GPS trace information as a predictive stopping section; a step of selecting a candidate interest point about the visit of the user based on the predictive stopping section; a step of extracting any one among the candidate interest points as any one visit interest point by the predictive stopping section; and a step of generating a semantic trace corresponding to the GPS trace information based on the visit interest point.

Description

SYSTEM AND METHOD FOR PROVIDING USER VISITS A PLACE

The present invention relates to a system and method for providing a user place of visit.

In mobile environment, user 's GPS trajectory is utilized as a new resource in location based service. To extend location-based services, it is necessary not only to display the user's location on the map, but also to discover the implications of the locations where the users are located. To this end, researches have been actively conducted to generate and analyze a semantic trajectory by combining points of interest (POI) with recent GPS position information.

Most of the known technologies have found a case where the user's GPS locus and the area information (polygon) of the point of interest overlap with each other to find the point of interest visited by the user, and have determined this as a point of interest visited by the user. However, since most conventionally disclosed geographic information systems (GIS), such as Google map, Naver map, OpenStreetMap, etc., do not provide area information of actual points of interest but provide only coordinate values, There is a problem in that the user can not determine the place visited.

In addition, the conventional methods find points of interest overlapping areas for each of the GPS reception points, and therefore, if an error occurs in the GPS reception points, there is a problem that the landing point can not be properly detected.

The background technology of this application is disclosed in Korean Patent No. 10-0573181 (Registered on Mar. 17, 2006).

The present invention has been made to solve the above problems of the prior art and it is an object of the present invention to provide a geographical information system capable of solving the problem that a geographical information system And to provide a system and method for providing a user place of visit.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a system and method for providing a user visit place that can solve a problem that a user has not visited at the time of occurrence of a GPS error.

It should be understood, however, that the technical scope of the embodiments of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to an aspect of the present invention, there is provided a method of providing a user visit location, the method comprising: receiving a GPS locus information of a user; receiving a GPS locus information, Selecting a candidate point of interest related to the user's visit based on the predicted stop interval, extracting one of the candidate points of interest as a point of interest interest for each of the predicted stop intervals, And generating a semantic locus corresponding to the GPS locus information based on the visited point of interest.

The step of selecting candidate points of interest may further comprise the steps of: setting an extended area for each of the first GPS sign information included in the predicted stop section; and selecting the point of interest included in the extended area as the candidate point of interest . ≪ / RTI >

According to another aspect of the present invention, the step of setting the extended area comprises the steps of: dividing a city space of a real world into unit areas based on a geographic information system (GIS), dividing the number of points of interest Extracting an interest point density of a first unit region including each of the first GPS locus information for each of the first GPS locus information, extracting a density of a point of interest for each of the first GPS locus information, And determining the magnitude of the radius of the extended region with respect to each of the first GPS locus information based on the density of points of interest in the first unit region.

Also, the size of the radius of the extended region may be determined from a position of the first GPS locator information included in the first unit region, a size including a point of interest of at least one of the points of interest included in the first unit region, Lt; / RTI >

In addition, the step of determining the size of the radius may include determining the size of the radius of the extended area to be smaller as the number of ROIs is larger in the first unit area including the first GPS locus information, It is possible to largely determine the size of the radius of the extended region.

The step of extracting the visiting point of interest may further include calculating a proximity value of each of the candidate points of interest based on the first GPS locus information and a point of interest of the candidate point of interest, Can be extracted.

In addition, the step of extracting the visiting point of interest may extract a point of interest having a small proximity value and a large time value of the candidate point of interest as the visiting point of interest.

In addition, the step of extracting the visiting point of interest may extract the visited point of interest by normalizing the proximity value and the staying time value.

The step of generating the semantic trajectory may generate the semantic trajectory by converting the first GPS locator information included in the predicted stop section into business category information of the visited point of interest.

Also, the critical speed may be an average moving speed of the user calculated based on the GPS locus information.

Meanwhile, the system for providing a user visit place according to an exemplary embodiment of the present invention includes a GPS locus receiver for receiving GPS locus information of a user, a prediction stopper for identifying a region shifted below a predetermined threshold speed in the GPS locus information, A candidate point of interest selector for selecting a candidate point of interest related to the user's visit based on the predicted stop section; a point-of-interest selection section for selecting any one of the candidate points of interest as a point of interest interest And a semantic locus generator for generating a semantic locus corresponding to the GPS locus information on the basis of the interest point extracting unit and the visited point of interest.

The candidate point of interest selector may set an extended area for each of the first GPS sign information included in the predicted stop section and may select the point of interest included in the extended area as the candidate point of interest.

In addition, the candidate point of interest selector may divide the city space of the real world into unit areas based on a geographic information system (GIS), and calculate the number of points of interest included in each of the unit areas, And extracting the interest point density of the first unit region including each of the first GPS locus information for each of the first GPS locus information, The size of the radius of the extended region can be determined for each of the first GPS locus information based on the density of points of interest of the region.

Also, the size of the radius of the extended region may be determined from a position of the first GPS locator information included in the first unit region, a size including a point of interest of at least one of the points of interest included in the first unit region, Lt; / RTI >

The candidate point of interest selection unit may determine that the radius of the extended area is smaller as the number of ROIs increases in the first unit area including the first GPS locus information, The size of the radius of the region can be largely determined.

The visiting point of interest extraction unit may extract the visiting point of interest based on the proximity values of the candidate points of interest based on the first GPS locus information and the time values of the candidate points of interest within the extended area have.

The visiting point of interest extraction unit may extract a point of interest having a small proximity value and a large time value of the candidate point of interest as the visiting point of interest.

The visiting point of interest extraction unit may extract the visiting point of interest by normalizing the proximity value and the time value of the staying time.

The semantic trajectory generator may generate the semantic trajectory by converting first GPS locator information included in the prediction stop section into business category information of the visited point of interest.

Also, the critical speed may be an average moving speed of the user calculated based on the GPS locus information.

The above-described task solution is merely exemplary and should not be construed as limiting the present disclosure. In addition to the exemplary embodiments described above, there may be additional embodiments in the drawings and the detailed description of the invention.

According to the above-mentioned problem solving means, the present invention provides the semantic trajectory of the point of interest visited by the user using the GPS locus information and the coordinates of the point of interest, so that even when the area information of the point of interest is not given, There is an effect that the point of interest can be estimated.

According to an embodiment of the present invention, the extended region is set for each of the first GPS locator information included in the predicted stop region, the region of interest included in the extended region is selected as a candidate point of interest, It is possible to more accurately estimate the point of interest visited by the user even when the area information of the point of interest is not given, by determining the size based on the number of points of interest around.

According to the above-mentioned problem solving means, the present invention extracts a point of interest having a small proximity value and a long time value as candidate point of interest among the candidate points of interest, thereby accurately estimating a point visited by a user even when a GPS error occurs There is an effect that can be done.

FIG. 1 is a schematic block diagram of a system for providing a user's visiting place according to an embodiment of the present invention.
2 is a diagram schematically showing an overall flow of a method of providing a user's visiting place according to an embodiment of the present invention.
3 is a diagram illustrating an example of setting an extended area in a system for providing a user's visiting place according to an embodiment of the present invention.
FIG. 4 is a view showing an example of extracting a visiting point of interest in the user visiting place providing system according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating an algorithm provided by a system for providing a user's visit place according to an embodiment of the present invention.
6 is a flowchart illustrating a method of providing a user visit place according to an exemplary embodiment of the present invention.
FIG. 7 is a flowchart illustrating a method of selecting a candidate point of interest in a method of providing a user visit place according to an exemplary embodiment of the present invention. Referring to FIG.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. It should be understood, however, that the present invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In the drawings, the same reference numbers are used throughout the specification to refer to the same or like parts.

Throughout this specification, when a part is referred to as being "connected" to another part, it is understood that it is not only "directly connected" but also "electrically connected" or "indirectly" "Is included.

It will be appreciated that throughout the specification it will be understood that when a member is located on another member "top", "top", "under", "bottom" But also the case where there is another member between the two members as well as the case where they are in contact with each other.

Throughout this specification, when an element is referred to as "including " an element, it is understood that the element may include other elements as well, without departing from the other elements unless specifically stated otherwise.

The present invention provides a semantic trajectory of a point of interest visited by a user using GPS locus information and center point information (or coordinate value) of a point of interest, thereby estimating a point of interest visited by a user even when area information of the point of interest is not given And more particularly, to a system and method for providing a place for a user to visit.

FIG. 1 is a schematic block diagram of a system for providing a user's visiting place according to an embodiment of the present invention.

Referring to FIG. 1, a user visit place providing system 100 according to an embodiment of the present invention includes a GPS locus receiving unit 110, a predicted stop region identifying unit 120, a candidate interest point selecting unit 130, An extraction unit 140, and a semantic locus generation unit 150.

Prior to a full-scale explanation, the overall flow of a method of providing a user's visiting place, which can be provided through the user's visiting place providing system 100 according to an embodiment of the present invention, will be briefly described with reference to FIG.

2 is a diagram schematically showing an overall flow of a method of providing a user's visiting place according to an embodiment of the present invention. Referring to FIG. 2, a method of providing a user visit place according to an embodiment of the present invention may be performed by the user visit providing system 100.

In step 1, the GPS locus receiver 110 can receive GPS locus information of the user from the user terminal.

Thereafter, in step 2, the prediction stop section identifying section 120 can identify, as a prediction stop section, a section that has moved to a predetermined threshold speed (for example, the average moving speed of the user) in the GPS locus information.

In step 2, the prediction stop section identifying section 120 can identify the sections that the user is expected to have stopped as prediction stop sections.

For example, in step 2, four intervals can be identified as a prediction stop interval, and four prediction stop intervals include a first prediction stop interval P1, a second prediction stop interval P2, a third prediction stop interval P3) and a fourth predicted stop interval P4.

Thereafter, in step 3, the candidate point of interest selection unit 130 selects a candidate point of interest related to the user's visit (for example, candidates of points of interest estimated to be visited by the user ) Can be selected.

In step 3, the candidate point of interest selector 130 can select points of interest that the user may visit in the predicted stopping interval identified in step 2.

In step 3, the candidate point of interest selector 130 may set an extended area for each of the GPS locator information included in the predicted stationary section to select a candidate point of interest, As shown in FIG.

For example, the first point of interest (1) and the second point of interest (2) may be selected as candidate points of interest in the extended area (A10) of the GPS locus information included in the first predicted stopping interval (P1) . The third point of interest 3 can be selected as a candidate point of interest within the extended region A20 of the GPS locus information included in the second predicted stop period P2. The fourth point of interest 4 can be selected as the candidate point of interest within the extended region A30 of the GPS locus information included in the third predicted stop interval P3. The fifth point of interest 5 may be selected as a candidate point of interest within the extended region A40 of the GPS locus information included in the fourth predicted stop period P4.

In step 3, the candidate point of interest selector 130 can determine the size of the radius of the extended area in consideration of the density of points of interest, in order to secure a certain number of candidate points of interest when selecting candidate points of interest. This will be described later in more detail.

Thereafter, in step 4, the visiting interest point extracting unit 140 can extract any one of the candidate points of interest as a visiting point of interest for each of the prediction stop intervals.

In step 4, the visiting point of interest extracting unit 140 can estimate a point of interest that the user has actually visited among the candidate points of interest.

The visiting point of interest extracting unit 140 can extract the point of interest of interest based on the proximity of the candidate point of interest based on the GPS locus information and the time that the candidate point of interest is staying within the extended area. This will be described later in more detail.

For example, among the first point of interest (1) and the second point of interest (2), which are the candidate points of interest, the second point of interest (2), which is located closer to the GPS locus information, Can be extracted as a visiting point of interest. Within the second prediction stop period P2, the third point of interest 3 can be extracted as a point of interest of interest. Within the third prediction stop period P3, the fourth point of interest 4 can be extracted as the point of interest of interest. Within the fourth prediction stop period P4, the fifth point of interest 5 can be extracted as a point of interest of interest.

Thereafter, in step 5, the semantic locus generator 150 can generate a semantic locus corresponding to the GPS locus information based on the visited point of interest extracted in step 4.

The semantic locus generator 150 can generate the semantic locus representing the GPS locus information represented by the movement between the coordinates by using the visited point of interest extracted in step 4 as the type information of the interest point visited by the user.

For example, the semantic locus generator 150 converts the GPS locus information included in the first prediction stop period P1 into business type information (for example, a restaurant) at two points of interest 2, The GPS locator information included in the prediction stop interval P2 is converted into the business type information (e.g., cafe) of the three points of interest 3 and the GPS locus information included in the third prediction stop period P3 is converted into four And converts the GPS locator information included in the fourth predicted stop section P4 into sector type information (e.g., boarding house) of five points of interest 5 By converting, the semantic trajectory can be generated.

Through the process of steps 1 to 5, the user visit place providing method according to the embodiment of the present invention can more accurately estimate the point of interest visited by the user even when the area information of the point of interest is not given. Hereinafter, the present invention will be described in more detail with reference to FIG.

Referring to FIG. 1, the GPS locus receiver 110 may receive GPS locus information of a user from a user terminal. The user terminal may include a portable terminal such as a notebook, a tablet PC, a mobile phone, a smart phone, a PDA, and the like.

In addition, the GPS locus receiver 110 can receive GPS information in real time from the user terminal and generate GPS locus information based on the received GPS information in real time. The GPS locus receiving unit 110 can calculate the speed from the GPS locus information received in real time. For example, the GPS locus information may be as shown in step 1 of FIG.

The predictive stop section identifying unit 120 can identify a section of the GPS locus information that has moved below a predetermined threshold speed as a predictive stop interval (PSI). At this time, the preset critical speed may be the average moving speed of the user calculated based on the GPS locus information.

Hereinafter, the GPS trajectory information and the point of interest (POI) information described herein will be described before describing the prediction stop section.

The GPS trajectory information indicating the user's movement path is GT = {P ₁ , ... , P _i, ... , P _n }. P _{i, which} is a position of the GPS locus, can be expressed as P _i = (id, (x, y), t). In this case, id denotes identification information of a point, (x, y) denotes coordinates of each point, and t denotes a timestamp when GPS information is received.

The point of interest (POI) information may be expressed as (pid, (x, y), c). Here, pid represents identification information of a point of interest, (x, y) represents coordinate information of a point of interest, and c represents industry information. The set of all points of interest that the user can visit is POIset = {POI ₁ , ... , POI _m }.

Predictive Stop Interval (PSI) means a section predicted that the user has stopped in the GPS locus information. However, in the case of GPS locus information indicating the movement path of the user, it is rare that the speed is 0 even if the actual user is stopped due to the reception error. In addition, the moving means of the actual user may be various vehicles such as a vehicle, a public transportation, a walk, etc. However, when the user finally visits a desired place, he generally moves on foot. In consideration of this point, the predicted stop section identifying unit 120 according to an embodiment of the present invention sets the average moving speed (for example, an average walking speed) as a threshold speed and the average moving speed It is possible to identify a section that moves below the speed as a predicted stop section.

a 이하가 되는 구간을 예측 정지 구간으로서 정의할 수 있다. 예측 정지 구간은 하기 식 1과 같이 표현될 수 있다.According to one embodiment of the present application, the average moving speed of the user may be defined as 1.3 m / s. Based on this, the prediction stop section identifying section 120 determines that the average speed from P _i to P _{i +1} in the GPS locus information is 1.3 m / s

a or less can be defined as a prediction stop section. The prediction stop interval may be expressed as Equation 1 below.

[Formula 1]

An arbitrary kth prediction stop interval that satisfies Equation 1 can be expressed as PSI _k = (P _i , P _{i + 1} , ..., P _{i + 1} ). The set of predicted stop intervals (PSI _k ) identified in the GPS locus information is PSIset = {PSI ₁ , ... , PSI _m }.

In Equation 1, α is a real number with 0 <α ≤ 1 and can be used to adjust the walking speed criterion (ie critical speed reference) according to the application environment. It is possible to identify the prediction stop section precisely as? is smaller,

If α becomes too small, a problem that an interval in which the user has actually stopped is divided into a plurality of prediction stop intervals occurs, so that the value of α can be determined according to the application environment.

The candidate point of interest selector 130 can select a candidate point of interest (CPOI, Candidate POI) related to the user's visit based on the prediction stop section. The candidate point of interest selection unit 130 can select candidates of interest points (i.e., candidate points of interest) that the user is supposed to have visited, in order to extract a point of interest actually visited by the user .

The candidate point of interest selector 130 may set an extended area for each of the first GPS sign information included in the predicted stop section, to select a candidate point of interest. In addition, the candidate point of interest selector 130 may select the point of interest included in the set extension area as a candidate point of interest. The first GPS locus information PSI _k may be a GPS locus included in the predicted stop interval PSIset among the entire GPS locus information received by the GPS locus receiver 110.

The candidate point of interest selector 130 selects candidate points of interest (CPOI, Candidate POI) estimated to be actually visited by the user in each of the prediction stop intervals identified by the prediction stop section identifying unit 120, Each of the GPS locus points (i.e., the first GPS locus points) included in the extended region can be extended to the region, and the points of interest included in the extended region can be selected as candidate points of interest.

GPS points have a problem that they can not accurately represent the actual user's position due to GPS errors. Accordingly, the determined region set through the candidate point of interest selector 130 is an area including all the points that the user may have stayed. The system 100 for providing a user-visiting place according to an exemplary embodiment of the present invention can select candidate points of interest in consideration of GPS errors. For this purpose, the radius of the extended region can be determined for each of the first GPS trajectories.

Hereinafter, for convenience of description, the k th prediction stop section PSI _k a point P _i to P _k, is expressed as _i, and the radius mainly focusing on the coordinate value of P _{k, i} R source contained in Circle _{k, i} = (P _{k, i} , R).

The candidate point of interest selector 130 may generate a circle (Circle _{k, i} ) having a radius R centered on all P _i of PSI _k in order to extend the points of each of the first GPS locus information into an area, The points of interest included in the generated Circle _{k, i} can be selected as candidate point of interest (CPOI).

In this case, if the sizes of the circles generated around the points P _i of the first GPS locus information are all the same, too many candidate points of interest are selected in the region where the points of interest are concentrated, The cost can be increased. Conversely, in areas where there are few points of interest, the candidate points of interest may not be selected, or too few candidate points of interest may be selected, so that the point of interest actually visited by the user may not be included in the candidate point of interest. Accordingly, the candidate point of interest selector 130 can determine the magnitude (R) of the radius of the extended area in inverse proportion to the number of points of interest around Pi to secure a certain number of candidate points of interest.

In order to determine R according to the number of neighboring points of interest, the candidate point of interest selector 130 divides the entire area into a unit area (i.e., a square cell) having a length L, The number of points of interest can be defined as the point of interest POIdensity. Further, the candidate point of interest selection unit (130) Circle _k, to produce a _i, P _{k, i} looking for a cell containing the, P _k, point of interest density of the cell containing _i is (POIdensity _{k, i)} Can be extracted.

At this time, the candidate interest point selection unit 130 determines the size of R so that Circle _{k, i} generated from P _{k, i} included in the cell includes at least one point of interest included in the cell . For example, the candidate point of interest selector 130 may determine R, assuming that the locations of interest points within the cell are uniformly distributed. Thus, the larger the number of points of interest around P _{k, i,} the smaller the size of R, and vice versa. (R) of the radius of the extended region can be expressed by the following Equation 2, and R is determined based on the PO density ( _{k, i} ) of the cell including P _{k, i} and the length L of the unit region .

[Formula 2]

An example of setting the extended area through the candidate point of interest selector 130 can be more easily understood with reference to FIG. 3 is a diagram illustrating an example of setting an extended area in a system for providing a user's visiting place according to an embodiment of the present invention.

Referring to FIG. 3, for example, the first sub-locus P ₁ and the second sub-locus P ₂ may be first GPS locus information included in the predicted stop interval. The first sub-locus P ₁ may be a GPS locus at time t and the second sub-locus P ₂ may be a GPS locus at time t + 1.

The candidate point of interest selection unit 130 selects an extension region for each of the first GPS locus information P ₁ and P ₂ based on a geographic information system (GIS) That is, the entire area) can be divided into square unit areas of L length. 3, the entire area can be divided into a unit area 1 (C1), a unit area 2 (C2), a unit area 3 (C3), and a unit area 4 (C4).

Then, the candidate point of interest selector 130 can define the number of points of interest included in each unit area as a point of interest POI density for each unit area. For example, since three interest regions (a, b, c) exist in the unit region 1 (C1), the density of the interest point of the unit region 1 (C1) can be defined as 3. Since there is one interest area in each of the unit area 2 (C2), the unit area 3 (C3), and the unit area 4 (C4), the unit area 2 (C2) The density of the point of interest can be defined as 1 respectively.

Then, the candidate point of interest selector 130 can extract the POI density _{k, i} of the first unit area including the first GPS locus information for each of the first GPS locus information. In this case, the first unit area refers to a unit area including the first GPS locus information of the entire area.

More specifically, the candidate point of interest selection unit 130 identifies a unit area (i.e., a first unit area) in which the first GPS locus information is located in the entire area, and determines a density of a point of interest extracted from the identified unit area It is possible to correspond to each of the first GPS locus information.

For example, since the first sub-locus P ₁ is included in the unit area 1 (C1) and the second sub-locus P ₂ is included in the unit area 4 (C4), the candidate interest point selector 130 may extract 3 as the point of interest density for the first sub-locus P ₁ and ₁ as the density of points of interest for the second sub-locus P ₂ .

Then, the candidate point of interest selection unit 130 selects the radius of the extended region for each of the first GPS locus information based on the length L of the unit region and the POI density _{k, i} of the first unit region The size R can be determined.

In this case, the size R of the radius of the extended area may be a size including at least one point of interest among the points of interest included in the first unit area from the position of the first GPS locator information included in the first unit area .

For example, first, because the sub-trajectory (P ₁₎ case, the three regions of interest in the unit region 1 (C1) of (a, b, c) are present, a first extended area for the sub-trajectory (P ₁₎ The magnitude R1 of the radius of the area A1 can be set to a size including the area of interest c as at least one of the three areas of interest a, b, c existing in the unit area C1 have. A second sub-locus (P ₂₎ of the case, since in the unit area 4 (C4) are present, only one region of interest (d), the second sub-trajectory extents for (P ₂₎ (A2 ') the radial dimension of the (R2) may be set to a size including the region of interest d.

In the example of FIG. 3, it is assumed that only the region of interest c exists in the extended region A1 'of the first sub-locus P _{1 for} the sake of explanation. However, the present invention is not limited thereto and there may be a plurality of regions of interest. For example, the region of interest b and the region of interest c first sub-trajectory, when present on the same distance from the (P _1), the first expansion region of the sub-trajectory (P ₁₎ (A1 ') in the region of interest b and interest Region c may exist.

The candidate point of interest selection unit 130 determines the size of the radius of the extended region to be smaller as the number of ROIs increases in the first unit region including the first GPS locus information and the radius of the extended region as the number of ROIs decreases. The size can be largely determined.

For example, to secure a candidate point of interest of the candidate point of interest selecting section 130 may be constant, in accordance with the size of the radius of the P _1, P _2, each of the number of P _1, P _2, respectively around points of interest The radius R1 of the radius P ₁ having a large number of peripheral points of interest a, b and c is smaller than the radius R ₂ of the radius P ₂ having a small number of peripheral points of interest d You can decide.

The visiting point of interest extracting unit 140 can extract any one of the candidate points of interest as a point of interest interest for each of the prediction stop periods.

The visiting point of interest extracting unit 140 can extract the point of interest of interest based on the proximity values of each candidate point of interest based on the first GPS locus information and the time each of the candidate points of interest stay within the extended area. In addition, the visiting point of interest extractor 140 can extract a point of interest having a small proximity value and a large time value of the candidate point of interest as a visiting point of interest. In addition, the visiting point of interest extractor 140 may extract the point of interest of interest by normalizing the proximity value and the time-of-stay value. The visiting point of interest extracting unit 140 will be described in more detail as follows.

The visited point of interest (VPOI _k , Visited POI) means the candidate point of interest which is most likely to be stayed by the user among the candidate points of interest (CPOIset _k ) selected in each of the prediction stop intervals. The visiting point of interest extracting unit 140 may consider proximity and duration for each candidate point of interest in order to extract the visiting point of interest VPOI _k among the candidate points of interest.

The proximity is information indicating how close each of the candidate points of interest is to the prediction stop interval PSI _k . It can be defined that the closer the candidate point of interest is to the prediction stop interval, the higher the proximity. Based on this, visit points of interest extraction unit 140, the proximity between the values P _k, the resulting Circle a _i with emphasis _{k, i} The CPOI _i and P _{k, i} contained therein can be defined as the sum of the distance have. Therefore, the proximity is higher as the sum of the distances is smaller, and the larger the sum of the distances is, the lower the degree of proximity is. This can be more easily understood with reference to FIG.

FIG. 4 is a view showing an example of extracting a visiting point of interest in the user visiting place providing system according to an embodiment of the present invention.

4, P _{k, 1} , P _{k, 2} , P _{k, 3} , and P _{k, 4} Each of which may be a first GPS locus included in the predicted stop interval. A1 may denote an extended region of P _{k, 1} , A2, P _k, an extended region of _{2 , A 3,} an extended region of P _{k, 3, and} an extended region of A4, P _k, It can be seen that the sizes of the extension areas A1 to A4 are formed differently depending on the density of interest points.

For example, the proximity value of the first candidate point of interest (CPOI ₁ ) may be the sum of the distance between P _{k, 1} and CPOI ₁ , and the distance between P _{k, 2} and CPOI ₁ . Equation (3) represents the definition of proximity, and the visiting point of interest extractor 140 can calculate the proximity values of each of the candidate points of interest by using Equation (3).

[Formula 3]

On the other hand, the duration can be defined as Equation 4 below.

[Formula 4]

Referring to equation (4), defined as the sum of the landing point of interest extraction unit 140 is the predicted time (PT, predictive time) were included in each of the circles generated by the time spent value to CPOI _i is weighted to P _{k, i} can do.

At a point P _{k, i} of the prediction time (PT _{k, i)} it is predicted stop interval (PSI _k) as meaning a schematic time the user had stopped, the predicted time may be calculated from the following formula 5.

[Formula 5]

For example, P _k, the predicted time at ₁ (PT _{k, 1)} is 30 _sec, P _k, the predicted time in ₂ (PT _{k, 2)} is 40 _sec, P _k, the predicted time in the ₃ (PT _{k, 3)} is 60 _sec, P _k, the predicted time in the ₄ (PT _{k, 4)} is 20 sec in the case, (duration time spent value of the second candidate points of interests (CPOI ₂₎ in FIG. 4) 90 sec (30 sec + 40 sec + 20 sec = 90 sec).

The visiting point of interest extracting unit 140 extracts a candidate point of interest having a long duration of stay and a long time interval from among the candidate points of interest (CPOIset _k ) selected for each prediction stop interval for each of the prediction stop periods as a point of interest interest can do.

Since the units representing the proximity values are distances, the units representing the staying time values are time, and the proximity values and the staying time values have different scales, the visiting point of interest extraction unit 140 extracts the candidate points of interest The proximity value and the time-of-day value calculated for each can be normalized by Equation 6 below.

[Formula 6]

At this time, as shown in the following equation 7, the landing point of interest (VPOI _k) time spent case is less than the minimum threshold time (△ minDuration), (VPOI _k) landing point of interest extraction unit 140 is the actual user visits a point of interest it of It can be judged that it has not stayed. Accordingly, the visiting point of interest extracting unit 140 can exclude the visiting point of interest (VPOI _k ) that is less than the minimum threshold time when extracting the point of interest of interest.

The semantic trajectory generating unit 150 may generate a semantic trajectory (ST) corresponding to the GPS trajectory information based on the point of interest of interest.

The semantic locus generator 150 can generate the semantic locus by converting each of the first GPS locus information PSI _i included in the prediction stop interval PSIset into the business type information of the visiting interest point VPOI _i .

Semantic trajectory (ST) means a sequence of sector information of the point of interest is selected as the predicted stop interval (PSI _k) landing point of interest (VPOI) identified from the GPS trajectory (GT) information, and semantic trajectory ST = (VPOI _{1 . c} , ..., VPOI _{i .c} , ..., VPOI _{m .c} ).

FIG. 5 is a diagram illustrating an algorithm provided by a system for providing a user's visit place according to an embodiment of the present invention.

FIG. 5 shows a process of each part of the system 100 for providing a user's visit place according to an embodiment of the present invention with an algorithm, which will be briefly described as follows.

Referring to FIG. 5, the user visiting place providing system 100 can calculate the speed from the GPS locus information (see line 1). Next, the system 100 generates a prediction stop interval PSI by searching all the intervals satisfying the equation 1 to identify the prediction stop interval PSI, sequentially predicts all the generated prediction stop intervals PSI, Can be added to the set of stop intervals (PSIset) (see lines 2 to 7). Next, the system 100 may generate a circle centered at each point P of the predicted stop interval PSI to select a candidate point of interest (CPOI) for each predicted stop interval PSI. At this time, the radius R of the generated circle can be determined through Equation 2, and the points of interest included in the circle can be selected as candidate points of interest (see lines 8 to 17). Next, the system 100 can select a candidate point of interest (CPOI) having a long staying time and a small proximity value as a visiting point of interest (VPOI) as shown in Equation 6. Here, If the time of stay of the point VPOI is less than the minimum threshold time, it can be removed (see lines 18-23). Next, the system 100 may add the business type information of the finally selected visiting point of interest (VPOI) to the semantic trajectory ST (see line 24).

Hereinafter, the operation flow of the present invention will be briefly described based on the details described above.

FIG. 6 is a flowchart illustrating a method of providing a user visit place according to an exemplary embodiment of the present invention. FIG. 7 is a flowchart illustrating a method of selecting candidate points of interest in a method of providing a user visit place according to an exemplary embodiment of the present invention.

6 to 7 can be performed by the user visiting place providing system 100 described above with reference to FIGS. 1 to 5. FIG. Therefore, even if omitted in the following description, the contents described with respect to the system 100 for providing the user's place of visit through Figs. 1 to 5 also apply to Figs. 6 to 7.

Referring to FIG. 6, in step S610, the GPS locus information may be received from the user terminal through the GPS locus receiver 110. FIG.

Next, in step S620, the section that has moved below the preset threshold speed in the GPS locus information can be identified as the predicted stop interval (PSI) through the predicted stop section identification unit 120. [ At this time, the preset critical speed may be the average moving speed of the user calculated based on the GPS locus information.

Next, in step S630, candidate point of interest (CPOI) related to the user's visit can be selected through the candidate point of interest selector 130 based on the predicted stop interval.

In step S630, the candidate point of interest selector 130 selects candidates of interest points (i.e., candidate points of interest) estimated to have been visited by the user to extract interest points actually visited by the user can do. This can be more easily understood with reference to FIG.

In step S630, the candidate point of interest selector 130 may divide the real world city space into unit areas based on the geographical information system (GIS) in order to set the extended area (S631). In operation S632, the candidate point of interest selector 130 may define the number of points of interest included in each unit area as POI density for each unit area. Then, the candidate point of interest selector 130 can extract the POI density _{k, i} of the first unit area including the first GPS locus information for each of the first GPS locus information (S633 ). Then, the candidate point of interest selection unit 130 _calculates the size (R ( _i )) of the radius of the extended region with respect to each of the first GPS locus information based on the length of the unit region and the POI density _{k, i} of the first unit region (Step S634). Since the description thereof has been described in detail above, the following description will be omitted.

Thereafter, in step S630, the candidate point of interest selector 130 may set an extension area for each of the first GPS sign information included in the predicted stop section based on the size of the radius determined in step S634. In addition, the candidate point of interest selector 130 may select the point of interest included in the set extension area as a candidate point of interest.

Next, in step S640, the visiting point of interest extracting unit 140 may extract any one of the candidate points of interest as a point of interest interest for each of the prediction stop sections.

In step S640, the visiting point of interest extractor 140 may extract the point of interest of interest based on the proximity values of each candidate point of interest based on the first GPS locus information and the time each of the candidate points of interest stay within the extended area. In addition, the visiting point of interest extractor 140 can extract a point of interest having a small proximity value and a large time value of the candidate point of interest as a visiting point of interest. In addition, the visiting point of interest extractor 140 may extract the point of interest of interest by normalizing the proximity value and the time-of-stay value.

Next, in step S650, the semantic trajectory generating unit 150 can generate a semantic trajectory (ST) corresponding to the GPS trajectory information on the basis of the visited point of interest.

In step S650, the semantic locus generator 150 may generate the semantic locus by converting each of the first GPS locus information included in the prediction stop section into the business type information of the visiting point of interest.

In the above description, steps S610 to S650 may be further divided into further steps, or combined in fewer steps, according to embodiments of the present disclosure. Also, some of the steps may be omitted as necessary, and the order between the steps may be changed.

The method of providing a user visit place according to one 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.

Furthermore, the above-mentioned method of providing the user's place of visit may also be implemented in the form of a computer program or an application executed by a computer stored in a recording medium.

It will be understood by those of ordinary skill in the art that the foregoing description of the embodiments is for illustrative purposes and that those skilled in the art can easily modify the invention without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included within the scope of the present invention.

100: User-provided place providing system
110: GPS locus reception unit 120: prediction stop section identification unit
130: Candidate interest point selection unit 140: Visit point of interest extraction unit
150: Semantic Trajectory Generator

Claims (21)

Receiving GPS trajectory information of a user;
Identifying an interval that is shifted to a predetermined threshold speed or less from the GPS locus information as a prediction stop section;
Selecting candidate points of interest related to the user's visit based on the predicted stop interval;
Extracting one of the candidate points of interest as a visiting point of interest for each of the prediction stop sections; And
Generating a semantic locus corresponding to the GPS locus information based on the visited point of interest;
Lt; / RTI &gt;
The step of selecting the candidate points of interest comprises:
Setting an extended area for each of the first GPS sign information included in the predicted stop section and selecting a point of interest included in the extended area as the candidate point of interest,
The method comprising the steps of: dividing a city space of an actual world into unit areas based on a geographic information system (GIS), setting a number of points of interest included in each of the unit areas, And extracts the interest point density of the first unit region including each of the first GPS locus information for each of the first GPS locus information, Wherein the magnitude of the radius of the extended region is determined for each of the first GPS locus information based on the density of points of interest of the first GPS locus information. delete delete The method according to claim 1,
The size of the radius of the extended region is
Wherein the first unit area has a size that includes at least one point of interest among the points of interest included in the first unit area from the position of the first GPS locator information included in the first unit area. The method according to claim 1,
The step of determining the magnitude of the radius
The size of the radius of the extended region is determined to be smaller as the number of ROIs increases, and the size of the radius of the extended region is determined to be larger as the number of ROIs is smaller in the first unit region including the first GPS locus information. A method for providing a user place of visit. The method according to claim 1,
The step of extracting the visited point of interest
Wherein the proximity value of each of the candidate points of interest based on the first GPS locus information and each of the candidate points of interest are calculated by taking into account time values in the extended area. The method according to claim 6,
The step of extracting the visited point of interest
Wherein a point of interest having a small proximity value and a small time value of the candidate point of interest is extracted as the point-of-interest point of interest. The method according to claim 6,
The step of extracting the visited point of interest
And extracting the visited point of interest by normalizing the proximity value and the time-of-stay value. The method according to claim 1,
The step of generating the semantic trajectory
And generating the semantic trajectory by converting first GPS locator information included in the predicted stop section into business category information of the visited point of interest. The method according to claim 1,
The critical speed
And the average moving speed of the user calculated based on the GPS locus information. A GPS locus receiver for receiving GPS locus information of a user;
A predicted stop section identifying unit that identifies, as a predicted stop section, a section that has moved below a predetermined threshold speed in the GPS locus information;
A candidate point of interest selection unit for selecting a candidate point of interest related to the user's visit based on the predicted stop period;
A visiting point of interest extracting unit for extracting any one of the candidate points of interest as a point of interest point of interest for each of the prediction stop intervals; And
A semantic locus generator for generating a semantic locus corresponding to the GPS locus information based on the visited point of interest;
Lt; / RTI &gt;
The candidate point of interest selector comprises:
Setting an extended area for each of the first GPS sign information included in the predicted stop section and selecting a point of interest included in the extended area as the candidate point of interest,
The method comprising the steps of: dividing a city space of an actual world into unit areas based on a geographic information system (GIS), setting a number of points of interest included in each of the unit areas, And extracts the interest point density of the first unit region including each of the first GPS locus information for each of the first GPS locus information, Wherein the magnitude of the radius of the extended region is determined for each of the first GPS locus information based on the density of points of interest of the first GPS locus information. delete delete 12. The method of claim 11,
The size of the radius of the extended region is
Wherein the first unit area has a size that includes at least one point of interest among the points of interest included in the first unit area from the position of the first GPS locator information included in the first unit area. 12. The method of claim 11,
The candidate point of interest selector
The size of the radius of the extended region is determined to be smaller as the number of ROIs increases, and the size of the radius of the extended region is determined to be larger as the number of ROIs is smaller in the first unit region including the first GPS locus information. A user visiting place providing system. 12. The method of claim 11,
The visiting interest point extracting unit
Wherein the proximity value of each of the candidate points of interest based on the first GPS locus information and each of the candidate points of interest are calculated by taking into account the time value within the extended area. 17. The method of claim 16,
The visiting interest point extracting unit
And extracts, as the visited point of interest, a point of interest having a small proximity value among the candidate points of interest and the time value of which is large. 17. The method of claim 16,
The visiting interest point extracting unit
And extracts the visited point of interest by normalizing the proximity value and the time-of-stay value. 12. The method of claim 11,
The semantic locator generating unit
And generating the semantic trajectory by converting first GPS locator information included in the predicted stop section into business category information of the visited point of interest. 12. The method of claim 11,
The critical speed
And the average moving speed of the user calculated based on the GPS locus information. A computer-readable recording medium having recorded therein a program for executing the method according to any one of claims 1 and 4 to 10.

Images