WO2015067119A1 - 一种位置兴趣点聚类方法和相关装置 - Google Patents

一种位置兴趣点聚类方法和相关装置 Download PDF

Info

Publication number
WO2015067119A1
WO2015067119A1 PCT/CN2014/088443 CN2014088443W WO2015067119A1 WO 2015067119 A1 WO2015067119 A1 WO 2015067119A1 CN 2014088443 W CN2014088443 W CN 2014088443W WO 2015067119 A1 WO2015067119 A1 WO 2015067119A1
Authority
WO
WIPO (PCT)
Prior art keywords
points
point
resident
positioning
hot zone
Prior art date
Application number
PCT/CN2014/088443
Other languages
English (en)
French (fr)
Inventor
丁强
宋韶旭
欧阳振
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to KR1020167013679A priority Critical patent/KR101806948B1/ko
Priority to EP14860583.5A priority patent/EP3056999B1/en
Priority to JP2016528174A priority patent/JP6225257B2/ja
Publication of WO2015067119A1 publication Critical patent/WO2015067119A1/zh
Priority to US15/148,365 priority patent/US10423728B2/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/021Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • G06F16/285Clustering or classification
    • G06F16/287Visualization; Browsing
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/36Input/output arrangements for on-board computers
    • G01C21/3679Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/08Testing, supervising or monitoring using real traffic
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/023Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/025Services making use of location information using location based information parameters
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/029Location-based management or tracking services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W64/00Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/006Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination

Definitions

  • the present invention relates to the field of geographic information processing technologies, and in particular, to a location interest point clustering method and related apparatus.
  • Point Of Interest refers to a location area where users frequently stay for a long time, such as a home, an office, a frequent supermarket, and the like, which are important to the user.
  • the trajectory information of the daily activities of the user can be obtained by using a Wi-Fi network such as a mobile phone, a Global Positioning System (GPS), and a positioning function of an ID (Identity), and the trajectory information is composed of a large number of locating information. Deviation of the positioning coordinate points, study how to extract the user's POI from these trajectory information, which is of great value for context-aware and location-based service (LBS) applications and services. Research hotspots.
  • the above method extracts the user's resident point through the space-time dimension, and the resident point can only represent the user's single visit, cannot represent the POI location important to the user, and only refers to the user's historical location data when mining the POI. The reliability and reference value of the excavated POI are low.
  • Embodiments of the present invention provide a location interest point clustering method and related apparatus for improving reliability and reference value of a POI.
  • a first aspect of the present invention provides a method for clustering location points of interest, including:
  • each of the resident points in the set of the resident points represents a hot zone, and the hot zone satisfies the following condition: a geographical position of any two of the hot spots The distance is smaller than the positioning accuracy of the two positioning points; the maximum value of the time interval between the positioning points in the hot zone is greater than the preset time threshold;
  • the density-connected trusted resident points are clustered into a location interest point, wherein the density connection refers to the direct or indirect connection of the hot zone represented by the two trusted resident points.
  • the foregoing generates a set of resident points according to the foregoing set of positioning points, including:
  • the geometric center point of the above hot zone is a dwell point representing the above hot zone.
  • the calculating the reliability of each of the resident points in the set of the resident points includes: :
  • the obtaining, by the foregoing, the motion states of the positioning points in the set of the positioning points specifically:
  • the motion state of each positioning point in the set of positioning points is obtained according to the sensor data on the user's terminal or the strength and number of the Wi-Fi network.
  • the above-mentioned density-connected trusted station Clustering points into a location of interest points including:
  • the closed area formed by sequentially connecting all the leaf dwell points in all the trusted dwell points connected by the density is determined as an area of the position interest point, wherein all the preset radius coverage centered on the leaf dwell point The sum of the trustworthiness of the dwelling points is not greater than the preset threshold.
  • a second aspect of the present invention provides a location point of interest clustering apparatus, including:
  • An obtaining unit configured to acquire a set of positioning points of a user in a predetermined time period
  • a residing point generating unit configured to generate a residing point set according to the set of positioning points acquired by the acquiring unit, where each of the residing point sets represents a hot zone, and the hot zone satisfies the following condition: The geographical distance of any two positioning points in the hot zone is smaller than the positioning accuracy of the positioning accuracy of the two positioning points; the maximum value of the time interval between the positioning points in the hot zone is greater than the preset time threshold;
  • a computing unit configured to calculate a credibility of each of the residing points in the set of the residing points, wherein the average speed corresponding to the motion state of all the positioning points in the hot zone represented by the dwelling point is smaller, the dwell point The higher the credibility;
  • a filtering unit configured to filter a trusted resident point from the set of the resident points according to the credibility of each of the resident points in the set of the resident points calculated by the calculating unit, where the trusted resident point The credibility is greater than the preset credibility threshold;
  • a clustering unit is configured to cluster the density-connected trusted resident points into a location interest point, wherein the density connection refers to directly or indirectly connecting the ranges of the hot zones represented by the two trusted resident points. Pick up.
  • the above resident point generating unit includes:
  • a first determining unit configured to determine a hot zone that satisfies the above conditions
  • a second determining unit configured to determine a geometric center point of the hot zone to represent a dwell point of the hot zone.
  • the above calculation unit includes:
  • a sub-acquisition unit configured to acquire motion states of respective positioning points included in the hot zone represented by each of the foregoing resident points
  • Sub-computing unit for formulating And the motion state of each anchor point included in the hot zone represented by each of the foregoing resident points obtained by the foregoing sub-acquisition unit, and calculating the reliability of each of the resident points in the set of the resident points,
  • Conf i represents a dwell point
  • n represents n possible motion states
  • W k represents the credibility weight of the kth motion state
  • n k represents the motion state in the hot zone represented by the dwell point i is the kth motion state
  • the foregoing sub-acquisition unit is specifically configured to: according to the sensor data on the terminal of the user or the strength of the Wi-Fi network The number of changes changes to obtain the motion state of each of the positioning points in the set of positioning points.
  • the clustering unit is specifically configured to: cluster all trusted residing points connected by density into one location interest point; and all trusted residing points connected to the density
  • the closed area formed by connecting all the dwelling points of the leaves in turn is determined as the area of a positional interest point, wherein the sum of the credibility of all the dwelling points within the preset radius coverage centered on the leaf dwelling point is not Greater than the preset threshold.
  • a plurality of positioning points form a dwell point according to the positioning accuracy and the time threshold, and most of the short stay points, the positioning jump points, and the way points can be determined by the positioning accuracy and the time threshold constraint. Filtering, at the same time, combining the motion state of the anchor point in the dwell point to calculate the credibility of the dwell point and filtering out the less reliable dwell point according to the credibility of the dwell point, further filtering out part The noise dwelling point on the way (such as traffic jams, red lights, slow dwellings, etc.), so that the reliability and reference value of the location interest points finally clustered by the density-connected trusted dwelling points higher.
  • FIG. 1 is a schematic flow chart of an embodiment of a location point of interest clustering method according to the present invention
  • FIG. 2 is a schematic diagram of a trajectory of a set of positioning points in an application scenario according to the present invention
  • FIG. 2 is a schematic diagram of a set of resident points formed in an application scenario according to the present invention
  • Figure 2-c is a schematic diagram of a collection of credibility residing points selected in an application scenario provided by the present invention.
  • FIG. 2-d is a schematic diagram of a POI clustered in an application scenario provided by the present invention.
  • FIG. 3 is a schematic structural diagram of an embodiment of a location point of interest clustering apparatus according to the present invention.
  • FIG. 4 is a schematic structural diagram of another embodiment of a location point of interest clustering apparatus according to the present invention.
  • FIG. 5 is a schematic structural diagram of still another embodiment of a location point of interest clustering apparatus according to the present invention.
  • Embodiments of the present invention provide a location interest point clustering method and related apparatus.
  • a method for clustering a location point of interest according to an embodiment of the present invention includes:
  • the set of positioning points includes one or more positioning points, and the positioning points are used to indicate location information of the user.
  • the positioning point is a GPS position point represented by a longitude value and a latitude value
  • the location point of interest clustering device acquires the set of positioning points of the user in the predetermined time period from the GPS location data of the user.
  • Each of the residing point sets represents a hot zone, and the hot zone satisfies the following condition: a geographical distance of any two of the hot zones is less than a positioning accuracy of the two positioning points. Large positioning accuracy; the maximum value of the time interval between the positioning points in the above hot zone is greater than the preset time threshold.
  • the set of positioning points ⁇ P j , P j+1 , . . . , P j+L ⁇ constitutes a hot zone that can form a dwelling point
  • the set of positioning points ⁇ P j , P j+1 ,. .., P j+L ⁇ must meet the following two conditions:
  • the geographical distance of any two positioning points in ⁇ P j , P j+1 ,..., P j+L ⁇ is smaller than the spatial threshold Dth, where Dth is not a fixed value, which is based on the positioning points involved.
  • Dth is not a fixed value, which is based on the positioning points involved.
  • D th (P 1 , P 2 ) is equal to the positioning point.
  • the larger positioning accuracy in P 1 and the positioning point P 2 is equal to 10 meters, and if the positioning accuracy of the positioning point P 3 is 15 meters, for the positioning point P 1 and the positioning point P 3 , D th (P 1 , P 3 ) is equal to a larger positioning accuracy in the positioning point P 1 and the positioning point P 3 , that is, D th (P 1 , P 3 ) is equal to 15 meters.
  • ⁇ P j , P j+1 , . . . , P j+L ⁇ also needs to satisfy: ⁇ P j , P j+1 , . . .
  • T th The preset time threshold T th (for example, T th may take 5 minutes, 7 minutes, or 10 minutes, etc.), that is, ⁇ P j , P j+1 , . . . , P j+L ⁇
  • T th can be specifically set according to actual needs, and is not limited herein.
  • the geometric center point of the hot zone is a dwell point representing the hot zone
  • the dwell point may represent all the anchor points in the hot zone.
  • other methods may be used to determine the dwell point corresponding to a hot zone.
  • the center of gravity of the hot zone is used as a dwelling point representing the hot zone, wherein the center of gravity of the hot zone is related to the distribution of the anchor points in the hot zone. .
  • the location point of interest clustering device acquires motion states of the respective anchor points included in the hot zone represented by each of the resident points in the set of the resident points, and represents each of the resident points in the set of the resident points.
  • Motion state and formula of each anchor point included in the hot zone The credibility weight of the dynamic state, n k represents the number of anchor points in the hot zone represented by the dwelling point i, which is the kth motion state, wherein each motion state corresponds to a credibility weight, and The smaller the motion speed corresponding to the motion state, the greater the weight of the confidence of the motion state.
  • the motion state is stationary, walking, or riding, for the three motion states, since the motion speed corresponding to the motion state is from small to large, it is: stationary, walking, or riding, therefore, the motion state
  • the weight of credibility is from small to small: stationary, walking or riding.
  • the location interest point clustering device changes according to sensor data (such as acceleration, gyroscope, etc.) on the user's terminal (such as a mobile phone, a tablet computer, a vehicle terminal, etc.) or the strength and number of the Wi-Fi network. Acquiring the motion state of each of the locating points in the set of locating points; or the locating point clustering device may obtain the motion state of each locating point in the set of locating points from other locating devices (such as a server), which is not limited herein. .
  • the credibility of the trusted residing point is greater than the preset credibility threshold.
  • the location interest point clustering device filters out the trusted resident point from the set of the resident points (that is, the resident point whose reliability is greater than the preset reliability threshold), and the rejection reliability is not greater than The dwell point of the preset credibility threshold.
  • the above density connection means that the ranges of the hot zones represented by the two trusted resident points are directly or indirectly connected.
  • the point P resides trusted coverage area coverage trusted resident 1 P 2 intersects the point, called the hot zone residence trusted dwell point P 1 and point P 2 trusted represented by the The range is directly connected, in which case the trusted resident point P 1 and the trusted resident point P 2 are connected in density; or, assuming the coverage of the trusted resident point P 1 and the trusted resident point P 3
  • the coverage of the intersection intersects, the coverage of the trusted resident point P 2 intersects the coverage of the trusted resident point P 4 , and the coverage of the trusted resident point P 3 intersects the coverage of the trusted resident point P 4
  • the range of the hot zone represented by the density of the trusted resident point P 1 and the trusted resident point P 2 is indirectly connected, in this case also referred to as the trusted resident point P 1 and the trusted resident.
  • the point P 2 density is connected.
  • the trusted resident point P 1 (which may be a leaf resident point or an internal resident point) is reachable from the internal resident point o
  • the trusted resident point P 2 (may be a leaf resident
  • the residual point which can also be an internal resident point, is connected to the density of the internal resident point o, and the density of the trusted resident point P 1 and the trusted point P 2 is said to be connected.
  • Leaf Retention Point The sum of the credibility of all dwell points within the preset radius coverage centered on the dwell point is not greater than the preset threshold.
  • Direct density up to: If a trusted resident point P (which can be a leaf resident point or an internal resident point) is within the coverage radius of a trusted resident point Q, and the trusted resident point Q For the internal resident point, then the trusted resident point P is said to be directly reachable from the trusted resident point Q.
  • a trusted resident point P which can be a leaf resident point or an internal resident point
  • all the trusted residing points connected by the density are clustered into one POI, and the closed areas formed by sequentially connecting all the leaf residing points in all the trusted residing points connected by the density are determined as one POI.
  • the area, or the area of the POI may also be a minimum circular area or a square area including all trusted resident points to which the density is connected, which is not limited herein.
  • a plurality of positioning points form a dwell point according to the positioning accuracy and the time threshold, and most of the short stay points, the positioning jump points, and the way points can be determined by the positioning accuracy and the time threshold constraint. Filtering, at the same time, combining the motion state of the anchor point in the dwell point to calculate the credibility of the dwell point and filtering out the less reliable dwell point according to the credibility of the dwell point, further filtering out part The noise dwelling point on the way (such as traffic jams, red lights, slow dwellings, etc.), so that the reliability and reference value of the location interest points finally clustered by the density-connected trusted dwelling points higher.
  • Step 1 The location point of interest clustering device uses the dynamic space threshold and the time threshold to determine a hot zone that satisfies the following two conditions from the set of anchor points shown in FIG. 2-a: 1. any two anchor points in the hot zone The geographical distance is smaller than the larger positioning accuracy of the two positioning points; 2. The maximum value of the time interval between the positioning points in the hot zone is greater than the preset time threshold. After determining the hot zone that satisfies the condition, determining the geometric center point in the hot zone as a dwelling point representing the hot zone, forming a plurality of dwelling points, and obtaining a dwell point trajectory diagram as shown in FIG. 2-b.
  • each small black dot in Figure 2-b represents a formed dwell point
  • each dwelling point can represent a large number of anchor points generated when the user stays at the same place
  • Figure 2-b and Figure 2 After comparison, it can be seen that most of the short stop points, positioning jump points and route points are filtered out in Figure 2-b.
  • Step 2 The location interest point clustering device calculates the credibility of each resident point according to the motion state of the user (such as stationary, walking, riding, etc.) at all the positioning points forming a dwell point, wherein if The smaller the average moving speed corresponding to the motion state of all the anchor points of a dwelling point, the greater the credibility of the dwelling point. For example, if there is a dwelling point, the motion state is stationary (ie, motion).
  • Step 3 performing credibility-based clustering on the above-mentioned residing points, and finding a set of the largest residing points connected to all the densities (that is, any two trusted residing points in the set are connected by density), and the maximum is
  • the residing point set is aggregated into a POI, and the POI area can be represented by a closed polygon formed by sequentially connecting all the leaf dwell points in the largest dwell point set, as shown in FIG. 2-d. .
  • Step 3 Consider the credibility of each dwelling point in the clustering process, which can improve the reliability of POI clustering, and make the range of the POI region closer to the real situation.
  • the embodiment of the present invention further provides a location point of interest clustering apparatus.
  • the location point of interest clustering apparatus 300 in the embodiment of the present invention includes: an obtaining unit 301, a resident point generating unit 302, and a calculating unit. 303. Filter unit 304 and clustering unit 305.
  • the obtaining unit 301 is configured to acquire a set of positioning points of the user in a predetermined time period
  • the set of positioning points includes one or more positioning points, and the positioning points are used to indicate location information of the user.
  • the positioning point is a GPS position point represented by a longitude value and a latitude value
  • the location point of interest clustering device acquires the set of positioning points of the user in the predetermined time period from the GPS location data of the user.
  • the residing point generating unit 302 is configured to generate a residing point set according to the set of positioning points acquired by the obtaining unit 301, where each of the residing point sets represents a hot zone, and the hot zone satisfies the following conditions: The geographical distance of any two positioning points in the hot zone is smaller than the positioning accuracy of the positioning accuracy of the two positioning points; the maximum time interval between the positioning points in the hot zone is greater than the preset time threshold;
  • the resident point generating unit 302 includes: a first determining unit 3021, configured to determine that the above a conditional hot zone; a second determining unit 3022, configured to determine a geometric center point of the hot zone as a dwell point representing the hot zone.
  • the calculating unit 303 is configured to calculate the reliability of each of the resident points in the set of the resident points, wherein the average speed corresponding to the motion state of all the positioning points in the hot zone represented by the resident point is smaller, the resident The higher the credibility of the point;
  • the calculating unit 303 includes:
  • a sub-acquisition unit configured to acquire motion states of respective positioning points included in the hot zone represented by each of the foregoing resident points
  • the foregoing sub-acquisition unit is configured to: obtain, according to the sensor data (such as acceleration, gyroscope, etc.) on the terminal of the user, or the strength and the number of the Wi-Fi network, acquire each positioning in the set of positioning points. The state of motion of the point.
  • the sensor data such as acceleration, gyroscope, etc.
  • the filtering unit 304 is configured to: according to the credibility of each of the residing points in the set of the residing points calculated by the calculating unit 303, select a trusted residing point from the set of the residing points, wherein the trusted residing The credibility of the point is greater than the preset credibility threshold;
  • the clustering unit 305 is configured to cluster the density-connected trusted resident points into a location interest point, wherein the density connection refers to directly or indirectly connecting the ranges of the hot areas represented by the two trusted resident points. Docked.
  • the clustering unit 305 is further configured to: cluster all the trusted residing points connected by the density into one location interest point; and sequentially connect all the leaf residing points in all the trusted residing points connected by the density.
  • the closed area is determined as an area of the location interest point, wherein the sum of the reliability of all the resident points within the preset radius coverage centered on the leaf resident point is not greater than the preset threshold.
  • the location interest point clustering device in the embodiment of the present invention may be a terminal (such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, or other terminal having a positioning function, etc.), or the location interest point clustering device may be A device that is independent of the terminal and can communicate with the terminal by wire or wirelessly is not limited herein.
  • location interest point clustering apparatus in the embodiment of the present invention may be implemented as described above.
  • the location point of interest clustering device in the embodiment may be used to implement all the technical solutions in the foregoing method embodiments, and the functions of the respective function modules may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the foregoing Related descriptions in the embodiments are not described herein again.
  • a plurality of positioning points form a dwell point according to the positioning accuracy and the time threshold, and most of the short stay points, the positioning jump points, and the way points can be determined by the positioning accuracy and the time threshold constraint. Filtering, at the same time, combining the motion state of the anchor point in the dwell point to calculate the credibility of the dwell point and filtering out the less reliable dwell point according to the credibility of the dwell point, further filtering out part The noise dwelling point on the way (such as traffic jams, red lights, slow dwellings, etc.), so that the reliability and reference value of the location interest points finally clustered by the density-connected trusted dwelling points higher.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores a program, and the program execution includes some or all of the arrangements described in the foregoing method embodiments.
  • the location interest point clustering apparatus 500 in the embodiment of the present invention includes:
  • the input device 501, the output device 502, the memory 503, and the processor 504 (the number of processors 504 of the location point of interest clustering device 500 may be one or more, and FIG. 5 takes a processor as an example).
  • the input device 501, the output device 502, the memory 503, and the processor 504 may be connected by a bus or other means, as shown in FIG.
  • the memory 503 is used to store data input from the input device 501, and may also store information such as necessary files processed by the processor 504; the input device 501 and the output device 502 may include the location interest point clustering device 500 and other devices.
  • the communication port may also include an output device externally connected to the location point of interest clustering device 500, such as a display, a keyboard, a mouse, a printer, etc.
  • the input device 501 may include a mouse and a keyboard, etc.
  • the output device 502 may include a display or the like.
  • the ports in the input device 501 and the output device 502 that communicate with other devices in this embodiment are antennas and/or communication cables.
  • the processor 504 performs the following steps:
  • each of the resident points in the set of the resident points represents a hot zone, and the hot zone satisfies the following condition: a geographical position of any two of the hot spots The distance is smaller than the positioning accuracy of the two positioning points; the maximum value of the time interval between the positioning points in the hot zone is greater than the preset time threshold;
  • the density-connected trusted resident points are clustered into a location interest point, wherein the density connection refers to the direct or indirect connection of the hot zone represented by the two trusted resident points.
  • the positioning point is a GPS location point represented by a longitude value and a latitude value
  • the processor 504 is configured to obtain, from the GPS location data of the user, the set of positioning points of the user within a predetermined time period.
  • the processor 504 determines that the geometric center point of the hot zone is a dwell point representing the hot zone, and the dwell point may represent all the anchor points in the hot zone.
  • the center of gravity of the hot zone is used as a dwelling point representing the hot zone, wherein the center of gravity of the hot zone is related to the distribution of the anchor points in the hot zone. .
  • the processor 504 acquires a motion state of each of the anchor points included in the hot zone represented by each of the resident points in the foregoing camping point set, according to the hot zone represented by each of the camping point sets.
  • Showing n possible motion states W k represents the credibility weight of the kth motion state, and n k represents the number of anchor points in the hot zone represented by the dwell point i as the kth motion state,
  • Each of the motion states corresponds to a credibility weight, and the smaller the motion speed corresponding to the motion state, the greater the credibility weight of the motion state.
  • the motion state is stationary, walking, or riding, for the three motion states, since the motion speed corresponding to the motion state is from small to large, it is: stationary, walking, or riding, therefore, the motion state
  • the weight of credibility is from small to small: stationary, walking or riding.
  • the processor 504 acquires the motion state of each positioning point in the set of positioning points according to the sensor data (such as acceleration, gyroscope, etc.) on the terminal of the user or the strength and number of the Wi-Fi network.
  • the location point of interest clustering device may also obtain the motion state of each of the positioning points in the set of positioning points from other positioning devices (such as a server), which is not limited herein.
  • the processor 504 clusters all trusted residing points connected by the density into one POI, and determines a closed area formed by sequentially connecting all the leaf residing points of all trusted residing points connected to the density as A region of a POI, or a region of a POI, may also be a site containing density
  • the smallest circular area or square area with a trusted resident point is not limited here.
  • the location interest point clustering device in the embodiment of the present invention may be a terminal (such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, or other terminal having a positioning function, etc.), or the location interest point clustering device may be A device that is independent of the terminal and can communicate with the terminal by wire or wirelessly is not limited herein.
  • location point of interest clustering apparatus in the embodiment of the present invention may be used as the location point of interest clustering apparatus in the foregoing method embodiments, and may be used to implement all the technical solutions in the foregoing method embodiments, and the respective functional modules.
  • specific implementation process reference may be made to the related description in the foregoing embodiments, and details are not described herein again.
  • a plurality of positioning points form a dwell point according to the positioning accuracy and the time threshold, and most of the short stay points, the positioning jump points, and the way points can be determined by the positioning accuracy and the time threshold constraint. Filtering, at the same time, combining the motion state of the anchor point in the dwell point to calculate the credibility of the dwell point and filtering out the less reliable dwell point according to the credibility of the dwell point, further filtering out part The noise dwelling point on the way (such as traffic jams, red lights, slow dwellings, etc.), so that the reliability and reference value of the location interest points finally clustered by the density-connected trusted dwelling points higher.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. You can choose some of them according to actual needs or All units are used to achieve the objectives of the solution of this embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Traffic Control Systems (AREA)
  • Information Transfer Between Computers (AREA)
  • Navigation (AREA)

Abstract

本发明实施例公开了一种位置兴趣点聚类方法和相关装置,其中,一种位置兴趣点聚类方法,包括:获取预定时间段内用户的定位点集合;根据定位点集合生成驻留点集合,其中,驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:热区中的任意两个定位点的地理位置距离小于两个定位点的定位精度中的较大定位精度;热区中定位点间的时间间隔的最大值大于预设时间阈值;计算驻留点集合中各个驻留点的可信度;根据驻留点集合中各个驻留点的可信度,从驻留点集合中筛选出可信驻留点;将密度相连的可信驻留点聚类成一个位置兴趣点。本发明提供的技术方案能够有效提高POI的可靠性和参考价值。

Description

一种位置兴趣点聚类方法和相关装置 技术领域
本发明涉及地理信息处理技术领域,尤其涉及一种位置兴趣点聚类方法和相关装置。
背景技术
位置兴趣点(POI,Point Of Interest)指的是用户频繁长时间逗留的位置区域,例如家、办公室、经常光顾的超市等对用户而言有重要意义的区域。
利用手机等终端的Wi-Fi网络、全球定位系统(GPS,Global Positioning System)、基站标识号(ID,Identity)定位功能等可以获取用户日常活动的轨迹信息,而这些轨迹信息是由大量具有定位偏差的定位坐标点组成,研究如何从这些轨迹信息中抽取出用户的POI,对于情境感知和基于位置的服务(LBS,Location-based Service)应用与服务来说具有重要的价值,目前也是学术界研究的热点。
目前存在一种基于多个用户GPS轨迹信息挖掘POI的方法,其主要思想是先利用树状分层图来对多个用户的历史位置数据进行建模,然后基于树状分层图提出基于超文本主体搜索的推理模型,对个体的一次到访建立从用户到位置的链接。
然而,上述方法通过时空维度抽取用户的驻留点,该驻留点仅能代表用户单次到访,不能代表对用户有重要意义的POI地点,且挖掘POI时只是参考了用户的历史位置数据,挖掘出的POI的可靠性和参考价值低。
发明内容
本发明实施例提供了一种位置兴趣点聚类方法和相关装置,用于提高POI的可靠性和参考价值。
本发明第一方面提供了一种位置兴趣点聚类方法,包括:
获取预定时间段内用户的定位点集合;
根据上述定位点集合生成驻留点集合,其中,上述驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:上述热区中的任意两个定位点的地理位置距离小于上述两个定位点的定位精度中的较大定位精度;上述热区中定位点间的时间间隔的最大值大于预设时间阈值;
计算上述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
根据上述驻留点集合中各个驻留点的可信度,从上述驻留点集合中筛选出可信驻留点,其中,上述可信驻留点的可信度大于预设可信度阈值;
将密度相连的可信驻留点聚类成一个位置兴趣点,其中,上述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
基于本发明第一方面,在第一种可能的实现方式中,
上述根据上述定位点集合生成驻留点集合,包括:
确定满足上述条件的热区;
确定上述热区的几何中心点为代表上述热区的驻留点。
基于本发明第一方面,或者本发明第一方面的第一种可能的实现方式,在第二种可能的实现方式中,上述计算上述驻留点集合中各个驻留点的可信度,包括:
获取上述各个驻留点代表的热区中包含的各个定位点的运动状态;
根据公式
Figure PCTCN2014088443-appb-000001
以及上述各个驻留点代表的热区中包含的各个定位点的运动状态,计算上述驻留点集合中各个驻留点的可信度,其中,Confi表示驻留点i的可信度,n表示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。
基于本发明第一方面的第二种可能的实现方式,在第三种可能的实现方式中,上述获取上述定位点集合中的各个定位点的运动状态,具体为:
根据用户的终端上的传感器数据或者Wi-Fi网络的强度和个数变化,获取上述定位点集合中的各个定位点的运动状态。
基于本发明第一方面,或者本发明第一方面的第一种可能的实现方式,或者本发明第一方面的第二种可能的实现方式,或者本发明第一方面的第三种可能的实现方式,在第四种可能的实现方式中,上述将密度相连的可信驻 留点聚类成一个位置兴趣点,包括:
将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个位置兴趣点的区域,其中,以叶子驻留点为中心的预设半径覆盖范围内的所有驻留点的可信度之和均不大于预设门限值。
本发明第二方面提供了一种位置兴趣点聚类装置,包括:
获取单元,用于获取预定时间段内用户的定位点集合;
驻留点生成单元,用于根据上述获取单元获取的定位点集合生成驻留点集合,其中,上述驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:上述热区中的任意两个定位点的地理位置距离小于上述两个定位点的定位精度中的较大定位精度;上述热区中定位点间的时间间隔的最大值大于预设时间阈值;
计算单元,用于计算上述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
过滤单元,用于根据上述计算单元计算出的上述驻留点集合中各个驻留点的可信度,从上述驻留点集合中筛选出可信驻留点,其中,上述可信驻留点的可信度大于预设可信度阈值;
聚类单元,用于将密度相连的可信驻留点聚类成一个位置兴趣点,其中,上述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
基于本发明第二方面,在第一种可能的实现方式中,
上述驻留点生成单元,包括:
第一确定单元,用于确定满足上述条件的热区;
第二确定单元,用于确定上述热区的几何中心点为代表上述热区的驻留点。
基于本发明第二方面,或者本发明第二方面的第一种可能的实现方式,在第二种可能的实现方式中,
上述计算单元,包括:
子获取单元,用于获取上述各个驻留点代表的热区中包含的各个定位点的运动状态;
子计算单元,用于根据公式
Figure PCTCN2014088443-appb-000002
以及上述子获取单元获取的上述各个驻留点代表的热区中包含的各个定位点的运动状态,计算上述驻留 点集合中各个驻留点的可信度,其中,Confi表示驻留点i的可信度,n表示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。
基于本发明第二方面的第二种可能的实现方式,在第三种可能的实现方式中,上述子获取单元具体用于:根据上述用户的终端上的传感器数据或者Wi-Fi网络的强度和个数变化,获取上述定位点集合中的各个定位点的运动状态。
基于本发明第二方面,或者本发明第二方面的第一种可能的实现方式,或者本发明第二方面的第二种可能的实现方式,或者本发明第二方面的第三种可能的实现方式,在第四种可能的实现方式中,所示聚类单元具体用于:将密度相连的所有可信驻留点聚类成一个位置兴趣点;将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个位置兴趣点的区域,其中,以叶子驻留点为中心的预设半径覆盖范围内的所有驻留点的可信度之和均不大于预设门限值。
从以上技术方案可以看出,本发明实施例具有以下优点:
由上可见,本发明实施例中根据定位精度和时间阈值将多个定位点形成一个驻留点,通过定位精度和时间阈值的约束,能够将大部分短暂停留点、定位跳变点和途经点滤除,同时,结合驻留点中的定位点的运动状态计算驻留点的可信度并根据驻留点的可信度筛选掉可信度较低的驻留点,能够进一步滤除一部分的途中噪音驻留点(如堵车路段、等红灯、缓慢步行等产生的伪驻留点),使得最终由密度相连的可信驻留点聚类成的位置兴趣点的可靠性和参考价值更高。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明提供的一种位置兴趣点聚类方法一个实施例流程示意图;
图2-a为本发明提供的一种应用场景下的定位点集合轨迹示意图;
图2-b为本发明提供的一种应用场景下形成的驻留点集合示意图;
图2-c为本发明提供的一种应用场景下筛选出的可信度驻留点集合示意;
图2-d为本发明提供的一种应用场景下聚类出的POI示意图;
图3为本发明提供的一种位置兴趣点聚类装置一个实施例结构示意图;
图4为本发明提供的一种位置兴趣点聚类装置另一个实施例结构示意图;
图5为本发明提供的一种位置兴趣点聚类装置再一个实施例结构示意图。
具体实施方式
本发明实施例提供了一种位置兴趣点聚类方法和相关装置。
为使得本发明的发明目的、特征、优点能够更加的明显和易懂,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而非全部实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的各个其他实施例,都属于本发明保护的范围。
下面对本发明实施例提供的一种位置兴趣点聚类方法进行描述,请参阅图1,本发明实施例中的位置兴趣点聚类方法,包括:
101、获取预定时间段内用户的定位点集合;
本发明实施例中定位点集合包含一个或者多个定位点,定位点用于指示用户的位置信息。
可选地,定位点为由一个经度值和一个纬度值所代表的GPS位置点,则位置兴趣点聚类装置从用户的GPS位置数据中获取预定时间段内该用户的定位点集合。
102、根据上述定位点集合生成驻留点集合;
其中,上述驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:上述热区中的任意两个定位点的地理位置距离小于上述两个定位点的定位精度中的较大定位精度;上述热区中定位点间的时间间隔的最大值大于预设时间阈值。
举例说明,假设定位点集合{Pj,Pj+1,...,Pj+L}构成一个可形成驻留点的热区,则定位点集合{Pj,Pj+1,...,Pj+L}需满足以下两个条件:
1、{Pj,Pj+1,...,Pj+L}中任意两个定位点的地理位置距离小于空间阈值Dth, 其中,Dth不是固定值,它根据所涉及的定位点的不同而不同,具体为两个定位点的定位精度的最大值,即Dth(Pn,Pm)=max(Radius(Pn),Radius(Pm))。举例说明,假设定位点P1的定位精度为5米,定位点P2的定位精度为10米,则对于定位点P1和定位点P2,Dth(P1,P2)等于定位点P1和定位点P2中的较大定位精度,即Dth(P1,P2)等于10米,若定位点P3的定位精度为15米,则对于定位点P1和定位点P3,Dth(P1,P3)等于定位点P1和定位点P3中的较大定位精度,即Dth(P1,P3)等于15米。
2、由于不同的定位点是在不同的时间点测得,因此,每两个定位点间存在时间间隔,例如,假设定位点P1在10:00测得,定位点P2在10:03测得,则定位点P1和定位点P3的时间间隔为3分钟。本发明实施例中,{Pj,Pj+1,...,Pj+L}还需要满足:{Pj,Pj+1,...,Pj+L}中定位点间的时间间隔的最大值大于预设时间阈值Tth(例如,Tth可取5分钟、7分钟或10分钟等),即{Pj,Pj+1,...,Pj+L}中最先测得的定位点和最后测得的定位点之间的时间间隔大于Tth。其中,Tth可以根据实际需要具体设定,此处不作限定。
可选地,在确定满足上述条件的热区后,确定上述热区的几何中心点为代表上述热区的驻留点,该驻留点可以代表热区中的所有定位点。当然,也可以采用其它方式确定一个热区所对应的驻留点,例如,取热区的重心作为代表该热区的驻留点,其中,热区的重心与热区内定位点分布情况相关。
103、计算上述驻留点集合中各个驻留点的可信度;
其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高。
在一种实现方式中,位置兴趣点聚类装置获取上述驻留点集合中各个驻留点代表的热区所包含的各个定位点的运动状态,根据上述驻留点集合中各个驻留点代表的热区所包含的各个定位点的运动状态以及公式
Figure PCTCN2014088443-appb-000003
动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。例如,假设用户可能的运动状态为静止、步行或乘车,则对于这三种运动状态,由于运动状态对应的运动速度由小到大依次为:静止、步行或乘车,因此,运动状态的可信度权重由大到小依次为:静止、步行或乘车。
可选地,位置兴趣点聚类装置根据上述用户的终端(如手机、平板电脑、车载终端等)上的传感器数据(如加速度、陀螺仪等)或者Wi-Fi网络的强度和个数变化,获取上述定位点集合中的各个定位点的运动状态;或者,位置兴趣点聚类装置也可以从其它定位设备(如服务器)获取上述定位点集合中的各个定位点的运动状态,此处不作限定。
104、根据上述驻留点集合中各个驻留点的可信度,从上述驻留点集合中筛选出可信驻留点;
其中,上述可信驻留点的可信度大于预设可信度阈值。
本发明实施例中,位置兴趣点聚类装置从上述驻留点集合中筛选出可信驻留点(即可信度大于预设可信度阈值的驻留点),剔除可信度不大于预设可信度阈值的驻留点。
105、将密度相连的可信驻留点聚类成一个POI;
其中,上述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。举例说明,假设可信驻留点P1的覆盖范围与可信驻留点P2的覆盖范围相交,则称可信驻留点P1和可信驻留点P2所代表的热区的范围直接相接,在这种情况下,可信驻留点P1和可信驻留点P2密度相连;或者,假设可信驻留点P1的覆盖范围与可信驻留点P3的覆盖范围相交,可信驻留点P2的覆盖范围与可信驻留点P4的覆盖范围相交,可信驻留点P3的覆盖范围与可信驻留点P4的覆盖范围相交,则称可信驻留点P1和可信驻留点P2密度所代表的热区的范围间接相接,在这种情况下,也称可信驻留点P1和可信驻留点P2密度相连。
可选地,若可信驻留点P1(可以是叶子驻留点,也可以是内部驻留点)从内部驻留点o密度可达,可信驻留点P2(可以是叶子驻留点,也可以是内部驻留点)从内部驻留点o密度可达,则称可信驻留点P1和信驻留点P2密度相连。下面对“内部驻留点”、“叶子驻留点”和“密度可达”进行说明。
内部驻留点:以该驻留点为中心的预设半径覆盖内的所有驻留点的可信度之和大于预设门限值。
叶子驻留点:以该驻留点为中心的预设半径覆盖内的所有驻留点的可信度之和不大于预设门限值。
密度可达:给定一串可信驻留点p1,p2,......pn,其中pi(0<i<n)必需是内部驻留点,pn可以是叶子驻留点或内部驻留点,P=p1,Q=pn,假设pi从pi-1(1<i<(n+1))直接密度可达,那么驻留点Q从内部驻留点P密度可达。
直接密度可达:如果一个可信驻留点P(可以是叶子驻留点,也可以是内部驻留点)在某一可信驻留点Q的覆盖半径内,并且可信驻留点Q为内部驻留点,那么称可信驻留点P从可信驻留点Q直接密度可达。
可选地,将密度相连的所有可信驻留点聚类成一个POI,并且,将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个POI的区域,或者,POI的区域也可以为包含密度相连的所有可信驻留点的最小圆形区域或者方形区域,此处不作限定。
由上可见,本发明实施例中根据定位精度和时间阈值将多个定位点形成一个驻留点,通过定位精度和时间阈值的约束,能够将大部分短暂停留点、定位跳变点和途经点滤除,同时,结合驻留点中的定位点的运动状态计算驻留点的可信度并根据驻留点的可信度筛选掉可信度较低的驻留点,能够进一步滤除一部分的途中噪音驻留点(如堵车路段、等红灯、缓慢步行等产生的伪驻留点),使得最终由密度相连的可信驻留点聚类成的位置兴趣点的可靠性和参考价值更高。
为便于更好地理解本发明技术方案,下面以一具体应用场景对本发明实施例中的位置兴趣点聚类方法进行描述。
假设预定时间段内用户的定位点集合的轨迹如图2-a所示。
步骤一:位置兴趣点聚类装置使用动态空间阈值和时间阈值,从图2-a所示的定位点集合中确定满足如下两个条件的热区:1、热区中的任意两个定位点的地理位置距离小于上述两个定位点中的较大定位精度;2、热区中定位点间的时间间隔的最大值大于预设时间阈值。在确定出满足条件的热区后,确定热区中的几何中心点作为代表该热区的驻留点,形成若干个驻留点,得到如图2-b所示的驻留点轨迹图,其中,图2-b中的每个小黑点代表一个形成的驻留点,每个驻留点能够表征用户在同一地点逗留时所产生的大量定位点,将图2-b与图2-a比较后可见,图2-b中滤除掉了大部分短暂停留点、定位跳变点和途径点。
步骤二:位置兴趣点聚类装置依据形成一个驻留点的所有定位点上用户的运动状态(如静止、步行、乘车等),分别计算出各个驻留点的可信度,其中,若用户在一个驻留点的所有定位点的运动状态所对应的平均运动速度越小,则该驻留点的可信度越大,比如,若一个驻留点上,运动状态为静止(即运动速度为0)的定位点占形成该驻留点的所有定位点的比重越多,则该驻留点的可信 度越大,反之,若一个驻留点上,运动状态为乘车(即运动速度远大于0)的定位点占形成该驻留点的所有定位点的比重越多,则该驻留点的可信度越小。在计算出每个驻留点的可信度后,从图2-b所示的驻留点集合中剔除可信度不大于预设可信度阈值的驻留点,即从图2-b所示的驻留点集合中筛选出可信度大于预设可信度阈值的驻留点,得到如图2-c所示的可信驻留点集合。将图2-c与图2-b比较后可见,图2-c对一部分途中噪音驻留点(例如:堵车路段、等红灯、缓慢步行对应的伪驻留点)进行了滤除。
步骤三、对上述驻留点进行基于可信度的聚类,找出所有密度相连的最大驻留点集合(即该集合中任意两个可信驻留点都为密度相连),将该最大驻留点集合聚成一个POI,该POI的区域可以由该最大驻留点集合中所有叶子驻留点依次连接形成的封闭多边形来表示,如图2-d所示的聚类得到的POI示意图。步骤三在聚类过程中考虑各驻留点的可信度,能提高POI聚类的可靠性,使POI包含的区域范围更趋近于真实情况。
本发明实施例还提供一种位置兴趣点聚类装置,如图3所示,本发明实施例中的位置兴趣点聚类装置300,包括:获取单元301,驻留点生成单元302,计算单元303,过滤单元304和聚类单元305。
其中:
获取单元301,用于获取预定时间段内用户的定位点集合;
本发明实施例中定位点集合包含一个或者多个定位点,定位点用于指示用户的位置信息。
可选地,定位点为由一个经度值和一个纬度值所代表的GPS位置点,则位置兴趣点聚类装置从用户的GPS位置数据中获取预定时间段内该用户的定位点集合。
驻留点生成单元302,用于根据获取单元301获取的定位点集合生成驻留点集合,其中,上述驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:上述热区中的任意两个定位点的地理位置距离小于上述两个定位点的定位精度中的较大定位精度;上述热区中定位点间的时间间隔的最大值大于预设时间阈值;
可选地,在图3所示实施例的基础上,如图4所示的位置兴趣点聚类装置400,驻留点生成单元302包括:第一确定单元3021,用于确定满足上述 条件的热区;第二确定单元3022,用于确定上述热区的几何中心点为代表上述热区的驻留点。
计算单元303,用于计算上述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
可选地,在图3或图4所示实施例的基础上,计算单元303包括:
子获取单元,用于获取上述各个驻留点代表的热区中包含的各个定位点的运动状态;
Figure PCTCN2014088443-appb-000004
驻留点集合中各个驻留点的可信度,其中,Confi表示驻留点i的可信度,n表示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。
可选地,上述子获取单元具体用于:根据上述用户的终端上的传感器数据(如加速度、陀螺仪等)或者Wi-Fi网络的强度和个数变化,获取上述定位点集合中的各个定位点的运动状态。
过滤单元304,用于根据计算单元303计算出的上述驻留点集合中各个驻留点的可信度,从上述驻留点集合中筛选出可信驻留点,其中,上述可信驻留点的可信度大于预设可信度阈值;
聚类单元305,用于将密度相连的可信驻留点聚类成一个位置兴趣点,其中,上述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
可选地,聚类单元305还用于:将密度相连的所有可信驻留点聚类成一个位置兴趣点;将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个位置兴趣点的区域,其中,以叶子驻留点为中心的预设半径覆盖范围内的所有驻留点的可信度之和均不大于预设门限值。
需要说明的是,本发明实施例中的位置兴趣点聚类装置可以为终端(如手机、平板电脑、笔记本、台式计算机或其它具备定位功能的终端等),或者,位置兴趣点聚类装置可以为独立于终端,且能够与该终端通过有线或者无线方式进行通讯的装置,此处不作限定。
需要说明的是,本发明实施例中的位置兴趣点聚类装置可以如上述方法实 施例中的位置兴趣点聚类装置,可以用于实现上述方法实施例中的全部技术方案,其各个功能模块的功能可以根据上述方法实施例中的方法具体实现,其具体实现过程可参照上述实施例中的相关描述,此处不再赘述。
由上可见,本发明实施例中根据定位精度和时间阈值将多个定位点形成一个驻留点,通过定位精度和时间阈值的约束,能够将大部分短暂停留点、定位跳变点和途经点滤除,同时,结合驻留点中的定位点的运动状态计算驻留点的可信度并根据驻留点的可信度筛选掉可信度较低的驻留点,能够进一步滤除一部分的途中噪音驻留点(如堵车路段、等红灯、缓慢步行等产生的伪驻留点),使得最终由密度相连的可信驻留点聚类成的位置兴趣点的可靠性和参考价值更高。
本发明实施例还提供一种计算机存储介质,其中,该计算机存储介质存储有程序,该程序执行包括上述方法实施例中记载的部分或全部布置。
下面对本发明实施中的另一种应用于对等网络的设备进行描述,请参阅图5,本发明实施例中的位置兴趣点聚类装置500包括:
输入装置501、输出装置502、存储器503以及处理器504(位置兴趣点聚类装置500的处理器504的数量可以是一个或者多个,图5以一个处理器为例)。在本发明的一些实施例中,输入装置501、输出装置502、存储器503以及处理器504可以通过总线或其它方式连接,如图5所示是以通过总线连接为例。其中,存储器503中用来储存从输入装置501输入的数据,且还可以储存处理器504处理数据的必要文件等信息;输入装置501和输出装置502可以包括位置兴趣点聚类装置500与其他设备通信的端口,且还可以包括位置兴趣点聚类装置500外接的输出设备比如显示器、键盘、鼠标和打印机等,具体地输入装置501可以包括鼠标和键盘等,而输出装置502可以包括显示器等,在本实施例中输入装置501和输出装置502中与其他设备通信的端口为天线和/或通信线缆。
其中,处理器504执行如下步骤:
获取预定时间段内用户的定位点集合;
根据上述定位点集合生成驻留点集合,其中,上述驻留点集合中的每个驻留点代表一个热区,上述热区满足如下条件:上述热区中的任意两个定位点的地理位置距离小于上述两个定位点的定位精度中的较大定位精度;上述热区中定位点间的时间间隔的最大值大于预设时间阈值;
计算上述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
根据上述驻留点集合中各个驻留点的可信度,从上述驻留点集合中筛选出可信驻留点,其中,上述可信驻留点的可信度大于预设可信度阈值;
将密度相连的可信驻留点聚类成一个位置兴趣点,其中,上述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
可选地,定位点为由一个经度值和一个纬度值所代表的GPS位置点,则处理器504用于从用户的GPS位置数据中获取预定时间段内该用户的定位点集合。
可选地,处理器504在确定满足上述条件的热区后,确定上述热区的几何中心点为代表上述热区的驻留点,该驻留点可以代表热区中的所有定位点。当然,也可以采用其它方式确定一个热区所对应的驻留点,例如,取热区的重心作为代表该热区的驻留点,其中,热区的重心与热区内定位点分布情况相关。
可选地,处理器504获取上述驻留点集合中各个驻留点代表的热区所包含的各个定位点的运动状态,根据上述驻留点集合中各个驻留点代表的热区
Figure PCTCN2014088443-appb-000005
示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。例如,假设用户可能的运动状态为静止、步行或乘车,则对于这三种运动状态,由于运动状态对应的运动速度由小到大依次为:静止、步行或乘车,因此,运动状态的可信度权重由大到小依次为:静止、步行或乘车。
可选地,处理器504根据上述用户的终端上的传感器数据(如加速度、陀螺仪等)或者Wi-Fi网络的强度和个数变化,获取上述定位点集合中的各个定位点的运动状态;或者,位置兴趣点聚类装置也可以从其它定位设备(如服务器)获取上述定位点集合中的各个定位点的运动状态,此处不作限定。
可选地,处理器504将密度相连的所有可信驻留点聚类成一个POI,并且,将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个POI的区域,或者,POI的区域也可以为包含密度相连的所 有可信驻留点的最小圆形区域或者方形区域,此处不作限定。
需要说明的是,本发明实施例中的位置兴趣点聚类装置可以为终端(如手机、平板电脑、笔记本、台式计算机或其它具备定位功能的终端等),或者,位置兴趣点聚类装置可以为独立于终端,且能够与该终端通过有线或者无线方式进行通讯的装置,此处不作限定。
需要说明的是,本发明实施例中的位置兴趣点聚类装置可以如上述方法实施例中的位置兴趣点聚类装置,可以用于实现上述方法实施例中的全部技术方案,其各个功能模块的功能可以根据上述方法实施例中的方法具体实现,其具体实现过程可参照上述实施例中的相关描述,此处不再赘述。
由上可见,本发明实施例中根据定位精度和时间阈值将多个定位点形成一个驻留点,通过定位精度和时间阈值的约束,能够将大部分短暂停留点、定位跳变点和途经点滤除,同时,结合驻留点中的定位点的运动状态计算驻留点的可信度并根据驻留点的可信度筛选掉可信度较低的驻留点,能够进一步滤除一部分的途中噪音驻留点(如堵车路段、等红灯、缓慢步行等产生的伪驻留点),使得最终由密度相连的可信驻留点聚类成的位置兴趣点的可靠性和参考价值更高。
需要说明的是,对于前述的各方法实施例,为了简便描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本发明,某些步骤可以采用其它顺序或者同时进行。在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其它实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或 者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上对本发明所提供的一种位置兴趣点聚类方法和相关装置进行了详细介绍,对于本领域的一般技术人员,依据本发明实施例的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种位置兴趣点聚类方法,其特征在于,包括:
    获取预定时间段内用户的定位点集合;
    根据所述定位点集合生成驻留点集合,其中,所述驻留点集合中的每个驻留点代表一个热区,所述热区满足如下条件:所述热区中的任意两个定位点的地理位置距离小于所述两个定位点的定位精度中的较大定位精度;所述热区中定位点间的时间间隔的最大值大于预设时间阈值;
    计算所述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
    根据所述驻留点集合中各个驻留点的可信度,从所述驻留点集合中筛选出可信驻留点,其中,所述可信驻留点的可信度大于预设可信度阈值;
    将密度相连的可信驻留点聚类成一个位置兴趣点,其中,所述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
  2. 根据权利要求1所述的方法,其特征在于,
    所述根据所述定位点集合生成驻留点集合,包括:
    确定满足所述条件的热区;
    确定所述热区的几何中心点为代表所述热区的驻留点。
  3. 根据权利要求1或2所述的方法,其特征在于,
    所述计算所述驻留点集合中各个驻留点的可信度,包括:
    获取所述各个驻留点代表的热区中包含的各个定位点的运动状态;
    Figure PCTCN2014088443-appb-100001
    中,Confi表示驻留点i的可信度,n表示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。
  4. 根据权利要求3所述的方法,其特征在于,所述获取所述定位点集合中的各个定位点的运动状态,具体为:
    根据用户的终端上的传感器数据或者Wi-Fi网络的强度和个数变化,获 取所述定位点集合中的各个定位点的运动状态。
  5. 根据权利要求1至4任一项所述的方法,其特征在于,
    所述将密度相连的可信驻留点聚类成一个位置兴趣点,包括:
    将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个位置兴趣点的区域,其中,以叶子驻留点为中心的预设半径覆盖范围内的所有驻留点的可信度之和均不大于预设门限值。
  6. 一种位置兴趣点聚类装置,其特征在于,包括:
    获取单元,用于获取预定时间段内用户的定位点集合;
    驻留点生成单元,用于根据所述获取单元获取的定位点集合生成驻留点集合,其中,所述驻留点集合中的每个驻留点代表一个热区,所述热区满足如下条件:所述热区中的任意两个定位点的地理位置距离小于所述两个定位点的定位精度中的较大定位精度;所述热区中定位点间的时间间隔的最大值大于预设时间阈值;
    计算单元,用于计算所述驻留点集合中各个驻留点的可信度,其中,驻留点代表的热区中的所有定位点的运动状态所对应的平均速度越小,该驻留点的可信度越高;
    过滤单元,用于根据所述计算单元计算出的所述驻留点集合中各个驻留点的可信度,从所述驻留点集合中筛选出可信驻留点,其中,所述可信驻留点的可信度大于预设可信度阈值;
    聚类单元,用于将密度相连的可信驻留点聚类成一个位置兴趣点,其中,所述密度相连是指两个可信驻留点所代表的热区的范围直接相接或间接相接。
  7. 根据权利要求6所述的位置兴趣点聚类装置,其特征在于,
    所述驻留点生成单元,包括:
    第一确定单元,用于确定满足所述条件的热区;
    第二确定单元,用于确定所述热区的几何中心点为代表所述热区的驻留点。
  8. 根据权利要求6或7所述的位置兴趣点聚类装置,其特征在于,
    所述计算单元,包括:
    子获取单元,用于获取所述各个驻留点代表的热区中包含的各个定位点的运动状态;
    Figure PCTCN2014088443-appb-100002
    驻留点集合中各个驻留点的可信度,其中,Confi表示驻留点i的可信度,n表示n种可能的运动状态,Wk表示第k种运动状态的可信度权重,nk表示驻留点i所代表的热区中运动状态为第k种运动状态的定位点的个数,其中,每种运动状态对应一个可信度权重,且运动状态对应的运动速度越小,该运动状态的可信度权重越大。
  9. 根据权利要求8所述的位置兴趣点聚类装置,其特征在于,
    所述子获取单元具体用于:根据所述用户的终端上的传感器数据或者Wi-Fi网络的强度和个数变化,获取所述定位点集合中的各个定位点的运动状态。
  10. 根据权利要求6至9任一项所述的位置兴趣点聚类装置,其特征在于,所示聚类单元具体用于:将密度相连的所有可信驻留点聚类成一个位置兴趣点;将密度相连的所有可信驻留点中的所有叶子驻留点依次连接形成的封闭区域确定为一个位置兴趣点的区域,其中,以叶子驻留点为中心的预设半径覆盖范围内的所有驻留点的可信度之和均不大于预设门限值。
PCT/CN2014/088443 2013-11-07 2014-10-13 一种位置兴趣点聚类方法和相关装置 WO2015067119A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020167013679A KR101806948B1 (ko) 2013-11-07 2014-10-13 관심 지점을 위한 클러스터링 방법 및 관련 장치
EP14860583.5A EP3056999B1 (en) 2013-11-07 2014-10-13 Method for clustering position points of interest and related device
JP2016528174A JP6225257B2 (ja) 2013-11-07 2014-10-13 関心ポイントのクラスタリング方法及び関連する装置
US15/148,365 US10423728B2 (en) 2013-11-07 2016-05-06 Clustering method for a point of interest and related apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310552636.2A CN104636354B (zh) 2013-11-07 2013-11-07 一种位置兴趣点聚类方法和相关装置
CN201310552636.2 2013-11-07

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/148,365 Continuation US10423728B2 (en) 2013-11-07 2016-05-06 Clustering method for a point of interest and related apparatus

Publications (1)

Publication Number Publication Date
WO2015067119A1 true WO2015067119A1 (zh) 2015-05-14

Family

ID=53040886

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/088443 WO2015067119A1 (zh) 2013-11-07 2014-10-13 一种位置兴趣点聚类方法和相关装置

Country Status (6)

Country Link
US (1) US10423728B2 (zh)
EP (1) EP3056999B1 (zh)
JP (1) JP6225257B2 (zh)
KR (1) KR101806948B1 (zh)
CN (1) CN104636354B (zh)
WO (1) WO2015067119A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110990455A (zh) * 2019-11-29 2020-04-10 杭州数梦工场科技有限公司 大数据识别房屋性质的方法与系统
CN113075648A (zh) * 2021-03-19 2021-07-06 中国舰船研究设计中心 一种无人集群目标定位信息的聚类与滤波方法

Families Citing this family (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106294485B (zh) * 2015-06-05 2019-11-01 华为技术有限公司 确定显著地点的方法及装置
CN105159926B (zh) * 2015-08-04 2019-04-16 百度在线网络技术(北京)有限公司 建立用户的用户信息关联的方法和装置
CN106568429B (zh) * 2015-10-09 2019-12-06 阿里巴巴集团控股有限公司 一种建立兴趣点的方法及装置
CN105682025B (zh) * 2016-01-05 2019-01-04 重庆邮电大学 基于移动信令数据的用户驻留地识别方法
BR112018072934A2 (pt) * 2016-05-09 2019-02-19 Tata Consultancy Services Limited método e sistema para alcançar agrupamento auto-adaptativo em cluster em uma rede sensorial
CN106096639B (zh) * 2016-06-06 2019-04-09 华侨大学 一种基于密度热度的电离层雷达数据的聚类方法
CN106202236A (zh) * 2016-06-28 2016-12-07 联想(北京)有限公司 一种用户位置预测方法及装置
CN106846795A (zh) * 2017-01-04 2017-06-13 百度在线网络技术(北京)有限公司 人群密集区域的获取方法及装置
CN108287841A (zh) * 2017-01-09 2018-07-17 北京四维图新科技股份有限公司 景点数据采集和更新方法及系统、游客终端设备及助导游设备
CN106840165B (zh) * 2017-01-17 2019-11-12 中国地质大学(武汉) 一种语义位置历史的构建方法及装置
CN108536695B (zh) * 2017-03-02 2021-06-04 北京嘀嘀无限科技发展有限公司 一种地理位置信息点的聚合方法以及装置
CN107289925B (zh) * 2017-05-25 2021-03-05 北京奇鱼时代科技有限公司 一种绘制用户轨迹的方法和装置
WO2018227373A1 (zh) * 2017-06-13 2018-12-20 深圳市伊特利网络科技有限公司 基于定位的报警方法及系统
CN107491474A (zh) * 2017-06-26 2017-12-19 北京三快在线科技有限公司 信息推荐方法和装置
CN109900281A (zh) * 2017-12-08 2019-06-18 北京搜狗科技发展有限公司 基于兴趣点的导航方法、装置以及用于导航的装置
CN108303100A (zh) * 2017-12-25 2018-07-20 厦门市美亚柏科信息股份有限公司 聚焦点分析方法及计算机可读存储介质
CN108307308B (zh) * 2018-01-25 2021-09-14 北京小米移动软件有限公司 无线局域网设备的定位方法、装置和存储介质
CN110873571B (zh) * 2018-08-30 2021-09-07 北京嘀嘀无限科技发展有限公司 一种路口停车线数据采集方法、系统和装置
CN109189876B (zh) * 2018-08-31 2021-09-10 深圳市元征科技股份有限公司 一种数据处理方法及装置
CN110888979A (zh) * 2018-09-10 2020-03-17 中国移动通信集团有限公司 一种兴趣区域提取方法、装置及计算机存储介质
CN109256029B (zh) * 2018-09-12 2021-09-03 广州小鹏汽车科技有限公司 一种地点属性的自动设置方法及装置
CN109168195B (zh) * 2018-10-25 2020-08-28 北京搜狐新媒体信息技术有限公司 一种定位信息提取方法及服务平台
CN111126653B (zh) * 2018-11-01 2022-06-17 百度在线网络技术(北京)有限公司 用户职住地预测方法、装置及存储介质
KR102213276B1 (ko) * 2018-11-27 2021-02-04 공주대학교 산학협력단 이동 경로 정보를 이용한 주소 인증 장치 및 방법
CN111380541B (zh) * 2018-12-29 2022-09-13 沈阳美行科技股份有限公司 兴趣点确定方法、装置、计算机设备和存储介质
CN109813318A (zh) * 2019-02-12 2019-05-28 北京百度网讯科技有限公司 坐标修正方法及装置、设备及存储介质
CN110213714B (zh) * 2019-05-10 2020-08-14 中国联合网络通信集团有限公司 终端定位的方法及装置
US11860911B2 (en) * 2019-08-20 2024-01-02 International Business Machines Corporation Method and apparatus of data classification for routes in a digitized map
CN110544132B (zh) * 2019-09-06 2023-04-07 上海喜马拉雅科技有限公司 用户常活动位置的确定方法、装置、设备和存储介质
CN110705480B (zh) * 2019-09-30 2022-12-02 重庆紫光华山智安科技有限公司 目标对象的停留点定位方法及相关装置
CN110850955B (zh) * 2019-10-30 2023-06-02 腾讯科技(深圳)有限公司 终端的位置信息处理方法、装置及计算设备、存储介质
CN110781855B (zh) * 2019-11-04 2022-12-06 浙江大华技术股份有限公司 目标停留点的确定方法、装置、设备及存储装置
CN111159583B (zh) * 2019-12-31 2023-08-04 中国联合网络通信集团有限公司 用户行为分析方法、装置、设备及存储介质
CN111898624B (zh) * 2020-01-21 2024-04-02 北京畅行信息技术有限公司 定位信息的处理方法、装置、设备及存储介质
CN112765226A (zh) * 2020-12-06 2021-05-07 复旦大学 基于轨迹数据挖掘的城市语义图谱构建方法
CN112749349A (zh) * 2020-12-31 2021-05-04 北京搜狗科技发展有限公司 一种交互方法和耳机设备
CN115083161B (zh) * 2022-06-15 2023-08-04 平安国际融资租赁有限公司 车辆停留点的评估方法、装置、电子设备及可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102595323A (zh) * 2012-03-20 2012-07-18 北京交通发展研究中心 基于手机定位数据的居民出行特征参数的获取方法
CN102682041A (zh) * 2011-03-18 2012-09-19 日电(中国)有限公司 用户行为识别设备及方法
WO2013060925A1 (en) * 2011-10-28 2013-05-02 Nokia Corporation Method and apparatus for constructing a road network based on point-of-interest (poi) information
CN103218442A (zh) * 2013-04-22 2013-07-24 中山大学 一种基于移动设备传感器数据的生活模式分析方法及系统

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5844522A (en) * 1995-10-13 1998-12-01 Trackmobile, Inc. Mobile telephone location system and method
CA2265875C (en) * 1996-09-09 2007-01-16 Dennis Jay Dupray Location of a mobile station
US7082365B2 (en) 2001-08-16 2006-07-25 Networks In Motion, Inc. Point of interest spatial rating search method and system
US7289105B2 (en) * 2003-06-04 2007-10-30 Vrbia, Inc. Real motion detection sampling and recording for tracking and writing instruments using electrically-active viscous material and thin films
JP5362544B2 (ja) 2006-03-15 2013-12-11 クゥアルコム・インコーポレイテッド ユーザのルートに基づいて関連性のある対象地点の情報を決定する方法および装置
US20080036758A1 (en) 2006-03-31 2008-02-14 Intelisum Inc. Systems and methods for determining a global or local position of a point of interest within a scene using a three-dimensional model of the scene
WO2008097694A1 (en) * 2007-02-05 2008-08-14 Andrew Corporation System and method for optimizing location estimate of mobile unit
EP2145265A4 (en) 2007-03-30 2011-09-14 Amazon Tech Inc CLUSTER-BASED ASSESSMENT OF USER INTERESTS
US8396470B2 (en) * 2007-04-26 2013-03-12 Research In Motion Limited Predicting user availability from aggregated signal strength data
US8339399B2 (en) 2007-10-31 2012-12-25 Microsoft Corporation Declustering point-of-interest icons
JP5049745B2 (ja) * 2007-11-05 2012-10-17 株式会社エヌ・ティ・ティ・ドコモ 位置情報解析装置、情報配信システムおよび位置情報解析方法
US8634796B2 (en) * 2008-03-14 2014-01-21 William J. Johnson System and method for location based exchanges of data facilitating distributed location applications
US9078095B2 (en) * 2008-03-14 2015-07-07 William J. Johnson System and method for location based inventory management
US8527308B2 (en) * 2008-10-02 2013-09-03 Certusview Technologies, Llc Methods and apparatus for overlaying electronic locate information on facilities map information and/or other image information displayed on a locate device
US8358224B2 (en) 2009-04-02 2013-01-22 GM Global Technology Operations LLC Point of interest location marking on full windshield head-up display
US20120046995A1 (en) * 2009-04-29 2012-02-23 Waldeck Technology, Llc Anonymous crowd comparison
US8335990B2 (en) 2009-08-18 2012-12-18 Nokia Corporation Method and apparatus for grouping points-of-interest on a map
WO2011046113A1 (ja) 2009-10-14 2011-04-21 日本電気株式会社 行動類型抽出システム、装置、方法、プログラムを記憶した記録媒体
CN101742545B (zh) * 2009-12-15 2012-11-14 中国科学院计算技术研究所 WiFi环境中的定位方法及其系统
US8543143B2 (en) 2009-12-23 2013-09-24 Nokia Corporation Method and apparatus for grouping points-of-interest according to area names
JP5536485B2 (ja) * 2010-02-17 2014-07-02 Kddi株式会社 ユーザの移動に伴って住所/居所を推定する携帯端末、サーバ、プログラム及び方法
WO2012080787A1 (en) * 2010-12-17 2012-06-21 Nokia Corporation Identification of points of interest and positioning based on points of interest
US9497584B2 (en) 2011-01-14 2016-11-15 Nec Corporation Action pattern analysis device, action pattern analysis method, and action pattern analysis program
US20130262479A1 (en) * 2011-10-08 2013-10-03 Alohar Mobile Inc. Points of interest (poi) ranking based on mobile user related data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102682041A (zh) * 2011-03-18 2012-09-19 日电(中国)有限公司 用户行为识别设备及方法
WO2013060925A1 (en) * 2011-10-28 2013-05-02 Nokia Corporation Method and apparatus for constructing a road network based on point-of-interest (poi) information
CN102595323A (zh) * 2012-03-20 2012-07-18 北京交通发展研究中心 基于手机定位数据的居民出行特征参数的获取方法
CN103218442A (zh) * 2013-04-22 2013-07-24 中山大学 一种基于移动设备传感器数据的生活模式分析方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3056999A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110990455A (zh) * 2019-11-29 2020-04-10 杭州数梦工场科技有限公司 大数据识别房屋性质的方法与系统
CN110990455B (zh) * 2019-11-29 2023-10-17 杭州数梦工场科技有限公司 大数据识别房屋性质的方法与系统
CN113075648A (zh) * 2021-03-19 2021-07-06 中国舰船研究设计中心 一种无人集群目标定位信息的聚类与滤波方法
CN113075648B (zh) * 2021-03-19 2024-05-17 中国舰船研究设计中心 一种无人集群目标定位信息的聚类与滤波方法

Also Published As

Publication number Publication date
EP3056999A1 (en) 2016-08-17
JP2016537718A (ja) 2016-12-01
JP6225257B2 (ja) 2017-11-01
CN104636354A (zh) 2015-05-20
KR101806948B1 (ko) 2017-12-08
CN104636354B (zh) 2018-02-06
KR20160075686A (ko) 2016-06-29
US10423728B2 (en) 2019-09-24
EP3056999A4 (en) 2016-11-23
EP3056999B1 (en) 2019-02-06
US20160253407A1 (en) 2016-09-01

Similar Documents

Publication Publication Date Title
WO2015067119A1 (zh) 一种位置兴趣点聚类方法和相关装置
Vo et al. A survey of fingerprint-based outdoor localization
US20140343984A1 (en) Spatial crowdsourcing with trustworthy query answering
US20120295639A1 (en) Discovering nearby places based on automatic query
US10467311B2 (en) Communication system and method of generating geographic social networks in virtual space
CN107409288B (zh) 用于基于隐匿轨迹发现社会联系的方法和装置
Yamaguchi et al. Landmark-based user location inference in social media
Chen et al. Range-free localization scheme in wireless sensor networks based on bilateration
PH12014501098B1 (en) Method and server for searching for nearby user in social networking services
CN107220312B (zh) 一种基于共现图的兴趣点推荐方法及系统
Kantarci et al. Mobility-aware trustworthy crowdsourcing in cloud-centric Internet of Things
US20230206034A1 (en) Prediction of Next Place Visits on Online Social Networks
Chen et al. Outlier-detection-based indoor localization system for wireless sensor networks
Chen et al. Privacy-aware high-quality map generation with participatory sensing
Redžić et al. Image and wlan bimodal integration for indoor user localization
US10506383B2 (en) Location prediction using wireless signals on online social networks
EP3966598A1 (en) Privacy management
Xu et al. Variance-based fingerprint distance adjustment algorithm for indoor localization
US10409857B2 (en) Method and system of generating and using a geographical hierarchy model
WO2013030439A2 (en) Method and apparatus for determining environmental context utilizing features obtained by multiple radio receivers
Huang et al. The personalized context‐aware mobile advertisement system using a novel approaching detection method over cellular networks
EP4258766A1 (en) Data processing method and apparatus
US20170169025A1 (en) Estimating Geographic Entity Capacity
US20220122738A1 (en) Method and system for contact tracing using positioning in a venue
Zhou et al. Inferring individual physical locations with social friendships

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14860583

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2016528174

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2014860583

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014860583

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 20167013679

Country of ref document: KR

Kind code of ref document: A