WO2020168767A1 - 基于用户位置确定地理围栏 - Google Patents

基于用户位置确定地理围栏 Download PDF

Info

Publication number
WO2020168767A1
WO2020168767A1 PCT/CN2019/120218 CN2019120218W WO2020168767A1 WO 2020168767 A1 WO2020168767 A1 WO 2020168767A1 CN 2019120218 W CN2019120218 W CN 2019120218W WO 2020168767 A1 WO2020168767 A1 WO 2020168767A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
aggregation point
aggregation
point
latitude
Prior art date
Application number
PCT/CN2019/120218
Other languages
English (en)
French (fr)
Inventor
张志强
甘彪
丁求伟
Original Assignee
北京三快在线科技有限公司
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 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2020168767A1 publication Critical patent/WO2020168767A1/zh
Priority to US17/407,905 priority Critical patent/US20210385610A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment

Definitions

  • This application relates to the field of computer technology, in particular to determining a geofence based on the user's location.
  • a geofence is a virtual geographic boundary, which represents a geographic area. When the user device enters or exits the area, the corresponding geofence event will be triggered.
  • the application can capture the geofence event of interest and perform corresponding operations.
  • the shape of the geofence can be a circle composed of points and a radius, or a polygon composed of a batch of latitude and longitude points. The determination of geo-fencing has great value.
  • the method for determining a geofence in the prior art is usually: clustering the latitude and longitude coordinates to obtain one or more latitude and longitude coordinate clusters, where each cluster includes multiple latitude and longitude coordinates, and generating the geofence based on the boundary points of the clusters .
  • data aggregation methods such as the K-Means algorithm are complicated and inefficient, and they need to specify the initialization clustering center, specify the minimum threshold of clusters and other manual intervention data. , Not only is not intelligent enough, but too much manual intervention results in the loss of accuracy of geofencing.
  • an embodiment of the present application provides a method for determining a geofence based on a user location, including:
  • the aggregated points after denoising processing are sorted according to the size of the longitude coordinate or the latitude coordinate, and the geofence boundary data in a preset format is determined.
  • an embodiment of the present application provides an apparatus for determining a geofence based on a user's location, including:
  • User location acquisition module used to acquire user locations in a number of user data
  • An aggregation module configured to aggregate the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determine an aggregation point and a central aggregation point;
  • a denoising module configured to perform denoising processing on the aggregation point according to the distance between the aggregation point and the central aggregation point;
  • the geofence building module is used to sort the aggregate points after denoising processing according to the size of the longitude coordinate or the latitude coordinate, and determine the geofence boundary data in a preset format.
  • an embodiment of the present application also discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and the processor executes the computer program when the computer program is executed.
  • an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of the method for determining a geofence based on the location of a user disclosed in the embodiment of the present application are disclosed.
  • the method for determining a geofence based on a user's location obtains the user's location in several user data; aggregates the user's location according to the similarity of the longitude and latitude coordinates of the user's location to determine the aggregation point and the central aggregation Points; according to the distance between the aggregation point and the central aggregation point, the aggregation point is denoised; the aggregation points after the denoising process are sorted according to the size of the longitude coordinate or the latitude coordinate, and determined Geofence boundary data in a preset format.
  • the method for determining a geofence based on the user location disclosed in the embodiment of the application performs location aggregation based on the similarity of the longitude and latitude coordinates of the user location, and automatically determines the effective user location data according to the aggregation result, and then determines the preset based on the effective user location data Format the boundary data to obtain the geofence without any manual intervention, which helps to improve the accuracy of the geofence.
  • FIG. 1 is a flowchart of a method for determining a geofence based on a user's location in Embodiment 1 of the present application;
  • FIG. 2 is one of the schematic structural diagrams of the device for determining the geofence based on the user's location in the second embodiment of the present application;
  • FIG. 3 is a second structural diagram of a device for determining a geofence based on a user's location in the second embodiment of the present application;
  • Fig. 4 shows a block diagram of an electronic device for executing the method according to the present application.
  • Fig. 5 shows a storage unit for holding or carrying the program code for implementing the method according to the present application.
  • This embodiment discloses a method for determining a geofence based on a user's location. As shown in FIG. 1, the method includes: step 110 to step 140.
  • Step 110 Obtain user locations in several user data.
  • the method for determining a geofence based on a user's location can be used to determine geofences in business areas such as geofencing, food delivery, and tourism, and for applications that need to determine a geofence based on location services.
  • the user data may be the user's ordering data, wireless access point link data, hotel reservation data, ticket reservation data, information query data, etc., which can be obtained by the service platform.
  • user data includes user location information. Several pieces of user location information can be obtained by analyzing and processing the data obtained by the platform.
  • the user location described in the embodiments of the present application is represented by latitude and longitude coordinates, and the user location information includes the longitude coordinates and latitude coordinates of the user location. For some data that uses other forms to represent the user's location, it can be first converted into latitude and longitude coordinates.
  • the step of obtaining the user location in several user data includes: obtaining user data matching the creation condition according to the creation condition of the geofence; obtaining the user location in the user data.
  • the creation conditions of the geofence include but are not limited to: the accuracy of the geofence, the geographical scope, and the category; the category is used to indicate the application scenarios of the geofence, which may include: ordering hotspots, geofences, popular attractions, geofences, Administrative business district fence etc.
  • the takeaway application scenario you can build a geofence of ordering hotspot merchants, and dispatch orders based on the determined geofence. For example, a certain take-out delivery person is responsible for the take-out delivery of a merchant within a certain geofence. Or, push messages to the user based on the geofence, and after the user enters a certain geofence, the information that matches the geofence is pushed to the user.
  • the category of geofencing is: ordering hotspot business district geofencing.
  • the user's order data can be obtained for analysis to determine the user's location in each piece of order data.
  • Step 120 Aggregate the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determine an aggregation point and a central aggregation point.
  • the latitude and longitude coordinates described in the embodiments of the present application include longitude coordinates and latitude coordinates.
  • the user positions are aggregated according to the similarity of the latitude and longitude coordinates of the user positions, the aggregation point and the central aggregation point are determined, and a number of aggregation points and the user location aggregated by each aggregation point are determined The number, and the central aggregation point corresponding to the plurality of aggregation points.
  • aggregating the user position according to the similarity of the longitude and latitude coordinates of the user position to determine the aggregation point and the central aggregation point includes: according to the similarity pair of the longitude and latitude coordinates of the user position
  • the user positions are aggregated, an aggregation point and a central aggregation point are determined, and several aggregation points are determined; the aggregation point with the most user positions aggregated is determined as the central aggregation point.
  • the user positions are aggregated according to the similarity of the latitude and longitude coordinates of the user positions, and the determination of the aggregation point and the central aggregation point can be achieved in the same manner.
  • the embodiment of the present application only three specific implementation manners are exemplified. Assist readers to understand the technical solution of this application. Those skilled in the art can also use other technical means based on the design idea of this application to aggregate the location of the user according to the similarity of the latitude and longitude coordinates of the location of the user to determine the aggregation point and the central aggregation point; this application should not be used.
  • the technical means exemplified in the embodiments serve as a limitation on the technical means for aggregating the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determining the aggregation point and the central aggregation point.
  • the step of aggregating the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determining the aggregation point and the central aggregation point includes: combining all the positions that meet the preset latitude and longitude coordinate similarity conditions The user positions are aggregated to the same aggregation point, and several aggregation points are determined; the aggregation point with the most user positions aggregated among the several aggregation points is determined as the central aggregation point; wherein the preset latitude and longitude coordinate similarity condition is: longitude The first 3 digits of the decimal point of the coordinate are the same, the N digits after the decimal point of the longitude coordinate are the same, the 2 digits before the decimal point of the latitude coordinate are the same, and the M digits after the decimal point of the latitude coordinate are the same. N and M are positive integers less than or equal to 5.
  • the latitude and longitude coordinates within 1 meter make sure that the first 3 digits of the longitude coordinate are the same and the 5 digits after the decimal point of the longitude coordinate are the same.
  • the first 2 digits of the latitude coordinate are the same and the latitude coordinate has 5 digits after the decimal point.
  • the same number is the condition of similarity of latitude and longitude coordinates.
  • the longitude coordinate first 3 digits of the decimal point are the same and the longitude coordinate 5 digits after the decimal point are the same
  • the latitude coordinate first 2 digits of the decimal point are the same and the latitude coordinate has the same 5 digits after the decimal point
  • the locations are aggregated into one category, and multiple user location categories can be obtained. All user locations aggregated in each user location category have the same three digits before the decimal point of the longitude coordinate and the same five digits after the decimal point of the longitude coordinate. At the same time, the two digits before the decimal point of the latitude coordinate are the same and the five digits after the decimal point of the latitude coordinate are the same.
  • the longitude coordinates of all user locations aggregated in each user location category can be determined by the three digits before the decimal point and the longitude coordinates determined by the five digits after the longitude coordinate as the longitude coordinates of the aggregation point corresponding to the user location category.
  • the latitude coordinates of all user locations aggregated in each user location category are determined by the latitude coordinates determined by 2 digits before the decimal point and 5 digits after the decimal point as the latitude coordinates of the aggregation point corresponding to the user location category to determine each user location category
  • the latitude and longitude coordinates of the corresponding aggregation point So far, after aggregation, several aggregation points will be obtained, and the latitude and longitude coordinates of each aggregation point and the number of user positions aggregated in the aggregation point are determined.
  • the latitude and longitude coordinates within 10 meters are regarded as similar coordinates, it is determined that the first 3 digits of the longitude coordinate are the same and the 4 digits after the decimal point of the longitude coordinate are the same.
  • the latitude coordinates are 2 before the decimal point.
  • the same digits and the same 4 digits after the decimal point of the latitude coordinates are the conditions for the similarity of the latitude and longitude coordinates. That is, the aggregation accuracy requirements are different, and the latitude and longitude coordinate similarity conditions are also different.
  • user location aggregation is directly based on the same number of digits of latitude and longitude coordinates.
  • the aggregation operation has low complexity, fast operation speed and higher efficiency; and the aggregation based on the similarity of latitude and longitude coordinates can be based on the application scenario of geofencing. Or it is more practical to set the conditions of latitude and longitude similarity with flexible and intuitive construction requirements.
  • the second aggregation method the step of aggregating the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determining the aggregation point and the central aggregation point includes: performing GeoHash conversion on the latitude and longitude coordinates of the user position , Respectively determine the GeoHash code corresponding to each user location; aggregate the user locations that meet the preset GeoHash code similarity condition to the same aggregation point, determine several aggregation points; determine that the plurality of aggregation points have the most user positions aggregated The aggregation point is used as the central aggregation point.
  • GeoHash encoding For example, first, perform GeoHash encoding on the latitude and longitude coordinates of each user's location, and convert the latitude and longitude coordinates into a GeoHash string. Different lengths of GeoHash indicate different geographic location accuracy.
  • the GeoHash coding similarity condition can be determined according to the accuracy requirements of the geofence.
  • the user locations corresponding to the GeoHash codes that meet the GeoHash code similarity conditions are aggregated into a user location category. For example, the first 10 user locations with the same GeoHash code for the drink are collected into a user location category.
  • the latitude and longitude coordinates corresponding to the first 10 digits of the GeoHash code of the user location grouped in the user location category may be used as the latitude and longitude coordinates of the aggregation point corresponding to the user location category.
  • the number of user locations aggregated into the corresponding user location category is determined according to the first 10 digits of the GeoHash code of the user locations aggregated in the user location category, and the aggregation point corresponding to the user location category that aggregates the largest number of user locations is taken as Central convergence point.
  • the third aggregation method includes: dividing the map into grids of a specified size and uniform distribution ; According to the similarity between the longitude coordinates of the user location and the longitude coordinates of the grid, and the similarity between the latitude coordinates of the user location and the latitude coordinates of the grid, the user location is aggregated into the corresponding grid Within; determine the central point of the grid as the aggregation point corresponding to the grid; take the aggregation point with the most user positions in the corresponding grid as the central aggregation point.
  • the map on which the geofence is constructed may be divided into uniformly distributed grids of a preset size, and the latitude and longitude coordinates of each grid may be determined.
  • the latitude and longitude coordinates of the center point of each grid can be used to identify the latitude and longitude coordinates of the grid.
  • the longitude coordinates of the user location and the grid longitude coordinates meet the grid latitude and longitude coordinates similarity condition and the latitude coordinates of the user location are consistent with the The positions of the users whose latitude coordinates of the grid satisfy the similarity condition of the grid latitude and longitude coordinates are aggregated into the corresponding grid.
  • the similarity condition of the grid latitude and longitude coordinates may be: the first 3 decimal places of the longitude coordinate are the same and the 5 decimal places are the same, and the latitude coordinate first 2 decimal places are the same and the 5 decimal places are the same. So far, the number of user positions aggregated into each grid is determined, and further, the center point of each grid is determined as the aggregation point corresponding to the grid, then the number of user positions aggregated into the grid Is the number of user locations aggregated to the corresponding aggregation point. Further, the aggregation point with the largest number of user positions (that is, the aggregation point corresponding to the grid with the largest number of users) is selected as the central aggregation point.
  • the number of user locations aggregated by the aggregation point truly reflects the distribution of user locations.
  • the clustering algorithm is simple and efficient, avoiding manual setting of cluster centers and cluster categories
  • the clustering result caused by the quantity does not match the actual demand, and the geofence is not accurate.
  • Step 130 Perform denoising processing on the aggregation point according to the distance between the aggregation point and the central aggregation point.
  • the aggregation result determined in the foregoing steps includes several aggregation points and a central aggregation point.
  • the user location denoising process is automatically performed based on the aggregation points and central aggregation points determined in the foregoing steps.
  • the step of performing denoising processing on the aggregation point according to the distance between the aggregation point and the central aggregation point includes: according to each aggregation point and the central aggregation point The distance between the central aggregation points is determined to determine the user location noise reduction radius; the aggregation points whose distance from the central aggregation point is greater than the user location noise reduction radius are used as noise for denoising processing. That is, the user location noise reduction radius is determined according to the distribution information of the aggregate point relative to the central aggregate point, and the aggregate point is further denoised according to the determined user location noise reduction radius, or the user location is denoised.
  • the step of determining the noise reduction radius of the user position according to the distance between each aggregation point and the central aggregation point includes: according to the distribution range of the distance between each aggregation point and the central aggregation point, Determine the user location distribution area according to the preset change step of the geofence range; determine the user location noise reduction radius based on the central aggregation point according to the number of the aggregation points distributed in each user location distribution area. First, set the change step length of the geofence range according to the longitude requirements of the geofence.
  • the range of the geofence is 500 meters in radius
  • 100 meters can be set as the change step of the geofence range
  • the central aggregation point is the center of the circle
  • the change step of the geofence range is the radius change step. Determine the circular or circular user location distribution area.
  • five user location distribution areas can be determined, namely: a circular user location distribution area with a central aggregation point as the center and a radius of 100; and a circular user location distribution area with the central aggregation point as the center and a radius of 100 to 200 Circular user location distribution area; a circular user location distribution area with a central aggregation point as the center and a radius of 200 to 300; a circular user location distribution area with a central aggregation point as the center and a radius of 300 to 400; and the central aggregation point as the center , A circular user location distribution area with a radius of 400 to 500).
  • the distance between each aggregation point and the central aggregation point is calculated, and the distance is used as the radius to determine the circular or circular user location distribution area where each aggregation point is distributed.
  • the maximum radius of the user location distribution area with the most distributed aggregation points is used as the user location noise reduction radius based on the central aggregation point. Based on the aforementioned user location distribution area distance, if the number of aggregation points distributed in the circular user location distribution area with a radius of 200 to 300 is the maximum value of the above 5 user location distribution areas, the maximum radius of the circular user location distribution area is determined 300 is the noise reduction radius of the user location.
  • an aggregation point whose distance from the central aggregation point and the user location noise reduction radius meets a preset condition is determined as noise. If it is determined that the distance from the central aggregation point is greater than the noise reduction radius of the user location aggregation point noise, that is, it is determined that the central aggregation point is a circle and the aggregation outside the circular area with a radius of 300 is determined. The point is noise.
  • the maximum distribution radius of the aggregation points is determined by calculating the distance between each aggregation point and the central aggregation point, and the distribution range of the aggregation points is divided according to the preset geofence range change step to determine the distribution Aggregate the area with the most points, and determine the distribution range of noise points with the upper limit radius of the area, which can realize smarter and faster denoising processing of user location data.
  • the step of determining the noise reduction radius of the user position according to the distance between each of the aggregation points and the central aggregation point includes: determining each of the aggregation points and the center The average distance of the aggregation point is used as the user location noise reduction radius. For example, first, the distance between each aggregation point and the central aggregation point is determined based on the latitude and longitude coordinates through the spherical distance calculation formula; then, according to the determined distance, the distance between all aggregation points and the central aggregation point is calculated Average distance; Finally, the calculated average distance is used as the user location noise reduction radius.
  • the step of performing denoising processing on the aggregation point includes: taking the aggregation point that is greater than a preset user position noise reduction radius from the central aggregation point as noise, and performing denoising processing.
  • the construction requirements of the geofence include the range of the geofence, and the noise reduction radius of the user location can be preset according to the range of the geofence.
  • Step 140 Sort the aggregate points after the denoising process according to the size of the longitude coordinate or the latitude coordinate, and determine the geofence boundary data in a preset format.
  • the noise positions are filtered out to obtain effective aggregation points.
  • the boundary data of the fence For example, connect the sorted aggregation points to get the boundary of the geofence.
  • the WKT (Well-known text) format boundary data is constructed based on the sorted aggregation points, and the specific implementation of the geofence based on the WKT format boundary data can be found in the prior art, which will not be repeated in the embodiments of this application.
  • the method for determining a geofence based on a user's location obtains the user's location in several user data; aggregates the user's location according to the similarity of the longitude and latitude coordinates of the user's location to determine the aggregation point and the central aggregation Points; according to the distance between the aggregation point and the central aggregation point, the aggregation point is denoised; the aggregation points after the denoising process are sorted according to the size of the longitude coordinate or the latitude coordinate, and determined
  • the geofence boundary data in a preset format solves the problem of geofence accuracy loss caused by manual setting of clustering parameters when clustering geographic locations in the prior art.
  • the method for determining a geofence based on the user location disclosed in the embodiment of the application performs location aggregation based on the similarity of the longitude and latitude coordinates of the user location, and automatically determines the effective user location data according to the aggregation result, and then determines the preset based on the effective user location data Format the boundary data to obtain the geofence without any manual intervention, which helps to improve the accuracy of the geofence.
  • the denoising processing is performed on the aggregation points obtained by the aggregation, and the geofence boundary data is further constructed based on the effective aggregation points obtained after the denoising processing, which effectively reduces the amount of data processing and improves the construction of the geofence effectiveness.
  • the aggregation point is obtained by aggregating the similarity of the user's location based on the latitude coordinates, the location feature of the aggregation point can accurately characterize the characteristics of the user location aggregated to the aggregation point, thereby ensuring the accuracy of the constructed geofence .
  • This embodiment discloses a device for determining a geofence based on a user's location. As shown in FIG. 2, the device includes:
  • the user location obtaining module 210 is used to obtain the user location in a number of user data
  • the aggregation module 220 is configured to aggregate the user positions according to the similarity of the latitude and longitude coordinates of the user positions, and determine an aggregation point and a central aggregation point;
  • the denoising module 230 is configured to perform denoising processing on the aggregation point according to the distance between the aggregation point and the central aggregation point;
  • the geofence building module 240 is configured to sort the aggregate points after the denoising process according to the size of the longitude coordinates or the latitude coordinates, and determine the geofence boundary data in a preset format.
  • the aggregation module 220 further includes:
  • the first aggregation sub-module 2201 is configured to aggregate the user positions that meet the preset longitude and latitude coordinate similarity conditions to the same aggregation point, and determine a number of aggregation points; and, determine which of the plurality of aggregation points has the most user locations.
  • the aggregation point is used as the central aggregation point; wherein the preset latitude and longitude coordinate similarity conditions are: the longitude coordinate has the same three digits before the decimal point, the longitude coordinate has the same N digits after the decimal point, the latitude coordinate has two digits before the decimal point, and the latitude After the decimal point of the coordinate, M digits are the same, and N and M are positive integers less than or equal to 5.
  • the user location aggregation is directly based on the same number of digits in the latitude and longitude coordinates.
  • the aggregation operation has low complexity, fast operation speed and higher efficiency; and when aggregation is performed based on the similarity of the latitude and longitude coordinates, it can be flexible and flexible according to the application scenarios or construction requirements of the geofence. It is more practical to set the similarity condition of latitude and longitude intuitively.
  • the aggregation module 220 further includes:
  • the second aggregation sub-module 2202 is configured to perform GeoHash conversion on the latitude and longitude coordinates of the user location, and respectively determine the GeoHash code corresponding to each user location;
  • the second aggregation sub-module 2202 is further configured to aggregate the user locations that meet the preset GeoHash coding similarity condition to the same aggregation point, and determine a number of aggregation points; and, determine that the plurality of aggregation points have the most aggregation
  • the aggregation point of the user's location is used as the central aggregation point.
  • the aggregation module 220 further includes:
  • the third aggregation submodule 2203 is configured to divide the map into grids of a specified size and uniformly distributed, and according to the similarity between the longitude coordinates of the user location and the longitude coordinates of the grid, and the latitude coordinates of the user location The similarity with the latitude coordinates of the grid, and aggregate the user positions into the corresponding grid;
  • the third aggregation submodule 2203 is also used to determine that the center point of the grid is the aggregation point corresponding to the grid; and is used to aggregate the aggregation points with the most user positions in the corresponding grid , As the central aggregation point.
  • the denoising module 230 further includes:
  • the noise reduction radius determining sub-module 2301 is configured to determine the noise reduction radius of the user location according to the distance between each aggregation point and the central aggregation point;
  • the first denoising processing sub-module 2302 is configured to use the aggregation point whose distance from the central aggregation point is greater than the noise reduction radius of the user location as noise, and perform denoising processing.
  • the noise reduction radius determination submodule 2301 is further configured to: according to the distribution range of the distance between each aggregation point and the central aggregation point, according to a preset geographic fence range change step Determining a user location distribution area; and, according to the number of the aggregation points distributed in each user location distribution area, determining a user location noise reduction radius based on the central aggregation point.
  • the noise reduction radius determining submodule 2301 is further configured to determine the average distance between each of the aggregation points and the central aggregation point as the user location noise reduction radius.
  • the denoising module 230 further includes:
  • the second denoising processing sub-module 2303 is configured to use the aggregation points whose distance from the central aggregation point is greater than the preset user location noise reduction radius as noise, and perform denoising processing.
  • the user location obtaining module 210 is further configured to:
  • the device for determining a geofence based on the location of a user disclosed in this embodiment is used to implement the steps of the method for determining a geofence based on the location of a user described in Embodiment 1 of the present application.
  • each module of the device refer to the corresponding steps. I won't repeat them here.
  • the device for determining a geofence based on the user location obtains the user location in several user data; aggregates the user location according to the similarity of the longitude and latitude coordinates of the user location to determine the aggregation point and the central aggregation Points; according to the distance between the aggregation point and the central aggregation point, the aggregation point is denoised; the aggregation points after the denoising process are sorted according to the size of the longitude coordinate or the latitude coordinate, and determined
  • the geofence boundary data in a preset format solves the problem of geofence accuracy loss caused by manual setting of clustering parameters when clustering geographic locations in the prior art.
  • the device for determining a geofence based on the user location disclosed in the embodiment of the present application performs location aggregation according to the similarity of the longitude and latitude coordinates of the user location, and automatically determines the effective user location data according to the aggregation result, and then determines the preset based on the effective user location data Format the boundary data to obtain the geofence without any manual intervention, which helps to improve the accuracy of the geofence.
  • the denoising processing is performed on the aggregation points obtained by the aggregation, and the geofence boundary data is further constructed based on the effective aggregation points obtained after the denoising processing, which effectively reduces the amount of data processing and improves the construction of the geofence effectiveness.
  • the aggregation point is obtained by aggregating the similarity of the user's location based on the latitude coordinates, the location feature of the aggregation point can accurately characterize the characteristics of the user location aggregated to the aggregation point, thereby ensuring the accuracy of the constructed geofence .
  • this application also discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor.
  • the processor executes the computer program, the implementation is as in this application.
  • the electronic device may be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc.
  • the application also discloses a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of the method for determining a geofence based on the user's location as described in the first embodiment of the application are realized.
  • the device embodiments described above are merely illustrative.
  • 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, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.
  • each implementation manner can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, or in one or more processes. Implementation of software modules running on the device. Based on this understanding, the above technical solutions can be embodied in the form of software products, which can be stored in computer-readable storage media, such as ROM/RAM, magnetic A disc, an optical disc, etc., include a number of instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiment.
  • a microprocessor or a digital signal processor may be used in practice to implement some or all of the functions of some or all of the components in the electronic device according to the embodiments of the present application.
  • the present invention can also be implemented as a device or device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein.
  • a program for implementing the present application may be stored on a computer-readable medium, or may have the form of one or more signals. Such signals can be downloaded from Internet websites, or provided on carrier signals, or provided in any other form.
  • FIG. 4 shows an electronic device that can implement the method according to the present application.
  • the electronic device traditionally includes a processor 420 and a computer program product in the form of a memory 410 or a computer readable medium.
  • the memory 410 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the memory 410 has a storage space 4101 for executing the program code 4102 of any method step in the above method.
  • the storage space 4101 used for program codes may include various program codes 4102 respectively used to implement various steps in the above method. These program codes can be read out from or written into one or more computer program products.
  • These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such a computer program product is usually a portable or fixed storage unit as described with reference to FIG. 5.
  • the storage unit may have storage segments, storage spaces, etc. arranged similarly to the storage 420 in the electronic device of FIG. 4.
  • the program code can be compressed in an appropriate form, for example.
  • the storage unit includes computer-readable codes 4102', that is, codes that can be read by, for example, a processor such as 410. These codes, when run by an electronic device, cause the electronic device to execute each of the methods described above. step.
  • any reference signs placed between parentheses should not be constructed as a limitation to the claims.
  • the word “comprising” does not exclude the presence of elements or steps not listed in the claims.
  • the word “a” or “an” before an element does not exclude the presence of multiple such elements.
  • the application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims enumerating several devices, several of these devices may be embodied by the same hardware item.
  • the use of the words first, second, and third, etc. do not indicate any order. These words can be interpreted as names.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Navigation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请公开了一种基于用户位置确定地理围栏的方法，属于计算机技术领域。本申请实施例公开的基于用户位置确定地理围栏的方法包括：获取若干用户数据中的用户位置；根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据，自动进行用户位置聚合和去噪，以生成地理围栏。

Description

基于用户位置确定地理围栏
本申请要求在2019年2月20日提交中国专利局、申请号为201910127295.1、发明名称为“基于用户位置的地理围栏确定方法、装置、电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，特别是涉及基于用户位置确定地理围栏。
背景技术
地理围栏是虚拟的地理边界，表示一片地理位置区域,当用户设备进入或退出该区域后会触发相应的地理围栏事件,应用程序可捕获感兴趣的地理围栏事件并执行相应操作。地理围栏的形状可以是以点和半径构成的圆形，可以是一批经纬度点构成的多边形。地理围栏的确定具有重大价值。
现有技术中确定地理围栏的方法通常为：对经纬度坐标进行聚类分析，得到一个或多个经纬度坐标团簇，其中每个团簇包括多个经纬度坐标，基于团簇的边界点生成地理围栏。然而，现有技术职工在对经纬度坐标进行聚类时，采用如K-Means算法进行数据聚合的方法复杂低效,并且需要指定初始化聚类中心，指定团簇的最小阈值等多种人工干预数据，不仅不够智能化，同时人工干预过多，导致地理围栏的精度的损失。
发明内容
第一方面，本申请实施例提供了一种基于用户位置确定地理围栏的方法，包括：
获取若干用户数据中的用户位置；
根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；
根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；
对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
第二方面，本申请实施例提供了一种基于用户位置确定地理围栏的装置，包括：
用户位置获取模块，用于获取若干用户数据中的用户位置；
聚合模块，用于根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；
去噪模块，用于根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；
地理围栏构建模块，用于对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
第三方面，本申请实施例还公开了一种电子设备，包括存储器、处理器及存储在所述存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现本申请实施例所述的基于用户位置确定地理围栏的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时本申请实施例公开的基于用户位置确定地理围栏的方法的步骤。
本申请实施例公开的基于用户位置确定地理围栏的方法，通过获取若干用户数据中的用户位置；根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。本申请实施例公开的基于用户位置确定地理围栏的方法根据用户位置的经纬度坐标的相似度进行位置聚合，并根据聚合结果自动确定有效的用户位置数据，然后，基于有效的用户位置数据确定预设格式的边界数据，从而得到地理围栏，不需要任何人工干预，有助于提升地理围栏的精度。
附图说明
为了更清楚地说明本申请实施例的技术方案，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申请的一些实施例，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是本申请实施例一的基于用户位置确定地理围栏的方法流程图；
图2是本申请实施例二的基于用户位置确定地理围栏的装置的结构示意图之一；
图3是本申请实施例二的基于用户位置确定地理围栏的装置的结构示意图之二；
图4示出了用于执行根据本申请的方法的电子设备的框图；以及，
图5示出了用于保持或者携带实现根据本申请的方法的程序代码的存储单元。
具体实施例
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
实施例一
本实施例公开的一种基于用户位置确定地理围栏的方法，如图1所示，该方法包括：步骤110至步骤140。
步骤110，获取若干用户数据中的用户位置。
本申请实施例公开的基于用户位置确定地理围栏的方法可以用于与确定商圈的地理围栏、外卖、旅游等业务的地理围栏、对于基于位置服务需要确定地理围栏的应用中。具体实施时，用户数据可以为服务平台能够获取的用户的点餐数据、无线接入点链接数据、酒店预订数据、门票预订数据、信息查询数据等。通常，用户数据中包括用户位置信息。通过对平台获取的数据进行解析处理，可以得到若干条用户位置信息。
本申请实施例中所述的用户位置通过经纬度坐标表示，用户位置信息包括用户位置的经度坐标和纬度坐标。对于一些采用其他形式表示用户位置的 数据，可以首先转换成通过经纬度坐标表示。
具体应用时，当需要为某一特定应用确定地理围栏时，优选的，基于与该特定应用相关的用户数据进行用户位置分析，有助于提升确定的地理围栏的准确性。本申请的一些实施例中，所述获取若干用户数据中的用户位置的步骤，包括：根据地理围栏的创建条件获取与所述创建条件匹配的用户数据；获取所述用户数据中的用户位置。其中，地理围栏的创建条件包括但不限于：地理围栏的精度、地域范围、类别；所述类别用于指示地理围栏的应用场景，可以包括：点餐热点商圈地理围栏、热门景点地理围栏、行政商圈围栏等。
以外卖应用场景为例，可以构建点餐热点商户的地理围栏，并基于确定的地理围栏进行外卖派单。例如，某个外卖配送员负责某一地理围栏内商户的外卖配送。或者，基于地理围栏对用户进行消息推送，当用户进入某一地理围栏之后，向用户推送与该地理围栏匹配的信息。在这种应用场景下，可以认为地理围栏的类别为：点餐热点商圈地理围栏。进一步的，可以通过获取用户的点餐数据进行分析，确定每一条点餐数据中的用户位置。
步骤120，根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点。
本申请实施例中所述的经纬度坐标包括经度坐标和纬度坐标。
本申请具体实施时，通过根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点，确定若干聚合点、每个所述聚合点所聚合的用户位置数量，以及，所述若干聚合点对应的中心聚合点。在本申请的一些实施例中，根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点，包括：根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点，确定若干聚合点；将聚合有最多用户位置的所述聚合点确定为中心聚合点。
根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点可以通过同种方式实现，本申请实施例中仅例举其中的三种具体实施方式，以辅助读者理解本申请的技术方案。本领域技术人员还可以基于本申请的设计思想，采用其他技术手段根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；而不 应以本申请实施例中所例举的技术手段作为对根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的技术手段的限定。
第一种聚合方式，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：将满足预设经纬度坐标相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点；其中，所述预设经纬度坐标相似度条件为：经度坐标小数点前3位数字相同，经度坐标小数点后N位数相同，纬度坐标小数点前2位数字，以及，纬度坐标小数点后M位数相同，N和M为小于等于5的正整数。
例如，将1米范围内的经纬度坐标作为相似坐标，确定经度坐标小数点前3位数字相同并且经度坐标小数点后5位数相同，同时，纬度坐标小数点前2位数字相同并且纬度坐标小数点后5位数相同为经纬度坐标相似度条件。然后，对于获取到的若干用户位置，将经度坐标小数点前3位数字相同并且经度坐标小数点后5位数相同，同时，纬度坐标小数点前2位数字相同并且纬度坐标小数点后5位数相同的用户位置聚合到一个类别中，可以得到多个用户位置类别。每个用户位置类别中聚合的所有用户位置的经度坐标小数点前3位数字相同并且经度坐标小数点后5位数相同，同时，纬度坐标小数点前2位数字相同并且纬度坐标小数点后5位数相同。具体实施时，可以将每个用户位置类别中聚合的所有用户位置的经度坐标小数点前3位数字和经度坐标小数点后5位数确定的经度坐标作为该用户位置类别对应的聚合点的经度坐标，将每个用户位置类别中聚合的所有用户位置的纬度坐标小数点前2位数字和小数点后5位数确定的纬度坐标作为该用户位置类别对应的聚合点的纬度坐标，从而确定每个用户位置类别对应的聚合点的经纬度坐标。至此，经过聚合，将得到若干聚合点，并确定了每个聚合点的经纬度坐标以及该聚合点中聚合的用户位置的数量。
接下来，确定聚合有最大数量用户位置的聚合点作为中心聚合点。
在本申请的另一些实施例中，如果将10米范围内的经纬度坐标作为相似坐标，则确定经度坐标小数点前3位数字相同并且经度坐标小数点后4位 数相同，同时，纬度坐标小数点前2位数字相同并且纬度坐标小数点后4位数相同为经纬度坐标相似度条件。即，聚合精度需求不同，经纬度坐标相似度条件也不同。
本申请实施例中直接依据经纬度坐标的相同位数进行用户位置聚合，聚合运算复杂度低，运算速度快，效率更高；并且，根据经纬度坐标的相似度进行聚合时可以根据地理围栏的应用场景或构建需求灵活、直观设置经纬度相似度条件，更实用。
第二种聚合方式，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：对所述用户位置的经纬度坐标进行GeoHash转换，分别确定每个用户位置对应的GeoHash编码；将满足预设GeoHash编码相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点。
例如，首先将每个用户位置的经纬度坐标进行GeoHash编码，将经纬度坐标转换为一个GeoHash串，GeoHash的长度不同表示的地理位置精度不同。具体实施时，可以根据地理围栏的精度需求确定GeoHash编码相似度条件。然后，根据设定的GeoHash编码相似度条件，把符合该GeoHash编码相似度条件的GeoHash编码对应的用户位置聚合到一个用户位置类别。例如把对饮的GeoHash编码前10位相同的用户位置集合到一个用户位置类别。进一步的，对于每个用户位置类别，可以将该用户位置类别中集合的用户位置的GeoHash编码前10位对应的经纬度坐标作为该用户位置类别对应的聚合点的经纬度坐标。进一步的，根据用户位置类别中集合的用户位置的GeoHash编码前10位确定聚合到相应用户位置类别中的用户位置的数量，并把聚合有最多数量用户位置的用户位置类别所对应的聚合点作为中心聚合点。
第三种聚合方式，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：将地图划分为指定大小均匀分布的网格；根据所述用户位置的经度坐标与所述网格的经度坐标的相似度、所述用户位置的纬度坐标与所述网格的纬度坐标的相似度，将所述用户位置聚合到相应网格内；确定所述网格的中心点为与所述网格对 应的聚合点；将所对应的网格中聚合有最多用户位置的聚合点，作为中心聚合点。
在本申请的另一些实施例中，可以首先将构建地理围栏所基于的地图划分为预设大小的均匀分布的网格，并确定每个网格的经纬度坐标。具体实施时，可以用每个网格的中心点的经纬度坐标标识该网格的经纬度坐标。然后，根据设置的网格经纬度坐标相似度条件，将所述用户位置的经度坐标与所述网格的经度坐标满足所述网格经纬度坐标相似度条件且所述用户位置的纬度坐标与所述网格的纬度坐标满足网格经纬度坐标相似度条件的所述用户位置聚合到相应网格内。例如，所述网格经纬度坐标相似度条件可以为：经度坐标小数点前3为相同且小数点后5位相同，同时，纬度坐标小数点前2为相同且小数点后5位相同。至此，确定了聚合到每个网格中的用户位置的数量，进一步的，将每个网格的中心点确定为该网格对应的聚合点，则聚合到该网格中的用户位置的数量为聚合到相应聚合点的用户位置的数量。进一步的，选择聚合有最多数量用户位置的聚合点(即聚合有最多用户数量的网格对应的聚合点)作为中心聚合点。
聚合点所聚合的用户位置的数量真实反映了用户位置的分布规律，通过选择聚合有最多用户位置的聚合点作为中心聚合点，聚类算法简洁高效，规避了人工设置聚类中心和聚类类别数量导致的聚类结果与实际需求不匹配，地理围栏不准确的问题。
步骤130，根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理。
前述步骤中确定的聚合结果包括：若干聚合点和一个中心聚合点，本申请具体实施时，基于前述步骤中确定的聚合点和中心聚合点自动进行用户位置去噪处理。
在本申请的一些实施例中，所述根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理的步骤，包括：根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径；将与所述中心聚合点的所述距离大于所述用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。即根据聚合点相对于中心聚合点的分布信息确定用户位置降噪半径，进 一步再根据确定的用户位置降噪半径对聚合点进行去噪处理，或对用户位置进行去噪处理。
其中，所述根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径的步骤，包括：根据各所述聚合点与所述中心聚合点的距离的分布范围，按照预设的地理围栏范围变化步长确定用户位置分布区域；根据各所述用户位置分布区域中分布的所述聚合点的数量，确定基于所述中心聚合点的用户位置降噪半径。首先，根据地理围栏的经度需求设定地理围栏范围变化步长。例如，当地理围栏的范围为方圆500米时，可以设置100米为地理围栏范围变化步长，并以所述中心聚合点为圆心，以所述地理围栏范围变化步长为半径变化步长，确定圆形或环形用户位置分布区域。按照本例中的数据，可以确定5个用户位置分布区域，分别为：以中心聚合点为圆心，半径为100的圆形用户位置分布区域；以中心聚合点为圆心，半径为100至200的环形用户位置分布区域；以中心聚合点为圆心，半径为200至300的环形用户位置分布区域；以中心聚合点为圆心，半径为300至400的环形用户位置分布区域；以中心聚合点为圆心，半径为400至500的环形用户位置分布区域)。然后，计算每个聚合点与中心聚合点之间的距离，并以所述距离作为半径，确定各聚合点所分布在的圆形或环形用户位置分布区域。最后，将所分布的聚合点最多的用户位置分布区域的最大半径作为基于所述中心聚合点的用户位置降噪半径。以前述用户位置分布区域距离，如果分布在半径为200至300的环形用户位置分布区域中的聚合点的数量为上述5个用户位置分布区域的最大值，则确定环形用户位置分布区域的最大半径300为用户位置降噪半径。
进一步的，确定与所述中心聚合点之间的距离与所述用户位置降噪半径满足预设条件的聚合点作为噪声。如确定与所述中心聚合点之间的距离大于所述用户位置降噪半径的聚合点位噪声，即确定以所述中心聚合点为圆形，以300为半径的圆形区域之外的聚合点为噪声。
本实施例中，通过计算每个聚合点与中心聚合点之间的距离确定聚合点的最大分布半径，并按照预设的地理围栏范围变化步长对聚合点分布范围进行区域划分，从而确定分布聚合点最多的区域，并以该区域的上限半径确定 噪声点的分布范围，可以实现更智能、更快速地进行用户位置数据去噪处理。
在本申请的另一些实施例中，所述根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径的步骤，包括：确定各所述聚合点与所述中心聚合点的平均距离，作为用户位置降噪半径。例如，首先，通过球面距离计算公式基于经纬度坐标确定每个聚合点与所述中心聚合点之间的距离；然后，根据确定的所述距离，计算所有聚合点与所述中心聚合点之间的平均距离；最后，以计算得到的所述平均距离作为用户位置降噪半径。
在本申请的另一些实施例中，还可以直接根据预设的用户位置降噪半径对聚合点进行去噪处理，所述根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理的步骤，包括：将与所述中心聚合点的距离大于预设用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。例如，地理围栏的构建需求中包括地理围栏范围，可以根据地理围栏的范围预先设置用户位置降噪半径。在进行聚合点去噪处理时，将与所述中心聚合点的距离大于预设用户位置降噪半径的所述聚合点作为噪声过滤掉。
步骤140，对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
在对聚合点进行去噪处理之后，滤出噪声位置，得到有效的聚合点。对于得到的所有有效聚合点，按照各聚合点的经度坐标或纬度坐标的大小顺序(如降序或升序)对所述聚合点进行排序，基于排序后的聚合点构建预设格式的用于构建地理围栏的边界数据。例如，将排序后的聚合点连线，即可得到地理围栏的边界。又例如，基于排序后的聚合点构建WKT(Well-known text)格式的边界数据，基于WKT格式的边界数据构建地理围栏的具体实施方式参见现有技术，本申请实施例中不再赘述。
本申请实施例公开的基于用户位置确定地理围栏的方法，通过获取若干用户数据中的用户位置；根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据，解决了现有技术中对地理位置进行聚类时需要人工干设置聚类参数导致 的地理围栏精度损失的问题。本申请实施例公开的基于用户位置确定地理围栏的方法根据用户位置的经纬度坐标的相似度进行位置聚合，并根据聚合结果自动确定有效的用户位置数据，然后，基于有效的用户位置数据确定预设格式的边界数据，从而得到地理围栏，不需要任何人工干预，有助于提升地理围栏的精度。
本申请具体实施时，通过对聚合得到的聚合点进行去噪处理，并进一步根据去噪处理后得到的有效聚合点构建地理围栏边界数据，有效降低了数据处理的数量，提升了地理围栏的构建效率。同时，由于聚合点是对用户位置基于纬度坐标的相似度进行聚合得到的，聚合点的位置特征可以准确地表征聚合到该聚合点的用户位置的特征，从而可以保障构建的地理围栏的准确度。
实施例二
本实施例公开的一种基于用户位置确定地理围栏的装置，如图2所示，所述装置包括：
用户位置获取模块210，用于获取若干用户数据中的用户位置；
聚合模块220，用于根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；
去噪模块230，用于根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；
地理围栏构建模块240，用于对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
在本申请的一些实施例中，如图3所示，所述聚合模块220进一步包括：
第一聚合子模块2201，用于将满足预设经纬度坐标相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；以及，确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点；其中，所述预设经纬度坐标相似度条件为：经度坐标小数点前3位数字相同，经度坐标小数点后N位数相同，纬度坐标小数点前2位数字，以及，纬度坐标小数点后M位数相同，N和M为小于等于5的正整数。直接依据经纬度坐标的相同位数进行用户位置聚合，聚合运算复杂度低，运算速度快，效率更高；并且，根据经纬 度坐标的相似度进行聚合时可以根据地理围栏的应用场景或构建需求灵活、直观设置经纬度相似度条件，更实用。
在本申请的另一些实施例中，如图3所示，所述聚合模块220进一步包括：
第二聚合子模块2202，用于对所述用户位置的经纬度坐标进行GeoHash转换，分别确定每个用户位置对应的GeoHash编码；
所述第二聚合子模块2202，还用于将满足预设GeoHash编码相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；以及，确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点。
在本申请的一些实施例中，如图3所示，所述聚合模块220进一步包括：
第三聚合子模块2203，用于将地图划分为指定大小均匀分布的网格，以及，根据所述用户位置的经度坐标与所述网格的经度坐标的相似度、所述用户位置的纬度坐标与所述网格的纬度坐标的相似度，将所述用户位置聚合到相应网格内；
所述第三聚合子模块2203，还用于确定所述网格的中心点为与所述网格对应的聚合点；以及，用于将所对应的网格中聚合有最多用户位置的聚合点，作为中心聚合点。
在本申请的一些实施例中，如图3所示，所述去噪模块230进一步包括：
降噪半径确定子模块2301，用于根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径；
第一去噪处理子模块2302，用于将与所述中心聚合点的所述距离大于所述用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。
在本申请的另一些实施例中，所述降噪半径确定子模块2301进一步用于：根据各所述聚合点与所述中心聚合点的距离的分布范围，按照预设的地理围栏范围变化步长确定用户位置分布区域；以及，根据各所述用户位置分布区域中分布的所述聚合点的数量，确定基于所述中心聚合点的用户位置降噪半径。
在本申请的另一些实施例中，所述降噪半径确定子模块2301进一步还用于：确定各所述聚合点与所述中心聚合点的平均距离，作为用户位置降噪 半径。
在本申请的另一些实施例中，如图3所示，所述去噪模块230进一步包括：
第二去噪处理子模块2303，用于将与所述中心聚合点的距离大于预设用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。
在本申请的一些实施例中，如图3所示，所述用户位置获取模块210进一步用于：
根据地理围栏的创建条件获取与所述创建条件匹配的用户数据；
获取所述用户数据中的用户位置。
本实施例公开的基于用户位置确定地理围栏的装置，用于实现本申请实施例一中所述的基于用户位置确定地理围栏的方法的各步骤，装置的各模块的具体实施方式参见相应步骤，此处不再赘述。
本申请实施例公开的基于用户位置确定地理围栏的装置，通过获取若干用户数据中的用户位置；根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据，解决了现有技术中对地理位置进行聚类时需要人工干设置聚类参数导致的地理围栏精度损失的问题。本申请实施例公开的基于用户位置确定地理围栏的装置根据用户位置的经纬度坐标的相似度进行位置聚合，并根据聚合结果自动确定有效的用户位置数据，然后，基于有效的用户位置数据确定预设格式的边界数据，从而得到地理围栏，不需要任何人工干预，有助于提升地理围栏的精度。
本申请具体实施时，通过对聚合得到的聚合点进行去噪处理，并进一步根据去噪处理后得到的有效聚合点构建地理围栏边界数据，有效降低了数据处理的数量，提升了地理围栏的构建效率。同时，由于聚合点是对用户位置基于纬度坐标的相似度进行聚合得到的，聚合点的位置特征可以准确地表征聚合到该聚合点的用户位置的特征，从而可以保障构建的地理围栏的准确度。
相应的，本申请还公开了一种电子设备，包括存储器、处理器及存储在所述存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如本申请实施例一所述的基于用户位置确定地理围栏的方法。所述电子设备可以为PC机、移动终端、个人数字助理、平板电脑等。
本申请还公开了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请实施例一所述的基于用户位置确定地理围栏的方法的步骤。
本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。对于装置实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上对本申请提供的一种基于用户位置确定地理围栏的方法及装置进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，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申请的限制。
以上所描述的装置实施例仅仅是示意性的，其中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模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件实现，或者以在一个或者多个处理器上运行的软件模块实现。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，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)执行各个实施例或者实施例的某 些部分所述的方法。
本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的电子设备中的一些或者全部部件的一些或者全部功能。本发明还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
例如，图4示出了可以实现根据本申请的方法的电子设备。该电子设备传统上包括处理器420和以存储器410形式的计算机程序产品或者计算机可读介质。存储器410可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器410具有用于执行上述方法中的任何方法步骤的程序代码4102的存储空间4101。例如，用于程序代码的存储空间4101可以包括分别用于实现上面的方法中的各种步骤的各个程序代码4102。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘，紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图5所述的便携式或者固定存储单元。该存储单元可以具有与图4的电子设备中的存储器420类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常，存储单元包括计算机可读代码4102’，即可以由例如诸如410之类的处理器读取的代码，这些代码当由电子设备运行时，导致该电子设备执行上面所描述的方法中的各个步骤。
本文中所称的“一个实施例”、“实施例”或者“一个或者多个实施例”意味着，结合实施例描述的特定特征、结构或者特性包括在本申请的至少一个实施例中。此外，请注意，这里“在一个实施例中”的词语例子不一定全指同一个实施例。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下被实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元 件之前的单词“一”或“一个”不排除存在多个这样的元件。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (13)

  1. 一种基于用户位置确定地理围栏的方法，包括：
    获取若干用户数据中的用户位置；
    根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；
    根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；
    对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
  2. 根据权利要求1所述的方法，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：
    将满足预设经纬度坐标相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；
    确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点；
    其中，所述预设经纬度坐标相似度条件为：经度坐标小数点前3位数字相同，经度坐标小数点后N位数相同，纬度坐标小数点前2位数字，以及，纬度坐标小数点后M位数相同，N和M为小于等于5的正整数。
  3. 根据权利要求1所述的方法，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：
    对所述用户位置的经纬度坐标进行GeoHash转换，分别确定每个用户位置对应的GeoHash编码；
    将满足预设GeoHash编码相似度条件的所述用户位置聚合到相同的聚合点，确定若干聚合点；
    确定所述若干聚合点中聚合有最多用户位置的聚合点，作为中心聚合点。
  4. 根据权利要求1所述的方法，所述根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点的步骤，包括：
    将地图划分为指定大小均匀分布的网格；
    根据所述用户位置的经度坐标与所述网格的经度坐标的相似度、所述用户位置的纬度坐标与所述网格的纬度坐标的相似度，将所述用户位置聚合到相应网格内；
    确定所述网格的中心点为与所述网格对应的聚合点；
    将所对应的网格中聚合有最多用户位置的聚合点，作为中心聚合点。
  5. 根据权利要求1至4任一项所述的方法，所述根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理的步骤，包括：
    根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径；
    将与所述中心聚合点的所述距离大于所述用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。
  6. 根据权利要求5所述的方法，所述根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径的步骤，包括：
    根据各所述聚合点与所述中心聚合点的距离的分布范围，按照预设的地理围栏范围变化步长确定用户位置分布区域；
    根据各所述用户位置分布区域中分布的所述聚合点的数量，确定基于所述中心聚合点的用户位置降噪半径。
  7. 根据权利要求5所述的方法，所述根据各所述聚合点与所述中心聚合点之间的距离，确定用户位置降噪半径的步骤，包括：
    确定各所述聚合点与所述中心聚合点的平均距离，作为用户位置降噪半径。
  8. 根据权利要求1至4任一项所述的方法，所述根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理的步骤，包括：
    将与所述中心聚合点的距离大于预设用户位置降噪半径的所述聚合点作为噪声，进行去噪处理。
  9. 根据权利要求1至4任一项所述的方法，所述获取若干用户数据中的用户位置的步骤，包括：
    根据地理围栏的创建条件获取与所述创建条件匹配的用户数据；
    获取所述用户数据中的用户位置。
  10. 一种基于用户位置确定地理围栏的装置，包括：
    用户位置获取模块，用于获取若干用户数据中的用户位置；
    聚合模块，用于根据所述用户位置的经纬度坐标的相似度对所述用户位置进行聚合，确定聚合点和中心聚合点；
    去噪模块，用于根据所述聚合点与所述中心聚合点之间的距离，对所述聚合点进行去噪处理；
    地理围栏构建模块，用于对去噪处理后的所述聚合点按照经度坐标或纬度坐标的大小进行排序，确定预设格式的地理围栏边界数据。
  11. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现权利要求1至9任意一项所述的基于用户位置确定地理围栏的方法。
  12. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现权利要求1至9任意一项所述的基于用户位置确定地理围栏的方法的步骤。
  13. 一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备上运行时，导致所述电子设备执行根据权利要求1至9中的任意一项所述的基于用户位置确定地理围栏的方法。
PCT/CN2019/120218 2019-02-20 2019-11-22 基于用户位置确定地理围栏 WO2020168767A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/407,905 US20210385610A1 (en) 2019-02-20 2021-08-20 Determining geofence based on user locations

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910127295.1A CN109992633B (zh) 2019-02-20 2019-02-20 基于用户位置的地理围栏确定方法、装置、电子设备
CN201910127295.1 2019-02-20

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/407,905 Continuation US20210385610A1 (en) 2019-02-20 2021-08-20 Determining geofence based on user locations

Publications (1)

Publication Number Publication Date
WO2020168767A1 true WO2020168767A1 (zh) 2020-08-27

Family

ID=67130306

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/120218 WO2020168767A1 (zh) 2019-02-20 2019-11-22 基于用户位置确定地理围栏

Country Status (3)

Country Link
US (1) US20210385610A1 (zh)
CN (1) CN109992633B (zh)
WO (1) WO2020168767A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210263957A1 (en) * 2019-03-19 2021-08-26 Tencent Technology (Shenzhen) Company Limited Method and apparatus for dividing region, storage medium, and electronic device
CN117539971A (zh) * 2024-01-10 2024-02-09 深圳市易甲文技术有限公司 一种海量地理坐标聚合方法及相关设备

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109992633B (zh) * 2019-02-20 2020-08-07 北京三快在线科技有限公司 基于用户位置的地理围栏确定方法、装置、电子设备
CN112398895B (zh) * 2019-08-19 2022-03-18 阿里巴巴集团控股有限公司 提供服务信息的方法及装置
CN112041210B (zh) * 2019-10-23 2023-10-31 北京航迹科技有限公司 用于自动驾驶的系统和方法
CN111078812B (zh) * 2019-12-03 2023-09-05 支付宝(杭州)信息技术有限公司 围栏的生成方法、装置和电子设备
CN111125557A (zh) * 2019-12-26 2020-05-08 北京每日优鲜电子商务有限公司 资源筛选方法、装置、计算机设备及存储介质
CN111835917A (zh) * 2020-07-14 2020-10-27 北京字节跳动网络技术有限公司 活动范围展示方法、装置、设备和计算机可读介质
CN112468546B (zh) * 2020-11-12 2023-11-24 北京锐安科技有限公司 账号位置确定方法、装置、服务器和存储介质
CN113610587B (zh) * 2020-12-17 2024-01-23 江苏锁安科技有限公司 一种智能家居订单服务平台的分发方法
CN113076719B (zh) * 2021-03-23 2021-10-08 马上消费金融股份有限公司 地理围栏的地址编码确定方法、位置确定方法及装置
CN113034186B (zh) * 2021-03-25 2023-04-28 支付宝(杭州)信息技术有限公司 一种商家召回推荐方法、装置以及设备
CN114491307B (zh) * 2022-01-14 2024-03-22 青岛海信网络科技股份有限公司 一种设备聚合方法及装置
US11494952B1 (en) * 2022-02-24 2022-11-08 Interleev, Llc Efficient integration of data into augmented and virtual reality environments
CN116033344B (zh) * 2022-06-13 2023-09-26 荣耀终端有限公司 地理围栏的确定方法、设备及存储介质
CN118520065B (zh) * 2024-07-23 2024-10-18 深圳天海宸光科技有限公司 基于gis地图的数据处理方法、装置、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103533501A (zh) * 2013-10-15 2014-01-22 厦门雅迅网络股份有限公司 一种地理围栏生成方法
US20140258201A1 (en) * 2013-03-05 2014-09-11 Qualcomm Incorporated Generating a geofence via an analysis of a gps fix utilization distribution
US20160057573A1 (en) * 2014-08-21 2016-02-25 International Business Machines Corporation Aggregated geo-fencing area based information delivery
CN105718465A (zh) * 2014-12-02 2016-06-29 阿里巴巴集团控股有限公司 地理围栏生成方法及装置
CN106162544A (zh) * 2015-04-21 2016-11-23 阿里巴巴集团控股有限公司 一种地理围栏的生成方法和设备
CN107070961A (zh) * 2016-09-30 2017-08-18 阿里巴巴集团控股有限公司 基于地理位置数据的热点区域确定方法及装置
CN109992633A (zh) * 2019-02-20 2019-07-09 北京三快在线科技有限公司 基于用户位置的地理围栏确定方法、装置、电子设备

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130290707A1 (en) * 2011-02-07 2013-10-31 Carpadium Consulting Pty. Ltd. Information distribution system
US8670783B2 (en) * 2011-09-23 2014-03-11 Motorola Solutions, Inc. Apparatus and method for utilizing location capable two-way radio transceivers as geo-fence posts
US10445774B2 (en) * 2014-02-14 2019-10-15 Retailmenot, Inc. Geotargeting of content by dynamically detecting geographically dense collections of mobile computing devices
US10020951B2 (en) * 2014-09-17 2018-07-10 Ca, Inc. Crowdsourcing-based detection, identification, and tracking of electronic devices
KR102297389B1 (ko) * 2015-01-05 2021-09-02 픽포켓, 아이엔시. 모바일 타겟과 관련된 미디어 공유와 집합을 제어하는 다이나믹 지오펜스의 용도
US9986527B2 (en) * 2016-06-07 2018-05-29 NinthDecimal, Inc. Systems and methods of tracking locations visited by mobile devices to quantify a change from a time series of responses
US10327094B2 (en) * 2016-06-07 2019-06-18 NinthDecimal, Inc. Systems and methods to track locations visited by mobile devices and determine neighbors of and distances among locations
US10036638B2 (en) * 2016-06-07 2018-07-31 NinthDecimal, Inc. Systems and methods of tracking locations visited by mobile devices residing within a predetermined activity area to quantify a change
US9679487B1 (en) * 2015-01-20 2017-06-13 State Farm Mutual Automobile Insurance Company Alert notifications utilizing broadcasted telematics data
US9571968B1 (en) * 2015-07-21 2017-02-14 International Business Machines Corporation Geo-fence management using a cluster analysis technique
KR102374438B1 (ko) * 2015-08-10 2022-03-15 삼성전자주식회사 지오펜스 관리 방법 및 그 전자 장치
CN105788341A (zh) * 2016-01-04 2016-07-20 北京百度网讯科技有限公司 车辆站点位置确定方法和装置
US11194873B1 (en) * 2016-05-18 2021-12-07 United Services Automobile Association (Usaa) Grid-based ranking of location data
US9961488B2 (en) * 2016-06-07 2018-05-01 NinthDecimal, Inc. Systems and methods to track locations visited by mobile devices and update keyword values based on neighbor relations and distances among locations
US10075811B1 (en) * 2017-08-16 2018-09-11 Tile, Inc. Tracking device operation in risk-classified zone
US10546043B1 (en) * 2018-07-16 2020-01-28 Here Global B.V. Triangulation for K-anonymity in location trajectory data
EP3649435A4 (en) * 2018-09-18 2020-05-13 Beijing Didi Infinity Technology and Development Co., Ltd. SYSTEMS WITH ARTIFICIAL INTELLIGENCE AND METHOD FOR THE PREDICTION OF TRAFFIC ACCIDENT LOCATIONS
US10542384B1 (en) * 2018-12-27 2020-01-21 Paypal, Inc. Efficient risk model computations

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140258201A1 (en) * 2013-03-05 2014-09-11 Qualcomm Incorporated Generating a geofence via an analysis of a gps fix utilization distribution
CN103533501A (zh) * 2013-10-15 2014-01-22 厦门雅迅网络股份有限公司 一种地理围栏生成方法
US20160057573A1 (en) * 2014-08-21 2016-02-25 International Business Machines Corporation Aggregated geo-fencing area based information delivery
CN105718465A (zh) * 2014-12-02 2016-06-29 阿里巴巴集团控股有限公司 地理围栏生成方法及装置
CN106162544A (zh) * 2015-04-21 2016-11-23 阿里巴巴集团控股有限公司 一种地理围栏的生成方法和设备
CN107070961A (zh) * 2016-09-30 2017-08-18 阿里巴巴集团控股有限公司 基于地理位置数据的热点区域确定方法及装置
CN109992633A (zh) * 2019-02-20 2019-07-09 北京三快在线科技有限公司 基于用户位置的地理围栏确定方法、装置、电子设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210263957A1 (en) * 2019-03-19 2021-08-26 Tencent Technology (Shenzhen) Company Limited Method and apparatus for dividing region, storage medium, and electronic device
US11966424B2 (en) * 2019-03-19 2024-04-23 Tencent Technology (Shenzhen) Company Limited Method and apparatus for dividing region, storage medium, and electronic device
CN117539971A (zh) * 2024-01-10 2024-02-09 深圳市易甲文技术有限公司 一种海量地理坐标聚合方法及相关设备
CN117539971B (zh) * 2024-01-10 2024-04-26 深圳市易甲文技术有限公司 一种海量地理坐标聚合方法及相关设备

Also Published As

Publication number Publication date
US20210385610A1 (en) 2021-12-09
CN109992633B (zh) 2020-08-07
CN109992633A (zh) 2019-07-09

Similar Documents

Publication Publication Date Title
WO2020168767A1 (zh) 基于用户位置确定地理围栏
CN112861972B (zh) 一种展业区域的选址方法、装置、计算机设备和介质
WO2021174944A1 (zh) 基于目标对象活跃度的消息推送方法及相关设备
JP6374863B2 (ja) モバイルアプリケーションのユーザの関心プロファイル
CN106095846B (zh) 一种虚拟资源的处理方法及服务器
WO2020052338A1 (zh) 地址标识及其经纬度挖掘
CN110781971B (zh) 一种商户类型识别方法、装置、设备和可读介质
CN110046929B (zh) 一种欺诈团伙识别方法、装置、可读存储介质及终端设备
CN110909222B (zh) 基于聚类的用户画像建立方法、装置、介质及电子设备
CN107220308B (zh) Poi的合理性的检测方法及装置、设备及可读介质
CN111626767B (zh) 资源数据的发放方法、装置及设备
CN104679810B (zh) 用于基于移动装置数据产生简档的方法和系统
CN105474212A (zh) 用于基于声音标签对数据项进行分类的方法及设备
CN110889036A (zh) 一种多维度信息的处理方法、装置及终端设备
WO2023020214A1 (zh) 检索模型的训练和检索方法、装置、设备及介质
CN104135718B (zh) 一种位置信息的获取方法及装置
US11810001B1 (en) Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis
CN110020150B (zh) 信息推荐方法及装置
CN113706222A (zh) 一种门店选址的方法、装置
CN111400520B (zh) 人脸识别库的构建方法、人脸支付方法、装置和系统
CN115034864A (zh) 商品选择方法及装置、电子设备、存储介质
CN104484329B (zh) 基于评论中心词时序变化分析的消费热点追踪方法及装置
CN110309235B (zh) 一种数据处理方法、装置、设备及介质
CN114187054A (zh) 客户分类方法、装置及存储介质
CN117634751B (zh) 数据要素评估方法、装置、计算机设备以及存储介质

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: 19916140

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19916140

Country of ref document: EP

Kind code of ref document: A1