WO2019196607A1 - 基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质 - Google Patents

基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质 Download PDF

Info

Publication number
WO2019196607A1
WO2019196607A1 PCT/CN2019/078761 CN2019078761W WO2019196607A1 WO 2019196607 A1 WO2019196607 A1 WO 2019196607A1 CN 2019078761 W CN2019078761 W CN 2019078761W WO 2019196607 A1 WO2019196607 A1 WO 2019196607A1
Authority
WO
WIPO (PCT)
Prior art keywords
poi
area
amount
influence
target area
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2019/078761
Other languages
English (en)
French (fr)
Inventor
潘广谋
孔繁硕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
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 Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Publication of WO2019196607A1 publication Critical patent/WO2019196607A1/zh
Priority to US16/891,920 priority Critical patent/US11449898B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/40—Business processes related to social networking or social networking services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to a location service based point of interest recommendation method, apparatus, network device, and storage medium.
  • the Point of Interest (POI) distributed in the city can be used as a landmark (geographical marker) to form a basic impression of the city, such as large shopping malls, high-end hotels, transportation hubs, urban parks, places of interest, leisure venues, and important institutions. , cultural education, hospitals, buildings or communities.
  • POI is based on the core data of Location Based Service (LBS), and can be applied to fields such as electronic maps or advertisement pushes, such as using a POI displayed in an electronic map as a destination before navigation, or displaying on an electronic map. View multiple restaurants, hotels, etc. around the user in multiple POIs.
  • LBS Location Based Service
  • the network device can evaluate the influence of the POI in its surrounding area based on the statistically obtained POI check-in amount and presentation amount.
  • the impact range of different POIs is different. It is impossible to accurately evaluate the influence of POI through only one POI dimension, resulting in lower accuracy of recommended POI and lower service quality of LBS.
  • a location service based point of interest recommendation method is provided.
  • an embodiment of the present application provides a location service based preference point recommendation method, where the method includes:
  • the network device determines a target area according to current location information of the user, where the target area is a geographical location range obtained by dividing the electronic map based on Mercator coordinates, and the Mercator coordinates are coordinates obtained by inkjet projection;
  • the network device acquires a target POI to be recommended in the target area, where the target POI is at least one POI selected according to the influence, and the influence includes the influence from the target area, the regional influence of the smooth window, and the At least one selected from the group consisting of regional integration influences;
  • the network device outputs the target POI.
  • an embodiment of the present application provides a location service based point of interest recommendation apparatus, the apparatus comprising means for performing the method of the first aspect.
  • an embodiment of the present application provides a non-transitory computer readable storage medium storing computer readable instructions, when executed by one or more processors, such that one or more The processor performs the following steps:
  • a target area Determining a target area according to current location information of the user, where the target area is a geographical location range obtained by dividing an electronic map based on Mercator coordinates, and the Mercator coordinates are coordinates obtained by Mercator projection;
  • the target POI is at least one POI selected according to the influence, and the influence includes the regional influence, the regional influence of the smooth window, and the influence of the multi-region fusion At least one of the selected groups;
  • the target POI is output.
  • an embodiment of the present application provides a network device, including a memory and a processor, where the computer stores computer readable instructions, where the computer readable instructions are executed by the processor, so that the processing Perform the following steps:
  • a target area Determining a target area according to current location information of the user, where the target area is a geographical location range obtained by dividing an electronic map based on Mercator coordinates, and the Mercator coordinates are coordinates obtained by Mercator projection;
  • the target POI is at least one POI selected according to the influence, and the influence includes the influence of the area, the regional influence of the smooth window, and the influence of the multi-region fusion At least one selected from the group consisting of;
  • the target POI is output.
  • 1A is an application environment diagram of a location point based interest point recommendation method in an embodiment
  • 1B is a schematic diagram of an interface of an electronic map provided in an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a location service based point of interest recommendation method provided in an embodiment of the present application
  • FIG. 3 is a schematic flowchart of a location service based point of interest recommendation method according to another embodiment of the present application.
  • FIG. 4 is a schematic diagram of an interface of an electronic map provided in another embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a location service based point of interest recommendation method according to another embodiment of the present application.
  • FIG. 6 is a schematic diagram of an interface of an electronic map provided in another embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a location service based point of interest recommendation apparatus provided in an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a network device provided in an embodiment of the present application.
  • FIG. 1A is an application environment diagram of a location service based point of interest recommendation method in some embodiments.
  • the terminal 110 may send a POI push request to the server 120, for example, requesting the server 120 to push a restaurant or a hotel around the location where the user is located, and the server obtains the current location information of the user according to the current location information of the user.
  • the target area is determined, the target POI to be recommended in the target area is obtained, and after the target POI is obtained, the target POI is sent to the terminal 110, and the target POI can be displayed in the electronic map of the terminal 110.
  • the location service based point of interest recommendation method provided by the embodiment of the present invention may also be applied to a social application, for example, may be applied to a location check-in service of a social application.
  • the server 120 receives the location check-in request sent by the terminal 110
  • the execution of the present application is performed.
  • Applying the location-based point of interest recommendation method provided by the embodiment to obtain the recommended target POI the social application of the terminal 110 can display the target POI, and the terminal 110 uses the target POI selected by the user as the POI where the user is currently located to implement the location check-in. .
  • the server 120 may be a stand-alone physical server or a server cluster composed of multiple physical servers, and may be a cloud server that provides basic cloud computing services such as a cloud server, a cloud database, a cloud storage, and a CDN.
  • the terminal 110 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto.
  • the terminal 110 and the server 120 can be connected through a communication connection such as a network, and the present invention is not limited thereto.
  • the embodiment of the present application provides a location-based interest point recommendation method, where the network device can obtain user location information, determine a target area according to the user location information, acquire a target POI to be recommended that affects the target area, and output a target POI.
  • the network device may divide the electronic map based on the Mercator coordinates to obtain at least two regions.
  • the target area is a geographical range obtained by dividing the electronic map based on Mercator coordinates.
  • the Mercator projection is a positive-axis isometric cylindrical projection. It is assumed that a cylinder that is aligned with the direction of the Earth's axis is cut on the earth. According to the equiangular condition, the warp and weft mesh is projected onto the cylindrical surface, and the cylindrical surface is flattened to obtain Mercator. projection.
  • the coordinates obtained by Mercator projection are Mercator coordinates. Taking the interface diagram of the electronic map shown in FIG. 1B as an example, the electronic map may include multiple regions.
  • the Mercator coordinate difference is approximately square at any position in the world, but only increases with latitude.
  • the side length of the area is getting shorter and shorter, and the Mercator coordinates are acceptable for a certain area such as the latitude of China, and the change in the length is acceptable, and the influence is small, and the statistics are in Mercator coordinates.
  • the accuracy of the resulting POI is higher.
  • the choice of 200 x 200 units combines these two considerations and is an appropriate choice, ie the size of the target area can be 200 x 200 units.
  • the network device can dynamically adjust the size of the area based on the total number of POIs in the area, for example, to narrow the area of the POI dense area; and expand the size of the area for the POI sparse area.
  • the size of the area with the geographical location in the high latitude area can be corrected to ensure that the area of the area at the high latitude area and the area of the low latitude area are approximately the same.
  • the target POI is at least one POI selected according to influence.
  • the POI affecting the target area includes 100 POIs, and the network device may select at least one POI among the above 100 POIs as the target POI according to the influence of the above 100 POIs on the target area.
  • the influence may include at least one of a target area influence, a smooth window's regional influence, or a multi-region fusion influence.
  • the influence is used to indicate the size of the impact ability. The greater the influence, the greater the impact.
  • the target area influence may refer to the influence of the POI on the target area obtained by dividing the electronic map based on the Mercator coordinates. For example, the regional influence of the POI on the target area is based on the first sign-off amount of the POI in the target area. And the first amount of presentation is determined.
  • the area influence of the smoothing window may refer to the area influence of the POI on the smoothing window.
  • the influence of the POI on the area generated by the smoothing window is determined according to the second sign-off amount and the second amount of the POI in the smoothing window.
  • the second amount of the POI in the smoothing window is obtained by weighting and summing the amount of the first POI in each area overlapping the smoothing window, and the second amount of the POI in the smoothing window is the first POI.
  • the amount of presentation in each area that overlaps with the smoothing window is weighted and summed, wherein the first POI is any POI within the target area.
  • the multi-region fusion influence can refer to the influence of the POI on the target region and the regional influence generated by at least one region adjacent to the target region.
  • the multi-region fusion influence of the POI on the target region is based on the POI.
  • the third sign-off amount and the third show amount in the target area are determined, and the third sign-off amount of the POI in the target area is obtained by weighted summation of the sign-off amount of the POI in each area of the merged area, and the POI is in the target.
  • the third amount of presentation in the region is obtained by weighted summation of the amount of presentation of the POI in each region of the fusion region.
  • the amount of sign-in can refer to the number of clicks that the network device detects that the user clicks on the POI within a preset time period.
  • the amount of presentation may refer to the number of times the network device presents the POI to the user within a preset time period.
  • the electronic map is not divided into regions, and the factors affecting the different regions by the same POI are not considered, which results in the accuracy of the statistically obtained POI.
  • the target area is determined based on the geographic location range obtained by dividing the electronic map by the Mercator coordinates, and the influence of the POI on the target area is obtained, and the influence of the POI calculated under the Mercator coordinates is more Accurate, can improve the quality of service of LBS.
  • the network device may be a user terminal or a server, and the user terminal may include a personal computer, a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), an in-vehicle device, or a wearable device, and the like, which is not limited by the embodiment of the present application.
  • a smart phone such as an Android mobile phone, an iOS mobile phone, etc.
  • FIG. 2 is a schematic flowchart of a method for recommending a point of interest based on a location service according to an embodiment of the present application.
  • the location service based point of interest recommendation method may at least include the following steps:
  • the network device can determine the target area according to the current location information of the user. Specifically, the network device may acquire current location information of the user, and determine the target area according to the current location information of the user.
  • the manner in which the network device determines the target area according to the current location information of the user may be: determining the area corresponding to the geographical location range where the user location is located as the target area.
  • the electronic map may be divided based on the Mercator coordinates to obtain at least two regions. , to obtain the geographical location range corresponding to each region.
  • the network device can determine that the target area is an area in the electronic map that includes the icon of the “People's Hall Ballroom”.
  • the first sign-on amount and the first amount of the first POI that are affected by the target area in the target area may be acquired, where the first POI is any of the target areas.
  • a POI is any of the target areas.
  • the first check-in amount may include the amount of the check-in per unit time, the total amount of the check-in within the preset period, or the sum of the checked-in amount that has been counted since the beginning (for example, the first check-in amount is obtained from the first time)
  • the most recent statistics show the sum of the check-in quantities obtained during the period of the sign-off amount.
  • the first amount of presentation includes the amount of presentation per unit time, the total amount of presentations within a preset period, or the sum of the amount of presentations ever recorded.
  • the unit time is one day
  • the first sign-off amount may be the amount of the check-in obtained in one day
  • the first-distribution amount may be the amount of the display obtained in one day.
  • the preset period includes 7 unit time and one unit time is one day
  • the first sign-off amount may be the check-in amount obtained in one week
  • the first display amount may be the amount of the display obtained in one week.
  • the network device may obtain the total amount of the check-in and the total amount of the display of the POI in the preset period in the target area, and determine the POI according to the total amount of the check-in and the total amount of the display in the preset period.
  • the regional influence in the target area can change the heat of the POI in a certain period of time as the evaluation criterion of the influence of the POI under different timeliness.
  • the network device may use the first sign-off amount and the first show quantity of the first POI in the target area as an evaluation criterion of the regional influence of the first POI in the target area.
  • the influence of the POI can be positively correlated with the amount of the POI, and the influence of the POI can be positively correlated with the amount of the POI.
  • the first sign-off amount may be divided by the first amount of the first POI to obtain the first POI in the target area.
  • the first click rate determines the regional influence of the first POI in the target area according to the first sign-in amount and the first click rate in the target area of the first POI. It should be noted that when the first presentation amount of the first POI in the target area is 0, the network device may determine that the first POI has a first hit rate of 0 in the target area.
  • the network device may divide the first sign-on amount of the first POI in the target area by the first sign-off amount of all POIs in the target area affected by the target area, to obtain the regional influence of the first POI.
  • the network device may acquire a first presentation quantity of all POIs in the target area that are affected by the target area, and select a maximum value in the first display quantity acquired above, and access the first POI based on the selected maximum value. The heat is evaluated.
  • S204 Sort each POI according to the order of regional influence from high to low.
  • the area influence can be used as a reference for sorting each POI, for example, according to the regional influence from high to low.
  • the individual POIs are sorted in order.
  • the network device can also sort the individual POIs in order of low-to-high regional influence.
  • S205 Select at least one POI as the target POI according to the sorting order.
  • the network devices sort the individual POIs in descending order of regional influence, at least one POI may be selected in the sort order as the target POI.
  • the POI affecting the target area includes 100 POIs, and the network device can select 10 POIs with higher regional influence among the above 100 POIs, wherein the selected 10 POIs have higher regional influence than the above 100 POIs.
  • the target POI may be output.
  • the target POI includes POI1-POI10, and the POI1-POI3 is located in an area adjacent to the target area and located on the left side of the target area.
  • POI4-POI10 is located in the target area, and the network device may be in the network.
  • POI4-POI10 is displayed in the target area, and POI1-POI3 is displayed in an area adjacent to the target area and located to the left of the target area.
  • the target area is determined according to the current location information of the user, and the first sign-on amount and the first display quantity of the first POI that is affected by the target area in the target area are obtained, and are determined according to the first sign-off amount and the first display quantity.
  • the regional influence of the first POI in the target area is sorted according to the order of influence from high to low, and at least one POI is selected as the target POI according to the sort order, and the target POI is output, and the influence of the POI can be accurately evaluated. Improve the quality of service of LBS.
  • FIG. 3 is a schematic flowchart diagram of a location service based preference point recommendation method according to another embodiment of the present application. As shown in FIG. 3, the location service based point of interest recommendation method may at least include the following steps:
  • step S301 in the embodiment of the present application refer to the detailed description of the step S201 in the foregoing embodiment, and details are not described herein again.
  • S302 Create a smooth window centering on the current location of the user.
  • the network device can create a smooth window centered on the current location of the user in the electronic map, and the smooth window overlaps with any one or more of the at least two regions.
  • the smoothing window may be a square window.
  • the side length of the smoothing window may be equal to the side length of any of the at least two regions, and the smoothing window may overlap with the four regions at most.
  • the distance between the current location of the user and the length of each side of the smoothed window is equal, and the area corresponding to the geographical location where the current location of the user is located is the target area, and the smoothed window is respectively the first The area S1, the second area S2, the third area S3, and the target area S4 overlap.
  • the network device may acquire the amount of the first POI that affects each area that overlaps with the smoothing window, and the first quantity of the area that overlaps with the smoothing window, and obtain the first effect on each area that overlaps with the smoothing window.
  • the first POI is any POI that affects each area that overlaps with the smoothing window.
  • the network device can obtain the check-in quantity of the first POI in the first area, the second area, the third area, and the target area, and the network device can also obtain the first POI in the first area, the second area, The amount of presentation in the third area and the target area.
  • the first POI that affects each region that overlaps with the smoothed window may be any POI within each region that overlaps with the smoothed window.
  • the network device may perform weighted summation on the quantity of the first POI in the first area, the second area, the third area, and the target area, and obtain the second quantity of the first POI in the target area.
  • the network device may further perform weighted summation of the amount of presentation of the first POI in the first region, the second region, the third region, and the target region to obtain a second amount of presentation of the first POI in the target region.
  • the second check-in amount may include the amount of the check-in per unit time, the total amount of the check-in within the preset period, or the sum of the check-in amounts counted in the history.
  • the second amount of presentation may include the amount of presentation per unit time, the total amount of presentations within a preset period, or the sum of the amount of presentations ever counted.
  • the unit time is one day
  • the second sign-off amount may be the amount of the check-in obtained in one day
  • the second amount of the show may be the amount of the display obtained in one day.
  • the preset period includes 7 unit time
  • one unit time is one day
  • the second sign-off amount may be the check-in amount obtained in one week
  • the second display amount may be the amount of the display obtained in one week.
  • the network device may obtain the total amount of the check-in and the total amount of the display of the POI in the preset period in the target area, and determine the POI according to the total amount of the check-in and the total amount of the display in the preset period.
  • the regional influence in the target area can change the heat of the POI in a certain period of time as the evaluation criterion of the influence of the POI under different timeliness.
  • the weight of the amount of the check-in or the amount of the first POI in the first area overlapping the smoothing window may be: the area of the overlapping area of the first area and the smoothing window occupies the total area of the smoothing window.
  • the ratio of the first region is any region that overlaps with the smoothing window.
  • the network device may calculate, by using the following formula, a second check-in quantity of the first POI in the target area, where:
  • C represents the second sign-off amount of the first POI in the target area
  • S i represents the area of the overlap area of the i-th area and the smoothing window
  • C i represents the amount of the first POI in the i-th area
  • n represents The number of areas that overlap with the smoothed window.
  • the area overlapping with the smoothing window includes the first area, the second area, the third area, and the target area.
  • the network device may use the first area as the first area, and the second area.
  • the third area serves as the third area
  • the target area serves as the fourth area.
  • the second presentation quantity of the first POI in the target area can be obtained by a similar calculation, which is not described in the embodiment of the present application.
  • the network device may use the second sign-off amount and the second show quantity of the first POI in the target area as an evaluation criterion of the regional influence of the first POI in the target area.
  • the second sign-off amount may be divided by the second-distribution quantity to obtain the first POI in the target area.
  • the second click rate determines the regional influence of the first POI in the target area according to the second sign-in amount and the second click rate in the target area of the first POI. It should be noted that, when the second presentation amount of the first POI in the target area is 0, the network device may determine that the second POI of the first POI in the target area is 0.
  • the network device may divide the second check-in amount of the first POI in the target area by the second check-in amount of all POIs in the target area that affects each area that overlaps with the smoothing window, to obtain the first POI. Regional influence.
  • the network device may acquire a second presentation quantity of all POIs in each area that affects each area that overlaps with the smoothing window, and select a maximum value in the obtained second display quantity, based on the selected maximum value. The access heat of the first POI is evaluated.
  • the regional influence may be used as a reference for sorting the respective POIs, for example, according to the regional influence.
  • the POIs are sorted in order from highest to lowest.
  • the network device can also sort the individual POIs in order of low-to-high regional influence.
  • the network devices sort the individual POIs in descending order of regional influence, at least one POI may be selected in the sort order as the target POI.
  • the POI that affects each area that overlaps with the smoothing window includes 100 POIs, and the network device can select 10 POIs with higher regional influence among the above 100 POIs, wherein the selected 10 POIs have high regional influence.
  • the target POI may be output.
  • the target POI includes POI1-POI10, and the POI1-POI3 is located in an area adjacent to the target area and located on the left side of the target area.
  • POI4-POI10 is located in the target area, and the network device may be in the network.
  • POI4-POI10 is displayed in the target area, and POI1-POI3 is displayed in an area adjacent to the target area and located to the left of the target area.
  • the target area is determined according to the current location information of the user, and a smooth window is created centering on the current location of the user, and the first POI that affects each area overlapping with the smooth window is overlapped with the smoothing window.
  • the amount of the check-in within the area, and the amount of presentation of the first POI that affects each area that overlaps with the smoothed window in each area that overlaps with the smoothed window, and the first POI overlaps each area that overlaps with the smoothed window The amount of the check-in is weighted and summed, the second sign-off amount of the first POI in the target area is obtained, and the amount of presentation of the first POI in each area overlapping with the smoothing window is weighted and summed to obtain the first a second presentation quantity of a POI in the target area, determining a regional influence of the first POI in the target area according to the second sign-off amount and the second presentation quantity, and sorting the POIs according to the order of influence from high to low, Select at least one POI as the target POI according to the sorting order, and output the target POI, which can compensate for the inaccuracy caused by the regional influence and improve the service of the LBS. Quality. Compared with the location service based point of
  • FIG. 5 is a schematic flowchart of a method for recommending a point of interest based on a location service according to another embodiment of the present application.
  • the location service based point of interest recommendation method may at least include the following steps:
  • step S501 in the embodiment of the present application reference may be made to the specific description of the step S201 in the foregoing embodiment, and details are not repeatedly described in the embodiment of the present application.
  • the target area and at least one area adjacent to the target area are used as the fusion area.
  • the network device may use the target area and at least one area adjacent to the target area as the fused area. For example, if the location of the user is within an area, the network device may use the area to which the user is located as the target area. There are 8 areas adjacent to the target area, and the network device can use the target area and 8 areas adjacent to the target area as the fused area.
  • the network device may use one of the two areas as the target area, and there are five areas adjacent to the target area, and the network device may The target area and the five areas adjacent to the target area are used as the fused area, for example, the two areas, two areas adjacent to the two areas and located above the two areas, and adjacent to the two areas Two areas below the two areas above.
  • the network device may use one of the four areas as the target area, and there are three areas adjacent to the target area, and the network device may The above four regions serve as fusion regions.
  • the network device can obtain the check-in amount and the amount of the first POI in the target area, and the network device can also obtain the check-in of the first POI in the first area to the eighth area adjacent to the target area. Quantity and amount of presentation.
  • the first POI is any POI that affects each region of the fusion region.
  • the first POI that affects each region of the fusion region may be any POI within the fusion region.
  • S504 Perform weighted summation of the number of the first POIs in the regions in the fusion region to obtain a third sign-off amount of the first POI in the target region, and display the amount of the first POI in each region in the fusion region. A weighted summation is performed to obtain a third amount of presentation of the first POI in the target area.
  • the network device may perform weighted summation on the number of the first POIs in the target area and the eight areas adjacent to the target area, and obtain the third sign-off amount of the first POI in the target area.
  • the network device may also weight the summation of the first POI in the target area and the eight areas adjacent to the target area to obtain a third presentation amount of the first POI in the target area.
  • the third check-in amount may include the amount of the check-in per unit time, the total amount of the check-in within the preset period, or the sum of the check-in amounts counted in history.
  • the third amount of presentation may include the amount of presentation per unit time, the total amount of presentations within a preset period, or the sum of the amount of presentations ever recorded.
  • the unit time is one day
  • the third sign-off amount may be the check-in amount obtained in one day
  • the third-issue amount may be the amount of the display obtained in one day.
  • the preset period includes 7 unit time, and one unit time is one day.
  • the third sign-off amount may be the amount of the check-in obtained in one week
  • the third-issue amount may be the amount of the display obtained in one week.
  • the network device may obtain the total amount of the check-in and the total amount of the display of the POI in the preset period in the target area, and determine the POI according to the total amount of the check-in and the total amount of the display in the preset period.
  • the regional influence in the target area can change the heat of the POI in a certain period of time as the evaluation criterion of the influence of the POI under different timeliness.
  • the obtaining step of the weight of the check-in amount or the presentation amount of the second area of the first POI in the fusion area may include: acquiring a preset distance value, and a center point of the second area The distance between the user's current location, the second region is any region within the fusion region; the larger of the preset distance value and the separation distance value is selected; the preset distance value is between the larger one.
  • the ratio is determined as the weight of the check-in amount or the amount of presentation of the first POI in the second region.
  • the network device may calculate, by using the following formula, a third check-in quantity of the first POI in the target area, where:
  • C represents the third sign-off amount of the first POI in the target area
  • C i represents the sign-off amount of the first POI in the i-th area
  • d i represents the center point of the i-th area and the current location of the user
  • the interval distance value, n represents the number of regions in the fusion region, and the preset distance value is 100.
  • the network device may calculate, by using the following formula, a third check-in quantity of the first POI in the target area, where:
  • C represents the third sign-off amount of the first POI in the target area
  • C i represents the sign-off amount of the first POI in the i-th area
  • d i represents the center point of the i-th area and the current location of the user
  • the interval distance value, n represents the number of regions in the fusion region, the preset distance value is 100 cos ⁇ , and ⁇ represents the latitude of the first POI.
  • the area adjacent to the target area and located above the target area is used as the second area, and the area adjacent to the target area and located at the upper right of the target area is used as the third area, and the area adjacent to the target area and located to the left of the target area
  • the target area is the fifth area
  • the area adjacent to the target area and located to the right of the target area is regarded as the sixth area
  • the area adjacent to the target area and located at the lower left of the target area is regarded as the seventh area.
  • the area is adjacent to the target area and located below the target area as the eighth area, and the area adjacent to the target area and located at the lower right of the target area serves as the ninth area.
  • the third display quantity of the first POI in the target area can be obtained by a similar calculation, which is not repeatedly described in the embodiment of the present application.
  • the network device may use the third sign-off amount and the third show quantity of the first POI in the target area as an evaluation criterion of the multi-region fusion influence of the first POI in the target area.
  • the third sign-off amount may be divided by the third-distribution quantity to obtain the first POI in the target area.
  • the third click rate determines the multi-region fusion influence of the first POI in the target area according to the third sign-in amount and the third click rate in the target area of the first POI. It should be noted that, when the third presentation amount of the first POI in the target area is 0, the network device may determine that the third POI of the first POI in the target area is 0.
  • the network device may divide the third sign-on amount of the first POI in the target area by the third sign-on amount of all POIs in the target area that affect each area of the merged area, and obtain the regional influence of the first POI. .
  • the network device may obtain a third presentation quantity of all POIs that affect each area of the fusion area in each area of the fusion area, and select a maximum value in the obtained third presentation quantity, based on the selected maximum value. The access heat of the first POI is evaluated.
  • S506 Sort each POI according to the order of multi-region fusion influence from high to low.
  • the regional influence may be used as a reference for sorting each POI, for example, according to regional influence.
  • the POIs are sorted in the lowest order.
  • the network device can also sort the individual POIs in order of low-to-high regional influence.
  • the network devices sort the individual POIs in descending order of regional influence, at least one POI may be selected in the sort order as the target POI.
  • the POI affecting each region of the fusion region includes 100 POIs, and the network device may select 10 POIs with higher regional influence among the 100 POIs, wherein the selected 10 POIs have higher regional influence than the above 100.
  • the target POI may be output.
  • the target POI includes POI1-POI10, and the POI1-POI3 is located in an area adjacent to the target area and located on the left side of the target area.
  • POI4-POI10 is located in the target area, and the network device may be in the network.
  • POI4-POI10 is displayed in the target area, and POI1-POI3 is displayed in an area adjacent to the target area and located to the left of the target area.
  • the target area is determined according to the current location information of the user, and the quantity and the amount of the first POI in the fusion area affected by each area of the fusion area are obtained, and the first POI is in the fusion area.
  • the amount of the registration of each area is weighted and summed to obtain the third sign-off amount of the first POI in the target area
  • the amount of presentation of each area of the first POI in the fusion area is weighted and summed to obtain the first POI.
  • the third presentation quantity in the target area determines the multi-region fusion influence of the first POI in the target area according to the third sign-off amount and the third presentation quantity, and performs each POI according to the order of multi-region fusion influence from high to low.
  • Sorting selecting at least one POI as the target POI according to the sorting order, and outputting the target POI can accurately evaluate the influence of the POI and improve the service quality of the LBS.
  • the embodiment of the present application can effectively improve the step problem that the regional influence is easy to generate at the regional boundary, and improve the accuracy of the assessment of the regional influence of the POI.
  • the network device may determine the target region according to the current location information of the user, and refer to FIG. 2 to obtain the target region influence of the first POI in the target region.
  • the regional influence of the smoothing window of the first POI in the target area is obtained, and each POI is sorted according to the influence of the target area and the regional influence of the smoothing window, and at least one POI is selected according to the sorting order.
  • the influence of the POI can be accurately evaluated and the service quality of the LBS can be improved.
  • the network device may determine the target region according to the current location information of the user, and refer to FIG. 2 to obtain the target region influence of the first POI in the target region.
  • the multi-region fusion influence of the first POI in the target area is obtained, and each POI is sorted according to the influence of the target area and the influence of the multi-region fusion, and at least one POI is selected according to the sort order.
  • POI, and output target POI can accurately assess the influence of POI and improve the service quality of LBS.
  • the network device may determine the target area according to the current location information of the user, and refer to FIG. 3 to obtain the regional influence of the smoothing window of the first POI in the target area. Force, see Figure 5 to obtain the multi-region fusion influence of the first POI in the target area, sort the individual POIs according to the regional influence of the smoothing window and the influence of the multi-region fusion, and select at least according to the sort order.
  • a POI is used as the target POI and the target POI is output, which can accurately evaluate the influence of the POI and improve the service quality of the LBS.
  • the network device may determine the target region according to the current location information of the user, and refer to FIG. 2 to obtain the regional influence of the first POI in the target region.
  • FIG. 3 obtains the regional influence of the smoothing window of the first POI in the target area
  • FIG. 5 acquires the multi-region fusion influence of the first POI in the target area, according to the regional influence, the regional influence of the smooth window, and the multi-region
  • the POI is sorted from high to low, and at least one POI is selected as the target POI according to the sorting order, and the target POI is output, which can accurately evaluate the influence of the POI and improve the service quality of the LBS.
  • acquiring a target POI to be recommended in the target area includes: acquiring an influence of each POI that affects the target area, and the influence includes the target At least two influences selected from the group consisting of regional influence, regional influence of smoothing window, and influence of multi-region fusion; determining the comprehensive influence of each POI according to at least two influences corresponding to the POI; Comprehensive influence select at least one POI as the target POI.
  • the weight coefficients corresponding to the influences of the selected regions may be obtained.
  • the weighted sum is obtained, and the comprehensive influence is obtained, and at least one POI is selected as the target POI according to the comprehensive influence.
  • the POI whose order is greater than the preset value is selected as the target POI according to the order of the overall influence from high to low.
  • the weight corresponding to each regional influence can be set according to needs or experience.
  • the weight corresponding to the influence of the target region is 0.5
  • the weight of the regional influence of the smoothing window is 0.3
  • the weight corresponding to the influence of the multi-region fusion is 0.2
  • the accuracy of the selected POI is high.
  • the comprehensive regional influence may be 0.5*a+0.3*b+0.2*c.
  • the location service-based POI recommendation method disclosed in the embodiment of the present application can optimize the effect of the LBS surrounding recommendation service.
  • the POI click rate can be 68%. Increased to 78%.
  • the various steps in the various embodiments of the present application are not necessarily performed in the order indicated by the steps. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in the embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be executed at different times, and the execution of these sub-steps or stages The order is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of the other steps.
  • a network device is further provided, where the network device includes a location service based point of interest recommendation device, and the location service based point of interest recommendation device includes each module, and each module may pass all or part of software, Hardware or a combination thereof is implemented.
  • FIG. 7 is a schematic structural diagram of a location service-based point of interest recommendation apparatus according to an embodiment of the present application.
  • the location service-based point of interest recommendation apparatus in the embodiment of the present application may include at least Processing unit 701 and transmitting unit 702, wherein:
  • the processing unit 701 is configured to determine a target area according to the current location information of the user, where the target area is a geographical location range obtained by dividing the electronic map based on the Mercator coordinates, and the Mercator coordinates are obtained by Mercator projection. coordinate of;
  • the processing unit 701 is further configured to acquire a target POI to be recommended in the target area, where the target POI is at least one POI selected according to the influence, and the influence includes the regional influence, the regional influence of the smooth window, or At least one of multi-regional integration influences;
  • the sending unit 702 is configured to output the target POI in the target area.
  • the processing unit 701 determines the target area according to the current location information of the user, including:
  • the area corresponding to the geographical location range in which the user location information is located is determined as the target area.
  • the processing unit 701 acquires a target POI to be recommended in the target area, including:
  • At least one POI is selected as the target POI in sort order.
  • the influence includes regional influence
  • the processing unit 701 acquires the influence of each POI that affects the target area, including:
  • the influencing force includes a regional influence force of the smoothing window
  • the processing unit 701 acquires the influence of each POI that affects the target area, including:
  • the weight of the check-in amount or the display quantity in the first area where the first POI overlaps with the smoothing window is: the overlapping area area of the first area and the smoothing window occupies the smoothing window The ratio of the total area; wherein the first area is any area that overlaps the smoothing window.
  • each side length of the smoothing window is equal to each side length of any one of the at least two areas.
  • the influence includes the multi-region fusion influence
  • the processing unit 701 acquires the influence of each POI that affects the target area, including:
  • the target area and at least one area adjacent to the target area are used as a fusion area;
  • the acquiring step of the weight of the check-in amount or the display quantity of the second area of the first POI in the fusion area includes:
  • the check-in amount includes the amount of the check-in per unit time, or the total amount of the check-in within the preset period;
  • the presentation amount includes a presentation amount per unit time or a presentation total amount in a preset period, and the presentation amount is obtained according to the number of times the POI is displayed in the preset time period.
  • the processing unit 701 determines a target area according to the current location information of the user, where the target area is a geographical location range obtained by dividing the electronic map based on the Mercator coordinates, and acquiring the target area to be recommended.
  • a target POI the target POI is at least one POI selected according to the influence, and the influence includes at least one of a regional influence, a regional influence of the smooth window, or a multi-region fusion influence
  • the sending unit 702 is Outputting the target POI in the target area can accurately evaluate the influence of the POI and improve the service quality of the LBS.
  • FIG. 8 is a schematic structural diagram of a network device according to an embodiment of the present disclosure.
  • the network device provided in this embodiment of the present application may be used to implement the method implemented in the foregoing embodiment of the present application. It is to be noted that only the parts related to the embodiments of the present application are shown, and the specific technical details are not disclosed. Please refer to the embodiment of the present application shown in FIG. 2 .
  • Figure 8 is a diagram showing the internal structure of a network device in one embodiment.
  • the network device may specifically be the server 120 in FIG. 1A.
  • the computer device includes the computer device including a processor, a memory, and a network interface connected by a system bus.
  • the memory comprises a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium of the computer device stores an operating system, and can also store computer readable instructions that, when executed by the processor, cause the processor to implement a location-based interest point recommendation method.
  • the internal memory can also store computer readable instructions that, when executed by the processor, cause the processor to perform a location based based point of interest recommendation method.
  • FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the computer device to which the solution of the present application is applied.
  • the specific computer device may include More or fewer components than shown in the figure, or some components combined, or with different component arrangements.
  • the group network identification device provided herein can be implemented in the form of a computer readable instruction that can be executed on a computer device as shown in FIG.
  • the program modules constituting the group network identification device such as the processing unit 701 and the transmitting unit 702 shown in FIG. 7, can be stored in the memory of the computer device.
  • the computer readable instructions formed by the various program modules cause the processor to perform the steps in the group network identification method of the various embodiments of the present application described in this specification.
  • the network device introduced in the embodiment of the present application may be used to implement some or all of the processes in the method embodiment introduced in conjunction with FIG. 2 in this application.
  • Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory can include random access memory (RAM) or external cache memory.
  • RAM is available in a variety of formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • Synchlink DRAM SLDRAM
  • Memory Bus Radbus
  • RDRAM Direct RAM
  • DRAM Direct Memory Bus Dynamic RAM
  • RDRAM Memory Bus Dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)
  • Computing Systems (AREA)
  • Instructional Devices (AREA)
  • Navigation (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请实施例公开了一种基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质，其中方法包括：根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括区域影响力、平滑窗口的区域影响力或者多区域融合影响力中的至少一个；输出所述目标POI。

Description

基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质
本申请要求于2018年04月12日提交中国专利局，申请号为2018103258206，申请名称为“基于位置服务的兴趣点推荐方法及装置”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
本申请涉及互联网技术领域，尤其涉及基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质。
背景技术
城市中分布的兴趣点(Point of Interest，POI)可以作为地标(地理标志物)构成人们对城市的基本印象，例如大型商场、高级酒店、交通枢纽、城市公园、名胜古迹、休闲场馆、重要机关、文化教育、医院、大厦或者小区等。POI是基于位置服务(Location Based Service，LBS)的核心数据，可运用于电子地图或者广告推送等领域，例如将电子地图中显示的某个POI作为导航前选择的目的地，或者在电子地图显示的多个POI中查看用户周边的餐馆或者酒店等。网络设备可以基于统计得到的POI的签到量和展现量，对POI在其周边范围内的影响力进行评估。但是不同POI的影响范围各不相同，仅通过一个POI维度无法准确对POI的影响力进行评估，导致推荐的POI精确度较低，LBS的服务质量较低。
发明内容
根据本申请提供的各种实施例，提供一种基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质。
为了解决上述技术问题，第一方面，本申请实施例提供了一种基于位置服务的兴趣点推荐方法，所述方法包括：
网络设备根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨 卡托投影得到的坐标；
所述网络设备获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选择的至少一个；
所述网络设备输出所述目标POI。
第二方面，本申请实施例提供了一种基于位置服务的兴趣点推荐装置，所述装置包括用于执行第一方面所述的方法的单元。
第三方面，本申请实施例提供了一种非易失性计算机可读存储介质，存储有计算机可读指令，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行如下步骤：
根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；
获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括从区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选择的至少一个；
输出所述目标POI。
第四方面，本申请实施例提供了一种网络设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行如下步骤:
根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；
获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括包括从区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选择的至少一个；
输出所述目标POI。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请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的前提下，还可以根据这些附图获得其他的附图；
图1A为一个实施例中基于位置服务的兴趣点推荐方法的应用环境图；
图1B是本申请实施例中提供的一种电子地图的界面示意图；
图2是本申请实施例中提供的一种基于位置服务的兴趣点推荐方法的流程示意图；
图3是本申请另一实施例中提供的一种基于位置服务的兴趣点推荐方法的流程示意图；
图4是本申请另一实施例中提供的一种电子地图的界面示意图；
图5是本申请另一实施例中提供的一种基于位置服务的兴趣点推荐方法的流程示意图；
图6是本申请另一实施例中提供的一种电子地图的界面示意图；
图7是本申请实施例中提供的一种基于位置服务的兴趣点推荐装置的结构示意图；
图8是本申请实施例中提供的一种网络设备的结构示意图。
具体实施方式
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，所描述的实施例仅仅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。
图1A为一些实施例中基于位置服务的兴趣点推荐方法的应用环境图。参照图1A，包括终端110以及服务器120，终端110可以向服务器120发送兴趣点推送请求，例如请求服务器120推送用户所在位置周围的餐馆或者酒店等，服务器获取用户当前位置信息，根据用户当前位置信息确定目标区域，获取目标区域内待推荐的目标POI，得到目标POI后，向终端110发送目标POI，目标 POI可以在终端110的电子地图中显示。
本发明实施例提供的基于位置服务的兴趣点推荐方法还可以应用于社交应用中，例如可以应用于社交应用的位置签到服务中，当服务器120接收到终端110发送的位置签到请求时，执行本申请实施例提供的基于位置服务的兴趣点推荐方法，得到推荐的目标POI，终端110的社交应用上可以显示目标POI，终端110将用户选择的目标POI作为用户当前所在的POI，以实现位置签到。
服务器120可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群，可以是提供云服务器、云数据库、云存储和CDN等基础云计算服务的云服务器。终端110可以是智能手机、平板电脑、笔记本电脑、台式计算机、智能音箱、智能手表等，但并不局限于此。终端110以及服务器120可以通过网络等通讯连接方式进行连接，本发明在此不做限制。
本申请实施例提供了基于位置服务的兴趣点推荐方法，网络设备可以获取用户位置信息，根据用户位置信息确定目标区域，获取对目标区域影响的待推荐的目标POI，并输出目标POI。
其中，网络设备可以基于墨卡托坐标对电子地图进行划分得到至少两个区域。目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围。墨卡托投影，是正轴等角圆柱投影，假想一个与地轴方向一致的圆柱切割于地球，按等角条件，将经纬网投影到圆柱面上，将圆柱面展为平面后，得到墨卡托投影。通过墨卡托投影得到的坐标为墨卡托坐标。以图1B所示的电子地图的界面示意图为例，该电子地图可以包括多个区域，对于相同的x、y维度墨卡托坐标差在全球任意位置都是近似正方形，只是随着纬度升高，区域的边长越来越短，而墨卡托坐标对于一定的区域例如中国所处的纬度范围内，边长上的变化是可以接受的，其影响较小，在墨卡托坐标下统计得到的POI的影响力的精确度较高。
基于墨卡托坐标对电子地图进行划分的尺寸的选择，若尺寸过大，则对于POI影响力的评估粒度就会过于粗糙；若尺寸过小，则对于线下POI的影响力的统计、线上LBS的内存资源以及统计稀疏都是很大考验。200×200单位的选择综合了这两方面考虑，是一个适当的选择，即目标区域的尺寸可以为200×200单位。可选的，网络设备可以基于区域内POI的总数量动态调整该区域的尺寸，例如针对POI密集的区域，缩小该区域的尺寸；针对POI稀疏的区域，扩大该 区域的尺寸。
需要说明的是，针对全球服务，可以对地理位置范围为高纬度地区的区域的尺寸进行修正，确保高纬度地区的区域面积和低纬度地区的区域面积近似相同。
目标POI是按照影响力所选取的至少一个POI。例如，对目标区域影响的POI包括100个POI，网络设备可以按照上述100个POI对目标区域的影响力在上述100个POI中选取至少一个POI作为目标POI。
影响力可以包括目标区域影响力、平滑窗口的区域影响力或者多区域融合影响力中的至少一个。影响力用于表示影响能力的大小，影响力越大，则影响越大。目标区域影响力可以指POI对基于墨卡托坐标对电子地图进行划分得到的目标区域产生的影响力，例如POI对目标区域产生的区域影响力是根据该POI在目标区域内的第一签到量和第一展现量确定得到的。平滑窗口的区域影响力可以指POI对平滑窗口产生的区域影响力，例如POI对平滑窗口产生的区域影响力是根据该POI在平滑窗口内的第二签到量和第二展现量确定得到的，POI在平滑窗口内的第二签到量是对第一POI在与平滑窗口存在重叠的各区域内的签到量进行加权求和得到的，POI在平滑窗口内的第二展现量是对第一POI在与平滑窗口存在重叠的各区域内的展现量进行加权求和得到的，其中第一POI为目标区域内的任一个POI。多区域融合影响力可以指的是POI对目标区域以及与目标区域相邻的至少一个区域产生的区域影响力相融合得到的影响力，例如POI对目标区域产生的多区域融合影响力是根据POI在目标区域内的第三签到量和第三展现量确定得到的，POI在目标区域内的第三签到量是POI在融合区域的各区域内的签到量进行加权求和得到的，POI在目标区域内的第三展现量是POI在融合区域的各区域内的展现量进行加权求和得到的。
签到量可以指的是网络设备检测到在预设时间段内用户点击POI的点击次数。展现量可以指的是网络设备在预设时间段内向用户展示POI的展示次数。
传统的LBS的POI推荐方法中，电子地图并未进行区域划分，未考虑同一POI对不同区域产生的影响力各不相同这一因素，导致统计得到的POI的影响力的精确度较低。本申请实施例基于墨卡托坐标对电子地图进行划分所得到的地理位置范围确定目标区域，获取对目标区域影响的POI的影响力，在墨卡托坐标下统计得到的POI的影响力更为准确，可提升LBS的服务质量。
网络设备可以为用户终端或者服务器，用户终端可以包括个人电脑、智能手机(如Android手机、iOS手机等)、车载设备或者可穿戴设备等，具体不受本申请实施例的限制。
请参见图2，图2是本申请实施例公开的一种基于位置服务的兴趣点推荐方法的流程示意图。如图2所示，该基于位置服务的兴趣点推荐方法至少可以包括以下步骤：
S201，根据用户当前位置信息确定目标区域。
网络设备可以根据用户当前位置信息确定目标区域。具体地，网络设备可以获取用户当前位置信息，并根据用户当前位置信息确定目标区域。
在一个可行的实施例中，网络设备根据用户当前位置信息确定目标区域的方式具体可以为：将用户位置所在的地理位置范围对应的区域确定为目标区域。示例性的，若网络设备未对电子地图进行划分，则网络设备将用户位置所在的地理位置范围对应的区域确定为目标区域之前，可以基于墨卡托坐标对电子地图进行划分得到至少两个区域，获取各区域对应的地理位置范围。
以图1B所示的电子地图的界面示意图为例，在用户当前位置为人民大会堂宴会厅时，网络设备可以确定目标区域为电子地图中包含“人民大会堂宴会厅”这一图标的区域。
S202，获取对目标区域影响的第一POI在目标区域内的第一签到量和第一展现量。
具体地，网络设备根据用户当前位置信息确定目标区域之后，可以获取对目标区域影响的第一POI在目标区域内的第一签到量和第一展现量，其中第一POI为目标区域内的任一个POI。
在一个可行的实施例中，第一签到量可以包括单位时间的签到量，预设周期内的签到总量，或者有史以来统计到的签到量总和(例如从第一次统计得到签到量开始至最近一次统计得到签到量这一时间段内统计得到的签到量总和)。第一展现量包括单位时间的展现量，预设周期内的展现总量或者有史以来统计到的展现量总和。例如，单位时间为一天，第一签到量可以为在一天内统计得到的签到量，第一展现量可以为在一天内统计得到的展现量。又如，预设周期包括7个单位时间，一个单位时间为一天，则第一签到量可以为在一周内统计 得到的签到量，第一展现量可以为在一周内统计得到的展现量。
在该技术方案中，考虑短期热点POI，网络设备可以获取POI在目标区域内的预设周期内的签到总量和展现总量，根据预设周期内的签到总量和展现总量确定该POI在目标区域内的区域影响力，可将POI在一定时间段内的热度变化，作为不同时效性下POI的影响力评估标准。
S203，根据第一签到量和第一展现量确定第一POI在目标区域内的区域影响力。
具体地，网络设备可以将第一POI在目标区域内的第一签到量和第一展现量，作为第一POI在目标区域内的区域影响力的评估标准。POI的影响力可以与该POI的签到量成正相关关系，POI的影响力可以与该POI的展现量成正相关关系。
在一个可行的实施例中，网络设备获取第一POI在目标区域内的第一签到量和第一展现量之后，可以将第一签到量除以第一展现量得到第一POI在目标区域内的第一点击率，根据第一POI在目标区域内的第一签到量和第一点击率确定第一POI在目标区域内的区域影响力。需要说明的是，当第一POI在目标区域内的第一展现量为0时，网络设备可以确定第一POI在目标区域内的第一点击率为0。
示例性的，网络设备可以将第一POI在目标区域内的第一签到量除以对目标区域影响的所有POI在目标区域内的第一签到量，得到第一POI的区域影响力。示例性的，网络设备可以获取对目标区域影响的所有POI在目标区域内的第一展现量，并在上述获取的第一展现量中选取最大值，基于选取的最大值对第一POI的访问热度进行评估。
S204，按照区域影响力从高至低的顺序对各个POI进行排序。
具体地，网络设备通过实施步骤S202以及S203确定对目标区域影响的各个POI的区域影响力之后，可以将区域影响力作为对各个POI进行排序的参考依据，例如按照区域影响力从高至低的顺序对各个POI进行排序。可选的，网络设备也可以按照区域影响力从低至高的顺序对各个POI进行排序。
S205，按照排序顺序选择至少一个POI作为目标POI。
网络设备按照区域影响力从高至低的顺序对各个POI进行排序之后，可以按照排序顺序选择至少一个POI作为目标POI。例如，对目标区域影响的POI 包括100个POI，网络设备可以在上述100个POI中选取区域影响力较高的10个POI，其中选取的10个POI的区域影响力高于上述100个POI中除上述10个POI以外的其他POI的区域影响力。
S206，输出目标POI。
网络设备确定目标POI之后，可以输出目标POI，例如目标POI包括POI1-POI10，POI1-POI3位于与目标区域相邻且位于目标区域左侧的区域，POI4-POI10位于目标区域，则网络设备可以在目标区域内显示POI4-POI10，在与目标区域相邻且位于目标区域左侧的区域内显示POI1-POI3。
本申请实施例中，根据用户当前位置信息确定目标区域，获取对目标区域影响的第一POI在目标区域内的第一签到量和第一展现量，根据第一签到量和第一展现量确定第一POI在目标区域内的区域影响力，按照影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可准确评估POI的影响力，提高LBS的服务质量。
请参见图3，图3是本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法的流程示意图。如图3所示，该基于位置服务的兴趣点推荐方法至少可以包括以下步骤：
S301，根据用户当前位置信息确定目标区域。
本申请实施例中的步骤S301可以参见上述实施例中步骤S201的具体描述，本申请实施例不再赘述。
S302，以用户当前所在位置为中心创建一个平滑窗口。
网络设备可以在电子地图中以用户当前所在位置为中心创建一个平滑窗口，平滑窗口与至少两个区域中任一个或多个存在重叠。可选的，平滑窗口可以为方形窗口，进一步的，平滑窗口的边长与至少两个区域中任一区域的边长可以相等，则平滑窗口最多可以和4个区域存在重叠。以图4所示的电子地图的界面示意图为例，用户当前所在位置与平滑窗口的各个边长的距离相等，用户当前位置所在的地理位置范围对应的区域为目标区域，平滑窗口分别与第一区域S1、第二区域S2、第三区域S3以及目标区域S4存在重叠。
S303，获取对与平滑窗口存在重叠的各区域影响的第一POI在各区域内的签到量，以及获取对与平滑窗口存在重叠的各区域影响的第一POI在各区域内 的展现量。
具体地，网络设备可以获取对与平滑窗口存在重叠的各区域影响的第一POI在与平滑窗口存在重叠的各区域内的签到量，以及获取对与平滑窗口存在重叠的各区域影响的第一POI在与平滑窗口存在重叠的各区域内的展现量。其中，第一POI为对与平滑窗口存在重叠的各区域影响的任一个POI。以图4为例，网络设备可以获取第一POI在第一区域、第二区域、第三区域以及目标区域内的签到量，网络设备还可以获取第一POI在第一区域、第二区域、第三区域以及目标区域内的展现量。示例性的，对与平滑窗口存在重叠的各区域影响的第一POI可以为与平滑窗口存在重叠的各区域内的任一POI。
S304，对第一POI在与平滑窗口存在重叠的各区域内的签到量进行加权求和，得到第一POI在目标区域内的第二签到量，以及，对第一POI在与平滑窗口存在重叠的各区域内的展现量进行加权求和，得到第一POI在目标区域内的第二展现量。
以图4为例，网络设备可以对第一POI在第一区域、第二区域、第三区域以及目标区域内的签到量进行加权求和，得到第一POI在目标区域内的第二签到量。网络设备还可以对第一POI在第一区域、第二区域、第三区域以及目标区域内的展现量进行加权求和，得到第一POI在目标区域内的第二展现量。
在一个可行的实施例中，第二签到量可以包括单位时间的签到量，预设周期内的签到总量，或者有史以来统计到的签到量总和。第二展现量可以包括单位时间的展现量，预设周期内的展现总量或者有史以来统计到的展现量总和。例如，单位时间为一天，第二签到量可以为在一天内统计得到的签到量，第二展现量可以为在一天内统计得到的展现量。又如，预设周期包括7个单位时间，一个单位时间为一天，则第二签到量可以为在一周内统计得到的签到量，第二展现量可以为在一周内统计得到的展现量。
在该技术方案中，考虑短期热点POI，网络设备可以获取POI在目标区域内的预设周期内的签到总量和展现总量，根据预设周期内的签到总量和展现总量确定该POI在目标区域内的区域影响力，可将POI在一定时间段内的热度变化，作为不同时效性下POI的影响力评估标准。
在一个可行的实施例中，第一POI在与平滑窗口存在重叠的第一区域内的签到量或展现量的权值可以为：第一区域与平滑窗口的重叠区域面积占平滑窗 口的总面积的比值；其中，第一区域为与平滑窗口存在重叠的任一区域。
示例性的，网络设备可以通过如下公式计算得到第一POI在目标区域内的第二签到量，其中：
Figure PCTCN2019078761-appb-000001
其中，C表示第一POI在目标区域内的第二签到量，S i表示第i个区域与平滑窗口的重叠区域面积，C i表示第一POI在第i个区域内的签到量，n表示与平滑窗口存在重叠的区域的数量。以图4为例，与平滑窗口存在重叠的区域包括第一区域、第二区域、第三区域以及目标区域，则n＝4，网络设备可以将第一区域作为第一个区域，第二区域作为第二个区域，第三区域作为第三个区域，目标区域作为第四个区域。
需要说明的是，第一POI在目标区域内的第二展现量可以通过类似计算得到，本申请实施例不再赘述。
S305，根据第二签到量和第二展现量确定第一POI在目标区域内的区域影响力。
具体地，网络设备可以将第一POI在目标区域内的第二签到量和第二展现量，作为第一POI在目标区域内的区域影响力的评估标准。
在一个可行的实施例中，网络设备获取第一POI在目标区域内的第二签到量和第二展现量之后，可以将第二签到量除以第二展现量得到第一POI在目标区域内的第二点击率，根据第一POI在目标区域内的第二签到量和第二点击率确定第一POI在目标区域内的区域影响力。需要说明的是，当第一POI在目标区域内的第二展现量为0时，网络设备可以确定第一POI在目标区域内的第二点击率为0。
示例性的，网络设备可以将第一POI在目标区域内的第二签到量除以对与平滑窗口存在重叠的各区域影响的所有POI在目标区域内的第二签到量，得到第一POI的区域影响力。示例性的，网络设备可以获取对与平滑窗口存在重叠的各区域影响的所有POI在各区域内的第二展现量，并在上述获取的第二展现量中选取最大值，基于选取的最大值对第一POI的访问热度进行评估。
S306，按照区域影响力从高至低的顺序对各个POI进行排序。
具体地，网络设备通过实施步骤S303至S305确定对与平滑窗口存在重叠的各区域影响的各个POI的区域影响力之后，可以将区域影响力作为对各个POI进行排序的参考依据，例如按照区域影响力从高至低的顺序对各个POI进行排序。可选的，网络设备也可以按照区域影响力从低至高的顺序对各个POI进行排序。
S307，按照排序顺序选择至少一个POI作为目标POI。
网络设备按照区域影响力从高至低的顺序对各个POI进行排序之后，可以按照排序顺序选择至少一个POI作为目标POI。例如，对与平滑窗口存在重叠的各区域影响的POI包括100个POI，网络设备可以在上述100个POI中选取区域影响力较高的10个POI，其中选取的10个POI的区域影响力高于上述100个POI中除上述10个POI以外的其他POI的区域影响力。
S308，输出目标POI。
网络设备确定目标POI之后，可以输出目标POI，例如目标POI包括POI1-POI10，POI1-POI3位于与目标区域相邻且位于目标区域左侧的区域，POI4-POI10位于目标区域，则网络设备可以在目标区域内显示POI4-POI10，在与目标区域相邻且位于目标区域左侧的区域内显示POI1-POI3。
本申请实施例中，根据用户当前位置信息确定目标区域，以用户当前所在位置为中心创建一个平滑窗口，获取对与平滑窗口存在重叠的各区域影响的第一POI在与平滑窗口存在重叠的各区域内的签到量，以及获取对与平滑窗口存在重叠的各区域影响的第一POI在与平滑窗口存在重叠的各区域内的展现量，对第一POI在与平滑窗口存在重叠的各区域内的签到量进行加权求和，得到第一POI在所述目标区域内的第二签到量，以及，对第一POI在与平滑窗口存在重叠的各区域内的展现量进行加权求和，得到第一POI在目标区域内的第二展现量，根据第二签到量和第二展现量确定第一POI在目标区域内的区域影响力，按照影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可补偿区域影响力所产生的不准确性，提升LBS的服务质量。相对图2所示的基于位置服务的兴趣点推荐方法，本申请实施例可有效改善区域影响力在区域边界容易产生的阶跃问题，提升对POI的区域影响力的评估的准确性。
请参见图5，图5是本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法的流程示意图。如图5所示，该基于位置服务的兴趣点推荐方法至少可以包括以下步骤：
S501，根据用户当前位置信息确定目标区域。
本申请实施例中的步骤S501可以参见上述实施例中步骤S201的具体描述，本申请实施例不再赘述。
S502，将目标区域及与目标区域相邻的至少一个区域作为融合区域。
网络设备可以将目标区域及与目标区域相邻的至少一个区域作为融合区域，以图6为例，若用户所在位置为一个区域内，则网络设备可以将用户所在位置所属的区域作为目标区域，存在8个与目标区域相邻的区域，网络设备可以将目标区域及与目标区域相邻的8个区域作为融合区域。示例性的，若用户所在位置为2个区域存在重叠的边上，则网络设备可以将上述2个区域中的一个区域作为目标区域，存在5个与目标区域相邻的区域，网络设备可以将目标区域及与目标区域相邻的5个区域作为融合区域，例如上述2个区域，与上述2个区域相邻且位于上述2个区域上方的两个区域，以及与上述2个区域相邻且位于上述2个区域下方的两个区域。示例性的，若用户所在位置为4个区域存在重叠的点上，则网络设备可以将上述4个区域中的一个区域作为目标区域，存在3个与目标区域相邻的区域，网络设备可以将上述4个区域作为融合区域。
S503，获取对融合区域的各区域影响的第一POI在融合区域的各区域内的签到量和展现量。
以图6为例，网络设备可以获取第一POI在目标区域内的签到量和展现量，网络设备还可以获取第一POI在与目标区域相邻的第一个区域至第八个区域的签到量和展现量。其中，第一POI为对融合区域的各区域影响的任一个POI。示例性的，对融合区域的各区域影响的第一POI可以为融合区域内的任一POI。
S504，将第一POI在融合区域内的各区域的签到量进行加权求和得到第一POI在目标区域内的第三签到量，以及，将第一POI在融合区域内的各区域的展现量进行加权求和得到第一POI在目标区域内的第三展现量。
以图6为例，网络设备可以对第一POI在目标区域以及与目标区域相邻的8个区域内的签到量进行加权求和，得到第一POI在目标区域内的第三签到量。网络设备还可以对第一POI在目标区域以及与目标区域相邻的8个区域内的展 现量进行加权求和，得到第一POI在目标区域内的第三展现量。
在一个可行的实施例中，第三签到量可以包括单位时间的签到量，预设周期内的签到总量，或者有史以来统计到的签到量总和。第三展现量可以包括单位时间的展现量，预设周期内的展现总量或者有史以来统计到的展现量总和。例如，单位时间为一天，第三签到量可以为在一天内统计得到的签到量，第三展现量可以为在一天内统计得到的展现量。又如，预设周期包括7个单位时间，一个单位时间为一天，则第三签到量可以为在一周内统计得到的签到量，第三展现量可以为在一周内统计得到的展现量。
在该技术方案中，考虑短期热点POI，网络设备可以获取POI在目标区域内的预设周期内的签到总量和展现总量，根据预设周期内的签到总量和展现总量确定该POI在目标区域内的区域影响力，可将POI在一定时间段内的热度变化，作为不同时效性下POI的影响力评估标准。
在一个可行的实施例中，第一POI在所述融合区域内的第二区域的签到量或展现量的权值的获取步骤可以包括：获取预设距离值，以及第二区域的中心点与用户当前所在位置之间的间隔距离值，第二区域为融合区域内的任一区域；选取预设距离值与间隔距离值中的较大者；将预设距离值与较大者之间的比值确定为第一POI在第二区域的签到量或展现量的权值。
示例性的，网络设备可以通过如下公式计算得到第一POI在目标区域内的第三签到量，其中：
Figure PCTCN2019078761-appb-000002
其中，C表示第一POI在目标区域内的第三签到量，C i表示第一POI在第i个区域内的签到量，d i表示第i个区域的中心点与用户当前所在位置之间的间隔距离值，n表示融合区域中区域的数量，预设距离值为100。
示例性的，网络设备可以通过如下公式计算得到第一POI在目标区域内的第三签到量，其中：
Figure PCTCN2019078761-appb-000003
其中，C表示第一POI在目标区域内的第三签到量，C i表示第一POI在第i个区域内的签到量，d i表示第i个区域的中心点与用户当前所在位置之间的间隔 距离值，n表示融合区域中区域的数量，预设距离值为100cosθ，θ表示第一POI的纬度。
以图6为例，融合区域包括目标区域及与目标区域相邻的8个区域，则n＝9，网络设备可以将与目标区域相邻且位于目标区域左上方的区域作为第一个区域，与目标区域相邻且位于目标区域上方的区域作为第二个区域，与目标区域相邻且位于目标区域右上方的区域作为第三个区域，与目标区域相邻且位于目标区域左方的区域作为第四个区域，目标区域作为第五个区域，与目标区域相邻且位于目标区域右方的区域作为第六个区域，与目标区域相邻且位于目标区域左下方的区域作为第七个区域，与目标区域相邻且位于目标区域下方的区域作为第八个区域，与目标区域相邻且位于目标区域右下方的区域作为第九个区域。
需要说明的是，第一POI在目标区域内的第三展现量可以通过类似计算得到，本申请实施例不再赘述。
S505，根据第三签到量和第三展现量确定第一POI在目标区域内的多区域融合影响力。
具体地，网络设备可以将第一POI在目标区域内的第三签到量和第三展现量，作为第一POI在目标区域内的多区域融合影响力的评估标准。
在一个可行的实施例中，网络设备获取第一POI在目标区域内的第三签到量和第三展现量之后，可以将第三签到量除以第三展现量得到第一POI在目标区域内的第三点击率，根据第一POI在目标区域内的第三签到量和第三点击率确定第一POI在目标区域内的多区域融合影响力。需要说明的是，当第一POI在目标区域内的第三展现量为0时，网络设备可以确定第一POI在目标区域内的第三点击率为0。
示例性的，网络设备可以将第一POI在目标区域内的第三签到量除以对融合区域的各区域影响的所有POI在目标区域内的第三签到量，得到第一POI的区域影响力。示例性的，网络设备可以获取对融合区域的各区域影响的所有POI在融合区域的各区域内的第三展现量，并在上述获取的第三展现量中选取最大值，基于选取的最大值对第一POI的访问热度进行评估。
S506，按照多区域融合影响力从高至低的顺序对各个POI进行排序。
具体地，网络设备通过实施步骤S502-S505确定对融合区域的各区域影响 的各个POI的区域影响力之后，可以将区域影响力作为对各个POI进行排序的参考依据，例如按照区域影响力从高至低的顺序对各个POI进行排序。可选的，网络设备也可以按照区域影响力从低至高的顺序对各个POI进行排序。
S507，按照排序顺序选择至少一个POI作为目标POI。
网络设备按照区域影响力从高至低的顺序对各个POI进行排序之后，可以按照排序顺序选择至少一个POI作为目标POI。例如，对融合区域的各区域影响的POI包括100个POI，网络设备可以在上述100个POI中选取区域影响力较高的10个POI，其中选取的10个POI的区域影响力高于上述100个POI中除上述10个POI以外的其他POI的区域影响力。
S508，输出目标POI。
网络设备确定目标POI之后，可以输出目标POI，例如目标POI包括POI1-POI10，POI1-POI3位于与目标区域相邻且位于目标区域左侧的区域，POI4-POI10位于目标区域，则网络设备可以在目标区域内显示POI4-POI10，在与目标区域相邻且位于目标区域左侧的区域内显示POI1-POI3。
本申请实施例中，根据用户当前位置信息确定目标区域，获取对融合区域的各区域影响的第一POI在融合区域内的各区域的签到量和展现量，将第一POI在融合区域内的各区域的签到量进行加权求和得到第一POI在目标区域内的第三签到量，以及，将第一POI在融合区域内的各区域的展现量进行加权求和得到第一POI在所述目标区域内的第三展现量，根据第三签到量和第三展现量确定第一POI在目标区域内的多区域融合影响力，按照多区域融合影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可准确评估POI的影响力，提高LBS的服务质量。相对图2所示的基于位置服务的兴趣点推荐方法，本申请实施例可有效改善区域影响力在区域边界容易产生的阶跃问题，提升对POI的区域影响力的评估的准确性。
在本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法中，网络设备可以根据用户当前位置信息确定目标区域，参见图2获取第一POI在目标区域内的目标区域影响力，参见图3获取第一POI在目标区域内的平滑窗口的区域影响力，按照目标区域影响力以及平滑窗口的区域影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出 目标POI，可准确评估POI的影响力，提高LBS的服务质量。
在本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法中，网络设备可以根据用户当前位置信息确定目标区域，参见图2获取第一POI在目标区域内的目标区域影响力，参见图5获取第一POI在目标区域内的多区域融合影响力，按照目标区域影响力以及多区域融合影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可准确评估POI的影响力，提高LBS的服务质量。
在本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法中，网络设备可以根据用户当前位置信息确定目标区域，参见图3获取第一POI在目标区域内的平滑窗口的区域影响力，参见图5获取第一POI在目标区域内的多区域融合影响力，按照平滑窗口的区域影响力以及多区域融合影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可准确评估POI的影响力，提高LBS的服务质量。
在本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法中，网络设备可以根据用户当前位置信息确定目标区域，参见图2获取第一POI在目标区域内的区域影响力，参见图3获取第一POI在目标区域内的平滑窗口的区域影响力，参见图5获取第一POI在目标区域内的多区域融合影响力，按照区域影响力、平滑窗口的区域影响力以及多区域融合影响力从高至低的顺序对各个POI进行排序，按照排序顺序选择至少一个POI作为目标POI，并输出目标POI，可准确评估POI的影响力，提高LBS的服务质量。
在本申请另一实施例公开的一种基于位置服务的兴趣点推荐方法中，获取目标区域内待推荐的目标POI，包括：获取对目标区域影响的各个POI的影响力，影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选取的至少两个影响力；根据POI对应的至少两个影响力确定各个POI的综合影响力；根据各个POI的综合影响力选择至少一个POI作为目标POI。
综合影响力是指利用至少两个区域影响力综合计算得到的影响力。当按照 从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选择的至少两个区域影响力选取POI时，可以获取选取的各个区域影响力对应的权重系数，根据区域影响力以及对应的权重系数进行加权求和，得到综合影响力，根据综合影响力选择至少一个POI作为目标POI。例如，按照综合影响力从高到低的排列顺序选择排列顺序大于预设值的POI作为目标POI。其中，各个区域影响力对应的权重可以根据需要或者经验设置。例如，根据经验，可以得到当目标区域影响力对应的权重为0.5，平滑窗口的区域影响力对应的权重为0.3，多区域融合影响力对应的权重为0.2时，所选择的POI准确性高，则当目标区域影响力为a、平滑窗口的区域影响力为b、多区域融合影响力为c时，综合区域影响力可以为0.5*a+0.3*b+0.2*c。
需要说明的是，通过本申请实施例公开的基于位置服务的兴趣点推荐方法，可优化LBS周边推荐服务的效果，例如在微信朋友圈的签到位置推荐列表服务中，POI的点击率可由68％提升至78％。
应该理解的是，本申请各实施例中的各个步骤并不是必然按照步骤标号指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，各实施例中至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中，还提供了一种网络设备，该网络设备包括基于位置服务的兴趣点推荐装置，基于位置服务的兴趣点推荐装置中包括各个模块，每个模块可全部或部分通过软件、硬件或其组合来实现。
请参见图7，图7是本申请实施例中提供的一种基于位置服务的兴趣点推荐装置的结构示意图，如图所示本申请实施例中的基于位置服务的兴趣点推荐装置至少可以包括处理单元701和发送单元702，其中：
处理单元701，用于根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；
处理单元701，还用于获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括区域影响力、平滑窗口的区域影响力或者多区域融合影响力中的至少一个；
发送单元702，用于在所述目标区域内输出所述目标POI。
可选的，所述处理单元701根据用户当前位置信息确定目标区域，包括：
基于墨卡托坐标对电子地图进行划分得到至少两个区域；
获取各区域对应的地理位置范围；
将所述用户位置信息所在的地理位置范围对应的区域确定为目标区域。
可选的，所述处理单元701获取所述目标区域内待推荐的目标POI，包括：
获取对所述目标区域影响的各个POI的影响力；
按照所述影响力从高至低的顺序对各个所述POI进行排序；
按照排序顺序选择至少一个POI作为所述目标POI。
可选的，所述影响力包括区域影响力；
所述处理单元701获取对所述目标区域影响的各个POI的影响力，包括：
获取对所述目标区域影响的第一POI在所述目标区域内的第一签到量和第一展现量，所述第一POI为对所述目标区域影响的任一个POI；
根据所述第一签到量和所述第一展现量确定所述第一POI在所述目标区域内的区域影响力。
可选的，所述影响力包括所述平滑窗口的区域影响力；
所述处理单元701获取对所述目标区域影响的各个POI的影响力，包括：
以用户位置信息为中心创建一个平滑窗口，所述平滑窗口与所述至少两个区域中任一个或多个存在重叠；
获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的签到量，以及获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的展现量，所述第一POI为对与所述平滑窗口存在重叠的各区域影响的任一个POI；
对所述第一POI在与所述平滑窗口存在重叠的各区域内的签到量进行加权求和，得到所述第一POI在所述目标区域内的第二签到量，以及，对所述第一POI在与所述平滑窗口存在重叠的各区域内的展现量进行加权求和，得到所述第一POI在所述目标区域内的第二展现量；
根据所述第二签到量和所述第二展现量确定所述第一POI在所述目标区域内的区域影响力。
可选的，所述第一POI在与所述平滑窗口存在重叠的第一区域内的签到量或展现量的权值为：第一区域与所述平滑窗口的重叠区域面积占所述平滑窗口的总面积的比值；其中，所述第一区域为与所述平滑窗口存在重叠的任一区域。
可选的，所述平滑窗口的各边长与所述至少两个区域中任一区域的各边长对应相等。
可选的，所述影响力包括所述多区域融合影响力；
所述处理单元701获取对所述目标区域影响的各个POI的影响力，包括：
将所述目标区域及与所述目标区域相邻的至少一个区域作为融合区域；
获取对所述融合区域内的各区域影响的第一POI在所述融合区域内的各区域的签到量和展现量，所述第一POI为对所述融合区域内的各区域影响的任一个POI；
将所述第一POI在所述融合区域内的各区域的签到量进行加权求和得到所述第一POI在所述目标区域内的第三签到量，以及，将所述第一POI在所述融合区域内的各区域的展现量进行加权求和得到所述第一POI在所述目标区域内的第三展现量；
根据所述第三签到量和所述第三展现量确定所述第一POI在所述目标区域内的多区域融合影响力。
可选的，所述第一POI在所述融合区域内的第二区域的签到量或展现量的权值的获取步骤包括：
获取预设距离值，以及所述第二区域的中心点与用户位置信息之间的间隔距离值，所述第二区域为所述融合区域内的任一区域；
选取所述预设距离值与所述间隔距离值中的较大者；
将所述预设距离值与所述较大者之间的比值确定为所述第一POI在所述第二区域的签到量或展现量的权值。
可选的，所述签到量包括单位时间的签到量，或预设周期内的签到总量；
所述展现量包括单位时间的展现量或预设周期内的展现总量，所述展现量是根据在预设时间段内展示POI的展示次数得到的。
本申请实施例中，处理单元701根据用户当前位置信息确定目标区域，所 述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，并获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括区域影响力、平滑窗口的区域影响力或者多区域融合影响力中的至少一个，发送单元702在所述目标区域内输出所述目标POI，可准确评估POI的影响力，提高LBS的服务质量。
请参见图8，图8为本申请实施例提供的一种网络设备的结构示意图，本申请实施例提供的网络设备可以用于实施上述图2所示的本申请实施例实现的方法，为了便于说明，仅示出了与本申请实施例相关的部分，具体技术细节未揭示的，请参照图2所示的本申请实施例。
图8示出了一个实施例中网络设备的内部结构图。该网络设备具体可以是图1A中的服务器120。如图8所示，该计算机设备包括该计算机设备包括通过系统总线连接的处理器、存储器以及网络接口。其中，存储器包括非易失性存储介质和内存储器。该计算机设备的非易失性存储介质存储有操作系统，还可存储有计算机可读指令，该计算机可读指令被处理器执行时，可使得处理器实现基于位置服务的兴趣点推荐方法。该内存储器中也可储存有计算机可读指令，该计算机可读指令被处理器执行时，可使得处理器执行基于位置服务的兴趣点推荐方法。
本领域技术人员可以理解，图8示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，本申请提供的团网络识别装置可以实现为一种计算机可读指令的形式，计算机可读指令可在如图8所示的计算机设备上运行。计算机设备的存储器中可存储组成该团网络识别装置的各个程序模块，比如，图7所示的处理单元701和发送单元702。各个程序模块构成的计算机可读指令使得处理器执行本说明书中描述的本申请各个实施例的团网络识别方法中的步骤。
具体的，本申请实施例中介绍的网络设备可以用以实施本申请结合图2介绍的方法实施例中的部分或全部流程。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程， 是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一非易失性计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (24)

  1. 一种基于位置服务LBS的兴趣点POI推荐方法，由网络设备执行，所述方法包括：
    所述网络设备根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；
    所述网络设备获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选取的至少一个；
    所述网络设备输出所述目标POI。
  2. 如权利要求1所述的方法，其特征在于，所述网络设备根据用户当前位置信息确定目标区域，包括：
    所述网络设备基于墨卡托坐标对电子地图进行划分得到至少两个区域；
    所述网络设备获取各区域对应的地理位置范围；
    所述网络设备将所述用户位置信息所在的地理位置范围对应的区域确定为目标区域。
  3. 如权利要求1所述的方法，其特征在于，所述网络设备获取所述目标区域内待推荐的目标POI，包括：
    所述网络设备获取对所述目标区域影响的各个POI的影响力；
    所述网络设备按照所述影响力从高至低的顺序对各个所述POI进行排序；
    所述网络设备按照排序顺序选择至少一个POI作为所述目标POI。
  4. 如权利要求1所述的方法，其特征在于，所述网络设备获取所述目标区域内待推荐的目标POI，包括：
    所述网络设备获取对所述目标区域影响的各个POI的影响力，所述影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选取的至少两个影响力；
    所述网络设备根据POI对应的所述至少两个影响力确定各个POI的综合影响力；
    所述网络设备根据各个POI的综合影响力选择至少一个POI作为所述目标 POI。
  5. 如权利要求3或4所述的方法，其特征在于，所述影响力包括目标区域影响力；
    所述网络设备获取对所述目标区域影响的各个POI的影响力，包括：
    所述网络设备获取对所述目标区域影响的第一POI在所述目标区域内的第一签到量和第一展现量，所述第一POI为对所述目标区域影响的任一个POI；
    所述网络设备根据所述第一签到量和所述第一展现量确定所述第一POI在所述目标区域内的目标区域影响力。
  6. 如权利要求3或4所述的方法，其特征在于，所述影响力包括所述平滑窗口的区域影响力；
    所述网络设备获取对所述目标区域影响的各个POI的影响力，包括：
    所述网络设备以用户位置信息为中心创建一个平滑窗口，所述平滑窗口与所述至少两个区域中任一个或多个存在重叠；
    所述网络设备获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的签到量，以及获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的展现量，所述第一POI为对与所述平滑窗口存在重叠的各区域影响的任一个POI；
    所述网络设备对所述第一POI在与所述平滑窗口存在重叠的各区域内的签到量进行加权求和，得到所述第一POI在所述目标区域内的第二签到量，以及，对所述第一POI在与所述平滑窗口存在重叠的各区域内的展现量进行加权求和，得到所述第一POI在所述目标区域内的第二展现量；
    所述网络设备根据所述第二签到量和所述第二展现量确定所述第一POI在所述目标区域内的区域影响力。
  7. 如权利要求6所述的方法，其特征在于，所述第一POI在与所述平滑窗口存在重叠的第一区域内的签到量或展现量的权值为：第一区域与所述平滑窗口的重叠区域面积占所述平滑窗口的总面积的比值；其中，所述第一区域为与所述平滑窗口存在重叠的任一区域。
  8. 如权利要求6所述的方法，其特征在于，所述平滑窗口的各边长与所述至少两个区域中任一区域的各边长对应相等。
  9. 如权利要求3或4所述的方法，其特征在于，所述影响力包括所述多区 域融合影响力；
    所述网络设备获取对所述目标区域影响的各个POI的影响力，包括：
    所述网络设备将所述目标区域及与所述目标区域相邻的至少一个区域作为融合区域；
    所述网络设备获取对所述融合区域内的各区域影响的第一POI在所述融合区域内的各区域的签到量和展现量，所述第一POI为对所述融合区域内的各区域影响的任一个POI；
    所述网络设备将所述第一POI在所述融合区域内的各区域的签到量进行加权求和得到所述第一POI在所述目标区域内的第三签到量，以及，将所述第一POI在所述融合区域内的各区域的展现量进行加权求和得到所述第一POI在所述目标区域内的第三展现量；
    所述网络设备根据所述第三签到量和所述第三展现量确定所述第一POI在所述目标区域内的多区域融合影响力。
  10. 如权利要求9所述的方法，其特征在于，所述第一POI在所述融合区域内的第二区域的签到量或展现量的权值的获取步骤包括：
    所述网络设备获取预设距离值，以及所述第二区域的中心点与用户位置信息之间的间隔距离值，所述第二区域为所述融合区域内的任一区域；
    所述网络设备选取所述预设距离值与所述间隔距离值中的较大者；
    所述网络设备将所述预设距离值与所述较大者之间的比值确定为所述第一POI在所述第二区域的签到量或展现量的权值。
  11. 如权利要求5-10任一项所述的方法，其特征在于，所述签到量包括单位时间的签到量，或预设周期内的签到总量；
    所述展现量包括单位时间的展现量或预设周期内的展现总量，所述展现量是根据在预设时间段内展示POI的展示次数得到的。
  12. 一种基于位置服务LBS的兴趣点POI推荐装置，其特征在于，所述装置包括用于执行如权利要求1-11任一项所述的方法的单元。
  13. 一种网络设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行如下步骤:
    根据用户当前位置信息确定目标区域，所述目标区域是基于墨卡托坐标对 电子地图进行划分所得到的地理位置范围，所述墨卡托坐标为通过墨卡托投影得到的坐标；
    获取所述目标区域内待推荐的目标POI，所述目标POI是按照影响力所选取的至少一个POI，所述影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选取的至少一个；
    输出所述目标POI。
  14. 如权利要求13所述的网络设备，其特征在于，所述根据用户当前位置信息确定目标区域，包括：
    基于墨卡托坐标对电子地图进行划分得到至少两个区域；
    获取各区域对应的地理位置范围；
    将所述用户位置信息所在的地理位置范围对应的区域确定为目标区域。
  15. 如权利要求13所述的网络设备，其特征在于，所述获取所述目标区域内待推荐的目标POI，包括：
    获取对所述目标区域影响的各个POI的影响力；
    按照所述影响力从高至低的顺序对各个所述POI进行排序；
    按照排序顺序选择至少一个POI作为所述目标POI。
  16. 如权利要求13所述的网络设备，其特征在于，所述网络设备获取所述目标区域内待推荐的目标POI，包括：
    获取对所述目标区域影响的各个POI的影响力，所述影响力包括从目标区域影响力、平滑窗口的区域影响力、多区域融合影响力组成的群组中选取的至少两个影响力；
    根据POI对应的所述至少两个影响力确定各个POI的综合影响力；
    根据各个POI的综合影响力选择至少一个POI作为所述目标POI。
  17. 如权利要求15或16所述的网络设备，其特征在于，所述影响力包括目标区域影响力；
    所述获取对所述目标区域影响的各个POI的影响力，包括：
    获取对所述目标区域影响的第一POI在所述目标区域内的第一签到量和第一展现量，所述第一POI为对所述目标区域影响的任一个POI；
    根据所述第一签到量和所述第一展现量确定所述第一POI在所述目标区域内的目标区域影响力。
  18. 如权利要求15或16所述的网络设备，其特征在于，所述影响力包括所述平滑窗口的区域影响力；
    所述获取对所述目标区域影响的各个POI的影响力，包括：
    以用户位置信息为中心创建一个平滑窗口，所述平滑窗口与所述至少两个区域中任一个或多个存在重叠；
    获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的签到量，以及获取对与所述平滑窗口存在重叠的各区域影响的第一POI在与所述平滑窗口存在重叠的各区域内的展现量，所述第一POI为对与所述平滑窗口存在重叠的各区域影响的任一个POI；
    对所述第一POI在与所述平滑窗口存在重叠的各区域内的签到量进行加权求和，得到所述第一POI在所述目标区域内的第二签到量，以及，对所述第一POI在与所述平滑窗口存在重叠的各区域内的展现量进行加权求和，得到所述第一POI在所述目标区域内的第二展现量；
    根据所述第二签到量和所述第二展现量确定所述第一POI在所述目标区域内的区域影响力。
  19. 如权利要求18所述的网络设备，其特征在于，所述第一POI在与所述平滑窗口存在重叠的第一区域内的签到量或展现量的权值为：第一区域与所述平滑窗口的重叠区域面积占所述平滑窗口的总面积的比值；其中，所述第一区域为与所述平滑窗口存在重叠的任一区域。
  20. 如权利要求18所述的网络设备，其特征在于，所述平滑窗口的各边长与所述至少两个区域中任一区域的各边长对应相等。
  21. 如权利要求15或16所述的网络设备，其特征在于，所述影响力包括所述多区域融合影响力；
    所述获取对所述目标区域影响的各个POI的影响力，包括：
    将所述目标区域及与所述目标区域相邻的至少一个区域作为融合区域；
    获取对所述融合区域内的各区域影响的第一POI在所述融合区域内的各区域的签到量和展现量，所述第一POI为对所述融合区域内的各区域影响的任一个POI；
    将所述第一POI在所述融合区域内的各区域的签到量进行加权求和得到所述第一POI在所述目标区域内的第三签到量，以及，将所述第一POI在所述融 合区域内的各区域的展现量进行加权求和得到所述第一POI在所述目标区域内的第三展现量；
    根据所述第三签到量和所述第三展现量确定所述第一POI在所述目标区域内的多区域融合影响力。
  22. 如权利要求21所述的网络设备，其特征在于，所述第一POI在所述融合区域内的第二区域的签到量或展现量的权值的获取步骤包括：
    获取预设距离值，以及所述第二区域的中心点与用户位置信息之间的间隔距离值，所述第二区域为所述融合区域内的任一区域；
    选取所述预设距离值与所述间隔距离值中的较大者；
    将所述预设距离值与所述较大者之间的比值确定为所述第一POI在所述第二区域的签到量或展现量的权值。
  23. 如权利要求17-22任一项所述的网络设备，其特征在于，所述签到量包括单位时间的签到量，或预设周期内的签到总量；
    所述展现量包括单位时间的展现量或预设周期内的展现总量，所述展现量是根据在预设时间段内展示POI的展示次数得到的。
  24. 一种非易失性计算机可读存储介质，存储有计算机可读指令，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行执行如权利要求1-11任一项所述的方法。
PCT/CN2019/078761 2018-04-12 2019-03-19 基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质 Ceased WO2019196607A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/891,920 US11449898B2 (en) 2018-04-12 2020-06-03 Method, device, and storage medium for recommending point of interest for location-based service

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810325820.6A CN110390045B (zh) 2018-04-12 2018-04-12 基于位置服务的兴趣点推荐方法及装置
CN201810325820.6 2018-04-12

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/891,920 Continuation US11449898B2 (en) 2018-04-12 2020-06-03 Method, device, and storage medium for recommending point of interest for location-based service

Publications (1)

Publication Number Publication Date
WO2019196607A1 true WO2019196607A1 (zh) 2019-10-17

Family

ID=68163935

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/078761 Ceased WO2019196607A1 (zh) 2018-04-12 2019-03-19 基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质

Country Status (3)

Country Link
US (1) US11449898B2 (zh)
CN (1) CN110390045B (zh)
WO (1) WO2019196607A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11587533B2 (en) 2020-09-02 2023-02-21 Beijng Baidu Netcom Science And Technology Co., Ltd. Method for displaying point of information of map, device, and readable storage medium

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112999648B (zh) * 2019-12-18 2024-06-07 腾讯云计算（北京）有限责任公司 互动场景中的地标确定方法、装置及电子设备
CN111859184B (zh) * 2020-06-28 2024-09-06 北京嘀嘀无限科技发展有限公司 上车点推荐方法和系统
CN112395495B (zh) 2020-10-22 2021-12-17 腾讯科技（深圳）有限公司 基于兴趣点的信息推荐方法、装置、设备及存储介质
CN112214568A (zh) * 2020-10-29 2021-01-12 沈阳美行科技有限公司 Poi融合阈值的确定方法、装置和电子设备
CN114691977A (zh) * 2020-12-30 2022-07-01 北京鸿享技术服务有限公司 活动信息推荐方法、设备、存储介质及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112213A (zh) * 2013-04-19 2014-10-22 腾讯科技（深圳）有限公司 推荐信息的方法及装置
CN105528384A (zh) * 2014-10-27 2016-04-27 阿里巴巴集团控股有限公司 信息的推送方法和装置
US20160132513A1 (en) * 2014-02-05 2016-05-12 Sk Planet Co., Ltd. Device and method for providing poi information using poi grouping
CN106844376A (zh) * 2015-12-03 2017-06-13 高德软件有限公司 推荐兴趣点的方法及装置

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12299693B2 (en) * 2002-06-14 2025-05-13 Dizpersion Corporation Method and system for providing network based target advertising and encapsulation
US8473194B2 (en) * 2008-01-03 2013-06-25 Groundspeak, Inc. System and method for conducting a location based search
WO2009154484A2 (en) * 2008-06-20 2009-12-23 Business Intelligence Solutions Safe B.V. Methods, apparatus and systems for data visualization and related applications
US20100010897A1 (en) * 2008-07-14 2010-01-14 Robert Tyler Method, Apparatus and System for Calculating and Displaying an Influence Map Using Adjacencies between Discontinuous Geographies
US20120046995A1 (en) * 2009-04-29 2012-02-23 Waldeck Technology, Llc Anonymous crowd comparison
US8589069B1 (en) * 2009-11-12 2013-11-19 Google Inc. Enhanced identification of interesting points-of-interest
US8788447B2 (en) * 2010-06-22 2014-07-22 Microsoft Corporation Hyperlocal smoothing
US20130262479A1 (en) * 2011-10-08 2013-10-03 Alohar Mobile Inc. Points of interest (poi) ranking based on mobile user related data
CN103167404A (zh) * 2011-12-14 2013-06-19 北京千橡网景科技发展有限公司 用于确定兴趣点的方法和设备
US9826345B2 (en) * 2012-06-18 2017-11-21 Here Global B.V. Method and apparatus for detecting points of interest or events based on geotagged data and geolocation seeds
US8781735B2 (en) * 2012-06-25 2014-07-15 Google Inc. Adaptive clustering of locations
WO2014018658A1 (en) * 2012-07-27 2014-01-30 Maier Zachary Paul System and method for communicating information in a location-based system
US9886703B2 (en) * 2012-11-08 2018-02-06 xAd, Inc. System and method for estimating mobile device locations
CN103023977B (zh) 2012-11-19 2015-07-01 华南理工大学 基于位置信息的推荐系统及推荐方法
KR102202231B1 (ko) * 2012-12-14 2021-01-13 한국전자통신연구원 지리 정보 분석 장치 및 그 방법
US20160180386A1 (en) * 2013-02-27 2016-06-23 Francis Konig System and method for cloud based payment intelligence
US10055751B2 (en) * 2013-04-05 2018-08-21 Visa International Service Association Systems and methods to enhance search results using transaction data of merchants
GB201409308D0 (en) * 2014-05-26 2014-07-09 Tomtom Int Bv Methods of obtaining and using point of interest data
US20170061024A1 (en) * 2014-06-11 2017-03-02 Sony Corporation Information processing device, control method, and program
CN104090970B (zh) * 2014-07-17 2018-02-02 百度在线网络技术（北京）有限公司 兴趣点的展现方法及装置
GB201506356D0 (en) * 2015-04-15 2015-05-27 Tomtom Int Bv Methods of obtaining point of interest data
CN106611004B (zh) * 2015-10-26 2019-04-12 北京捷泰天域信息技术有限公司 基于矢量正四边形格网的兴趣点属性显示方法
CN106909560B (zh) * 2015-12-23 2021-01-12 香港中文大学 兴趣点排序方法
CN105677804B (zh) * 2015-12-31 2020-08-07 百度在线网络技术（北京）有限公司 权威站点的确定以及权威站点数据库的建立方法和装置
JP6640880B2 (ja) * 2016-05-10 2020-02-05 ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド 個人別コンテンツを推奨するためのシステム及び方法
CN107766375B (zh) * 2016-08-19 2020-06-09 华为技术有限公司 一种生成热力图的方法及装置
US10565751B2 (en) * 2016-09-30 2020-02-18 Here Global B.V. Method and apparatus for spatial data visualization
AU2017381768A1 (en) * 2016-12-19 2019-08-01 Groupon, Inc. Methods and systems for detecting geographic areas having elevated supply and demand levels
CN107085600B (zh) * 2017-03-31 2021-05-14 百度在线网络技术（北京）有限公司 Poi推荐方法、装置、设备及计算机可读存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112213A (zh) * 2013-04-19 2014-10-22 腾讯科技（深圳）有限公司 推荐信息的方法及装置
US20160132513A1 (en) * 2014-02-05 2016-05-12 Sk Planet Co., Ltd. Device and method for providing poi information using poi grouping
CN105528384A (zh) * 2014-10-27 2016-04-27 阿里巴巴集团控股有限公司 信息的推送方法和装置
CN106844376A (zh) * 2015-12-03 2017-06-13 高德软件有限公司 推荐兴趣点的方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11587533B2 (en) 2020-09-02 2023-02-21 Beijng Baidu Netcom Science And Technology Co., Ltd. Method for displaying point of information of map, device, and readable storage medium

Also Published As

Publication number Publication date
US20200294091A1 (en) 2020-09-17
CN110390045B (zh) 2021-12-17
US11449898B2 (en) 2022-09-20
CN110390045A (zh) 2019-10-29

Similar Documents

Publication Publication Date Title
WO2019196607A1 (zh) 基于位置服务的兴趣点推荐方法、装置、网络设备和存储介质
JP6784308B2 (ja) 施設特性を更新するプログラム、施設をプロファイリングするプログラム、コンピュータ・システム、及び施設特性を更新する方法
KR101725886B1 (ko) 자동으로 결정된 스타팅 포인트들과 선택된 목적지들 사이의 네비게이션 경로들
US9553936B2 (en) Targeting of digital content to geographic regions
US9672240B2 (en) Apparatus and method to update geographic database
CN103154993B (zh) 使用社交图信息的位置排序
US20130095855A1 (en) Method, System, and Computer Program Product for Obtaining Images to Enhance Imagery Coverage
CN104239396B (zh) 一种搜索电子地图上业务对象的方法和装置
US10146794B2 (en) System and method for spatial clustering using multiple-resolution grids
CN108256117B (zh) 用于识别与位置相关联的地点的方法、系统和存储介质
CN104090927B (zh) 一种基于电子地图的划线搜索方法和装置
US9546880B2 (en) Dynamically determining meeting locations
Mourafetis et al. Enhancing cadastral surveys by facilitating the participation of owners
CN108141706A (zh) 基于地理围栏化搜索结果提供通知
Socharoentum et al. A comparative analysis of routes generated by Web Mapping APIs
WO2020040799A1 (en) Hyper-locating places-of-interest in buildings
US9811539B2 (en) Hierarchical spatial clustering of photographs
CN113569159A (zh) 企业门店的推荐方法、装置及存储介质
CN105992153A (zh) 一种定位信息展示方法及装置
WO2019076216A1 (zh) 一种搜索方法和装置
CN119622123B (zh) 一种融合用户移动方向的轻量级兴趣点推荐方法及装置
CN105991677A (zh) 向用户提供信息对象的方法和设备
CN104581633B (zh) 支持隐私保护的障碍空间内的区域最近邻查询系统及方法
US20190005574A1 (en) System and method for matching a service provider to a service requestor
WO2015192716A1 (zh) 一种基于电子地图的划线搜索方法和装置

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: 19784220

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: 19784220

Country of ref document: EP

Kind code of ref document: A1