WO2019153889A1

WO2019153889A1 - Implementation of geographical location service

Info

Publication number: WO2019153889A1
Application number: PCT/CN2018/121318
Authority: WO
Inventors: 虞金花; 华镇; 侯培旭; 张弓
Original assignee: 北京三快在线科技有限公司
Priority date: 2018-02-06
Filing date: 2018-12-14
Publication date: 2019-08-15
Also published as: CN108415960B; CN108415960A

Abstract

A method for implementing a geographical location service of the present application, belonging to the technical field of computers, which solves the problem in existing technology in which a method for providing related services on the basis of geographical location has poor results. The method for implementing a geographical location service disclosed by an embodiment of the present application comprises: determining a reference geographical location associated with a real-time geographical location that is specified in a geographical location service request; determining features of the real-time geographical location according to request scene information that is specified in the geographical location service request and feature information of the reference geographical location so as to provide a service on the basis of the real-time geographical location according to the features of the real-time geographical location.

Description

Implementation of geographic location services

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 201101119487.3, entitled "A Method and Apparatus for Realizing Geographical Location Services, Electronic Devices", filed on February 06, 2018, the entire disclosure of which is incorporated herein by reference. The manner of reference is incorporated herein.

Technical field

The present application relates to the field of computer technology, and in particular to the implementation of geographic location services.

Background technique

With the development of mobile Internet technology and the introduction of LBS (Location Based Service) based elements, people can easily access the network and obtain services through mobile devices. This led to the emergence of a number of O2O (Online-to-Offline) local life services, the essence of this model is to make users and services more convenient to discover each other. Geographic location is a basic attribute when the O2O platform provides users with context-related services. For example, when the O2O platform is a service related to a user provider, a straight line distance between the user location and the merchant location or a travel distance between the user location and the merchant location is generally adopted as the location feature, so that the output is closer to the user location. Merchants to enhance the user experience.

Summary of the invention

The application provides a method for implementing a geographic location service.

In a first aspect, an embodiment of the present application provides a method for implementing a geographic location service, including: determining a target reference geographic location associated with a real-time geographic location specified in a geographic location service request; and determining, according to the request specified in the geographic location service request The scene information and the feature information of the target reference geographic location determine characteristics of the real-time geographic location to provide a service based on the real-time geographic location according to the feature.

In a second aspect, the embodiment of the present application provides an apparatus for implementing a geographic location service, including: a reference geographic location determining module, configured to determine a target reference geographic location associated with a real-time geographic location specified in a geographic location service request; a feature determining module, configured to determine, according to the request scenario information specified in the geographic location service request and feature information of the target reference geographic location, a feature of the real-time geographic location, according to the feature of the real-time geographic location A service based on the real-time geographic location is provided.

Optionally, the device further includes a reference geographic location information mining module, configured to determine feature information of the multiple reference geographic locations based on the user historical behavior data, where each of the reference geographic locations is selected from the historical behavior of the user a geographic location in the data, the target reference geographic location being at least one of the reference geographic locations associated with the real-time geographic location of the plurality of reference geographic locations.

Optionally, the reference geographic location information mining module is further configured to: determine, according to the first geographic location accuracy, a plurality of candidate reference geographic locations; and aggregate the user historical behavior data to the corresponding candidate reference according to the geographic location. a plurality of the reference geographic locations according to the second geographic location accuracy; and the user historical behavior data corresponding to each of the candidate reference geographic locations is aggregated to the corresponding reference geographic location according to the geographic location; Aggregating to the user historical behavior data of each of the reference geographic locations, determining feature information of each of the reference geographic locations; wherein the first geographic location accuracy is less than the second geographic location accuracy.

Optionally, the reference geographic location determining module is further configured to: determine, by using a dynamic circle recall, the target reference geographic location associated with the real-time geographic location; wherein the dynamic circle recall is based on a pre- The evaluation index is adjusted to adjust the geographical area, and the reference geographic location within the geographic area is recalled as the target reference geographic location.

Optionally, the determining, by the dynamic circle recall, the target reference geographic location associated with the real-time geographic location by using the dynamic circle recall, including: determining the real-time geographic location. Determining the reference geographic location within a radius; determining the popularity of the real-time geographic location and the merchant density based on at least part of the characteristic information of the reference geographic location within the specified radius; when the heat and the merchant When the density satisfies a preset threshold condition, the reference geographic location within the specified radius is determined as the target reference geographic location associated with the real-time geographic location.

Optionally, determining, by the manner of the dynamic circle recall, the target reference geographic location associated with the real-time geographic location, further comprising: when the heat and the merchant density do not satisfy the preset threshold condition, Adjusting the specified radius range according to a preset rule, and repeatedly performing determining the reference geographic location within the specified radius of the real-time geographic location to at least the reference geographic location within the specified radius And the step of determining the popularity of the real-time geographic location and the merchant density.

Optionally, the geographic location feature determining module is further configured to: determine the real-time geographic location according to the requested scenario information specified in the geographic location service request, and at least part of the feature information of the target reference geographic location. Characteristics.

Optionally, the feature of the real-time geographic location includes: a single scene feature or a composite scene feature; the single scene feature includes any one of the following: a popular merchant feature, a propensity radar feature, a heat feature, a merchant density feature, and a geographic location classification. Characteristics, cross-city attribute characteristics, popular keyword characteristics, and popular category features; the composite scene features include any of the following: hot time categories of time-divided categories, popular merchant characteristics by time period, popular keyword characteristics by time period, and classification items Popular merchant characteristics, classification target hot keyword characteristics.

Optionally, the propensity radar feature is determined by determining a linear distance and a direction angle of each merchant from the real-time geographic location according to the feature information of the target reference geographic location associated with the real-time geographic location; a straight line distance and a direction angle that maps the merchant to a predetermined sector of the radar map of the real-time geographic location; for each of the sector blocks, by a preset merchant that maps to a merchant on the sector The behavior is aggregated to determine a heat value of the sector; a list of heat values of each of the segments of the radar map is used as a propensity radar feature of the real-time geographic location.

Optionally, the cross-city attribute feature is determined by determining an urban distribution of each of the reference geographic locations according to a preset number of merchant behaviors and a city identifier of all target reference geographic locations associated with the real-time geographic location. a probability; when the urban distribution probability satisfies a preset probability threshold, determining that the real-time geographic location has a cross-city attribute; a list of city identifiers corresponding to the urban distribution probability that meets a preset condition and indicating the real-time geographic location A result identifier having a cross-city attribute as a cross-city attribute feature of the real-time geographic location.

In a third aspect, an embodiment of the present application further discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, where the processor implements the computer program A method for implementing a geographic location service according to an embodiment of the present application.

In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, where the computer program is stored, and the program is executed by the processor, and the steps of the method for implementing the geographic location service disclosed in the embodiment of the present application are performed.

The method for implementing the geographic location service disclosed in the embodiment of the present application determines a target reference geographic location associated with the real-time geographic location specified in the geographic location service request; and the request scenario information specified in the geographic location service request and the target reference The feature information of the geographic location determines the feature of the real-time geographic location to provide a service based on the real-time geographic location according to the feature, which solves the problem that the method for providing related services based on the geographic location in the prior art is less effective. The method for implementing the geographic location service disclosed in the present application dynamically determines the multi-dimensional geographic location feature on which the geographic location service is provided by combining the feature information of the predetermined reference geographic location and the real-time information of the requested geographic location service, and further Improve the usability and accuracy of geo-location based services.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only some of the present application. For the embodiments, other drawings may be obtained from those skilled in the art without any inventive labor.

1 is a flowchart of a method for implementing a geographic location service according to Embodiment 1 of the present application;

2 is a flow chart of a specific application embodiment of a method for implementing a geographic location service according to Embodiment 2 of the present application;

3 is a schematic structural diagram of an apparatus for implementing a geographic location service according to Embodiment 3 of the present application;

4 is a schematic structural diagram of an apparatus for implementing a geographic location service according to Embodiment 4 of the present application.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

With the development of mobile Internet technology and the introduction of LBS (Location Based Service) based elements, people can easily access the network and obtain services through mobile devices. This led to the emergence of a number of O2O (Online-to-Offline) local life services, the essence of this model is to make users and services more convenient to discover each other. Geographic location is a basic attribute when the O2O platform provides users with context-related services. For example, when the O2O platform is a service related to a user provider, a straight line distance between the user location and the merchant location or a travel distance between the user location and the merchant location is generally adopted as the location feature, so that the output is closer to the user location. Merchants to enhance the user experience. However, there is a certain irrationality in relying solely on linear distances. For example, although the linear distance between the user and the merchant is very short, the user and the merchant are separated by a wide river, and it is necessary to go through a bridge far away to reach the merchant. Compared to the linear distance between the user's location and the merchant's location, it is more reasonable to provide geographic location-related services based on the travel distance between the user's location and the merchant's location. However, the current travel distance can only be obtained by calling the map service. The O2O search recommendation calls the map service online for a long time, which does not meet the requirements of the fast response in the O2O search recommendation scenario.

It can be seen that the method of providing related services based on geographical location still has the defects of low efficiency and poor service effect.

Embodiment 1

As shown in FIG. 1 , the method includes the following steps: Step 110 to Step 120.

Step 110: Determine a target reference geographic location associated with the real-time geographic location specified in the geographic location service request.

The real-time location specified in the location service request is the current geographic location of the user contained in the user search request. When the user or the application initiates a location-based search request to the platform, the platform acquires a real-time geographic location of the user or the application; and then determines a geographic location in the preset range near the real-time geographic location where the preset user behavior occurs , as a target reference geographic location associated with the real-time geographic location. The preset behavior includes but is not limited to any one or more of the following: click, purchase, browse, search.

The preset range may be a preset radius range centered on the real-time geographic location, or may be a radius range determined according to a preset index. The preset indicator may be data such as merchant popularity, concentration, and the like within the preset range.

When determining a geographical location in which a preset user behavior occurs within a preset range near the real-time geographic location, firstly, the historical behavior data of the user needs to be acquired; and then, the geographical location where the preset user behavior has occurred is determined according to the historical historical behavior data of the user. Finally, clustering and screening the geographical locations according to geographic location distribution (such as sparsity, heat, etc.) to determine the reference geographic location; and clustering according to the geographic location, screening the results, and user history of the geographic location The behavior data is combined to determine the feature information of the corresponding reference geographic location. Each reference geographic location will correspond to a set of feature information; each set of feature information is composed of multiple dimensions; each dimension may be a feature or a feature list.

The feature information is statistical information of user behavior and a preset indicator of the merchant determined according to user historical behavior data on each reference geographic location, such as search information, click information, browsing information, business category, and the like. In a specific implementation, the feature information includes, but is not limited to, any one or more of the following: latitude, longitude, city identity, search keywords in different time periods, number of clicks of search keywords in different time periods, search category identifier, search Category click statistics, business logo, business clicks, merchant orders, business location longitude, business location latitude, 5 star merchants, 4.5 star merchants, 4 star merchants, 3.5 star merchants, 3 Number of star merchants, number of merchants below 3 stars, merchant price, geographical location category, total uv (unique visitor), click uv number, order uv number, total pv (Page View, number of visits), click The number of pv, the number of pv orders, and the like.

Step 120: Determine, according to the request scenario information specified in the geographic location service request and the feature information of the reference geographic location, a feature of the real-time geographic location. In this way, a service based on the real-time geographic location can be provided based on the characteristics of the real-time geographic location.

When the user or the application initiates a location-based search request to the platform, the user search request may include request scenario information, where the request scenario information is used to indicate a feature matching condition of the real-time geographic location. The feature matching condition includes a single scene feature extraction condition or a composite scene feature extraction condition. In a specific implementation, the feature information of the reference geographic location is processed according to the feature matching condition indicated in the request scenario information of the real-time geographic location, such as the feature category to be extracted, the time period of the feature matching, and the like. The characteristics of real-time geographic location. The feature matching conditions indicated by the request scenario information are different, and the extracted features of the real-time geographic location are also different.

The method for implementing a geographic location service disclosed in the embodiment of the present application, by determining a target reference geographic location associated with a real-time geographic location specified in a geographic location service request; and requesting scenario information specified in the geographic location service request and the target Referring to the feature information of the geographic location, determining the feature of the real-time geographic location to provide a service based on the real-time geographic location according to the feature of the real-time geographic location, and effectively improving the effect of providing related services based on the geographic location. The method for realizing the geographic location service disclosed in the present application can dynamically determine the multi-dimensional geographic location feature by combining the feature information of the predetermined reference geographic location with the real-time information of the requested geographic location service, thereby effectively improving the geographical location based on the geographic location. The practicality and accuracy of the service.

Embodiment 2

As shown in FIG. 2, the method for implementing a geographic location service disclosed in this embodiment includes: Step 210 to Step 240.

Step 210: Determine feature information of the reference geographic location based on the user historical behavior data.

The reference geographic location is selected from a geographic location in the historical behavior data of the user. The feature information is statistical information of user behavior and a preset indicator of the merchant determined according to user historical behavior data on each reference geographic location, such as search information, click information, browsing information, business category, and the like.

By processing the historical behavior data of the user, the geographical location of all users of the platform providing the geographic location service is determined, and the geographical location is filtered and merged according to the historical historical behavior data of the user, and finally the reference geographic location is determined. The feature information for each reference geographic location is then mined as part of the data source for subsequent determination of the characteristics of the real-time geographic location.

First, the candidate reference geographic location is determined according to the first geographic location accuracy.

Each piece of user historical behavior data includes a geographic location, which may be represented by latitude and longitude coordinates. The latitude and longitude coordinates can be expressed in different precisions. The first geographical position precision may be set to 10 meters in advance, and then the latitude and longitude coordinates represented by the 10 m precision of the geographical position included in the user history behavior data are determined as the candidate reference geographical position.

Then, based on the geographic location, the user historical behavior data is aggregated to the corresponding candidate reference geographic location.

When the user historical behavior data is aggregated to the corresponding candidate reference geographic location according to the geographic location, the user historical behavior data corresponding to the same candidate reference geographic location is merged into the user historical behavior data on the candidate reference geographic location, for example, The user historical behavior data of the same merchant is simply superimposed by different users in the same time period corresponding to the same candidate reference geographic location. The first geographical location accuracy is 10 meters, the fourth position after the latitude and longitude coordinates represents 10 meters, and the two user history behavior data corresponding to a merchant A in the candidate reference geographical position of the latitude and longitude (31.2134, 121.4235) respectively correspond to pv ( Page view page views) 1 and 2, then the merged latitude and longitude (31.2134, 121.4235) candidate reference geographic location has a pv equal to 3 for merchant A.

Further, in order to improve the accuracy and usability of the determined candidate reference geographic location, reduce the impact of sparse data on the geographic location feature extraction, and simultaneously reduce the amount of data storage, after preliminary data combining, according to the candidate reference geography The candidate location is cleaned by the heat of the location and the corresponding user historical behavior data sparsity. For example, the candidate reference geographic location whose user history behavior data amount is less than a certain value is deleted, and the candidate reference geographic location whose heat is less than the preset heat threshold is deleted.

Thereafter, the reference geographic location is determined according to the second geographic location accuracy. For example, the second geographic location accuracy may be set to 100 meters, and the latitude and longitude coordinates represented by the 100 m precision of each candidate reference geographic location after cleaning may be used as the reference geographic location. For example, the candidate reference geographic location (31.2134, 121.4235) has a corresponding reference geographic location latitude and longitude (31.213, 121.423), that is, 3 decimal places are reserved after the decimal point.

Then, according to the geographic location, the user historical behavior data corresponding to the candidate reference geographic location is aggregated to the corresponding reference geographic location.

For example, the candidate reference geographic locations whose heats corresponding to the same reference geographic location are lower than the preset heat value may be determined, and the user historical behavior data on the candidate reference geographic locations may be combined as the user history in the same reference geographic location. Behavioral data. For the specific data merging method, refer to the data merging with the first geographical location precision, which will not be described here. The second geographic location accuracy is greater than the first geographic location accuracy.

Finally, the feature information of the corresponding reference geographic location is determined according to the user historical behavior data aggregated to each of the reference geographic locations.

After the data cleaning and merging as described above, each reference geographic location corresponds to at least one merged user historical behavior data, and each field in the user historical behavior data represents a user behavior of the reference geographic location corresponding to the user historical behavior data, Information such as merchants, such as the time, number of times the user clicks, the popularity of the business, the category attribute, and so on. By processing and analyzing the user historical behavior data corresponding to each reference geographic location, the feature information of the corresponding reference geographic location can be obtained.

In a specific implementation, the feature information of the corresponding reference geographic location is determined according to the user historical behavior data aggregated to each of the reference geographic locations, including: the timestamp according to the historical behavior data of the user is from the first to the last, and is aggregated to each Each user historical behavior data on the reference geographic location sets a credibility weight from small to large; according to each user historical behavior data and corresponding credibility weights in each of the reference geographic locations, respectively Determine the feature information of the corresponding reference geographic location.

For the historical behavior data of a geographical location point, the closer the time stamp is, the higher the referenceability of the data, the higher the reliability. Therefore, the timestamps of the historical behavior data of the user are set in a first-to-last order, and a credibility weight from small to large is set for each user historical behavior data corresponding to each reference geographic location. For example, for a business who clicked on a location today and two user behaviors that also clicked on the same business a month ago, when calculating the click behavior score for that location, today’s click behavior scores It is higher than the click behavior of 1 month ago.

Then, according to the user historical behavior data and the corresponding credibility weights aggregated to each reference geographic location, the feature information of the corresponding reference geographic location is determined respectively. For example, the feature information of each reference geographic location may include, but is not limited to, any one or more of the following: latitude, longitude, city identification, time period 1 search keyword, time period 2 search keyword, time period 3 search keyword, time period 4 search keywords, time period 1 search keyword clicks, time 2 search keyword hits, time 3 search keyword hits, time 4 search keyword hits, search category identification, search category click statistics, merchants Logo, business clicks, merchant orders, business location longitude, business location latitude, 5-star merchants, 4.5-star merchants, 4-star merchants, 3.5-star merchants, 3-star merchants, 3 stars The number of merchants below the rank, merchant price, geographical location category, total uv number, click uv number, order uv number, total pv number, click pv number, order pv number.

For a specific method for determining the feature information of each reference geographic location based on the credibility weight of the user's historical behavior data, refer to any technology that is well known to those skilled in the art, and details are not described herein again. The determined reference geographic location and the feature information for each reference geographic location will be used as part of the data source for subsequent determination of the characteristics of the real-time geographic location.

Step 220: Acquire real-time geographic location and request scenario information specified in the received geographic location service request.

Taking the application requesting the location-based search service as an example, when the user performs a search operation through the client input, the search service platform will receive the geographic location service request sent by the client. Typically, the geographic location service request includes a real-time geographic location of the device in which the client is located. The real-time geographic location is a real-time geographic location of a host device (such as a mobile terminal used by the user) acquired by the client by calling the system interface of the client. In a specific implementation, the real-time geographic location may be represented by latitude and longitude coordinates.

Preferably, the search service platform further needs the client to send the request scenario information of the geographic location service request. The request scenario information is used to indicate a feature matching condition of the real-time geographic location. The feature matching condition includes a single scene feature extraction condition or a composite scene feature extraction condition. The single scene feature includes any one of the following: a popular merchant feature, a propensity radar feature, a heat feature, a merchant density feature, a geographic location classification feature, a cross-city attribute feature, a popular keyword feature, and a popular category feature; The composite scene feature includes any one of the following: superimposing at least two of the single scene features, superimposing at least one of the single scene features, and a time period. For example, the request scenario information is a preset identifier of a popular merchant feature, and is used to indicate that a popular merchant feature of the real-time geographic location is acquired. For another example, the request scenario information includes a preset identifier of the time period and the hot category feature, and is used to indicate that the hot category feature of the time zone of the real-time geographic location is acquired.

Step 230: Determine a target reference geographic location in the reference geographic location that is associated with the real-time geographic location specified in the geographic location service request.

For example, the target reference geographic location associated with the real-time geographic location specified in the geographic service request can be determined by dynamic circle recall. The dynamic circle recall is to adjust a geographic area according to a preset evaluation index, and recall a reference geographic location within the geographic area. The preset evaluation indicators include, but are not limited to, the heat of the real-time geographic location and the merchant density.

Determining a target reference geographic location associated with the real-time geographic location specified in the geographic location service request by means of a dynamic circle recall, including: determining a reference geographic location within a specified radius of the real-time geographic location specified in the geographic location service request; Determining the heat of the real-time geographic location and the merchant density of the at least part of the feature information of the reference geographic location within the specified radius; determining the specified radius range when the heat and the merchant density satisfy a preset threshold condition The reference geographic location within the reference geographic location associated with the real-time geographic location.

According to the specific needs of the geographic location service, the initial value of the specified radius can be preset, for example, the initial value of the specified radius is set to 100 meters. After obtaining the real-time geographic location, it may be determined that a circular geographic extent is determined by using a real-time geographic location as a center and a specified radius of 100 meters, and the reference geographic location within the circular geographic extent is associated with the real-time geographic location. The target is referenced to the geographic location and is used as part of the data source to extract features of the real-time geographic location.

Then, determining the heat of the real-time geographic location and the merchant density according to at least part of the feature information of the reference geographic location within the specified radius.

For popular geographic location points, the user data is dense, and the radius of the circle is small to obtain sufficient data amount, so that the acquired data is sufficient to reflect the characteristics of the real-time geographic location. However, for the geographic location of the unpopular, the radius of the circle is relatively large to obtain sufficient data. Therefore, it is necessary to first perform online aggregation based on the data at various points recalled within the initially determined circular geographic range to determine the heat of the circular geographic range and the merchant density, and determine whether to perform a second circle recall and The radius of the circle of the second recall.

Among them, the heat can be calculated by the following formula:

Heat = click uv * 0.8 + order uv * 1.2.

Among them, click uv is the sum of the clicks uv of all the reference geographic locations recalled, and the order uv is the sum of the order uvs of all the reference geographic locations recalled.

The merchant density can be obtained by counting the total number of merchants of different stars in each reference geographic location, and then dividing the number of merchants by the area of the circular geographic area corresponding to the recall to obtain the merchant density.

Further, after determining the heat of the real-time geographic location and the merchant density according to at least part of the feature information of the reference geographic location within the specified radius, when the heat and the merchant density do not meet the preset threshold condition Adjusting the specified radius range according to a preset rule, repeatedly performing a determination of a reference geographic location within a specified radius of the real-time geographic location specified in the geographic location service request, and again according to the reference geographic location within the specified radius And the step of determining the popularity of the real-time geographic location and the merchant density.

When the heat and the merchant density do not meet the preset threshold condition, such as less than the preset heat threshold and the merchant density threshold, the data volume of the reference geographic location of the circular geographic range of the recall is insufficient to determine the real-time geographic location. Feature, the specified radius range is adjusted according to a preset rule, such as increasing the radius by 100 meters according to the preset gradient, and repeating the determination within the specified radius of the real-time geographic location requesting the geographic location service according to the specified radius equal to 200 meters. Refer to the geographic location. Then, determining, according to at least part of the feature information of the reference geographic location within the specified radius, the heat of the real-time geographic location and the merchant density, and determining, until the heat and the merchant density meet the pre- Set the threshold condition.

When the heat and merchant density meet a preset threshold condition, the reference geographic location within the specified radius is determined as the target reference geographic location associated with the real-time geographic location. When the heat and the merchant density meet the preset threshold condition, the feature data of the reference geographic location of the current circle recall is sufficient to reflect the feature of the real-time geographic location, and then the feature data of the referenced geographic location may be The request scenario information of the current geographic location service request determines the characteristics of the real-time geographic location.

The preset threshold conditions of the heat and merchant density may be determined according to the data distribution of the actual test. The preset rule for adjusting the specified radius may be to increase the radius by 100 meters or other steps.

Step 240: Determine, according to the request scenario information specified in the geographic location service request and the feature information of the reference geographic location, a feature of the real-time geographic location. In this way, services based on the real-time geographic location can be provided based on characteristics of the real-time geographic location.

The feature of the real-time geographic location includes a single scene feature or a composite scene feature. The present application determines the characteristics of the real-time geographic location by combining the feature data of the reference geographic location within a certain geographic range, so that the rich geographic location feature can be determined for implementing the geographic location-based service. At the same time, in order to further improve the accuracy and practicability of the location-based service, the geographic location feature for requesting the scenario information may be further determined by the request scenario information of the geographic service request.

The features of the real-time geographic location include a single scene feature or a composite scene feature. When the feature matching condition specified by the request scenario information is a single scene feature extraction condition, at least the request scenario information specified in the geographic location service request and the target reference geographic location associated with the real-time geographic location may be at least And the part of the feature information determines a single scene feature of the real-time geographic location.

In the following, the meanings and specific extraction methods of each single scene feature are illustrated.

1. Popular merchant characteristics

Popular merchant features are used to represent popular merchants near the real-time location. The real-time geographic location may be calculated according to the feature information of each of the target reference geographic locations associated with the real-time geographic location, such as the browsing, clicking, and purchase quantity of the merchants at each location point. Popular business features. For example, each merchant's heat score can be calculated by the following formula:

Score=a*Click pv number+b*click uv number+c* to place a single pv number.

Then, the merchant of the heat score topN is taken as the popular merchant feature of the real-time geographic location. Where a, b, and c are weights of different feature information, which are set according to actual business needs; click pv number, click uv number, and order pv number are corresponding feature information of all target reference geographic locations associated with the real-time geographic location. Sum.

2. Propensity to radar characteristics

The propensity radar feature is used to indicate the amount of heat on each sector of the radar chart. When the single scene feature includes a propensity radar feature, determining a linear distance and a direction angle of each merchant from the real-time geographic location according to feature information of the target reference geographic location associated with the real-time geographic location; a straight line distance and a direction angle that maps the merchant to a predetermined sector of the radar map of the real-time geographic location; for each of the sector blocks, by a preset merchant that maps to a merchant on the sector The behavior is aggregated to determine a heat value of the sector; a list of heat values of each of the segments of the radar map is used as a propensity radar feature of the real-time geographic location.

Among them, the preset merchant behavior can be the behavior of clicking, browsing, and purchasing the merchant. The preset merchant behavior of each merchant is determined by accumulating the browsing, clicking, and purchasing behaviors of the same merchant according to the feature information of all the target reference geographic locations associated with the real-time geographic location recalled by the circle. Then, calculating the geographic location of each merchant on the referenced geographic location and the linear distance and direction angle of the real-time geographic location, and mapping each merchant to the real-time geographic location according to the linear distance and the direction angle Centered on the radar chart. Finally, the business and merchant behaviors on each sector of the radar chart are aggregated to obtain a heat value on each sector. The aggregation calculation may be to accumulate preset merchant behaviors of all merchants within the same sector. A list of corresponding heat values on each sector of the radar map is used as the propensity radar feature of the real-time geographic location.

3, heat characteristics

The heat characteristics include absolute heat, relative heat, and time-division heat for indicating the heat of the real-time geographic location. For example, the feature information of all target reference geographic locations associated with the real-time geographic location recalled by the circle may be calculated by the following formula:

Heat = click uv * 0.8 + order uv * 1.2,

Among them, click uv is the sum of the clicks uv of all reference geographic locations, and the order uv is the sum of the order uvs of all reference geographic locations. The absolute heat is the absolute value of the heat. The relative heat is the heat value after the heat value is divided by the overall heat of all the geographical locations of the current city. The heat of the time is the heat value calculated by only counting the data of the specified time period. . In a specific implementation, the heat value in the range of 0-1 after normalization is used as the heat feature of the real-time geographic location.

4. Merchant density characteristics

The merchant density feature is used to indicate the distribution density of merchants in the vicinity of the real-time geographic location. When the single scene feature includes the merchant density feature, the total number of merchants of different star ratings in each of the reference geographic locations may be determined according to the feature information of the target reference geographic location associated with the real-time geographic location recalled by the circle Calculating the total number of merchants of different stars in all the reference geographical locations; dividing the total number of merchants of each star by the area of the specified radius of the real-time geographic location to obtain the merchant corresponding to each star Density, as a merchant density feature of the real-time geographic location.

For example, the total number of merchants with different star ratings in each reference geographic location may be calculated according to the feature information of all target reference geographic locations associated with the real-time geographic location recalled by the circle, and then the number of merchants is divided by the recall corresponding The area of the circular geographic area, the density of merchants. For example, first, for each merchant in the reference geographical location, first count the number of merchants by star rating, such as 3 Samsung merchants, 4 four-star merchants, etc., and divide the number of merchants by star rating by this recall. The area of the circular geographical area, that is, the density of merchants by star rating. Further, by dividing the total number of all star-level merchants in each reference geographic location by the area of the circular geographic area of the recall, the overall merchant density is obtained. The merchant density of the corresponding star value calculated by the star rating is 0-1 as the merchant density characteristic of the real-time geographic location.

5. Geographical classification features

The geographic location classification feature is used to indicate the category of the real-time geographic location, such as the real-time geographic location located in the school area, the shopping mall area, and the like. When the single scene feature includes a geographic location classification feature, the probability distribution of the reference geographic location classification may be determined according to the geographic location category feature corresponding to all the target reference geographic locations associated with the real-time geographic location; Determining a geographic location category corresponding to the highest probability, as a geographic location category of the real-time geographic location; using a geographic location category of the real-time geographic location and a probability value corresponding to the geographic location category as a geographic location classification of the real-time geographic location feature.

For example, calculating a probability distribution of geographical locations belonging to a shopping mall, an airport, a school, and the like among all target reference geographic locations associated with the real-time geographic location, and determining the real-time geographic location if the location points belonging to the shopping mall category are the most The geographical distribution feature is the mall.

6, cross-city attribute characteristics

The cross-city attribute is used to indicate whether the real-time geographic location supports services across cities and cities that can be entered. When the single scene feature includes a cross-city attribute feature, the city distribution probability of each of the reference geographic locations may be determined according to a preset number of merchant behaviors and a city identifier of all target reference geographic locations associated with the real-time geographic location. Determining, when the urban distribution probability satisfies a preset probability threshold, the real-time geographic location has a cross-city attribute; a list of city identifiers corresponding to the urban distribution probability that meets a preset condition and indicating that the real-time geographic location has The result identifier of the cross-city attribute is used as the cross-city attribute feature of the real-time geographic location.

First, counting the number of clicks, browsing, and ordering behaviors in each reference geographic location according to the click, browse, and order data in the feature information of all target reference geographic locations associated with the real-time geographic location recalled by the circle And the city identifier, determining the city distribution of the merchants in the historical behavior data of the users, for example, determining the number of preset merchant behaviors (such as click, browse, and order behavior) across the city in each reference geographic location. Then, based on the number of cross-city behaviors on each reference geographic location, determine the cross-city probability of the cities that can enter. Finally, determining whether the real-time geographic location has a cross-city attribute according to the cross-city probability, and the traversable city corresponding to the real-time geographic location. For example, the real-time geographic location is Suzhou Kunshan Huaqiao, where the city is Suzhou, and 60% of the reference locations of “Suzhou Kunshan Huaqiao” are in Shanghai, indicating that “Suzhou Kunshan Huaqiao” has Cross-city attributes can be incorporated into cities including Shanghai. When the merchants associated with “Suzhou Kunshan Huaqiao” are recommended based on the geographic location service, there will be merchants in Shanghai.

7, popular keyword features

Popular keywords are used to indicate popular keywords involved in the service near the real-time location. Statistic aggregation of search keywords in feature information of all target reference geographic locations associated with the real-time geographic location recalled according to the circle, and a list of topN search keywords with the most occurrences as the real-time geography Popular keyword features for location.

8, hot category features

The popular category is used to indicate the hot category of the item involved in the service near the real-time location. Performing statistical aggregation on the search category identifiers in the feature information of all target reference geographic locations associated with the real-time geographic location recalled according to the circle, and using the list of topN search categories with the most occurrences as the real-time Popular category features for geographic locations.

In a specific implementation, the single scene feature of the real-time geographic location is not limited to the above, and may also include other features. The method of determining each feature is also not limited to the method exemplified in the embodiment of the present application.

The composite scene features include, but are not limited to, any one of the following: a time-series popular category feature, a time-divided popular merchant feature, a time-divided popular keyword feature, a classified target popular merchant feature, and a classified target popular keyword feature. The composite scene feature is determined according to a composite scene feature extraction condition specified in the request scenario information. The composite scene feature extraction condition includes any one of the following: a single scene feature corresponding to a single scene constituting the composite scene, a single scene feature corresponding to a single scene constituting the composite scene, and a time segment respectively. When the request scenario information is a composite scene feature extraction condition, the target reference geographic information associated with the real-time geographic location may be determined according to the requested scenario information specified in the geographic location service request and the manner of dynamic circle recall. At least a portion of the feature information of the location determines a composite scene feature of the real-time geographic location.

In the following, the meaning of the composite scene feature and the specific extraction method are illustrated.

1. Popular merchant characteristics in different time periods

The time-divided popular merchant feature is used to indicate a popular merchant for a specified time period near the real-time geographic location. For example, when the composite scene feature extraction condition in the request scene information is a time period and a popular merchant feature, first, according to the specified time period, the characteristics of all the target reference geographic locations associated with the real-time geographic location recalled from the circle are retrieved according to the specified time period. In the information, the merchant information of the corresponding time period is filtered out; then, the merchant information after the screening is calculated according to the foregoing method for determining the hot merchant characteristics; and finally, the list of the merchants of the heat score topN is obtained as the A time-sharing popular business feature of a real-time geographic location.

2. Classification of popular merchant characteristics

The classification target popular merchant feature is used to indicate a popular merchant of a specified category near the real-time geographic location. For example, when the composite scene feature extraction condition in the request scene information is a superimposed category feature and a popular merchant feature, first, all target references associated with the real-time geographic location are determined according to a specified category feature, such as a category identifier. In the feature information of the geographical location, the merchant information of the corresponding category is filtered out; then, the merchant information after the screening is calculated according to the foregoing method for determining the characteristics of the popular merchants; and finally, the heat score of the category is obtained. The list of topN merchants serves as the hotline feature of the classified real-time location.

In a specific implementation, the composite scene feature described in the present application may also be obtained by other methods. This embodiment is only a possible example and should not constitute a limitation on the method for acquiring a composite scene feature.

Finally, the determined feature of the real-time geographic location is further returned to the client that initiates the geographic location service request, and the client inputs the feature of the real-time geographic location into a search or ranking model of the geographic location service platform, Participate in search rankings to implement services based on the real-time geographic location.

In a specific implementation, the feature information of the reference geographical location may be stored in the database of the geographic location service platform in the form of an index table by offline mining, and the feature information of the reference geographic location may be read when the feature of the real-time geographic location is determined. And through simple calculations to determine various characteristics of the real-time geographic location. In this way, there is no need to call a third-party interface. For example, if the map or navigation interface is not required to calculate the travel distance, the accuracy and practicability of the geographic location service can be improved, and the timeliness of the geographical location service is improved, and the user experience is better.

The method for implementing the geographic location service disclosed in the embodiment of the present application determines the feature information of the reference geographic location based on the historical behavior data of the user; after determining the real-time geographic location of the obtained geographic location service request and requesting the scenario information, determining the geographic location Determining the target location of the real-time geographic location associated with the real-time geographic location specified in the service request; determining the feature of the real-time geographic location according to the request scenario information specified in the geographic location service request and the feature information of the target reference geographic location, The feature of the real-time geographic location provides a service based on the real-time geographic location, improving the effectiveness of providing related services based on geographic location. The method for realizing the geographical location service disclosed in the present application determines the geographical location feature information by combining the offline data, and combines the real-time information of the requested geographic location service to determine the multi-dimensional geographic location feature based on the geographic location service, and accurately reflects the geographical location. The location features further enhance the practicality and accuracy of location-based services. By combining the request scenario information, dynamically determining the characteristics of the real-time geographic location, and returning the geographical location features in a targeted manner, the utility and accuracy of the geographic location-based service are further improved. The upper layer application can adjust the request scenario information in the geographic location service request according to actual needs, thereby obtaining richer geographic location features.

The dynamic reference circle recalls the reference geographic location to ensure sufficient reference data volume, further improving the accuracy of geographic location feature extraction.

Embodiment 3

An apparatus for implementing a geographic location service disclosed in this embodiment, as shown in FIG. 3, the apparatus includes: a reference geographic location determining module 310, configured to determine a target reference associated with a real-time geographic location specified in a geographic location service request a geographic location feature determining module 320, configured to determine a feature of the real-time geographic location according to the requested scenario information specified in the geographic location service request and feature information of the target reference geographic location, according to the real-time The feature of the geographic location provides a service based on the real-time geographic location.

The device for implementing the geographic location service disclosed in the embodiment of the present application determines the target reference geographic location associated with the real-time geographic location specified in the geographic location service request; and the request scenario information specified in the geographic location service request and the target Determining the feature of the real-time geographic location with reference to the feature information of the geographic location to provide a service based on the real-time geographic location according to the feature of the real-time geographic location, and improving a method for providing related services based on the geographic location in the prior art. effect. The device for implementing the geographic location service disclosed in the present application further improves the multi-dimensional geographic location feature based on the geographic location service by combining the feature information of the predetermined reference geographic location and the real-time information of the requested geographic location service. Based on the practicality and accuracy of geolocation services.

Optionally, as shown in FIG. 4, the device further includes: a reference geographic location information mining module 300, configured to determine feature information of a reference geographic location based on user historical behavior data, where the reference geographic location is selected from a geographic location in the user historical behavior data, the target reference geographic location being at least one of the reference geographic locations associated with the real-time geographic location of the plurality of reference geographic locations.

The feature information is statistical information of user behavior and a preset indicator of the merchant determined according to user historical behavior data on each reference geographic location, such as search information, click information, browsing information, business category, and the like.

Optionally, the reference geographic location information mining module 300 is further configured to: determine, according to the first geographic location accuracy, a plurality of candidate reference geographic locations; and aggregate the user historical behavior data to the corresponding candidate reference geography according to the geographic location. Locating a plurality of reference geographic locations according to the second geographic location accuracy; and synthesizing the user historical behavior data corresponding to each of the candidate reference geographic locations to the corresponding reference geographic location according to the geographic location; Determining feature information of each of the reference geographic locations by referring to user historical behavior data of a geographic location; wherein the first geographic location accuracy is less than the second geographic location accuracy.

Optionally, the reference geographic location information mining module 300 is further configured to: clean the reference geographic location according to the heat of the candidate reference geographic location and the corresponding user historical behavior data sparsity.

By aggregating geographic locations according to geographical accuracy from small to large, the amount of data storage can be reduced, and at the same time, reducing the impact of sparse data or low-temperature geographic locations on geographic feature extraction can improve the accuracy of the reference geographic location. And availability.

Optionally, the reference geographic location determining module 310 is further configured to:

The target reference geographic location associated with the real-time geographic location is determined by dynamic circle recall. The dynamic circle recall is to adjust a geographic area range according to a preset evaluation index, and recall the reference geographic location within the geographic area as the target reference geographic location. The preset evaluation indicators include, but are not limited to, the heat of the real-time geographic location and the merchant density.

Optionally, the determining, by the dynamic circle recall, the target reference geographic location associated with the real-time geographic location specified in the geographic location service request, including: determining the specified radius within the real-time geographic location Determining a hot spot and a merchant density of the real-time geographic location according to at least part of the feature information of the reference geographic location within the specified radius; when the heat and merchant density meet a preset threshold condition Determining the reference geographic location within the specified radius as the target reference geographic location associated with the real-time geographic location.

Optionally, determining, by the manner of the dynamic circle recall, the target reference geographic location associated with the real-time geographic location, further comprising: when the heat and the merchant density do not satisfy the preset threshold condition, Adjusting the specified radius range according to a preset rule, and repeatedly performing determining the reference geographic location within the specified radius of the real-time geographic location to at least the reference geographic location within the specified radius Part of the characteristic information, the step of determining the heat of the real-time geographic location and the merchant density

Optionally, the geographic location feature determining module 320 is further configured to: determine the real-time geography according to the request scenario information specified in the geolocation service request, and at least part of the feature information of the target reference geographic location. The characteristics of the location.

Optionally, the search service platform further needs the client to send the request scenario information of the geographic location service request. The request scenario information is used to indicate a feature matching condition of the real-time geographic location. In a specific implementation, the feature matching condition includes: a single scene feature or a composite scene feature extraction condition. The composite scene feature extraction requirement includes any one of the following: superimposing at least two of the single scene features, superimposing at least one of the single scene features, and a time period.

Optionally, the propensity radar feature is determined by determining a linear distance and a direction angle of each merchant from the real-time geographic location according to the feature information of the target reference geographic location associated with the real-time geographic location; a linear distance and a direction angle, the merchant is mapped onto a predetermined sector of the radar map of the real-time geographic location; for each of the sector, by a preset mapped to a merchant on the sector The merchant behavior is aggregated to determine a heat value of the sector block; a list of heat values of each of the sector blocks of the radar chart is used as a propensity radar feature of the real-time geographic location.

For the specific implementation, the method for determining the other various single scene features and the composite scene features is described in the method embodiment part, and is not described in this embodiment.

The device for realizing the geographic location service disclosed in the present application determines the geographical location feature of the geographic location service by combining the offline information with the offline information, and determines the multi-dimensional geographic location feature based on the geographic location service to accurately reflect the geographic location. The location features further enhance the practicality and accuracy of location-based services. By combining the request scenario information, dynamically determining the characteristics of the real-time geographic location, and returning the geographical location features in a targeted manner, the utility and accuracy of the geographic location-based service are further improved. The upper layer application can adjust the request scenario information in the geographic location service request according to actual needs, thereby obtaining richer geographic location features.

Accordingly, the present application also discloses an electronic device including a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor executing the computer program to implement the present application The method for implementing the geographic location service described in the first embodiment and the second embodiment. The electronic device can be a PC, a mobile terminal, a personal digital assistant, a tablet, or the like.

The present application also discloses a computer readable storage medium, on which a computer program is stored, and when the program is executed by the processor, the steps of implementing the geographic location service according to the first embodiment and the second embodiment of the present application are implemented.

The various embodiments in the present specification are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same similar parts between the various embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The method and device for implementing a geographic location service provided by the present application are described in detail. The principles and implementation manners of the application are described in the specific examples. The description of the above embodiments is only used to help understand the present application. The method and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of the specification should not be understood as Limitations on this application.

Through the description of the above embodiments, those skilled in the art can clearly understand that the various embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on such understanding, the above-described technical solutions may be embodied in the form of software products in essence or in the form of software products, which may be stored in a computer readable storage medium such as ROM/RAM, magnetic Discs, optical discs, etc., include instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments or portions of the embodiments.

Claims

A method for implementing a geographic location service, comprising:

Determining a target reference geographic location associated with the real-time geographic location specified in the geographic service request;

Determining a feature of the real-time geographic location according to the request scenario information specified in the geographic location service request and feature information of the target reference geographic location;

Based on the characteristics of the real-time geographic location, a service based on the real-time geographic location is provided.
The method of claim 1 further comprising:

Determining feature information of multiple reference geographic locations based on user historical behavior data,

Wherein each of the reference geographical locations is selected from a geographic location in the historical behavior data of the user.

The target reference geographic location is at least one of the reference geographic locations associated with the real-time geographic location of the plurality of reference geographic locations.
The method of claim 2, determining feature information of the plurality of reference geographic locations based on the historical behavior data of the user, including:

Determining a plurality of candidate reference geographic locations according to the first geographic location accuracy;

Aggregating the user historical behavior data to a corresponding candidate reference geographic location according to a geographic location;

Determining a plurality of the reference geographic locations according to the second geographic location accuracy;

Aggregating the user historical behavior data corresponding to each of the candidate reference geographic locations to a corresponding reference geographic location according to a geographic location;

Determining feature information of each of the reference geographic locations according to user historical behavior data aggregated to each of the reference geographic locations;

The first geographic location accuracy is less than the second geographic location accuracy.
The method according to any one of claims 2 to 3, determining the target reference geographic location associated with the real-time geographic location, comprising:

Determining, by means of a dynamic circle recall, the target reference geographic location associated with the real-time geographic location;

The dynamic circle recall is to adjust a geographic area range according to a preset evaluation index, and recall the reference geographic location within the geographic area as the target reference geographic location.
The method according to claim 4, wherein the target reference geographic location associated with the real-time geographic location is determined by the dynamic circle recalling manner, including:

Determining the reference geographic location within a specified radius of the real-time geographic location;

Determining the heat of the real-time geographic location and the merchant density according to at least part of the feature information of the reference geographic location within the specified radius;

When the heat and merchant density meet a preset threshold condition, the reference geographic location within the specified radius is determined as the target reference geographic location associated with the real-time geographic location.
The method of claim 5, determining the target reference geographic location associated with the real-time geographic location by means of the dynamic circle recall, further comprising:

Adjusting the specified radius range according to a preset rule when the heat and the merchant density do not satisfy the preset threshold condition,

Determining determining the reference geographic location within the specified radius of the real-time geographic location to determine the real-time geography based on at least a portion of the characteristic information of the reference geographic location within the specified radius The steps of location heat and merchant density.
The method according to claim 4, determining the feature of the real-time geographic location according to the request scenario information specified in the geographic location service request and the feature information of the target reference geographic location, including:

Determining the feature of the real-time geographic location according to the request scenario information specified in the geographic location service request and at least part of the feature information of the target reference geographic location.
A method according to any one of claims 1 to 7,

The features of the real-time geographic location include a single scene feature or a composite scene feature;

The single scene feature includes any one of the following: a popular merchant feature, a propensity radar feature, a heat feature, a merchant density feature, a geographic location classification feature, a cross-city attribute feature, a popular keyword feature, and a popular category feature;

The composite scene feature includes any one of the following: a time-series popular category feature, a time-divided popular merchant feature, a time-divided popular keyword feature, a classified target popular merchant feature, and a classified target popular keyword feature.
The method of claim 8 wherein said propensating radar signature is determined by:

Determining a linear distance and a direction angle of each merchant from the real-time geographic location according to the feature information of the target reference geographic location associated with the real-time geographic location;

Mapping the merchant to a preset sector of the radar map of the real-time geographic location according to the linear distance and the direction angle;

For each of the sector blocks, determining a heat value of the sector block by aggregating a preset merchant behavior of a merchant mapped to the sector block;

A list of heat values for each of the segments of the radar map is used as a propensity radar feature of the real-time geographic location.
The method of claim 8 wherein the cross-city attribute feature is determined by:

Determining a city distribution probability of each of the reference geographic locations according to a preset number of merchant behaviors and a city identifier of all the target reference geographic locations associated with the real-time geographic location;

Determining that the real-time geographic location has a cross-city attribute when the urban distribution probability satisfies a preset probability threshold;

A list of city identifiers corresponding to the city distribution probability that meets the preset condition and a result identifier indicating that the real-time geographic location has a cross-city attribute is used as a cross-city attribute feature of the real-time geographic location.
A device for implementing a geographic location service, comprising:

a reference geographic location determining module for determining a reference geographic location associated with the real-time geographic location specified in the geographic location service request;

a geographic location feature determining module, configured to determine a feature of the real-time geographic location according to the requested scenario information specified in the geographic location service request and feature information of the reference geographic location, according to the real-time geographic location The feature provides a service based on the real-time geographic location.
The apparatus of claim 11 further comprising:

a reference geographic location information mining module, configured to determine feature information of a plurality of reference geographic locations based on user historical behavior data, where each of the reference geographic locations is selected from a geographic location in the historical behavior data of the user, the target The reference geographic location is at least one of the reference geographic locations associated with the real-time geographic location of the plurality of reference geographic locations.
The apparatus according to claim 12, wherein the reference geographic location determining module is further configured to:

Determining a target reference geographic location associated with the real-time geographic location by means of a dynamic circle recall;

The dynamic circle recall is to adjust a geographic area range according to a preset evaluation index, and recall the reference geographic location within the geographic area as the target reference geographic location.
The apparatus according to claim 13, wherein the target reference geographic location associated with the real-time geographic location is determined by the dynamic circle recalling manner, including:

Determining the reference geographic location within a specified radius of the real-time geographic location;

Determining the heat of the real-time geographic location and the merchant density according to at least part of the feature information of the reference geographic location within the specified radius;

When the heat and merchant density meet a preset threshold condition, the reference geographic location within the specified radius is determined as the target reference geographic location associated with the real-time geographic location.
The device of claim 14, determining the target reference geographic location associated with the real-time geographic location by means of the dynamic circle recall, further comprising:

Adjusting the specified radius range according to a preset rule when the heat and the merchant density do not satisfy the preset threshold condition,

Repeating the reference geographic location within the specified radius of the real-time geographic location to determine the real-time geographic location based on at least a portion of the characteristic information of the reference geographic location within the specified radius The steps of heat and merchant density.
An electronic device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor executing the computer program to implement any one of claims 1 to 10 The implementation method of the geographical location service.
A computer readable storage medium having stored thereon a computer program, the program being executed by a processor to implement the steps of the method for implementing a geographic location service according to any one of claims 1 to 10.