CN106767835B

CN106767835B - Positioning method and device

Info

Publication number: CN106767835B
Application number: CN201710068541.1A
Authority: CN
Inventors: 许梦雯; 周景博; 汪天一; 夏源; 程允胜; 吴海山
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2017-02-08
Filing date: 2017-02-08
Publication date: 2020-09-25
Anticipated expiration: 2037-02-08
Also published as: CN106767835A

Abstract

The application discloses a positioning method and a positioning device. One embodiment of the method comprises: acquiring positioning information of a user, wherein the positioning information comprises positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time; acquiring at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point; for each geographic information point in the at least one geographic information point, determining a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time; and determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values. This embodiment improves the accuracy of the user positioning.

Description

Positioning method and device

Technical Field

The application relates to the technical field of computers, in particular to the technical field of internet, and particularly relates to a positioning method and device.

Background

With the continuous development of mobile internet, mobile intelligent devices and terminals, terminal users generate a large amount of offline data such as positioning and track. The offline data truly reflects the behavior characteristics of the user in the air during physical time, and forms good supplement for the online data. And the offline data and the online data are combined, so that more accurate user portrait depicting can be realized. The user image can be widely applied to a plurality of specific applications such as online information pushing and accurate marketing. In particular, if it can be determined or predicted that a user visits a geographic information Point (POI), also called "information Point" or "Interest Point", such as a hotel, a school, a shopping mall, an office building, a subway station, an airport, etc., information push that accurately hits the actual needs Of the user can be completed.

However, in the prior art, the geographic information points visited by the user are generally predicted according to the current positioning coordinates and/or the current time of the user, and the historical visited geographic information points of the user are not considered, so that the prediction accuracy is not high.

Disclosure of Invention

The present application aims to provide an improved positioning method and apparatus to solve the technical problems mentioned in the background section above.

In a first aspect, the present application provides a positioning method, including: acquiring positioning information of a user, wherein the positioning information comprises positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time; acquiring at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point; for each geographic information point in the at least one geographic information point, determining a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time; and determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values.

In some embodiments, the determining, for each geographic information point of the at least one geographic information point, a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time includes: importing a historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model to obtain a visited category probability value of a geographic entity indicated by each geographic information point category of at least one geographic information point category visited by the user at the positioning time; for each geographic information point in the at least one geographic information point, determining a probability value of the positioning coordinate belonging to a geographic entity indicated by the geographic information point at the positioning time according to the positioning information; and for each geographic information point in the at least one geographic information point, determining the visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and the visiting category probability value of the geographic entity indicated by the geographic information point category of the user visiting the geographic information point at the positioning time.

In some embodiments, the determining, according to the location information, a probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time includes: determining a probability value that the positioning coordinate belongs to a geographic entity indicated by the geographic information point according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point; determining the probability value of the visited geographic entity indicated by the geographic information point at the positioning time according to the positioning time and the positioning time probability distribution of the geographic information point, wherein the positioning time probability distribution of the geographic information point is obtained by counting according to the historical positioning time of the historical visited user of the geographic information point; and determining the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the positioning time.

In some embodiments, the probability distribution of the location coordinates of the geographic information point is obtained by: acquiring historical positioning coordinates of historical visiting users of the geographic information points; clustering the acquired historical positioning coordinates to obtain at least one positioning coordinate clustering center of the geographic information point; and determining the probability value of each positioning coordinate cluster center of the geographic information point belonging to the geographic entity indicated by the geographic information point according to the distance between the geographic information point coordinate of the geographic information point and each positioning coordinate cluster center in at least one positioning coordinate cluster center of the geographic information point, and taking the determined probability value of each positioning coordinate cluster center belonging to the geographic entity indicated by the geographic information point as the positioning coordinate probability distribution of the geographic information point.

In some embodiments, the method further includes a step of training a geographic information point category prediction model, and the step of training the geographic information point category prediction model includes: obtaining at least one historical visited geographic information point category sequence of at least one user; and taking the at least one historical visited geographic information point category sequence as training data, and training a recurrent neural network as a geographic information point category prediction model.

In a second aspect, the present application provides a positioning device comprising: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is configured to acquire positioning information of a user, the positioning information comprises positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time; the second acquisition unit is configured to acquire at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point; a first determining unit, configured to determine, for each geographic information point of the at least one geographic information point, a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the location time based on the location information and a historical visiting geographic information point category sequence of the user before the location time; and the second determining unit is configured to determine the geographic information point corresponding to the geographic entity visited by the user at the positioning time according to each determined visiting probability value.

In some embodiments, the first determining unit includes: a first determining module, configured to import a historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model, to obtain a visited category probability value of a geographic entity indicated by each geographic information point category of at least one geographic information point category visited by the user at the positioning time; a second determining module, configured to determine, for each geographic information point of the at least one geographic information point, a probability value that the positioning coordinate belongs to a geographic entity indicated by the geographic information point at the positioning time according to the positioning information; and a third determining module, configured to determine, for each geographic information point of the at least one geographic information point, an visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time according to a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and a visiting category probability value of the user visiting the geographic entity indicated by the geographic information point category of the geographic information point at the positioning time.

In some embodiments, the second determining module comprises: the first determining submodule is configured to determine a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point; a second determining submodule configured to determine, according to the positioning time and positioning time probability distribution of the geographic information point, a probability value that a geographic entity indicated by the geographic information point is visited at the positioning time, where the positioning time probability distribution of the geographic information point is obtained by performing statistics on historical positioning time of a historical visited user of the geographic information point; and a third determining submodule configured to determine, according to the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the location time, the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time.

In some embodiments, the apparatus further comprises a geographic information point class prediction model training unit, the geographic information point class prediction model training unit configured to: obtaining at least one historical visited geographic information point category sequence of at least one user; and taking the at least one historical visited geographic information point category sequence as training data, and training a recurrent neural network as a geographic information point category prediction model.

In a third aspect, the present application provides a server, comprising: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation manner of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

According to the positioning method and the positioning device, the visiting probability value of the geographic entity indicated by each geographic information point in at least one geographic information point with the distance between the visiting geographic information point and the positioning coordinate of the user being smaller than the preset distance threshold value at the positioning time is determined according to the positioning coordinate and the positioning time of the user and the historical visiting geographic information point category sequence of the user before the positioning time, and the geographic information point corresponding to the geographic entity visited by the user at the positioning time is finally determined, so that the historical visiting geographic information point category sequence of the user is considered in the process of positioning the user, the accuracy of determining the geographic information point corresponding to the geographic entity visited by the user is improved, and the accuracy of portrait of the user can be improved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2a is a flow chart of one embodiment of a positioning method according to the present application;

fig. 2b is a schematic diagram of a probability distribution of positioning time of geographic information points in the positioning method according to the present application;

FIG. 3 is a flow chart of yet another embodiment of a positioning method according to the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a positioning device according to the present application;

FIG. 5 is a block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 shows an exemplary system architecture 100 to which embodiments of the positioning method or positioning apparatus of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various client applications, such as a map-like application, a location-like application, a web browser application, a shopping-like application, a search-like application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the

terminal devices

101, 102, 103.

The

terminal devices

101, 102, 103 may be various electronic devices that support positioning and/or WiFi functionality including, but not limited to, smart phones, tablets, laptop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for location services of the

terminal devices

101, 102, 103. The background server can analyze and process the received data such as the positioning information.

It should be noted that the positioning method provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the positioning apparatus is generally disposed in the server 105.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2a, a flow 200 of one embodiment of a positioning method according to the present application is shown. The positioning method comprises the following steps:

step 201, obtaining the positioning information of the user including the positioning time and the positioning coordinate and the historical visited geographic information point category sequence of the user before the positioning time.

In this embodiment, an electronic device (for example, a server shown in fig. 1) on which the positioning method operates may first acquire the positioning information of the user from the terminal of the user through a wired connection manner or a wireless connection manner. Here, the location information of the user may include location coordinates and a location time. Then, the electronic device may obtain a historical visited geographic information point category sequence of the user before the positioning time.

In this embodiment, the positioning information of the user may be current positioning information of the user, or historical positioning information of the user.

In this embodiment, the geographic information points are used to characterize the geographic entity. Wherein the geographic entity may be any particular entity on the surface of the earth. For example, the geographic entity may be a particular building, road, geographic area, river, ocean, mountain, and so forth. The geographic information point category is used for representing the category to which the geographic entity indicated by the geographic information point belongs. As an example, the geographic information point categories may include: a primary school campus, a secondary school campus, a college campus, a subway station, a bus station, an airport, a government office, a hotel, a mall, a movie theater, a library, a square, an office building, a park, an amusement park, a village, a gas station, a national road, a highway, an urban road, and the like. For example, the geographic information point category to which the geographic entity "hai lake park" and the geographic entity "purple bamboo yard park" belong is "park".

In the present embodiment, the location coordinates and the geographic information point coordinates of the user may be coordinates based on various coordinate systems. For example, the location coordinates and geographic information point coordinates of the user may be three-dimensional coordinates (e.g., longitude and latitude coordinates in a geodetic coordinate system) or two-dimensional coordinates (e.g., abscissa and ordinate in UTMGS (Universal Transverse mercator grid system)).

In this embodiment, the electronic device may acquire, as the positioning information of the user, the positioning information of the terminal of the user through various positioning manners, where the various positioning manners include, but are not limited to, the following positioning manners: positioning based on GPS (global positioning System), positioning based on a base station of a mobile operator, positioning based on AGPS (Assisted global positioning System), positioning based on WiFi, and other now known or later developed terminal positioning means.

In this embodiment, the above-mentioned historical visited geographic information point category sequence of the user may be a chronological geographic information point category.

In some optional implementations of this embodiment, the historical visited geographic information point category sequence of the user may be pre-stored in the electronic device locally or in another electronic device connected to the electronic device through a network, so that the electronic device may obtain, locally or remotely, the historical visited geographic information point category sequence of the user before the positioning time from another electronic device connected to the electronic device through the network.

In some optional implementation manners of this embodiment, the electronic device may obtain, as the historical visited geographical information point category sequence of the user before the positioning time, a first predetermined number (e.g., 10) of historical visited geographical information point category sequences that are closest to the positioning time of the user in the historical visited geographical information point category sequences of the user.

In some optional implementation manners of this embodiment, the electronic device may also obtain, as the historical visited geographical information point category sequence before the positioning time of the user, a historical visited geographical information point category sequence within a predetermined time period (for example, 1 day or 1 week) that is closest to the positioning time of the user in the historical visited geographical information point category sequence of the user.

Step 202, at least one geographic information point is obtained, wherein the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold.

In this embodiment, the geographic information points are used to characterize the geographic entity. In the physical world, a geographic entity is usually an area composed of a certain building and a material in the natural world, however, in practice, for convenience of representation, coordinates are often set for the geographic entity as geographic information point coordinates of a geographic information point corresponding to the geographic entity.

In order to determine the geographic information points corresponding to the geographic entities visited by the user at the positioning time, at least one geographic information point needs to be determined in each geographic information point to narrow the range. For this purpose, the electronic device may first acquire each geographic information point, and then select, from the acquired geographic information points, at least one geographic information point whose geographic information point coordinate is less than a preset distance threshold (e.g., 100 meters) from the positioning coordinate. Specifically, the geographical information point coordinates of each geographical information point may be obtained from a Location Based Service (LBS).

Step 203, for each geographic information point in at least one geographic information point, determining a visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time.

In this embodiment, based on the positioning information of the user obtained in step 201 and the category sequence of the geographic information points visited by the user in the history before the positioning time, the electronic device (for example, the server shown in fig. 1) may determine, for each geographic information point of the at least one geographic information point obtained in step 202, a visiting probability value that the user visits the geographic entity indicated by the geographic information point at the positioning time in various implementations.

In some optional implementations of this embodiment, step 203 may include the following sub-steps:

substep 2031, importing a historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model, and obtaining a visited category probability value of a geographic entity indicated by each geographic information point category of at least one geographic information point category visited by the user at the positioning time.

The at least one geographic information point category comprises each historical visited geographic information point category in the historical visited geographic information point category sequence of the user and the geographic information point category of each geographic information point in the at least one geographic information point. In practice, at least one geographic information point category may be obtained from a location-based service. Here, the geographic information point category prediction model is used to represent the correspondence between the historical visited geographic information point category sequence and the geographic information point category.

Optionally, the positioning method may further include the following step of training a geographic information point category prediction model: first, at least one historical visited geographic information point category sequence of at least one user is obtained. And then, taking the obtained at least one historical visited geographic information point category sequence as training data, and training a recurrent neural network as a geographic information point category prediction model.

Recurrent neural networks are a class of artificial neural networks that possess a specific memory pattern that can be used to identify patterns in sequence data such as text, genome, handwritten handwriting, speech, etc., and can also be used to identify numerical time series data generated by sensors, stock markets, government agencies. The input to the recurrent neural network includes not only the sample of the input currently seen, but also the information perceived by the network at the previous time. The decision of the recurrent neural network at the (n-1) th time step affects the decision at the subsequent (n) th time step, where n is a natural number. Therefore, the recurrent neural network continuously takes the output of the recurrent neural network as the feedback loop of the input, so that the recurrent neural network can complete the tasks which cannot be completed by the feedforward neural network by using the sequence information carried by the sequence, the sequence information is stored in the hidden state of the recurrent neural network and continuously transmitted to the front layer by layer, and the processing of each new sample is influenced by spanning a plurality of time steps. Therefore, the recurrent neural network is adopted to train the geographic information point category prediction model, and the category of the geographic information point which is possibly visited next by the user can be accurately predicted through the historical visited geographic information point category sequence of the user.

Sub-step 2032, for each geographic information point of the at least one geographic information point, taking the probability value of the visiting category of the geographic entity indicated by the geographic information point visited by the user at the positioning time as the probability value of the visiting category of the geographic entity indicated by the geographic information point visited by the user at the positioning time.

In some optional implementations of this embodiment, step 203 may also be performed as follows:

for each geographic information point in at least one geographic information point, determining a probability value that a positioning coordinate belongs to a geographic entity indicated by the geographic information point at positioning time according to positioning information of a user, and taking the probability value that the determined positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time as an visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time.

Optionally, wherein the determining of the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time may include the following substeps a to C:

and a substep A, determining a probability value of the positioning coordinate belonging to the geographic entity indicated by the geographic information point according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point.

Alternatively, the probability distribution of the location coordinates of the geographic information points may be obtained through sub-step a1 through sub-step A3 as follows:

and a sub-step A1 of obtaining the historical positioning coordinates of the historical visiting user of the geographic information point.

By way of example, data of historical user connection to WiFi may be obtained, and if the WiFi is determined to belong to a certain geographic information point, it may be determined that the historical user is a historical visited user of the geographic information point, and then obtaining the historical location coordinates of the historical user may obtain the historical location coordinates of the historical visited user of the geographic information point.

As an example, the navigation may also be started by acquiring the geographic information point searched by the history user using the electronic map navigation class application, and using the geographic information point as the destination, acquiring the positioning coordinates of the terminal used by the history user when the navigation is ended, and using the acquired positioning coordinates as the historical positioning coordinates of the history visited user of the geographic information point if the distance between the acquired positioning coordinates and the coordinates of the geographic information point is not greater than a preset positioning distance threshold (e.g., 50 meters).

As an example, the location coordinates of the terminal used by the historical user may also be obtained by obtaining the historical user when using the consumption ticket related to the geographic information point (e.g., a group purchase ticket for the geographic information point), and if the distance between the obtained location coordinates and the geographic information point coordinates of the geographic information point is not greater than a preset location distance threshold (e.g., 50 meters), the obtained location coordinates may be used as the historical location coordinates of the historical visiting user of the geographic information point.

Sub-step a2, clustering the acquired historical positioning coordinates to obtain at least one positioning coordinate cluster center of the geographic information point.

The clustering algorithm may include, but is not limited to: K-Means Clustering algorithm, Gaussian Mixture Model (Gaussian Mixture Model) Clustering algorithm, Hierarchical Clustering (Hierarchical Clustering) algorithm, Self-Organizing mapping (SOM) Clustering algorithm, and FCM (Fuzzy C-Means) Clustering algorithm. It should be understood that the above-mentioned clustering algorithm itself is well known to those skilled in the art, and will not be described herein.

And a substep a3, determining a probability value of each location coordinate cluster center of the geographic information point belonging to the geographic entity indicated by the geographic information point according to the distance between the geographic information point coordinate of the geographic information point and each location coordinate cluster center of at least one location coordinate cluster center of the geographic information point, and taking the determined probability value of each location coordinate cluster center belonging to the geographic entity indicated by the geographic information point as the location coordinate probability distribution of the geographic information point.

As an example, a specific implementation manner of determining a probability value that each location coordinate cluster center of the geographic information point belongs to the geographic entity indicated by the geographic information point according to a distance between the geographic information point coordinate of the geographic information point and each location coordinate cluster center of at least one location coordinate cluster center of the geographic information point is given below:

wherein, the geographic information point poi has K positioning coordinate clustering centers mu_iK is a positive integer greater than 1, i is a positive integer between 1 and KLocating the coordinate clustering center mu_iMay be a two-dimensional coordinate (x)_i,y_i) Or may be three-dimensional coordinates (x)_i,y_i,z_i)，P(μ_i| poi) is the calculated location coordinate clustering center μ of the geographic information point poi₀Probability value, D, pertaining to a geographic entity indicated by a geographic information point poi₁Is a constant greater than 0,/_1iIs a location coordinate cluster center mu_iA distance from the geographic information point coordinates of the geographic information point poi, and the location coordinates of the geographic information point may be two-dimensional coordinates (x ×)_poi,y_poi) Or may be three-dimensional coordinates (x)_poi,y_poi,z_poi). As can be seen from the above formula, the cluster center μ of the location coordinates at the geographic information point poi_iDistance l from the geographical information point coordinates of the geographical information point poi_1iLess than or equal to D₁In the case of (D), P (. mu.),_iall | poi) equal 1. In l_1iGreater than D₁In the case of (D), P (. mu.),_ii poi) is less than 1, and P (. mu.))_iI poi) with l_1iA negative correlation.

A specific implementation of determining a probability value that a location coordinate belongs to a geographic entity indicated by the geographic information point according to the location coordinate and the location coordinate probability distribution of the geographic information point is given below:

where U is the location coordinate of the user, U may be a two-dimensional coordinate (x)_u,y_u) Or may be three-dimensional coordinates (x)_u,y_u,z_u) Poi is a geographical information point, P (U | poi) is a probability value that the calculated location coordinate U belongs to the geographical entity indicated by the geographical information point poi, P (μ |)_i| poi) is the location coordinate cluster center μ of the geographic information point poi calculated as described above_iProbability value, P (U | μ) belonging to the geographic entity indicated by the geographic information point poi_i) The positioning coordinate U belongs to the positioning coordinate clustering center mu of the geographic information point poi_iProbability value of P (U | μ)_i) And the positioning seatPositioning coordinate clustering center mu of target U and geographic information point poi_iThe distance between them is inversely related, as an example, P (U | μ)_i) Can be calculated by the following formula:

wherein D is₂Is a constant greater than 0,/_2iIs a geographic information point coordinate clustering center mu of a positioning coordinate U and a geographic information point poi_iThe distance between them.

And a substep B, determining a probability value of the geographic entity indicated by the geographic information point visited at the positioning time according to the positioning time and the positioning time probability distribution of the geographic information point.

Here, the probability distribution of the positioning time of the geographic information point may be obtained by counting according to the historical positioning time of the historical visiting user of the geographic information point.

As an example, one implementation of determining a probability value that a geographic entity indicated by a geographic information point poi is visited at a location time t according to the location time t and a location time probability distribution of the geographic information point poi is given below:

p (t | poi) ═ P (hour | poi) P (week | poi) (equation 4)

Where t denotes a positioning time, poi denotes a geographical information point, P (hour | poi) denotes a positioning time probability distribution of the geographical information point poi in units of one hour and in a cycle of 24 hours, that is, P (hour | poi) denotes a probability value that the geographical information point poi is visited within a time period of one hour represented by hour, and P (week | poi) denotes a positioning time probability distribution of the geographical information point poi in units of 24 hours and in a cycle of one week, that is, P (week | poi) denotes a probability value that the geographical information point poi is visited within a time period of 24 hours of the day represented by week. P (t | poi) is a probability value that the calculated geographic information point poi is visited at the positioning time t.

As an example, P (hour | poi) can be obtained by: and dividing the ratio of the times of searching the geographic information points poi by the preset user (for example, all registered users or the registered user searching the geographic information points poi) in the time period represented by the hour within a preset historical time period (for example, the last month) by the total times of searching the geographic information points poi by the preset user within the preset historical time period, and taking the ratio as the probability value of the visited geographic information points poi within the time period represented by the hour within one hour. The distribution of the geographical information points poi over 24 hours P (hour | poi) is shown in fig. 2 b. It can be seen that the geographic information point is searched more times during the daytime period, and thus the corresponding P (hour | poi) is also higher, and the geographic information point is searched less times during the night period, and thus the corresponding P (hour | poi) is also lower. It is understood that P (week | poi) can be obtained in a similar manner.

And a substep C, determining the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the positioning time.

As an example, a specific implementation is given below:

p (U, t | poi) ═ P (t | poi) P (U | poi) (equation 5)

Where U is the location coordinate of the user, U may be a two-dimensional coordinate (x)_u,y_u) Or may be three-dimensional coordinates (x)_u,y_u,z_u) And t is a positioning time, P (U | poi) is a probability value that the positioning coordinate U calculated in the substep a belongs to the geographic entity indicated by the geographic information point poi, P (t | poi) is a probability value that the geographic entity indicated by the geographic information point poi calculated in the substep B is visited at the positioning time t, and P (U, t | poi) is a probability value that the positioning coordinate U calculated belongs to the geographic entity indicated by the geographic information point poi at the positioning time t.

Through substeps a to C, the electronic device may determine a probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time, and then, the electronic device may use the determined probability value as a visiting probability value that the user visits the geographic entity indicated by the geographic information point at the location time.

And step 204, determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values.

In this embodiment, based on the respective visiting probability values determined in step 203, the electronic device may determine, from at least one geographic information point, a geographic information point corresponding to a geographic entity visited by the user at the positioning time.

In some optional implementation manners of this embodiment, the electronic device may select, from the at least one geographic information point, a geographic information point with the maximum determined visiting probability value as a geographic information point corresponding to a geographic entity visited by the user at the positioning time.

In some optional implementation manners of this embodiment, the electronic device may also select, from the at least one geographic information point, a second predetermined number (e.g., 3) of geographic information points as geographic information points corresponding to geographic entities visited by the user at the positioning time in an order from a large value to a small value of the determined visiting probability value.

According to the method provided by the embodiment of the application, the visiting probability value of the geographic entity indicated by each geographic information point in at least one geographic information point with the distance between the visiting geographic information point and the positioning coordinate of the user being smaller than the preset distance threshold value at the positioning time is determined according to the positioning coordinate and the positioning time of the user and the historical visiting geographic information point category sequence of the user before the positioning time, and the geographic information point corresponding to the geographic entity visited by the user at the positioning time is finally determined, so that the positioning coordinate, the positioning time and the historical visiting geographic information point category of the user before the positioning time are considered, the accuracy of determining the geographic information point corresponding to the geographic entity visited by the user is improved, and the accuracy of portrait of the user can be improved.

Further referring to fig. 3, a flow 300 of yet another embodiment of a positioning method according to the present application is shown. The process 300 of the positioning method includes the following steps:

step 301, obtaining the positioning information of the user including the positioning time and the positioning coordinates and the historical visited geographic information point category sequence of the user before the positioning time.

Step 302, at least one geographic information point is obtained, wherein the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold.

In this embodiment, the specific operations of step 301 and step 302 are substantially the same as the operations of step 201 and step 202 in the embodiment shown in fig. 2a, and are not described again here.

Step 303, importing the historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model to obtain a visited category probability value of the geographic entity indicated by each geographic information point category of at least one geographic information point category visited by the user at the positioning time.

The at least one geographic information point category comprises each historical visited geographic information point category in the historical visited geographic information point category sequence of the user and the geographic information point category of each geographic information point in the at least one geographic information point. In practice, at least one geographic information point category may be obtained from a location-based service. Here, the geographic information point category prediction model is used to represent the correspondence between the geographic information point category sequence and the geographic information point category.

And step 304, determining a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the positioning information for each geographic information point in the at least one geographic information point.

Optionally, wherein the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time is determined, the following may be performed:

firstly, according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point, determining the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point. Specifically, reference may be made to the related description of sub-step a in the embodiment shown in fig. 2a, and details are not repeated here.

Secondly, according to the positioning time and the positioning time probability distribution of the geographic information point, determining the probability value of the visited geographic entity at the positioning time indicated by the geographic information point. Specifically, reference may be made to the related description of sub-step B in the embodiment shown in fig. 2a, and details are not repeated here.

And finally, determining the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the positioning time. Reference may be made to the related description of sub-step C in the embodiment shown in fig. 2a, and details are not repeated here.

Step 305, for each geographic information point in at least one geographic information point, determining a probability value of visiting the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and the probability value of visiting category of the geographic entity indicated by the category of the geographic information point visited by the user at the positioning time.

A specific implementation is given below:

P(U,t,S_cat|poi)＝P(S_cat|poi_cat) P (U, t | poi) (equation 6)

Where U is a positioning coordinate, U may be a two-dimensional coordinate (x)_u,y_u) Or may be three-dimensional coordinates (x)_u,y_u,z_u) T is the positioning time, S_catIs a historical geographic information point category sequence, P (S), of the user before the location time t_cat|poi_cat) Is to obtain the historical visited geographic information point category sequence S in step 303_catGeographic information point category prediction model with pre-training importGeographical information point type poi obtained by type of visiting geographical information point poi at positioning time t_catP (U, t | poi) is a probability value that the location coordinate U calculated in step 304 belongs to the geographic entity indicated by the geographic information point poi at the location time t. P (U, t, S)_cat| poi) is the calculated probability value of the user visiting the geographic entity indicated by the geographic information point poi at the location time t.

And step 306, determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values.

In this embodiment, the specific operation of step 306 is substantially the same as the operation of step 204 in the embodiment shown in fig. 2a, and is not repeated herein.

As can be seen from fig. 3, compared with the embodiment corresponding to fig. 2a, the process 300 of the positioning method in this embodiment highlights a step of fusing a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and a visiting category probability value of the geographic entity indicated by the category of the geographic information point visited by the user at the positioning time.

With further reference to fig. 4, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of a positioning apparatus, which corresponds to the embodiment of the method shown in fig. 2a, and which is particularly applicable to various electronic devices.

As shown in fig. 4, the positioning apparatus 400 of the present embodiment includes: a first acquisition unit 401, a second acquisition unit 402, a first determination unit 403, and a second determination unit 404. The first obtaining unit 401 is configured to obtain location information of a user, where the location information includes location time and location coordinates, and a historical visited geographic information point category sequence of the user before the location time; a second obtaining unit 402, configured to obtain at least one geographic information point whose distance between the geographic information point coordinate and the positioning coordinate is smaller than a preset distance threshold, where the geographic information point includes a geographic information point coordinate and a geographic information point category; a first determining unit 403, configured to determine, for each geographic information point of the at least one geographic information point, a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the location time based on the location information and a historical visiting geographic information point category sequence of the user before the location time; a second determining unit 404, configured to determine, according to the determined visiting probability values, geographic information points corresponding to geographic entities visited by the user at the positioning time.

In this embodiment, the specific processing of the first obtaining unit 401, the second obtaining unit 402, the first determining unit 403, and the second determining unit 404 of the positioning apparatus 400 and the technical effects thereof can refer to the related descriptions of step 201, step 202, step 203, and step 204 in the corresponding embodiment of fig. 2a, and are not repeated herein.

In some optional implementations of this embodiment, the first determining unit 403 may include: a first determining module 4031, configured to import the historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model, and obtain a visited category probability value of a geographic entity indicated by each of at least one geographic information point category visited by the user at the positioning time, where the at least one geographic information point category includes each historical visited geographic information point category in the historical visited geographic information point category sequence of the user before the positioning time and a geographic information point category of each geographic information point in the at least one geographic information point; a second determining module 4032, configured to determine, for each geographic information point in the at least one geographic information point, a probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time according to the location information; a third determining module 4033, configured to determine, for each geographic information point of the at least one geographic information point, a probability value that the user visits the geographic entity indicated by the geographic information point at the location time according to the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time and the probability value of the category of the geographic information point that the user visits the geographic information point at the location time. For specific processing of the first determination module 4031, the second determination module 4032 and the third determination module 4033 and technical effects thereof, reference may be made to the related descriptions of step 303, step 304 and step 305 in the corresponding embodiment of fig. 3, which are not described herein again.

In some optional implementations of this embodiment, the second determining module 4032 may include: a first determining submodule (not shown) configured to determine, according to the location coordinate and the location coordinate probability distribution of the geographic information point, a probability value that the location coordinate belongs to a geographic entity indicated by the geographic information point; a second determining submodule (not shown) configured to determine, according to the positioning time and a positioning time probability distribution of the geographic information point, a probability value that the geographic entity indicated by the geographic information point is visited at the positioning time, where the positioning time probability distribution of the geographic information point is obtained by statistics according to historical positioning time of a historical visited user of the geographic information point; and a third determining submodule (not shown) configured to determine, according to the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the location time, the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time. For specific processing of the first determining submodule, the second determining submodule and the third determining submodule and technical effects brought by the specific processing, reference may be made to the relevant descriptions of sub-step a, sub-step B and sub-step C in the corresponding embodiment of fig. 2a, and details are not repeated here.

In some optional implementations of the present embodiment, the probability distribution of the location coordinates of the geographic information point may be obtained by: acquiring historical positioning coordinates of historical visiting users of the geographic information points; clustering the acquired historical positioning coordinates to obtain at least one positioning coordinate clustering center of the geographic information point; and determining the probability value of each positioning coordinate cluster center of the geographic information point belonging to the geographic entity indicated by the geographic information point according to the distance between the geographic information point coordinate of the geographic information point and each positioning coordinate cluster center in at least one positioning coordinate cluster center of the geographic information point, and taking the determined probability value of each positioning coordinate cluster center belonging to the geographic entity indicated by the geographic information point as the positioning coordinate probability distribution of the geographic information point. Reference may be made to the related descriptions of sub-step a1, sub-step a2 and sub-step A3 in the corresponding embodiment of fig. 2a, which are not repeated herein.

In some optional implementations of this embodiment, the positioning apparatus 400 may further include a geographic information point class prediction model training unit (not shown), where the geographic information point class prediction model training unit is configured to: obtaining at least one historical visited geographic information point category sequence of at least one user; and taking the at least one historical visited geographic information point category sequence as training data, and training a recurrent neural network as a geographic information point category prediction model. For the specific processing of the geographic information point type prediction model training unit and the technical effects thereof, reference may be made to the related description of sub-step 2031 in the embodiment corresponding to fig. 2a, which is not repeated herein.

Referring now to FIG. 5, a block diagram of a computer system 500 suitable for use in implementing a server according to embodiments of the present application is shown. The server shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 506 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM502, and RAM 503 are connected to each other via a bus 504. An Input/Output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: a storage section 506 including a hard disk and the like; and a communication section 507 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 507 performs communication processing via a network such as the internet. The driver 508 is also connected to the I/O interface 505 as necessary. A removable medium 509 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 508 as necessary, so that a computer program read out therefrom is mounted into the storage section 506 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 507 and/or installed from the removable medium 509. The computer program performs the above-described functions defined in the method of the present application when executed by the Central Processing Unit (CPU) 501. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first acquisition unit, a second acquisition unit, a first determination unit, and a second determination unit. Where the names of the units do not in some cases constitute a limitation of the unit itself, the second acquisition unit may also be described as a "unit acquiring at least one geographical information point", for example.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: acquiring positioning information of a user, wherein the positioning information comprises positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time; acquiring at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point; for each geographic information point in the at least one geographic information point, determining a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time; and determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. A method of positioning, the method comprising:

acquiring positioning information of a user, wherein the positioning information comprises positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time;

acquiring at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point;

for each geographic information point in the at least one geographic information point, determining a visiting probability value of the user visiting a geographic entity indicated by the geographic information point at the positioning time based on the positioning information and the historical visiting geographic information point category sequence of the user before the positioning time, including: importing the historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model to obtain a visited category probability value of a geographic entity indicated by each geographic information point category in at least one geographic information point category visited by the user at the positioning time; for each geographic information point in the at least one geographic information point, determining a probability value that the positioning coordinate belongs to a geographic entity indicated by the geographic information point at the positioning time according to the positioning information, the positioning coordinate probability distribution of the geographic information point and the positioning time probability distribution; for each geographic information point in the at least one geographic information point, determining a visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time according to a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and a visiting category probability value of the user visiting the geographic entity indicated by the geographic information point category of the geographic information point at the positioning time;

and determining the geographic information points corresponding to the geographic entities visited by the user at the positioning time according to the determined visiting probability values.

2. The method of claim 1, wherein determining the probability value that the location coordinate belongs to the geographic entity indicated by the geographic information point at the location time according to the location information and the location coordinate probability distribution and the location time probability distribution of the geographic information point comprises:

determining a probability value that the positioning coordinate belongs to a geographic entity indicated by the geographic information point according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point;

determining the probability value of the visited geographic entity indicated by the geographic information point at the positioning time according to the positioning time and the positioning time probability distribution of the geographic information point, wherein the positioning time probability distribution of the geographic information point is obtained by counting according to the historical positioning time of the historical visited user of the geographic information point;

and determining the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the positioning time.

3. The method according to claim 2, wherein the probability distribution of the location coordinates of the geographic information points is obtained by:

acquiring historical positioning coordinates of historical visiting users of the geographic information points;

clustering the acquired historical positioning coordinates to obtain at least one positioning coordinate clustering center of the geographic information point;

and determining the probability value of each positioning coordinate cluster center of the geographic information point belonging to the geographic entity indicated by the geographic information point according to the distance between the geographic information point coordinate of the geographic information point and each positioning coordinate cluster center in at least one positioning coordinate cluster center of the geographic information point, and taking the determined probability value of each positioning coordinate cluster center belonging to the geographic entity indicated by the geographic information point as the positioning coordinate probability distribution of the geographic information point.

4. A method according to any of claims 1-3, characterized in that the method further comprises the step of training a geographical information point class prediction model, said step of training a geographical information point class prediction model comprising:

obtaining at least one historical visited geographic information point category sequence of at least one user;

and taking the at least one historical visited geographic information point category sequence as training data, and training a recurrent neural network as a geographic information point category prediction model.

5. A positioning device, the device comprising:

the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring positioning information of a user, including positioning time and positioning coordinates, and a historical visited geographic information point category sequence of the user before the positioning time;

the second acquisition unit is configured to acquire at least one geographic information point of which the distance between the coordinate of the geographic information point and the positioning coordinate is smaller than a preset distance threshold, wherein the geographic information point comprises the coordinate of the geographic information point and the category of the geographic information point;

a first determining unit, configured to determine, for each geographic information point of the at least one geographic information point, a visiting probability value that the user visits a geographic entity indicated by the geographic information point at the location time based on the location information and a historical visiting geographic information point category sequence of the user before the location time;

a second determining unit, configured to determine, according to the determined visiting probability values, geographic information points corresponding to geographic entities visited by the user at the positioning time;

the first determination unit includes: the first determining module is configured to import a historical visited geographic information point category sequence of the user before the positioning time into a pre-trained geographic information point category prediction model to obtain a visited category probability value of a geographic entity indicated by each geographic information point category of at least one geographic information point category visited by the user at the positioning time; a second determining module, configured to determine, for each geographic information point of the at least one geographic information point, a probability value that the location coordinate belongs to a geographic entity indicated by the geographic information point at the location time according to the location information, a location coordinate probability distribution of the geographic information point, and a location time probability distribution; and a third determining module, configured to determine, for each geographic information point of the at least one geographic information point, an visiting probability value of the user visiting the geographic entity indicated by the geographic information point at the positioning time according to a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time and a visiting category probability value of the user visiting the geographic entity indicated by a category of the geographic information point visiting the geographic information point at the positioning time.

6. The apparatus of claim 5, wherein the second determining module comprises:

the first determining submodule is configured to determine a probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point according to the positioning coordinate and the positioning coordinate probability distribution of the geographic information point;

a second determining submodule configured to determine, according to the positioning time and positioning time probability distribution of the geographic information point, a probability value that a geographic entity indicated by the geographic information point is visited at the positioning time, where the positioning time probability distribution of the geographic information point is obtained by performing statistics on historical positioning time of a historical visited user of the geographic information point;

and the third determining submodule is configured to determine the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point at the positioning time according to the probability value that the positioning coordinate belongs to the geographic entity indicated by the geographic information point and the probability value that the geographic entity indicated by the geographic information point is visited at the positioning time.

7. The apparatus of claim 6, wherein the probability distribution of the location coordinates of the geographic information point is obtained by:

8. The apparatus according to any of claims 5-7, wherein the apparatus further comprises a geographic information point class prediction model training unit configured to:

9. A server, comprising:

one or more processors;

a storage device for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-4.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-4.