CN105893537B - Method and device for determining geographic information point - Google Patents

Abstract

The present application discloses a method and device for determining geographic information points. A specific implementation of the method includes: obtaining the user's location information, wherein the location information includes the user's location coordinates; using the user's location coordinates as the input value of a pre-trained Bayesian prediction model, and obtaining the probability value of the user being at each geographic information point in at least one geographic information point based on the Bayesian prediction model, wherein the Bayesian prediction model is trained using the basic information of the geographic information point as sample data, wherein the basic information includes the location coordinates of the geographic information point and the historical location information of historically visited users; and determining the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located. This implementation achieves the determination of the geographic information point where the user is located.

Description

Method and device for determining geographic information point

technical field

The present application relates to the field of computer technology, in particular to the field of Internet technology, and in particular to a method and apparatus for determining geographic information points.

Background technique

Geographic Information Points (POI, Point Of Interest), also known as "points of information" or "points of interest", refer to places with a certain meaning, such as restaurants, schools, and parking lots. The positioning in the prior art, especially the user positioning, is aimed at researching the absolute position of the user.

However, the prior art lacks mining and calculation of the data of the geographic information point where the user is located, and cannot determine the geographic information point where the user is located.

SUMMARY OF THE INVENTION

The purpose of this application is to propose an improved method and device for determining geographic information points to solve the technical problems mentioned in the above background technology section.

In a first aspect, the present application provides a method for determining geographic information points, the method includes: acquiring user positioning information, wherein the positioning information includes user positioning coordinates; using the user positioning coordinates as a pre-trained shell The input value of the Yesian prediction model, and the probability value of the user being located at each geographical information point in the at least one geographical information point is obtained according to the Bayesian prediction model, wherein the Bayesian prediction model uses the geographical information point The basic information is obtained by training as sample data, wherein the basic information includes the positioning coordinates of the geographic information point and the historical positioning information of the historical visiting users; the geographic information point corresponding to the maximum probability value is determined as the geographic information point where the user is located. Information point.

In some embodiments, the Bayesian prediction model parameters include a historical visiting probability of each geographic information point in the at least one geographic information point, wherein the historical visiting probability is based on the positioning coordinates of the geographic information point and the Obtaining historical positioning information, wherein: obtaining the historical visiting probability according to the positioning coordinates of the geographic information point and the historical positioning information includes: selecting at least one geographic information point according to a preset rule, and establishing a set of geographic information points; according to the geographic information The positioning coordinates of each geographic information point in the point set and the positioning information of each historical visiting user in the geographic information point set obtain each historical visit times in the geographic information point set; calculate the number of times in the geographic information point set The sum of the number of historical visits of each geographic information in the The number of historical visits to obtain the historical visit probability of each geographic information point in the set of geographic information points.

In some embodiments, the obtaining the number of historical visits to the geographic information point according to the positioning coordinates of the geographic information point and the user positioning information of historical visitors to the geographic information point includes: selecting a geographic information point within a preset range the historical user; obtain the historical positioning information and historical search records of the historical user corresponding to the historical positioning coordinates, wherein the historical positioning information includes the historical positioning coordinates and the historical positioning time when collecting the historical positioning coordinates; if the historical search The record includes the identification information of the geographic information point; then calculate the time interval between the historical positioning time and the time point when the geographic information point is searched; in response to the time interval being less than a predetermined threshold, determine the historical user For the historical visiting users of the geographic information point.

In some embodiments, the historical positioning information of the historical visiting user includes historical positioning coordinates and a historical positioning time when the historically visiting user is located at the historical positioning coordinates; and, the Bayesian prediction model parameters include : the time probability distribution of the geographic information point, wherein the time probability distribution is obtained according to the historical positioning time of the historical visiting users of the geographic information point.

In some embodiments, the user's positioning information further includes a user positioning time when the user is located at the user positioning coordinates; and the user positioning coordinates are used as an input to a pre-trained Bayesian prediction model and obtaining the probability value of the user at each geographic information point in at least one geographic information point according to the Bayesian prediction model, including: taking the user positioning time and the user positioning coordinates as pre-trained Bayesian The input value of the Yesian prediction model, and the probability value of the user being located at each geographical information point in the at least one geographical information point is obtained according to the Bayesian prediction model.

In some embodiments, the Bayesian prediction model parameters include a location probability of a geographic information point, wherein the location probability is obtained according to a distance between the geographic information point and a cluster center, wherein the cluster The center is obtained by clustering at least one geographic information point.

In some embodiments, the cluster center is obtained by clustering at least one geographic information point, including: obtaining the cluster center of at least one geographic information point through K-means algorithm clustering, wherein: selecting at least one geographic information point, And establish a cluster geographic information point set; determine the number of clusters according to the total number of visits of the cluster geographic information point set; select the number of positioning coordinates of the cluster number as the initial cluster center; The coordinates corresponding to the initial cluster centers and the location coordinates of the geographic information points in the clustered geographic information point set are set as input values of the K-means algorithm to obtain the number of cluster centers.

In some embodiments, the user's positioning information further includes the user's positioning time when the user is located at the user's positioning coordinates; and the acquiring the user's positioning information includes: filtering out the user's positioning time at a preset time The user positioning coordinates in the segment are obtained, and an original user positioning coordinate set is established; the abnormal points in the original user positioning coordinate set are eliminated to obtain a user positioning coordinate set, wherein the abnormal point refers to the second preset time period. A coordinate point whose moving distance is greater than a preset distance threshold; at least one user positioning coordinate in the user positioning coordinate set is aggregated into a track center coordinate through a track clustering algorithm; at least one user positioning coordinate set in the user positioning coordinate set is aggregated. The average time point of the corresponding time points of the positioning time is used as the track center time; Obtaining the probability value of the user at each geographic information point in the at least one geographic information point by the Yesian prediction model includes: taking the coordinate of the trajectory center as the input value of the pre-trained Bayesian forecasting model, and according to the Bayesian prediction model The Yesian prediction model obtains a probability value that the user is located at each geographic information point in at least one geographic information point.

In some embodiments, after determining the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located, the method further includes: adding a geographic information point corresponding to the maximum probability value to the user's positioning information The historical visiting user marking of geographic information points; adding the positioning information of the user with the historical visiting user marking to the sample data set of the Bayesian prediction model; using the sample data in the sample data set Train to generate a new Bayesian predictive model.

In a second aspect, the present application provides a device for determining a geographic information point, the device includes: an acquisition module configured to acquire user positioning information, wherein the positioning information includes user positioning coordinates; a calculation module configured for is based on using the user positioning coordinates as the input value of the pre-trained Bayesian prediction model, and obtaining the probability value of the user at each geographic information point in the at least one geographic information point according to the Bayesian prediction model, wherein , the Bayesian prediction model is obtained by training the basic information of the geographic information points as sample data, wherein the basic information includes the positioning coordinates of the geographic information points and the historical positioning information of the historical visiting users; the determination module is configured to The geographic information point corresponding to the maximum probability value is determined as the geographic information point where the user is located.

In some embodiments, the Bayesian prediction model parameters include a historical visiting probability of each geographic information point in the at least one geographic information point, wherein the historical visiting probability is based on the positioning coordinates of the geographic information point and the Obtaining historical positioning information, wherein: obtaining the historical visiting probability according to the positioning coordinates of the geographic information point and the historical positioning information includes: selecting at least one geographic information point according to a preset rule, and establishing a set of geographic information points; according to the geographic information The positioning coordinates of each geographic information point in the point set and the positioning information of each historical visiting user in the geographic information point set obtain each historical visit times in the geographic information point set; calculate the number of times in the geographic information point set The sum of the number of historical visits of each geographic information in the The number of historical visits to obtain the historical visit probability of each geographic information point in the set of geographic information points.

In some embodiments, the obtaining the number of historical visits to the geographic information point according to the positioning coordinates of the geographic information point and the user positioning information of historical visitors to the geographic information point includes: selecting a geographic information point within a preset range the historical user; obtain the historical positioning information and historical search records of the historical user corresponding to the historical positioning coordinates, wherein the historical positioning information includes the historical positioning coordinates and the historical positioning time when collecting the historical positioning coordinates; if the historical search The record includes the identification information of the geographic information point; then calculate the time interval between the historical positioning time and the time point when the geographic information point is searched; in response to the time interval being less than a predetermined threshold, determine the historical user For the historical visiting users of the geographic information point.

In some embodiments, the historical positioning information of the historical visiting user includes historical positioning coordinates and a historical positioning time when the historically visiting user is located at the historical positioning coordinates; and, the Bayesian prediction model parameters include : the time probability distribution of the geographic information point, wherein the time probability distribution is obtained according to the historical positioning time of the historical visiting users of the geographic information point.

In some embodiments, the user's positioning information further includes a user positioning time when the user is located at the user positioning coordinates; and the computing module is further configured to: combine the user positioning time with the user positioning time. The positioning coordinates are used as input values of a pre-trained Bayesian prediction model, and a probability value of the user being at each geographic information point in at least one geographic information point is obtained according to the Bayesian prediction model.

In some embodiments, the Bayesian prediction model parameters include a location probability of a geographic information point, wherein the location probability is obtained according to a distance between the geographic information point and a cluster center, wherein the cluster The center is obtained by clustering at least one geographic information point.

In some embodiments, the cluster center is obtained by clustering at least one geographic information point, including: obtaining the cluster center of at least one geographic information point through K-means algorithm clustering, wherein: selecting at least one geographic information point, And establish a cluster geographic information point set; determine the number of clusters according to the total number of visits of the cluster geographic information point set; select the number of positioning coordinates of the cluster number as the initial cluster center; The coordinates corresponding to the initial cluster centers and the location coordinates of the geographic information points in the clustered geographic information point set are set as input values of the K-means algorithm to obtain the number of cluster centers.

In some embodiments, the user's positioning information further includes the user positioning time when the user is located at the user positioning coordinates; and the acquiring module is further configured to: filter out the user positioning time within a preset time period The user positioning coordinates in the original user positioning coordinate set are established, and the original user positioning coordinate set is established; the abnormal point in the original user positioning coordinate set is eliminated to obtain the user positioning coordinate set, wherein the abnormal point refers to the movement within the second preset time period. A coordinate point whose distance is greater than a preset distance threshold; at least one user positioning coordinate in the user positioning coordinate set is aggregated into a track center coordinate through a trajectory clustering algorithm; at least one user positioning coordinate in the user positioning coordinate set is positioned The average time point of the corresponding time points of the time is used as the track center time; Obtaining the probability value of the user at each geographic information point in the at least one geographic information point by using the Bayesian prediction model, including: using the coordinates of the trajectory center as the input value of the pre-trained Bayesian prediction model, The SS prediction model obtains a probability value that the user is at each geographic information point in at least one geographic information point.

In some embodiments, the apparatus further includes an update module configured to: add a historical visiting user mark of the geographic information point corresponding to the maximum probability value to the positioning information of the user; The marked location information of the user is added to the sample data set of the Bayesian prediction model; and a new Bayesian prediction model is generated by training with the sample data in the sample data set.

The method and device for determining a geographic information point provided by the present application obtain the user's positioning information, wherein the positioning information includes the user's positioning coordinates; the user's positioning coordinates are used as the input value of the pre-trained Bayesian prediction model, and obtain the probability value of each geographic information point in at least one geographic information point of the user according to the Bayesian prediction model, wherein the Bayesian prediction model uses the basic information of the geographic information point as sample data to train to obtain , wherein the basic information includes the positioning coordinates of the geographic information point and the historical positioning information of the historical visiting users; the geographic information point corresponding to the maximum probability value is determined as the geographic information point where the user is located, which realizes the determination of the user's location. geographic information point.

Description of drawings

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

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

2 is a flow chart of an embodiment of a method for determining a geographic information point according to the present application;

3 is a flow chart of another embodiment of a method for determining a geographic information point according to the present application;

Fig. 4 is the time probability distribution of the geographic information point according to the determination method of the geographic information point of the present application;

5 is a schematic structural diagram of an embodiment of an apparatus for determining geographic information points according to the present application;

FIG. 6 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present application.

Detailed ways

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

FIG. 1 shows an exemplary system architecture 100 to which an embodiment of a method for determining a geographic information point or an apparatus for determining a geographic information point of the present application may be applied.

As shown in FIG. 1 , the system architecture 100 may include terminal devices 101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. Various communication client applications may be installed on the terminal devices 101 , 102 and 103 , such as map applications, shopping applications, search applications, instant communication tools, email clients, social platform software, and the like.

The terminal devices 101, 102, and 103 may be various electronic devices that have a display screen and support web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, moving image Expert Compression Standard Audio Layer 3), MP4 (Moving PictureExperts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) Players, Laptops and Desktops, etc.

The server 105 may be a server that provides various services, for example, a location service server that supports the location services of the terminal devices 101 , 102 and 103 . The location service server may analyze and process the received location data and other data.

It should be noted that the method for determining the geographic information point provided by the embodiment of the present application is generally performed by the server 105 , and accordingly, the device for determining the geographic information point is generally set in the server 105 .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

Continuing to refer to FIG. 2 , a flow 200 of an embodiment of a method for determining a geographic information point according to the present application is shown. The above-mentioned method for determining geographic information points includes the following steps:

Step 201: Acquire the positioning information of the user.

In this embodiment, the electronic device (for example, the server shown in FIG. 1 ) on which the method for determining the geographic information point runs may acquire the user's positioning information based on the mobile terminal used by the user. It should be pointed out that the above-mentioned acquisition of the user's positioning information based on the mobile terminal used by the user can be implemented in various ways. Here, the implementation methods include but are not limited to GPS (Global Positioning System)-based positioning, The positioning of the base station of the mobile operating network, the positioning based on AGPS (Assisted GPS, Assisted Global Positioning System), the positioning based on WiFi and other mobile terminal positioning methods known now or developed in the future.

In this embodiment, the above-mentioned user positioning information includes user positioning coordinates. Here, the user positioning coordinates may be longitude and latitude coordinates.

Step 202 , taking the user positioning coordinates as the input value of the pre-trained Bayesian prediction model, and obtaining the probability value of the user at each geographic information point in the at least one geographic information point according to the Bayesian prediction model.

In this embodiment, based on the user positioning coordinates of the user obtained in step 201, the above-mentioned electronic device (such as the server shown in FIG. 1 ) may first use the above-mentioned positioning coordinates as the input values of the pre-trained Bayesian prediction model; The Bayesian prediction model obtains the probability that the user is at a certain geographic information point; the Bayesian prediction model is used one or more times to obtain the probability that the user is at each geographic information point in at least one geographic information point. The user positioning coordinates are used as the input value of the Bayesian prediction model to obtain the probability that the user is in place A as a, and then the Bayesian prediction model is used to predict the above-mentioned user and the probability that the user is in place B is b.

In this embodiment, the Bayesian prediction model is obtained by training the basic information of the geographic information points as sample data, wherein the basic information includes the positioning coordinates of the geographic information points and historical positioning information of historical visiting users. Here, the above-mentioned Bayesian prediction model is a prediction model established based on the Bayesian formula. As an example, the Bayesian formula applied in this embodiment can be expressed by the following formula:

P(U|poi)=A*B

Among them, poi represents a certain geographic information point, U represents the user's positioning information, P(U|poi) represents the probability that the user is at a certain geographic information point, A and B are the parameters of the Bayesian prediction model, and * represents the parameter Bayesian There is an operation relationship between the Yesian prediction model A and the Bayesian prediction model parameter B, and the above operation relationship includes but is not limited to a product relationship and an addition relationship.

In some optional implementations of this embodiment, the above-mentioned Bayesian prediction model parameters include a historical visit probability of each geographic information point in the at least one geographic information point, wherein the above-mentioned historical visit probability is based on the The positioning coordinates and the above-mentioned historical positioning information are obtained, wherein, the positioning coordinates according to the geographical information and the historical visiting probability of the above-mentioned historical positioning information can be obtained through the following steps: select at least one geographical information point according to a preset rule, and establish a set of geographical information points Obtain each historical visit times in the above-mentioned geographic information point set according to the positioning coordinates of each geographic information point in the above-mentioned geographic information point set and each historical visiting user positioning information in the above-mentioned geographic information point set; Calculate the above-mentioned geographic information point The sum of the number of historical visits of each geographic information in the set, and the above sum is taken as the total number of historical visits of the set of geographic information points; according to the total number of historical visits and the history of the geographic information points in the above set of geographic information points The number of visits to obtain the historical visiting probability of each geographic information point in the above-mentioned geographic information point set.

As an example, select three geographic information points that are close to each other to establish a geographic information point set, and the three geographic information points are named as geographic information point a, geographic information point b, and geographic information point c. These three geographic information points visit The total number of visits in a day is 100, of which the number of visits to geographic information point a is 20, the number of visits to geographic information point b is 30 times in traffic jams, and the number of visits to geographic information point c is 50 times. Then the historical visiting probability of geographic information point a is 20/100, which is 20%, then the historical visiting probability of geographic information point a is 30/100, which is 30%. Then the historical visiting probability of geographic information point a is 30/100. The probability of visiting is 50/100 for fifty percent.

Optionally, obtaining the number of historical visits of the above-mentioned geographic information point according to the positioning coordinates of the geographic information point and the historical visiting user positioning information of the above-mentioned geographic information point can be obtained by the following steps: selecting the historical data within the preset range of the geographic information point user; obtain the historical positioning information and historical search records of the historical users corresponding to the above-mentioned historical positioning coordinates, wherein the historical positioning information includes historical positioning coordinates and the historical positioning time when the above-mentioned historical positioning coordinates are collected; if the above-mentioned historical search records include the above-mentioned geographic The identification information of the information point; then calculate the time interval between the above-mentioned historical positioning time and the time point of searching for the geographical information point; in response to the above-mentioned time interval being less than a predetermined threshold, the above-mentioned historical user is determined as the historical visit of the above-mentioned geographical information point user.

As an example, select the historical users from 10:00 am to 11:00 am within the radius of 100 meters of the geographic information point armor. For example, the user Zhang Yi is located in this range at 10:30 am, and then obtain the search records of Zhang Yi, if the search records , if the search record includes the identification information of the geographic information point A, such as the name of the geographic information point A, a name similar to the name of the geographic information point A, and then obtain the time point when the identification information of the geographic information point A is searched, such as It is 10:15, and the time interval between the search time 10:15 and the historical positioning time 10:30 is less than the predetermined threshold, then the above historical user is determined as the historical visiting user of the above geographic information point. It is understandable that the above The predetermined threshold can be half an hour, one day, or one month.

Optionally, according to the positioning coordinates of the geographic information point and the historical visiting user positioning information of the geographic information point, the number of historical visits to the geographic information point can be obtained in the following manner: obtaining the data of the historical user connection WiFi, if this The WiFi has been determined to belong to a certain geographic information point, then it can be determined that the historical user is a historical visiting user of the geographic information point.

Optionally, at least one geographic information point is selected according to a preset rule, and a set of geographic information points is established, wherein the preset rule for selecting at least one geographic information may be to select several geographic information points within a predetermined range centered on the user. It can also be established in advance to divide the geographic information points of a certain area into several sets of geographic information points according to the density of geographic information points. For example, a university campus is centered on the main teaching building, gymnasium, and library. Three sets of geographic information points are established, among which, the set of geographic information points centered on the gymnasium may include equipment rooms and playgrounds.

In some optional implementation manners of this embodiment, the Bayesian prediction model parameter includes a location probability of a geographic information point, wherein the location probability is obtained according to the distance between the geographic information point and the cluster center, wherein the above The cluster center is obtained by clustering at least one geographic information point. For example, the inverse ratio of the distance between the geographic information point and the cluster center is used as the positioning probability of the geographic information point. Of course, the inverse ratio of the distance between the geographic information point and the cluster center can also be multiplied by a coefficient as the positioning probability of the geographic information point.

Optionally, the above-mentioned cluster center can be used as a bridge between the above-mentioned users and the geographic information points, and the user-cluster center probability is calculated first, for example, the inverse ratio of the distance between the above-mentioned users and the cluster center can be used as the user-cluster center probability. , and then take the product of the user-cluster center probability and the above positioning probability as the probability of the user at the geographic information point. As an example, user A is near cluster center A and cluster center B, the distance between user A and cluster center A is 10 meters, and the distance between user A and cluster center A is 20 meters; The cluster geographic information point set of A includes geographic information point c and geographic information point d, wherein the distance between geographic information point c and cluster center A is 1 meter, and the distance between geographic information point c and cluster center A is 1 meter. The distance is 2 meters; there is a geographic information point e in the clustering geographic information point set of the cluster center B, and the distance between the geographic information point e and the cluster center B is 4 meters; then, if the geographic center and the The inverse ratio of the distance between the class centers is used as the positioning probability, then the positioning probability of geographic information point a is 1/1, then the positioning probability of geographic information point b is 1/2, then the positioning probability of geographic information point c is 1/4, The user-cluster center probability between the user and the cluster center A is 1/10, and the user-cluster center probability between the user and the cluster center B is 1/20; The probability of a is (1/1)*(1/10), the probability of the above-mentioned user at the geographic information point b is (1/2)*(1/10), and the probability of the above-mentioned user at the geographic information point c is (1 /4)*(1/20). Here, "/" represents a division sign, "*" represents an operation, and preferably, "*" represents a multiplication sign.

Optionally, the cluster center obtained by clustering at least one geographic information point can be randomly divided into regions, and a clustering algorithm can be used for clustering, wherein the clustering algorithm includes but is not limited to: k-means clustering algorithm, hierarchical clustering algorithm, SOM clustering algorithm, FCM clustering algorithm. It should be understood that the calculation process of the above-mentioned clustering algorithm itself is well known to those skilled in the art, and will not be repeated here.

Optionally, the cluster center of at least one geographic information point can be obtained by clustering the K-means algorithm. Optionally, the specific process is as follows: select at least one geographic information point, and establish a clustering geographic information point set; The number of clusters is determined by the total number of visits of the quasi-geographic information point set; the positioning coordinates of the above-mentioned number of clusters are selected as the initial cluster center; The positioning coordinates of the geographic information points in the middle are set as the input values of the K-means algorithm, and the number of cluster centers above is obtained. It should be understood that the K-means algorithm is a clustering algorithm known to those skilled in the art, and details are not described here.

Optionally, the number of clusters can be determined according to the number of geographic information points in the clustered geographic information set, or the number of geographic information points can be determined according to whether the distribution of geographic information points in the clustered geographic information point set has an obvious phenomenon of dense partitions. number.

Optionally, the above-mentioned number of locating coordinates of the number of clusters may be randomly selected as the initial cluster centers, or the locating coordinates of geographic information points whose historical visiting probability is greater than a predetermined threshold may be used as the initial cluster centers.

Step 203: Determine the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located.

In this embodiment, based on the probability value of the user at each geographic information point in at least one geographic information point obtained in step 202, the largest probability value is selected as the maximum probability value from the above probability values, and the geographic information corresponding to the maximum probability value is The information point is determined as the geographic information point where the user is located.

The method provided by the above embodiments of the present application realizes the determination of the geographic information point where the user is located by using the historical visiting probability and positioning probability of the geographic information point.

With further reference to FIG. 3, a flow 300 of a further embodiment of a method for determining a geographic information point is shown. The process 300 of the method for determining the geographic information point includes the following steps:

Step 301: Obtain user positioning coordinates and user positioning time of the user.

In this embodiment, the electronic device (for example, the server shown in FIG. 1 ) on which the method for determining the geographic information point runs may acquire the user's positioning information based on the mobile terminal used by the user.

In this embodiment, the positioning information of the user includes the user positioning coordinates and the user positioning time when the user is located at the user positioning coordinates. The user's positioning information can be obtained through the following steps: filtering out the user positioning coordinates whose user positioning time is within a preset time period, and establishing an original user positioning coordinate set; excluding abnormal points in the above-mentioned original user positioning coordinate set, obtaining the user positioning coordinates set, wherein, the above-mentioned abnormal point refers to a coordinate point whose distance moved within the second preset time period is greater than the preset distance threshold; at least one user positioning coordinate in the above-mentioned user positioning coordinate set is aggregated into one through the trajectory clustering algorithm Track center coordinates; take the average time point of the corresponding time points of at least one user positioning time in the above-mentioned user positioning coordinate set as the track center time; take the above-mentioned track center coordinates and the above-mentioned track center time as the pre-trained Bayesian prediction model The input value of , and the probability value of the user being located at each geographic information point in the at least one geographic information point is obtained according to the above-mentioned Bayesian prediction model.

Step 302 , taking the user positioning coordinates and the user positioning time as input values of the pre-trained Bayesian prediction model, and obtaining the probability value of the user at each geographic information point in the at least one geographic information point according to the Bayesian prediction model.

In this embodiment, based on the user positioning coordinates of the user obtained in step 301, the above-mentioned electronic device (such as the server shown in FIG. 1 ) may first use the above-mentioned positioning coordinates as the input values of the pre-trained Bayesian prediction model; The Bayesian prediction model obtains the probability that the user is at a certain geographic information point; the Bayesian prediction model is used one or more times to obtain the probability that the user is at at least one geographic information point.

In this embodiment, the Bayesian prediction model is obtained by training the basic information of the geographic information points as sample data, wherein the basic information includes the positioning coordinates of the geographic information points and historical positioning information of historical visiting users. Here, the above-mentioned Bayesian prediction model is a prediction model established based on the Bayesian formula. As an example, the Bayesian formula applied in this embodiment can be expressed by the following formula:

P(U|poi)=A*B

Among them, poi represents a certain geographic information point, U represents the user's positioning information, P(U|poi) represents the probability that the user is at a certain geographic information point, A and B are the parameters of the Bayesian prediction model, and * represents the parameter Bayesian There is an operation relationship between the Yesian prediction model A and the Bayesian prediction model parameter B, and the above operation relationship includes but is not limited to a product relationship and an addition relationship.

In this embodiment, the parameters of the Bayesian prediction model include a historical visit probability of each geographic information point in the at least one geographic information point, wherein the historical visit probability is based on the positioning coordinates of the geographic information point and the historical positioning information. get.

In this embodiment, the parameters of the Bayesian prediction model include the positioning probability of the geographic information point, wherein the positioning probability is obtained according to the distance between the geographic information point and the cluster center, wherein the cluster center is composed of at least one Geographic information point clustering is obtained.

In this embodiment, the above-mentioned Bayesian prediction model parameters include the time probability distribution of geographic information points, wherein the above-mentioned time probability distribution is obtained according to the historical positioning time of the historical visiting users of the geographic information points, wherein the above-mentioned historical positioning time is The time point when the historical visiting user is at the historical positioning coordinates, the historical positioning coordinates and the historical positioning time belong to the historical positioning information of the historical visiting user, and the above historical positioning coordinates and historical positioning time are obtained by collecting the historical positioning information of the historical user. As an example, reference may be made to FIG. 4, which shows the time probability distribution of geographic information points over a week. Geographic information point A has a total of 100 historical visiting users in seven days a week, 10 historical visiting users every day from Monday to Friday, 20 historical visiting users on Saturday, and 30 historical visiting users on Sunday. Here, it is assumed that each historical visiting user visits the geographic information point A once. A time probability distribution with a period of weeks can be established.

Optionally, the period of the time probability distribution can be twenty-four hours of a day, seven days of a week, days of a month, twelve months of a year, or four quarters of a year . Of course, a combination of the above periodic forms is also possible. As an example, a combination of twenty-four hours a day and seven days a week can be established. The probability of a user visiting Geographic Information Point A at 19:00 on Friday can be calculated by combining the time probability of Friday at Geographic Information Point A with 19 The probability of the time corresponding to the point at the geographic information point A in one day is used as a parameter value to calculate the probability of the user visiting the geographic information point A at 19:00 on Friday.

In some optional implementations of this embodiment, the positioning information of the user further includes the user positioning time when the user is located at the user positioning coordinates, and the user positioning time and the user positioning coordinates may be used as the pre-trained Bayesian The input value of the prediction model is obtained, and the probability value of the user at each geographic information point in the at least one geographic information point is obtained according to the above-mentioned Bayesian prediction model.

Step 303: Determine the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located.

In this embodiment, based on the probability value that the user is in each geographic information point of at least one geographic information point obtained in step 302, the largest probability value is selected as the maximum probability value from the above probability values, and the geographic information corresponding to the maximum probability value is The information point is determined as the geographic information point where the user is located.

Step 304, generating a new Bayesian prediction model based on the user's positioning information.

In this embodiment, based on step 303, add the historically visited user mark of the geographic information point corresponding to the above-mentioned maximum probability value to the above-mentioned user's positioning information, and add the above-mentioned user's positioning information with the above-mentioned historically visited user mark to the above-mentioned In the sample data set of the Bayesian prediction model, a new Bayesian prediction model is generated by using the sample data in the above-mentioned sample data set to train.

As can be seen from FIG. 3 , compared with the embodiment corresponding to FIG. 2 , the flow 300 of the method for determining a geographic information point in this embodiment highlights the step of introducing the user's user positioning time, and utilizes the Time probability distribution, so as to more accurately determine the geographic information point where the user is located.

Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present application provides an embodiment of an apparatus for determining a geographic information point. The apparatus embodiment corresponds to the method embodiment shown in FIG. 2 . The device can be specifically applied to various electronic devices.

As shown in FIG. 5 , the apparatus 500 for determining a geographic information point in this embodiment includes: an acquisition module 501 , a calculation module 502 , and a determination module 503 . The obtaining module is configured to obtain the user's positioning information, wherein the positioning information includes the user positioning coordinates; the computing module is configured to use the user positioning coordinates as the input value of the pre-trained Bayesian prediction model, and according to The above-mentioned Bayesian prediction model obtains the probability value of the user at each geographic information point in at least one geographic information point, wherein the above-mentioned Bayesian prediction model is obtained by using the basic information of the geographic information point as sample data training, wherein the above-mentioned basic information is obtained. The information includes the positioning coordinates of the geographic information point and historical positioning information of the historical visiting users; the determining module is configured to determine the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located.

In this embodiment, the obtaining module 501 of the apparatus 500 for determining a geographic information point may obtain the user's positioning information based on the mobile terminal used by the user. It should be noted that the above-mentioned acquisition of the user's positioning information based on the mobile terminal used by the user may be implemented in various ways.

In this embodiment, based on the user's positioning information obtained by the obtaining module 501, the above-mentioned calculating module 502 can obtain the user's user positioning coordinates in the obtaining module 501, and the above-mentioned electronic device (such as the server shown in FIG. 1) can firstly locate the above-mentioned positioning The coordinates are used as the input value of the pre-trained Bayesian prediction model; then the Bayesian prediction model is used to obtain the probability that the user is at a certain geographic information point; the Bayesian prediction model is used one or more times to obtain the user at least one geographic information point. The probability of each geographic information point in .

In this embodiment, based on the probability value that the user is in each geographic information point in at least one geographic information point obtained by the calculation module 502, the determination module 503 selects the maximum probability value from the above probability values as the maximum probability value, and takes the maximum probability value as the maximum probability value. The geographic information point corresponding to the probability value is determined as the geographic information point where the user is located.

In some optional implementation manners of this embodiment, the apparatus 500 for determining a geographic information point further includes an update module 504 configured to add a historically visited user mark of the geographic information point corresponding to the above-mentioned maximum probability value to the above-mentioned user's positioning information , adding the positioning information of the above-mentioned users marked with historical visiting users to the sample data set of the above-mentioned Bayesian prediction model, and using the sample data in the above-mentioned sample data set to train to generate a new Bayesian prediction model.

Those skilled in the art can understand that the above-mentioned apparatus 500 for determining a geographic information point also includes some other well-known structures, such as a processor, a memory, etc., in order to unnecessarily obscure the embodiments of the present disclosure, these well-known structures are not shown in FIG. 5 . out.

Referring to FIG. 6 below, it shows a schematic structural diagram of a computer system 600 suitable for implementing the server of the embodiment of the present application.

As shown in FIG. 6, a computer system 600 includes a central processing unit (CPU) 601, which can be loaded into a random access memory (RAM) 603 according to a program stored in a read only memory (ROM) 602 or a program from a storage section 608 Instead, various appropriate actions and processes are performed. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601 , the ROM 602 , and the RAM 603 are connected to each other through a bus 604 . An input/output (I/O) interface 605 is also connected to bus 604 .

The following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc. ; and a communication section 609 including a network interface card such as a LAN card, a modem, and the like. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I/O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

In particular, according to embodiments 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 tangibly embodied on a machine-readable medium, the computer program containing program code for performing the methods illustrated in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 609 and/or installed from the removable medium 611 .

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 that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks 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 is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The modules involved in the embodiments of the present application may be implemented in a software manner, and may also be implemented in a hardware manner. The described modules can also be provided in the processor, for example, it can be described as: a processor includes an acquisition module, a calculation module, and a determination module. Wherein, the names of these modules do not constitute a limitation of the module itself under certain circumstances. For example, the acquisition module may also be described as "a module for acquiring user's positioning information".

As another aspect, the present application also provides a non-volatile computer storage medium, and the non-volatile computer storage medium may be the non-volatile computer storage medium included in the above-mentioned apparatus in the above-mentioned embodiment; or It is a non-volatile computer storage medium that exists alone and is not assembled into the terminal. The above-mentioned non-volatile computer storage medium stores one or more programs, and when the above-mentioned one or more programs are executed by a device, the above-mentioned device: obtains the user's positioning information, wherein the above-mentioned positioning information includes user positioning coordinates; The above-mentioned user positioning coordinates are used as the input value of the pre-trained Bayesian prediction model, and the probability value of the above-mentioned user at each geographic information point in at least one geographic information point is obtained according to the above-mentioned Bayesian prediction model, wherein the above-mentioned Bayesian The prediction model is obtained by training the basic information of the geographic information points as sample data, wherein the above-mentioned basic information includes the positioning coordinates of the geographic information points and the historical positioning information of historical visiting users; the geographic information point corresponding to the maximum probability value is determined as the above-mentioned user. The geographic information point at which it is located.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above technical features, and should also cover the above technical features or Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above-mentioned features with the technical features disclosed in this application (but not limited to) with similar functions.

Claims (16)

1. A method for determining a geographic information point, wherein the method comprises: Obtaining the user's positioning information, wherein the positioning information includes user positioning coordinates; The user positioning coordinates are used as the input value of the pre-trained Bayesian prediction model, and the probability value of the user at each geographic information point in the at least one geographic information point is obtained according to the Bayesian prediction model, wherein, The Bayesian prediction model is obtained by using the basic information of the geographic information points as sample data, wherein the basic information includes the positioning coordinates of the geographic information points and the historical positioning information of historical visiting users; The geographic information point corresponding to the maximum probability value is determined as the geographic information point where the user is located; wherein Historical visiting users are determined in the following ways: Select historical users within the preset range of geographic information points; Obtain the historical positioning information and historical search records of the historical users corresponding to the historical positioning coordinates, wherein the historical positioning information includes the historical positioning coordinates and the historical positioning time when the historical positioning coordinates are collected; If the historical search record includes the identification information of the geographic information point; then calculate the time interval between the historical positioning time and the time point of searching for the geographic information point; In response to the time interval being less than a predetermined threshold, the historical user is determined as a historical visiting user of the geographic information point. 2. The method according to claim 1, wherein the Bayesian prediction model parameter comprises a historical visiting probability of each geographic information point in the at least one geographic information point, wherein the historical visiting probability is based on The positioning coordinates of the geographic information point and the historical positioning information are obtained, wherein: Obtaining the historical visit probability according to the positioning coordinates of the geographic information point and the historical positioning information includes: Select at least one geographic information point according to a preset rule, and establish a set of geographic information points; According to the positioning coordinates of each geographic information point in the geographic information point set and the positioning information of each historical visiting user in the geographic information point set, obtain each historical visit times in the geographic information point set; Calculate the total number of historical visits of each geographic information in the set of geographic information points, and use the sum as the total number of historical visits of the set of geographic information points; The historical visiting probability of each geographic information point in the geographic information point set is obtained according to the total number of historical visits and the historical visiting times of the geographic information points in the geographic information point set. 3. The method according to claim 1, wherein the historical positioning information of the historical visiting user comprises historical positioning coordinates and the historical positioning time when the historical visiting user is located at the historical positioning coordinates; and, The Bayesian prediction model parameters include: The time probability distribution of the geographic information point, wherein the time probability distribution is obtained according to the historical positioning time of the historical visiting users of the geographic information point. 4. The method according to claim 3, wherein the positioning information of the user further comprises a user positioning time when the user is located at the user positioning coordinates; and, The user positioning coordinates are used as the input value of the pre-trained Bayesian prediction model, and the probability value that the user is at each geographic information point in the at least one geographic information point is obtained according to the Bayesian prediction model, include: Taking the user positioning time and the user positioning coordinates as input values of a pre-trained Bayesian prediction model, and obtaining each geographic information point where the user is located in at least one geographic information point according to the Bayesian prediction model probability value. 5. The method according to claim 1, wherein the Bayesian prediction model parameter comprises a location probability of a geographic information point, wherein the location probability is based on the difference between the geographic information point and the cluster center. distance is obtained, wherein the cluster center is obtained by clustering at least one geographic information point. 6. The method according to claim 5, wherein the cluster center is obtained by clustering at least one geographic information point, comprising: The cluster center of at least one geographic information point is obtained by K-means algorithm clustering, where: Select at least one geographic information point, and establish a clustered geographic information point set; Determine the number of clusters according to the total number of visits of the clustered geographic information point set; Select the number of positioning coordinates of the cluster as the initial cluster center; The number of clusters, the coordinates corresponding to the initial cluster centers and the location coordinates of the geographic information points in the cluster geographic information point set are set as the input values of the K-means algorithm, and the number of cluster centers is obtained. . 7. The method according to any one of claims 1-6, wherein the user's positioning information further comprises a user positioning time when the user is located at the user positioning coordinates; and, The obtaining of the user's positioning information includes: Filter out the user positioning coordinates whose user positioning time is within the preset time period, and establish the original user positioning coordinate set; Eliminating abnormal points in the original user positioning coordinate set to obtain a user positioning coordinate set, wherein the abnormal point refers to a coordinate point whose moving distance in the second preset time period is greater than a preset distance threshold; Aggregating at least one user positioning coordinate in the set of user positioning coordinates into one track center coordinate through a trajectory clustering algorithm; Taking the average time point of the corresponding time points of at least one user positioning time in the user positioning coordinate set as the track center time; and, The track center coordinates and the track center time are used as input values of the pre-trained Bayesian prediction model, and according to the Bayesian prediction model, it is obtained that the user is located in each geographic location of at least one geographic information point. The probability value of the information point, including: The coordinates of the track center are used as input values of a pre-trained Bayesian prediction model, and a probability value of the user being at each geographic information point in the at least one geographic information point is obtained according to the Bayesian prediction model. 8. The method according to claim 7, wherein after determining the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located, the method further comprises: adding the historical visiting user mark of the geographic information point corresponding to the maximum probability value to the positioning information of the user; adding the positioning information of the user marked with the historical visiting user to the sample data set of the Bayesian prediction model; Using the sample data in the sample data set to train and generate a new Bayesian prediction model. 9. A device for determining geographic information points, wherein the device comprises: an acquisition module, configured to acquire user positioning information, wherein the positioning information includes user positioning coordinates; A computing module, configured to use the user positioning coordinates as an input value of a pre-trained Bayesian prediction model, and obtain, according to the Bayesian prediction model, that the user is at each geographic information point in at least one geographic information point The probability value of , wherein the Bayesian prediction model uses the basic information of geographic information points as sample data to train and obtain, wherein, the basic information includes the positioning coordinates of geographic information points, historical positioning information of historical visiting users; a determining module, configured to determine the geographic information point corresponding to the maximum probability value as the geographic information point where the user is located; wherein Historical visiting users are determined in the following ways: Select historical users within the preset range of geographic information points; Obtain the historical positioning information and historical search records of the historical users corresponding to the historical positioning coordinates, wherein the historical positioning information includes the historical positioning coordinates and the historical positioning time when the historical positioning coordinates were collected; If the historical search record includes the identification information of the geographic information point; then calculate the time interval between the historical positioning time and the time point of searching for the geographic information point; In response to the time interval being less than a predetermined threshold, the historical user is determined as a historical visiting user of the geographic information point. 10. The apparatus according to claim 9, wherein the Bayesian prediction model parameter comprises a historical visiting probability of each geographic information point in the at least one geographic information point, wherein the historical visiting probability is based on The positioning coordinates of the geographic information point and the historical positioning information are obtained, wherein: Obtaining the historical visit probability according to the positioning coordinates of the geographic information point and the historical positioning information includes: Select at least one geographic information point according to a preset rule, and establish a set of geographic information points; According to the positioning coordinates of each geographic information point in the geographic information point set and the positioning information of each historical visiting user in the geographic information point set, obtain each historical visit times in the geographic information point set; Calculate the total number of historical visits of each geographic information in the set of geographic information points, and use the sum as the total number of historical visits of the set of geographic information points; The historical visiting probability of each geographic information point in the geographic information point set is obtained according to the total number of historical visits and the historical visiting times of the geographic information points in the geographic information point set. 11. The device according to claim 9, wherein the historical positioning information of the historical visiting user comprises historical positioning coordinates and a historical positioning time when the historical visiting user is located at the historical positioning coordinates; and, The Bayesian prediction model parameters include: The time probability distribution of the geographic information point, wherein the time probability distribution is obtained according to the historical positioning time of the historical visiting users of the geographic information point. 12. The apparatus according to claim 11, wherein the user's positioning information further comprises a user positioning time when the user is located at the user positioning coordinates; and, The computing module is further used for: Taking the user positioning time and the user positioning coordinates as input values of a pre-trained Bayesian prediction model, and obtaining each geographic information point where the user is located in at least one geographic information point according to the Bayesian prediction model probability value. 13 . The apparatus according to claim 9 , wherein the Bayesian prediction model parameter comprises a location probability of a geographic information point, wherein the location probability is based on the difference between the geographic information point and the cluster center. 14 . distance is obtained, wherein the cluster center is obtained by clustering at least one geographic information point. 14. The apparatus according to claim 13, wherein the cluster center is obtained by clustering at least one geographic information point, comprising: The cluster center of at least one geographic information point is obtained by K-means algorithm clustering, where: Select at least one geographic information point, and establish a clustered geographic information point set; Determine the number of clusters according to the total number of visits of the clustered geographic information point set; Select the number of positioning coordinates of the cluster as the initial cluster center; The number of clusters, the coordinates corresponding to the initial cluster centers and the location coordinates of the geographic information points in the cluster geographic information point set are set as the input values of the K-means algorithm, and the number of cluster centers is obtained. . 15. The device according to any one of claims 9-14, wherein the user's positioning information further comprises a user positioning time when the user is located at the user positioning coordinates; and, The obtaining module is further used for: Filter out the user positioning coordinates whose user positioning time is within the preset time period, and establish the original user positioning coordinate set; Eliminating abnormal points in the original user positioning coordinate set to obtain a user positioning coordinate set, wherein the abnormal point refers to a coordinate point whose moving distance in the second preset time period is greater than a preset distance threshold; Aggregating at least one user positioning coordinate in the set of user positioning coordinates into one track center coordinate through a trajectory clustering algorithm; Taking the average time point of the corresponding time points of at least one user positioning time in the user positioning coordinate set as the track center time; and, The track center coordinates and the track center time are used as input values of the pre-trained Bayesian prediction model, and according to the Bayesian prediction model, it is obtained that the user is located in each geographic location of at least one geographic information point. The probability value of the information point, including: The coordinates of the track center are used as input values of a pre-trained Bayesian prediction model, and a probability value of the user being at each geographic information point in the at least one geographic information point is obtained according to the Bayesian prediction model. 16. The apparatus of claim 15, wherein the apparatus further comprises an update module configured to: adding the historical visiting user mark of the geographic information point corresponding to the maximum probability value to the positioning information of the user; adding the positioning information of the user marked with the historical visiting user to the sample data set of the Bayesian prediction model; Using the sample data in the sample data set to train and generate a new Bayesian prediction model.