CN107085600B

CN107085600B - POI recommendation method, device, equipment and computer readable storage medium

Info

Publication number: CN107085600B
Application number: CN201710210187.1A
Authority: CN
Inventors: 刘巍
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2017-03-31
Filing date: 2017-03-31
Publication date: 2021-05-14
Anticipated expiration: 2037-03-31
Also published as: CN107085600A

Abstract

The invention provides a POI recommendation method, a POI recommendation device, POI recommendation equipment and a computer readable storage medium. According to the method and the device for recommending the POI, the request POI cluster on the electronic map is obtained according to the obtained tile data of the electronic map requested by the user, the display level of the request POI cluster is adjusted according to the user personalized data of the user, so that the POI in the request POI cluster is displayed on the electronic map according to the display level of the request POI cluster, the personalized electronic map can be provided for each user based on the user personalized data, the personalized requirements of the user can be met, therefore, the POI possibly interested by the user or the POI needing to be known can be accurately recommended to the user based on the user personalized data, and the POI recommending success rate is improved.

Description

POI recommendation method, device, equipment and computer readable storage medium

[ technical field ] A method for producing a semiconductor device

The present invention relates to recommendation technologies, and in particular, to a POI recommendation method, apparatus, device, and computer-readable storage medium.

[ background of the invention ]

With the development of communication technology, terminals integrate more and more functions, so that more and more corresponding Applications (APPs) are included in a system function list of the terminal. Some applications may involve some electronic map services, some Point of Interest (POI) information may be displayed on an electronic map, and the POI information is an information element in geographic information, and is information of buildings such as shops, public service sites, and bus stations based on the geographic information or service sites capable of providing services.

However, because each user has personalized characteristics, providing the same electronic map to all users is unlikely to meet personalized requirements of each user, and therefore, how to provide a personalized electronic map to accurately recommend POIs that the user may be interested in or POIs that need to be understood to the user so as to improve the success rate of POI recommendation is a technical problem that needs to be solved.

[ summary of the invention ]

Aspects of the present invention provide a method, an apparatus, a device and a computer-readable storage medium for POI recommendation, so as to improve the success rate of POI recommendation.

In one aspect of the present invention, a POI recommendation method is provided, including:

obtaining tile data of an electronic map requested by a user;

acquiring a request POI cluster on the electronic map according to the tile data;

and adjusting the display level of the request POI cluster according to the user personalized data of the user, so that the POI in the request POI cluster can be displayed on the electronic map according to the display level of the request POI cluster.

The foregoing aspect and any possible implementation manner further provide an implementation manner, where the adjusting, according to the user personalization data of the user, the display level of the requested POI cluster so as to display, according to the display level of the requested POI cluster, POIs in the requested POI cluster on the electronic map further includes:

acquiring the access amount of the user to a target POI which is interested by the user;

obtaining the statistical access quantity of the user to a target POI cluster to which the POI belongs according to the access quantity of the user to the target POI;

obtaining the data of the interest degree of the user to the target POI cluster according to the transmission access amount of the user to the target POI cluster, wherein the data is used as the user personalized data of the user; or

According to the statistical visit quantity of the user to the target POI cluster, obtaining the transfer visit quantity of the user to an associated POI cluster, wherein the associated POI cluster and the target POI cluster have an association relation; and obtaining the data of the interest degree of the user to the associated POI cluster according to the transmission access amount of the user to the associated POI cluster, wherein the data is used as the user personalized data of the user.

The above aspect and any possible implementation further provide an implementation, where the association includes at least one of the following associations:

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

The above-described aspects and any possible implementation further provide an implementation, where the association is a homogeneous association; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

obtaining a homogeneous correlation attenuation coefficient;

and obtaining the transfer visit quantity of the user to the associated POI cluster according to the statistical visit quantity of the user to the target POI cluster and the homogeneous association attenuation coefficient.

The above-described aspects and any possible implementation further provide an implementation, where the association is a heterogeneous association; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

obtaining a heterogeneous correlation attenuation coefficient;

and obtaining the transfer visit quantity of the user to the associated POI cluster according to the statistical visit quantity of the user to the target POI cluster and the heterogeneous association attenuation coefficient.

The above-described aspects and any possible implementation further provide an implementation, where the association is a global homogeneous association; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

acquiring the statistical access amount of the user to other POI clusters, wherein the other POI clusters and the target POI clusters and the associated POI clusters have a global homogeneous association relationship;

and obtaining the transmission access amount of the user to the associated POI cluster according to the statistical access amount of the user to the target POI cluster and the statistical access amount of the user to the other POI clusters.

The above-described aspect and any possible implementation manner further provide an implementation manner, where the obtaining of a target POI interested by a user includes:

obtaining the target POI according to the attribute data of the user; or

Obtaining the target POI according to the latest query operation of the user; or

Obtaining the target POI according to the current query operation of the user; or

And obtaining the target POI according to the current position of the user.

The above aspect and any possible implementation manner further provide an implementation manner, before obtaining, according to the amount of access to the target POI by the user, a statistical amount of access to a target POI cluster to which the POI belongs by the user, the method further includes:

acquiring user behavior data of users in the whole network;

acquiring an association relation between every two POIs according to the user behavior data;

and carrying out POI clustering processing by adopting a community discovery algorithm according to the association relationship between every two POIs and the association parameters of the association relationship between every two POIs so as to obtain at least one POI cluster with a tree structure relationship, so as to obtain a target POI cluster to which the target POI belongs according to the target POI, and obtain the POI cluster with a homogeneous association relationship with the target POI cluster according to the target POI cluster.

The above-mentioned aspect and any possible implementation manner further provide an implementation manner, where the association parameter of the association relationship between two POIs includes:

the support degree of the incidence relation between every two POIs; or

And the support degree of the association between every two POIs and the cosine similarity of the association between every two POIs.

The foregoing aspect and any possible implementation manner further provide an implementation manner, where performing POI clustering processing according to the association relationship between each two POIs and the association parameters of the association relationship between each two POIs by using a community discovery algorithm to obtain at least one POI cluster having a tree structure relationship includes:

filtering the association relationship between every two POIs according to the association parameters of the association relationship between every two POIs;

and carrying out POI clustering processing by adopting a community discovery algorithm according to the incidence relation between every two POIs after the filtering processing so as to obtain at least one POI cluster with a tree structure relation.

The foregoing aspect and any possible implementation manner further provide an implementation manner, where after performing POI clustering processing by using a community discovery algorithm according to the association relationship between two POIs and the association parameter of the association relationship between two POIs to obtain at least one POI cluster having a tree structure relationship, the implementation manner further includes:

acquiring the support degree of the incidence relation between every two POIs which are not under the same appointed node in the tree structure;

and according to the support degree of the association relationship between every two POIs which are not under the same appointed node in the tree structure and the association relationship between every two POIs which are not under the same appointed node in the tree structure, carrying out POI cluster heterogeneous association processing to obtain a heterogeneous association relationship between every two POI clusters, so as to obtain a related POI cluster which has a heterogeneous association relationship with the target POI cluster according to the target POI cluster.

obtaining description data of each POI cluster in the at least one POI cluster; the description data includes at least one of comment data and brand data;

obtaining the description characteristics of each POI cluster according to the description data;

and performing POI cluster global association processing according to the description characteristics of each POI cluster to obtain a global homogeneous association relationship between every two POI clusters, so as to obtain an associated POI cluster having a global homogeneous association relationship with the target POI cluster according to the target POI cluster.

In another aspect of the present invention, there is provided a POI recommending apparatus including:

the request unit is used for acquiring tile data of the electronic map requested by a user;

the matching unit is used for acquiring a request POI cluster on the electronic map according to the tile data;

and the adjusting unit is used for adjusting the display level of the request POI cluster according to the user personalized data of the user, so that the POI in the request POI cluster can be displayed on the electronic map according to the display level of the request POI cluster.

The above-described aspects and any possible implementations further provide an implementation, where the apparatus further includes:

an acquisition unit, configured to acquire an amount of access by the user to a target POI in which the user is interested;

the association unit is used for acquiring the statistical visit quantity of the user to the target POI cluster to which the POI belongs according to the visit quantity of the user to the target POI;

the association unit is further configured to obtain, according to the statistical visit amount of the user to the target POI cluster, a transfer visit amount of the user to an associated POI cluster, where the associated POI cluster and the target POI cluster have an association relationship;

the construction unit is used for obtaining the data of the interest degree of the user to the associated POI cluster according to the transmission access amount of the user to the associated POI cluster, and the data is used as the user personalized data of the user; or obtaining the data of the interest degree of the user to the target POI cluster according to the transmission access amount of the user to the target POI cluster, and using the data as the user personalized data of the user.

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

The above-described aspects and any possible implementation further provide an implementation, where the association is a homogeneous association; the association unit is particularly used for

Obtaining a homogeneous correlation attenuation coefficient; and

The above-described aspects and any possible implementation further provide an implementation, where the association is a heterogeneous association; the association unit is particularly used for

Obtaining a heterogeneous correlation attenuation coefficient; and

The above-described aspects and any possible implementation further provide an implementation, where the association is a global homogeneous association; the association unit is particularly used for

Acquiring the statistical access amount of the user to other POI clusters, wherein the other POI clusters and the target POI clusters and the associated POI clusters have a global homogeneous association relationship; and

The above-mentioned aspects and any possible implementation manner further provide an implementation manner, and the obtaining unit is specifically configured

Obtaining the target POI according to the attribute data of the user; or

And obtaining the target POI according to the current position of the user.

The above-mentioned aspect and any possible implementation manner further provide an implementation manner, and the association unit is further configured to

Acquiring user behavior data of users in the whole network;

acquiring an association relation between every two POIs according to the user behavior data; and

the support degree of the incidence relation between every two POIs; or

The above-mentioned aspects and any possible implementation further provide an implementation, and the association unit is specifically configured to

Acquiring the support degree of the incidence relation between every two POIs which are not under the same appointed node in the tree structure; and

obtaining the description characteristics of each POI cluster according to the description data; and

In another aspect of the present invention, there is provided an apparatus comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a POI recommendation method as provided in an aspect above.

In another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the POI recommendation method provided in the above aspect.

According to the technical scheme, the requesting POI cluster on the electronic map is obtained according to the obtained tile data of the electronic map requested by the user, the display level of the requesting POI cluster is adjusted according to the user personalized data of the user, and the POI in the requesting POI cluster is displayed on the electronic map according to the display level of the requesting POI cluster, so that the personalized electronic map can be provided for each user based on the user personalized data, the personalized requirements of the user can be met, therefore, the POI which the user may be interested in or needs to know can be accurately recommended to the user based on the user personalized data, and the POI recommendation success rate is improved.

In addition, by adopting the technical scheme provided by the invention, the statistical access amount of the user to the target POI cluster to which the POI belongs is obtained according to the obtained access amount of the user to the target POI cluster in which the user is interested, and further the transmission access amount of the user to the associated POI cluster having the association relationship with the target POI cluster is obtained according to the statistical access amount of the user to the target POI cluster, so that the data of the interest degree of the user to the associated POI cluster can be obtained according to the transmission access amount of the user to the associated POI cluster to be used as the user personalized data of the user, and the access amount of the user to a single POI is mapped to the access amount of the POI cluster to which the single POI belongs, and further the access amount of the associated POI cluster having the association relationship with the single POI cluster to be transmitted to discover the interest degree of the user to the associated cluster, and the access amount of the user to the POI cluster to which the single POI belongs can be transmitted to the associated POI cluster which has an association relationship with the POI cluster to which the single POI belongs and is not accessed, so that effective user personalized data can be obtained, therefore, the POI which the user may be interested in or the POI which needs to be known can be accurately recommended to the user based on the user personalized data, and the POI recommendation success rate is improved.

In addition, by adopting the technical scheme provided by the invention, the cluster is used for replacing a single POI, and the individual information of the POI is described by using the whole information of the cluster, so that the information of the single POI is enriched, and the reliability of POI recommendation can be effectively improved.

In addition, by adopting the technical scheme provided by the invention, the POI is divided more accurately, and the situation that the division is not clear or even wrong due to the key words or information loss of the POI is avoided.

In addition, by adopting the technical scheme provided by the invention, POI with different levels and different semantic granularities can be selected according to different scene requirements.

In addition, by adopting the technical scheme provided by the invention, the user experience can be greatly improved.

[ description of the drawings ]

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed in the embodiments or the prior art descriptions will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without inventive labor.

Fig. 1 is a schematic flowchart of a POI recommendation method according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a POI recommendation apparatus according to another embodiment of the present invention;

fig. 3 is a schematic structural diagram of a POI recommendation apparatus according to another embodiment of the present invention;

FIG. 4 is a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present invention.

[ detailed description ] embodiments

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

It should be noted that the terminal according to the embodiment of the present invention may include, but is not limited to, a mobile phone, a Personal Digital Assistant (PDA), a wireless handheld device, a Tablet Computer (Tablet Computer), a Personal Computer (PC), an MP3 player, an MP4 player, a wearable device (e.g., smart glasses, smart watch, smart bracelet, etc.), and the like.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

Fig. 1 is a schematic flowchart of a POI recommendation method according to an embodiment of the present invention, as shown in fig. 1.

101. And acquiring tile data of the electronic map requested by the user.

The tile data refers to data of map tiles. The map Tile technology cuts a configured map in a certain coordinate range into square pictures in a plurality of rows and columns according to a plurality of fixed scales (Tile levels) and specified picture sizes, stores the square pictures in a directory system or a database system according to a certain naming rule and an organization mode, forms a static map cache of a pyramid model, and map slices obtained by map cutting are also called map tiles (tiles).

102. And acquiring a request POI cluster on the electronic map according to the tile data.

Specifically, the POI cluster on the electronic map corresponding to the tile data may be obtained by using the tile data. It is to be understood that the obtained request POI cluster may be one POI cluster or may also be multiple POI clusters, which is not particularly limited in this embodiment.

103. And adjusting the display level of the request POI cluster according to the user personalized data of the user, so that the POI in the request POI cluster can be displayed on the electronic map according to the display level of the request POI cluster.

The display level of the requested POI cluster is a display level of each POI in the requested POI cluster. The display level of the POI is a tile level at which the POI is displayed on the electronic map, and the tile map is the lowest tile level.

Generally, when a user opens an Application (APP) for the first time, tile data of a requested electronic map, which is generally tile data with a tile level of 16 to 21, is not suitable for requesting tile data of a tile map with a tile level of less than 16, since a tile map with a tile level of less than 16 is geographic data with a large area, and in this case, it is somewhat inappropriate to adjust the display level of a single POI.

Optionally, in a possible implementation manner of this embodiment, in 103, if the user personalized data of the user hits a POI in the requesting POI cluster, the display level of the POI may be adjusted, that is, the preset adjustment parameter, for example, 2, is subtracted from the display level of the POI, so as to display the POI on the electronic map in advance.

It can be understood that, when the POI in the requested POI cluster is displayed on the electronic map, the top N POIs in accordance with the total display number may be selected in a descending order according to the heat of each POI in the requested POI cluster, and the display level is adjusted.

It should be noted that part or all of the execution subjects 101 to 103 may be an application located at the local terminal, or may also be a functional unit such as a plug-in or Software Development Kit (SDK) set in the application located at the local terminal, or may also be a processing engine located in a server on the network side, or may also be a distributed system located on the network side, which is not particularly limited in this embodiment.

It is to be understood that the application may be a native app (native app) installed on the terminal, or may also be a web page program (webApp) of a browser on the terminal, and this embodiment is not particularly limited thereto.

In this way, the requested POI cluster on the electronic map is acquired according to the acquired tile data of the electronic map requested by the user, and then the display level of the requested POI cluster is adjusted according to the user personalized data of the user, so that the POI in the requested POI cluster is displayed on the electronic map according to the display level of the requested POI cluster, and the personalized electronic map can be provided for each user based on the user personalized data, and the personalized requirements of the user can be met.

In the present invention, before 103, a step of obtaining user personalized data of the user may be further included. Specifically, the access amount of the user to the target POI interested by the user may be specifically obtained, and further, the statistical access amount of the user to the target POI cluster to which the POI belongs may be obtained according to the access amount of the user to the target POI. Then, according to the transmission access amount of the user to the target POI cluster, obtaining the data of the interest degree of the user to the target POI cluster, as the user personalized data of the user; or the transfer visit amount of the user to the associated POI cluster can be obtained according to the statistical visit amount of the user to the target POI cluster, and the associated POI cluster and the target POI cluster have an association relationship; and obtaining the data of the interest degree of the user to the associated POI cluster according to the transmission access amount of the user to the associated POI cluster, wherein the data is used as the user personalized data of the user.

It can be understood that, since the statistical access amount of the user to the target POI cluster to which the POI belongs can be directly obtained, the data of the degree of interest of the user to the target POI cluster can be directly obtained according to the statistical access amount of the user to the target POI cluster to which the POI belongs, so as to be used as the user personalization data of the user.

In this way, the statistical access amount of the user to the target POI cluster to which the POI belongs is obtained according to the obtained access amount of the user to the target POI which the user is interested in, and further the transfer access amount of the user to the associated POI cluster having an association relationship with the target POI cluster is obtained according to the statistical access amount of the user to the target POI cluster, so that the data of the interest degree of the user to the associated POI cluster can be obtained according to the transfer access amount of the user to the associated POI cluster to be used as the user personalized data of the user, the access amount of the user to a single POI is mapped to the access amount of the POI cluster to which the single POI belongs, and further the access amount of the associated cluster having an association relationship with the single POI cluster is transferred to find the interest degree of the user to the associated cluster, and the access amount of the user to the single POI cluster to which the single POI belongs to be transferred to the single POI which is not visited and which the single POI belongs to be transferred to The associated POI clusters with the association relationship of the POI clusters can obtain effective user personalized data, so that POIs possibly interested by the user or POIs needing to be known can be accurately recommended to the user based on the user personalized data, and the POI recommendation success rate is improved.

Optionally, in a possible implementation manner of this embodiment, in the present invention, a plurality of methods may be specifically adopted to obtain a target POI that is of interest to a user.

In a specific implementation process, the target POI may be obtained according to the attribute data of the user. For example, if the attribute data of the user is age 20, sex is female, resident address is home, and love is shopping at a park, then the target POI can be obtained as a garden.

In another specific implementation process, the target POI may be obtained according to a latest query operation of the user. For example, if the user inquires of the Yuanming Garden within three days, then the target POI can be obtained as the Yuanming garden.

In another specific implementation process, the target POI may be obtained according to the current query operation of the user. For example, if the user is currently querying the Yuanming Garden, then the target POI may be obtained as the Yuanming garden.

In another specific implementation process, the target POI may be obtained according to a current location of the user. For example, if the current location of the user is in the garden, then the target POI may be obtained as the garden.

Then, after the target POI interested by the user is obtained, the access amount of the user to the target POI interested by the user, for example, clicking, browsing, etc., may be counted according to the user behavior data of the user.

Optionally, in a possible implementation manner of this embodiment, in the present invention, constructing a POI cluster set having a tree structure may be further included.

In a specific implementation process, user behavior data of the whole network user can be specifically acquired, and further, an association relationship between every two POIs can be acquired according to the user behavior data. Then, according to the association relationship between the two POIs and the association parameters of the association relationship between the two POIs, a community discovery algorithm is adopted to perform POI clustering processing to obtain at least one POI cluster with a tree structure relationship, so as to obtain a target POI cluster to which the target POI belongs according to the target POI, and obtain an associated POI cluster with a homogeneous association relationship with the target POI cluster, namely a homogeneous POI cluster according to the target POI cluster. Wherein each POI cluster of the at least one POI cluster may include at least one POI therein.

Therefore, the association relationship between the POI and the POI is mined out through the long-time behaviors of a large number of users, and all the POI in the whole number are connected together through the association relationship to form a POI network. Then, a community discovery algorithm is adopted to discover a cluster of POI with good cohesion in the network, namely a POI cluster, wherein the POI cluster has the characteristic of meeting the specific requirements of a large number of users in similar scenes. The scheme is a hierarchical division, and POI classification with larger granularity can be obtained by dividing POI after the first classification by using the same method again.

In the implementation process, the adopted association parameter of the association relationship between every two POIs may be a support degree of the association relationship between every two POIs, or may also be a support degree of the association relationship between every two POIs and a cosine similarity of the association relationship between every two POIs, which is not particularly limited in this embodiment.

Specifically, first, user behavior data of each user in the network-wide users within a certain time range, for example, click behavior data, retrieval behavior data, positioning trajectory data, or the like, may be collected to obtain an association relationship between each two POIs, and meanwhile, according to the collected user behavior data, association parameters of the association relationship between each two POIs, for example, a support degree of the association relationship between each two POIs and a cosine similarity of the association relationship between each two POIs, may also be further obtained.

The support degree of the association relationship between two POIs depends on the number of times that the two POIs are clicked, retrieved or located by the user continuously or simultaneously in a certain time range.

For example, if a user clicks, retrieves or locates two POIs consecutively or simultaneously within a certain time range, the support of the association between the two POIs may be increased by 1.

The cosine similarity of the association between two POIs depends on the support degree of the association between two POIs and the heat degree of each POI in the two POIs.

For example, the cosine similarity of the association between two POIs may be

If a user clicks, retrieves or locates the POI within a certain time range, the heat of the POI can be increased by 1.

After obtaining the association relationship between each two POIs and the association parameters of the association relationship between each two POIs, the association relationship between each two POIs may be filtered according to the association parameters of the association relationship between each two POIs, that is, the association relationship between each two POIs with a weak association relationship is deleted.

In the following, how to filter the association between two POIs will be described by taking the support degree of the association between two POIs as an example of the association parameter of the association between two POIs.

Two thresholds S1 and S2 may be preset for the support degree of the association relationship between two POIs, and S2 is greater than S1. Directly deleting the association relation between every two POIs with the support degree smaller than S1; directly reserving the association relationship between every two POIs with the support degree greater than or equal to S2; for the association relationship between two POIs with the support degree greater than or equal to S1 and less than S2, further judgment needs to be made to determine which POIs can be reserved and which POIs need to be deleted. For example, a threshold L is further set, and for the association relationship between two POIs with the support degree greater than or equal to S1 and less than S2, if the support degree of the association relationship between the two POIs and other POIs is less than L, the association relationship between the two POIs needs to be preserved; if the support degree of the association between the two POIs and other POIs is greater than or equal to L, the association between the two POIs needs to be deleted.

After filtering out the weaker association relationship in the association relationships between every two POIs, a network which is formed by organizing the POIs through the association relationships and takes the POIs as nodes and the association relationships as edges is obtained. Then, a community discovery algorithm can be adopted to find a cluster of POIs with a relatively close association relationship, namely a POI cluster, in the obtained network. In the community discovery algorithm, an upper limit of the data amount of each cluster of POIs, for example, 25, or the like, may be set. And taking the result of the first division as a basic unit of the next processing, namely, regarding the result as a new POI, and repeating the operation to obtain a POI division result with coarser granularity. The partitioning is terminated until no valid association between any two POI clusters is found.

In this way, a POI cluster set having a tree structure is constructed, and POI clusters in the POI cluster set are all homogeneous POI clusters having a homogeneous association relationship.

According to the method and the device, the target POI cluster to which the target POI belongs is obtained according to the obtained target POI which is interested by the user, the homogeneous POI cluster having a homogeneous association relation with the target POI cluster is further obtained according to the target POI cluster, so that the homogeneous POI cluster can be recommended to the user.

Optionally, in a possible implementation manner of this embodiment, after constructing the POI cluster set having the tree structure, it is further required to further mine an associated POI cluster having a heterogeneous association relationship with the POI clusters in the POI cluster set, that is, a heterogeneous POI cluster.

Specifically, the support degree of the association relationship between two POIs not under the same designated node in the tree structure may be specifically obtained, and then, according to the support degree of the association relationship between two POIs not under the same designated node in the tree structure and the association relationship between two POIs not under the same designated node in the tree structure, POI cluster heterogeneous association processing may be performed to obtain a heterogeneous association relationship between two POI clusters, so as to obtain a heterogeneous POI cluster, which is an associated POI cluster having a heterogeneous association relationship with the target POI cluster, according to the target POI cluster.

Therefore, heterogeneous association relations among POI can be excavated through the construction of heterogeneous POI clusters, and the purposes of reducing data sparsity and improving clustering fine granularity are achieved.

In this implementation process, the designated node may be a root node, or may also be another higher-level node below the root node, which is not particularly limited in this embodiment.

For the support degree of the association between each two POIs, reference may be made to the related content in the previous embodiment for specific description, and details are not described here again.

A threshold S3 may be preset for the support degree of the association between two POIs. And determining the association relationship between every two POIs with the support degree greater than or equal to S3 as the heterogeneous association relationship between the POI clusters to which the POIs belong.

According to the method and the device, the target POI cluster to which the target POI belongs is obtained according to the obtained target POI which is interested by the user, and then the heterogeneous POI cluster which has a heterogeneous association relationship with the target POI cluster is obtained according to the target POI cluster, so that the heterogeneous POI cluster can be recommended to the user.

Optionally, in a possible implementation manner of this embodiment, after the POI cluster set with the tree structure is constructed, associated POI clusters among the global homogeneous POI clusters, that is, global homogeneous association relationships, may be further mined.

Specifically, description data of each POI cluster in the at least one POI cluster may be obtained, where the description data may include, but is not limited to, at least one of comment data and brand data. Then, according to the description data, the description feature of each POI cluster can be obtained, and further, according to the description feature of each POI cluster, POI cluster global association processing is performed to obtain a global homogeneous association relationship between every two POI clusters, so that a global homogeneous POI cluster having a global homogeneous association relationship with the target POI cluster can be obtained according to the target POI cluster.

Therefore, the similarity among the same POI clusters in different regions (namely tree structures under different root nodes) is found globally, the same association relation among the same POI clusters in the whole region is mined, and the user preference of a familiar region is transmitted to another strange region, so that the reliability of POI recommendation can be effectively improved.

In this implementation manner, for the case that the description data is comment data, comment data of each POI cluster may be acquired based on the constructed POI cluster set of the tree structure, and then, word segmentation processing (including stop word processing) may be performed on the comment data to obtain a word segmentation result. And selecting a part of word segmentation results or all word segmentation results as the description characteristics of each POI cluster according to the statistical parameters of each word segmentation result, such as the use frequency and the like. Calculating the similarity between every two POI clusters according to the description characteristics of each POI cluster, and determining every two POI clusters with the similarity larger than or equal to a preset similarity threshold value M as having a global homogeneous association relationship; and determining every two POI clusters with the similarity smaller than a preset similarity threshold value M as not having the global homogeneous association relationship.

In this implementation manner, for the case that the description data is brand data, the brand data of each POI cluster may be acquired based on the constructed tree-structured POI cluster set, and specifically may be acquired from the POI attribute field. Furthermore, the descriptive characteristics of each POI cluster can be obtained from these brand data of each POI cluster. Calculating the similarity between every two POI clusters according to the description characteristics of each POI cluster, and determining every two POI clusters with the similarity larger than or equal to a preset similarity threshold value M as having a global homogeneous association relationship; and determining every two POI clusters with the similarity smaller than a preset similarity threshold value M as not having the global homogeneous association relationship.

Thus, after mining the homogeneous association relationship between homogeneous POI clusters in the global, it can be determined whether the user is located in the familiar area of the user, i.e. the resident area of the user, according to the location data of the user. The familiar area of the user can be obtained according to the operation behavior data of the user or the attribute data of the user, and a mining method in the prior art can be adopted, which is not described herein again.

If the user is no longer located in the familiar area of the user, obtaining a global homogeneous POI cluster having a global homogeneous incidence relation with the target POI cluster according to the target POI cluster; if the user is still located in the familiar area of the user, a global homogeneous POI cluster having a global homogeneous incidence relation with the target POI cluster is obtained without the need of the target POI cluster, and the homogeneous POI cluster having the homogeneous incidence relation with the target POI cluster is directly recommended to the user according to the target POI cluster and based on the constructed POI cluster set having the tree structure.

The location data of the user refers to location data of a current location of the user, and specifically, the location data of the terminal, i.e., the geographical location data of the location of the terminal, obtained by using various existing location technologies, such as a Global Positioning System (GPS) technology, a Wireless Fidelity (Wi-Fi) location technology, a base station location technology, and the like, for the terminal used by the user.

According to the method and the device, the target POI cluster to which the target POI belongs is obtained according to the obtained target POI which is interested by the user, and then the global homogeneous POI cluster with the homogeneous association relation with the target POI cluster is obtained according to the target POI cluster and the position data of the user, so that the global homogeneous POI cluster can be recommended to the user.

Optionally, in a possible implementation manner of this embodiment, in 102, when performing the visit amount statistics on the target POI cluster, the statistical visit amount of each POI in the target POI cluster by the same user may be summed, and a calculation result of the summation is used as the total visit amount of the target POI cluster, that is, the statistical visit amount.

Optionally, in a possible implementation manner of this embodiment, the association relationship may include, but is not limited to, at least one of the following association relationships:

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

In a specific implementation process, in a case where the association relationship is a homogeneous association relationship, then, in the present invention, a homogeneous association attenuation coefficient may be specifically obtained, for example, 0.8; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained from the statistical visit amount of the user to the target POI cluster and the homogeneous correlation attenuation coefficient, for example, a product of the statistical visit amount of the user to the target POI cluster and the homogeneous correlation attenuation coefficient is used as the transfer visit amount of the user to the associated POI cluster.

In another specific implementation process, in a case that the association relationship is a heterogeneous association relationship, in the present invention, a heterogeneous association attenuation coefficient may be specifically obtained, for example, 0.75; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained according to the statistical visit amount of the user to the target POI cluster and the heterogeneous correlation attenuation coefficient, for example, a product of the statistical visit amount of the user to the target POI cluster and the heterogeneous correlation attenuation coefficient is used as the transfer visit amount of the user to the associated POI cluster. Generally speaking, the heterogeneous correlation attenuation coefficient needs to be set smaller than the homogeneous correlation attenuation coefficient.

In another specific implementation process, in view of a situation that the association relationship is a global homogeneous association relationship, in the present invention, a statistical access amount of the user to other POI clusters may be specifically obtained, and a global homogeneous association relationship exists between the other POI clusters and the target POI cluster and the associated POI cluster; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained from the statistical visit amount of the user to the target POI cluster and the statistical visit amount of the user to the other POI clusters, for example, a sum of the statistical visit amount of the user to the target POI cluster and the statistical visit amount of the user to the other POI clusters is used as the transfer visit amount of the user to the associated POI cluster.

Optionally, in a possible implementation manner of this embodiment, in the present invention, data regularization processing may be specifically performed on the transfer visit amount of the associated POI cluster by the user, so as to obtain the data of the degree of interest of the user in the associated POI cluster.

In a specific implementation process, a formula (1-q ^ n)/1-q may be specifically used, where q is 9/10, and n is a transfer visit amount of an associated POI cluster, and the transfer visit amount of the associated POI cluster by the user is subjected to data regularization processing to generate the data of the degree of interest of the user in the associated POI cluster.

In this way, the interest level data may be used as the basic user personalization data for other business modules to invoke, for example, a business module that performs ranking of associated POI clusters.

In this embodiment, the requested POI cluster on the electronic map is acquired according to the acquired tile data of the electronic map requested by the user, and then the display level of the requested POI cluster is adjusted according to the user personalized data of the user, so that the POI in the requested POI cluster is displayed on the electronic map according to the display level of the requested POI cluster, so that a personalized electronic map can be provided to each user based on the user personalized data, and personalized requirements of the user can be met.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

Fig. 2 is a schematic structural diagram of a POI recommendation apparatus according to another embodiment of the present invention, as shown in fig. 2. The POI recommending apparatus of the present embodiment may include a requesting unit 21, a matching unit 22, and an adjusting unit 23. The request unit 21 is configured to obtain tile data of an electronic map requested by a user; the matching unit 22 is configured to obtain a request POI cluster on the electronic map according to the tile data; an adjusting unit 23, configured to adjust a display level of the requested POI cluster according to the user personalization data of the user, so as to display the POI in the requested POI cluster on the electronic map according to the display level of the requested POI cluster.

It should be noted that, part or all of the POI recommendation apparatus provided in this embodiment may be an application of a terminal device located on a local terminal, that is, a designated vehicle, or may also be a functional unit such as a plug-in or Software Development Kit (SDK) set in the application located on the local terminal, or may also be a processing engine located in a server on a network side, or may also be a distributed system located on the network side, which is not particularly limited in this embodiment.

Optionally, in a possible implementation manner of this embodiment, as shown in fig. 3, the POI recommending apparatus provided in this embodiment may further include an obtaining unit 31, an associating unit 32, and a constructing unit 33. The obtaining unit 31 is configured to obtain an access amount of the user to a target POI in which the user is interested; the association unit 32 is configured to obtain, according to the access amount of the user to the target POI, a statistical access amount of the user to a target POI cluster to which the POI belongs; the associating unit 32 is further configured to obtain, according to the statistical visit amount of the user to the target POI cluster, a transfer visit amount of the user to an associated POI cluster, where the associated POI cluster and the target POI cluster have an association relationship; the constructing unit 33 is configured to obtain, according to the transmission access amount of the user to the associated POI cluster, data of a degree of interest of the user to the associated POI cluster, so as to serve as user personalized data of the user; or obtaining the data of the interest degree of the user to the target POI cluster according to the transmission access amount of the user to the target POI cluster, and using the data as the user personalized data of the user.

Optionally, in a possible implementation manner of this embodiment, the obtaining unit 31 may be specifically configured to obtain the target POI according to the attribute data of the user; or obtaining the target POI according to the latest query operation of the user; or obtaining the target POI according to the current query operation of the user; or obtaining the target POI according to the current position of the user.

Optionally, in a possible implementation manner of this embodiment, the associating unit 32 may be further configured to obtain user behavior data of users over the whole network; acquiring an association relation between every two POIs according to the user behavior data; and according to the association relationship between every two POIs and the association parameters of the association relationship between every two POIs, carrying out POI clustering processing by adopting a community discovery algorithm to obtain at least one POI cluster with a tree structure relationship, so as to obtain a target POI cluster to which the target POI belongs according to the target POI, and obtaining an associated POI cluster with a homogeneous association relationship with the target POI cluster, namely a homogeneous POI cluster according to the target POI cluster.

Optionally, in a possible implementation manner of this embodiment, the association unit 32 may be specifically configured to perform filtering processing on the association relationship between each two POIs according to an association parameter of the association relationship between each two POIs; and carrying out POI clustering processing by adopting a community discovery algorithm according to the incidence relation between every two POIs after the filtering processing so as to obtain at least one POI cluster with a tree structure relation.

Optionally, in a possible implementation manner of this embodiment, the association unit 32 may be further configured to obtain a support degree of an association relationship between every two POIs that are not under the same designated node in the tree structure; and according to the support degree of the association relationship between every two POIs which are not under the same appointed node in the tree structure and the association relationship between every two POIs which are not under the same appointed node in the tree structure, carrying out POI cluster heterogeneous association processing to obtain a heterogeneous association relationship between every two POI clusters, so as to obtain a related POI cluster which has a heterogeneous association relationship with the target POI cluster, namely a heterogeneous POI cluster according to the target POI cluster.

Optionally, in a possible implementation manner of this embodiment, the associating unit 32 may be further configured to acquire description data of each POI cluster in the at least one POI cluster; the description data includes at least one of comment data and brand data; obtaining the description characteristics of each POI cluster according to the description data; and according to the description characteristics of each POI cluster, carrying out POI cluster global association processing to obtain a global homogeneous association relationship between every two POI clusters, so as to obtain an associated POI cluster having a global homogeneous association relationship with the target POI cluster, namely a global homogeneous POI cluster according to the target POI cluster.

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

In a specific implementation process, for a case that the association relationship is a homogeneous association relationship, the association unit 32 may be specifically configured to obtain a homogeneous association attenuation coefficient, for example, 0.8; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained from the statistical visit amount of the user to the target POI cluster and the homogeneous correlation attenuation coefficient, for example, a product of the statistical visit amount of the user to the target POI cluster and the homogeneous correlation attenuation coefficient is used as the transfer visit amount of the user to the associated POI cluster.

In another specific implementation process, for a case that the association relationship is a heterogeneous association relationship, the association unit 32 may be specifically configured to obtain a heterogeneous association attenuation coefficient, for example, 0.75; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained according to the statistical visit amount of the user to the target POI cluster and the heterogeneous correlation attenuation coefficient, for example, a product of the statistical visit amount of the user to the target POI cluster and the heterogeneous correlation attenuation coefficient is used as the transfer visit amount of the user to the associated POI cluster. Generally speaking, the heterogeneous correlation attenuation coefficient needs to be set smaller than the homogeneous correlation attenuation coefficient.

In another specific implementation process, for a case that the association relationship is a global homogeneous association relationship, the associating unit 32 may be specifically configured to obtain a statistical access amount of the user to other POI clusters, where the other POI clusters have a global homogeneous association relationship with the target POI cluster and the associated POI cluster; furthermore, the transfer visit amount of the user to the associated POI cluster may be obtained from the statistical visit amount of the user to the target POI cluster and the statistical visit amount of the user to the other POI clusters, for example, a sum of the statistical visit amount of the user to the target POI cluster and the statistical visit amount of the user to the other POI clusters is used as the transfer visit amount of the user to the associated POI cluster.

It should be noted that the method in the embodiment corresponding to fig. 1 may be implemented by the POI recommendation apparatus provided in this embodiment. For a detailed description, reference may be made to relevant contents in the embodiment corresponding to fig. 1, and details are not described here.

In this embodiment, the matching unit acquires the requested POI cluster on the electronic map according to the tile data of the electronic map requested by the user, which is acquired by the requesting unit, and the adjusting unit adjusts the display level of the requested POI cluster according to the user personalized data of the user, so that the POI in the requested POI cluster is displayed on the electronic map according to the display level of the requested POI cluster, so that a personalized electronic map can be provided to each user based on the user personalized data, and personalized requirements of the user can be met.

In addition, by adopting the technical scheme provided by the invention, the statistical visit amount of the user to the target POI cluster to which the POI belongs is obtained through the visit amount of the user to the target POI cluster to which the user is interested, which is obtained through the association unit, and then the transfer visit amount of the user to the associated POI cluster having the association relationship with the target POI cluster is obtained according to the statistical visit amount of the user to the target POI cluster, so that the construction unit can obtain the data of the degree of interest of the user to the associated POI cluster according to the transfer visit amount of the user to the associated POI cluster, and the data is used as the user personalized data of the user, and the visit amount of the user to the single POI is mapped to the visit amount of the POI cluster to which the single POI belongs, and then transferred to the visit amount of the associated POI cluster having the association relationship with the POI cluster to which the single POI belongs, the method and the device have the advantages that the interest degree of the user to the associated cluster is found, the visit quantity of the user to the POI cluster to which the single POI belongs can be transmitted to the associated POI cluster which has the association relation with the POI cluster to which the single POI belongs and is not visited, and effective user personalized data can be obtained.

FIG. 4 illustrates a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present invention. The computer system/server 12 shown in FIG. 4 is only one example and should not be taken to limit the scope of use or functionality of embodiments of the present invention.

As shown in FIG. 4, computer system/server 12 is in the form of a general purpose computing device. The components of computer system/server 12 may include, but are not limited to: one or more processors or processing units 16, a storage device or system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Computer system/server 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 46. The computer system/server 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 3, and commonly referred to as a "hard drive"). Although not shown in FIG. 3, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

The computer system/server 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer system/server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the computer system/server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 44. Also, the computer system/server 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 20. As shown, network adapter 20 communicates with the other modules of computer system/server 12 via bus 18. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer system/server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing the POI recommendation method provided in the embodiment corresponding to fig. 1.

Another embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the POI recommendation method provided in the embodiment corresponding to fig. 1.

In particular, any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. 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 (a non-exhaustive list) of the computer readable storage medium would include the following: 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 context of this document, 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.

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 any of a variety of 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, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A POI recommendation method is characterized by comprising the following steps:

obtaining tile data of an electronic map requested by a user;

acquiring a request POI cluster on the electronic map according to the tile data; wherein each POI cluster in the at least one POI cluster having the tree structure, and each POI cluster in the at least one POI cluster having the tree structure and other POI clusters not within the tree structure are POI clusters having an association relationship; each POI cluster in the at least one POI cluster comprises at least one POI; the construction mode of the at least one POI cluster with the tree structure comprises the following steps: all the POIs in the total amount are connected together to form a POI network through the association relationship between the POIs; discovering at least one POI cluster with good cohesion in the network by adopting a community discovery algorithm;

according to the user personalized data of the user, adjusting the display level of the request POI cluster, so that the POI in the request POI cluster can be displayed on the electronic map according to the display level of the request POI cluster; wherein the adjusting the display level of the requested POI cluster according to the user personalization data of the user to display the POI in the requested POI cluster on the electronic map according to the display level of the requested POI cluster comprises:

and if the user personalized data of the user hits the POI in the request POI cluster, adjusting the display level of the hit POI so as to display the POI on the electronic map in advance.

2. The method of claim 1, wherein the adjusting the display level of the requested POI cluster according to the user personalization data of the user for displaying the POIs in the requested POI cluster on the electronic map according to the display level of the requested POI cluster further comprises:

3. The method of claim 2, wherein the association comprises at least one of the following associations:

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

4. The method of claim 2, wherein the correlation is a homogeneous correlation; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

obtaining a homogeneous correlation attenuation coefficient;

5. The method of claim 2, wherein the association is a heterogeneous association; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

obtaining a heterogeneous correlation attenuation coefficient;

6. The method of claim 2, wherein the association is a global homogenous association; the obtaining of the transfer visit amount of the user to the associated POI cluster according to the statistical visit amount of the user to the target POI cluster includes:

7. The method of claim 2, wherein the obtaining of the target POI of interest to the user comprises:

obtaining the target POI according to the attribute data of the user; or

And obtaining the target POI according to the current position of the user.

8. The method according to any one of claims 2 to 7, wherein before obtaining the statistical access amount of the user to the target POI cluster to which the POI belongs according to the access amount of the user to the target POI, the method further comprises:

acquiring user behavior data of users in the whole network;

9. The method according to claim 8, wherein the association parameters of the association relationship between two POIs comprise:

the support degree of the incidence relation between every two POIs; or

10. The method according to claim 8, wherein the performing POI clustering processing according to the association relationship between the two POIs and the association parameter of the association relationship between the two POIs by using a community discovery algorithm to obtain at least one POI cluster having a tree structure relationship comprises:

11. The method according to claim 8, wherein after the POI clustering processing is performed according to the association relationship between the two POIs and the association parameter of the association relationship between the two POIs by using a community discovery algorithm to obtain at least one POI cluster having a tree structure relationship, the method further comprises:

12. The method according to claim 8, wherein after the POI clustering processing is performed according to the association relationship between the two POIs and the association parameter of the association relationship between the two POIs by using a community discovery algorithm to obtain at least one POI cluster having a tree structure relationship, the method further comprises:

13. A POI recommendation apparatus, comprising:

the matching unit is used for acquiring a request POI cluster on the electronic map according to the tile data; wherein each POI cluster in the at least one POI cluster having the tree structure, and each POI cluster in the at least one POI cluster having the tree structure and other POI clusters not within the tree structure are POI clusters having an association relationship; each POI cluster in the at least one POI cluster comprises at least one POI; the construction mode of the at least one POI cluster with the tree structure comprises the following steps: all the POIs in the total amount are connected together to form a POI network through the association relationship between the POIs; discovering at least one POI cluster with good cohesion in the network by adopting a community discovery algorithm;

the adjusting unit is used for adjusting the display level of the request POI cluster according to the user personalized data of the user, so that the POI in the request POI cluster can be displayed on the electronic map according to the display level of the request POI cluster; wherein the content of the first and second substances,

the adjusting unit is particularly used for

14. The apparatus of claim 13, further comprising:

15. The apparatus of claim 14, wherein the association comprises at least one of the following associations:

homogeneous association relation;

a heterogeneous association relationship; and

global homogenous correlation.

16. The apparatus of claim 14, wherein the association is a homogenous association; the association unit is particularly used for

Obtaining a homogeneous correlation attenuation coefficient; and

17. The apparatus of claim 14, wherein the association is a heterogeneous association; the association unit is particularly used for

Obtaining a heterogeneous correlation attenuation coefficient; and

18. The apparatus of claim 14, wherein the association is a global homogenous association; the association unit is particularly used for

19. The apparatus according to claim 14, wherein the obtaining unit obtains the target POI specifically according to attribute data of the user; or

And obtaining the target POI according to the current position of the user.

20. The apparatus according to any of claims 14 to 19, wherein the correlation unit is further configured to correlate the received signal with a reference signal

Acquiring user behavior data of users in the whole network;

21. The apparatus according to claim 20, wherein the association parameters of the association relationship between two POIs include:

the support degree of the incidence relation between every two POIs; or

22. Device according to claim 20, characterized in that the association unit is specifically configured to

23. The apparatus according to claim 20, wherein the associating unit is further configured to obtain a support degree of an association relationship between two POIs that are not under the same designated node in the tree structure; and

24. The apparatus of claim 20, wherein the associating unit is further configured to associate the received data with the specific device

25. An electronic device, characterized in that the electronic device comprises:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a method as claimed in any one of claims 1 to 12.

26. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method of any one of claims 1 to 12.