CN104391853A

CN104391853A - POI (point of interest) recommending method, POI information processing method and server

Info

Publication number: CN104391853A
Application number: CN201410497492.XA
Authority: CN
Inventors: 乐阳; 贺鹏; 陈川; 岳亚丁; 王巨宏; 管刚; 常晓猛; 李清泉
Original assignee: Tencent Technology Shenzhen Co Ltd; Shenzhen University
Current assignee: Tencent Technology Shenzhen Co Ltd; Shenzhen University
Priority date: 2014-09-25
Filing date: 2014-09-25
Publication date: 2015-03-04
Anticipated expiration: 2034-09-25
Also published as: CN104391853B

Abstract

The invention discloses a POI (point of interest) recommending method, a POI information processing method and a server. The POI recommending method comprises the steps: acquiring spatio-temporal information of user activity of each user in a social group according to the user generation content; determining a core activity space of the user activity in the social group according to the spatio-temporal information; acquiring POI access information of each user in the social group according to the user generation content; analyzing the POI access information to generate a POI analysis result and selecting POI in the core activity space according to the POI analysis result, and recommending the POI to the user in the social group.

Description

POI recommend method, POI information processing method and server

Technical field

The present invention relates to the information processing technology of Internet technical field, particularly relate to a kind of point of interest (Point ofinterest, POI) recommend method, POI information processing method and server.

Background technology

Along with the development of the communication technology and electronic technology, increasing user utilizes Network Capture service; Concrete waiting network predetermined as utilized network to carry out to make a reservation, arriving solid shop/brick and mortar store afterwards and consuming; Concrete as the service of information network based on POI.

POI:Point of interest, POI information is an information word in geography information, is the information that maybe can provide the services sites of service based on buildings such as the retail shop of geography information, public service website and bus stations.Usual each described POI information can comprise the information such as title and/or the code of correspondence, the COS provided and traffic of services sites.

How recommending its interested POI to accurate user, to improve the user satisfaction of user, enabling POI to be recommended accurately navigate to its corresponding potential user group and improve simultaneously and recommend success ratio, is prior art problem to be solved.

Summary of the invention

In view of this, the embodiment of the present invention is expected to provide a kind of POI recommend method, POI information processing method and server.

For achieving the above object, technical scheme of the present invention is achieved in that

Embodiment of the present invention first aspect provides a kind of POI recommend method, and described method comprises:

The space time information of the User Activity of each user in social group is obtained according to user-generated content;

The core activity space of User Activity in described social group is determined according to described space time information;

The POI visit information of each user in described social group is obtained according to described user-generated content;

Described POI visit information is analyzed, forms POI analysis result;

According to the POI that described POI analysis result is selected in described core activity space, recommend to the user in described social group.

Preferably,

Described described POI information to be analyzed, form POI analysis result, comprising: determine the visitation frequency of each POI within the first fixed time according to described POI information;

The described POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group, comprising: the POI selected in described core activity space according to described visitation frequency, recommend to the user in described social group.

Preferably,

Described described POI information to be analyzed, forms POI analysis result, also comprise:

The Annual distribution information of each POI accessed frequency within the first fixed time is determined according to described POI information;

According to described visitation frequency and described Annual distribution information, determine to access temperature;

The described POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group, comprising: recommend POI according to described access temperature to the user in described social group.

Preferably,

The evaluation information of each POI within the first fixed time is determined according to described POI information;

The described POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group, comprising: recommend POI according to described visitation frequency and described evaluation information to the user in described social group.

Preferably,

The described POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group, comprising:

According to described POI analysis result, select by the POI accessed in described social group in described core activity space, the user not accessing a described POI in described social group recommends.

Preferably,

The described POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group, also comprises:

According to described POI analysis result, to select in described core activity space and to meet the 2nd POI of default similarity condition with a described POI, recommending to the user in described social group.

Preferably,

Described method also comprises:

According to described space time information, space clustering is carried out to the User Activity in described social group, activity space is met the first pre-conditioned user and form clustering cluster;

The described core activity space determining user described in described user set according to described spatial information, comprising:

According to the space time information of each user in a described jth clustering cluster, obtain a jth core activity space;

Described described POI visit information to be analyzed, forms POI analysis result, comprising:

Described POI visit information is analyzed, is formed at the jth POI analysis result of a jth clustering cluster;

According to the POI that described jth POI analysis result is selected in a described jth core activity space, recommend to the user in described social group.

Preferably,

The described core activity space determining User Activity in described social group according to described space time information, comprising:

Determine that the activity space of described social user inside the group is divided into several regions according to described space time information;

The access probability information in region described in each is determined according to described space time information;

According to the access probability information in region described in each, determine described core activity space.

Preferably,

The described access probability information determining region described in each according to described space time information, comprising:

According to described space time information, to determine within the second fixed time each user access times in each region in described social group;

Calculate the single-user access probability in each user region described in each;

According to described single-user access probability, determine the average access probability in region described in each;

The described access probability information according to region described in each, determines described core activity space, comprising: according to described average access probability, determine described core activity space.

Preferably,

Describedly also to comprise:

According to described access times, determine the visitation frequency in described core activity space;

Judge whether the visitation frequency in described core activity space meets default frequency condition;

When the visitation frequency in described core activity space meet visitation frequency pre-conditioned time, the POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group.

Embodiment of the present invention second aspect provides a kind of POI information processing method, and described method comprises:

Obtain the POI information of the 3rd POI;

The calling party of described 3rd POI is carried out cluster, forms cluster result;

According to described cluster result, extract the first user attribute information to described 3rd POI user interested;

According to described first user attribute information, described calling party is formed at least one social group.

Preferably,

Described method also comprises:

In described social group, recommend described social user inside the group to access the POI of POI association.

Preferably,

The described POI recommending described social user inside the group to access POI association in described social group, comprising:

The 4th POI meeting default difference condition with described 3rd POI is recommended in described social group.

Preferably,

Obtain the POI visit information of described social user inside the group;

According to described visit information, determine the 5th POI to be recommended;

Described 5th POI is recommended between each user in described social group.

Preferably,

Described according to described cluster result, extract the first user attribute information to described 3rd POI user interested, comprising:

Add up the distributed intelligence of access customer in specified attribute of described 3rd POI in the 3rd fixed time;

According to described distributed intelligence, determine the first user attribute information to described 3rd POI user interested

The embodiment of the present invention third aspect provides a kind of server, and described server comprises:

First acquiring unit, for obtaining the space time information of the User Activity of each user in social group according to user-generated content;

First determining unit, for determining the core activity space of User Activity in described social group according to described space time information;

Second acquisition unit, for obtaining the POI visit information of each user in described social group according to described user-generated content;

Analytic unit, for analyzing described POI visit information, forms POI analysis result;

First recommendation unit, for the POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group.

Preferably,

Described analytic unit, specifically for determining the visitation frequency of each POI within the first fixed time according to described POI information;

Described first recommendation unit, for the POI selected in described core activity space according to described visitation frequency, recommends to the user in described social group.

Preferably,

Described analytic unit, also for determining the Annual distribution information of each POI accessed frequency within the first fixed time according to described POI information; And according to described visitation frequency and described Annual distribution information, determine to access temperature;

Described first recommendation unit, specifically for recommending POI according to described access temperature to the user in described social group.

Preferably,

Described analytic unit, also for determining the evaluation information of each POI within the first fixed time according to described POI information;

Described first recommendation unit, specifically for recommending POI according to described visitation frequency and described evaluation information to the user in described social group.

Preferably,

Described first recommendation unit, for according to described POI analysis result, selects by the POI accessed in described social group in described core activity space, and the user not accessing a described POI in described social group recommends.

Preferably,

Described first recommendation unit, also for according to described POI analysis result, to select in described core activity space and to meet the 2nd POI of default similarity condition with a described POI, recommending to the user in described social group.

Preferably,

Described server also comprises:

First cluster cell, also for carrying out space clustering according to described space time information to the User Activity in described social group, meeting the first pre-conditioned user and forming clustering cluster by activity space;

Described first determining unit, specifically for the space time information according to each user in a described jth clustering cluster, obtains a jth core activity space;

Described analytic unit, specifically for analyzing described POI visit information, is formed at the jth POI analysis result of a jth clustering cluster;

Described first recommendation unit, specifically for the POI selected in a described jth core activity space according to described jth POI analysis result, recommends to the user in described social group.

Preferably,

Described first determining unit, for determining that according to described space time information the activity space of described social user inside the group is divided into several regions; The access probability information in region described in each is determined according to described space time information; And according to the access probability information in region described in each, determine described core activity space.

Preferably,

Described first determining unit, specifically for according to described space time information, to determine within the second fixed time each user access times in each region in described social group; Calculate the single-user access probability in each user region described in each; According to described single-user access probability, determine the average access probability in region described in each; And according to described average access probability, determine described core activity space.

Preferably,

Described server, also comprises:

Second determining unit, for according to described access times, determines the visitation frequency in described core activity space;

Described first recommendation unit 150, for judging whether the visitation frequency in described core activity space meets default frequency condition; And when the visitation frequency in described core activity space meet visitation frequency pre-conditioned time, the POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group.

Embodiment of the present invention fourth aspect provides a kind of server, and described server comprises:

3rd acquiring unit, for obtaining the POI information of the 3rd POI;

Second cluster cell, for the calling party of described 3rd POI is carried out cluster, forms cluster result;

Extraction unit, for according to described cluster result, extracts the first user attribute information to described 3rd POI user interested;

Forming unit, for forming at least one social group according to described first user attribute information by described calling party.

Preferably,

Described server also comprises:

Second recommendation unit, for recommend and described social user inside the group has accessed the POI that POI associates in described social group.

Preferably,

Described second recommendation unit, specifically for recommending the 4th POI meeting default difference condition with described 3rd POI in described social group.

Preferably,

Described second recommendation unit, also for obtaining the POI visit information of described social user inside the group; According to described visit information, determine the 5th POI to be recommended; And in described social group, between each user, recommend described 5th POI.

Preferably,

Described extraction unit, specifically for adding up the distributed intelligence of access customer in specified attribute of described 3rd POI in the 3rd fixed time; And according to described distributed intelligence, determine the first user attribute information to described 3rd POI user interested.

POI recommend method described in the embodiment of the present invention and server, first select to have user in the social group of strong social association as user to be recommended, the POI information of having accessed according to user again determines the POI recommended, POI is determined according to accessing POI information, obviously what kind of POI requirements for access the user known in this social group is had, improve POI and recommend success ratio.POI information processing method described in the embodiment of the present invention and server, set up social group according to POI; Facilitate the user in social group carry out POI access interchange and to having the operations such as similar POI requirements for access (concrete as, POI recommend) user's Referral POI, be conducive to improving POI equally and recommend success ratio etc.

Accompanying drawing explanation

One of schematic flow sheet that Fig. 1 is the POI recommend method described in the embodiment of the present invention;

Fig. 2 is the schematic diagram of the evaluation information described in the embodiment of the present invention;

Fig. 3 is for recommending the effect schematic diagram of POI based on the method described in the embodiment of the present invention;

One of schematic diagram that Fig. 4 is the core activity space described in the embodiment of the present invention;

Fig. 5 is the schematic flow sheet recommending POI to user in social group described in the embodiment of the present invention;

Fig. 6 is the schematic diagram two in the core activity space described in the embodiment of the present invention;

Fig. 7 is the schematic flow sheet two of the POI recommend method described in the embodiment of the present invention;

One of determination schematic diagram that Fig. 8 is the core activity space described in the embodiment of the present invention;

One of schematic flow sheet that Fig. 9 a is the POI information processing method described in the embodiment of the present invention;

Fig. 9 b is the schematic flow sheet two of the POI information processing method described in the embodiment of the present invention;

One of distributed intelligence schematic diagram that Figure 10 is the specified attribute described in the embodiment of the present invention;

The distributed intelligence schematic diagram two that Figure 11 is the specified attribute described in the embodiment of the present invention;

One of structural representation that Figure 12 is the server described in the embodiment of the present invention;

The structural representation two that Figure 13 is the server described in the embodiment of the present invention;

Figure 14 is the information interaction schematic diagram between the server described in the embodiment of the present invention, client;

The structural representation three that Figure 15 is the server described in the embodiment of the present invention.

Embodiment

Below in conjunction with Figure of description and specific embodiment technical scheme of the present invention done and further elaborate.

Embodiment of the method one:

As shown in Figure 1, the present embodiment provides a kind of POI recommend method, and described method comprises:

Step S110: the space time information obtaining the User Activity of each user in social group according to user-generated content;

Step S120: the core activity space determining User Activity in described social group according to described space time information;

Step S130: the POI visit information obtaining each user in described social group according to described user-generated content;

Step S140: analyze described POI visit information, forms POI analysis result;

Step S150: the POI selected in described core activity space according to described POI analysis result, recommend to the user in described social group.

What described POI was concrete corresponding can be that restaurant, cinema, market or sight spot equal place.

Described user-generated content (Users Generate Content, UGC) is the information formed according to user operation, specifically as the network application of user in Internet and/or the information of web page operation formation.Specifically as user logs in predetermined webpage, as O2O (line is consumed under preset lines) webpage.

Described user-generated content specifically records time of user operation, content of operation, the information such as operand and operational feedback.

In concrete implementation procedure, different users has different hobbies, will like or select accessing different POI, thus will have different POI requirements for access.Specifically if any user likes caring for Hunan cuisine shop, the user that has likes patronizing Guangdong dishes shop; Some users like strolling designer-label store, the user that has likes various par shop.And specifically the most authentic, which Guangdong dishes of the taste in which Hunan cuisine shop do good, need to be patronized temperature by user actual and evaluated to judge.And having the user of same POI requirements for access may because location is different or daily life system is different, the user with identical POI requirements for access is convenient also different to which family POI of access.

Based on These characteristics, known when recommending POI, only recommend the POI meeting user POI requirements for access and could improve recommendation success ratio and acceptance.

The POI how really directional user recommends is the interested POI of user, is meet the POI of user POI requirements for access, in the present embodiment, first selects social group; Described social group can be specifically the friend group etc. of QQ group, micro-letter group, the alumnus group of Renren Network, schoolmates' address book, facebook.Described social group is user's set that at least two users are formed; User in general social group defines user's set based on a certain social networks, concrete as classmate group, based on classmate's relation; Colleague group based on Peer Relationships, friend group based on friends, relatives group based on kinship etc.Popular has strong social networks by between the user in social group, and their life usually involves each other and affects each other, usually can have a meal together, see a film, tourism etc., and these will cause them to have same or analogous POI requirements for access.

But what kind of POI requirements for access is a social group specifically have and will access which POI; Specifically how to determine the POI requirements for access of a social group and which POI will be accessed, will the space time information of social group User Activity being obtained in the present embodiment.Described space time information comprises temporal information and spatial information.

Suppose that described space time information specifically comprises: during xxxx xx month xx day xx, xx divides, and have accessed Haidian District, Beijing City xx movie theatre etc.; Wherein, when described temporal information is xxxx xx month xx day xx, xx divides, and spatial information is Haidian District, Beijing City xx movie theatre; In addition the operation information of user may also be included in described space time information, concrete as information such as accessing, make a reservation for or register.

Described space time information specifically may comprise following at least one of them:

First: the space time information that user's logging in network server produces, as the information of the webserver that user still logs at home in company; Concrete as, the time, IP address, geographic position (geographic name or latitude and longitude information) etc. of user's logging in network server.

Second: the space time information that the information that user accesses POI is formed, as the POI of user's access; Title, the geographic position of the POI registered as user and register the time etc.

Space time information that the trip track that user uploads is corresponding (electronic equipment write with oneself as user obtain user's trip information by alignment sensor, as from company to home or from school to dormitory etc.); Specifically can comprise the region of reference position, final position, on the way process; These information can characterize with geographic name or latitude and longitude information.

Described in concrete implementation procedure, space time information comprises a variety of, just schematically illustrates no longer one by one at this.

A social group is made up of multiple user, the activity space of the user in each social group is not quite similar, but may can form a core activity space based on social networks, the concrete group as formed based on classmate's relation, core activity space may by centered by school, based on the group that Peer Relationships are formed, core activity space may by centered by company.Therefore in the present embodiment by the core activity space according to described space time information determination User Activity; The coverage in concrete core activity space has much, specifically how to determine described core activity space, the concrete scope can crossed according to the spatial information determination User Activity in described space time information, the frequent degree of User Activity can be determined according to described space time information, the scope crossed according to described activity and frequent degree, select frequent degree to meet the region of preset need as described core activity space.In concrete implementation procedure, the information that can also simply fill according to social group is determined, but the core activity spatial precision determined based on the space time information of User Activity provided relative to the present embodiment is low.

User in this social group concrete can like the POI accessing what type, will obtain user's Visitor Logs, and then can obtain POI visit information in the present embodiment according to user-generated content.Described POI visit information, generally includes the attribute information of accessed POI, if concrete dining room, specifically western-style restaurant, Chinese Restaurant, the dining room of which kind; In the information of ordering in dining room, be the information such as dessert or dinner, the cuisine of point as what select.

These POI information have directly reacted hobby and the POI access needs of user, therefore can analyze described POI visit information in the present embodiment, form POI analysis result; Described POI analysis result at least can reflect the POI requirements for access of most of user in social group, thus according to the POI that POI analysis result is selected in core activity space in step S150, recommend to the user in described social group, the POI requirements for access that the POI recommended according to method described in the present embodiment obviously more can be close to the users, received probability is higher, thus the success ratio received can be improved, and improve user's user satisfaction.

Embodiment of the method two:

Step S140: analyze described POI visit information, forms POI analysis result;

Described step S140 specifically can comprise: determine the visitation frequency of each POI within the first fixed time according to described POI information;

Described S150 specifically can comprise: the POI selected in described core activity space according to described visitation frequency, recommends to the user in described social group.

In concrete implementation procedure, according to described POI visit information, the attribute information of social user inside the group POI interested can be analyzed one by one, concrete as Chinese Restaurant or western-style restaurant, to form POI analysis result, the attribute information according to the POI in described POI analysis result recommends POI.But in the present embodiment for simplifying the analysis, analysis be POI visitation frequency.

Concrete as each user in social group, the first fixed time (concrete as two weeks, 1 month, in a season or half a year) access the information of POI, can by the statistics to each POI visitation frequency of statistics within the first fixed time, which the POI that the user that can know in social group likes best access is, thus determines the POI requirements for access of most of user in described social group.

In the present embodiment simply by the visitation frequency of statistics POI, determine that social user inside the group may like accessing which type of POI, simplify information processing; And determine the POI requirements for access of user according to visitation frequency, and degree of accuracy is high.

Embodiment of the method three:

Step S140: analyze described POI visit information, forms POI analysis result;

Describedly according to preset strategy, described POI information to be analyzed, forms POI analysis result, also comprise:

Within the first fixed time, suppose that POI A is the same with the visitation frequency of POI B, but in social group, every day there is user to access POI A; And POI B is very concentrated by the time of the user's access in social group.This situation shows, the hobby of user to POI A has persistent, and the access to POI B may be the factor appearance that POI has preferential activity to wait affect POI visit capacity within the time period that access is concentrated.

Therefore introducing Annual distribution information in the present embodiment, described Annual distribution information can carry out quantization signifying by user time distribution probability.Described Annual distribution probability can be the ratio of the access times of each time quantum and the total access times in the first fixed time in the first fixed time; Concrete as, within the first fixed time, POI A is accessed 1000 times, and wherein, on September 10th, 2014, accessed number of times was 56 times, then can be 56/1000 time at the Annual distribution probability of on September 10th, 2014 this day; To be corresponding duration be described time quantum is less than the time quantum of duration corresponding to described first fixed time, concrete as 1 day, 2 days or 1 week etc.

Will further according to described visitation frequency and time distributed intelligence in the present embodiment, determine to access temperature; Concrete can be access temperature wherein, the Annual distribution function that described f is described visitation frequency, described p (t) is characterization time distributed intelligence, concrete as distribution probability.In concrete implementation procedure, be not limited to above-mentioned funtcional relationship.

The present embodiment carrys out the POI of true directional user recommendation by access temperature, can obtain the POI requirements for access of user further accurately, thus again can improve the probability of the reception POI of user.

Embodiment of the method four:

Step S140: analyze described POI visit information, forms POI analysis result;

After user have accessed a POI, also access POI may can be formed user's evaluation and upload to network.In fig. 2, huang 1077 and 224135 is user name or the user ID of identifying user; The score value that the user that pentagram wherein in diagram represents gets; 3 points, 5 points is the score value corresponding with described 5 jiaos of stars; Comprise the Consumer's Experience impression of user's text description in fig. 2, as " sensation is pretty good ", " very good, next time patronizes again " etc.

Also will comprise evaluation information in the present embodiment, specifically comprise described score value, user's text description etc.Usual score value is higher, shows that user satisfaction is higher, obviously also reflects the POI requirements for access of user from another side; Text description directly gives the access supervisor impression of user, can obtain user specifically evaluate by the mode of keyword extraction.

Therefore in the present embodiment by combining assessment information and visitation frequency, the POI that common really directional user recommends, to improve the probability that user receives recommendation.

Embodiment of the method five:

Step S140: analyze described POI visit information, forms POI analysis result;

Described step S150, comprising:

Concrete as 100 users in social group; Wherein, 50 users are had to have accessed POI C, and POI C is the POI that in social group, visitation frequency makes number one, and user A did not access POI C, before this user A may from social group other with having heard POI C in the registered permanent residence, just never accessed, if recommend POI C to user A, user A may immediately will receive.

In concrete implementation procedure, described step S150 can comprise:

According to described POI analysis result, select in described core activity space by the POI (described POI C) visited in described social group;

Generate the recommendation information of a described POI;

Described POI information is sent to client, and shows in client.

Fig. 3 is the schematic diagram showing described information in client; Wherein, the user of client and little A and little B are the user of same social group, and the part shown in recommendation information in social group accessed the user of described POI C, and after recommended user sees the friend oneself known, it will be larger for receiving the probability recommended.

In concrete implementation procedure, also may add up with recommended user by social networks interaction the most frequently user be presented in recommendation information.

The present embodiment, on the basis of above-described embodiment, defines the POI accessed in social group, recommends in group the user not accessing a POI, again improves the probability that user receives POI recommendation.

Embodiment of the method six:

Step S140: analyze described POI visit information, forms POI analysis result;

Described step S150, comprising:

In concrete implementation procedure, described step S150 comprises the step of the similarity determining a POI and the 2nd POI.Specifically as described in a POI and the 2nd POI all to there being POI attribute information, specifically as property parameters such as the scope of business of POI, POI type or styles; When calculating similarity, the attribute corresponding with the 2nd POI to a POI can be compared, the similarity of both acquisitions; And the similarity of accumulative all properties, obtain the overall similarity of a POI and the 2nd POI.Determined two POI the most similar to a described POI by the mode such as threshold decision or sequencing of similarity, and recommending to user.

Before the similarity determining a POI and the 2nd POI, also comprise the step of the POI attribute information of acquisition the 2nd POI, specifically can obtain a described POI and the 2nd POI from POI storehouse; Described POI information comprises the information such as timetable corresponding to the title of POI, POL type, the average per capita consumption of POI, the geographic position of POI, reached at the mode of transportation of POI open hour and POI and various mode of transportation.

In concrete implementation procedure, the conveniently recommendation of POI, can also set up a POI storehouse for social group; The POI information that POI that social user inside the group often accesses is corresponding is stored in described POI storehouse.

The present embodiment is different from an embodiment: also to the 2nd POI that user in social group recommends user not access in the present embodiment, and same can ensure higher acceptance and successful referral rate.

In step S150 described in the embodiment of the present invention, before recommending POI to user, also comprise and determine user to be recommended, specifically as shown in Figure 4, activity space and the core activity space of social group is determined according to the space time information of each user in social group, recommending success ratio and acceptance to improve POI further, when recommending POI, also determining that those users recommend POI in group; As shown in Figure 5, described step S150 specifically can comprise:

Step S151: according to the central movable space of each user; Specifically if user company and lodging are all at road junction, Haidian District, Beijing City five, the central movable space of usual user is also road junction, Haidian District, Beijing City five;

Step S152: determine that central movable is spatially located at the user in core activity space;

Step S153: according to described POI analysis result, is spatially located at the user in described core activity space to central movable, recommend to be positioned at described core activity space POI.

Concrete as in 4, the central movable space of the central movable space of user B, the central movable space of user C and user D, all in the core activity space of social group, and the central movable space of user A is not in the core activity space of social group, therefore the POI selecting to be positioned at core activity space is when recommending to the user of social group, first get rid of user A, select to recommend to user C, user B and user D.

In a upper embodiment and the present embodiment basis; step S150 also determined that the central movable space of which user is positioned at core activity space before recommendation POI; the POI that user in core activity space recommends to be positioned at core activity space is spatially located to central movable; after user receives POI recommendation information by client; find that this POI is positioned at its often movable scope, the probability obviously received can be higher.

The concrete central movable space how determining user, can see the determination in the core activity space of social group.

Embodiment of the method seven:

Step S140: analyze described POI visit information, forms POI analysis result;

Described method also comprises:

According to described space time information, space clustering is carried out to the User Activity in described social group, activity space is met the first pre-conditioned user and form clustering cluster.

Described step S130 can comprise:

As shown in Figure 6, according to the space time information of user, social group activity space can be determined, obtained the core activity space of each clustering cluster in 4 clustering cluster by cluster.In figure 6, the 1st clustering cluster is corresponding 1st core activity space, the 2nd clustering cluster are corresponding 2nd core activity space, the 3rd clustering cluster are corresponding 3rd core activity space and corresponding 4th the core activity space of the 4th clustering cluster.

Described step S150 can comprise:

Described step S160 comprises:

Each clustering cluster corresponding forms a POI analysis result and recommends POI respectively again, obviously can improve recommendation success ratio again like this.

Concrete as university's social group, after graduating from university, everybody is distributed in each place, for example social group comprises 100 users, wherein stay Haidian District Beijing for 45,13 at Chaoyang District Beijing, 26 in Futian Area of Shenzhen City, Guangdong Province, other users disperse distribution, and now this customer group at least can form 3 clustering cluster; The core activity space of these clustering cluster corresponding can be Haidian District Beijing, Chaoyang District Beijing and Futian Area of Shenzhen City, Guangdong Province.

In units of clustering cluster, information processing and POI recommendation is carried out when POI respectively concrete recommendation.

By clustering processing in the present embodiment, the success ratio of recommendation again can be improved.

Embodiment of the method eight:

As shown in Figure 7, the present embodiment provides a kind of POI recommend method, and described method comprises:

Step S120: the core activity space determining User Activity in described social group according to described space time information; Described step S120 specifically comprises: step S121: determine that the activity space of described social user inside the group is divided into several regions according to described space time information; Step S122: the access probability information determining region described in each according to described space time information; And step S123: according to the access probability information in region described in each, determine described core activity space;

Step S140: analyze described POI visit information, forms POI analysis result;

Specifically provide a kind of method how determining core activity space in the present embodiment, determine described core activity frequency by access probability information, have and calculate easy and accurately can obtain the advantage in core activity space.

The specific implementation of described step S122 breath has multiple, below provides two kinds of optimal ways:

The first:

The visitation frequency of statistics regional;

Obtain the ratio of total visitation frequency of the visitation frequency in each region and the activity space of social group, obtain described access probability west and pinch.

The second:

Described second fixed time can be the time realizing specifying, be specifically as follows 1 month, 3 months or half a year, the core activity spatial variations of a usual social group is little relative to the rate of change of user to the access of POI, therefore the duration that described second fixed time is corresponding usually can specify than described first the duration that duration is corresponding, be preferably for the second fixed time identical with the stop time point of the first fixed time, be preferably current time.

It is little and solve simple advantage that first kind of way has calculated amount, solving of the second way, by the access probability that the weighted sum of each user's access probability obtains, avoid the high individual user of visitation frequency to affect the out of true of the determination of social group inner core activity space, thus improve degree of accuracy.Concrete as comprised 50 users in social group, be 200 times in the POI access times of the first fixed time, wherein, occur in the access behavior of 5 users for 150 times.Other 45 clients also have 50 access; and concentrate in a presumptive area; can be because 5 clients have 150 visiting distribution local at other; if directly with the access probability in each region for determining the foundation in the core activity space of social group; the phenomenon that region that wherein 45 people are often movable occurs not in core activity space can be caused, thus adopt second method with unique user at regional access probability for according to determining that the degree of accuracy in described core access space is higher.

Below provide one based on the determination example in the core activity space of the second way, as shown in Figure 8, specifically comprise:

Step S1: the positional information obtaining User Activity; Described positional information can obtain from (place name of client ip address, User Activity position, the POI accessed, latitude and longitude coordinates) information; Preferably convert described positional information to longitude and latitude.

Step S2: by map grid corresponding for the activity space of User Activity each in social group, formation rule graticule mesh; Described specification grid is above-mentioned region; Concrete as, form the grid of 30 " * 30 " (being similar to 1km*1km);

Step S3: calculate an xth user U in social group _xthe access probability p at a kth grid _x(k); In concrete implementation procedure, access tlv triple { <L (k), p can be formed _x(k), w _xk wherein, described L (k) can be the coordinate of a kth grid element center point to () >}; Described w _xk () is an xth U _xat the visitation frequency of a kth grid.

Step S4: according to the average access probability of following formulae discovery regional;

described N is total number of users in social group;

Wherein, described in for the access probability of a kth grid.

Step S5: according to described access probability, determines core activity region.Concrete as, utilize Spatial Interpolation Method, with interpolation radius R ₀and the border W in given access probability threshold value determination core activity space _core; Border W _corewithin region be described core activity space.Described Spatial Interpolation Method can be interpolation algorithm or ordinary kriging interpolation algorithm; Described interpolation radius is the radius pre-set, concrete as 30 " etc.

The present embodiment puies forward the method specifically how determining core activity space, for determining the mode in core activity space in social group in the present embodiment, also may be used for the determination in the determination in the central movable space of user in above-described embodiment and core activity space corresponding to clustering cluster.

Embodiment of the method nine:

Step S140: analyze described POI visit information, forms POI analysis result;

Described step S122 specifically can comprise:

Describedly also to comprise:

Suppose that described second specifies duration to be 1 month; Visitation frequency in the core activity space of the first social group is 3 times, visitation frequency in the core activity space of the second social group is 50 times, in obvious first social group, visitation frequency is less, the user of obvious second social group is in life, work and learning process, more rely on social group and network, more can receive the recommendation of POI.

Therefore in the present embodiment in order to the probability that the reception POI improving user further recommends, on the basis of a upper embodiment, after described step S5, described method also comprises:

Step S6: calculate an xth U _xat the visitation frequency Ω of each grid _x, according to Ω _xdetermine the visitation frequency in described core activity space.、

Embodiment of the method ten:

As illustrated in fig. 9, the present embodiment provides a kind of POI recommend method, and described method comprises:

Step S210: the POI information obtaining the 3rd POI;

Step S220: the calling party of described 3rd POI is carried out cluster, forms cluster result;

Step S230: according to described cluster result, extracts the first user attribute information to described 3rd POI user interested;

Step S240: described calling party is formed at least one social group according to described first user attribute information.

After each business a period of time, will form the customer group of its correspondence, these customer groups often have much similar attribute information, specifically as the main coverage etc. of age bracket, consumption level and POI.

Described 3rd POI can be any one POI in the present embodiment, and the cluster in described step S220 comprises the information such as main coverage, customer consumption level and age of user section.

To the user of same POI be accessed, formed at least one social group.Concrete like accessing dining room A working day as some user; The nonworkdays of liking had accesses dining room A; The user accessing dining room A working day is the crowd worked near the A of dining room mostly; The user of nonworkdays access dining room A stays in the user near the A of dining room, conveniently recommends POI, can form two groups, so that time segment is the POI that two customer groups are recommended.

If the user accessing the 3rd POI for another example has 3000; Wherein the level of consumption of 500 is first grade; 600 is second gear; Obviously two groups can be also divided into according to the difference of the level of consumption of user; Recommend to distinguish according to the level of consumption of user during the 4th POI similar to the 3rd POI to the user in social group follow-up; Similarity may be had more due to what there is the user of the identical level of consumption, in the process of subsequent access dining room A, may occur the phenomenon of sharing a table with stranger and all make an appointment and together access a POI etc., obviously these users are recommended as a social group, the similarity of the user in group can be made higher, thus the similarity of the requirements for access of POI is also higher, thus the recommendation of POI can be facilitated.In concrete implementation procedure, described social group is not limited to for carrying out POI recommendation, and the user in described social group can also by described social group, exchanges POI access impression, mutually recommends POI or or to exchange and POI accesses unconnected information etc.

The user accessing same POI is set up social group by the present embodiment, and the user facilitating same or similar POI requirements for access is exchanged by described social group, thus can enliven the interchange between interchange and user of accessing about POI.

In concrete realization, as described in Fig. 9 b, method also can comprise:

Step S250: recommendation and described social user inside the group have accessed the POI that POI associates in described social group.Described social user inside the group has accessed POI and has comprised POI for user in set up social group accessed; Concrete as, described 3rd POI.

Present embodiments provide the recommend method of a kind of POI, the POI that be equally based on social group this strong incidence relation the same as embodiment of the method one recommends, and accesses same POI formed unlike the social group described in the present embodiment based on user; But same having can improve the advantage that POI recommends success ratio.

Described step S250 can comprise:

The difference of described POI can relatively determining by the attribute information of the 3rd POI and the 4th POI, also can convert the attribute information of described 3rd POI and the 4th POI to comprise multiple element vector; By the distance between vector, or the mode such as cluster computing determines the otherness of the 3rd POI and the 4th POI, similar less as the 3rd POI and the 4th POI, then user access the satisfaction of the 4th POI may be suitable with the satisfaction of access the 3rd POI.

Described step S250 also can comprise:

Obtain the POI visit information of described social user inside the group;

Described 5th POI is recommended between each user in described social group.

Based on the social group that the 3rd POI is formed, except accessing the 3rd POI, also can will form described POI visit information by other POI of orientation, according to described POI visit information, can determine which POI social user inside the group may access maybe may be interested in which POI.

Specifically how to determine described 5th POI, see the embodiment of the present invention one to embodiment of the method nine, just no longer can do elaboration detailed further at this.

Embodiment of the method 11:

Step S210: the POI information obtaining the 3rd POI;

Described step S230 can comprise:

According to described distributed intelligence, determine the first user attribute information to described 3rd POI user interested.

Described distributed intelligence can quantize with distribution probability, can also the number of user quantize.

The age of the concrete user as added up access the 3rd POI in Figure 10, by the age illustrating known calling party 18-23 year and 23-28 year these two age brackets.As shown in figure 11, the level of consumption of calling party concentrates between second gear and third gear; According to the distributed intelligence of Figure 10 and Figure 11 in age and these two specified attribute of the level of consumption, described first user attribute information can be known.

Can 4 social group by the calling party of accessing the 3rd POI; The age of first social group, the level of consumption was second gear between 18-23 year; The age of second social group, the level of consumption was third gear between 23-28; The age of the 3rd social group, the level of consumption was second gear between 23-28 year; The age of the 4th social group, the level of consumption was third gear between 18-23 year.In concrete implementation procedure, directly can also carry out a relatively large social group, the user's age in this social group, then the level of consumption was second gear and third gear at 18 to 28 years old.

In concrete implementation procedure, can also determine to form described social group according to the distributed intelligence of the specified attribute in conjunction with 3 specified attribute or more than 3.

Provide a kind of method specifically how forming described social group in the present embodiment, have and realize simply, can accurately obtaining the social group with identical requirements for access, the recommendation of follow-up POI can being convenient to, recommend success ratio so that POI can be improved.

Apparatus embodiments one:

As shown in figure 12, the present embodiment provides a kind of server, and described server comprises:

First acquiring unit 110, for obtaining the space time information of the User Activity of each user in social group according to user-generated content;

First determining unit 120, for determining the core activity space of User Activity in described social group according to described space time information;

Second acquisition unit 130, for obtaining the POI visit information of each user in described social group according to described user-generated content;

Analytic unit 140, for analyzing described POI visit information, forms POI analysis result;

First recommendation unit 150, for the POI selected in described core activity space according to described POI analysis result, recommends to the user in described social group.

The concrete structure of described first acquiring unit 110 is different according to the difference of the mode of the described space time information of described acquisition, and by inquiry storage medium, then described first acquiring unit 110 may comprise storage medium and inquire about the processor of described storage medium; If receive from client or receive from user-generated content server, then described first acquiring unit 110 comprises communication interface.Described communication interface can be specifically wired communication interface or wireless communication interface; Wired communication interface is as twisted-pair communication interface; Described wireless communication interface can be specifically the structures such as dual-mode antenna.

The concrete structure of described first determining unit 120, analytic unit 130 and the first recommendation unit 150 may correspond in processor.Described processor is specifically as follows central processor CPU, Micro-processor MCV, digital signal processor DSP or programmable logic device (PLD) PLC etc. and has the electronic devices and components of processing capacity or the set of electronic devices and components.Wherein, described executable code is stored in storage medium, described processor can be connected with described storage medium by communication interfaces such as buses, at the analytical capabilities of execution correspondence and when generating described first play cuing information, read from described storage medium and run described executable code.Described storage medium is preferably non-moment storage medium for the part storing described executable code.

Described first determining unit 120, analytic unit 130 and the first recommendation unit 150, can comprise different processors respectively, also can the same processor of integrated correspondence; When described first determining unit 120, analytic unit 130 and the first recommendation unit 150 are integrated correspond to same processor time, when described processor adopts different, divisional processing or concurrent thread are to process the information of different units.

Figure 13 provides the another kind of structural drawing of server described in the present embodiment; As shown in figure 13, described server comprises processor 302, storage medium 304 and at least one external communication interface 301; Described processor 302, storage medium 304 and external communication interface 301 are all connected by bus 303.Described processor 302 can be the electronic devices and components that microprocessor, central processing unit, digital signal processor or programmable logic array etc. have processing capacity.

Described external communication interface 301 for carrying out information interaction with other electronic equipments, such as, communicates with client, communicates with other webservers.Described bus 303 is the link of server internal.

Described processor 302, by running executable instruction, controlling the information processing of information interaction between described external communication interface, storage medium and bus and described processor 302 inside, realizing the function of above-mentioned unit.

As shown in figure 14, for recommending the server of POI to can be described as recommendation server in the present embodiment, described user content can exist in its storage medium by recommendation server, also can be received by the external communication interface 301 shown in Figure 13 from client or user content server; First recommendation unit of described recommendation server will form recommendation information, and described recommendation information is sent to client by described external communication interface 301.When described user-generated content is stored in client or user content generation server, the feature that the storage data volume in described recommendation server is little.When described user-generated content is stored in recommendation server, then the information interaction amount of the peripheral hardware such as described recommendation server and client is little, specifically how to arrange and can determine according to the hardware configuration of current network.

Server described in the present embodiment is the POI recommend method described in embodiment of the method one, provides and realizes hardware, can be used for technical scheme described arbitrarily in implementation method embodiment one; Same has the advantage of recommending success ratio high.

Apparatus embodiments two:

The visitation frequency that the present embodiment analytic unit is specifically added up, the first recommendation unit specifically really selects the POI in core activity space to recommend to the user in social group according to described visitation frequency; Specifically define in an embodiment and recommend POI, while there is the high advantage of recommendation success ratio, also have and realize easy advantage.

In the present embodiment in order to obtain the POI requirements for access of user further accurately, to improve POI recommending success ratio, the present embodiment, also by the basis of above-described embodiment, provides two kinds of preferred structures further:

The first:

Described analytic unit 140, also for determining the Annual distribution information of each POI accessed frequency within the first fixed time according to described POI information; And according to described visitation frequency and described Annual distribution information, determine to access temperature;

Described first recommendation unit 150, specifically for recommending POI according to described access temperature to the user in described social group.

The second:

Described analytic unit 140, also for determining the evaluation information of each POI within the first fixed time according to described POI information;

Described first recommendation unit 150, specifically for recommending POI according to described visitation frequency and described evaluation information to the user in described social group.

The present embodiment is on the basis of visitation frequency, also introduce Annual distribution information and evaluation information to determine POI to be recommended, Annual distribution information and evaluation information reflect user POI requirements for access from different dimensions, again can improve and recommend success ratio and user satisfaction.

Apparatus embodiments three:

It is multiple that described first recommendation unit 150 recommends the mode of POI to have, and corresponding structure also has multiple, thus server is also different from the interactive mode of client; Be connected by network between server with client described in concrete implementation procedure, described network can be wired network or wireless network.

The preferred structure of two kinds of described first recommendation unit 150 is below provided;

The first: described first recommendation unit 150, for according to described POI analysis result, select by the POI accessed in described social group in described core activity space, the user not accessing a described POI in described social group recommends.

The second: described first recommendation unit 150, also for according to described POI analysis result, to select in described core activity space and to meet the 2nd POI of default similarity condition with a described POI, recommending to the user in described social group.

What the present embodiment was concrete for the POI recommendation described in embodiment of the method provides realizes hardware, and described server can be specifically QQ net purchase server/or micro-letter subscription server.

Apparatus embodiments four:

Described server also comprises the first cluster cell; Described first cluster cell, also for carrying out space clustering according to described space time information to the User Activity in described social group, meeting the first pre-conditioned user and forming clustering cluster by activity space;

Described first determining unit 120, specifically for the space time information according to each user in a described jth clustering cluster, obtains a jth core activity space;

Described analytic unit 140, specifically for analyzing described POI visit information, is formed at the jth POI analysis result of a jth clustering cluster;

Described first recommendation unit 150, specifically for the POI selected in a described jth core activity space according to described jth POI analysis result, recommends to the user in described social group.

Described first cluster cell specifically can be undertaken having lifted by K-meas cluster, density based cluster or the method such as cluster based on distance.What the concrete structure of described first cluster cell was same comprises processor, and the processor that comprises of described first cluster cell can with the integrated corresponding same processors such as the first recommendation unit 150 and/or the first determining unit 120.

POI described in the present embodiment is the POI recommend method described in said method embodiment, provides and realizes hardware; The same POI that has recommends the advantage that success ratio is high and user's user satisfaction is high.

Apparatus embodiments five:

Described first determining unit 120, for determining that according to described space time information the activity space of described social user inside the group is divided into several regions; The access probability information in region described in each is determined according to described space time information; And according to the access probability information in region described in each, determine described core activity space.

Described in the present embodiment, the concrete structure of the first determining unit 120 is see above-described embodiment, has just repeated no more at this.It is according to access probability information determination core activity space that the present embodiment specifically defines described first determining unit 120, realizes hardware for the POI recommend method described in embodiment of the method provides.

Apparatus embodiments six:

Described server, also comprises:

Server described in the present embodiment also comprises the second determining unit, and what the concrete structure of described second determining unit was same may correspond to various forms of processor.

Described in the present embodiment, the first recommendation unit 150 is relative to the server described in above-mentioned any embodiment, when recommending POI, whether what reached by the visitation frequency in each the core activity space first judging this social group is pre-conditioned, concrete as reached predetermined threshold value etc.; Determining whether to need to recommend POI between the user in social group or clustering cluster, recommend acceptance and user's user satisfaction again to improve POI.

Apparatus embodiments seven:

As shown in figure 15, the present embodiment provides a kind of server, and described server comprises:

Described server comprises:

3rd acquiring unit 210, for obtaining the POI information of the 3rd POI;

Second cluster cell 220, for the calling party of described 3rd POI is carried out cluster, forms cluster result;

Extraction unit 230, for according to described cluster result, extracts the first user attribute information to described 3rd POI user interested;

Forming unit 240, for forming at least one social group according to described first user attribute information by described calling party.

The POI information of described 3rd POI can obtain from POI storehouse; Described POI storehouse is the database of the POI information of each POI.

The social group that described forming unit 240 unit is formed, the user can be convenient in social group carries out various forms of interchange, as exchanged POI access impression etc.; Also be convenient to, in POI recommendation process, in units of social group, in social group, recommend POI etc.

In some instances, described server also comprises:

Second recommendation unit, for the POI recommending described social user inside the group to access POI association in described social group.

The concrete structure of described 3rd acquiring unit 210 is different according to obtain manner difference, and as information as described in inquiry from POI storehouse, then described 3rd acquiring unit 210 comprises various forms of external communication interface; When the part storage medium in described server is described POI storehouse, then described 3rd acquiring unit 210 is the message structure that processor etc. can access described storage medium.

The concrete structure of described extraction unit 220, forming unit 240 and the second recommendation unit also comprises processor and storage medium; Described storage medium stores computer executable instructions; Described processor is connected with storage medium by the internal communications interface of the servers such as data bus, and described processor reads and runs described computer executable instructions, can realize the function of above-mentioned unit.

The concrete structure of the server described in the present embodiment, also can be as shown in Figure 13 by structures such as processor 301, storage medium 304, bus 303 and external communication interface 301, server described in the embodiment of the present invention realizes hardware for the POI recommend method described in embodiment of the method ten provides, and same having can improve the advantage that POI recommends success ratio and user's user satisfaction.

Apparatus embodiments eight:

Described server comprises:

3rd acquiring unit 210, for obtaining the POI information of the 3rd POI;

Forming unit 240, for forming at least one social group according to described first user attribute information by described calling party;

Particularly, described second recommendation unit recommends the mode of POI to have multiple, and corresponding structure is also different; Two kinds of preferred structures are below provided:

The first: described second recommendation unit, specifically for recommending the 4th POI meeting default difference condition with described 3rd POI in described social group.

The second: described second recommendation unit, also for obtaining the POI visit information of described social user inside the group; According to described visit information, determine the 5th POI to be recommended; And in described social group, between each user, recommend described 5th POI.

The concrete structure of described second recommendation unit see the said equipment embodiment, just no longer can illustrate at this.In concrete implementation procedure, described second recommendation unit is sent to client by by the external communication interface in described server by recommending the recommendation information of described 4th POI and/or the 5th POI.

Comprehensively above-mentioned, the server described in the present embodiment, on the basis of above-mentioned any described embodiment, specifically defines the POI how the second recommendation unit is determined to recommend in social group; The advantage that success ratio is high and user satisfaction is high is recommended in same having.

Apparatus embodiments nine:

Described server comprises:

3rd acquiring unit 210, for obtaining the POI information of the 3rd POI;

Described extraction unit 230, specifically for adding up the distributed intelligence of access customer in specified attribute of described 3rd POI in the 3rd fixed time; And according to described distributed intelligence, determine the first user attribute information to described 3rd POI user interested.

The concrete structure of described extraction unit 230 can comprise counter, for counting the access customer number of each appointed information, and then obtains described distributed intelligence; Described distributed intelligence end user distribution number or distribution probability carry out quantization means.The concrete structure of described extraction unit 230 also comprises message handler; Described message handler can be the structures such as digital signal processor, central processing unit, microprocessor or programmable logic processor PLC.

Server described in the present embodiment determines the first user attribute information to the 3rd POI user interested according to the distributed intelligence of specified attribute, has server architecture simple and realize simple advantage.

In several embodiments that the application provides, should be understood that disclosed equipment and method can realize by another way.Apparatus embodiments described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, and as: multiple unit or assembly can be in conjunction with, maybe can be integrated into another system, or some features can be ignored, or do not perform.In addition, the coupling each other of shown or discussed each ingredient or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of equipment or unit or communication connection can be electrical, machinery or other form.

The above-mentioned unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, also can be distributed in multiple network element; Part or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.

In addition, each functional unit in various embodiments of the present invention can all be integrated in a processing module, also can be each unit individually as a unit, also can two or more unit in a unit integrated; Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.

One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that programmed instruction is relevant, aforesaid program can be stored in a computer read/write memory medium, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: movable storage device, ROM (read-only memory) (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. various can be program code stored medium.

The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.

Claims

1. a POI recommend method, is characterized in that, described method comprises:

Described POI visit information is analyzed, forms POI analysis result;

2. method according to claim 1, is characterized in that,

3. method according to claim 2, is characterized in that,

4. method according to claim 2, is characterized in that,

5. method according to claim 1, is characterized in that,

6. method according to claim 5, is characterized in that,

7. method according to claim 1, is characterized in that,

Described method also comprises:

8. method according to claim 1, is characterized in that,

9. method according to claim 8, is characterized in that,

10. method according to claim 9, is characterized in that,

Describedly also to comprise:

11. 1 kinds of POI information processing methods, is characterized in that,

Described method comprises:

Obtain the POI information of the 3rd POI;

12. methods according to claim 11, is characterized in that,

Described method also comprises:

13. methods according to claim 12, is characterized in that,

14. methods according to claim 12, is characterized in that,

Obtain the POI visit information of described social user inside the group;

Described 5th POI is recommended between each user in described social group.

15. methods according to claim 14, is characterized in that,

16. 1 kinds of servers, is characterized in that, described server comprises:

17. servers according to claim 16, is characterized in that,

18. servers according to claim 17, is characterized in that,

19. servers according to claim 17, is characterized in that,

20. servers according to claim 16, is characterized in that,

21. servers according to claim 20, is characterized in that,

22. servers according to claim 16, is characterized in that,

Described server also comprises:

23. servers according to claim 16, is characterized in that,

24. servers according to claim 23, is characterized in that,

25. servers according to claim 23, is characterized in that,

Described server, also comprises:

26. 1 kinds of servers, is characterized in that,

Described server comprises:

3rd acquiring unit, for obtaining the POI information of the 3rd POI;

27. servers according to claim 26, is characterized in that,

Described server also comprises:

28. servers according to claim 27, is characterized in that,

29. servers according to claim 27, is characterized in that,

30. servers according to claim 26, is characterized in that,