CN104408043A - Information processing method and server - Google Patents

Abstract

The invention discloses an information processing method and a server, wherein the method comprises the following steps that: the user time and space activity information of each user in a group is obtained according to UGCs (Users Generate Contents); first information is determined according to the user time and space activity information, and a first screening parameter is determined according to the first information; the first information is used for representing the user change in the space dimension; second information is determined according to the user time and space activity information, and a second screening parameter is determined according to the second information; the second information is used for representing the user change in the time dimension; and the first screening parameter and/or the second screening parameter are/is selected from a screening parameter set according to preset strategies, and a target user best matched with a first user is screened from a candidate user group corresponding to the first user in the group according to the first screening parameter and/or the second screening parameter.

Description

A kind of information processing method and server

Technical field

The present invention relates to the mechanics of communication of internet arena, particularly relate to a kind of information processing method and server.

Background technology

Present inventor, in the process realizing the embodiment of the present application technical scheme, at least finds to there is following technical matters in correlation technique:

Current internet development is rapid, and interpersonal communication exchange channel is more and more abundanter.Wherein the various friend-making mode such as blog, space, microblogging, micro-letter, in time communication and platform become the social irreplaceable part of people already, which together form the social networks of complexity on network.

The rise of social networks, widen the friend-making scope between people to a great extent, user can be familiar with more people in social network-i i-platform, how effectively to find the good friend of suitable contacts, become research topic important at present, based on this problem, the demand of friend recommendation function is more and more important.And in existing friend recommendation method, conventional comprises: 1) mate according to the essential information of fill data during user's login account, carry out friend recommendation based on similarity height afterwards; 2) friend recommendation is carried out according to the distance of orientation distance between user; 3) friend recommendation is carried out in the mode of the good friend of commending friends.

Following problem is there is in prior art:

One, for such scheme 1) for, there is the possibility that information is incomplete or information is false in the basic document filled in due to user, iff carrying out the similarity mating and recommend be able to not to reflect well user's real information based on these essential informations, cause the precision carrying out friend recommendation not high;

Two, for such scheme 2) for, the distance of distance well can not recommend suitable potential good friend, and the precision carrying out friend recommendation also can be caused not high;

Three, for such scheme 3) for, the good friend of good friend might not be the potential good friend of user, carries out friend recommendation by this way, and the precision carrying out friend recommendation can be caused too not high.

Summary of the invention

In view of this, the embodiment of the present invention is desirable to provide a kind of information processing method and server, solve at least the problems referred to above that prior art exists, thus improve the precision of friend recommendation, the good friend of suitable contacts accurately, effectively can be found to provide higher success ratio for user.

The technical scheme of the embodiment of the present invention is achieved in that

Embodiments provide a kind of information processing method, described method comprises:

User's spatio-temporal activity information of each user in group is obtained according to user-generated content;

According to described user's spatio-temporal activity information determination first information, determine the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Determine the second information according to described user's spatio-temporal activity information, determine the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

To concentrate from screening parameter according to preset strategy and choose described first screening parameter and/or described second screening parameter, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

In such scheme, described method also comprises:

Three screening parameter is determined according to described first screening parameter and described second screening parameter;

Screening parameter described in described three screening parameter read-in is concentrated, from candidate user group corresponding to the first user described group, filters out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter and/or described three screening parameter further.

In such scheme, the described user's spatio-temporal activity information obtaining each user in group according to user-generated content, comprises with one or more of under type:

Mode one: search user and log in and exit the spatio-temporal activity information that server produces in described user-generated content;

Mode two: search the spatio-temporal activity information that user and server communication produce in described user-generated content;

Mode three: search the spatio-temporal activity information of user about registering produced in described user-generated content;

Mode four: search user and upload about the spatio-temporal activity information that produces of trip track in described user-generated content.

In such scheme, describedly in described user-generated content, search user log in and exit the spatio-temporal activity information that server produces, comprising:

The log information being logged in and exit application APP by recording user is searched and is obtained described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: user's history logs in and exit the temporal information and/or Internet protocol IP address information and/or cellular base station information and/or GPS information and/or information of place names and/or WIFI information of applying APP.

In such scheme, describedly in described user-generated content, search the spatio-temporal activity information that user and server communication produce comprise:

In use APP process, handshaking procedures in send information searching is kept to obtain described spatio-temporal activity information according to assigned frequency and server by recording user;

Described spatio-temporal activity information at least comprises: user and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information.

In such scheme, describedly in described user-generated content, search the spatio-temporal activity information of user about registering produced;

APP active upload is used to obtain described spatio-temporal activity information to the information searching of registering of server by recording user;

Described spatio-temporal activity information at least comprises: user registers the POI information of point of interest and/or temporal information and/or geographical location information and/or Word message and/or pictorial information.

In such scheme, describedly in described user-generated content, search user upload about the spatio-temporal activity information that produces of trip track comprises:

Use APP active upload to search to the trace information of server by recording user and obtain described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographical location information; And/or

The POI information of user's trajectory paths point between Origin And Destination and/or temporal information and/or geographical location information.

In such scheme, described according to described user's spatio-temporal activity information determination first information, comprising:

Relate to the extraction of spatial information of Spatial Dimension out by described user's spatio-temporal activity information, and isolate explicit spatial information and the spatial information of implicit expression;

After the spatial information of described implicit expression is converted into explicit spatial information, described explicit spatial information is obtained the second sampled point of gridding as the first sampled point by mesh mapping resampling;

By the coordinate of described second sampled point according to user's accessing points and the frequency of accessing points, generate the spatial dimension of User Activity and Density Distribution by the interpolation strategies preset, and using the spatial dimension of described User Activity and Density Distribution as the described first information.

In such scheme, describedly determine the first screening parameter according to the described first information, comprising:

Judge whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result;

When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Obtain all users in the candidate user group corresponding with described first user;

The User Activity space distribution index of similarity of all users respectively and between described first user according to the spatial dimension of described User Activity and Density Distribution computing, and using described User Activity space distribution index of similarity as described first screening parameter.

In such scheme, describedly determine the second information according to described user's spatio-temporal activity information, comprising:

Relate to the extraction of spatial information of time dimension out by described user's spatio-temporal activity information, carry out from high to Low sequence to all accessing points of the user in the spatial information extracted according to its access frequency, obtain the access point set after sorting;

Travel through each point that the accessing points after described sequence is concentrated successively, obtain the accumulated probability of each point, when the accumulated probability of described each point is greater than a threshold value, the point being greater than described threshold value is designated as user and resides accessing points;

Reside by described user the space-time track sets that accessing points generates user's common activities after traversal terminates, and using the space-time track sets of described user's common activities as described second information.

In such scheme, describedly determine the second screening parameter according to described second information, comprising:

Judge whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result;

When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Obtain all users in the candidate user group corresponding with described first user;

The user space-time track index of similarity of all users respectively and between described first user according to the space-time track sets computing of described user's common activities, and using described user's space-time track index of similarity as described second screening parameter.

Embodiments provide a kind of server, described server comprises:

Acquisition module, for obtaining user's spatio-temporal activity information of each user in group according to user-generated content;

First determination module, for according to described user's spatio-temporal activity information determination first information, determines the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Second determination module, for determining the second information according to described user's spatio-temporal activity information, determines the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

Processing module, choosing described first screening parameter and/or described second screening parameter for concentrating from screening parameter according to preset strategy, from candidate user group corresponding to the first user described group, filtering out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

In such scheme, described server also comprises:

3rd determination module, for determining three screening parameter according to described first screening parameter and described second screening parameter;

Processing module, be further used for screening parameter described in described three screening parameter read-in to concentrate, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter and/or described three screening parameter further.

In such scheme, described acquisition module, is further used for adopting the user's spatio-temporal activity information comprising and obtain each user in groups with one or more of under type:

Mode one: search user and log in and exit the spatio-temporal activity information that server produces in described user-generated content;

Mode two: search the spatio-temporal activity information that user and server communication produce in described user-generated content;

Mode three: search the spatio-temporal activity information of user about registering produced in described user-generated content;

Mode four: search user and upload about the spatio-temporal activity information that produces of trip track in described user-generated content.

In such scheme, described acquisition module also comprises:

First searches submodule, and the log information for being logged in and exit application APP by recording user is searched and obtained described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: user's history logs in and exit the temporal information and/or Internet protocol IP address information and/or cellular base station information and/or GPS information and/or information of place names and/or WIFI information of applying APP.

In such scheme, described acquisition module also comprises:

Second searches submodule, for keeping the information searching that in handshaking procedures send to obtain described spatio-temporal activity information according to assigned frequency and server by recording user in use APP process;

Described spatio-temporal activity information at least comprises: user and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information.

In such scheme, described acquisition module also comprises:

3rd searches submodule, searches the spatio-temporal activity information of user about registering produced for described in described user-generated content;

APP active upload is used to obtain described spatio-temporal activity information to the information searching of registering of server by recording user;

Described spatio-temporal activity information at least comprises: user registers the POI information of point of interest and/or temporal information and/or geographical location information and/or Word message and/or pictorial information.

In such scheme, described acquisition module also comprises:

4th searches submodule, to search obtain described spatio-temporal activity information for being used APP active upload by recording user to the trace information of server;

Described spatio-temporal activity information at least comprises: the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographical location information; And/or

The POI information of user's trajectory paths point between Origin And Destination and/or temporal information and/or geographical location information.

In such scheme, described first determination module also comprises:

First extracts submodule, for relating to the extraction of spatial information of Spatial Dimension out by described user's spatio-temporal activity information, and isolates explicit spatial information and the spatial information of implicit expression;

Mapping submodule, after the spatial information of described implicit expression is converted into explicit spatial information, obtains the second sampled point of gridding using described explicit spatial information as the first sampled point by mesh mapping resampling;

The first information generates submodule, for by the coordinate of described second sampled point according to user's accessing points and the frequency of accessing points, the spatial dimension of User Activity and Density Distribution is generated by the interpolation strategies preset, and using the spatial dimension of described User Activity and Density Distribution as the described first information.

In such scheme, described first determination module also comprises:

First judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

First obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

First similarity exponent arithmetic submodule, for the User Activity space distribution index of similarity of all users respectively and between described first user according to the spatial dimension of described User Activity and Density Distribution computing, and using described User Activity space distribution index of similarity as described first screening parameter.

In such scheme, described second determination module also comprises:

Second extracts submodule, for relating to the extraction of spatial information of time dimension out by described user's spatio-temporal activity information, carry out from high to Low sequence to all accessing points of the user in the spatial information extracted according to its access frequency, obtain the access point set after sorting;

Traversal searches submodule, for traveling through each point that the accessing points after described sequence is concentrated successively, obtaining the accumulated probability of each point, when the accumulated probability of described each point is greater than a threshold value, the point being greater than described threshold value is designated as user and resides accessing points;

Second information generates submodule, for travel through terminate after reside by described user the space-time track sets that accessing points generates user common activities, and using the space-time track sets of described user's common activities as described second information.

In such scheme, described second determination module also comprises:

Second judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Second obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

Second similarity exponent arithmetic submodule, for the user space-time track index of similarity of all users according to the space-time track sets computing of described user's common activities respectively and between described first user, and using described user's space-time track index of similarity as described second screening parameter.

The information processing method of the embodiment of the present invention comprises: the user's spatio-temporal activity information obtaining each user in group according to user-generated content; According to described user's spatio-temporal activity information determination first information, determine the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension; Determine the second information according to described user's spatio-temporal activity information, determine the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension; To concentrate from screening parameter according to preset strategy and choose described first screening parameter and/or described second screening parameter, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

Adopt the embodiment of the present invention, the first corresponding screening parameter and the second screening parameter is obtained further by the first information and the second information characterizing these two different dimensions of room and time respectively, from candidate user group corresponding to the first user described group, the targeted customer of mating most with described first user is filtered out by the first screening parameter and the second screening parameter, thus improve the precision of friend recommendation, the good friend of suitable contacts accurately, effectively can be found to provide higher success ratio for user.

Accompanying drawing explanation

Fig. 1 is the realization flow schematic diagram of the inventive method embodiment one;

Fig. 2 is the realization flow schematic diagram of the inventive method embodiment two;

Fig. 3 is the realization flow schematic diagram of the inventive method embodiment three;

Fig. 4 is the schematic diagram of a social networks of the application embodiment of the present invention;

Fig. 5 is that a social network user position of the application embodiment of the present invention has the schematic diagram of movement;

Fig. 6 is application one of the embodiment of the present invention is mapped to the second sampled point set of gridding schematic diagram from the first sampled point set;

Fig. 7 is the inside composition structural representation of server example one of the present invention;

Fig. 8 is the outside universal architecture schematic diagram of one of embodiment of the present invention server two;

Fig. 9 is the inside composition structural representation of server example three of the present invention.

Embodiment

Be described in further detail below in conjunction with the enforcement of accompanying drawing to technical scheme.

Embodiment of the method one:

Embodiments provide a kind of information processing method, as shown in Figure 1, described method comprises:

Step 101, obtain user's spatio-temporal activity information of each user in group according to user-generated content;

Step 102, according to described user's spatio-temporal activity information determination first information, determine the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Step 103, determine the second information according to described user's spatio-temporal activity information, determine the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

Step 104, to concentrate from screening parameter according to preset strategy and choose described first screening parameter and/or described second screening parameter, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

Adopt the embodiment of the present invention, the first corresponding screening parameter and the second screening parameter is obtained further by the first information and the second information characterizing these two different dimensions of room and time respectively, from candidate user group corresponding to the first user described group, the targeted customer of mating most with described first user is filtered out by the first screening parameter and the second screening parameter, thus improve the precision of friend recommendation, the good friend of suitable contacts accurately, effectively can be found to provide higher success ratio for user

Embodiment of the method two:

Based on embodiment of the method one, be applied as example with a concrete field of social network, such as blog, space, microblogging, micro-letter, in time communication etc., wherein any one all constitutes the social networks of the complexity based on user;

The first information is spatial dimension and the Density Distribution of User Activity in social networks, and the first screening parameter that correspondence obtains is User Activity space distribution index of similarity; Second information is the space-time track sets of user's common activities in social networks, and the second screening parameter that correspondence obtains is user's space-time track index of similarity;

The then information processing method of the embodiment of the present invention, as shown in Figure 2, described method comprises:

Step 201, obtain user's spatio-temporal activity information of each user in group according to user-generated content;

Step 202, determine spatial dimension and the Density Distribution of described User Activity according to described user's spatio-temporal activity information;

Step 203, determine the space-time track sets of described user's common activities according to described user's spatio-temporal activity information;

Step 204, calculate described User Activity space distribution index of similarity according to the spatial dimension of described User Activity and Density Distribution;

Step 205, calculate described user's space-time track index of similarity according to the space-time track sets of described user's common activities;

Step 206, according to preset strategy be adopt single screening parameter or multiple screening parameter be combined into row filter, come correspondingly to choose described User Activity space distribution index of similarity and/or described user's space-time track index of similarity;

Step 207, carry out user's sequence, to filter out the targeted customer of mating most with described first user according to described User Activity space distribution index of similarity and/or described user's space-time track index of similarity in candidate user group corresponding to the first user in described group.

The above-mentioned steps flow process of the embodiment of the present invention is not restricted to current statement, and can adjust order as required, such as, the order of step 202 and step 203 can be exchanged, and the order of step 204 and step 205 also can be exchanged.

Embodiment of the method three:

Based on embodiment of the method one, be applied as example with a concrete field of social network, such as blog, space, microblogging, micro-letter, in time communication etc., wherein any one all constitutes the social networks of the complexity based on user;

The first information is spatial dimension and the Density Distribution of User Activity in social networks, and the first screening parameter that correspondence obtains is User Activity space distribution index of similarity; Second information is the space-time track sets of user's common activities in social networks, and the second screening parameter that correspondence obtains is user's space-time track index of similarity; Be User Activity space-time unite index of similarity according to the three screening parameter that the first screening parameter and the second screening parameter obtain;

The then information processing method of the embodiment of the present invention, as shown in Figure 3, described method comprises:

Step 201, obtain user's spatio-temporal activity information of each user in group according to user-generated content;

Step 202, determine spatial dimension and the Density Distribution of described User Activity according to described user's spatio-temporal activity information;

Step 203, determine the space-time track sets of described user's common activities according to described user's spatio-temporal activity information;

Step 204, calculate described User Activity space distribution index of similarity according to the spatial dimension of described User Activity and Density Distribution;

Step 205, calculate described user's space-time track index of similarity according to the space-time track sets of described user's common activities;

Step S205, calculate User Activity space-time unite index of similarity according to described User Activity space distribution index of similarity and described user's space-time track index of similarity;

Step S206, according to preset strategy be adopt single screening parameter or multiple screening parameter be combined into row filter, come correspondingly to choose described User Activity space distribution index of similarity, described user's space-time track index of similarity and/or User Activity space-time unite index of similarity;

Step S207, carry out user's sequence, to filter out the targeted customer of mating most with described first user according to described User Activity space distribution index of similarity, described user's space-time track index of similarity and/or User Activity space-time unite index of similarity in candidate user group corresponding to the first user in described group.

Adopt the embodiment of Fig. 2-Fig. 3, three screening parameters: described user's space-time track index of similarity, described User Activity space-time unite index of similarity, described User Activity space-time unite index of similarity, they separately can separately as screening parameter, also can combination of two or three combine together arbitrarily, for to the user's sequence in candidate user group corresponding to first user (or claiming candidate good friend collection), the order of sequence is felt priority, to filter out the targeted customer of mating most, for friend recommendation, and sequence is the most forward, be be all the targeted customer of mating most from spatially or from the time with described first user.

In sum, under this kind of scene, information processing scheme of the present invention is actually a kind of based on the distribution of user's space scope of activities and the friend recommendation scheme of space-time track similarity, for this friend recommendation scheme, can from blog, space, microblogging, micro-letter, obtain user in the described social networks such as timely communication to log in, register and the geographical location information such as event trace, access time and frequency information, these information all belong to described user's spatio-temporal activity information, spatial dimension (border or radius) and the Density Distribution (intensity or probability) of 1. User Activity then can be got according to user's spatio-temporal activity information, the main space-time track sets of 2. user can also be obtained according to user's spatio-temporal activity information.

Thus, according to 1. above-mentioned and 2. information obtain User Activity space distribution index of similarity and described user's space-time track index of similarity respectively, User Activity space-time unite index of similarity can also be calculated according to User Activity space distribution index of similarity and described user's space-time track index of similarity further.For unique user (i.e. described first user), according to one or more in each index above-mentioned, candidate user collection is sorted and be its commending friends.Based on the friend recommendation of User Activity space distribution and space-time track similarity, user can be caught to find familiar stranger's psychology, good friend's acceptance of recommending is with to meet chance under line high, it is long that the friend relation formed maintains the time, be conducive to improving and recommend efficiency, further extension friend relation circle and improve friend relation network structure.

Based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, comprise the combination of one or more modes following according to user-generated content acquisition user spatio-temporal activity information:

Mode one: search the spatio-temporal activity information that user logged in and exited server info generation in user-generated content;

Mode two: the spatio-temporal activity information of searching the information of user and server communication in user-generated content;

Mode three: search the spatio-temporal activity information of user about registering in user-generated content;

Mode four: the spatio-temporal activity information of searching the relevant trip track that user uploads in user-generated content.

1) based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, the described spatio-temporal activity information produced when user logs in and exit APP of searching in user-generated content comprises:

User logs in and exits time of APP and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information etc. in history.

As shown in Figure 4, user 11-user 15 is comprised in social networks, 21-base station, base station 23 respectively in user 11-user 15 administer user and carry out signal transmitting and Signal reception, guarantee that the mobile data network that user supports by base station exchanges in social networks, such as many people chat cluster, many people's networkings are played games, many people video calling or voice call etc., also can mobile data network be utilized to carry out application download by unique user, use application, a series of application operatings such as application unloading, user by the mobile data network of base station coverage and server 41 and server 42 mutual, to obtain candidate good friend collection from server, chat messages record, game, multimedia resource such as video or music etc., in order to ensure the network coverage, also comprise a relaying 31, certainly except mobile data network, WIFI network can also be comprised, do not show in figure.

In the present embodiment, for user 11, user utilizes the search dog Video Applications that notebook is installed to see video, the time that recording user logged in and exited this search dog Video Applications is in history respectively at 9 in the morning and 12 noon, the IP address of user 11, user 11 by GPS location obtain with geographic position etc. of longitude and latitude mark, these information both comprised the time, also spatial information is comprised, be an example of described spatio-temporal activity information, this is an example just, depending on concrete condition, is not limited to description here.

2) based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, spatio-temporal activity information when searching user and server communication in user-generated content comprises:

User and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information etc.

As shown in Figure 4, user 11-user 15 is comprised in social networks, 21-base station, base station 23 respectively in user 11-user 15 administer user and carry out signal transmitting and Signal reception, guarantee that the mobile data network that user supports by base station exchanges in social networks, such as many people chat cluster, many people's networkings are played games, many people video calling or voice call etc., also can mobile data network be utilized to carry out application download by unique user, use application, a series of application operatings such as application unloading, user by the mobile data network of base station coverage and server 41 and server 42 mutual, to obtain candidate good friend collection from server, chat messages record, game, multimedia resource such as video or music etc., in order to ensure the network coverage, also comprise a relaying 31, certainly except mobile data network, WIFI network can also be comprised, do not show in figure.

In the present embodiment, for user 15, user utilizes surfing Internet with cell phone to play games, need to obtain its game resource stored from this content server of server 42, just can play games after server downloads to game resource, certainly, server 42 is except storing game resource, all right store video, the multimedia messagess such as audio frequency.Recording user initiatively to server communication, time to server request game resource is point in evening 8, server timing recommends the time of video to be point in the morning 10 at weekend to user, the title of user 15 geographic location, such as user 15 drinks coffee in Startbuck, online is simultaneously played games, record current position is called new middle Startbuck of closing etc., these information both comprised the time, also comprise spatial information, be an example of described spatio-temporal activity information, this is an example just, depending on concrete condition, be not limited to description here.

3) based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, in user-generated content, searching user about the spatio-temporal activity information of registering comprises:

User registers the time that point of interest (POI, Point of interest) is put; And/or

User registers the geographic position of POI point; Wherein, the geographic position of POI point comprises place name and/or latitude and longitude information.

As shown in Figure 4, user 11-user 15 is comprised in social networks, 21-base station, base station 23 respectively in user 11-user 15 administer user and carry out signal transmitting and Signal reception, guarantee that the mobile data network that user supports by base station exchanges in social networks, such as many people chat cluster, many people's networkings are played games, many people video calling or voice call etc., also can mobile data network be utilized to carry out application download by unique user, use application, a series of application operatings such as application unloading, user by the mobile data network of base station coverage and server 41 and server 42 mutual, to obtain candidate good friend collection from server, chat messages record, game, multimedia resource such as video or music etc., in order to ensure the network coverage, also comprise a relaying 31, certainly except mobile data network, WIFI network can also be comprised, do not show in figure.

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.By recommending its interested POI to accurate user, to improve the user satisfaction of user, POI to be recommended can be enable simultaneously accurately to navigate to its corresponding potential user group and improve and to recommend success ratio.In the present embodiment, for user 12, user 12 holds digital PDA and to register the position at oneself place, such as user has a meal in restaurant, can to comment on masses oneself current interested vegetable and application software evaluate and makes a blueprint, POI information can comprise the name in restaurant, the speciality in restaurant, the geographic position in restaurant, the time that user registers and comments on, these information both comprised the time, also comprise spatial information, be an example of described spatio-temporal activity information, this is an example just, depending on concrete condition, be not limited to description here.

4) based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, the spatio-temporal activity information of searching the relevant trip track that user uploads in user-generated content comprises:

The starting point of user trajectory, the time of terminal and/or geographical location information; Wherein, described geographical location information comprises POI and/or place name and/or latitude and longitude information;

The time of user trajectory approach point and/or geographical location information.

As shown in Figure 5, user 11-user 15 is comprised in social networks, 21-base station, base station 23 respectively in user 11-user 15 administer user and carry out signal transmitting and Signal reception, guarantee that the mobile data network that user supports by base station exchanges in social networks, such as many people chat cluster, many people's networkings are played games, many people video calling or voice call etc., also can mobile data network be utilized to carry out application download by unique user, use application, a series of application operatings such as application unloading, user by the mobile data network of base station coverage and server 41 and server 42 mutual, to obtain candidate good friend collection from server, chat messages record, game, multimedia resource such as video or music etc., in order to ensure the network coverage, also comprise a relaying 31, certainly except mobile data network, WIFI network can also be comprised, do not show in figure.

Here it is pointed out that user 13 position changes, by starting point A, the point between a series of Origin And Destination, as X1-X3 reaches home B, the position of user 12 also changes, and to be reached home E by starting point D.

In the present embodiment, the starting point of user trajectory, terminal, also have time and/or the position at the intermediate trace points place between starting point and terminal, select such as user 13 morning Saturday 10 coffee-house at place, starting point A position-on island coffee, the drink of coffee-house is commented on, register, navigation software is opened in the process of walking, record the latitude and longitude information of intermediate trace points, walking arrives duck king restaurant, also the latitude and longitude information at time of arrival and place, duck king restaurant is recorded, these information both comprised the time, also spatial information is comprised, be an example of described spatio-temporal activity information, this is an example just, depending on concrete condition, be not limited to description here.

Based on said method embodiment two-three, in the embodiment of the present invention one preferred implementation, comprise time and the frequency information of all access locations of user according to social network user generating content UGC acquisition user spatio-temporal activity information.

Embodiment of the method four:

Based on said method embodiment two to three, step 202 specifically comprises:

Step 2021, by relating to the element of user's geographical location information, comprising and logging in IP, place name, POI, coordinate and WIFI information, by the spatial information of these implicit expression, by co-located algorithm and or place name coordinate database, be unifiedly converted into latitude and longitude information;

Step 2022, by global map gridding, generate the regular grid of 30 " * 30 " (being similar to 1km*1km);

Step 2023, according to the coordinate information of user's historical act and frequency information, all for user spatio-temporal activity points to be mapped on grid, with the coordinate dropping on grid element center coordinate and substitute actual activity point, the visitation frequency dropping on uniform grid point is added up;

Step 2024, be <L by the spatio-temporal activity point Unify legislation of all griddings that obtains in step 201 _x, p _x, f _x(t) >, L _xfor the coordinate (Lon of an xth point _x, Lat _x), p _xfor the accumulative access frequency of an xth grid points, f _xt () is the frequency distribution of xth point on time dimension;

Step 2025, according to the coordinate of user's accessing points and the frequency of accessing points, utilize spatial interpolation algorithm (recommend interpolation algorithm or ordinary kriging interpolation algorithm), interpolation radius is R ₀(") generates user's space motion frequency distribution (density) figure Γ to be recommended as 30 _x, the frequency values of grid m is Γ _xm (), given frequency threshold H0 (recommending threshold value to be 0.01), with grid space motion frequency for H ₀the curve be surrounded as counts the spatio-temporal activity range boundary W of user _x.

In the embodiment of the present invention one preferred implementation, step 204 can calculate User Activity space distribution index of similarity Sim according to the User Activity spatial dimension obtained and Density Distribution information _area, can be realized by following formula (1):

${\mathrm{Sim}}_{\mathrm{area}}=\frac{{\mathrm{\&Gamma;}}_x\&cap;{\mathrm{\&Gamma;}}_y}{{\mathrm{\&Gamma;}}_x\&cup;{\mathrm{\&Gamma;}}_y}=1-\frac{{(\underset{k\&Element;S_x}{\overset{S_x}{\mathrm{\&Sigma;}}}{({\mathrm{\&Gamma;}}_x\left(k\right)-{\mathrm{\&Gamma;}}_y\left(k\right))}^2+\underset{k\&Element;S_y}{\overset{S_y}{\mathrm{\&Sigma;}}}{({\mathrm{\&Gamma;}}_x\left(k\right)-{\mathrm{\&Gamma;}}_y\left(k\right))}^2)}^{\frac{1}{2}}}{2}---\left(1\right)$

Wherein S _xand S _yrepresent the spatio-temporal activity range boundary W of user x and y respectively _xand W _ythe pixel set covered.

Embodiment of the method five:

Based on said method embodiment two to four, step 203 specifically comprises:

Step 2031, to all accessing points of user, { according to its access frequency, { p} carries out, from high and low sequence, obtaining the access point set { <L after sorting L} ₁, p ₁, f ₁(t) >, <L ₂, p ₂, f ₂(t) >, <L ₃, p ₃, f ₃(t) > ... <L _n, p _n, f _n(t) >};

The point that accessing points in step 2032, successively traversal C1 after sequence is concentrated, calculates accumulated probability until a kth point, make p0 is accumulated probability threshold value (recommending P0 to be 95%), obtains user's frequentation and asks stationary point collection Θ={ <L ₁, p ₁, f ₁(t) >, <L ₂, p ₂, f ₂(t) >, <L ₃, p ₃, f ₃(t) > ... <L _k, p _k, f _k(t) >}.

In the embodiment of the present invention one preferred implementation, step 205 can calculate user's space-time track index of similarity Sim according to the User Activity spatial dimension obtained and space-time track sets _route, can be realized by following formula (2):

${\mathrm{Sim}}_{\mathrm{route}}=\frac{{\mathrm{\&Theta;}}_x\&cap;{\mathrm{\&Theta;}}_y}{{\mathrm{\&Theta;}}_x{\&cup;\mathrm{\&Theta;}}_u}=\frac{\underset{k=1}{\overset{K}{\mathrm{\&Sigma;}}}(p_x\left(k\right)+p_y\left(k\right)-{\&Integral;}_t|p_x\left(k\right)\&CenterDot;f_x(t,k)-p_y\left(k\right)\&CenterDot;f_y(t,k)\left|\right)}{2}---\left(2\right)$

Wherein K represents user Θ _xand Θ _yoverlapping stationary point number.

Embodiment of the method six:

This method embodiment obtains described User Activity space distribution index of similarity according to the spatial dimension of described User Activity and Density Distribution, and then obtain described user's space-time track index of similarity according to the space-time track sets of described user's common activities, finally, carry out by described User Activity space distribution index of similarity and described user's space-time track index of similarity user that candidate good friend concentrates to sort screening, thus therefrom find the targeted customer of mating most, embodiment comprises:

Step 301, obtain user's spatio-temporal activity information according to social network user generating content (UGC, Users Generate Content).

Here, user-generated content is Users Generate Content, is abbreviated as UGC.

Concrete, user-generated content comprise user's open source information, individualized signature, issue microblogging, blog, reprinted articles, information of registering, log in APP information, with server communication information etc.

Here, according to the user-generated content of social networks, obtain in the process of user spatio-temporal activity information, obtain that spatio-temporal activity information comprises in following mode one or more:

Mode one: search the spatio-temporal activity information that user logged in and exited server info generation in user-generated content.Specifically log in and exit the log information of APP by recording user, comprise user and log in and exit time of APP and/or IP address and/or cellular base station information and/or GPS position information and/or WIFI information etc.

Mode two: the spatio-temporal activity information of searching the information of user and server communication in user-generated content.In use APP process, specifically keep the spatio-temporal activity information sent in handshaking procedures according to set frequency and server by recording user, comprise the spatio-temporal activity information that user constantly changes, comprise time of change and/or IP address and/or cellular base station information and/or GPS position information and/or WIFI information etc.

Mode three: search the spatio-temporal activity information of user about registering in user-generated content.Specifically use APP active upload to the information of registering of server by recording user, comprise POI information and/or geographic coordinate information and/or temporal information and/or word content and/or pictorial information etc. that user registers.

Mode four: search the spatio-temporal activity information of user about track of going on a journey in user-generated content.Specifically use APP active upload to the trace information of server by recording user, comprise the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographic coordinate information, and/or the time of constantly change in seconds in User Activity process and/or geographic coordinate information, by calculate try to achieve about the configuration information in User Activity process, comprise average velocity, acceleration etc., and/or the information that user stays, comprise the geographic position of stationary point, and/or the initial sum termination time that user stays, and/or residence time, and/or the POI information etc. near stationary point.

Step 302, according to the user's spatio-temporal activity information obtained, calculate the spatial dimension of User Activity and Density Distribution.

Wherein, the spatio-temporal activity information of user, comprises the space of User Activity and the information of time two aspect corresponding with locus.

The spatial information of the user obtained from user-generated content, comprises explicit spatial information, also comprises implicit expression spatial information.Explicit spatial information and real latitude and longitude coordinates.Namely the spatial information of implicit expression can be converted into the information of coordinate information by certain way.The coordinate information of implicit expression comprises the IP address that user logs in APP and/or place name, and/or base station location, and/or POI information, and/or WIFI information etc.

The coordinate information of implicit expression, by co-located algorithm and/or based on place name coordinate database, needs unification to be converted into explicit spatial information, i.e. latitude and longitude coordinates in this article.

Here, the spatial dimension of User Activity is not the location information be of user, but the space surface information come by spatial point information and frequency interpolation and frequency information.

Here, space interpolation does not directly utilize latitude and longitude coordinates information and the frequency information of luv space point, needs to carry out geographic grid mapping and resampling to these points.

Concrete, according to the spatio-temporal activity information of user, utilize spatial interpolation algorithm, obtain user's main activities scope and Spatial Density Distribution, comprising:

A1, the element of user's geographical location information will be related to, comprise and log in IP, place name, POI, coordinate and WIFI information, by the spatial information of implicit expression, be converted into explicit spatial information, i.e. latitude and longitude coordinates based on place name coordinate database and/or by co-located algorithm is unified;

A2, by global map gridding, generate the regular grid of 30 " * 30 " (being similar to 1km*1km);

A3, all for user spatio-temporal activity points are carried out mapping and resampling on grid, the visitation frequency dropping on uniform grid point is added up, with the coordinate dropping on grid element center coordinate and substitute actual activity point;

Here, the initial samples point obtained before carrying out described mapping and resampling, the position of all spatio-temporal activity points of user namely obtained according to actual longitude and latitude can be called the first sampled point, as shown in Figure 6, first sampled point at user 11-user 14 place constitutes sampled point set S1, the sampled point obtained after carrying out described mapping and resampling can be called the second sampled point, second sampled point at user 11-user 14 place constitutes sampled point set S2, the benefit by this mapping and resampling mode just intuitively can be found out from Fig. 6, be: each user initially comparing dispersion again can be mapped in proportion and resampling within the scope of the grid of controlled mathematics category, the frequency that meeting adding users occurs and probability, so that better carry out follow-up computing statistics.

A4, be <L by the spatio-temporal activity point Unify legislation of all griddings obtained in steps A _x, p _x, f _x(t) >, L _xfor the coordinate (Lon of an xth point _x, Lat _x), p _xfor the accumulative access frequency of an xth grid points, f _xt () is the frequency distribution of xth point on time dimension;

A5, according to the coordinate of user's accessing points and the frequency of accessing points, utilize spatial interpolation algorithm (recommend interpolation algorithm or ordinary kriging interpolation algorithm), interpolation radius is R ₀(") generates user's space motion frequency distribution (density) figure Γ to be recommended as 30 _x, the frequency values of grid m is Γ _xm (), given frequency threshold H0 (recommending threshold value to be 0.01), with grid space motion frequency for H ₀the curve be surrounded as counts the spatio-temporal activity range boundary W of user _x;

Threshold value H0 is between 0 and 1, and threshold value is larger, and user's main activities scope of screening is less.

Step 303, according to the user's spatio-temporal activity information obtained, calculate the space-time track sets of User Activity.

Concrete, according to the user's spatio-temporal activity information obtained, the detailed process calculating the space-time track sets of User Activity comprises:

B1. to all accessing points of user, { according to its access frequency, { p} carries out the low sequence from height to L}, obtains the access point set { <L after sorting ₁, p ₁, f ₁(t) >, <L ₂, p ₂, f ₂(t) >, <L ₃, p ₃, f ₃(t) > ... <L _n, p _n, f _n(t) >};

B2. travel through the point that the accessing points in C1 after sequence is concentrated successively, calculate accumulated probability until a kth point, make p0 is accumulated probability threshold value (recommending P0 to be 95%), obtains user's frequentation and asks stationary point collection Θ={ <L ₁, p ₁, f ₁(t) >, <L ₂, p ₂, f ₂(t) >, <L ₃, p ₃, f ₃(t) > ... <L _k, p _k, f _k(t) >};

Step 304, calculate User Activity space distribution index of similarity according to the User Activity spatial dimension obtained and Density Distribution information.

Concrete, the detailed process calculating User Activity space distribution index of similarity according to User Activity spatial dimension and Density Distribution information comprises:

C1. for specific user x, the space operation that first will obtain this user has the candidate user collection Ω of similarity _x, to reduce operand.Whether candidate user collection can have this index overlapping by its main activities scope with user's main activities of specifying scope judges.Main activities scope due to user is an irregular polygon, and when doing Spatial Overlap computing, Algorithms T-cbmplexity is higher, can substitute with the minimum outsourcing rectangle of scope of activities.

C2. to all user y in candidate user collection, the activity space distribution similarity index Sim between specific user x and candidate user y is calculated _areacan be realized by following formula (1):

${\mathrm{Sim}}_{\mathrm{area}}=\frac{{\mathrm{\&Gamma;}}_x\&cap;{\mathrm{\&Gamma;}}_y}{{\mathrm{\&Gamma;}}_x\&cup;{\mathrm{\&Gamma;}}_y}=1-\frac{{(\underset{k\&Element;S_x}{\overset{S_x}{\mathrm{\&Sigma;}}}{({\mathrm{\&Gamma;}}_x\left(k\right)-{\mathrm{\&Gamma;}}_y\left(k\right))}^2+\underset{k\&Element;S_y}{\overset{S_y}{\mathrm{\&Sigma;}}}{({\mathrm{\&Gamma;}}_x\left(k\right)-{\mathrm{\&Gamma;}}_y\left(k\right))}^2)}^{\frac{1}{2}}}{2}---\left(1\right)$

In step 305, calculate space-time track index of similarity between user according to User Activity spatial dimension and Density Distribution information.

Concrete, the detailed process calculating space-time track index of similarity between user according to User Activity spatial dimension and Density Distribution information comprises:

D1. for specific user x, the space operation that first will obtain this user has the candidate user collection Ω of similarity _x, step is with 0051.

D2. to all user y in candidate user collection, the space-time track index of similarity Sim between specific user x and candidate user y is calculated _routecan be realized by following formula (2):

${\mathrm{Sim}}_{\mathrm{route}}=\frac{{\mathrm{\&Theta;}}_x\&cap;{\mathrm{\&Theta;}}_y}{{\mathrm{\&Theta;}}_x{\&cup;\mathrm{\&Theta;}}_u}=\frac{\underset{k=1}{\overset{K}{\mathrm{\&Sigma;}}}(p_x\left(k\right)+p_y\left(k\right)-{\&Integral;}_t|p_x\left(k\right)\&CenterDot;f_x(t,k)-p_y\left(k\right)\&CenterDot;f_y(t,k)\left|\right)}{2}---\left(2\right)$

In step 306, according to User Activity space distribution index of similarity and space-time track index of similarity, the candidate user collection of user is sorted and be its commending friends.

Concrete, according to User Activity space distribution index of similarity and space-time track index of similarity, the candidate user collection of user is sorted and be that the detailed process of its commending friends comprises:

E1. for specific user x, to its good friend candidate collection Ω _xinterior all user y (y ∈ Ω _x), according to the User Activity space distribution index of similarity between user y and x, from high and lowly to sort, under user is recommended specific user successively.

E2. and/or for specific user x, to its good friend candidate collection Ω _xinterior all user y (y ∈ Ω _x), according to the User Activity space-time track index of similarity between user y and x, from high and lowly to sort, under user is recommended specific user successively.

The sampling embodiment of the present invention, by obtaining user's spatio-temporal activity information in user-generated content, obtain more real User Activity spatial dimension, Spatial Density Distribution and space-time track sets, overlapping all users are had to specific user's main activities scope, based on activity space distribution similarity index between user and/or space-time track index of similarity, according to similarity from high and low order to specific user's commending friends.The embodiment of the present invention obtains activity space between user and has high superposed, and User Activity custom has high similarity, is conducive to improving friend recommendation acceptance.

Here it is to be noted: the description of following electronic equipment item, it is similar for describing with said method, and the beneficial effect with method describes, and does not repeat.For the ins and outs do not disclosed in electronic equipment embodiment of the present invention, please refer to the description of the inventive method embodiment.

Server example one:

Embodiments provide a kind of server, as shown in Figure 7, server 401 comprises:

Acquisition module 4011, for obtaining user's spatio-temporal activity information of each user in group according to user-generated content;

First determination module 4012, for according to described user's spatio-temporal activity information determination first information, determines the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Second determination module 4013, for determining the second information according to described user's spatio-temporal activity information, determines the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

Processing module 4015, choosing described first screening parameter and/or described second screening parameter for concentrating from screening parameter according to preset strategy, from candidate user group corresponding to the first user described group, filtering out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

In the embodiment of the present invention one preferred implementation, described server also comprises:

3rd determination module 4014, for determining three screening parameter according to described first screening parameter and described second screening parameter;

Processing module 4015, be further used for screening parameter described in described three screening parameter read-in to concentrate, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter and/or described three screening parameter further.

In the embodiment of the present invention one preferred implementation, described acquisition module, is further used for adopting the user's spatio-temporal activity information comprising and obtain each user in groups with one or more of under type:

Mode one: search user and log in and exit the spatio-temporal activity information that server produces in described user-generated content;

Mode two: search the spatio-temporal activity information that user and server communication produce in described user-generated content;

Mode three: search the spatio-temporal activity information of user about registering produced in described user-generated content;

Mode four: search user and upload about the spatio-temporal activity information that produces of trip track in described user-generated content.

In the embodiment of the present invention one preferred implementation, described acquisition module also comprises:

First searches submodule, and the log information for being logged in and exit application APP by recording user is searched and obtained described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: user's history logs in and exit the temporal information and/or Internet protocol IP address information and/or cellular base station information and/or GPS information and/or information of place names and/or WIFI information of applying APP.

In the embodiment of the present invention one preferred implementation, described acquisition module also comprises:

Second searches submodule, for keeping the information searching that in handshaking procedures send to obtain described spatio-temporal activity information according to assigned frequency and server by recording user in use APP process;

Described spatio-temporal activity information at least comprises: user and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information.

In the embodiment of the present invention one preferred implementation, described acquisition module also comprises:

3rd searches submodule, searches the spatio-temporal activity information of user about registering produced for described in described user-generated content;

APP active upload is used to obtain described spatio-temporal activity information to the information searching of registering of server by recording user;

Described spatio-temporal activity information at least comprises: user registers the POI information of point of interest and/or temporal information and/or geographical location information and/or Word message and/or pictorial information.

In the embodiment of the present invention one preferred implementation, described acquisition module also comprises:

4th searches submodule, to search obtain described spatio-temporal activity information for being used APP active upload by recording user to the trace information of server;

Described spatio-temporal activity information at least comprises: the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographical location information; And/or

The POI information of user's trajectory paths point between Origin And Destination and/or temporal information and/or geographical location information.

In the embodiment of the present invention one preferred implementation, described first determination module also comprises:

First extracts submodule, for relating to the extraction of spatial information of Spatial Dimension out by described user's spatio-temporal activity information, and isolates explicit spatial information and the spatial information of implicit expression;

Mapping submodule, after the spatial information of described implicit expression is converted into explicit spatial information, obtains the second sampled point of gridding using described explicit spatial information as the first sampled point by mesh mapping resampling;

The first information generates submodule, for by the coordinate of described second sampled point according to user's accessing points and the frequency of accessing points, the spatial dimension of User Activity and Density Distribution is generated by the interpolation strategies preset, and using the spatial dimension of described User Activity and Density Distribution as the described first information.

In the embodiment of the present invention one preferred implementation, described first determination module also comprises:

First judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

First obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

First similarity exponent arithmetic submodule, for the User Activity space distribution index of similarity of all users respectively and between described first user according to the spatial dimension of described User Activity and Density Distribution computing, and using described User Activity space distribution index of similarity as described first screening parameter.

In the embodiment of the present invention one preferred implementation, described second determination module also comprises:

Second extracts submodule, for relating to the extraction of spatial information of time dimension out by described user's spatio-temporal activity information, carry out from high to Low sequence to all accessing points of the user in the spatial information extracted according to its access frequency, obtain the access point set after sorting;

Traversal searches submodule, for traveling through each point that the accessing points after described sequence is concentrated successively, obtaining the accumulated probability of each point, when the accumulated probability of described each point is greater than a threshold value, the point being greater than described threshold value is designated as user and resides accessing points;

Second information generates submodule, for travel through terminate after reside by described user the space-time track sets that accessing points generates user common activities, and using the space-time track sets of described user's common activities as described second information.

In the embodiment of the present invention one preferred implementation, described second determination module also comprises:

Second judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Second obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

Second similarity exponent arithmetic submodule, for the user space-time track index of similarity of all users according to the space-time track sets computing of described user's common activities respectively and between described first user, and using described user's space-time track index of similarity as described second screening parameter.

Server example two:

Embodiments provide a kind of server, based on server example one, be applied as example with a concrete field of social network, such as blog, space, microblogging, micro-letter, in time communication etc., wherein any one all constitutes the social networks of the complexity based on user;

The first information is spatial dimension and the Density Distribution of User Activity in social networks, and the first screening parameter that correspondence obtains is User Activity space distribution index of similarity; Second information is the space-time track sets of user's common activities in social networks, and the second screening parameter that correspondence obtains is user's space-time track index of similarity; Be User Activity space-time unite index of similarity according to the three screening parameter that the first screening parameter and the second screening parameter obtain;

Under this application scenarios, as shown in Figure 8, the server of the information processing that the present invention is used for is actually a kind of friend recommendation scheme based on the distribution of user's space scope of activities and space-time track similarity, described server can be recommendation server, Fig. 8 is different from internal module composition structural drawing, for the another kind of structural drawing of the server described in the present embodiment, as shown in Figure 8, described server comprises processor 502, storage medium 504 and at least one external communication interface 501; Described processor 502, storage medium 504 and external communication interface 501 are all connected by bus 503.Described processor 502 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 501 for carrying out information interaction with other electronic equipments, such as, communicates with client, communicates with other webservers.Described bus 503 is the link of server internal.

Described processor 502, by running executable instruction, controlling the information processing of information interaction between described external communication interface, storage medium and bus and described processor 502 inside, realizing the function of above-mentioned unit.

Server example three:

Based on the application scenarios of above-mentioned server example two, Fig. 9 is the server block diagram for friend recommendation, and server 601 comprises:

Acquisition module 6011, similarity computing module 6012, friend recommendation module 6013, wherein:

Acquisition module 6011, for the user-generated content according to social networks, obtains and upgrades the spatio-temporal activity information of user;

Similarity computing module 6012, for the spatio-temporal activity information according to user, calculates the spatio-temporal activity index of similarity between user;

Friend recommendation module 6013, for according to the spatio-temporal activity index of similarity between user, according to the height of index of similarity, recommends the good friend with similar active space and similar custom to targeted customer;

By acquisition module 6011 according to the user-generated content acquisition of social networks and the spatio-temporal activity information upgrading user, the spatio-temporal activity index of similarity between user is calculated by similarity computing module 6012, by the main activities scope of friend recommendation module 6013 based on user, Density Distribution and space-time track sets, to user's main activities scope, there is overlapping candidate user, the index of similarity of calculated candidate user and targeted customer's space distribution and/or space-time track sets, according to the height of index of similarity, the good friend with similar active space and similar custom is recommended to targeted customer.By the embodiment of the present invention, accuracy rate and user's acceptance of friend recommendation can be improved, be conducive to improving and recommend efficiency.

In the embodiment of the present invention one preferred implementation, still as shown in Figure 9, be described as follows to the internal module in acquisition module 6011, similarity computing module 6012, friend recommendation module 6013:

Acquisition module 6011 specifically comprises:

Search submodule 60111, for searching the spatio-temporal activity information of user at the user generated content (UGC) of social networks;

Obtain submodule 60112, for obtaining the spatio-temporal activity information of user at the user generated content (UGC) of social networks.

Wherein, search submodule 60111 described in specifically to comprise:

Resolve subelement 601111: for the spatial information of the implicit expression such as place name, POI, IP address, WIF address, base station location is resolved to explicit spatial information, i.e. latitude and longitude coordinates;

Generate subelement 601112: for generating and upgrade the spatio-temporal activity information of user, the moving position new to user carries out geographic grid spatial mappings, and frequency renewal and the renewal of Annual distribution frequency are carried out to the geographic grid in user's historical act district;

Wherein, described similarity computing module 6012 specifically comprises:

Screening submodule 60121: for the spatio-temporal activity information according to social network user, calculates the main space scope of activities of user, Density Distribution and space-time track sets, obtains the candidate user collection with targeted customer's main space scope of activities with plyability;

First similarity calculating sub module 60122: in targeted customer's candidate user collection, calculated candidate user and targeted customer's activity space distribution similarity index; And/or

Second similarity calculating sub module 60123: in targeted customer's candidate user collection, calculated candidate user and targeted customer's space-time track index of similarity;

Wherein, described friend recommendation module 6013 specifically comprises:

First recommends submodule 60131: in targeted customer's candidate user collection, according to the order that candidate user and targeted customer's activity space distribution similarity index are low from height, to targeted customer's commending friends; And/or

Second recommends submodule 60132: in targeted customer's candidate user collection, according to the order that candidate user and targeted customer movable space-time track index of similarity is low from height, to targeted customer's commending friends.

Here it is to be noted, acquisition module 6011 is according to the user generated content (UGC) of social networks, obtain user's spatio-temporal activity information, be included in user-generated content and search the spatio-temporal activity information that user logged in and exited server info generation, the spatio-temporal activity information of the information of user and server communication, the spatio-temporal activity information of user about registering, the spatio-temporal activity information of the relevant trip track that user uploads, explicit spatial information (latitude and longitude coordinates) is resolved to user concealed spatial information, and carry out geographic grid spatial mappings according to user coordinates, the frequency that counting user historical act maps at geographic grid and Annual distribution frequency distribution.Activity space scope and the Spatial Density Distribution of user is calculated by similarity computing module 6012, obtain the candidate user collection with targeted customer's main space scope of activities with plyability, according to Spatial Density Distribution and the space-time track sets of User Activity, calculated candidate user and targeted customer's activity space distribute and/or space-time track sets index of similarity.By friend recommendation module 6013, distribute according to candidate user and targeted customer's activity space and/or space-time track sets index of similarity height, recommend the good friend with similar active space and/or similar custom to targeted customer.User can be caught to find familiar stranger's psychology by the present invention, good friend's acceptance of recommending is with to meet chance under line high, it is long that the friend relation formed maintains the time, can improve accuracy rate and user's acceptance of friend recommendation, further extension friend relation circle and improve friend relation network structure.

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 unit, 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.

Or, if the above-mentioned integrated unit of the present invention using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.Based on such understanding, the technical scheme of the embodiment of the present invention can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product is stored in a storage medium, comprises some instructions and performs all or part of of method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server or the network equipment etc.).And aforesaid storage medium comprises: movable storage device, ROM, RAM, 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 (22)

1. an information processing method, is characterized in that, described method comprises:

User's spatio-temporal activity information of each user in group is obtained according to user-generated content;

According to described user's spatio-temporal activity information determination first information, determine the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Determine the second information according to described user's spatio-temporal activity information, determine the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

To concentrate from screening parameter according to preset strategy and choose described first screening parameter and/or described second screening parameter, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

2. method according to claim 1, is characterized in that, described method also comprises:

Three screening parameter is determined according to described first screening parameter and described second screening parameter;

Screening parameter described in described three screening parameter read-in is concentrated, from candidate user group corresponding to the first user described group, filters out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter and/or described three screening parameter further.

3. method according to claim 2, is characterized in that, the described user's spatio-temporal activity information obtaining each user in group according to user-generated content, comprises with one or more of under type:

Mode one: search user and log in and exit the spatio-temporal activity information that server produces in described user-generated content;

Mode two: search the spatio-temporal activity information that user and server communication produce in described user-generated content;

Mode three: search the spatio-temporal activity information of user about registering produced in described user-generated content;

Mode four: search user and upload about the spatio-temporal activity information that produces of trip track in described user-generated content.

4. method according to claim 3, is characterized in that, describedly in described user-generated content, searches user log in and exit the spatio-temporal activity information that server produces, and comprising:

The log information being logged in and exit application APP by recording user is searched and is obtained described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: user's history logs in and exit the temporal information and/or Internet protocol IP address information and/or cellular base station information and/or GPS information and/or information of place names and/or WIFI information of applying APP.

5. method according to claim 3, is characterized in that, describedly in described user-generated content, searches the spatio-temporal activity information that user and server communication produce comprise:

In use APP process, handshaking procedures in send information searching is kept to obtain described spatio-temporal activity information according to assigned frequency and server by recording user;

Described spatio-temporal activity information at least comprises: user and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information.

6. method according to claim 3, is characterized in that, describedly in described user-generated content, searches the spatio-temporal activity information of user about registering produced;

APP active upload is used to obtain described spatio-temporal activity information to the information searching of registering of server by recording user;

Described spatio-temporal activity information at least comprises: user registers the POI information of point of interest and/or temporal information and/or geographical location information and/or Word message and/or pictorial information.

7. method according to claim 3, is characterized in that, describedly in described user-generated content, searches user upload about the spatio-temporal activity information that produces of trip track comprises:

Use APP active upload to search to the trace information of server by recording user and obtain described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographical location information; And/or

The POI information of user's trajectory paths point between Origin And Destination and/or temporal information and/or geographical location information.

8. method according to claim 2, is characterized in that, described according to described user's spatio-temporal activity information determination first information, comprising:

Relate to the extraction of spatial information of Spatial Dimension out by described user's spatio-temporal activity information, and isolate explicit spatial information and the spatial information of implicit expression;

After the spatial information of described implicit expression is converted into explicit spatial information, described explicit spatial information is obtained the second sampled point of gridding as the first sampled point by mesh mapping resampling;

By the coordinate of described second sampled point according to user's accessing points and the frequency of accessing points, generate the spatial dimension of User Activity and Density Distribution by the interpolation strategies preset, and using the spatial dimension of described User Activity and Density Distribution as the described first information.

9. method according to claim 8, is characterized in that, describedly determines the first screening parameter according to the described first information, comprising:

Judge whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result;

When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Obtain all users in the candidate user group corresponding with described first user;

The User Activity space distribution index of similarity of all users respectively and between described first user according to the spatial dimension of described User Activity and Density Distribution computing, and using described User Activity space distribution index of similarity as described first screening parameter.

10. method according to claim 2, is characterized in that, describedly determines the second information according to described user's spatio-temporal activity information, comprising:

Relate to the extraction of spatial information of time dimension out by described user's spatio-temporal activity information, carry out from high to Low sequence to all accessing points of the user in the spatial information extracted according to its access frequency, obtain the access point set after sorting;

Travel through each point that the accessing points after described sequence is concentrated successively, obtain the accumulated probability of each point, when the accumulated probability of described each point is greater than a threshold value, the point being greater than described threshold value is designated as user and resides accessing points;

Reside by described user the space-time track sets that accessing points generates user's common activities after traversal terminates, and using the space-time track sets of described user's common activities as described second information.

11. methods according to claim 10, is characterized in that, describedly determine the second screening parameter according to described second information, comprising:

Judge whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result;

When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Obtain all users in the candidate user group corresponding with described first user;

The user space-time track index of similarity of all users respectively and between described first user according to the space-time track sets computing of described user's common activities, and using described user's space-time track index of similarity as described second screening parameter.

12. 1 kinds of servers, is characterized in that, described server comprises:

Acquisition module, for obtaining user's spatio-temporal activity information of each user in group according to user-generated content;

First determination module, for according to described user's spatio-temporal activity information determination first information, determines the first screening parameter according to the described first information; The described first information is used for the change of characterizing consumer at Spatial Dimension;

Second determination module, for determining the second information according to described user's spatio-temporal activity information, determines the second screening parameter according to described second information; Described second information is used for the change of characterizing consumer at time dimension;

Processing module, choosing described first screening parameter and/or described second screening parameter for concentrating from screening parameter according to preset strategy, from candidate user group corresponding to the first user described group, filtering out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter.

13. servers according to claim 12, is characterized in that, described server also comprises:

3rd determination module, for determining three screening parameter according to described first screening parameter and described second screening parameter;

Processing module, be further used for screening parameter described in described three screening parameter read-in to concentrate, from candidate user group corresponding to the first user described group, filter out the targeted customer of mating most with described first user according to described first screening parameter and/or described second screening parameter and/or described three screening parameter further.

14. servers according to claim 13, is characterized in that, described acquisition module, are further used for adopting the user's spatio-temporal activity information comprising and obtain each user in groups with one or more of under type:

Mode one: search user and log in and exit the spatio-temporal activity information that server produces in described user-generated content;

Mode two: search the spatio-temporal activity information that user and server communication produce in described user-generated content;

Mode three: search the spatio-temporal activity information of user about registering produced in described user-generated content;

Mode four: search user and upload about the spatio-temporal activity information that produces of trip track in described user-generated content.

15. servers according to claim 14, is characterized in that, described acquisition module also comprises:

First searches submodule, and the log information for being logged in and exit application APP by recording user is searched and obtained described spatio-temporal activity information;

Described spatio-temporal activity information at least comprises: user's history logs in and exit the temporal information and/or Internet protocol IP address information and/or cellular base station information and/or GPS information and/or information of place names and/or WIFI information of applying APP.

16. servers according to claim 14, is characterized in that, described acquisition module also comprises:

Second searches submodule, for keeping the information searching that in handshaking procedures send to obtain described spatio-temporal activity information according to assigned frequency and server by recording user in use APP process;

Described spatio-temporal activity information at least comprises: user and server are initiatively and the time of passive communication and/or IP address and/or cellular base station information and/or GPS information and/or place name and/or WIFI information.

17. servers according to claim 14, is characterized in that, described acquisition module also comprises:

3rd searches submodule, searches the spatio-temporal activity information of user about registering produced for described in described user-generated content;

APP active upload is used to obtain described spatio-temporal activity information to the information searching of registering of server by recording user;

Described spatio-temporal activity information at least comprises: user registers the POI information of point of interest and/or temporal information and/or geographical location information and/or Word message and/or pictorial information.

18. servers according to claim 14, is characterized in that, described acquisition module also comprises:

4th searches submodule, to search obtain described spatio-temporal activity information for being used APP active upload by recording user to the trace information of server;

Described spatio-temporal activity information at least comprises: the starting point of user trajectory and the POI information of terminal and/or temporal information and/or geographical location information; And/or

The POI information of user's trajectory paths point between Origin And Destination and/or temporal information and/or geographical location information.

19. servers according to claim 13, is characterized in that, described first determination module also comprises:

First extracts submodule, for relating to the extraction of spatial information of Spatial Dimension out by described user's spatio-temporal activity information, and isolates explicit spatial information and the spatial information of implicit expression;

Mapping submodule, after the spatial information of described implicit expression is converted into explicit spatial information, obtains the second sampled point of gridding using described explicit spatial information as the first sampled point by mesh mapping resampling;

The first information generates submodule, for by the coordinate of described second sampled point according to user's accessing points and the frequency of accessing points, the spatial dimension of User Activity and Density Distribution is generated by the interpolation strategies preset, and using the spatial dimension of described User Activity and Density Distribution as the described first information.

20. servers according to claim 19, is characterized in that, described first determination module also comprises:

First judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

First obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

First similarity exponent arithmetic submodule, for the User Activity space distribution index of similarity of all users respectively and between described first user according to the spatial dimension of described User Activity and Density Distribution computing, and using described User Activity space distribution index of similarity as described first screening parameter.

21. servers according to claim 13, is characterized in that, described second determination module also comprises:

Second extracts submodule, for relating to the extraction of spatial information of time dimension out by described user's spatio-temporal activity information, carry out from high to Low sequence to all accessing points of the user in the spatial information extracted according to its access frequency, obtain the access point set after sorting;

Traversal searches submodule, for traveling through each point that the accessing points after described sequence is concentrated successively, obtaining the accumulated probability of each point, when the accumulated probability of described each point is greater than a threshold value, the point being greater than described threshold value is designated as user and resides accessing points;

Second information generates submodule, for travel through terminate after reside by described user the space-time track sets that accessing points generates user common activities, and using the space-time track sets of described user's common activities as described second information.

22. servers according to claim 21, is characterized in that, described second determination module also comprises:

Second judges submodule, for judging whether the main activities scope of described first user exists overlapping with the main activities scope that at least one alternative candidate user organizes, and obtains judged result; When described judged result is for existing overlapping, will overlapping candidate user group be there is as the candidate user group corresponding with described first user;

Second obtains submodule, for obtaining all users in the candidate user group corresponding with described first user;

Second similarity exponent arithmetic submodule, for the user space-time track index of similarity of all users according to the space-time track sets computing of described user's common activities respectively and between described first user, and using described user's space-time track index of similarity as described second screening parameter.