CN105450510A - Friend management method, device and server for social network platform - Google Patents

Abstract

The invention provides a friend management method, device and server for a social network platform. The specific implementation way of the method is as follows: acquiring partial or total social network information released by friends of a social network user; finding out friends of a predetermined type from the friends of the user based on the social network information; and pushing a list of the friends of the predetermined type to the user, so as to remind the user to perform no disturbing setting according to the list. The implementation way does not need the user to search the friends of the predetermined type, so that the time is saved and the use efficiency of the social network is improved.

Description

For the friend management method of social network-i i-platform, device and server

Technical field

The disclosure relates to field of computer technology, particularly a kind of friend management method for social network-i i-platform, device and server.

Background technology

Along with the development of network technology, some network JICQs occur thereupon, such as, and the JICQ that micro-letter, credulity etc. are conventional.User can share with friend in the circle of friends of these JICQs some social network informations (as user dynamically or the information etc. forwarded), greatly improve Consumer's Experience.But the part good friend of some user may often send out some advertising messages or brush screen, bring to a lot of user and bother.

At present, most of user manually searches the good friend of those advertisement brush screens, then shields it or deletes, thus wasting the time, reducing the service efficiency of social networks.

Summary of the invention

In order to solve the problem, the disclosure provides a kind of friend management method for social network-i i-platform, device and server.

According to the first aspect of disclosure embodiment, a kind of friend management method for social network-i i-platform is provided, comprises:

The part or all of social network information that the good friend obtaining social network user issued;

From the good friend of described user, the good friend of predefined type is found out based on described social network information;

Push the list of the good friend of described predefined type to described user, carry out interruption-free setting with reminding user according to described list.

Optionally, the described good friend finding out predefined type based on described social network information from the good friend of described user, comprising:

Obtain the information of textual form corresponding to the content of described social network information;

Based on the information of described textual form, judge whether corresponding social network information belongs to predetermine class;

According to the result of described judgement, the related data of what the good friend adding up described user issued the belong to social network information of described predetermine class;

Find out from the good friend of described user meet predetermined condition good friend as the good friend of predefined type, wherein, the described good friend meeting predetermined condition is the good friend that corresponding described related data exceedes predetermined threshold.

Optionally, described related data comprises following one or more:

The quantity belonging to the social network information of described predetermine class that the good friend of described user issued;

The social network information proportion belonging to described predetermine class that the good friend of described user issued.

Optionally, the information of the textual form that the content of the described social network information of described acquisition is corresponding, comprising:

Determine the expression forms of information of each described social network information;

According to corresponding to the mode of described expression forms of information, extract the information of textual form corresponding to the content of each described social network information;

Wherein, described expression forms of information comprises word, image, video, link and sound.

Optionally, based on the information of described textual form, judge whether corresponding social network information belongs to predetermine class, comprising:

Obtain through training the kind judging dictionary obtained;

Described kind judging dictionary is adopted to carry out kind judging to the information of described textual form, to determine whether social network information corresponding to the information of described textual form belongs to predetermine class.

Optionally, described kind judging dictionary is trained in the following way and is obtained:

Obtain text message corresponding to multiple sample social network information as sample information, wherein, whether known described sample social network information belongs to described predetermine class;

Keyword is extracted from described sample information;

Determine the relevance parameter of described keyword and described predetermine class;

Extract and be more than or equal to keyword corresponding to the described relevance parameter of predetermined threshold;

Described relevance parameter based on described keyword and correspondence generates kind judging dictionary.

Optionally, determine the relevance parameter of described keyword and described predetermine class, comprising:

The method of card side's checking CHI is adopted to calculate the chi-square value of described keyword and described predetermine class as relevance parameter.

Optionally, described employing described kind judging dictionary carries out kind judging to the information of described textual form, comprising:

Keyword is extracted as keyword to be determined from the information of described textual form;

Described relevance parameter corresponding to described keyword to be determined is searched from described kind judging dictionary;

Obtain with reference to ratio, in the sample social network information of described reference ratio for correspondence, belong to the ratio shared by information of described predetermine class;

The described relevance parameter corresponding based on described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, wherein, described first degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and predetermine class, and described second degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and non-predetermined classification;

Judge the size of first degree of correlation and second degree of correlation; If described first degree of correlation is large, then the social network information that the information of described textual form is corresponding belongs to predetermine class.

Optionally, the described described relevance parameter corresponding based on described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, comprising:

Calculate the product of the described relevance parameter of described keyword to be determined as the first product, and be multiplied with reference to ratio with described by described first product again, result is as first degree of correlation;

The product of the difference of the described relevance parameter of calculating 1 and described keyword to be determined as the second product, and is multiplied 1 with described second product with the described difference with reference to ratio again, and result is as second degree of correlation.

According to the second aspect of disclosure embodiment, a kind of good friend's management devices for social network-i i-platform is provided, comprises:

Acquisition module, the part or all of social network information that the good friend being configured to obtain social network user issued;

Search module, the social network information being configured to get based on described acquisition module finds out the good friend of predefined type from the good friend of described user;

Pushing module, is configured to the list searching the good friend of the described predefined type that module searches goes out described in pushing to described user, carries out interruption-free setting with reminding user according to described list.

Optionally, search module described in comprise:

Text message obtains submodule, is configured to obtain the information of textual form corresponding to the content of described social network information;

Decision sub-module, is configured to the information obtaining the described textual form that submodule gets based on described text message, judges whether corresponding social network information belongs to predetermine class;

Statistics submodule, is configured to the result judged according to described decision sub-module, the related data of what the good friend adding up described user issued the belong to social network information of described predetermine class;

Search submodule, be configured to find out from the good friend of described user meet predetermined condition good friend as the good friend of predefined type, wherein, the described good friend meeting predetermined condition is the good friend that corresponding described related data exceedes predetermined threshold.

Optionally, described related data comprises following one or more:

The quantity belonging to the social network information of described predetermine class that the good friend of described user issued;

The social network information proportion belonging to described predetermine class that the good friend of described user issued.

Optionally, described text message acquisition submodule comprises:

Determine submodule, be configured to the expression forms of information determining each described social network information;

Extracting submodule, being configured to, according to corresponding to the described mode determining the described expression forms of information that submodule is determined, extract the information of textual form corresponding to the content of each described social network information;

Wherein, described expression forms of information comprises word, image, video, link and sound.

Optionally, described decision sub-module comprises:

Dictionary obtains submodule, is configured to obtain through training the kind judging dictionary obtained;

Kind judging submodule, described kind judging dictionary that submodule gets carries out kind judging to the information of described textual form to be configured to adopt described dictionary to obtain, to determine whether social network information corresponding to the information of described textual form belongs to predetermine class.

Optionally, described kind judging dictionary is trained in the following way and is obtained:

Obtain text message corresponding to multiple sample social network information as sample information, wherein, whether known described sample social network information belongs to described predetermine class;

Keyword is extracted from described sample information;

Determine the relevance parameter of described keyword and described predetermine class;

Extract and be more than or equal to keyword corresponding to the described relevance parameter of predetermined threshold;

Described relevance parameter based on described keyword and correspondence generates kind judging dictionary.

Optionally, determine the relevance parameter of described keyword and described predetermine class, comprising:

The method of card side's checking CHI is adopted to calculate the chi-square value of described keyword and described predetermine class as relevance parameter.

Optionally, described kind judging submodule comprises:

Keyword extraction submodule, is configured to extract keyword as keyword to be determined from the information of described textual form;

Parameter searches submodule, is configured to from described kind judging dictionary, search described relevance parameter corresponding to described keyword to be determined;

Reference ratio obtains submodule, is configured to obtain with reference to ratio, belongs to the ratio shared by information of described predetermine class in the sample social network information of described reference ratio for correspondence;

Calculating sub module, be configured to based on described relevance parameter corresponding to described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, wherein, described first degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and predetermine class, and described second degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and non-predetermined classification;

Judge submodule, be configured to the size of judgement first degree of correlation and second degree of correlation; If described first degree of correlation is large, then the social network information that the information of described textual form is corresponding belongs to predetermine class.

Optionally, described calculating sub module comprises:

First degree of correlation calculating sub module, is configured to the product of the described relevance parameter calculating described keyword to be determined as the first product, and is multiplied with reference to ratio with described by described first product again, and result is as first degree of correlation;

Second degree of correlation calculating sub module, is configured to the product of the difference of the described relevance parameter of calculating 1 and described keyword to be determined as the second product, and is multiplied 1 with described second product with the described difference with reference to ratio again, and result is as second degree of correlation.

According to the third aspect of disclosure embodiment, a kind of server is provided, comprises:

Processor;

For the memory of storage of processor executable instruction;

Wherein, described processor is configured to:

The part or all of social network information that the good friend obtaining social network user issued;

From the good friend of described user, the good friend of predefined type is found out based on described social network information;

Push the list of the good friend of described predefined type to described user, carry out interruption-free setting with reminding user according to described list.

The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:

A kind of friend management method for social network-i i-platform that above-described embodiment of the present disclosure provides, by the part or all of social network information issued based on the good friend of the social network user got, the good friend of predefined type is found out from the good friend of this user, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus save the time, improve the service efficiency of social networks.

The another kind that above-described embodiment of the present disclosure provides is for the friend management method of social network-i i-platform, by judging whether the social network information that good friend issues belongs to predetermine class, and according to the result of this judgement, the related data belonging to the social network information of predetermine class that the good friend of counting user issued, thus find out from the good friend of this user meet predetermined condition good friend as the good friend of predefined type, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

The another kind that above-described embodiment of the present disclosure provides is for the friend management method of social network-i i-platform, by determining the expression forms of information of social network information, and according to corresponding to the mode of this expression forms of information, extract the information of textual form corresponding to the content of social network information, find out from the good friend of this user further meet predetermined condition good friend as the good friend of predefined type, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

The another kind that above-described embodiment of the present disclosure provides is for the friend management method of social network-i i-platform, by adopting through training the kind judging dictionary obtained to carry out kind judging to the information of above-mentioned textual form, to determine whether social network information corresponding to the information of text form belongs to predetermine class, and according to the result of this judgement, the related data belonging to the social network information of predetermine class that the good friend of counting user issued, thus find out from the good friend of this user meet predetermined condition good friend as the good friend of predefined type, the list of the good friend of above-mentioned predefined type is pushed to this user, interruption-free setting is carried out according to this list with reminding user.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.

Accompanying drawing explanation

Accompanying drawing to be herein merged in specification and to form the part of this specification, shows and meets embodiment of the present disclosure, and is used from specification one and explains principle of the present disclosure.

Fig. 1 is the flow chart of a kind of friend management method for social network-i i-platform of the disclosure according to an exemplary embodiment;

Fig. 2 is the flow chart of the another kind of the disclosure according to an exemplary embodiment for the friend management method of social network-i i-platform;

Fig. 3 is the flow chart of the another kind of the disclosure according to an exemplary embodiment for the friend management method of social network-i i-platform;

Fig. 4 is the flow chart of the another kind of the disclosure according to an exemplary embodiment for the friend management method of social network-i i-platform;

Fig. 5 is the block diagram of a kind of good friend management devices for social network-i i-platform of the disclosure according to an exemplary embodiment;

Fig. 6 is the block diagram of the another kind of the disclosure according to an exemplary embodiment for good friend's management devices of social network-i i-platform;

Fig. 7 is the block diagram of the another kind of the disclosure according to an exemplary embodiment for good friend's management devices of social network-i i-platform;

Fig. 8 is the block diagram of the another kind of the disclosure according to an exemplary embodiment for good friend's management devices of social network-i i-platform;

Fig. 9 is the block diagram of the another kind of the disclosure according to an exemplary embodiment for good friend's management devices of social network-i i-platform;

Figure 10 is the block diagram of the another kind of the disclosure according to an exemplary embodiment for good friend's management devices of social network-i i-platform;

Figure 11 is a kind of exemplary system architecture figure that can apply disclosure embodiment of the disclosure according to an exemplary embodiment;

Figure 12 is a structural representation of a kind of good friend management devices for social network-i i-platform of the disclosure according to an exemplary embodiment.

Embodiment

Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Execution mode described in following exemplary embodiment does not represent all execution modes consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.

The term used in the disclosure is only for the object describing specific embodiment, and the not intended to be limiting disclosure." one ", " described " and " being somebody's turn to do " of the singulative used in disclosure and the accompanying claims book is also intended to comprise most form, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more project of listing be associated any or all may combine.

Term first, second, third, etc. may be adopted although should be appreciated that to describe various information in the disclosure, these information should not be limited to these terms.These terms are only used for the information of same type to be distinguished from each other out.Such as, when not departing from disclosure scope, the first information also can be called as the second information, and similarly, the second information also can be called as the first information.Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining ".

As shown in Figure 1, Fig. 1 is the flow chart of a kind of friend management method for social network-i i-platform according to an exemplary embodiment, and the method can be applied in server.The method comprises the following steps:

In a step 101, the part or all of social network information that the good friend obtaining social network user issued.

In the present embodiment, social networks can be IM (InstantMessenger, instant messaging) instrument (as micro-letter, QQ, Fetion etc.), or website (as facebook, Renren Network, microblogging etc.) etc.The information etc. of the dynamic or forwarding that social network information can be issued by social networks for social network user, such as, the dynamic message that social network information can be issued by circle of friends for micro-credit household, or the dynamic message that QQ user is issued by QQ space, or the dynamic message issued by microblogging of microblog users etc.

In the present embodiment, can in response to the generation of scheduled event, the part or all of social network information that the good friend obtaining social network user issued, and carry out subsequent operation, thus the list of the good friend of predefined type is pushed to above-mentioned user.In one implementation, the generation of scheduled event can be predetermined expiring, and the expected time of arrival can be predetermined time length (as a week, or month, or two months etc.).Such as, week about or one month, the list of the good friend of a predefined type is pushed to user.Separately plant in implementation one, the generation of scheduled event can also be the instruction of the list receiving the request propelling movement predefined type good friend that user sends.Such as, user can use the user end to server that terminal is installed to send request the instruction etc. of the list pushing predefined type good friend.Be appreciated that the generation of scheduled event can also be the generation of other event, the particular content of the disclosure to the generation of scheduled event does not limit.

In the present embodiment, in response to the generation of scheduled event, whole social network informations that the good friend that can obtain certain designated user once issued, whole social network informations (namely this designated user has the authority browsing above-mentioned social network information) that this designated user that the good friend that also can obtain certain designated user once issued can be browsed, the good friend that can also obtain certain designated user in certain time period (as nearest one week, or nearest one month, or nearest 1 year) social network information issued, the good friend that can also obtain certain designated user at random issued predetermined number (as, article 30, or social network information 50 etc.).Be appreciated that the disclosure is to not limiting in this respect.

In a step 102, from the good friend of above-mentioned user, the good friend of predefined type is found out based on above-mentioned social network information.

In general, people can to share knowledge in life, enjoyment and perception by issuing social network information with good friend, add with the interaction of good friend with exchange, meanwhile, also can by browsing the social network information of good friend, thus the recent developments of understanding good friend.But some people utilizes social network-i i-platform to issue some advertising messages, or issue some other easily offensive content (as constellation literary composition, chicken soup literary composition, subsides of starting a rumour, show off subsides etc.), and frequent brush screen, allows a lot of good friend detest, have impact on the experience of good friend.

In the present embodiment, the good friend of predefined type issues the good friend that certain classification information is more or the frequency that releases news is higher.Such as, the good friend of predefined type can be the more good friend of releasing advertisements classification information, or also can be issue the more good friend of chicken soup literary composition classification information, or can also be issue to start a rumour to paste the more good friend of classification information, or can also be that the frequency that releases news exceedes the good friend etc. of predetermined threshold.Because, whether certain good friend of user belongs to the good friend of predefined type, content or the Information issued situation of the information issued with this good friend are closely related, and therefore, the social network information can issued based on this good friend differentiates whether this good friend belongs to the good friend of predefined type.

In the present embodiment, to obtain certain social network user good friend in belong to the list of the good friend of predefined type, need the part or all of social network information that the good friend first obtaining this social network user issued, then, judge based on the type of above-mentioned social network information to each good friend, determine whether each good friend belongs to the good friend of predefined type, then from the good friend of this user, find out the good friend (good friend etc. that e.g., releasing advertisements classification information is more) belonging to predefined type.

In step 103, push the list of the good friend of predefined type to above-mentioned user, carry out interruption-free setting with reminding user according to this list.

In the present embodiment, when after the good friend belonging to predefined type in the good friend finding out social network user, obtain the list of the good friend belonging to predefined type in the good friend of this user, and this list is pushed to above-mentioned user, carry out interruption-free setting with reminding user according to this list.Wherein, it can be this good friend of shielding that interruption-free is arranged, and also can be delete this good friend, can also be other set-up mode, be appreciated that the disclosure does not limit the concrete mode aspect that interruption-free is arranged.

The friend management method for social network-i i-platform that above-described embodiment of the present disclosure provides, by the part or all of social network information issued based on the good friend of the social network user got, the good friend of predefined type is found out from the good friend of this user, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus save the time, improve the service efficiency of social networks.

As shown in Figure 2, the another kind of Fig. 2 according to an exemplary embodiment is for the flow chart of the friend management method of social network-i i-platform, this embodiment describes the process of the good friend finding out predefined type based on social network information from the good friend of user in detail, the method can be applied in server, comprises the following steps:

In step 201, the part or all of social network information that the good friend obtaining social network user issued.

In step 202., the information of textual form corresponding to the content of above-mentioned social network information is obtained.

In the present embodiment, above-mentioned social network information may be the information of textual form, also can be the information of image format, can also be the information etc. of link form.Information due to textual form is easier to process, therefore, after the part or all of social network information that the good friend getting social network user issued, first, corresponding process is carried out to above-mentioned social network information, obtain the information of textual form corresponding to the content of above-mentioned social network information, to carry out follow-up treatment and analysis.

Such as, if above-mentioned social network information is the information of textual form, then this information can directly be obtained.Again such as, if above-mentioned social network information is the information of link form, then can finds out map network resource according to this link, and therefrom extract the information of textual form.Again such as, if above-mentioned social network information is the information of image format, then can carry out image recognition processing to this image, extract the Word message in image, as the information etc. of textual form.

In step 203, based on the information of above-mentioned textual form, judge whether corresponding social network information belongs to predetermine class.

In the present embodiment, by the content of social network information, this social network information can be divided into several classification, and same social network information also can belong to multiple classification.The predetermine class of the present embodiment can be the classification separated according to any principle, can be the classification easily allowing other user dislike.Such as, the social network information of predetermine class can be other information of commercial paper, also can be the information of constellation literary composition classification, can also be the information of chicken soup literary composition classification, can also be start a rumour to paste the information etc. of classification, be appreciated that, can also have the information of other classification, the disclosure is to not limiting in this respect.

In the present embodiment, analyzing and processing can be carried out to the information of each textual form, thus judge whether corresponding social network information belongs to predetermine class.In one implementation, the information of the method for cluster to the above-mentioned all textual forms got can be adopted to carry out cluster analysis, thus judge whether social network information corresponding to the information of each textual form belongs to predetermine class.

In another kind of implementation, the discrimination model that training in advance is good can also be adopted, judge whether social network information corresponding to the information of each textual form belongs to predetermine class.Wherein, a corresponding a kind of predetermine class of discrimination model, can train different discrimination models for different predetermine class.Be appreciated that the method that other can also be adopted can to realize arbitrarily judges whether social network information corresponding to the information of textual form belongs to predetermine class, and the disclosure is to not limiting in this respect.

In step 204, according to the result of above-mentioned judgement, the related data of what the good friend adding up above-mentioned user issued the belong to social network information of predetermine class.

In the present embodiment, above-mentioned related data can comprise following one or more: the quantity belonging to the social network information of predetermine class that the good friend of above-mentioned user issued, and the social network information proportion belonging to predetermine class that the good friend of above-mentioned user issued.

In a kind of implementation of the present embodiment, the quantity of what the good friend that can add up above-mentioned user issued the belong to social network information of predetermine class, as above-mentioned related data.Such as, suppose that the information of predetermine class is other information of commercial paper, then the quantity (as number) of other information of commercial paper that each good friend that can add up above-mentioned user issued, as above-mentioned related data.

In the another kind of implementation of the present embodiment, the ratio shared by social network information of what the good friend that can also add up above-mentioned user issued belong to predetermine class, as above-mentioned related data.Such as, suppose that the information of predetermine class is other information of commercial paper, the quantity of other information of commercial paper that each good friend that can also add up above-mentioned user issued in certain hour section account for this time period the ratio of information sum issued, or with this time period the ratio of the quantity of non-advertisement classification information issued, as above-mentioned related data.

Be appreciated that related data can also be the data of other side, the concrete form aspect of the disclosure to related data does not limit.

In step 205, find out from the good friend of above-mentioned user meet predetermined condition good friend as the good friend of predefined type.

In the present embodiment, the good friend meeting predetermined condition is the good friend that corresponding related data exceedes predetermined threshold.Such as, suppose that the information of predetermine class is other information of commercial paper, then the good friend meeting predetermined condition can be the good friend of the quantity a predetermined level is exceeded threshold value of releasing advertisements classification information.The good friend meeting predetermined condition can also be the good friend that ratio that the advertisement classification information issued accounts for the information sum issued exceedes predetermined ratio threshold value.Using the good friend of good friend as predefined type meeting predetermined condition found out.Be appreciated that predetermined condition can also be other condition, the disclosure is to not limiting in this respect.

In step 206, push the list of the good friend of predefined type to above-mentioned user, carry out interruption-free setting with reminding user according to this list.

It should be noted that, for the step identical with Fig. 1 embodiment, no longer repeat in above-mentioned Fig. 2 embodiment, related content can see Fig. 1 embodiment.

The friend management method for social network-i i-platform that above-described embodiment of the present disclosure provides, by judging whether the social network information that good friend issues belongs to predetermine class, and according to the result of this judgement, the related data belonging to the social network information of predetermine class that the good friend of counting user issued, thus find out from the good friend of this user meet predetermined condition good friend as the good friend of predefined type, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

As shown in Figure 3, Fig. 3 is the flow chart of the another kind according to an exemplary embodiment for the friend management method of social network-i i-platform, this embodiment describes the process of the information obtaining textual form corresponding to the content of social network information in detail, the method may be used for, in server, comprising the following steps:

In step 301, the part or all of social network information that the good friend obtaining social network user issued.

In step 302, the expression forms of information of each above-mentioned social network information is determined.

In step 303, according to corresponding to the mode of above-mentioned expression forms of information, extract the information of textual form corresponding to the content of each above-mentioned social network information.

In the present embodiment, expression forms of information includes but not limited to word, image, video, link and sound etc.Before the information extracting textual form corresponding to the content of each above-mentioned social network information, first the expression forms of information determining each above-mentioned social network information is needed, because for the social network information that the form of expression is different, the mode extracting the information of corresponding textual form is different.Then, then according to corresponding to the mode of above-mentioned expression forms of information, the information of textual form corresponding to the content of each above-mentioned social network information is extracted.

In a kind of implementation of the present embodiment, if the expression forms of information of the social network information determined is word, then extracting directly goes out the word content of this social network information.

In the another kind of implementation of the present embodiment, if the expression forms of information of the social network information determined is image, then first can carry out image recognition to this image, extract the Word message comprised in this image, the information of the textual form that the content as this social network information is corresponding.

In the another kind of implementation of the present embodiment, if the expression forms of information of the social network information determined is image, feature extraction can also be carried out to this image, according to the feature of the image extracted, the text description relevant to this image is obtained, the information of the textual form that the content as this social network information is corresponding from network.

In another implementation of the present embodiment, if the expression forms of information of the social network information determined is link, corresponding Internet resources (as linked corresponding webpage etc.) can be found out according to link and then from above-mentioned network money, obtain relevant Word message, the information of the textual form that the content as this social network information is corresponding.

In another implementation of the present embodiment, if the expression forms of information of the social network information determined is video, caption information can be obtained from the data of this video, or frame of video is identified thus obtains the related text information in video, the information of the textual form that the content as this social network information is corresponding.

In another implementation of the present embodiment, if the expression forms of information of the social network information determined is sound, first speech recognition can be carried out to this sound, by this converting voice message into text message, the information of the textual form that the content as this social network information is corresponding.

In step 304, based on the information of above-mentioned textual form, judge whether corresponding social network information belongs to predetermine class.

In step 305, according to the result of above-mentioned judgement, the related data of what the good friend adding up above-mentioned user issued the belong to social network information of predetermine class.

Within step 306, find out from the good friend of above-mentioned user meet predetermined condition good friend as the good friend of predefined type.

In step 307, push the list of the good friend of predefined type to above-mentioned user, carry out interruption-free setting with reminding user according to this list.

It should be noted that, for the step identical with Fig. 1 with Fig. 2 embodiment, no longer repeat in above-mentioned Fig. 3 embodiment, related content can see Fig. 1 and Fig. 2 embodiment.

The friend management method for social network-i i-platform that above-described embodiment of the present disclosure provides, by determining the expression forms of information of social network information, and according to corresponding to the mode of this expression forms of information, extract the information of textual form corresponding to the content of social network information, find out from the good friend of this user further meet predetermined condition good friend as the good friend of predefined type, and the list of the good friend of above-mentioned predefined type is pushed to this user, carry out interruption-free setting with reminding user according to this list.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

As shown in Figure 4, Fig. 4 is the flow chart of the another kind according to an exemplary embodiment for the friend management method of social network-i i-platform, this embodiment describes the information based on textual form in detail, judge whether corresponding social network information belongs to the process of predetermine class, the method may be used for, in server, comprising the following steps:

In step 401, the part or all of social network information that the good friend obtaining social network user issued.

In step 402, the information of textual form corresponding to the content of above-mentioned social network information is obtained.

In step 403, obtain through training the kind judging dictionary obtained.

In the present embodiment, can the better kind judging dictionary of training in advance, each kind judging dictionary can judge a kind.Need to judge which classification, just obtain the kind judging dictionary that this classification is corresponding.Kind judging dictionary can be trained at home server and be stored in home server, when needing kind judging dictionary, directly can obtain from this locality; Also can train at other server and be stored in home server, when needing kind judging dictionary, directly obtain from this locality; Can also train at other server and be stored in other server, when needing kind judging dictionary, can be obtained from other server by network.

In the present embodiment, kind judging dictionary can be trained in the following way and be obtained: first, obtains text message corresponding to multiple sample social network information as sample information, and wherein, whether this sample social network information known belongs to predetermine class.Specifically, the social network information of any amount can be obtained arbitrarily from the social network information that multiple user issues, as sample social network information.Then manually these information are classified according to predetermine class.Such as, suppose that predetermine class is advertisement classification, then these sample social network informations can be divided into other information of commercial paper and other information of non-commercial paper.Extract text message corresponding to these sample social network informations again as sample information, and classification logotype is carried out to sample information, e.g., identify by 1 pair of other information of commercial paper, with 0, other information of non-commercial paper is identified.

Then, from these sample informations above-mentioned, keyword is extracted.Specifically, can extract in sample information that some have the word of practical significance, as keyword, such as some nouns, verb, adjective etc.And some do not have the function word of practical significance, if some prepositions, conjunction, auxiliary word, modal particle etc. are not usually by as keyword.The keyword extracted can form a crucial phrase, guarantees there is not dittograph language in crucial phrase.

Then, the relevance parameter of each keyword in crucial phrase and above-mentioned predetermine class is determined.Wherein, the relevance parameter of keyword and predetermine class is the parameter of the correlation that can represent arbitrarily keyword and predetermine class, and specifically the ask method of the disclosure to the parameter of correlation does not limit.In a kind of implementation of the present embodiment, card side can be adopted to verify, and the method for CHI calculates the chi-square value of each keyword and predetermine class as relevance parameter.

Such as, suppose that predetermine class is advertisement classification, carry out identified ad classification with 1, identify non-advertisement classification with 0." preferential " this keyword is comprised in crucial phrase, in sample information, not only the sample information belonging to other information of commercial paper but also comprise " preferential " this keyword has A bar, do not belong to other information of commercial paper but the sample information comprising " preferential " this keyword has B bar, only belong to the sample information that other information of commercial paper do not comprise " preferential " this keyword and have C bar, not only the sample information not belonging to other information of commercial paper but also do not comprise " preferential " this keyword has D bar, and the total number of sample information is N bar.With P (x ∣ c ₁) represent the chi-square value of keyword and predetermine class, represent the relevance parameter of keyword and predetermine class with Ω, wherein, x represents keyword " preferential ", c ₁represent advertisement classification.Then

$P\left(x\right|c_1)=\frac{N{(AD-BC)}^2}{(A+C)(A+B)(B+D)(C+D)}$

Ω=P (x ∣ c can be made ₁).And be fixed value due to A+C and B+D and N, therefore, can also make $\mathrm{\Ω}=P\left(x\right|c_1)*(A+C)(B+d)/N-\frac{{(AD-BC)}^2}{(A+B)(C+D)},$ Ω can also be made to get and P (x ∣ c ₁) relevant some parameter, the concrete value aspect of the disclosure to Ω does not limit.

Finally, extract and be more than or equal to keyword corresponding to the relevance parameter of predetermined threshold, and generate kind judging dictionary based on the relevance parameter of above-mentioned keyword and correspondence.Specifically, first, preset the predetermined threshold of a relevance parameter, in the crucial phrase then obtained from preceding step, find out the keyword that corresponding relevance parameter is more than or equal to predetermined threshold, and by these keyword extraction out.Relevance parameter based on above-mentioned keyword and correspondence generates kind judging dictionary, wherein, comprises the information of the relevance parameter of above-mentioned keyword and correspondence in this kind judging dictionary.

In step 404, this kind judging dictionary is adopted to carry out kind judging to the information of above-mentioned textual form, to determine whether social network information corresponding to the information of text form belongs to predetermine class.

In the present embodiment, this kind judging dictionary can be adopted to carry out kind judging to the information of above-mentioned textual form, thus determine whether social network information corresponding to the information of text form belongs to predetermine class.Specifically, for the information of textual form corresponding to every bar social network information, first, from the information of text form, keyword is extracted as keyword to be determined.Then, from the above-mentioned kind judging dictionary trained, the relevance parameter that in the information of text form, all keywords to be determined are corresponding is found out.Such as, suppose, predetermine class is advertisement classification, and the keyword all to be determined extracted from the information of above-mentioned textual form comprises A, B, C, D, E, c ₁represent advertisement classification, c ₂represent advertisement classification.These keywords are found out and other relevance parameter of commercial paper is respectively P (A ∣ c from the advertisement kind judging dictionary trained ₁), P (B ∣ c ₁), P (C ∣ c ₁), P (D ∣ c ₁), P (E ∣ c ₁).

Then, obtain with reference to ratio, in the sample social network information of reference ratio for correspondence, belong to the ratio shared by information of predetermine class.When training kind judging dictionary, calculating above-mentioned with reference to ratio simultaneously, then associatedly storing above-mentioned with corresponding dictionary with reference to ratio.In conjunction with above-mentioned example, such as, suppose, when training dictionary, have m bar to belong to other sample social network information of commercial paper, other n bar belongs to other sample social network information of non-commercial paper, represents with reference to ratio, then α=m/m+n with α.Associatedly store with reference to ratio α and this advertisement kind judging dictionary.When adopting above-mentioned advertisement kind judging dictionary to carry out kind judging to the information of textual form, can obtain above-mentioned with reference to ratio from the data stored.

Then, the above-mentioned relevance parameter corresponding based on above-mentioned keyword to be determined and reference ratio, calculate first degree of correlation and second degree of correlation, wherein, first degree of correlation is the degree of correlation of social network information corresponding to the information of above-mentioned textual form and predetermine class, and second degree of correlation is the degree of correlation of social network information corresponding to the information of above-mentioned textual form and non-predetermined classification.In the present embodiment, can calculate the product of the relevance parameter of all keywords to be determined in the information of above-mentioned textual form as the first product, and be multiplied with reference to ratio with above-mentioned by the first product again, result is as first degree of correlation.In the information of calculating 1 and above-mentioned textual form, the product of the difference of the above-mentioned relevance parameter of each keyword to be determined is as the second product, and is multiplied 1 with the second product with the above-mentioned difference with reference to ratio again, and result is as second degree of correlation.

In conjunction with above-mentioned example, such as, first degree of correlation can use P (c ₁∣ X) represent, second degree of correlation can use P (c ₂∣ X) represent, wherein, X represents the social network information that the information of above-mentioned form is corresponding, then

P(c ₁∣X)＝P(A∣c ₁)·P(B∣c ₁)·P(C∣c ₁)·P(D∣c ₁)·P(E∣c ₁)·α

P(c ₂∣X)＝[1-P(A∣c ₁)]·[1-P(B∣c ₁)]·[1-P(C∣c ₁)]·[1-P(D∣c ₁)]·[1-P(E∣c ₁)]·(1-α)

Finally, judge the size of first degree of correlation and second degree of correlation, if first degree of correlation is large, then the social network information that the information of text form is corresponding belongs to predetermine class.If second degree of correlation is large, then the social network information that the information of text form is corresponding belongs to non-predetermined classification.Such as, in conjunction with above-mentioned example, if P is (c ₁∣ X) > P (c ₂∣ X), then the social network information that the information of explanation text form is corresponding belongs to other information of commercial paper.If P is (c ₁∣ X) < P (c ₂∣ X), then the social network information that the information of explanation text form is corresponding belongs to other information of non-commercial paper.

In step 405, according to the result of above-mentioned judgement, the related data of what the good friend adding up above-mentioned user issued the belong to social network information of predetermine class.

In a step 406, find out from the good friend of above-mentioned user meet predetermined condition good friend as the good friend of predefined type.

In step 407, push the list of the good friend of predefined type to above-mentioned user, carry out interruption-free setting with reminding user according to this list.

It should be noted that, for the step identical with Fig. 1 with Fig. 2 embodiment, no longer repeat in above-mentioned Fig. 4 embodiment, related content can see Fig. 1 and Fig. 2 embodiment.

The friend management method for social network-i i-platform that above-described embodiment of the present disclosure provides, by adopting through training the kind judging dictionary obtained to carry out kind judging to the information of above-mentioned textual form, to determine whether social network information corresponding to the information of text form belongs to predetermine class, and according to the result of this judgement, the related data belonging to the social network information of predetermine class that the good friend of counting user issued, thus find out from the good friend of this user meet predetermined condition good friend as the good friend of predefined type, the list of the good friend of above-mentioned predefined type is pushed to this user, interruption-free setting is carried out according to this list with reminding user.Manually search the good friend of predefined type without the need to user, thus contribute to saving time, improve the service efficiency of social networks.

Although it should be noted that the operation describing the inventive method in the accompanying drawings with particular order, this is not that requirement or hint must perform these operations according to this particular order, or must perform the result that all shown operation could realize expectation.On the contrary, the step described in flow chart can change execution sequence.Such as, in the flow process 400 of Fig. 4, first can perform step 403, obtain through training the kind judging dictionary that obtains, and then perform step 402, obtain the information of textual form corresponding to the content of above-mentioned social network information.Additionally or alternatively, some step can be omitted, multiple step be merged into a step and perform, and/or a step is decomposed into multiple step and perform.

Corresponding with the aforementioned friend management method embodiment for social network-i i-platform, the disclosure additionally provides good friend's management devices for social network-i i-platform and the embodiment of server applied thereof.

As shown in Figure 5, Fig. 5 is a kind of good friend management devices block diagram for social network-i i-platform of the disclosure according to an exemplary embodiment, and this device comprises: acquisition module 501, searches module 502 and pushing module 503.

Wherein, acquisition module 501, the part or all of social network information that the good friend being configured to obtain social network user issued.

Search module 502, the social network information being configured to get based on acquisition module 501 finds out the good friend of predefined type from the good friend of above-mentioned user.

Pushing module 503, is configured to push to above-mentioned user the list searching the good friend of the predefined type that module 502 finds out, carries out interruption-free setting with reminding user according to this list.

As shown in Figure 6, Fig. 6 is the good friend management devices block diagram of the another kind of the disclosure according to an exemplary embodiment for social network-i i-platform, this embodiment is on aforementioned basis embodiment illustrated in fig. 5, search module 502 can comprise: text message obtains submodule 601, decision sub-module 602, adds up submodule 603 and searches submodule 604.

Wherein, text message obtains submodule 601, is configured to obtain the information of textual form corresponding to the content of above-mentioned social network information.

Decision sub-module 602, is configured to the information obtaining the textual form that submodule 601 gets based on text message, judges whether corresponding social network information belongs to predetermine class.

Statistics submodule 603, is configured to the result judged according to decision sub-module 602, the related data of what the good friend adding up above-mentioned user issued the belong to social network information of predetermine class.

Search submodule 604, be configured to find out from the good friend of above-mentioned user meet predetermined condition good friend as the good friend of predefined type, wherein, the good friend meeting predetermined condition is the good friend that corresponding related data exceedes predetermined threshold.

In some Alternate embodiments, above-mentioned related data comprises following one or more: the quantity belonging to the social network information of predetermine class that the good friend of user issued.The social network information proportion belonging to predetermine class that the good friend of user issued.

As shown in Figure 7, Fig. 7 is the good friend management devices block diagram of the another kind of the disclosure according to an exemplary embodiment for social network-i i-platform, this embodiment is on aforementioned basis embodiment illustrated in fig. 6, and text message obtains submodule 601 and can comprise: determine submodule 701 and extract submodule 702.

Wherein, determine submodule 701, be configured to the expression forms of information determining each social network information.

Extract submodule 702, be configured to according to corresponding to the mode determining the expression forms of information that submodule 701 is determined, extract the information of textual form corresponding to the content of each social network information.

Wherein, above-mentioned expression forms of information comprises word, image, video, link and sound.

As shown in Figure 8, Fig. 8 is the good friend management devices block diagram of the another kind of the disclosure according to an exemplary embodiment for social network-i i-platform, this embodiment is on aforementioned basis embodiment illustrated in fig. 6, and decision sub-module 602 can comprise: dictionary obtains submodule 801 and kind judging submodule 802.

Wherein, dictionary obtains submodule 801, is configured to obtain through training the kind judging dictionary obtained.

Kind judging submodule 802, is configured to adopt dictionary to obtain the kind judging dictionary that gets of submodule 801 and carries out kind judging to the information of above-mentioned textual form, to determine whether social network information corresponding to the information of text form belongs to predetermine class.

In some Alternate embodiments, above-mentioned kind judging dictionary is trained in the following way and is obtained: obtain text message corresponding to multiple sample social network information as sample information, and wherein, whether known above-mentioned sample social network information belongs to predetermine class.Keyword is extracted from above-mentioned sample information.Determine the relevance parameter of this keyword and predetermine class.Extract and be more than or equal to keyword corresponding to the described relevance parameter of predetermined threshold.Relevance parameter based on this keyword and correspondence generates kind judging dictionary.

In some Alternate embodiments, determine the relevance parameter of keyword and predetermine class, comprising: adopt the method for card side's checking CHI to calculate the chi-square value of this keyword and predetermine class as relevance parameter.

As shown in Figure 9, Fig. 9 is the good friend management devices block diagram of the another kind of the disclosure according to an exemplary embodiment for social network-i i-platform, this embodiment is on aforementioned basis embodiment illustrated in fig. 8, kind judging submodule 802 can comprise: keyword extraction submodule 901, parameter searches submodule 902, submodule 903 is obtained, calculating sub module 904 and judge submodule 905 with reference to ratio.

Wherein, keyword extraction submodule 901, is configured to extract keyword as keyword to be determined from the information of above-mentioned textual form.

Parameter searches submodule 902, is configured to from above-mentioned kind judging dictionary, search above-mentioned relevance parameter corresponding to keyword to be determined.

Reference ratio obtains submodule 903, is configured to obtain with reference to ratio, belongs to the ratio shared by information of predetermine class in the sample social network information of above-mentioned reference ratio for correspondence.

Calculating sub module 904, be configured to based on relevance parameter corresponding to above-mentioned keyword to be determined and with reference to ratio, calculate first degree of correlation and second degree of correlation, wherein, first degree of correlation is the degree of correlation of social network information corresponding to the information of above-mentioned textual form and predetermine class, and second degree of correlation is the degree of correlation of social network information corresponding to the information of above-mentioned textual form and non-predetermined classification.

Judge submodule 905, be configured to the size of first degree of correlation and second degree of correlation judging that calculating sub module 904 calculates.If first degree of correlation is large, then the social network information that the information of above-mentioned textual form is corresponding belongs to predetermine class.

As shown in Figure 10, Figure 10 is the good friend management devices block diagram of the another kind of the disclosure according to an exemplary embodiment for social network-i i-platform, this embodiment is on aforementioned basis embodiment illustrated in fig. 9, and calculating sub module 904 can comprise: the first degree of correlation calculating sub module 1001 and the second degree of correlation calculating sub module 1002.

Wherein, the first degree of correlation calculating sub module 1001, is configured to the product of the relevance parameter calculating above-mentioned keyword to be determined as the first product, and is multiplied again with reference to ratio by the first product, and result is as first degree of correlation.

Second degree of correlation calculating sub module 1002, be configured to the product of the difference of the relevance parameter of calculating 1 and keyword to be determined as the second product, and be multiplied 1 with the second product with the difference with reference to ratio again, result is as second degree of correlation.

Should be appreciated that said apparatus can pre-set in the server, also can be loaded in server by modes such as downloads.Corresponding units in said apparatus can cooperatively interact the scheme realizing managing for the good friend of social network-i i-platform with the unit in server.

For device embodiment, because it corresponds essentially to embodiment of the method, so relevant part illustrates see the part of embodiment of the method.Device embodiment described above is only schematic, the wherein said modular unit illustrated as separating component or can may not be and physically separates, parts as modular unit display can be or may not be physical module unit, namely can be positioned at a place, or also can be distributed on multiple mixed-media network modules mixed-media unit.Some or all of module wherein can be selected according to the actual needs to realize the object of disclosure scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.

Figure 11 shows the exemplary system architecture can applying disclosure embodiment.

As shown in figure 11, system architecture 1100 can comprise terminal equipment 1101,1102, network 1103 and server 1104,1105.Network 1103 for providing the medium of communication link between terminal equipment 1101,1102 and server 1104.Network 1103 can comprise various connection type, such as wired, wireless communication link or fiber optic cables etc.

User 1110 can use terminal equipment 1101,1102 mutual by network 1103 and server 1104, to receive or to send message etc.Terminal equipment 1101,1102 can be provided with various client application, such as various immediate communication tool, social networks client, browser etc.

Terminal equipment 1101,1102 can be various electronic equipment, includes but not limited to smart mobile phone, panel computer, personal digital assistant, pocket computer on knee and Intelligent wearable equipment etc.

Server 1104,1105 can be to provide the server of various service.The process such as server can store the data received, analysis, and result is fed back to terminal equipment.Server can provide service in response to the service request of user.Such as, server can push the list etc. of the good friend of predefined type to terminal equipment.Be appreciated that a server can provide one or more to serve, same service also can be provided by multiple server.

Should be appreciated that, the number of the terminal equipment in Figure 11, network and server is only schematic.According to realizing needs, the terminal equipment of arbitrary number, network and server can be had.

Accordingly, the disclosure also provides a kind of server, and this server includes processor; For the memory of storage of processor executable instruction; Wherein, this processor is configured to:

The part or all of social network information that the good friend obtaining social network user issued;

From the good friend of described user, the good friend of predefined type is found out based on described social network information;

Push the list of the good friend of described predefined type to described user, carry out interruption-free setting with reminding user according to described list.

Figure 12 is a structural representation of the device 1200 that a kind of good friend for social network-i i-platform according to an exemplary embodiment manages.Such as, device 1200 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant etc.

With reference to Figure 12, device 1200 can comprise following one or more assembly: processing components 1202, memory 1204, power supply module 1206, multimedia groupware 1208, audio-frequency assembly 1210, the interface 1212 of I/O (I/O), sensor cluster 1214, and communications component 1216.

The integrated operation of the usual control device 1200 of processing components 1202, such as with display, call, data communication, camera operation and record operate the operation be associated.Treatment element 1202 can comprise one or more processor 1220 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 1202 can comprise one or more module, and what be convenient between processing components 1202 and other assemblies is mutual.Such as, processing components 1202 can comprise multi-media module, mutual with what facilitate between multimedia groupware 1208 and processing components 1202.

Memory 1204 is configured to store various types of data to be supported in the operation of device 1200.The example of these data comprises for any application program of operation on device 1200 or the instruction of method, contact data, telephone book data, message, picture, video etc.Memory 1204 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or CD.

The various assemblies that power supply module 1206 is device 1200 provide electric power.Power supply module 1206 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 1200 and be associated.

Multimedia groupware 1208 is included in the screen providing an output interface between described device 1200 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 1208 comprises a front-facing camera and/or post-positioned pick-up head.When device 1200 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.

Audio-frequency assembly 1210 is configured to export and/or input audio signal.Such as, audio-frequency assembly 1210 comprises a microphone (MIC), and when device 1200 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The audio signal received can be stored in memory 1204 further or be sent via communications component 1216.In certain embodiments, audio-frequency assembly 1210 also comprises a loud speaker, for output audio signal.

I/O interface 1212 is for providing interface between processing components 1202 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.

Sensor cluster 1214 comprises one or more transducer, for providing the state estimation of various aspects for device 1200.Such as, sensor cluster 1214 can detect the opening/closing state of device 1200, the relative positioning of assembly, such as described assembly is display and the keypad of device 1200, the position of all right checkout gear 1200 of sensor cluster 1214 or device 1200 assemblies changes, the presence or absence that user contacts with device 1200, the variations in temperature of device 1200 orientation or acceleration/deceleration and device 1200.Sensor cluster 1214 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor cluster 1214 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor cluster 1214 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor, microwave remote sensor or temperature sensor.

Communications component 1216 is configured to the communication being convenient to wired or wireless mode between device 1200 and other equipment.Device 1200 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 1216 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communications component 1216 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.

In the exemplary embodiment, device 1200 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.

In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the memory 1204 of instruction, above-mentioned instruction can perform said method by the processor 1220 of device 1200.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.

Those skilled in the art, at consideration specification and after putting into practice invention disclosed herein, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Specification and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.

Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.

Claims (18)

1. for a friend management method for social network-i i-platform, it is characterized in that, described method comprises:

The part or all of social network information that the good friend obtaining social network user issued;

From the good friend of described user, the good friend of predefined type is found out based on described social network information;

Push the list of the good friend of described predefined type to described user, carry out interruption-free setting with reminding user according to described list.

2. method according to claim 1, is characterized in that, the described good friend finding out predefined type based on described social network information from the good friend of described user, comprising:

Obtain the information of textual form corresponding to the content of described social network information;

Based on the information of described textual form, judge whether corresponding social network information belongs to predetermine class;

According to the result of described judgement, the related data of what the good friend adding up described user issued the belong to social network information of described predetermine class;

Find out from the good friend of described user meet predetermined condition good friend as the good friend of predefined type, wherein, the described good friend meeting predetermined condition is the good friend that corresponding described related data exceedes predetermined threshold.

3. method according to claim 2, is characterized in that, described related data comprises following one or more:

The quantity belonging to the social network information of described predetermine class that the good friend of described user issued;

The social network information proportion belonging to described predetermine class that the good friend of described user issued.

4. method according to claim 2, is characterized in that, the information of the textual form that the content of the described social network information of described acquisition is corresponding, comprising:

Determine the expression forms of information of each described social network information;

According to corresponding to the mode of described expression forms of information, extract the information of textual form corresponding to the content of each described social network information;

Wherein, described expression forms of information comprises word, image, video, link and sound.

5. method according to claim 2, is characterized in that, the described information based on described textual form, judges whether corresponding social network information belongs to predetermine class, comprising:

Obtain through training the kind judging dictionary obtained;

Described kind judging dictionary is adopted to carry out kind judging to the information of described textual form, to determine whether social network information corresponding to the information of described textual form belongs to predetermine class.

6. method according to claim 5, is characterized in that, described kind judging dictionary is trained in the following way and obtained:

Obtain text message corresponding to multiple sample social network information as sample information, wherein, whether known described sample social network information belongs to described predetermine class;

Keyword is extracted from described sample information;

Determine the relevance parameter of described keyword and described predetermine class;

Extract and be more than or equal to keyword corresponding to the described relevance parameter of predetermined threshold;

Described relevance parameter based on described keyword and correspondence generates kind judging dictionary.

7. method according to claim 6, is characterized in that, the described relevance parameter determining described keyword and described predetermine class, comprising:

The method of card side's checking CHI is adopted to calculate the chi-square value of described keyword and described predetermine class as relevance parameter.

8. method according to claim 6, is characterized in that, described employing described kind judging dictionary carries out kind judging to the information of described textual form, comprising:

Keyword is extracted as keyword to be determined from the information of described textual form;

Described relevance parameter corresponding to described keyword to be determined is searched from described kind judging dictionary;

Obtain with reference to ratio, in the sample social network information of described reference ratio for correspondence, belong to the ratio shared by information of described predetermine class;

The described relevance parameter corresponding based on described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, wherein, described first degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and predetermine class, and described second degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and non-predetermined classification;

Judge the size of first degree of correlation and second degree of correlation; If described first degree of correlation is large, then the social network information that the information of described textual form is corresponding belongs to predetermine class.

9. method according to claim 8, is characterized in that, the described described relevance parameter corresponding based on described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, comprising:

Calculate the product of the described relevance parameter of described keyword to be determined as the first product, and be multiplied with reference to ratio with described by described first product again, result is as first degree of correlation;

The product of the difference of the described relevance parameter of calculating 1 and described keyword to be determined as the second product, and is multiplied 1 with described second product with the described difference with reference to ratio again, and result is as second degree of correlation.

10. for good friend's management devices of social network-i i-platform, it is characterized in that, described device comprises:

Acquisition module, the part or all of social network information that the good friend being configured to obtain social network user issued;

Search module, the social network information being configured to get based on described acquisition module finds out the good friend of predefined type from the good friend of described user;

Pushing module, is configured to the list searching the good friend of the described predefined type that module searches goes out described in pushing to described user, carries out interruption-free setting with reminding user according to described list.

11. devices according to claim 10, is characterized in that, described in search module and comprise:

Text message obtains submodule, is configured to obtain the information of textual form corresponding to the content of described social network information;

Decision sub-module, is configured to the information obtaining the described textual form that submodule gets based on described text message, judges whether corresponding social network information belongs to predetermine class;

Statistics submodule, is configured to the result judged according to described decision sub-module, the related data of what the good friend adding up described user issued the belong to social network information of described predetermine class;

Search submodule, be configured to find out from the good friend of described user meet predetermined condition good friend as the good friend of predefined type, wherein, the described good friend meeting predetermined condition is the good friend that corresponding described related data exceedes predetermined threshold.

12. devices according to claim 11, is characterized in that, described related data comprises following one or more:

The quantity belonging to the social network information of described predetermine class that the good friend of described user issued;

The social network information proportion belonging to described predetermine class that the good friend of described user issued.

13. devices according to claim 11, is characterized in that, described text message obtains submodule and comprises:

Determine submodule, be configured to the expression forms of information determining each described social network information;

Extracting submodule, being configured to, according to corresponding to the described mode determining the described expression forms of information that submodule is determined, extract the information of textual form corresponding to the content of each described social network information;

Wherein, described expression forms of information comprises word, image, video, link and sound.

14. devices according to claim 11, is characterized in that, described decision sub-module comprises:

Dictionary obtains submodule, is configured to obtain through training the kind judging dictionary obtained;

Kind judging submodule, described kind judging dictionary that submodule gets carries out kind judging to the information of described textual form to be configured to adopt described dictionary to obtain, to determine whether social network information corresponding to the information of described textual form belongs to predetermine class.

15. devices according to claim 14, is characterized in that, described kind judging dictionary is trained in the following way and obtained:

Obtain text message corresponding to multiple sample social network information as sample information, wherein, whether known described sample social network information belongs to described predetermine class;

Keyword is extracted from described sample information;

Determine the relevance parameter of described keyword and described predetermine class;

Extract and be more than or equal to keyword corresponding to the described relevance parameter of predetermined threshold;

Described relevance parameter based on described keyword and correspondence generates kind judging dictionary.

16. devices according to claim 15, is characterized in that, described kind judging submodule comprises:

Keyword extraction submodule, is configured to extract keyword as keyword to be determined from the information of described textual form;

Parameter searches submodule, is configured to from described kind judging dictionary, search described relevance parameter corresponding to described keyword to be determined;

Reference ratio obtains submodule, is configured to obtain with reference to ratio, belongs to the ratio shared by information of described predetermine class in the sample social network information of described reference ratio for correspondence;

Calculating sub module, be configured to based on described relevance parameter corresponding to described keyword to be determined and described reference ratio, calculate first degree of correlation and second degree of correlation, wherein, described first degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and predetermine class, and described second degree of correlation is the degree of correlation of social network information corresponding to the information of described textual form and non-predetermined classification;

Judge submodule, be configured to the size of first degree of correlation and second degree of correlation judging that described calculating sub module calculates; If described first degree of correlation is large, then the social network information that the information of described textual form is corresponding belongs to predetermine class.

17. devices according to claim 16, is characterized in that, described calculating sub module comprises:

First degree of correlation calculating sub module, is configured to the product of the described relevance parameter calculating described keyword to be determined as the first product, and is multiplied with reference to ratio with described by described first product again, and result is as first degree of correlation;

Second degree of correlation calculating sub module, is configured to the product of the difference of the described relevance parameter of calculating 1 and described keyword to be determined as the second product, and is multiplied 1 with described second product with the described difference with reference to ratio again, and result is as second degree of correlation.

18. 1 kinds of servers, is characterized in that, comprising:

Processor;

For the memory of storage of processor executable instruction;

Wherein, described processor is configured to:

The part or all of social network information that the good friend obtaining social network user issued;

From the good friend of described user, the good friend of predefined type is found out based on described social network information;

Push the list of the good friend of described predefined type to described user, carry out interruption-free setting with reminding user according to described list.