CN102523274B - Based on wireless personalized accurate information active pushing system and the method for core-network side - Google Patents
Based on wireless personalized accurate information active pushing system and the method for core-network side Download PDFInfo
- Publication number
- CN102523274B CN102523274B CN201110406878.1A CN201110406878A CN102523274B CN 102523274 B CN102523274 B CN 102523274B CN 201110406878 A CN201110406878 A CN 201110406878A CN 102523274 B CN102523274 B CN 102523274B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- core
- customized information
- personalized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application provides a kind of wireless personalized accurate information active pushing system based on core-network side and method, wherein, described method comprises: the 3G wireless network connection request that step S11, reception user submit to, and described connection request comprises subscriber identity information; Step S12, judge whether to there is customized information record corresponding to described subscriber identity information; If so, then step S13 is performed; Step S13, judge whether described customized information record meets presetting rule, if so, then perform step S14; Step S14, according to described customized information record, to this user's pushing personalized page.The application can provide personalized service accurately for user, and the ease for operation that the 3G business promoting user uses, reduce the use of flow.
Description
Technical field
The application relates to the technical field of mobile communication, particularly relate to a kind of wireless personalized accurate information active pushing system based on core-network side, a kind of wireless personalized accurate information active push method based on core-network side, and, a kind of wireless personalized accurate information active push device based on core-network side.
Background technology
People, to the instantaneity of information and personalized demand, promote the fast development of 3G mobile network.But the application of wireless 3G and the application of the Internet have huge difference:
One, terminal type variation, and terminal display size is far smaller than internet terminal (PC etc.), and the few of ancillary hardware of the use of wireless terminal (keyboard, mouse etc.), operation ease for use is nothing like the Internet;
Its two, the Internet is very universal, the mode of expense many employings monthly payment of fixed network, and therefore people can not take notice of very much the consumption of flow, but 3G wireless network just rises, the concern to flow when the network hardware cost of operator result in wireless Internet access.
For promoting the experience of the wireless 3G application of user, in prior art, domestic each mobile communication carrier has released one after another respective 3G wireless portal, as " the fertile door " of UNICOM, " mobile dream network " of movement, " wing space, sky " of telecommunications, but, this type of wireless portal is the popularized service released for all mobile subscribers, although provide user's registering service, the personalized services such as querying individual tariff information, because needs are progressively selected by user and inputted to face page by page, with the customized information searched for and search needed for it, operate very complicated, loaded down with trivial details, and extremely expend flow.
Therefore, the technical problem needing those skilled in the art urgently to solve at present is exactly: propose a kind of wireless personalized accurate information active push mechanism based on core-network side, in order to provide personalized service accurately for user, and the ease for operation that the 3G business promoting user uses, reduce the use of flow.
Summary of the invention
The object of the application is, provides a kind of wireless personalized accurate information active push method based on core-network side, provides personalized service accurately for user, and the ease for operation that the 3G business promoting user uses, reduce the use of flow.
Accordingly, present invention also provides a kind of wireless personalized accurate information active pushing system based on core-network side, and a kind of wireless personalized accurate information active push device based on core-network side, in order to ensure said method realization in practice and application.
In order to solve the problem, this application discloses a kind of wireless personalized accurate information active pushing system based on core-network side, comprise the equipment of the core network being mounted in and core net accepting wireless user's solicited message, described equipment of the core network by the light splitting of wireless user's solicited message or mirror image to the user's discriminance analysis navigation module in core net, user's request sends to the lift-launch user ID identification that can provide on the internet to identify with accurate by described core network, accurate personal page is provided and user individual is revised to user's precision individual character WEB server of preserving.
Preferably, described user identifies to share navigation module is equipped with and carries out to user user behavior analysis engine that behavioural analysis and individual business excavate and user identifies engine.
Preferably, the data feedback after Accurate Analysis to core network device, is accurately accessed precision homepage by core network device to user and is guided by described user's discriminance analysis navigation module.
The embodiment of the present application also discloses a kind of wireless personalized accurate information active push method based on core-network side, comprising:
The 3G wireless network connection request that step S11, reception user submit to, described connection request comprises subscriber identity information;
Step S12, judge whether to there is customized information record corresponding to described subscriber identity information; If so, then step S13 is performed;
Step S13, judge whether described customized information record meets presetting rule, if so, then perform step S14;
Step S14, according to described customized information record, to this user's pushing personalized page.
Preferably, described method, also comprises:
If step S15 does not exist customized information record corresponding to described subscriber identity information, then generate user when IP information corresponding to time connection request, and set up associating of described subscriber identity information and IP information;
The operation information of the 3G wireless network that step S16, collection user submit to based on current IP information, generates corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Go to step S13.
Preferably, described method, also comprises:
If described customized information record does not meet presetting rule, then return step S16.
Preferably, described customized information record comprises the 3G wireless network operations behavioural information of described user, and/or, the network data message that the 3G wireless network operations for described user generates, the described step judging whether customized information record meets presetting rule comprises:
Behavioural analysis is carried out to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
Judge whether the characteristic parameter of described user behavior meets predetermined threshold value.
Preferably, described according to customized information record, the step to this user's pushing personalized page comprises:
The personalized identification of active user is generated according to described customized information record;
Generate the page navigation of coupling according to described personalized identification, push corresponding personal page in the mode be redirected to user by described page navigation.
Preferably, described method, also comprises:
Step S17, the amendment of reception user on corresponding personal page, and preserve described amendment.
Preferably, described step S11, step S12, step S13, step S15, step S16 perform in core-network side; Described step S14, step S17 perform in side, the Internet.
The embodiment of the present application also discloses a kind of wireless personalized accurate information active push device based on core-network side, comprising:
Link block, for receiving the 3G wireless network connection request that user submits to, described connection request comprises subscriber identity information;
, there is customized information record corresponding to described subscriber identity information for judging whether in user individual record judge module; If so, presetting rule judge module is then called;
Presetting rule judge module, for judging whether described customized information record meets presetting rule; If so, pushing personalized pages module is then called;
Pushing personalized pages module, for according to described customized information record, to this user's pushing personalized page.
Preferably, described device, also comprises:
IP information generating module, for when there is not customized information record corresponding to described subscriber identity information, generates user when IP information corresponding to time connection request, and sets up associating of described subscriber identity information and IP information;
Customized information logging modle, for collecting the operation information of the 3G wireless network that user submits to based on current IP information, generates corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Described customized information logging modle is connected with presetting rule judge module.
Preferably, if described presetting rule judge module judges that described customized information record does not meet presetting rule, then customized information logging modle is called.
Preferably, described customized information record comprises the 3G wireless network operations behavioural information of described user, and/or, the network data message that the 3G wireless network operations for described user generates, described presetting rule judge module comprises:
User behavior characteristic parameter obtains submodule, for carrying out behavioural analysis to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
Threshold decision submodule, for judging whether the characteristic parameter of described user behavior meets predetermined threshold value.
Preferably, described pushing personalized pages module comprises:
Personalized identification generates submodule, for generating the personalized identification of active user according to described customized information record;
Page reorientation submodule, for generating the page navigation of coupling according to described personalized identification, pushes corresponding personal page in the mode be redirected to user by described page navigation.
Preferably, described link block, user individual record judge module, presetting rule judge module, IP information generating module, customized information logging modle are positioned at core-network side; Described pushing personalized pages module is positioned at side, the Internet.
Compared with prior art, the application comprises following advantage:
By core-network side, user is identified, then carry out long-term network behavior to user to analyze, excavate the hobby of user and personalized custom, when user uses 3G wireless network, accurate customized information homepage is provided to user, by the scheduling of accurate personal page, the ease for operation that the 3G business promoting user uses, and reduce user to the search of customized information and search, thus reduce the use of customer flow.
Accompanying drawing explanation
Fig. 1 is the wireless personalized accurate information active pushing system schematic diagram based on core-network side of the present invention;
Fig. 2 is the wireless personalized accurate information active pushing system flow chart based on core-network side of the present invention;
Fig. 3 is the flow chart of steps of a kind of wireless personalized accurate information active push embodiment of the method 1 based on core-network side of the application;
Fig. 4 is the flow chart of a kind of user behavior analysis method example of the application;
Fig. 5 is the dendrogram model schematic of the network user classification method according to the application first embodiment;
Fig. 6 is the flow chart of the another kind of user behavior analysis method example of the application;
Fig. 7 is the flow chart of steps of a kind of wireless personalized accurate information active push embodiment of the method 2 based on core-network side of the application;
Fig. 8 is the structured flowchart of a kind of wireless personalized accurate information active push device embodiment based on core-network side of the application.
Embodiment
For enabling above-mentioned purpose, the feature and advantage of the application more become apparent, below in conjunction with the drawings and specific embodiments, the application is described in further detail.
Now introduce the wireless personalized accurate information active pushing system embodiment based on core-network side described in the application in conjunction with Figure of description 1 and Fig. 2: comprise the equipment of the core network being mounted in and core net accepting wireless user's solicited message, described equipment of the core network by the light splitting of wireless user's solicited message or mirror image to the user's discriminance analysis navigation module in core net, described light splitting or mirror image be exactly user's internet information mirror image (copying) is gone out a to user's discriminance analysis navigation module.User search, access, download request are sent to lift-launch can provide user ID identification and accurately identifying, provide accurate personal page and user individual revised to user's precision individual character WEB server of preserving on the internet by described core network.
Described user identifies to share navigation module is equipped with and carries out to user user behavior analysis engine that behavioural analysis and individual business excavate and user identifies engine.
Data feedback after Accurate Analysis to core network device, is accurately accessed precision homepage by core network device to user and is guided by described user's discriminance analysis navigation module.
The application's system, by the flow light splitting/mirror image platform environment of core-network side, carries out uniqueness identification to user; By the browsing of user, search for, the behavior such as download, data mining is carried out to user profile, draws the accurate information of user and personalized potential demand; By core-network side, accurate information and Personalized Navigation service dispatch are carried out to user; According to user, the amendment of accurate Personalized Navigation page is preserved; When user reuses wireless, accurate customized information scheduling is carried out to user.
The application's system business sequence:
1, wireless user verifies use wireless service authority, the unique ID of user such as carrying mobile phone number, IMEI, IMSI in these information.
2, equipment of the core network is by these information light splitting/mirror images to user's discriminance analysis navigation module, and user's discriminance analysis navigation module uniquely identifies user according to this information.
3, user uses wireless service, carries out searching for, access to content or download.
4, core network data message light splitting/mirror image is to user's discriminance analysis navigation module, and user's discriminance analysis navigation module carries out behavioural analysis to user and individual business excavates.
5, when user uses wireless service, packet light splitting/mirror image to user's discriminance analysis navigation module, if reach accurate personal page schedulable condition, is carried out the scheduling of accurate personal page to user and guides (use redirecting technique) by core net.
6, user accesses accurate personal page according to guiding message, accurate personal page according to user's unique identification of carrying in the privately owned agreement protocol of user's discriminance analysis navigation module and accurate personalized identification, provide accurate personal page to user.
7, user may carry out custom-modification to accurate personal page, and accurate personal page will be preserved these amendments, when next user accesses, preserves to displaying amendment the accurate personal page come into force.
One of core idea of the application is, by core-network side, user is identified, then the behavior of user's longer-term network is analyzed, excavate the hobby of user and personalized custom, when user uses 3G wireless network, provide accurate customized information homepage to user, by the scheduling of accurate personal page, the ease for operation that the 3G business promoting user uses, and reduce user to the search of customized information and search, thus reduce the use of customer flow.
With reference to Fig. 3, it illustrates the flow chart of steps of a kind of wireless personalized accurate information active push embodiment of the method 1 based on core-network side of the application, specifically can comprise the steps:
The 3G wireless network connection request that step 301, reception user submit to, described connection request comprises subscriber identity information;
In a particular application, when user accesses 3G wireless network, 3G wireless network connection request can be submitted to, the identity information of user can be carried in the message of described request, as phone number, IMEI (International Mobile Equipment Identity, International Mobile Equipment Identity code), user's unique identification information such as IMSI (International Mobile SubscriberIdentity, international mobile subscriber identity).
Step 302, judge whether to there is customized information record corresponding to described subscriber identity information; If not, then step 303 is performed; If so, then step 305 is performed;
Step 303, generate user when IP information corresponding to time connection request, and set up associating of described subscriber identity information and IP information; Go to step 304;
For the 3G wireless network connection request that user submits at every turn, all can generate a corresponding temporary IP information, the network operation of user after 3G wireless network connects all can carry this temporary IP information.By setting up associating of described subscriber identity information and this temporary IP information, subscriber identity information and this temporary IP information are bound as will be described, then can find corresponding subscriber identity information, to realize the unique identification to user by this temporary IP information.
The operation information of the 3G wireless network that step 304, collection user submit to based on current IP information, generates corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Go to step 305;
User, after connection 3G wireless network, using wireless service, searching for as carried out, the operation of the 3G wireless network such as access to content or download, all can carry described IP information.In practice, can according to described subscriber identity information and customized information record sheet corresponding to IP information creating, customized information corresponding according to the operation information real time record of the 3G wireless network of user in the table.
In a preferred embodiment of the present application, described customized information record can comprise: the 3G wireless network operations behavioural information of described user, and/or, the network data message that the 3G wireless network operations for described user generates.Wherein, the 3G wireless network operations behavioural information of described user may further include, the behavioural information of user's accessed web page, the behavioural information of user search, the behavioural information etc. that user clicks.
Step 305, judge whether described customized information record meets presetting rule, if not, then returns step 304; If so, then step 306 is performed;
In a preferred embodiment of the present application, can judge whether described customized information record meets presetting rule by following sub-step 51 and sub-step S52:
Sub-step S51, behavioural analysis is carried out to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
For making those skilled in the art understand the application better, two kinds are below provided to carry out the example of behavioural analysis to the 3G wireless network operations behavioural information of user:
Example 1:
With reference to Fig. 4, it illustrates the flow process of a kind of user behavior analysis method example of the application, specifically can comprise the following steps:
Sub-step 110, pre-determines multiple (corresponding to the second setting quantity) webpage classification.
Based on the webpage of the first setting quantity, carry out the webpage classification of predefined second setting quantity.Wherein, each webpage classification is made up of multiple theme, and such as, webpage classification is that social network sites can be expressed as " social network sites: campus, activity, tourism ", wherein, " campus ", " activity ", " tourism " for affiliated webpage classification be each theme of social network sites.First the webpage of the first setting quantity is carried out subject classification, then determine the webpage classification belonging to webpage of the first setting quantity according to the webpage classification be associated with theme.Such as, theming as in " campus " belonging to Renren Network, and " campus " and social network sites have relevance, then the webpage classification of Renren Network can be defined as social network sites.
Particularly, manual sort can be carried out to the webpage of setting quantity (corresponding to the first setting quantity), such as, manual sort can be carried out for several ten thousand in existing 1,000,000 webpages or a hundreds of thousands typical webpage, obtain webpage classification, such as, Jingdone district net attribute is e-commerce website, Renren Network attribute is social network sites, and U.S. group net is group buying websites.
The webpage of setting quantity can also be carried out classification and obtains Web page classifying applying web page automatic classification technology.Such as applied statistics study method, by analyzing the webpage through manual sort, therefrom excavates the contact between keyword and class, contact between recycling keyword and class, classify to the webpage of the first setting quantity, this Statistical learning-based approaches is prior art, does not repeat them here.
Sub-step 120, the network behavior based on user generates the behavioural characteristic vector of user.
Particularly, first can obtain the network behavior of user, the network behavior of user is carried out preliminary treatment, to obtain the behavioural characteristic vector of user.
Preprocessing process is the basis of whole network user classification, generally comprise and use record preprocessing, content information preliminary treatment and structural information preliminary treatment, by carrying out preliminary treatment to obtained user network behavior, removing redundant information, fuzzy information and meaningless information, obtain the data of accurate Characterization user network behavior.
In the embodiment of the present application, the network behavior for the behavioural characteristic vector generating user can comprise access to netwoks behavior and search behavior.Such as, network address access to netwoks behavior can accessed is (in the application, by in IP address, website/English domain name etc. is referred to as network address) and search behavior involved by the vocabulary such as search keyword be defined as the element of the behavioural characteristic vector of user, such as user has carried out the access behavior of Jingdone district net, Renren Network and U.S. group net, then the vocabulary such as the vocabulary comprised in accessed network address " Jingdone district ", " everybody " and " U.S. group " is defined as the element of the behavioural characteristic vector of user; Search keyword involved by the search behavior of user, such as the vocabulary such as " Jingdone district ", " everybody " and " U.S. group " is defined as the element of the behavioural characteristic vector of user.
The behavioural characteristic of user vector W can be expressed as follows:
W
UserId＝{w
1，w
2，...，w
n，...}
Wherein, U
serIdin order to identifying user, w
nbe the n-th feature (also known as vocabulary) generated according to access to netwoks behavior or the search behavior of user, comprise access to netwoks behavior and the search behavior of user.
For example, certain user have accessed 3 network address and has searched for 5 keywords, then when this user have accessed 3 network address, these 3 network address represent 3 features (vocabulary) respectively, then the user behavior feature about the access to netwoks behavior of this user can use w
1, w
2, w
3represent, wherein, w
1, w
2, w
3represent that user accesses the number of times of these 3 network address respectively; And this user has also searched for 5 keywords, then when this user search 5 keyword, can using these 5 keywords as 5 features, then the user behavior feature about the search behavior of this user can w
3+1, w
3+2..., w
3+5represent, wherein w
3+1, w
3+2..., w
3+5represent that user is based on the 1st, 2 respectively ..., the number of times that 5 keywords carry out searching for, based on the above, then the user behavior characteristic vector W of this user can be expressed as W
userId={ w
1, w
2, w
3, w
3+1, w
3+2..., w
3+5.
Sub-step 130, the behavioural characteristic vector based on each user carries out cluster, and to build user-theme matrix M, wherein, each element value of user-theme matrix M characterizes the degree of association between each user and each theme respectively, more specifically, the d capable jth row M of M
d, jrepresent that d user belongs to probability and the θ of a jth theme
d j.
Theme as more than one feature obtaining through cluster or compose the set of power feature, such as, theme can be expressed as " 0.1 school bag; 0.2 school uniform; 0.3 morning exercises; 0.4 homework book "; wherein " school bag ", " school uniform ", " morning exercises ", " homework book " they are feature; and the coefficient before them is weight; be same subject by similar characteristic aggregation; the theme including above-mentioned feature is set as campus; be conducive to analyzing the network behavior custom of user, thus be convenient to reach the object of classifying to it.
Preferably, topic model (Topic Model) can be utilized to carry out cluster.Using the characteristic vector of the behavioural characteristic of each user vector as characteristic layer in topic model, to build user's topic model (being called for short UTM model), and utilizing this user's topic model to realize the cluster of carrying out user, user's topic model of the present embodiment carries out modeling by adopting Dirichlet distribution to the behavioural characteristic vector of user.
Fig. 5 is the dendrogram model example of the network user classification method according to the application first embodiment.As shown in Figure 5, the graph model of cluster has hierarchical structure clearly, and every one deck is characterized by corresponding parameter or stochastic variable, comprises characteristic layer, subject layer and client layer three-decker.Fig. 2 hollow core point represents implicit variable, and solid dot represents parameter, and arrow represents dependence.User's topic model is defined by the parameter alpha of client layer and parameter beta, wherein, α reflects in user's set implicit intersubjective relatively strong and weak, β reflects the probability distribution of all implicit themes self, θ represents the proportion of each implicit theme in user, and z represents that user is distributed in the implicit theme proportion in each feature, and w is the characteristic vector representation of user, P represents the quantity that user gathers, and n represents the quantity of feature contained by user.Large rectangle represents that each user d concentrated for user from Dirichlet distribution extracts theme distribution θ repeatedly; Little rectangle represents repeatedly extract feature w from theme distribution.
For example, a given user gathers D, contains P user, and each user d comprises a characteristic sequence { w
1, w
2..., w
n.In the UTM model that set D is corresponding, theme number is set to K, be easy to make UTM model process the new user outside known users, during application UTM model, UTM model first carries out the process of prior probability hypothesis, then carrying out cluster to the behavioural characteristic vector of a user can be expressed as following steps:
1) be that each user d extracts with multinomial distribution θ from Dirichlet distribution p (θ | α)
dthe theme represented, wherein this multinomial distribution every is the multinomial distribution on feature space, particularly, according to θ ~ Dir (α), gather each user in D for user, from Dirichlet distribution, randomly draw the theme distribution θ of a k dimension
d, it is expressed as the mixing of each theme ratio of each user, theme distribution θ
din the element of every one dimension be designated as θ
d j, it is expressed as the probability that user d belongs to a jth theme, wherein, p (θ | α) be shown below,
Wherein, α is the Dirichlet parameter of a K dimension, α
ifor super parameter, θ is parameter vector, and Γ is the gamma function of standard, and α reflects that user gathers the power relatively in D between each theme, and θ represents the probability of each theme of each user's subordinate.
2) from Dirichlet priori β, be the distribution of each subject extraction proper polynomial, particularly, distribute, to obtain p (w for each user d extracts each proper polynomial from Dirichlet priori β based on particular topic ratio
n| θ
d, β).Wherein, β generates the probability of certain feature (vocabulary) under representing certain theme condition, β is the matrix of a K × V.
3) all feature w in all user d and user are gathered in D for user to proceed as follows, first selected theme z
i, z
iobey Multinomial (θ
d) multinomial distribution, then select feature w
i, at z
imultinomial distribution under condition, i-th feature w in each user d
ican be shown below,
Wherein, z
ibe potential theme variable, show i-th feature w
itake from this theme, P (w
i| z
i=j) be feature w
ibelong to the probability of theme j, P (z
i=j) j that is the theme belongs to the probability of active user.Then T theme formation D user represents with W uniqueness characteristic, order
represent the multinomial distribution for theme j, feature w; Order
represent for the multinomial distribution on user d, a K theme, therefore in user d, the probability of feature w is shown below,
4) extrapolate P (w|d) by EM algorithm or Gibbs sampling, then indirectly try to achieve based on P (w|d) the probability θ that d user belong to a jth theme
d jto build user-theme matrix M.
It should be noted that, estimate θ owing to directly using EM algorithm
dthe problem of local extremum can be there is, therefore first for given observed value feature w
i, utilize Gibbs to sample and get feature (vocabulary) at theme z
ion posterior probability P (w
i| z
i) approximation.
Particularly, in Gibbs sampling, the theme first fixing other words distributes, and then estimates current signature w
igive the probability P (z of various theme
i=j), that is the value of P (w|d), the value according to gained P (w|d) indirectly obtains θ
dvalue.Wherein, theme distribution θ
din the element of every one dimension be designated as θ
d j, it is expressed as the probability that user d belongs to a jth theme, carries out above-mentioned 1 to each user that user gathers in D) to 4) operation, the theme distribution θ of each user can be obtained
d, based on obtained theme distribution θ
dbuild user-theme matrix M.
Sub-step 140, determines the webpage classification belonging to user based on user-theme matrix M.
More specifically, based on user-theme matrix M, the probability that user belongs to each theme can be obtained, then determine the webpage classification belonging to user according to these probable values.Determine that mode is varied, such as, each theme and other correlation degree of each web page class can be preset, then, by long-pending and that maximum webpage classification of the probability of each theme that makes belonging to user and other correlation degree of web page class, as the webpage classification belonging to user.
For example, be social network sites for webpage classification, preset each theme and other correlation degree of web page class is " social network sites: 0.5 campus; 0.3 is movable; 0.2 tourism ", be e-commerce website for webpage classification, preset each theme and other correlation degree of web page class is " e-commerce website: 0.5 concludes the business; 0.3 company; 0.2 electronics ", the coefficient before each theme is the value of each theme and affiliated other correlation degree of web page class, assuming that belong to the probability of each theme according to certain user d of step 130 gained for " 0.3 campus; 0.2 is movable; 0.1 tourism; 0.1 transaction; 0.1 company; 0.2 electronics "; then by the probability of each theme belonging to this user with preset other correlation degree of web page class belonging to each theme and be multiplied; obtain the actual subject probability of each theme be associated with each webpage classification; carried out by the actual subject probability of affiliated other each theme of web page class addition gained and as final result, the final result of above-mentioned example is " 0.23 social network sites; 0.12 e-commerce website "; according to the long-pending of gained and maximum value, the classification belonging to this user known is social network sites, and this user is interested for the activity of social interaction class; when carrying out targeted ads and sending, and can send the targeted ads that be similar to tourism, lie fallow to this type of user.
example 2:
With reference to Fig. 6, it illustrates the flow process of the another kind of user behavior analysis method example of the application, specifically can comprise the following steps:
Sub-step 110, sub-step 120, sub-step 130 are substantially identical with the example 1 shown in Fig. 4, for convenience of explanation, no longer launch in detail the step identical with aforementioned exemplary, and only stress the difference with aforementioned exemplary.In Figure 5, to same or analogous step in aforementioned exemplary, have employed identical Reference numeral.
In this example, in sub-step 140, sub-step 141 and 142 is specifically comprised.
Sub-step 141, determines the one or more themes associated by webpage classification of setting quantity (corresponding to the first setting quantity) webpage in abovementioned steps 110, to build theme-classification transformation matrix.
Particularly, be associated in the webpage by the setting quantity in statistics abovementioned steps 110, with a jth theme and be classified to other webpage of kth web page class quantity t '
j, kdetermine the jth row kth column element value of theme-classification transformation matrix T, j is the natural number being less than or equal to theme quantity, and k is for being less than or equal to the natural number of webpage categorical measure (i.e. the second setting quantity).The element assignment that such as the jth row kth of theme-classification transformation matrix T can be arranged is t
j, k=t '
j, k/ total, wherein, total is the quantity of the webpage of setting quantity in abovementioned steps 110 (i.e. the first setting quantity).In brief, build described theme-classification transformation matrix, its element value characterizes theme and other degree of association of web page class.
Sub-step 142, the matrix of consequence based on the product of user-theme matrix M and theme-classification transformation matrix T determines the webpage classification belonging to user.
Particularly, by user-theme matrix M and theme-classification transformation matrix T-phase multiplied to user-classification matrix N.Wherein, the d capable kth row N of user-classification matrix N
d, krepresent that d user belongs to the probability of a kth classification, that is the degree of association of d user in a kth classification, determine the webpage classification belonging to user according to the size of the value of the degree of association of classification, such as, can be defined as belonging to this user webpage classification based on described user-classification matrix by with the maximum one or more webpage classification of user-association degree.
For example, assuming that obtain the user-theme matrix about four users according to step 130, matrix is as follows,
Wherein, row vector represents four users such as user 1, user 2, user 3, user 4 respectively, and column vector represents six themes such as campus, activity, tourism, transaction, company, electronics respectively.
Be social network sites for webpage classification, what to preset with web page class that other is associated themes as " social network sites: campus; Movable; Tourism ", be e-commerce website for webpage classification, what to preset with web page class that other is associated themes as " e-commerce website: conclude the business; Company; Electronics ".
According to set in sub-step 110 quantity webpage webpage classification associated by one or more themes, to be associated in the webpage of setting quantity in aforementioned sub-step 110 (corresponding to the first setting quantity), with a jth theme by adding up and to be classified to other webpage of kth web page class quantity t '
j, kdetermine theme-classification transformation matrix, assuming that the webpage of setting quantity in sub-step 110 is 8, the webpage numerical representation then belonging to each theme is respectively " 2 campuses, 2 activities, 2 tourisms, 2 transaction, 0 company, 0 electronics ", theme-classification transformation matrix can be constructed according to the above results, as follows
Wherein, row vector represents six themes such as campus, activity, tourism, transaction, company, electronics respectively, and column vector represents social network sites and e-commerce website two webpage classifications respectively.
Gained user-theme matrix is multiplied with theme-analogy transformation matrix and obtains user-classification matrix, as follows,
Wherein, row vector represents four users such as user 1, user 2, user 3, user 4 respectively, and column vector represents social network sites and e-commerce website two webpage classifications respectively.The d capable kth row N of user-classification matrix
d, krepresent that d user belongs to the probability of a kth classification, that is the degree of association of d user in a kth classification, the webpage classification belonging to user is determined according to the size of the value of the degree of association of classification, according to above-mentioned matrix, described in known user 1, user 2 and user 3, classification is social network sites, user 4 generic is e-commerce website, therefore when sending targeted ads, can the webpage classification belonging to user send targetedly.
It should be noted that above-mentioned example is only a simple example, described content is only the execution mode adopted for the ease of understanding the application, and is not used to limit the application.Due to popularizing of the Internet, number of users in the Internet is with 10,000,000,000 notes, and the application's method is classified by unsupervised approaches, have nothing to do with number of users, the behavior of large-scale consumer can be processed, the application's method can cover comprehensive user behavior on less calculation cost, thus can utilize the information of user fully and a large amount of users be classified, and makes full use of the interest of the abundant information consumer positioning that mass data contains.
In another preferred embodiment of the present application, described network data message can comprise the 3G wireless network operations information of user, as the information such as webpage, search that user browses, by carrying out data mining to these network data messages, also the characteristic parameter of user behavior can be obtained, in specific implementation, the characteristic parameter of described user behavior can be the frequency of user's generic operation, the rank etc. that also can access content for user.Such as, carry out data mining by network data message, obtain the concrete behavior information of user, the Type of website that such as user browses, the content of interest etc. that user clicks in webpage, the user behavior characteristic parameter of acquisition is the frequency of operation of user.
Certainly, those skilled in the art adopt any one existingly carry out the technology of user behavior analysis by data mining or adopt the technology of any one user behavior analysis, and the characteristic parameter obtaining any one user behavior is all feasible, and the application is not restricted this.
Sub-step S52, judge whether the characteristic parameter of described user behavior meets predetermined threshold value.
Wherein, described predetermined threshold value can be arranged arbitrarily according to actual conditions by those skilled in the art, such as, arranging user to the threshold value of the frequency of operation of the website of certain type is 20 times, once analyze the frequency of operation (user behavior characteristic parameter) of acquisition user to the website of this type to be more than or equal to 20 times, the consumer positioning behavior and the navigation scheduling that get final product triggering following operate.Or as, arranging the access times rank of user to certain content page is the 1st, then obtain user to the clicking operation (user behavior characteristic parameter) of the page of various dissimilar content, and carry out rank by number of clicks, after obtaining the page info of the highest corresponding types content of number of clicks, the consumer positioning behavior and the navigation scheduling that get final product triggering following operate.
Step 306, according to described customized information record, to this user's pushing personalized page.
In a preferred embodiment of the present application, described step 306 specifically can comprise following sub-step:
Sub-step S61, generate the personalized identification of active user according to described customized information record;
Sub-step S62, the page navigation mated according to described personalized identification generation, push corresponding personal page in the mode be redirected to user by described page navigation.
When described customized information record meets presetting rule, then can form the personalized identification of user, what described personalized identification can be paid close attention to for the user carrying out analyzing acquisition to customized information record wants dot information, i.e. the main points of user individual behavior.Then according to the personalized behavior of user, for user formulates Personalized Navigation, the personal page meeting described personalized behavior for customization is.After this access 3G wireless network this user, as long as its personalized record meets presetting rule, then transmit Personalized Navigation to this user, namely the scheduling of accurate personal page is carried out to user and guide.
In concrete reality, redirecting technique can be adopted to carry out the scheduling of accurate personal page to user guide, be redirected the personal page namely again user being directed to correspondence to conduct interviews, be redirected to user by personal page, provide accurate personal page to be embodied as user.
With reference to Fig. 7, it illustrates the flow chart of steps of a kind of wireless personalized accurate information active push embodiment of the method 2 based on core-network side of the application, specifically can comprise the steps:
Step 601, core-network side receive the 3G wireless network connection request that user submits to, and described connection request comprises subscriber identity information;
Step 602, core-network side judge whether to there is customized information record corresponding to described subscriber identity information;
If not, then step 603 and step 604 is performed;
If so, then step 605 is performed;
Step 603, core-network side generate user when IP information corresponding to time connection request, and set up associating of described subscriber identity information and IP information;
Step 604, core-network side collect the operation information of the 3G wireless network that user submits to based on current IP information, generate corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Go to step 605.
Step 605, core-network side judge whether described customized information record meets presetting rule, if so, then perform step 606;
Step 606, side, the Internet according to described customized information record, to this user's pushing personalized page.
Step 607, the Internet side joint receive the amendment of user on corresponding personal page, and preserve described amendment.
In the embodiment of the present application, described the Internet can comprise mobile Internet (comprising 3G wireless network); Described core net is by service supplier and Access Network, or, by the network that Access Network and other Access Networks link together, typically refer to the network portion except Access Network and the local network of users.Simply, mobile network can be divided into three parts, base station sub-system, network subsystem, and system support part such as safety management etc. these.Core network part is positioned at network subsystem exactly, and the call request that the Main Function of core net comes up A mouth or request of data, be routed on different networks.Mainly relate to the continuing of calling, charging, mobile management, supplementary service realizes, and the aspect body supports such as intelligent trigger are at switch.Then have two concepts clearly as soft switch, control and being separated of carrying, control channel is separated with data channel.To be exactly it from it is stipulated in the agreement that exchange or the network element of call routing function to core core net, is all generally the same, at R4 framework such as MSC SERVER MGW for 2G/3G core net, HLR, VLR, EIR, AUC etc., Main Function is that whole call signaling controls and carrying is set up.From the angle of application, by core net selection protocol when namely core net refers to SCN subscriber connection network, provide the network that user connects.
In practice, user may carry out custom-modification to personal page, application the present embodiment, will preserve user to the amendment of described personal page, when next user accesses, will show the personal page revised and come into force to user in side, the Internet.
It should be noted that, for aforesaid embodiment of the method, in order to simple description, therefore it is all expressed as a series of combination of actions, but those skilled in the art should know, the application is not by the restriction of described action along pagination, because foundation the application, some step can adopt other along pagination or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in specification all belongs to preferred embodiment, and involved action and module might not be that the application is necessary.
Moreover each embodiment of the method above-mentioned all adopts the mode of going forward one by one to describe, what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
With reference to Fig. 8, it illustrates the structured flowchart of a kind of wireless personalized accurate information active push device embodiment based on core-network side of the application, specifically can comprise with lower module:
Link block 701, for receiving the 3G wireless network connection request that user submits to, described connection request comprises subscriber identity information;
, there is customized information record corresponding to described subscriber identity information for judging whether in user individual record judge module 702;
If not, then IP information generating module 703 and customized information logging modle 704 is called;
If so, presetting rule judge module 705 is then called;
IP information generating module 703, for when there is not customized information record corresponding to described subscriber identity information, generates user when IP information corresponding to time connection request, and sets up associating of described subscriber identity information and IP information;
Customized information logging modle 704, for collecting the operation information of the 3G wireless network that user submits to based on current IP information, generates corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Described customized information logging modle 704 is connected 705 with presetting rule judge module.
Presetting rule judge module 705, for judging whether described customized information record meets presetting rule; If not, then customized information logging modle 704 is returned; If so, pushing personalized pages module 706 is then called;
Pushing personalized pages module 706, for according to described customized information record, to this user's pushing personalized page.
In specific implementation, described customized information record can comprise the 3G wireless network operations behavioural information of described user, and/or, for the network data message that the 3G wireless network operations of described user generates, in this case, described presetting rule judge module 705 can comprise following submodule:
User behavior characteristic parameter obtains submodule, for carrying out behavioural analysis to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
Threshold decision submodule, for judging whether the characteristic parameter of described user behavior meets predetermined threshold value.
In a preferred embodiment of the present application, described pushing personalized pages module 706 can comprise following submodule:
Personalized identification generates submodule, for generating the personalized identification of active user according to described customized information record;
Page reorientation submodule, for generating the page navigation of coupling according to described personalized identification, pushes corresponding personal page in the mode be redirected to user by described page navigation.
In a particular application, described link block 701, user individual record judge module 702, presetting rule judge module 705, IP information generating module 703, customized information logging modle 704 can be arranged on core-network side; Described pushing personalized pages module 704 can be arranged on side, the Internet.
As a preferred embodiment of the present application, this device embodiment can also comprise as lower module:
Modified module, for receiving the amendment of user on corresponding personal page, and preserves described amendment.
In a particular application, described modified module can be arranged on side, the Internet.
For device embodiment, due to itself and embodiment of the method basic simlarity, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
The application can be used in numerous general or special purpose computing system environment or configuration.Such as: personal computer, server computer, handheld device or portable set, laptop device, multicomputer system, system, set top box, programmable consumer-elcetronics devices, network PC, minicom, mainframe computer, the distributed computing environment (DCE) comprising above any system or equipment etc. based on microprocessor.
The application can describe in the general context of computer executable instructions, such as program module.Usually, program module comprises the routine, program, object, assembly, data structure etc. that perform particular task or realize particular abstract data type.Also can put into practice the application in a distributed computing environment, in these distributed computing environment (DCE), be executed the task by the remote processing devices be connected by communication network.In a distributed computing environment, program module can be arranged in the local and remote computer-readable storage medium comprising memory device.
Above to a kind of wireless personalized accurate information active pushing system based on core-network side that the application provides, a kind of wireless personalized accurate information active push method based on core-network side, and, a kind of wireless personalized accurate information active push device based on core-network side, be described in detail, apply specific case herein to set forth the principle of the application and execution mode, the explanation of above embodiment is just for helping method and the core concept thereof of understanding the application; Meanwhile, for one of ordinary skill in the art, according to the thought of the application, all will change in specific embodiments and applications, in sum, this description should not be construed as the restriction to the application.
Claims (7)
1., based on a wireless personalized accurate information active push method for core-network side, it is characterized in that, comprising:
Step S11, core-network side receive the 3G wireless network connection request that user submits to, and described connection request comprises subscriber identity information;
Step S12, core-network side judge whether to there is customized information record corresponding to described subscriber identity information; If so, then step S13 is performed;
Step S13, core-network side judge whether described customized information record meets presetting rule, if so, then perform step S14;
Step S14, side, the Internet according to described customized information record, to this user's pushing personalized page;
Wherein, described customized information record comprises the 3G wireless network operations behavioural information of described user, and/or, the network data message that the 3G wireless network operations for described user generates, described step S13 comprises:
Behavioural analysis is carried out to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
Judge whether the characteristic parameter of described user behavior meets predetermined threshold value;
Wherein, described according to customized information record, the step to this user's pushing personalized page comprises:
The personalized identification of active user is generated according to described customized information record;
Generate the page navigation of coupling according to described personalized identification, push corresponding personal page in the mode be redirected to user by described page navigation.
2. method according to claim 1, is characterized in that, also comprises:
If step S15 does not exist customized information record corresponding to described subscriber identity information, then core-network side generates user when IP information corresponding to time connection request, and sets up associating of described subscriber identity information and IP information;
Step S16, core-network side collect the operation information of the 3G wireless network that user submits to based on current IP information, generate corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Go to step S13.
3. method according to claim 2, is characterized in that, also comprises:
If described customized information record does not meet presetting rule, then return step S16.
4. method according to claim 1, is characterized in that, also comprises:
Step S17, the Internet side joint receive the amendment of user on corresponding personal page, and preserve described amendment.
5., based on a wireless personalized accurate information active push device for core-network side, it is characterized in that, comprising:
Be positioned at the link block of core-network side, for receiving the 3G wireless network connection request that user submits to, described connection request comprises subscriber identity information;
Being positioned at the user individual record judge module of core-network side, there is customized information record corresponding to described subscriber identity information for judging whether; If so, presetting rule judge module is then called;
Be positioned at the presetting rule judge module of core-network side, for judging whether described customized information record meets presetting rule; If so, pushing personalized pages module is then called;
Be positioned at the pushing personalized pages module of side, the Internet, for according to described customized information record, to this user's pushing personalized page;
Wherein, described customized information record comprises the 3G wireless network operations behavioural information of described user, and/or, the network data message that the 3G wireless network operations for described user generates, described presetting rule judge module comprises:
User behavior characteristic parameter obtains submodule, for carrying out behavioural analysis to the 3G wireless network operations behavioural information of described user, and/or, data mining is carried out to the network data message that the described 3G wireless network operations for user generates, obtains the characteristic parameter of user behavior;
Threshold decision submodule, for judging whether the characteristic parameter of described user behavior meets predetermined threshold value;
Wherein, described pushing personalized pages module comprises:
Personalized identification generates submodule, for generating the personalized identification of active user according to described customized information record;
Page reorientation submodule, for generating the page navigation of coupling according to described personalized identification, pushes corresponding personal page in the mode be redirected to user by described page navigation.
6. device according to claim 5, is characterized in that, also comprises:
Being positioned at the IP information generating module of core-network side, for when there is not customized information record corresponding to described subscriber identity information, generating user when IP information corresponding to time connection request, and set up associating of described subscriber identity information and IP information;
Being positioned at the customized information logging modle of core-network side, for collecting the operation information of the 3G wireless network that user submits to based on current IP information, generating corresponding customized information record; And set up associating of described subscriber identity information and customized information record; Described customized information logging modle is connected with presetting rule judge module.
7. device according to claim 6, is characterized in that, if described presetting rule judge module judges that described customized information record does not meet presetting rule, then calls customized information logging modle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110406878.1A CN102523274B (en) | 2011-06-28 | 2011-12-08 | Based on wireless personalized accurate information active pushing system and the method for core-network side |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110176700 | 2011-06-28 | ||
| CN201110176700.2 | 2011-06-28 | ||
| CN2011101767002 | 2011-06-28 | ||
| CN201110406878.1A CN102523274B (en) | 2011-06-28 | 2011-12-08 | Based on wireless personalized accurate information active pushing system and the method for core-network side |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102523274A CN102523274A (en) | 2012-06-27 |
| CN102523274B true CN102523274B (en) | 2015-10-07 |
Family
ID=46294063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110406878.1A Expired - Fee Related CN102523274B (en) | 2011-06-28 | 2011-12-08 | Based on wireless personalized accurate information active pushing system and the method for core-network side |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102523274B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103716804B (en) * | 2012-09-28 | 2017-02-15 | 北京亿赞普网络技术有限公司 | Wireless data communication network user network behavior analyzing method, device and system |
| CN103002412B (en) * | 2012-11-28 | 2016-02-24 | 北京亿赞普网络技术有限公司 | A kind of wireless accurate information supplying system and method thereof |
| CN103905488B (en) * | 2012-12-26 | 2018-10-12 | ***通信集团公司 | A kind of mobile terminal advertisement put-on method and equipment |
| CN103051725B (en) * | 2012-12-31 | 2015-07-29 | 华为技术有限公司 | Application and identification method, data digging method, Apparatus and system |
| US9477718B2 (en) | 2012-12-31 | 2016-10-25 | Huawei Technologies Co., Ltd | Application identification method, and data mining method, apparatus, and system |
| CN103152324B (en) * | 2013-01-29 | 2016-01-27 | 北京凯华信业科贸有限责任公司 | The user authen method of Behavior-based control feature |
| CN104156356B (en) * | 2013-05-13 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Personalized Navigation page generation method and device |
| CN103699823B (en) * | 2014-01-08 | 2017-01-25 | 同济大学 | Identity authentication system based on user behavior pattern and method thereof |
| CN104123380B (en) * | 2014-07-31 | 2018-03-30 | 珠海市君天电子科技有限公司 | web access method and device |
| CN104199641A (en) * | 2014-08-04 | 2014-12-10 | 联想(北京)有限公司 | Information processing method and first electronic equipment |
| CN106549818A (en) * | 2015-09-21 | 2017-03-29 | 中兴通讯股份有限公司 | A kind of method and apparatus in core network system acquisition function performance data |
| CN107018161B (en) * | 2016-01-28 | 2020-04-17 | 中国电信股份有限公司 | Method, device and system for WLAN personalized reminder |
| CN105975529A (en) * | 2016-04-29 | 2016-09-28 | 维沃移动通信有限公司 | Information processing method and mobile terminal |
| CN106302748B (en) * | 2016-08-17 | 2020-07-10 | 北京字节跳动科技有限公司 | Cross-media personalized recommendation method and system |
| CN108259481B (en) * | 2018-01-02 | 2021-08-20 | 中电万维信息技术有限责任公司 | Electronic government affair personalized information service method |
| CN111294798B (en) * | 2018-12-07 | 2023-04-28 | ***通信集团陕西有限公司 | Data interaction method, device, terminal equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296256A (en) * | 2008-06-19 | 2008-10-29 | 中国电信股份有限公司 | Method and system for implementing accurate information propelling by internet |
| CN101437048A (en) * | 2008-11-11 | 2009-05-20 | ***通信集团北京有限公司 | Method and system for pushing personalized page |
| CN101626551A (en) * | 2009-06-26 | 2010-01-13 | 武汉虹旭信息技术有限责任公司 | System and method for popularizing advertisements based on mobile Internet |
| CN101957834A (en) * | 2010-08-12 | 2011-01-26 | 百度在线网络技术（北京）有限公司 | Content recommending method and device based on user characteristics |
-
2011
- 2011-12-08 CN CN201110406878.1A patent/CN102523274B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296256A (en) * | 2008-06-19 | 2008-10-29 | 中国电信股份有限公司 | Method and system for implementing accurate information propelling by internet |
| CN101437048A (en) * | 2008-11-11 | 2009-05-20 | ***通信集团北京有限公司 | Method and system for pushing personalized page |
| CN101626551A (en) * | 2009-06-26 | 2010-01-13 | 武汉虹旭信息技术有限责任公司 | System and method for popularizing advertisements based on mobile Internet |
| CN101957834A (en) * | 2010-08-12 | 2011-01-26 | 百度在线网络技术（北京）有限公司 | Content recommending method and device based on user characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102523274A (en) | 2012-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102523274B (en) | Based on wireless personalized accurate information active pushing system and the method for core-network side | |
| CN102521248B (en) | Network user classification method and device | |
| Wang et al. | Identifying technological topics and institution-topic distribution probability for patent competitive intelligence analysis: a case study in LTE technology | |
| AU2016303436B2 (en) | Method and system for applying probabilistic topic models to content in a tax environment to improve user satisfaction with a question and answer customer support system | |
| US7421429B2 (en) | Generate blog context ranking using track-back weight, context weight and, cumulative comment weight | |
| Lai et al. | Sparse learning-to-rank via an efficient primal-dual algorithm | |
| US9043348B2 (en) | System and method for performing set operations with defined sketch accuracy distribution | |
| CN102799610A (en) | Method and system for collecting network information | |
| CN104008109A (en) | User interest based Web information push service system | |
| CN102426610A (en) | Microblog rank searching method and microblog searching engine | |
| CN104090907A (en) | Method and device for providing information for user in specific application field | |
| CN102163230B (en) | Method for implementing personalized information retrieval system for customizing privacy protection | |
| CN104217030A (en) | Method and device for classifying users according to search log data of server | |
| CN103902535A (en) | Method, device and system for obtaining associational word | |
| Al-Masri et al. | MobiEureka: an approach for enhancing the discovery of mobile web services | |
| CN104750760A (en) | Application software recommending method and device | |
| CN103248677A (en) | Internet behavior analysis system and working method thereof | |
| KR102457359B1 (en) | Marketing cost efficiency calculation method and electronic system for performing the method using neural networks | |
| CN103064842A (en) | Information subscription processing device and information subscription processing method | |
| KR101816205B1 (en) | Server and computer readable recording medium for providing internet content | |
| CN103631946A (en) | Content pushing system based on geographic positions | |
| CN105787066A (en) | Digital content distribution system based on total analysis | |
| CN101976394A (en) | Data acquiring and counting system and method | |
| CN101661490A (en) | Search engine, client thereof and method for searching page | |
| CN104021124A (en) | Method, device and system used for processing webpage data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100081, building 2, building 18, 1607 South Main Street, Beijing, Haidian District, Zhongguancun, China Patentee after: Izp (China) Network Technology Co. Ltd. Address before: 100081, building 2, building 18, 1607 South Main Street, Beijing, Haidian District, Zhongguancun, China Patentee before: Beijing IZP Technologies Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151007 Termination date: 20161208 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |