CN104239327A - Location-based mobile internet user behavior analysis method and device - Google Patents
Location-based mobile internet user behavior analysis method and device Download PDFInfo
- Publication number
- CN104239327A CN104239327A CN201310239737.4A CN201310239737A CN104239327A CN 104239327 A CN104239327 A CN 104239327A CN 201310239737 A CN201310239737 A CN 201310239737A CN 104239327 A CN104239327 A CN 104239327A
- Authority
- CN
- China
- Prior art keywords
- theme
- application service
- place
- information
- parameter matrix
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a location-based mobile internet user behavior analysis method and device. The method includes the steps of S1, acquiring and storing an IMEI (international mobile equipment identity) number and an IMSI (international mobile subscriber identity) number of each mobile internet user; S2, acquiring and storing historical location and historical application service information of each mobile internet user; S3, initializing a site theme according to the historical locations, and initializing an application service theme of the historical application service information; S4, acquiring a parameter matrix Phi and a parameter matrix B; S5, acquiring a parameter matrix Theta according to parameters; S6, updating the parameter matrixes Phi, B and Theta; S7, judging whether the parameter matrixes Phi, B and Theta are convergent or not, and updating the parameter matrixes Phi, B and Theta until convergence; S8, acquiring application service elements the most related to the current locations according to convergence values Bf, Thetaf and Phif, and pushing the application service elements to users. The location-based mobile internet user behavior analysis method and device has the advantages that application services are pushed according to the geographic locations of mobile internet users, and marketing accuracy is improved.
Description
[technical field]
The present invention relates to Data Mining, particularly relate to a kind of mobile Internet user behavior analysis method and device of position-based information.
[background technology]
Nowadays the content type in network service is more and more abundanter, the webpage of various information is provided to contain all trades and professions, the various application services that may operate in mobile-terminal platform are powerful and of a great variety, enrich while user selects in these application services, simultaneously also bring the challenge that quantity of information explodes to user.For the service making user can select to meet self-demand from the application service of numerous and complicated, operator wishes to provide personalized service for different users, to realize marketing strategy accurately, thus makes maximize revenue.Therefore need to carry out accurate analysis to the behavior pattern of user, know behavioral characteristic and the use habit thereof of different user colony.
At present the behavioural analysis based on legacy interconnect network users and the large class of the behavioural analysis two based on wireless interconnected network users are mainly contained to the method for Internet user's behavioural analysis.
Behavioural analysis based on legacy interconnect network users exists and effectively cannot identify sole user and obtain its personal attribute and behavioral data, can only carry out the shortcoming of analyses and prediction to single behavior itself.In addition, some adopt the class of service that the user behavior analysis scheme as tagsort algorithms such as neural networks needs predefined user to use at present, and the corresponding relation between the class of business of setting network user use and networks congestion control classification, this way needs to classify to business in advance, the automatic identification of class of business cannot be accomplished, cost of labor is higher, and along with the increase of user and the constantly soaring of class of business, the extensibility of the program is not strong.
Also there is many spaces that can promote in the behavioural analysis based on wireless interconnected network users in subscriber segmentation, user characteristics extraction, at present the segmentation of client is also just rested on and carry out a point stage for heap according to the statistical indicator of user, the excavation carried out user's pent-up demand is careful not and deep, seldom in conjunction with the geographical location information of user in particularly current user behavior analysis scheme.Because there is great correlativity in the behavior of Internet user and the geographic position at this user place, therefore the geographical location information of user has great significance for user behavior analysis.
[summary of the invention]
The present invention is intended to solve above-mentioned problems of the prior art, proposes a kind of mobile Internet user behavior analysis method and device of position-based information.
One aspect of the present invention proposes a kind of mobile Internet user behavior analysis method of position-based information, comprises step: S1, obtain and IMEI code, the IMSI code of storing mobile Internet user, identifies mobile Internet user identity; S2, acquisition store historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, the place of described place element representation mobile interchange network users process, described historical usage information on services comprises some ASEs and the frequency thereof, and described ASE represents the used application service of mobile interchange network users; S3, according to described historical position information initialization place theme L
i(i=1,2 ...), according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, each described application service theme A
jrepresent the set of ASE described in identical type; S4, described historical usage information on services to be sampled, connected applications service theme A
jget parms matrix Φ, and sample to described historical position information, in conjunction with place theme L
iget parms matrix Β, and wherein Φ represents the probability producing each ASE under each application service theme, and Β represents the probability producing each place element under each place theme; S5, employing Gibbs sampling, according to application service theme A
j, place theme L
i, get parms matrix Θ, Θ of parameter matrix Φ, Β represent the probability producing each place theme under each application service theme; S6, employing Gibbs sampling, and based on Maximum-likelihood estimation criterion, undated parameter matrix Φ, Β, Θ; S7, judge whether parameter matrix Φ, Β, Θ value restrains, then repeat step S4 to S6 if not, undated parameter matrix Φ, Β, Θ value is until restrain; S8, the IMEI code obtaining mobile interchange network users, IMSI code and current location information thereof, according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the ASE maximum with the current location information degree of association, and push to described user, wherein, Φ
f, Β
f, Θ
fbe respectively the optimal value after Φ, Β, Θ convergence.
The present invention proposes a kind of mobile Internet user behavior analysis device of position-based information on the other hand, comprise memory module, customer attribute information acquisition module, historical information acquisition module, data processing module, application service pushing module, wherein, described customer attribute information acquisition module obtains IMEI code, the IMSI code of mobile interchange network users, and described memory module stores described IMEI code, IMSI code; Described historical information acquisition module obtains historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, the place of described place element representation mobile interchange network users process, described historical usage information on services comprises some ASEs and the frequency thereof, described ASE represents the used application service of mobile interchange network users, and described memory module stores described historical position information and historical usage information on services; Described data processing module is according to described historical position information initialization place theme L
i(i=1,2 ...), and according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, each described application service theme A
jrepresent the set of ASE described in identical type; Described data processing module is sampled to described historical usage information on services, connected applications service theme A
jget parms matrix Φ, and sample to described historical position information, in conjunction with place theme L
iget parms matrix Β, and wherein Φ represents the probability producing each ASE under each application service theme, and Β represents the probability producing each place element under each place theme; According to application service theme A
j, place theme L
i, parameter matrix Φ, Β, based on Gibbs sampling, get parms matrix Θ, Θ of described data processing module represents the probability producing each place theme under each application service theme; Based on Gibbs sampling and Maximum-likelihood estimation criterion, described data processing module undated parameter matrix Φ, Β, Θ value, until convergence, obtains the optimal value Φ of Φ
f, Β optimal value Β
fand the optimal value Θ of Θ
f; Described customer attribute information acquisition module obtains the IMEI code of mobile interchange network users, IMSI code and current location information thereof, and described data processing module is according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the application service maximum with the current location information degree of association; Described application service pushing module pushes the application service maximum with the current location information degree of association to described user.
The mobile Internet user behavior analysis method of the position-based information that the present invention proposes and device make use of the geographical location information of mobile interchange network users, and based on mobile interchange network users geographical location information and be in this geographic position use the high correlation of application service kind to push its application service of showing great attention to user, improve the accuracy of marketing; The present invention program adopts the probability topic model of improvement automatically from the set of the place of user and behavior set, to extract theme simultaneously, and do not need the class of business of user to classify in advance, decrease the cost of labor that manual classification causes, achieve the automatic identification of class of business, there is stronger extensibility.
[accompanying drawing explanation]
Fig. 1 is the mobile Internet user behavior analysis method flow diagram of the position-based information of one embodiment of the invention;
Fig. 2 is the method flow diagram of the maximum ASE of the acquisition of one embodiment of the invention and the mobile Internet current location information degree of association;
Fig. 3 is the mobile Internet user behavior analysis structure drawing of device of the position-based information of one embodiment of the invention.
[embodiment]
In order to make object of the present invention, technical scheme and advantage more clear, below in conjunction with specific embodiment and accompanying drawing, the present invention is described in further detail.Should be appreciated that specific embodiment described in literary composition is only in order to explain technical scheme of the present invention, and not should be understood to limitation of the present invention.
One aspect of the present invention provides a kind of mobile Internet user behavior analysis method of position-based information, as shown in Figure 1, the method comprises the following steps: S1, obtain and IMEI code, the IMSI code of storing mobile Internet user, identifies mobile Internet user identity; S2, acquisition store historical position information and the historical usage information on services of each identity mobile interchange network users; S3, according to described historical position information initialization place theme L
i(i=1,2 ...), according to described historical usage information on services initialization application service theme A
j(j=1,2 ...); S4, described historical usage information on services to be sampled, connected applications service theme A
jget parms matrix Φ, and sample to described historical position information, and in conjunction with place theme L
iget parms matrix Β; S5, employing Gibbs sampling, according to application service theme A
j, place theme L
i, parameter matrix Φ, Β get parms matrix Θ; S6, employing Gibbs sampling, and based on Maximum-likelihood estimation criterion, undated parameter matrix Φ, Β, Θ; S7, judge whether parameter matrix Φ, Β, Θ value restrains, then repeat step S4 to S6 if not, undated parameter matrix Φ, Β, Θ value is until restrain; S8, the IMEI code obtaining mobile interchange network users, IMSI code and current location information thereof, according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the ASE maximum with the current location information degree of association, and push to described user, wherein, Φ
f, Β
f, Θ
fbe respectively the optimal value after Φ, Β, Θ convergence.
Below the technical scheme of the mobile Internet user behavior analysis method to above-mentioned position-based information is further described in detail.
In step sl, obtained and IMEI code (the International Mobile Equipment Identity of storing mobile Internet user by mobile operator data server, International Mobile Equipment Identity code), IMSI code (International Mobile Subscriber Identity, international mobile subscriber identity), due to the situation of one-telephone multi-card or a card multimachine may be there is, in the present embodiment, using IMEI code and IMSI code jointly as the identify label of mobile interchange network users.
In step s 2, obtained by mobile operator data server and store historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, described place element representation mobile interchange network users is the place of process or place in a period of time T in the past, such as " First People's Hospital ", " Suning market ", " Xinhua Bookstore " etc., the frequency herein and described Internet user be the interior number of times through each place element above-mentioned of a period of time T in the past; Described historical usage information on services comprises some ASEs and the frequency thereof, described ASE represents the used application service in a period of time T in the past of mobile interchange network users, such as " QQ ", " Google Maps ", " popular comment " etc., the frequency herein and described Internet user be the interior number of times using each application service above-mentioned of a period of time T in the past.Preferably, enough large for ensureing the data sample that described historical position information and historical usage information on services comprise, to the value of described time T with some moons or to be longlyer advisable.
In step s3, according to the described historical position information initialization place theme L obtained in step s 2
i(i=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, as as described in mobile interchange network users in a period of time T, once went to the place such as " First People's Hospital ", " the second the People's Hospital ", " healthcare hospital for women & children ", then the set of some above-mentioned places element such as place theme " hospital " representative " First People's Hospital ", " the second the People's Hospital ", " healthcare hospital for women & children "; Meanwhile, in step s3, according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described application service theme A
jrepresent the set of ASE described in identical type, as as described in mobile interchange network users in a period of time T, once used the application service such as " QQ ", " micro-letter ", " Skype ", then the set of some above-mentioned ASEs such as application service theme " chat class " representative " QQ ", " micro-letter ", " Skype ".
Preferably, described application service theme A
j(j=1,2 ...) obeying Multinomial (π) distribution, π obeys Dirichlet (α) distribution, and α is Dirichlet distribution parameter.
In step s 4 which, described historical usage information on services is sampled, in conjunction with described application service theme A
jget parms matrix Φ; Described historical position information is sampled, in conjunction with place theme L simultaneously
iget parms matrix Β, and wherein parameter matrix Φ represents the probability producing each ASE under each application service theme, and parameter matrix Β represents the probability producing each place element under each place theme.
In step s 5, Gibbs sampling is adopted, according to described application service theme A
j(j=1,2 ...), place theme L
i(i=1,2 ...), get parms matrix Θ, Θ of parameter matrix Φ, Β represent the probability producing each place theme under each application service theme.
In step s 6, adopt Gibbs sampling, and based on Maximum-likelihood estimation criterion, undated parameter matrix Φ, Β, Θ; In the step s 7, judge whether parameter matrix Φ, Β, Θ value restrains, then repeat step S4 to S6 if not, undated parameter matrix Φ, Β, Θ value is until convergence.Gibbs sampling calculates LDA(Latent Dirichlet Allocation) a kind of mathematics implementation method of topic model parameter, the method is by Monte Carlo method (Monte Carlo method), adopt class integration method, by a large amount of circulation random samplings, utilize last result of calculation as prior probability, calculate posterior probability more afterwards, according to Bayes and statistics correlation theory, when cycle index is abundant by result of calculation approaching to reality value.The circulation update times K of Gibbs sampling can preset, and K value is larger, parameter matrix optimal value Φ
f, Β
f, Θ
fmore accurate, in the present embodiment, specifically defining K value can be established according to the arithmetic capability of data processor.
In step s 8, the IMEI code of mobile interchange network users, IMSI code and current location information thereof is obtained, according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the ASE maximum with the current location information degree of association, and push to described user, wherein, Φ
f, Β
f, Θ
fbe respectively the optimal value after Φ, Β, Θ convergence.Obtain the IMEI code of mobile interchange network users, IMSI code for determining the identity of described mobile interchange network users, because the IMEI code, the IMSI code that have stored described mobile interchange network users in step sl identify its identity, therefore in step s 8, according to the parameter matrix Β belonging to described mobile interchange network users
f, Θ
f, Φ
fobtain the ASE maximum with the described mobile interchange network users current location information degree of association, and push this application service to described mobile interchange network users.
Preferably, as shown in Figure 2, step S8 specifically comprises the following steps: S81, according to described current location information and parameter matrix Β
fobtain the place theme L maximum with the described current location information degree of association
c; S82, according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c; S83, according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cnamely maximum with the described mobile interchange network users current location information degree of association.Particularly, in step S81, according to the place element in described current location information and parameter matrix Β
fobtain the place theme L maximum with described place elements correlation degree
c, wherein parameter matrix Β
frow represent place element, place theme is shown in list, according to described place element, from parameter matrix Β
fthe column vector that this place element of middle extraction is corresponding, this place element of the element representation wherein in column vector belongs to the probability distribution situation of different location theme, column vector is sorted, and obtains the place theme L of this maximum probability belonging to element of place
c; In step S82, according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c, wherein parameter matrix Θ
frow represent application service theme, place theme is shown in list, according to the place theme L obtained in step S81
c, from parameter matrix Θ
fmiddle extraction place theme L
ccorresponding row vector, the element representation wherein in row vector represents place theme L
cthe probability distribution situation of corresponding different application service theme, sorts row vector, obtains place theme L
cthe application service theme A of corresponding maximum probability
c; In step S83, according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cmaximum with described user's current location information degree of association, wherein parameter matrix Φ
frow represent ASE, application service theme is shown in list, according to the application service theme obtained in step S82, from parameter matrix Φ
fmiddle extraction application service theme A
ccorresponding row vector, the element representation application service theme A wherein in row vector
cthe probability distribution situation of the different application service element comprised, row vector sorted, the ASE that probability is larger represents at application service theme A
clower user uses the possibility of this ASE higher, chooses the ASE E of maximum probability
cas the application service maximum with the described mobile interchange network users current location information degree of association, and push to described mobile interchange network users.
The present invention provides a kind of mobile Internet user behavior analysis device of position-based information on the other hand, as shown in Figure 3, described device comprises: memory module 100, customer attribute information acquisition module 200, historical information acquisition module 300, data processing module 400, application service pushing module 500.
Below the annexation between the mobile Internet user behavior analysis device modules to described position-based information and principle of work are described in further detail.
Described customer attribute information acquisition module 200 is obtained and IMEI code (the International Mobile Equipment Identity of storing mobile Internet user by mobile operator data server, International Mobile Equipment Identity code), IMSI code (International Mobile Subscriber Identity, international mobile subscriber identity), due to the situation of one-telephone multi-card or a card multimachine may be there is, in the present embodiment, using IMEI code and IMSI code jointly as the identify label of mobile interchange network users.Described memory module 100 stores described IMEI code, IMSI code, is used as to identify described mobile Internet user identity.
Described historical information acquisition module 300 is obtained by mobile operator data server and stores historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, described place element representation mobile interchange network users is the place of process or place in a period of time T in the past, such as " First People's Hospital ", " Suning market ", " Xinhua Bookstore " etc., the frequency herein and described Internet user be the interior number of times through each place element above-mentioned of a period of time T in the past; Described historical usage information on services comprises some ASEs and the frequency thereof, described ASE represents the used application service in a period of time T in the past of mobile interchange network users, such as " QQ ", " Google Maps ", " popular comment " etc., the frequency herein and described Internet user be the interior number of times using each application service above-mentioned of a period of time T in the past.Preferably, enough large for ensureing the data sample that described historical position information and historical usage information on services comprise, to the value of described time T with some moons or to be longlyer advisable.Described memory module 100 stores described historical position information and historical usage information on services.
Described data processing module 400 is according to described historical position information initialization place theme L
i(i=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, as as described in mobile interchange network users in a period of time T, once went to the place such as " First People's Hospital ", " the second the People's Hospital ", " healthcare hospital for women & children ", then the set of some above-mentioned places element such as place theme " hospital " representative " First People's Hospital ", " the second the People's Hospital ", " healthcare hospital for women & children "; Meanwhile, described data processing module 400 is according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described application service theme A
jrepresent the set of ASE described in identical type, as as described in mobile interchange network users in a period of time T, once used the application service such as " QQ ", " micro-letter ", " Skype ", then the set of some above-mentioned ASEs such as application service theme " chat class " representative " QQ ", " micro-letter ", " Skype ".
Preferably, described application service theme A
j(j=1,2 ...) obeying Multinomial (π) distribution, π obeys Dirichlet (α) distribution, and α is Dirichlet distribution parameter.
Described data processing module 400 is sampled to described historical usage information on services, in conjunction with described application service theme A
jget parms matrix Φ; Described historical position information is sampled, in conjunction with place theme L simultaneously
iget parms matrix Β, and wherein parameter matrix Φ represents the probability producing each ASE under each application service theme, and parameter matrix Β represents the probability producing each place element under each place theme.
According to described application service theme A
j(j=1,2 ...), place theme L
i(i=1,2 ...), parameter matrix Φ, Β, and based on Gibbs sampling, get parms matrix Θ, Θ of described data processing module 400 represents the probability producing each place theme under each application service theme.
Based on Gibbs sampling and Maximum-likelihood estimation criterion, described data processing module 400 upgrades described parameter matrix Φ, Β, Θ value until convergence, obtains the optimal value Φ of Φ
f, Β optimal value Β
fand the optimal value Θ of Θ
f.Gibbs sampling calculates LDA(Latent Dirichlet Allocation) a kind of mathematics implementation method of topic model parameter, the method is by Monte Carlo method (Monte Carlo method), adopt class integration method, by a large amount of circulation random samplings, utilize last result of calculation as prior probability, calculate posterior probability more afterwards, according to Bayes and statistics correlation theory, when cycle index is abundant by result of calculation approaching to reality value.The circulation update times K of Gibbs sampling can preset, and K value is larger, parameter matrix optimal value Φ
f, Β
f, Θ
fmore accurate, in the present embodiment, specifically defining K value can be established according to the arithmetic capability of described data processing module 400.
Described customer attribute information acquisition module 200 obtains the IMEI code of mobile interchange network users, IMSI code and current location information thereof, and described data processing module 400 is according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the ASE maximum with the current location information degree of association, described application service pushing module 500 pushes this application service to described user.The IMEI code of mobile interchange network users, IMSI code are for determining the identity of described mobile interchange network users, because described memory module 100 has stored the IMEI code of described mobile interchange network users, IMSI code for identifying user identity, therefore according to the parameter matrix Β belonging to described mobile interchange network users
f, Θ
f, Φ
fobtain the ASE maximum with the described mobile interchange network users current location information degree of association, described application service pushing module 500 pushes this application service to described mobile interchange network users.
Preferably, described data processing module 400 is according to described current location information and parameter matrix Β
fobtain the place theme L maximum with the described current location information degree of association
c, according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c, according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cbe the application service maximum with the current location information degree of association.
Particularly, described data processing module 400 is according to the place element in described current location information and parameter matrix Β
fobtain the place theme L maximum with described place elements correlation degree
c, wherein parameter matrix Β
frow represent place element, place theme is shown in list, according to described place element, from parameter matrix Β
fthe column vector that this place element of middle extraction is corresponding, this place element of the element representation wherein in column vector belongs to the probability distribution situation of different location theme, column vector is sorted, and obtains the place theme L of this maximum probability belonging to element of place
c; Described data processing module 400 is according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c, wherein parameter matrix Θ
frow represent application service theme, place theme is shown in list, according to the place theme L obtained in step S71
c, from parameter matrix Θ
fmiddle extraction place theme L
ccorresponding row vector, the element representation wherein in row vector represents place theme L
cthe probability distribution situation of corresponding different application service theme, sorts row vector, obtains place theme L
cthe application service theme A of corresponding maximum probability
c; Described data processing module 400 is according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cmaximum with described user's current location information degree of association, wherein parameter matrix Φ
frow represent ASE, application service theme is shown in list, according to application service theme A
c, from parameter matrix Φ
fmiddle extraction application service theme A
ccorresponding row vector, the element representation application service theme A wherein in row vector
cthe probability distribution situation of the different application service element comprised, row vector sorted, the ASE that probability is larger represents at application service theme A
clower user uses the possibility of this ASE higher, chooses the ASE E of maximum probability
cas the application service maximum with the described mobile interchange network users current location information degree of association, described application service pushing module 500 pushes this application service to described mobile interchange network users.
The mobile Internet user behavior analysis method of the position-based information that the present invention proposes and device make use of the geographical location information of mobile interchange network users, and based on mobile interchange network users geographical location information and be in this geographic position use the high correlation of application service kind to push its application service of showing great attention to user, improve the accuracy of marketing; The present invention program adopts the probability topic model of improvement automatically from the set of the place of user and behavior set, to extract theme simultaneously, and do not need the class of business of user to classify in advance, decrease the cost of labor that manual classification causes, achieve the automatic identification of class of business, there is stronger extensibility.
Although the present invention is described with reference to current better embodiment; but those skilled in the art will be understood that; above-mentioned better embodiment is only used for explaining and technical scheme of the present invention being described; and be not used for limit protection scope of the present invention; any within the spirit and principles in the present invention scope; any modification of doing, equivalence replacement, distortion, improvement etc., all should be included within claims of the present invention.
Claims (6)
1. a mobile Internet user behavior analysis method for position-based information, comprises the following steps:
S1, to obtain and IMEI code, the IMSI code of storing mobile Internet user, mobile Internet user identity is identified;
S2, acquisition store historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, the place of described place element representation mobile interchange network users process, described historical usage information on services comprises some ASEs and the frequency thereof, and described ASE represents the used application service of mobile interchange network users;
S3, according to described historical position information initialization place theme L
i(i=1,2 ...), according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, each described application service theme A
jrepresent the set of ASE described in identical type;
S4, described historical usage information on services to be sampled, connected applications service theme A
jget parms matrix Φ, and sample to described historical position information, in conjunction with place theme L
iget parms matrix Β, and wherein Φ represents the probability producing each ASE under each application service theme, and Β represents the probability producing each place element under each place theme;
S5, employing Gibbs sampling, according to application service theme A
j, place theme L
i, get parms matrix Θ, Θ of parameter matrix Φ, Β represent the probability producing each place theme under each application service theme;
S6, employing Gibbs sampling, and based on Maximum-likelihood estimation criterion, undated parameter matrix Φ, Β, Θ;
S7, judge whether parameter matrix Φ, Β, Θ value restrains, then repeat step S4 to S6 if not, undated parameter matrix Φ, Β, Θ value is until restrain;
S8, the IMEI code obtaining mobile interchange network users, IMSI code and current location information thereof, according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the ASE maximum with the current location information degree of association, and push to described user, wherein, Φ
f, Β
f, Θ
fbe respectively the optimal value after Φ, Β, Θ convergence.
2. the mobile Internet user behavior analysis method of position-based information according to claim 1, is characterized in that, application service theme A
jobey Multinomial (π) distribution, π obeys Dirichlet (α) distribution, and α is Dirichlet distribution parameter.
3. the mobile Internet user behavior analysis method of position-based information according to claim 1, step S8 comprises the following steps:
S81, according to described current location information and parameter matrix Β
fobtain the place theme L maximum with the described current location information degree of association
c;
S82, according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c;
S83, according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cmaximum with described user's current location information degree of association.
4. a mobile Internet user behavior analysis device for position-based information, comprising: memory module, customer attribute information acquisition module, historical information acquisition module, data processing module, application service pushing module, wherein,
Described customer attribute information acquisition module obtains IMEI code, the IMSI code of mobile interchange network users, and described memory module stores described IMEI code, IMSI code;
Described historical information acquisition module obtains historical position information and the historical usage information on services of each identity mobile interchange network users, described historical position information comprises some places element and the frequency thereof, the place of described place element representation mobile interchange network users process, described historical usage information on services comprises some ASEs and the frequency thereof, described ASE represents the used application service of mobile interchange network users, and described memory module stores described historical position information and historical usage information on services;
Described data processing module is according to described historical position information initialization place theme L
i(i=1,2 ...), and according to described historical usage information on services initialization application service theme A
j(j=1,2 ...), wherein each described place theme L
irepresent the set of place element described in identical type, each described application service theme A
jrepresent the set of ASE described in identical type;
Described data processing module is sampled to described historical usage information on services, connected applications service theme A
jget parms matrix Φ, and sample to described historical position information, in conjunction with place theme L
iget parms matrix Β, and wherein Φ represents the probability producing each ASE under each application service theme, and Β represents the probability producing each place element under each place theme;
According to application service theme A
j, place theme L
i, parameter matrix Φ, Β, based on Gibbs sampling, get parms matrix Θ, Θ of described data processing module represents the probability producing each place theme under each application service theme;
Based on Gibbs sampling and Maximum-likelihood estimation criterion, described data processing module undated parameter matrix Φ, Β, Θ value, until convergence, obtains the optimal value Φ of Φ
f, Β optimal value Β
fand the optimal value Θ of Θ
f;
Described customer attribute information acquisition module obtains the IMEI code of mobile interchange network users, IMSI code and current location information thereof, and described data processing module is according to the parameter matrix Β belonging to described user
f, Θ
f, Φ
fobtain the application service maximum with the current location information degree of association;
Application service pushing module pushes the application service maximum with the current location information degree of association to described user.
5. the mobile Internet user behavior analysis device of position-based information according to claim 4, is characterized in that, application service theme A
jobey Multinomial (π) distribution, π obeys Dirichlet (α) distribution, and α is Dirichlet distribution parameter.
6. the mobile Internet user behavior analysis device of position-based information according to claim 4, is characterized in that, described data processing module is according to described current location information and parameter matrix Β
fobtain the place theme L maximum with the described current location information degree of association
c, according to parameter matrix Θ
fobtain and L
cthe application service theme A that the degree of association is maximum
c, according to parameter matrix Φ
fobtain and A
cthe ASE E that the degree of association is maximum
c, described ASE E
cbe the application service maximum with the current location information degree of association.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310239737.4A CN104239327B (en) | 2013-06-17 | 2013-06-17 | A kind of mobile Internet user behavior analysis method and device based on positional information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310239737.4A CN104239327B (en) | 2013-06-17 | 2013-06-17 | A kind of mobile Internet user behavior analysis method and device based on positional information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104239327A true CN104239327A (en) | 2014-12-24 |
| CN104239327B CN104239327B (en) | 2017-11-07 |
Family
ID=52227416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310239737.4A Active CN104239327B (en) | 2013-06-17 | 2013-06-17 | A kind of mobile Internet user behavior analysis method and device based on positional information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239327B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106488493A (en) * | 2015-08-24 | 2017-03-08 | 阿里巴巴集团控股有限公司 | The method and apparatus of the network hotspot type of identifying user and electronic equipment |
| CN107071181A (en) * | 2017-04-27 | 2017-08-18 | 长沙军鸽软件有限公司 | A kind of method of Auto-matching communication contact people |
| CN107613084A (en) * | 2017-10-09 | 2018-01-19 | 陈包容 | The methods, devices and systems that a kind of address book contact is grouped automatically |
| CN107704586A (en) * | 2017-10-09 | 2018-02-16 | 陈包容 | A kind of methods, devices and systems of user's portrait based on User Activity address |
| CN110070371A (en) * | 2017-11-20 | 2019-07-30 | 腾讯科技（深圳）有限公司 | A kind of data prediction model method for building up and its equipment, storage medium, server |
| CN110377521A (en) * | 2019-07-23 | 2019-10-25 | 郑州阿帕斯科技有限公司 | A kind of target object verification method and device |
| CN110852556A (en) * | 2019-09-20 | 2020-02-28 | 国网浙江省电力有限公司 | 95598 automatic order dispatching method for first-aid repair work order |
| CN111209531A (en) * | 2018-11-21 | 2020-05-29 | 百度在线网络技术（北京）有限公司 | Method and device for processing association degree and storage medium |
| CN113946753A (en) * | 2021-10-29 | 2022-01-18 | 平安科技（深圳）有限公司 | Service recommendation method, device, equipment and storage medium based on position fence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293116A1 (en) * | 2007-11-08 | 2010-11-18 | Shi Cong Feng | Url and anchor text analysis for focused crawling |
| CN101986298A (en) * | 2010-10-28 | 2011-03-16 | 浙江大学 | Information real-time recommendation method for online forum |
| CN102355623A (en) * | 2011-06-29 | 2012-02-15 | 青岛百灵信息科技有限公司 | System and method for changing applicable desktop theme of mobile terminal according to position of mobile terminal |
| CN102591917A (en) * | 2011-12-16 | 2012-07-18 | 华为技术有限公司 | Data processing method and system and related device |
| CN102902700A (en) * | 2012-04-05 | 2013-01-30 | 中国人民解放军国防科学技术大学 | Online-increment evolution topic model based automatic software classifying method |
-
2013
- 2013-06-17 CN CN201310239737.4A patent/CN104239327B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293116A1 (en) * | 2007-11-08 | 2010-11-18 | Shi Cong Feng | Url and anchor text analysis for focused crawling |
| CN101986298A (en) * | 2010-10-28 | 2011-03-16 | 浙江大学 | Information real-time recommendation method for online forum |
| CN102355623A (en) * | 2011-06-29 | 2012-02-15 | 青岛百灵信息科技有限公司 | System and method for changing applicable desktop theme of mobile terminal according to position of mobile terminal |
| CN102591917A (en) * | 2011-12-16 | 2012-07-18 | 华为技术有限公司 | Data processing method and system and related device |
| CN102902700A (en) * | 2012-04-05 | 2013-01-30 | 中国人民解放军国防科学技术大学 | Online-increment evolution topic model based automatic software classifying method |
Non-Patent Citations (2)
| Title |
|---|
| MEMILLAN,C ETC: "Categorizing software applications for maintenance", 《INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE》 * |
| 朱荣鑫: "基于地理位置的社交网络***和位置推荐模型研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106488493A (en) * | 2015-08-24 | 2017-03-08 | 阿里巴巴集团控股有限公司 | The method and apparatus of the network hotspot type of identifying user and electronic equipment |
| CN106488493B (en) * | 2015-08-24 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Method and device for identifying network hotspot type of user and electronic equipment |
| CN107071181B (en) * | 2017-04-27 | 2020-01-10 | 长沙军鸽软件有限公司 | Method for automatically matching communication contact persons |
| CN107071181A (en) * | 2017-04-27 | 2017-08-18 | 长沙军鸽软件有限公司 | A kind of method of Auto-matching communication contact people |
| CN107704586A (en) * | 2017-10-09 | 2018-02-16 | 陈包容 | A kind of methods, devices and systems of user's portrait based on User Activity address |
| CN107613084A (en) * | 2017-10-09 | 2018-01-19 | 陈包容 | The methods, devices and systems that a kind of address book contact is grouped automatically |
| CN110070371A (en) * | 2017-11-20 | 2019-07-30 | 腾讯科技（深圳）有限公司 | A kind of data prediction model method for building up and its equipment, storage medium, server |
| CN110070371B (en) * | 2017-11-20 | 2022-11-18 | 腾讯科技（深圳）有限公司 | Data prediction model establishing method and equipment, storage medium and server thereof |
| CN111209531A (en) * | 2018-11-21 | 2020-05-29 | 百度在线网络技术（北京）有限公司 | Method and device for processing association degree and storage medium |
| CN111209531B (en) * | 2018-11-21 | 2023-08-08 | 百度在线网络技术（北京）有限公司 | Correlation degree processing method, device and storage medium |
| CN110377521A (en) * | 2019-07-23 | 2019-10-25 | 郑州阿帕斯科技有限公司 | A kind of target object verification method and device |
| CN110377521B (en) * | 2019-07-23 | 2022-11-18 | 郑州阿帕斯科技有限公司 | Target object verification method and device |
| CN110852556A (en) * | 2019-09-20 | 2020-02-28 | 国网浙江省电力有限公司 | 95598 automatic order dispatching method for first-aid repair work order |
| CN113946753A (en) * | 2021-10-29 | 2022-01-18 | 平安科技（深圳）有限公司 | Service recommendation method, device, equipment and storage medium based on position fence |
| CN113946753B (en) * | 2021-10-29 | 2024-04-12 | 平安科技（深圳）有限公司 | Service recommendation method, device, equipment and storage medium based on location fence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104239327B (en) | 2017-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104239327A (en) | Location-based mobile internet user behavior analysis method and device | |
| CN108985309B (en) | Data processing method and device | |
| CN107657015B (en) | Interest point recommendation method and device, electronic equipment and storage medium | |
| CN103678431B (en) | A kind of recommendation method to be scored based on standard label and project | |
| CN111210269A (en) | Object identification method based on big data, electronic device and storage medium | |
| CN105338619B (en) | Positioning method and device | |
| CN108052639A (en) | Industry user based on carrier data recommends method and device | |
| CN111339436B (en) | Data identification method, device, equipment and readable storage medium | |
| CN110738577B (en) | Community discovery method, device, computer equipment and storage medium | |
| CN107545451B (en) | Advertisement pushing method and device | |
| CN109344314B (en) | Data processing method and device and server | |
| US20160034968A1 (en) | Method and device for determining target user, and network server | |
| CN104750705A (en) | Information returning method and device | |
| CN107404656A (en) | Live video recommends method, apparatus and server | |
| CN109446171B (en) | Data processing method and device | |
| CN104765793A (en) | Software recommending method and server | |
| JP6049186B2 (en) | Apparatus, program, and method for estimating staying place of user having portable terminal | |
| CN105512156B (en) | Click model generation method and device | |
| CN111382212A (en) | Associated address acquisition method and device, electronic equipment and storage medium | |
| CN110019622A (en) | A kind of real time mass map point polymerization and device | |
| CN110263840B (en) | Line analysis method, device, program product and storage medium | |
| CN109145129A (en) | Depth measure learning method and its device based on level triple loss function | |
| CN112214677B (en) | Point of interest recommendation method and device, electronic equipment and storage medium | |
| CN110968802B (en) | Analysis method and analysis device for user characteristics and readable storage medium | |
| CN111158828A (en) | User interface determining method and device of application program APP and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |