CN105227445B - Recommend platform using methods and applications are recommended - Google Patents
Recommend platform using methods and applications are recommended Download PDFInfo
- Publication number
- CN105227445B CN105227445B CN201510697893.4A CN201510697893A CN105227445B CN 105227445 B CN105227445 B CN 105227445B CN 201510697893 A CN201510697893 A CN 201510697893A CN 105227445 B CN105227445 B CN 105227445B
- Authority
- CN
- China
- Prior art keywords
- application
- user
- business platform
- recommended
- access
- 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.)
- Active
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of application and methods and applications is recommended to recommend business platform, wherein this method includes:Using the application data for recommending business platform to acquire acquisition user from carrier server;Using recommending business platform application data to carry out data mining analysis, the characteristic information of user is obtained;The list information of the application to be recommended to user is determined, and the list information of application is sent to user according to characteristic information using business platform is recommended.The demand according to user itself is realized to the recommendation list of user's sending application, meets individual demand of the different user for application.
Description
Technical field
The present invention relates to development of Mobile Internet technology more particularly to a kind of application, and methods and applications to be recommended to recommend business platform.
Background technology
With the continuous development of development of Mobile Internet technology, various applications are constantly come into being, these applications can be with
It is applied on mobile terminal, network or application shop can recommend various applications to user.
In the prior art, network or application shop can get all users for each application searching times, under
It carries number and user comments grading information, the comprehensive score of each application is obtained after then being calculated these information;Network
Or application shop is ranked up each application according to the comprehensive score of each application, thus by the higher application of comprehensive score
Recommend user.
However the prior art provide can only recommend that user's searching times, download time are higher to answer using recommendation method
With cannot be satisfied individual demand of the different user for application.
Invention content
The present invention provides a kind of application recommendation methods and applications recommendation business platform, to solve answering for prior art offer
The higher application of user's searching times, download time can only be recommended with recommendation method, cannot be satisfied different user for application
Individual demand the problem of.
It is an aspect of the present invention to provide method is recommended in a kind of application, including:
Using the application data for recommending business platform to acquire acquisition user from carrier server;
The application recommends business platform to carry out data mining analysis to the application data, obtains the feature of the user
Information;
The application recommends business platform according to the characteristic information, determines the list of the application to be recommended to the user
Information, and the list information of the application is sent to the user.
It is an aspect of the present invention to provide business platform is recommended in a kind of application, including:
Data acquisition module, the application data for the acquisition acquisition user from carrier server;
Data-mining module obtains the feature letter of the user for carrying out data mining analysis to the application data
Breath;
Using recommending module, for according to the characteristic information, determining the list letter of the application to be recommended to the user
Breath, and the list information of the application is sent to the user.
The present invention acquires the application data for obtaining user by application recommendation business platform from carrier server;Using
Recommend business platform application data to carry out data mining analysis, obtains the characteristic information of user;Using recommendation business platform root
According to characteristic information, the list information of the application to be recommended to user is determined, and the list information of application is sent to user.It realizes
By analyzing the feature of user itself, according to the demand of user itself to the recommendation list of user's sending application, meet different
Individual demand of the user for application.
Description of the drawings
Fig. 1 is the flow chart using recommendation method that the embodiment of the present invention one provides;
Fig. 2 is the flow chart using recommendation method that the embodiment of the present invention one provides;
Fig. 3 is the structural schematic diagram that business platform is recommended in the application that the embodiment of the present invention three provides;
Fig. 4 is the structural schematic diagram that business platform is recommended in the application that the embodiment of the present invention four provides.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart using recommendation method that the embodiment of the present invention one provides, as shown in Figure 1, the side of the present embodiment
Method, including:
Step 101 acquires the application data for obtaining user using recommendation business platform from carrier server.
In the present embodiment, it specifically, collecting device can be disposed on carrier server, goes to detect user in real time and exists
Mobile interchange online behavioral data and signaling data, deep analysis analysis, to which application recommends business platform can be from fortune
The application data that acquisition on quotient's server obtains user are sought, these are using the phone number that data can be mobile terminal, access
Network address accesses the time started, accesses the end time, accesses the letters such as duration, flowing of access, type of service, user base station/cell
Breath.Such as:
Table 1 applies data
Step 102 carries out data mining analysis using recommendation business platform application data, obtains the feature letter of user
Breath.
In the present embodiment, specifically, application recommends business platform to carry out data to the application data obtained in step 101
Mining analysis, so as to obtain characteristic information of the user within period certain time.
Step 103, using business platform is recommended according to characteristic information, determine that the list of the application to be recommended to user is believed
Breath, and the list information of application is sent to user.
In the present embodiment, specifically, application recommends business platform according to characteristic information, the feature of user is determined, from
And the list information of application can be recommended to user according to the feature of user itself, and the list information of application is sent to use
Family.
The present embodiment recommends application data of the business platform to the user got from carrier server by application,
Data mining analysis is carried out, the characteristic information of user can be obtained, then according to characteristic information, determine answering to user to be recommended
List information, and the list information of application is sent to user.To realize the feature by analyzing user itself, root
According to the demand of user itself to the recommendation list of user's sending application, meet individual demand of the different user for application.
Fig. 2 is the flow chart using recommendation method that the embodiment of the present invention one provides, and on the basis of embodiment one, is such as schemed
Shown in 2, in the method for the present embodiment, including:
Step 101 acquires the application data for obtaining user using recommendation business platform from carrier server.
In the present embodiment, specifically, application, which recommends business platform that can be acquired from carrier server, obtains user
Application data, these using data can be mobile terminal phone number, access network address, access the time started, access knot
The beam time accesses the information such as duration, flowing of access, type of service, user base station/cell.
Step 201 carries out data mining analysis using recommendation business platform application data, obtains the hobby of user
Feature and/or crowd's attributive character.
In the present embodiment, specifically, application recommends business platform to carry out data to the application data obtained in step 101
Mining analysis in the present embodiment, does not limit the concrete mode of data mining analysis.To pass through the digging of application data
Pick, hobby feature of analysis user when using each application software, hobby characteristic present user uses each
The fancy grade of application software;Crowd's attributive character of user can also be analyzed, crowd's attributive character characterizes user and belongs to
Which kind of crowd;The hobby feature and crowd's attributive character of user can also be obtained simultaneously.
Step 202, using recommend business platform according to hobby feature and/or crowd's attributive character, determine to be recommended
To the list information of the application of user.
In the present embodiment, specifically, application recommends business platform that can go basis according to the hobby feature of user
User uses the fancy grade of each application software, the list information of the application to be recommended to user is determined, for example, user's is emerging
Interest hobby feature shows that user is interested in the application software of game class, class of doing shopping, it is determined that goes out answering to user to be recommended
Include in list information game class, do shopping class application software.It can also be according to user's using recommendation business platform
Crowd's attributive character determines the list information of the application to be recommended to user, for example, crowd's attributive character display of user is used
Family is working clan, it is determined that is gone out to be recommended to the application software in the list information of the application of user including office class.Using
Recommend business platform can also be according to the hobby feature and crowd's attributive character of user, comprehensive going is determining to be recommended to use
The list information of the application at family, for example, the hobby feature of user shows that user is interested in the application software for class of doing shopping,
Crowd's attributive character of the user is working clan simultaneously, it is determined that goes out in the list information to be recommended to the application of user and includes
Shopping class, the application software for class of handling official business.
The present embodiment recommends business platform special according to the hobby feature and/or crowd's attribute for obtaining user by application
Sign removes the list information for determining the application to be recommended to user.To realize by analyze user itself feature, according to
The demand at family itself meets individual demand of the different user for application to the recommendation list of user's sending application.
Further, on the basis of the above embodiments, step 101, specifically include:
Using the access service corresponding with each application for recommending business platform to acquire acquisition user from carrier server
Type accesses duration, visitation frequency and flowing of access.
Then correspondingly, the application in step 201 recommends business platform application data to carry out data mining analysis, used
The hobby feature at family, specifically includes:
Using recommendation business platform according to access duration S corresponding with each applicationi, visitation frequency FiWith flowing of access Mi, really
The score A of fixed each applicationi=Q1Si/STotal i+Q2Fi/FTotal i+Q3Mi/MTotal i, wherein Q1、Q2And Q3For the first different default weights
Value, STotal i、FTotal iAnd MTotal iRespectively user accesses the access total duration of each application, accesses total frequency and accesses total flow, i ∈ [1,
N], i is positive integer, and N is positive integer;
Using recommendation business platform according to the score A of each applicationi, and access service type corresponding with each application, really
Surely belong to each interest index of the application of same access service typeWherein, [1, B] b ∈, b are positive integer,
B is positive integer;
Using recommendation business platform according to each interest index Ib, and the scoring respectively applied that obtains in advance, determination respectively answer
Recommend indices P in basisi;
Using each similarity for recommending business platform to determine the application in each application mobile terminal currently used with user
Sij, wherein j ∈ [1, J], j are positive integer, and J is positive integer;
Using recommendation business platform according to each similarity Sij, indices P is recommended on the basis for adjusting each applicationi'={ 1- (Si1-
SThreshold value)}PiQ1'+…+{1-(Sij-SThreshold value)}PiQi'+…+{1-(SiJ-SThreshold value)}PiQ'N, wherein SThreshold valueTo preset similarity threshold,
Qi' it is the second default weighted value;
Using recommending business platform to recommend index according to the basis after adjustment, each application is ranked up, interest is obtained and pushes away
List is recommended, interest recommendation list is used to characterize the hobby feature of user.
In the present embodiment, specifically, application recommendation business platform can be acquired from carrier server and be got
The various data corresponding with each application of user, these data include access service type corresponding with each application, access duration,
Visitation frequency and flowing of access.So as to get each application, i.e., the access service type of each application, when accessing
Long, visitation frequency and flowing of access.
For each application, according to the access duration S of the application each timei, visitation frequency FiWith flowing of access Mi, really
It is scheduled on the access total duration S that user in preset time accesses each applicationTotal i, access total frequency FTotal iWith access total flow MTotal i, calculate
Go out the score A of each applicationi=Q1Si/STotal i+Q2Fi/FTotal i+Q3Mi/MTotal i, wherein, Q1、Q2And Q3For the difference being arranged according to experience
The first default weighted value, and i ∈ [1, N], i are positive integer, and N is positive integer.Then statistics belongs to same access service class
The sum of score of application of type, can be according to the obtained score A respectively appliedi, and access service class corresponding with each application
Type calculates each interest index for the application for belonging to same access service typeWherein, [1, B] b ∈, b are
Positive integer, B are positive integer.Each interest index is ranked up, then according to the descending of the value of each interest index to belonging to same
The application of access service type is ranked up, and it is interested in the application of which type can to obtain user.
Using recommending business platform that can get comprehensive score of all users for each application in advance, according to these scorings
And each interest index Ib, indices P is recommended on the basis that each application is calculated using common proposed algorithmi, common proposed algorithm
Can be that applicating cooperation is recommended, user coordinates to recommend scheduling algorithm.Then application recommends business platform to recommend the basis of each application
Indices PiBe ranked up according to descending, choose before ranking n applications and with the corresponding basic recommendation of preceding n of application
Index forms a basic recommendation list.
The installed score respectively applied in the mobile terminal in active user is counted using recommendation business platform, this
Score can be obtained by data mining analysis, can also be scoring of all users for each application, be put down using business is recommended
It is preceding m of application that platform, which chooses score rank,.Using recommend business platform according to the label respectively applied in basic recommendation list,
And m labels respectively applied before the ranking in the currently used mobile terminal of user, it determines each in the recommendation list of basis
Using the similarity S between m before the ranking in the currently used mobile terminal of user each applicationsij, wherein j ∈ [1,
J], j is positive integer, and J is positive integer.Label can be converted into vector, and the calculating of similarity, which may be used, seeks two vector folders
The method of angle cosine value.
Then business platform is recommended in application, according to each similarity Sij, indices P is recommended on the basis for adjusting each applicationi'={ 1-
(Si1-SThreshold value)}PiQ1'+…+{1-(Sij-SThreshold value)}PiQi'+…+{1-(SiJ-SThreshold value)}PiQ'N, wherein SThreshold valueTo preset similarity
Threshold value, Qi' it is the second default weighted value being arranged according to experience.
Using recommending business platform to recommend index according to the basis after adjustment, recommend the drop of index according to the basis after adjustment
Sequence resequences to each application in basic recommendation list, obtains an interest recommendation list, it is known that current use
The more interested application in family is discharged to before interest recommendation list, to which interest recommendation list characterizes the interest love of user
Good feature.
Present embodiment by according to get access service type corresponding with each application, access duration, access frequently
Secondary and flowing of access determines the hobby feature of active user.
Further, on the basis of the above embodiments, step 101, specifically include:
Using recommendation business platform since acquisition on carrier server obtains the access corresponding with each application of user
Time accesses the end time, accesses base station;
Then correspondingly, the application in step 201 recommends business platform application data to carry out data mining analysis, used
Crowd's attributive character at family, specifically includes:
User is determined according to access time started corresponding with each application, access end time using business platform is recommended
Daily surf time ratio;
The daily movement locus of user is determined according to access base station corresponding with each application using business platform is recommended;
It determines and uses according to the daily surf time ratio of user and daily movement locus using business platform is recommended
Crowd's attributive character at family.
In the present embodiment, specifically, application recommends business platform that can also acquire acquisition from carrier server
To user's various data corresponding with each application, these data include the access time started corresponding with each application, access knot
The beam time accesses base station.
It can be counted according to access time started corresponding with each application, access end time using business platform is recommended
Go out user each preset time period surf time distribution situation.Specifically, one day time was divided into first several isometric
Period, such as be divided into the morning (6:00-12:00), afternoon (12:00-18:00), evening (18:00-24:00), night
(24:00-6:00).It is determined according to access time started corresponding with each application, access end time using business platform is recommended
Go out user in the online total time of each period, may thereby determine that out surf time of the user daily in each period
Ratio, for example, it is 0.5 hour morning that situation is distinguished in the daily online of user, in 0.5 hour afternoon, 4 hours at night, night 0 was small
When, then the daily surf time ratio for obtaining the user is { 0.5/24,0.5/24,4/24,0 }.Meanwhile using recommendation business
The daily surf time ratio of each user can be compared by platform, obtained each user and referred in the leisure of each period
Number, for example, all users are counted in the online total time of each period, the descending pair of the online total time of each period
User is ranked up on each period, the leisure index of each period is redefined for as Pyatyi, in some period
20% user's leisure index is 5 before middle ranking, and 20%~40% user's leisure index is 4, and 40%~60% user stops
Not busy index is 3, and 60%~80% user's leisure index is 2, and 80% or more user's leisure index is 1, and active user A exists
The surf time ratio of each period is respectively 70%, 70%, 15%, 100%, correspondingly, leisure of the user in each period
Index is { 2,2,5,1 }.
Visit corresponding with each application can be determined using business platform is recommended according to access base station corresponding with each application
It asks the location information carried in the update signaling message of base station, user location is divided into several regions, such as business according to function
Area, living area, workspace, school, hospital etc..Using recommendation business platform according to location information corresponding with each application, and
Access starting and end time corresponding with each application, user is determined in the location of each time point environment, for example,
9 points in the morning of user A, present position is workspace.Existed according to the user determined in preset time using business platform is recommended
The location of each time point environment, examinations go out change in location situation of the user in preset time, to be used
The daily movement locus in family, for example, 9 points of user's A mornings, in workspace, at ten two points at noon in shopping centre, is living for 8 points at night
Area etc..
Using recommendation business platform according to the daily surf time ratio of the user determined and daily movement rail
Mark judges crowd's attributive character of user, wherein crowd's attributive character of user can be working clan, student, idle race
Deng.For example, user's A Mon-Fris, daytime, at night in living area, deducibility user A was working clan in workspace.
Present embodiment is by the end of according to access time started corresponding with each application of the user that gets, access
Between, access base station, determine the daily surf time ratio of user and daily movement locus, then can determine user
Crowd's attributive character.
Further, on the basis of the above embodiments, in step 103 using recommend business platform according to characteristic information,
The list information for determining the application to be recommended to user, specifically includes:
Using the geographical location and current time for recommending business platform to be presently according to characteristic information, user, determine
The list information of application to be recommended to user.
In the present embodiment, specifically, application recommend business platform according to determine user hobby feature and/or
These characteristic informations of crowd's attributive character, while the geographical location being presently according to user and current time, determination wait pushing away
It recommends to the list information of the application of user.
Specifically, application recommends business platform that can be only presently according to the hobby feature of user and user
Geographical location and current time, the list information of the application to be recommended to user is determined, for example, the hobby of user is special
Sign shows that user is interested in the application of game class, detects that the current place of user goes out the time in the evening using business platform is recommended
Section and be located at residential area, it is determined that the list information of the application to be recommended to user gone out includes answering for various game class
With.
Using the geography for recommending business platform that can also be only presently according to crowd's attributive character of user and user
Position and current time determine the list information of the application to be recommended to user, for example, crowd's attributive character of user is shown
User is working clan, using recommend business platform detect user be currently located at workspace and currently for the work hours section, then really
The list information for the application to be recommended to user made includes news, weather, investment software, office software, chat software
Equal tool-class application.For another example crowd's attributive character of user shows that user is working clan, detected using business platform is recommended
User is currently located at workspace or shopping centre, and is currently time of having a rest section, it is determined that the application to be recommended to user gone out
List information includes the service class applications such as take-away, food delivery, food and drink recommendation.For another example crowd's attributive character display of user is used
Family is working clan, and using recommending business platform to detect, user is currently located at living area, and is currently the period in the evening, it is determined that
The list information of the application to be recommended to user gone out includes the amusement such as video, music, game, Taobao, the application of shopping class.
User can be carried out to crowd's division, the time of user carries out fragment processing, and position carries out function division, formulates context aware and pushes away
Strategy is recommended, is exemplified below:
The list information of the application to be recommended to user of table 2
It can also be simultaneously according to the hobby feature and crowd's attributive character of user, Yi Jiyong using recommendation business platform
The geographical location and current time that family is presently in determine the list information of the application to be recommended to user.For example, user
Hobby feature show user to financial class and music class should be interested, crowd's attributive character display of user is used
Family is working clan, and using recommending business platform to detect, user is currently located at living area, and is currently the period in the evening, it is determined that
The list information of the application to be recommended to user gone out includes the application of financial class, music class.
Present embodiment recommends business platform special according to the hobby feature or/and crowd's attribute of user by application
Sign, the geographical location and current time that user is presently in determine the list information of the application to be recommended to user.To needle
It to each user feature of itself, and according to current time and position, specifies out using recommendation list, to precisely be pushed away for user
It recommends and meets its interest, and take into account the application of its current location, temporal information, meet different user in different time, different location
For the individual demand of application.
Further, on the basis of the above embodiments, the list information of application is sent to user in step 103, wrapped
It includes:
The list information of application is sent to after the recommendation request for receiving user's transmission using business platform is recommended
User;
Alternatively,
After user logs in application recommendation business platform, the list information of application is sent to use using business platform is recommended
Family;
Alternatively,
The list information of application is sent to user within the preset period using business platform is recommended.
In the present embodiment, specifically, application recommends business platform to be sent to the list information for the application determined
User.User can recommend the recommendation request that business platform is sent to application, will in real time be analyzed using business platform is recommended
The list information of application is sent to user, or application recommends business platform by the list information for the application having predetermined that out
It is sent to user.
It can also be that user logs in application and recommends business platform, then, will be had confirmed using business platform is recommended
The list information of application is sent to user, or after user logs in application recommendation business platform, using recommendation business platform
The list information for the application determined in real time is sent to user.
Can also be that it includes each period that user, which specifies out a first push timetable, the first push timetable,
Using recommendation business platform within preset each period, the list information of application is sent to user,
Can also be, using recommending business platform to specify out a second push timetable, to be wrapped in the second push timetable
Include each period, using current location and time of the business platform according to user is recommended, in different times in section to
The higher application of ranking in the list information for the application that family transmission is determined.
Can also be, using in recommendation business platform in different times section, to the leisure higher user of index, to send true
The higher application of ranking in the list information for the application made.
Fig. 3 is the structural schematic diagram that business platform is recommended in the application that the embodiment of the present invention three provides, as shown in figure 3, this reality
Business platform is recommended in the application for applying example offer, including:
Data acquisition module 31, the application data for the acquisition acquisition user from carrier server;
Data-mining module 32 carries out data mining analysis for application data, obtains the characteristic information of user;
Using recommending module 33, it is used to, according to characteristic information, determine the list information of the application to be recommended to user, and will
The list information of application is sent to user.
What the executable embodiment of the present invention one of application recommendation business platform of the present embodiment provided applies recommendation method, in fact
Existing principle is similar, and details are not described herein again.
The present embodiment recommends application data of the business platform to the user got from carrier server by application,
Data mining analysis is carried out, the characteristic information of user can be obtained, then according to characteristic information, determine answering to user to be recommended
List information, and the list information of application is sent to user.To realize the feature by analyzing user itself, root
According to the demand of user itself to the recommendation list of user's sending application, meet individual demand of the different user for application.
Fig. 4 is the structural schematic diagram that business platform is recommended in the application that the embodiment of the present invention four provides, in the base of embodiment three
On plinth, as shown in figure 4, application provided in this embodiment is recommended in business platform, data-mining module 32, including:
Data mining submodule 321 carries out data mining analysis for application data, and the hobby for obtaining user is special
Sign and/or crowd's attributive character;
Correspondingly, using recommending module 33, including:
Using determination sub-module 331, for according to hobby feature and/or crowd's attributive character, determine it is to be recommended to
The list information of the application of user;
Using sending submodule 332, for the list information applied to be sent to user.
Data acquisition module 31, is specifically used for:Acquisition obtains the corresponding with each application of user from carrier server
Access service type accesses duration, visitation frequency and flowing of access;
Correspondingly, data mining submodule 321 is carrying out data mining analysis for application data, the emerging of user is obtained
When interest hobby feature, it is specifically used for:
According to access duration S corresponding with each applicationi, visitation frequency FiWith flowing of access Mi, determine the score A of each applicationi
=Q1Si/STotal i+Q2Fi/FTotal i+Q3Mi/MTotal i, wherein Q1、Q2And Q3For the first different default weighted values, STotal i、FTotal iAnd MTotal iRespectively
The access total duration of each application is accessed, total frequency is accessed and accesses total flow for user, i ∈ [1, N], i are positive integer, and N is just
Integer;
According to the score A of each applicationi, and access service type corresponding with each application, it is determining to belong to same access industry
Each interest index of the application of service typeWherein, [1, B] b ∈, b are positive integer, and B is positive integer;
According to each interest index Ib, and the scoring respectively applied that obtains in advance, determine that index is recommended on the basis of each application
Pi;
Determine each similarity S of the application in each application mobile terminal currently used with userij, wherein j ∈ [1, J],
J is positive integer, and J is positive integer;
According to each similarity Sij, indices P is recommended on the basis for adjusting each applicationi'={ 1- (Si1-SThreshold value)}PiQ1'+…+{1-
(Sij-SThreshold value)}PiQi'+…+{1-(SiJ-SThreshold value)}PiQ'N, wherein SThreshold valueTo preset similarity threshold, Qi' it is the second default weight
Value;
Recommend index according to the basis after adjustment, each application is ranked up, obtain interest recommendation list, interest recommends row
Table is used to characterize the hobby feature of user.
Data acquisition module 31, is specifically used for:Acquisition obtains the corresponding with each application of user from carrier server
The time started is accessed, the end time is accessed, accesses base station;
Correspondingly, data mining submodule 321 is carrying out data mining analysis for application data, the people of user is obtained
When group's attributive character, it is specifically used for:
According to the access time started corresponding with each application, the end time is accessed, determines the daily surf time ratio of user
Example;
According to access base station corresponding with each application, the daily movement locus of user is determined;
According to the daily surf time ratio of user and daily movement locus, crowd's attributive character of user is determined.
Using determination sub-module 331, it is specifically used for:
The geographical location being presently according to characteristic information, user and current time determine answering to user to be recommended
List information.
Using sending submodule 332, it is specifically used for:
After the recommendation request for receiving user's transmission, the list information of application is sent to user;Alternatively, in user
After logging in application recommendation business platform, the list information of application is sent to user;Alternatively, within the preset period, will answer
List information is sent to user.
The application of the present embodiment recommends the executable embodiment of the present invention two of business platform and the above embodiment to provide
Using method is recommended, realization principle is similar, and details are not described herein again.
The present embodiment recommends business platform special according to the hobby feature and/or crowd's attribute for obtaining user by application
Sign removes the list information for determining the application to be recommended to user.To realize by analyze user itself feature, according to
The demand at family itself meets individual demand of the different user for application to the recommendation list of user's sending application.Also, this
Embodiment recommends business platform current according to the hobby feature of user or/and crowd's attributive character, user by application
Residing geographical location and current time determines the list information of the application to be recommended to user.To be directed to each user
The feature of itself, and according to current time and position, specify out using recommendation list, it is emerging to meet its for the accurate recommendation of user
Interest, and the application of its current location, temporal information is taken into account, meet different user in different time, different location for application
Individual demand.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer read/write memory medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned includes:ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that:It still may be used
With technical scheme described in the above embodiments is modified or equivalent replacement of some of the technical features;
And these modifications or replacements, various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (8)
1. method is recommended in a kind of application, which is characterized in that including:
Using the application data for recommending business platform to acquire acquisition user from carrier server;
The application recommends business platform to carry out data mining analysis to the application data, obtains the feature letter of the user
Breath;
The application recommends business platform according to the characteristic information, determines the list letter of the application to be recommended to the user
Breath, and the list information of the application is sent to the user;
Wherein, the application recommends business platform to acquire the application data for obtaining user from carrier server, including:
The application recommends business platform to acquire the access service corresponding with each application for obtaining user from carrier server
Type accesses duration, visitation frequency and flowing of access;
Correspondingly, the application recommends business platform to carry out data mining analysis to the application data, obtain the user's
Hobby feature, including:
The application recommends business platform according to the access duration S corresponding with each applicationi, visitation frequency FiAnd flowing of access
Mi, determine the score A of each applicationi=Q1Si/STotal i+Q2Fi/FTotal i+Q3Mi/MTotal i, wherein Q1、Q2And Q3For the different first default power
Weight values, STotal i、FTotal iAnd MTotal iThe respectively described user accesses the access total duration of each application, accesses total frequency and accesses total flow, i
∈ [1, N], i are positive integer, and N is positive integer;
The application recommends business platform according to the score A of each applicationi, and access service type corresponding with each application, it determines
Belong to each interest index of the application of same access service typeWherein, [1, B] b ∈, b are positive integer, B
For positive integer;
The application recommends business platform according to each interest index Ib, and the scoring respectively applied that obtains in advance, it determines each
Recommend indices P in the basis of applicationi;
The application recommends business platform to determine each each phase for applying the application in the mobile terminal currently used with the user
Like degree Sij, wherein j ∈ [1, J], j are positive integer, and J is positive integer;
The application recommends business platform according to each similarity Sij, indices P is recommended on the basis for adjusting each applicationi'={ 1-
(Si1-SThreshold value)}PiQ1'+…+{1-(Sij-SThreshold value)}PiQi'+…+{1-(SiJ-SThreshold value)}PiQ'N, wherein SThreshold valueTo preset similarity
Threshold value, Qi' it is the second default weighted value;
The application recommends business platform to recommend index according to the basis after adjustment, is ranked up to each application, obtains interest and push away
List is recommended, the interest recommendation list is used to characterize the hobby feature of the user.
2. according to the method described in claim 1, it is characterized in that, the application recommend business platform to the application data into
Row data mining analysis obtains the characteristic information of the user, including:
The application recommends business platform to carry out data mining analysis to the application data, obtains the hobby of the user
Feature and/or crowd's attributive character;
Correspondingly, the application recommends business platform according to the characteristic information, the application to be recommended to the user is determined
List information, including:
The application recommends business platform according to the hobby feature and/or crowd's attributive character, determines to be recommended to institute
State the list information of the application of user.
3. according to the method described in claim 2, it is characterized in that, the application recommends business platform from carrier server
Acquisition obtains the application data of user, including:
The application recommends business platform since acquisition on carrier server obtains the access corresponding with each application of user
Time accesses the end time, accesses base station;
Correspondingly, the application recommends business platform to carry out data mining analysis to the application data, obtain the user's
Crowd's attributive character, including:
The application recommends business platform according to the access time started corresponding with each application, accesses the end time, determines
The daily surf time ratio of the user;
The application recommends business platform according to the access base station corresponding with each application, determines the daily movement of the user
Track;
The application recommends business platform according to the daily surf time ratio of the user and daily movement locus, really
Crowd's attributive character of the fixed user.
4. according to the method in claim 2 or 3, which is characterized in that the application recommends business platform according to the feature
Information determines the list information of the application to be recommended to the user, including:
The application recommend the geographical location that business platform is presently according to the characteristic information, the user and it is current when
Between, determine the list information of the application to be recommended to the user;
The list information by the application is sent to the user, including:The application recommends business platform receiving
After the recommendation request that user sends, the list information of the application is sent to the user;
Alternatively, after user logs in application recommendation business platform, the application recommends business platform to believe the list of the application
Breath is sent to the user;
Alternatively, the application recommends business platform within the preset period, the list information of the application is sent to described
User.
5. business platform is recommended in a kind of application, which is characterized in that including:
Data acquisition module, the application data for the acquisition acquisition user from carrier server;
Data-mining module obtains the characteristic information of the user for carrying out data mining analysis to the application data;
Using recommending module, for according to the characteristic information, determining the list information of the application to be recommended to the user, and
The list information of the application is sent to the user;
Wherein, the data acquisition module, is specifically used for:
Acquisition obtains the access service type corresponding with each application of user, accesses duration, accesses frequency from carrier server
Secondary and flowing of access;
Correspondingly, the data mining submodule obtains the use for carrying out data mining analysis to the application data
When the hobby feature at family, it is specifically used for:
According to the access duration S corresponding with each applicationi, visitation frequency FiWith flowing of access Mi, determine the score A of each applicationi
=Q1Si/STotal i+Q2Fi/FTotal i+Q3Mi/MTotal i, wherein Q1、Q2And Q3For the first different default weighted values, STotal i、FTotal iAnd MTotal iRespectively
The access total duration of each application is accessed, total frequency is accessed and accesses total flow for the user, i ∈ [1, N], i are positive integer, N
For positive integer;
According to the score A of each applicationi, and access service type corresponding with each application, it is determining to belong to same access service type
Application each interest indexWherein, [1, B] b ∈, b are positive integer, and B is positive integer;
According to each interest index Ib, and the scoring respectively applied that obtains in advance, determine that index is recommended on the basis of each application
Pi;
Determine each similarity S of the application in each application mobile terminal currently used with the userij, wherein j ∈ [1, J],
J is positive integer, and J is positive integer;
According to each similarity Sij, indices P is recommended on the basis for adjusting each applicationi'={ 1- (Si1-SThreshold value)}PiQ1'+…+{1-
(Sij-SThreshold value)}PiQi'+…+{1-(SiJ-SThreshold value)}PiQ'N, wherein SThreshold valueTo preset similarity threshold, Qi' it is the second default weight
Value;
Recommend index according to the basis after adjustment, each application is ranked up, obtain interest recommendation list, the interest recommends row
Table is used to characterize the hobby feature of the user.
6. business platform is recommended in application according to claim 5, which is characterized in that the data-mining module, including:
Data mining submodule obtains the hobby of the user for carrying out data mining analysis to the application data
Feature and/or crowd's attributive character;
Correspondingly, it is described using recommending module, including:
Using determination sub-module, for according to the hobby feature and/or crowd's attributive character, determining to be recommended to described
The list information of the application of user;
Using sending submodule, for the list information of the application to be sent to the user.
7. business platform is recommended in application according to claim 6, which is characterized in that the data acquisition module, it is specific to use
In:
Acquisition obtains the access time started corresponding with each application of user, accesses the end time, visits from carrier server
Ask base station;
Correspondingly, the data mining submodule obtains the use for carrying out data mining analysis to the application data
When crowd's attributive character at family, it is specifically used for:
According to the access time started corresponding with each application, the end time is accessed, when determining the daily online of the user
Between ratio;
According to the access base station corresponding with each application, the daily movement locus of the user is determined;
According to the daily surf time ratio of the user and daily movement locus, crowd's attribute of the user is determined
Feature.
8. business platform is recommended in the application described according to claim 6 or 7, which is characterized in that described to apply determination sub-module, tool
Body is used for:
The geographical location being presently according to the characteristic information, the user and current time determine to be recommended to described
The list information of the application of user;
It is described to apply sending submodule, it is specifically used for:After the recommendation request for receiving user's transmission, by the row of the application
Table information is sent to the user;
Alternatively, after user logs in application recommendation business platform, the list information of the application is sent to the user;
Alternatively, within the preset period, the list information of the application is sent to the user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510697893.4A CN105227445B (en) | 2015-10-23 | 2015-10-23 | Recommend platform using methods and applications are recommended |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510697893.4A CN105227445B (en) | 2015-10-23 | 2015-10-23 | Recommend platform using methods and applications are recommended |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105227445A CN105227445A (en) | 2016-01-06 |
CN105227445B true CN105227445B (en) | 2018-09-14 |
Family
ID=54996149
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510697893.4A Active CN105227445B (en) | 2015-10-23 | 2015-10-23 | Recommend platform using methods and applications are recommended |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105227445B (en) |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105744305A (en) * | 2016-02-05 | 2016-07-06 | 尼尔森网联媒介数据服务有限公司 | Monitoring methods and monitoring apparatuses for watching users of digital media terminal |
CN105808743B (en) * | 2016-03-11 | 2019-04-30 | 中国联合网络通信集团有限公司 | Terminal recommended method and terminal recommender system |
CN106101170A (en) * | 2016-05-20 | 2016-11-09 | 努比亚技术有限公司 | A kind of recommendation method and device of application |
CN107517190B (en) * | 2016-06-17 | 2020-06-12 | 中国移动通信集团上海有限公司 | Service recommendation method and device |
CN107688951B (en) * | 2016-08-03 | 2022-03-29 | 美的智慧家居科技有限公司 | Information pushing method and device |
CN107220269B (en) * | 2016-09-12 | 2020-10-30 | 中山大学 | Personalized recommendation method for geographic position sensitive app |
CN106775849A (en) * | 2016-12-02 | 2017-05-31 | 广东欧珀移动通信有限公司 | Application message treatment, the method using installing, device and computer equipment |
CN106844240A (en) * | 2017-01-25 | 2017-06-13 | 百度在线网络技术(北京)有限公司 | Information displaying method and device |
CN107087017B (en) | 2017-03-09 | 2020-02-21 | 阿里巴巴集团控股有限公司 | Method and device for service drainage |
CN107612974B (en) * | 2017-08-23 | 2020-04-17 | Oppo广东移动通信有限公司 | Information recommendation method and device, mobile terminal and storage medium |
CN107493339A (en) * | 2017-08-23 | 2017-12-19 | 广东欧珀移动通信有限公司 | Information-pushing method, device, terminal and computer-readable recording medium |
CN110771121A (en) * | 2017-08-31 | 2020-02-07 | 深圳市欢太科技有限公司 | Application resource recommendation method and related equipment |
CN109660574B (en) * | 2017-10-10 | 2022-03-04 | 阿里巴巴集团控股有限公司 | Data providing method and device |
CN107705156B (en) * | 2017-10-16 | 2021-02-05 | 深圳大宇无限科技有限公司 | User feature analysis method and device |
CN109714378A (en) * | 2017-10-26 | 2019-05-03 | 中国电信股份有限公司 | The recommended method and system of application program |
CN107958056A (en) * | 2017-11-29 | 2018-04-24 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus and mobile terminal |
CN108153891A (en) * | 2017-12-29 | 2018-06-12 | 北京奇虎科技有限公司 | Active time statistical method of surfing the Internet and device |
CN108804167B (en) * | 2018-06-12 | 2022-02-22 | 北京智明星通科技股份有限公司 | Method, device and server for identifying player of pupil |
CN109242252B (en) * | 2018-08-03 | 2020-09-04 | 张继升 | Intelligent service platform and method |
CN110827044A (en) * | 2018-08-07 | 2020-02-21 | 北京京东尚科信息技术有限公司 | Method and device for extracting user interest mode |
CN109190047A (en) * | 2018-09-20 | 2019-01-11 | 北京奇元科技有限公司 | A kind of application recommended method, device |
CN109300218A (en) * | 2018-10-18 | 2019-02-01 | 南京奥拓电子科技有限公司 | A kind of queuing machine management system and method for the auto arrangement number of taking work flow |
CN109859006A (en) * | 2019-01-15 | 2019-06-07 | 上海连尚网络科技有限公司 | For determining method, system, electronic equipment and the computer-readable medium of user interest profile |
CN113327151A (en) * | 2021-06-03 | 2021-08-31 | 广州华多网络科技有限公司 | Commodity object recommendation method and device, computer equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7543051B2 (en) * | 2003-05-30 | 2009-06-02 | Borland Software Corporation | Method of non-intrusive analysis of secure and non-secure web application traffic in real-time |
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
CN102999588A (en) * | 2012-11-15 | 2013-03-27 | 广州华多网络科技有限公司 | Method and system for recommending multimedia applications |
CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
CN104601659A (en) * | 2014-12-17 | 2015-05-06 | 深圳市腾讯计算机系统有限公司 | Application recommendation method and system |
-
2015
- 2015-10-23 CN CN201510697893.4A patent/CN105227445B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7543051B2 (en) * | 2003-05-30 | 2009-06-02 | Borland Software Corporation | Method of non-intrusive analysis of secure and non-secure web application traffic in real-time |
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
CN102999588A (en) * | 2012-11-15 | 2013-03-27 | 广州华多网络科技有限公司 | Method and system for recommending multimedia applications |
CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
CN104601659A (en) * | 2014-12-17 | 2015-05-06 | 深圳市腾讯计算机系统有限公司 | Application recommendation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN105227445A (en) | 2016-01-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105227445B (en) | Recommend platform using methods and applications are recommended | |
US10275530B2 (en) | System and method for communal search | |
Courtois et al. | Gratifications and seeding behavior of online adolescents | |
EP2820616B1 (en) | Empirical expert determination and question routing system and method | |
CN107424043A (en) | A kind of Products Show method and device, electronic equipment | |
CN112104642B (en) | Abnormal account number determination method and related device | |
Gonçalves et al. | Social phenomena: From data analysis to models | |
CN106846053A (en) | A kind of recommendation method and device of the page advertisement that is polymerized | |
CN109033180A (en) | A kind of information-pushing method, device, computer installation and computer readable storage medium | |
CN104145264A (en) | Systems and methods for sentiment detection, measurement, and normalization over social networks | |
De Sabbata et al. | Criteria of geographic relevance: an experimental study | |
Mizzaro et al. | A social approach to context-aware retrieval | |
Vickey et al. | Twitter classification model: the ABC of two million fitness tweets | |
Horrigan | What are the consequences of being disconnected in a broadband-connected world? | |
Mordacchini et al. | Crowdsourcing through cognitive opportunistic networks | |
Ectors et al. | Developing an optimised activity type annotation method based on classification accuracy and entropy indices | |
US20140101267A1 (en) | Selecting user accounts in social network to answer question | |
US20080177794A1 (en) | Street quality assessment method and system | |
CN110196951A (en) | User matching method and equipment | |
Muruli et al. | Marketing of library services and products through social media: An evaluation | |
Araujo-Batlle et al. | Selfies versus conservation: The influence of user-generated content in the image of protected natural spaces | |
Zaglago | The adoption of digital marketing among SMEs in Ghana: Increasing profitability and bridging the digital divide using social media | |
KR101861828B1 (en) | Method of providing personalized content and computer program for the same | |
Mich | Towards a Web 2.0 presence model for tourism destination management Organizations | |
CN105791334A (en) | Multimedia data processing method and device |
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 |